diff options
| author |   José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-11 10:41:07 +0300 |
|---|---|---|
| committer | José Pekkarinen <jose.pekkarinen@nokia.com> | 2016-04-13 08:17:18 +0300 |
| commit | e09b41010ba33a20a87472ee821fa407a5b8da36 (patch) | |
| tree | d10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/arch/x86 | |
| parent | f93b97fd65072de626c074dbe099a1fff05ce060 (diff) | |
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page.
During the rebasing, the following patch collided:
Force tick interrupt and get rid of softirq magic(I70131fb85).
Collisions have been removed because its logic was found on the
source already.
Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/arch/x86')
550 files changed, 32238 insertions, 18876 deletions
diff --git a/kernel/arch/x86/Kbuild b/kernel/arch/x86/Kbuild index 3942f74c9..1538562cc 100644 --- a/kernel/arch/x86/Kbuild +++ b/kernel/arch/x86/Kbuild @@ -1,3 +1,6 @@ + +obj-y += entry/ + obj-$(CONFIG_KVM) += kvm/ # Xen paravirtualization support @@ -11,7 +14,7 @@ obj-y += kernel/ obj-y += mm/ obj-y += crypto/ -obj-y += vdso/ + obj-$(CONFIG_IA32_EMULATION) += ia32/ obj-y += platform/ diff --git a/kernel/arch/x86/Kconfig b/kernel/arch/x86/Kconfig index aac357a4c..d8a1650a0 100644 --- a/kernel/arch/x86/Kconfig +++ b/kernel/arch/x86/Kconfig @@ -9,141 +9,150 @@ config 64BIT config X86_32 def_bool y depends on !64BIT - select CLKSRC_I8253 - select HAVE_UID16 config X86_64 def_bool y depends on 64BIT - select X86_DEV_DMA_OPS - select ARCH_USE_CMPXCHG_LOCKREF - select HAVE_LIVEPATCH ### Arch settings config X86 def_bool y select HAVE_PREEMPT_LAZY - select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI - select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI + select ACPI_LEGACY_TABLES_LOOKUP if ACPI + select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ANON_INODES + select ARCH_CLOCKSOURCE_DATA + select ARCH_DISCARD_MEMBLOCK + select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_PMEM_API if X86_64 + select ARCH_HAS_MMIO_FLUSH + select ARCH_HAS_SG_CHAIN + select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO - select HAVE_AOUT if X86_32 - select HAVE_UNSTABLE_SCHED_CLOCK - select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 - select ARCH_SUPPORTS_INT128 if X86_64 - select HAVE_IDE - select HAVE_OPROFILE - select HAVE_PCSPKR_PLATFORM - select HAVE_PERF_EVENTS - select HAVE_IOREMAP_PROT - select HAVE_KPROBES - select HAVE_MEMBLOCK - select HAVE_MEMBLOCK_NODE_MAP - select ARCH_DISCARD_MEMBLOCK - select ARCH_WANT_OPTIONAL_GPIOLIB + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT + select ARCH_SUPPORTS_INT128 if X86_64 + select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 + select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_CMPXCHG_LOCKREF if X86_64 + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_QUEUED_SPINLOCKS + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP + select ARCH_WANTS_DYNAMIC_TASK_STRUCT select ARCH_WANT_FRAME_POINTERS - select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS - select HAVE_KRETPROBES + select ARCH_WANT_IPC_PARSE_VERSION if X86_32 + select ARCH_WANT_OPTIONAL_GPIOLIB + select BUILDTIME_EXTABLE_SORT + select CLKEVT_I8253 + select CLKSRC_I8253 if X86_32 + select CLOCKSOURCE_VALIDATE_LAST_CYCLE + select CLOCKSOURCE_WATCHDOG + select CLONE_BACKWARDS if X86_32 + select COMPAT_OLD_SIGACTION if IA32_EMULATION + select DCACHE_WORD_ACCESS + select EDAC_ATOMIC_SCRUB + select EDAC_SUPPORT + select GENERIC_CLOCKEVENTS + select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) + select GENERIC_CLOCKEVENTS_MIN_ADJUST + select GENERIC_CMOS_UPDATE + select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP - select HAVE_OPTPROBES - select HAVE_KPROBES_ON_FTRACE - select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FENTRY if X86_64 + select GENERIC_FIND_FIRST_BIT + select GENERIC_IOMAP + select GENERIC_IRQ_PROBE + select GENERIC_IRQ_SHOW + select GENERIC_PENDING_IRQ if SMP + select GENERIC_SMP_IDLE_THREAD + select GENERIC_STRNCPY_FROM_USER + select GENERIC_STRNLEN_USER + select GENERIC_TIME_VSYSCALL + select HAVE_ACPI_APEI if ACPI + select HAVE_ACPI_APEI_NMI if ACPI + select HAVE_ALIGNED_STRUCT_PAGE if SLUB + select HAVE_AOUT if X86_32 + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE + select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_ARCH_KGDB + select HAVE_ARCH_KMEMCHECK + select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_SOFT_DIRTY if X86_64 + select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_BPF_JIT if X86_64 + select HAVE_CC_STACKPROTECTOR + select HAVE_CMPXCHG_DOUBLE + select HAVE_CMPXCHG_LOCAL + select HAVE_CONTEXT_TRACKING if X86_64 + select HAVE_COPY_THREAD_TLS select HAVE_C_RECORDMCOUNT + select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_STACKOVERFLOW + select HAVE_DMA_API_DEBUG + select HAVE_DMA_ATTRS + select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_FUNCTION_TRACER - select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_FP_TEST - select HAVE_SYSCALL_TRACEPOINTS - select SYSCTL_EXCEPTION_TRACE - select HAVE_KVM - select HAVE_ARCH_KGDB - select HAVE_ARCH_TRACEHOOK - select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS - select USER_STACKTRACE_SUPPORT - select HAVE_REGS_AND_STACK_ACCESS_API - select HAVE_DMA_API_DEBUG - select HAVE_KERNEL_GZIP + select HAVE_FENTRY if X86_64 + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_GRAPH_FP_TEST + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER + select HAVE_GENERIC_DMA_COHERENT if X86_32 + select HAVE_HW_BREAKPOINT + select HAVE_IDE + select HAVE_IOREMAP_PROT + select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_BZIP2 + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZ4 select HAVE_KERNEL_LZMA - select HAVE_KERNEL_XZ select HAVE_KERNEL_LZO - select HAVE_KERNEL_LZ4 - select HAVE_HW_BREAKPOINT + select HAVE_KERNEL_XZ + select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE + select HAVE_KRETPROBES + select HAVE_KVM + select HAVE_LIVEPATCH if X86_64 + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP select HAVE_MIXED_BREAKPOINTS_REGS - select PERF_EVENTS + select HAVE_OPROFILE + select HAVE_OPTPROBES + select HAVE_PCSPKR_PLATFORM + select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_DEBUG_KMEMLEAK - select ANON_INODES - select HAVE_ALIGNED_STRUCT_PAGE if SLUB - select HAVE_CMPXCHG_LOCAL - select HAVE_CMPXCHG_DOUBLE - select HAVE_ARCH_KMEMCHECK - select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_SYSCALL_TRACEPOINTS + select HAVE_UID16 if X86_32 || IA32_EMULATION + select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER - select ARCH_HAS_ELF_RANDOMIZE - select HAVE_ARCH_JUMP_LABEL - select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select SPARSE_IRQ - select GENERIC_FIND_FIRST_BIT - select GENERIC_IRQ_PROBE - select GENERIC_PENDING_IRQ if SMP - select GENERIC_IRQ_SHOW - select GENERIC_CLOCKEVENTS_MIN_ADJUST select IRQ_FORCED_THREADING - select HAVE_BPF_JIT if X86_64 - select HAVE_ARCH_TRANSPARENT_HUGEPAGE - select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE) - select ARCH_HAS_SG_CHAIN - select CLKEVT_I8253 - select ARCH_HAVE_NMI_SAFE_CMPXCHG - select GENERIC_IOMAP - select DCACHE_WORD_ACCESS - select GENERIC_SMP_IDLE_THREAD - select ARCH_WANT_IPC_PARSE_VERSION if X86_32 - select HAVE_ARCH_SECCOMP_FILTER - select BUILDTIME_EXTABLE_SORT - select GENERIC_CMOS_UPDATE - select HAVE_ARCH_SOFT_DIRTY if X86_64 - select CLOCKSOURCE_WATCHDOG - select GENERIC_CLOCKEVENTS - select ARCH_CLOCKSOURCE_DATA - select CLOCKSOURCE_VALIDATE_LAST_CYCLE - select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) - select GENERIC_TIME_VSYSCALL - select GENERIC_STRNCPY_FROM_USER - select GENERIC_STRNLEN_USER - select HAVE_CONTEXT_TRACKING if X86_64 - select HAVE_IRQ_TIME_ACCOUNTING - select VIRT_TO_BUS - select MODULES_USE_ELF_REL if X86_32 - select MODULES_USE_ELF_RELA if X86_64 - select CLONE_BACKWARDS if X86_32 - select ARCH_USE_BUILTIN_BSWAP - select ARCH_USE_QUEUE_RWLOCK - select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION - select OLD_SIGACTION if X86_32 - select COMPAT_OLD_SIGACTION if IA32_EMULATION + select MODULES_USE_ELF_RELA if X86_64 + select MODULES_USE_ELF_REL if X86_32 + select OLD_SIGACTION if X86_32 + select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION + select PERF_EVENTS select RTC_LIB - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 - select HAVE_CC_STACKPROTECTOR - select GENERIC_CPU_AUTOPROBE - select HAVE_ARCH_AUDITSYSCALL - select ARCH_SUPPORTS_ATOMIC_RMW - select HAVE_ACPI_APEI if ACPI - select HAVE_ACPI_APEI_NMI if ACPI - select ACPI_LEGACY_TABLES_LOOKUP if ACPI - select X86_FEATURE_NAMES if PROC_FS + select SPARSE_IRQ select SRCU + select SYSCTL_EXCEPTION_TRACE + select USER_STACKTRACE_SUPPORT + select VIRT_TO_BUS + select X86_DEV_DMA_OPS if X86_64 + select X86_FEATURE_NAMES if PROC_FS config INSTRUCTION_DECODER def_bool y @@ -252,6 +261,11 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y +config KASAN_SHADOW_OFFSET + hex + depends on KASAN + default 0xdffffc0000000000 + config HAVE_INTEL_TXT def_bool y depends on INTEL_IOMMU && ACPI @@ -264,10 +278,6 @@ config X86_64_SMP def_bool y depends on X86_64 && SMP -config X86_HT - def_bool y - depends on SMP - config X86_32_LAZY_GS def_bool y depends on X86_32 && !CC_STACKPROTECTOR @@ -345,7 +355,7 @@ config X86_FEATURE_NAMES config X86_X2APIC bool "Support x2apic" - depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP + depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) ---help--- This enables x2apic support on CPUs that have this feature. @@ -445,6 +455,7 @@ config X86_UV depends on X86_EXTENDED_PLATFORM depends on NUMA depends on X86_X2APIC + depends on PCI ---help--- This option is needed in order to support SGI Ultraviolet systems. If you don't have one of these, you should say N here. @@ -470,7 +481,6 @@ config X86_INTEL_CE select X86_REBOOTFIXUPS select OF select OF_EARLY_FLATTREE - select IRQ_DOMAIN ---help--- Select for the Intel CE media processor (CE4100) SOC. This option compiles in support for the CE4100 SOC for settop @@ -670,7 +680,7 @@ config PARAVIRT_DEBUG config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP - select UNINLINE_SPIN_UNLOCK + select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS ---help--- Paravirtualized spinlocks allow a pvops backend to replace the spinlock implementation with something virtualization-friendly @@ -855,11 +865,12 @@ config NR_CPUS default "1" if !SMP default "8192" if MAXSMP default "32" if SMP && X86_BIGSMP - default "8" if SMP + default "8" if SMP && X86_32 + default "64" if SMP ---help--- This allows you to specify the maximum number of CPUs which this kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum - supported value is 4096, otherwise the maximum value is 512. The + supported value is 8192, otherwise the maximum value is 512. The minimum value which makes sense is 2. This is purely to save memory - each supported CPU adds @@ -867,7 +878,7 @@ config NR_CPUS config SCHED_SMT bool "SMT (Hyperthreading) scheduler support" - depends on X86_HT + depends on SMP ---help--- SMT scheduler support improves the CPU scheduler's decision making when dealing with Intel Pentium 4 chips with HyperThreading at a @@ -877,7 +888,7 @@ config SCHED_SMT config SCHED_MC def_bool y prompt "Multi-core scheduler support" - depends on X86_HT + depends on SMP ---help--- Multi-core scheduler support improves the CPU scheduler's decision making when dealing with multi-core CPU chips at a cost of slightly @@ -918,12 +929,12 @@ config X86_UP_IOAPIC config X86_LOCAL_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI - select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ + select IRQ_DOMAIN_HIERARCHY + select PCI_MSI_IRQ_DOMAIN if PCI_MSI config X86_IO_APIC def_bool y depends on X86_LOCAL_APIC || X86_UP_IOAPIC - select IRQ_DOMAIN config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" @@ -950,6 +961,7 @@ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS config X86_MCE bool "Machine Check / overheating reporting" + select GENERIC_ALLOCATOR default y ---help--- Machine Check support allows the processor to notify the @@ -997,19 +1009,42 @@ config X86_THERMAL_VECTOR def_bool y depends on X86_MCE_INTEL -config VM86 - bool "Enable VM86 support" if EXPERT - default y +config X86_LEGACY_VM86 + bool "Legacy VM86 support" + default n depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run - 16-bit real mode legacy code on x86 processors. It also may - be needed by software like XFree86 to initialize some video - cards via BIOS. Disabling this option saves about 6K. + This option allows user programs to put the CPU into V8086 + mode, which is an 80286-era approximation of 16-bit real mode. + + Some very old versions of X and/or vbetool require this option + for user mode setting. Similarly, DOSEMU will use it if + available to accelerate real mode DOS programs. However, any + recent version of DOSEMU, X, or vbetool should be fully + functional even without kernel VM86 support, as they will all + fall back to software emulation. Nevertheless, if you are using + a 16-bit DOS program where 16-bit performance matters, vm86 + mode might be faster than emulation and you might want to + enable this option. + + Note that any app that works on a 64-bit kernel is unlikely to + need this option, as 64-bit kernels don't, and can't, support + V8086 mode. This option is also unrelated to 16-bit protected + mode and is not needed to run most 16-bit programs under Wine. + + Enabling this option increases the complexity of the kernel + and slows down exception handling a tiny bit. + + If unsure, say N here. + +config VM86 + bool + default X86_LEGACY_VM86 config X86_16BIT bool "Enable support for 16-bit segments" if EXPERT default y + depends on MODIFY_LDT_SYSCALL ---help--- This option is required by programs like Wine to run 16-bit protected mode legacy code on x86 processors. Disabling @@ -1059,24 +1094,19 @@ config TOSHIBA Say N otherwise. config I8K - tristate "Dell laptop support" + tristate "Dell i8k legacy laptop support" select HWMON + select SENSORS_DELL_SMM ---help--- - This adds a driver to safely access the System Management Mode - of the CPU on the Dell Inspiron 8000. The System Management Mode - is used to read cpu temperature and cooling fan status and to - control the fans on the I8K portables. - - This driver has been tested only on the Inspiron 8000 but it may - also work with other Dell laptops. You can force loading on other - models by passing the parameter `force=1' to the module. Use at - your own risk. - - For information on utilities to make use of this driver see the - I8K Linux utilities web site at: - <http://people.debian.org/~dz/i8k/> + This option enables legacy /proc/i8k userspace interface in hwmon + dell-smm-hwmon driver. Character file /proc/i8k reports bios version, + temperature and allows controlling fan speeds of Dell laptops via + System Management Mode. For old Dell laptops (like Dell Inspiron 8000) + it reports also power and hotkey status. For fan speed control is + needed userspace package i8kutils. - Say Y if you intend to run this kernel on a Dell Inspiron 8000. + Say Y if you intend to run this kernel on old Dell laptops or want to + use userspace package i8kutils. Say N otherwise. config X86_REBOOTFIXUPS @@ -1097,8 +1127,10 @@ config X86_REBOOTFIXUPS Say N otherwise. config MICROCODE - tristate "CPU microcode loading support" + bool "CPU microcode loading support" + default y depends on CPU_SUP_AMD || CPU_SUP_INTEL + depends on BLK_DEV_INITRD select FW_LOADER ---help--- @@ -1140,24 +1172,6 @@ config MICROCODE_OLD_INTERFACE def_bool y depends on MICROCODE -config MICROCODE_INTEL_EARLY - bool - -config MICROCODE_AMD_EARLY - bool - -config MICROCODE_EARLY - bool "Early load microcode" - depends on MICROCODE=y && BLK_DEV_INITRD - select MICROCODE_INTEL_EARLY if MICROCODE_INTEL - select MICROCODE_AMD_EARLY if MICROCODE_AMD - default y - help - This option provides functionality to read additional microcode data - at the beginning of initrd image. The data tells kernel to load - microcode to CPU's as early as possible. No functional change if no - microcode data is glued to the initrd, therefore it's safe to say Y. - config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" ---help--- @@ -1282,6 +1296,7 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" depends on X86_32 && !HIGHMEM4G + select SWIOTLB ---help--- PAE is required for NX support, and furthermore enables larger swapspace support for non-overcommit purposes. It @@ -1426,8 +1441,15 @@ config ILLEGAL_POINTER_VALUE source "mm/Kconfig" +config X86_PMEM_LEGACY_DEVICE + bool + config X86_PMEM_LEGACY - bool "Support non-standard NVDIMMs and ADR protected memory" + tristate "Support non-standard NVDIMMs and ADR protected memory" + depends on PHYS_ADDR_T_64BIT + depends on BLK_DEV + select X86_PMEM_LEGACY_DEVICE + select LIBNVDIMM help Treat memory marked using the non-standard e820 type of 12 as used by the Intel Sandy Bridge-EP reference BIOS as protected memory. @@ -1506,6 +1528,7 @@ config X86_RESERVE_LOW config MATH_EMULATION bool + depends on MODIFY_LDT_SYSCALL prompt "Math emulation" if X86_32 ---help--- Linux can emulate a math coprocessor (used for floating point @@ -1721,6 +1744,7 @@ source kernel/Kconfig.hz config KEXEC bool "kexec system call" + select KEXEC_CORE ---help--- kexec is a system call that implements the ability to shutdown your current kernel, and to start another kernel. It is like a reboot @@ -1737,8 +1761,8 @@ config KEXEC config KEXEC_FILE bool "kexec file based system call" + select KEXEC_CORE select BUILD_BIN2C - depends on KEXEC depends on X86_64 depends on CRYPTO=y depends on CRYPTO_SHA256=y @@ -2007,6 +2031,55 @@ config COMPAT_VDSO If unsure, say N: if you are compiling your own kernel, you are unlikely to be using a buggy version of glibc. +choice + prompt "vsyscall table for legacy applications" + depends on X86_64 + default LEGACY_VSYSCALL_EMULATE + help + Legacy user code that does not know how to find the vDSO expects + to be able to issue three syscalls by calling fixed addresses in + kernel space. Since this location is not randomized with ASLR, + it can be used to assist security vulnerability exploitation. + + This setting can be changed at boot time via the kernel command + line parameter vsyscall=[native|emulate|none]. + + On a system with recent enough glibc (2.14 or newer) and no + static binaries, you can say None without a performance penalty + to improve security. + + If unsure, select "Emulate". + + config LEGACY_VSYSCALL_NATIVE + bool "Native" + help + Actual executable code is located in the fixed vsyscall + address mapping, implementing time() efficiently. Since + this makes the mapping executable, it can be used during + security vulnerability exploitation (traditionally as + ROP gadgets). This configuration is not recommended. + + config LEGACY_VSYSCALL_EMULATE + bool "Emulate" + help + The kernel traps and emulates calls into the fixed + vsyscall address mapping. This makes the mapping + non-executable, but it still contains known contents, + which could be used in certain rare security vulnerability + exploits. This configuration is recommended when userspace + still uses the vsyscall area. + + config LEGACY_VSYSCALL_NONE + bool "None" + help + There will be no vsyscall mapping at all. This will + eliminate any risk of ASLR bypass due to the vsyscall + fixed address mapping. Attempts to use the vsyscalls + will be reported to dmesg, so that either old or + malicious userspace programs can be identified. + +endchoice + config CMDLINE_BOOL bool "Built-in kernel command line" ---help--- @@ -2018,7 +2091,7 @@ config CMDLINE_BOOL To compile command line arguments into the kernel, set this option to 'Y', then fill in the - the boot arguments in CONFIG_CMDLINE. + boot arguments in CONFIG_CMDLINE. Systems with fully functional boot loaders (i.e. non-embedded) should leave this option set to 'N'. @@ -2050,6 +2123,22 @@ config CMDLINE_OVERRIDE This is used to work around broken boot loaders. This should be set to 'N' under normal conditions. +config MODIFY_LDT_SYSCALL + bool "Enable the LDT (local descriptor table)" if EXPERT + default y + ---help--- + Linux can allow user programs to install a per-process x86 + Local Descriptor Table (LDT) using the modify_ldt(2) system + call. This is required to run 16-bit or segmented code such as + DOSEMU or some Wine programs. It is also used by some very old + threading libraries. + + Enabling this feature adds a small amount of overhead to + context switches and increases the low-level kernel attack + surface. Disabling it removes the modify_ldt(2) system call. + + Saying 'N' here may make sense for embedded or server kernels. + source "kernel/livepatch/Kconfig" endmenu @@ -2519,7 +2608,7 @@ config IA32_EMULATION depends on X86_64 select BINFMT_ELF select COMPAT_BINFMT_ELF - select HAVE_UID16 + select ARCH_WANT_OLD_COMPAT_IPC ---help--- Include code to run legacy 32-bit programs under a 64-bit kernel. You should likely turn this on, unless you're @@ -2533,7 +2622,7 @@ config IA32_AOUT config X86_X32 bool "x32 ABI for 64-bit mode" - depends on X86_64 && IA32_EMULATION + depends on X86_64 ---help--- Include code to run binaries for the x32 native 32-bit ABI for 64-bit processors. An x32 process gets access to the @@ -2547,7 +2636,6 @@ config X86_X32 config COMPAT def_bool y depends on IA32_EMULATION || X86_X32 - select ARCH_WANT_OLD_COMPAT_IPC if COMPAT config COMPAT_FOR_U64_ALIGNMENT diff --git a/kernel/arch/x86/Kconfig.cpu b/kernel/arch/x86/Kconfig.cpu index 6983314c8..3ba5ff2f2 100644 --- a/kernel/arch/x86/Kconfig.cpu +++ b/kernel/arch/x86/Kconfig.cpu @@ -3,10 +3,6 @@ choice prompt "Processor family" default M686 if X86_32 default GENERIC_CPU if X86_64 - -config M486 - bool "486" - depends on X86_32 ---help--- This is the processor type of your CPU. This information is used for optimizing purposes. In order to compile a kernel @@ -23,9 +19,9 @@ config M486 Here are the settings recommended for greatest speed: - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or - SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. + SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. - "586" for generic Pentium CPUs lacking the TSC - (time stamp counter) register. + (time stamp counter) register. - "Pentium-Classic" for the Intel Pentium. - "Pentium-MMX" for the Intel Pentium MMX. - "Pentium-Pro" for the Intel Pentium Pro. @@ -34,17 +30,31 @@ config M486 - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron. - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D). - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird). + - "Opteron/Athlon64/Hammer/K8" for all K8 and newer AMD CPUs. - "Crusoe" for the Transmeta Crusoe series. - "Efficeon" for the Transmeta Efficeon series. - "Winchip-C6" for original IDT Winchip. - "Winchip-2" for IDT Winchips with 3dNow! capabilities. + - "AMD Elan" for the 32-bit AMD Elan embedded CPU. - "GeodeGX1" for Geode GX1 (Cyrix MediaGX). - "Geode GX/LX" For AMD Geode GX and LX processors. - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3. - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above). - "VIA C7" for VIA C7. + - "Intel P4" for the Pentium 4/Netburst microarchitecture. + - "Core 2/newer Xeon" for all core2 and newer Intel CPUs. + - "Intel Atom" for the Atom-microarchitecture CPUs. + - "Generic-x86-64" for a kernel which runs on any x86-64 CPU. + + See each option's help text for additional details. If you don't know + what to do, choose "486". - If you don't know what to do, choose "486". +config M486 + bool "486" + depends on X86_32 + ---help--- + Select this for an 486-class CPU such as AMD/Cyrix/IBM/Intel + 486DX/DX2/DX4 or SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. config M586 bool "586/K5/5x86/6x86/6x86MX" diff --git a/kernel/arch/x86/Kconfig.debug b/kernel/arch/x86/Kconfig.debug index 72484a645..137dfa96a 100644 --- a/kernel/arch/x86/Kconfig.debug +++ b/kernel/arch/x86/Kconfig.debug @@ -65,10 +65,14 @@ config EARLY_PRINTK_EFI This is useful for kernel debugging when your machine crashes very early before the console code is initialized. +config X86_PTDUMP_CORE + def_bool n + config X86_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL select DEBUG_FS + select X86_PTDUMP_CORE ---help--- Say Y here if you want to show the kernel pagetable layout in a debugfs file. This information is only useful for kernel developers @@ -79,7 +83,8 @@ config X86_PTDUMP config EFI_PGT_DUMP bool "Dump the EFI pagetable" - depends on EFI && X86_PTDUMP + depends on EFI + select X86_PTDUMP_CORE ---help--- Enable this if you want to dump the EFI page table before enabling virtual mode. This can be used to debug miscellaneous @@ -105,6 +110,34 @@ config DEBUG_RODATA_TEST feature as well as for the change_page_attr() infrastructure. If in doubt, say "N" +config DEBUG_WX + bool "Warn on W+X mappings at boot" + depends on DEBUG_RODATA + select X86_PTDUMP_CORE + ---help--- + Generate a warning if any W+X mappings are found at boot. + + This is useful for discovering cases where the kernel is leaving + W+X mappings after applying NX, as such mappings are a security risk. + + Look for a message in dmesg output like this: + + x86/mm: Checked W+X mappings: passed, no W+X pages found. + + or like this, if the check failed: + + x86/mm: Checked W+X mappings: FAILED, <N> W+X pages found. + + Note that even if the check fails, your kernel is possibly + still fine, as W+X mappings are not a security hole in + themselves, what they do is that they make the exploitation + of other unfixed kernel bugs easier. + + There is no runtime or memory usage effect of this option + once the kernel has booted up - it's a one time check. + + If in doubt, say "Y". + config DEBUG_SET_MODULE_RONX bool "Set loadable kernel module data as NX and text as RO" depends on MODULES @@ -297,6 +330,18 @@ config OPTIMIZE_INLINING If unsure, say N. +config DEBUG_ENTRY + bool "Debug low-level entry code" + depends on DEBUG_KERNEL + ---help--- + This option enables sanity checks in x86's low-level entry code. + Some of these sanity checks may slow down kernel entries and + exits or otherwise impact performance. + + This is currently used to help test NMI code. + + If unsure, say N. + config DEBUG_NMI_SELFTEST bool "NMI Selftest" depends on DEBUG_KERNEL && X86_LOCAL_APIC @@ -332,4 +377,27 @@ config X86_DEBUG_STATIC_CPU_HAS If unsure, say N. +config X86_DEBUG_FPU + bool "Debug the x86 FPU code" + depends on DEBUG_KERNEL + default y + ---help--- + If this option is enabled then there will be extra sanity + checks and (boot time) debug printouts added to the kernel. + This debugging adds some small amount of runtime overhead + to the kernel. + + If unsure, say N. + +config PUNIT_ATOM_DEBUG + tristate "ATOM Punit debug driver" + select DEBUG_FS + select IOSF_MBI + ---help--- + This is a debug driver, which gets the power states + of all Punit North Complex devices. The power states of + each device is exposed as part of the debugfs interface. + The current power state can be read from + /sys/kernel/debug/punit_atom/dev_power_state + endmenu diff --git a/kernel/arch/x86/Makefile b/kernel/arch/x86/Makefile index 2fda005bb..4086abca0 100644 --- a/kernel/arch/x86/Makefile +++ b/kernel/arch/x86/Makefile @@ -39,6 +39,16 @@ ifdef CONFIG_X86_NEED_RELOCS LDFLAGS_vmlinux := --emit-relocs endif +# +# Prevent GCC from generating any FP code by mistake. +# +# This must happen before we try the -mpreferred-stack-boundary, see: +# +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 +# +KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow +KBUILD_CFLAGS += $(call cc-option,-mno-avx,) + ifeq ($(CONFIG_X86_32),y) BITS := 32 UTS_MACHINE := i386 @@ -77,6 +87,12 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 + # Align jump targets to 1 byte, not the default 16 bytes: + KBUILD_CFLAGS += -falign-jumps=1 + + # Pack loops tightly as well: + KBUILD_CFLAGS += -falign-loops=1 + # Don't autogenerate traditional x87 instructions KBUILD_CFLAGS += $(call cc-option,-mno-80387) KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) @@ -84,6 +100,9 @@ else # Use -mpreferred-stack-boundary=3 if supported. KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) + # Use -mskip-rax-setup if supported. + KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) + # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) @@ -152,9 +171,11 @@ asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1) asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1) avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1) avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1) +sha1_ni_instr :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA1_NI=1) +sha256_ni_instr :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,-DCONFIG_AS_SHA256_NI=1) -KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) -KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) +KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr) +KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr) $(sha1_ni_instr) $(sha256_ni_instr) LDFLAGS := -m elf_$(UTS_MACHINE) @@ -164,9 +185,6 @@ KBUILD_CFLAGS += -pipe KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -# prevent gcc from generating any FP code by mistake -KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -KBUILD_CFLAGS += $(call cc-option,-mno-avx,) KBUILD_CFLAGS += $(mflags-y) KBUILD_AFLAGS += $(mflags-y) @@ -178,7 +196,7 @@ archscripts: scripts_basic # Syscall table generation archheaders: - $(Q)$(MAKE) $(build)=arch/x86/syscalls all + $(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all archprepare: ifeq ($(CONFIG_KEXEC_FILE),y) @@ -209,6 +227,8 @@ drivers-$(CONFIG_PM) += arch/x86/power/ drivers-$(CONFIG_FB) += arch/x86/video/ +drivers-$(CONFIG_RAS) += arch/x86/ras/ + #### # boot loader support. Several targets are kept for legacy purposes @@ -241,7 +261,7 @@ install: PHONY += vdso_install vdso_install: - $(Q)$(MAKE) $(build)=arch/x86/vdso $@ + $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ archclean: $(Q)rm -rf $(objtree)/arch/i386 diff --git a/kernel/arch/x86/boot/Makefile b/kernel/arch/x86/boot/Makefile index 57bbf2fb2..2ee62dba0 100644 --- a/kernel/arch/x86/boot/Makefile +++ b/kernel/arch/x86/boot/Makefile @@ -9,13 +9,13 @@ # Changed by many, many contributors over the years. # +KASAN_SANITIZE := n + # If you want to preset the SVGA mode, uncomment the next line and # set SVGA_MODE to whatever number you want. # Set it to -DSVGA_MODE=NORMAL_VGA if you just want the EGA/VGA mode. # The number is the same as you would ordinarily press at bootup. -KASAN_SANITIZE := n - SVGA_MODE := -DSVGA_MODE=NORMAL_VGA targets := vmlinux.bin setup.bin setup.elf bzImage @@ -23,7 +23,7 @@ targets += fdimage fdimage144 fdimage288 image.iso mtools.conf subdir- := compressed setup-y += a20.o bioscall.o cmdline.o copy.o cpu.o cpuflags.o cpucheck.o -setup-y += early_serial_console.o edd.o header.o main.o mca.o memory.o +setup-y += early_serial_console.o edd.o header.o main.o memory.o setup-y += pm.o pmjump.o printf.o regs.o string.o tty.o video.o setup-y += video-mode.o version.o setup-$(CONFIG_X86_APM_BOOT) += apm.o diff --git a/kernel/arch/x86/boot/boot.h b/kernel/arch/x86/boot/boot.h index bd49ec612..9011a8835 100644 --- a/kernel/arch/x86/boot/boot.h +++ b/kernel/arch/x86/boot/boot.h @@ -23,7 +23,6 @@ #include <stdarg.h> #include <linux/types.h> #include <linux/edd.h> -#include <asm/boot.h> #include <asm/setup.h> #include "bitops.h" #include "ctype.h" @@ -307,9 +306,6 @@ void query_edd(void); /* header.S */ void __attribute__((noreturn)) die(void); -/* mca.c */ -int query_mca(void); - /* memory.c */ int detect_memory(void); diff --git a/kernel/arch/x86/boot/compressed/aslr.c b/kernel/arch/x86/boot/compressed/aslr.c index d7b1f655b..6a9b96b46 100644 --- a/kernel/arch/x86/boot/compressed/aslr.c +++ b/kernel/arch/x86/boot/compressed/aslr.c @@ -82,7 +82,7 @@ static unsigned long get_random_long(void) if (has_cpuflag(X86_FEATURE_TSC)) { debug_putstr(" RDTSC"); - rdtscll(raw); + raw = rdtsc(); random ^= raw; use_i8254 = false; diff --git a/kernel/arch/x86/boot/compressed/eboot.c b/kernel/arch/x86/boot/compressed/eboot.c index 0cdc154a2..583d539a4 100644 --- a/kernel/arch/x86/boot/compressed/eboot.c +++ b/kernel/arch/x86/boot/compressed/eboot.c @@ -624,7 +624,7 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, static efi_status_t __gop_query32(struct efi_graphics_output_protocol_32 *gop32, struct efi_graphics_output_mode_info **info, - unsigned long *size, u32 *fb_base) + unsigned long *size, u64 *fb_base) { struct efi_graphics_output_protocol_mode_32 *mode; efi_status_t status; @@ -650,7 +650,8 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, unsigned long nr_gops; u16 width, height; u32 pixels_per_scan_line; - u32 fb_base; + u32 ext_lfb_base; + u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; efi_status_t status; @@ -667,6 +668,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u32 h = handles[i]; + u64 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop32); @@ -678,7 +680,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query32(gop32, &info, &size, &fb_base); + status = __gop_query32(gop32, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -692,6 +694,7 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, @@ -713,6 +716,13 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + si->pages = 1; setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); @@ -727,7 +737,7 @@ out: static efi_status_t __gop_query64(struct efi_graphics_output_protocol_64 *gop64, struct efi_graphics_output_mode_info **info, - unsigned long *size, u32 *fb_base) + unsigned long *size, u64 *fb_base) { struct efi_graphics_output_protocol_mode_64 *mode; efi_status_t status; @@ -753,7 +763,8 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, unsigned long nr_gops; u16 width, height; u32 pixels_per_scan_line; - u32 fb_base; + u32 ext_lfb_base; + u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; efi_status_t status; @@ -770,6 +781,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, bool conout_found = false; void *dummy = NULL; u64 h = handles[i]; + u64 current_fb_base; status = efi_call_early(handle_protocol, h, proto, (void **)&gop64); @@ -781,7 +793,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, if (status == EFI_SUCCESS) conout_found = true; - status = __gop_query64(gop64, &info, &size, &fb_base); + status = __gop_query64(gop64, &info, &size, ¤t_fb_base); if (status == EFI_SUCCESS && (!first_gop || conout_found)) { /* * Systems that use the UEFI Console Splitter may @@ -795,6 +807,7 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, pixel_format = info->pixel_format; pixel_info = info->pixel_information; pixels_per_scan_line = info->pixels_per_scan_line; + fb_base = current_fb_base; /* * Once we've found a GOP supporting ConOut, @@ -816,6 +829,13 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + si->pages = 1; setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); @@ -1041,7 +1061,6 @@ void setup_graphics(struct boot_params *boot_params) struct boot_params *make_boot_params(struct efi_config *c) { struct boot_params *boot_params; - struct sys_desc_table *sdt; struct apm_bios_info *bi; struct setup_header *hdr; struct efi_info *efi; @@ -1089,7 +1108,6 @@ struct boot_params *make_boot_params(struct efi_config *c) hdr = &boot_params->hdr; efi = &boot_params->efi_info; bi = &boot_params->apm_bios_info; - sdt = &boot_params->sys_desc_table; /* Copy the second sector to boot_params */ memcpy(&hdr->jump, image->image_base + 512, 512); @@ -1118,8 +1136,6 @@ struct boot_params *make_boot_params(struct efi_config *c) /* Clear APM BIOS info */ memset(bi, 0, sizeof(*bi)); - memset(sdt, 0, sizeof(*sdt)); - status = efi_parse_options(cmdline_ptr); if (status != EFI_SUCCESS) goto fail2; @@ -1228,6 +1244,10 @@ static efi_status_t setup_e820(struct boot_params *params, e820_type = E820_NVS; break; + case EFI_PERSISTENT_MEMORY: + e820_type = E820_PMEM; + break; + default: continue; } diff --git a/kernel/arch/x86/boot/compressed/misc.c b/kernel/arch/x86/boot/compressed/misc.c index e28437e0f..79dac1758 100644 --- a/kernel/arch/x86/boot/compressed/misc.c +++ b/kernel/arch/x86/boot/compressed/misc.c @@ -220,6 +220,23 @@ void __putstr(const char *s) outb(0xff & (pos >> 1), vidport+1); } +void __puthex(unsigned long value) +{ + char alpha[2] = "0"; + int bits; + + for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) { + unsigned long digit = (value >> bits) & 0xf; + + if (digit < 0xA) + alpha[0] = '0' + digit; + else + alpha[0] = 'a' + (digit - 0xA); + + __putstr(alpha); + } +} + static void error(char *x) { error_putstr("\n\n"); @@ -399,6 +416,13 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; + /* Report initial kernel position details. */ + debug_putaddr(input_data); + debug_putaddr(input_len); + debug_putaddr(output); + debug_putaddr(output_len); + debug_putaddr(run_size); + /* * The memory hole needed for the kernel is the larger of either * the entire decompressed kernel plus relocation table, or the diff --git a/kernel/arch/x86/boot/compressed/misc.h b/kernel/arch/x86/boot/compressed/misc.h index 805d25ca5..3783dc3e1 100644 --- a/kernel/arch/x86/boot/compressed/misc.h +++ b/kernel/arch/x86/boot/compressed/misc.h @@ -34,16 +34,27 @@ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; extern struct boot_params *real_mode; /* Pointer to real-mode data */ void __putstr(const char *s); +void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) +#define error_puthex(__x) __puthex(__x) #ifdef CONFIG_X86_VERBOSE_BOOTUP #define debug_putstr(__x) __putstr(__x) +#define debug_puthex(__x) __puthex(__x) +#define debug_putaddr(__x) { \ + debug_putstr(#__x ": 0x"); \ + debug_puthex((unsigned long)(__x)); \ + debug_putstr("\n"); \ + } #else static inline void debug_putstr(const char *s) { } +static inline void debug_puthex(const char *s) +{ } +#define debug_putaddr(x) /* */ #endif diff --git a/kernel/arch/x86/boot/header.S b/kernel/arch/x86/boot/header.S index 16ef02596..6236b9ec4 100644 --- a/kernel/arch/x86/boot/header.S +++ b/kernel/arch/x86/boot/header.S @@ -154,7 +154,7 @@ extra_header_fields: #else .quad 0 # ImageBase #endif - .long CONFIG_PHYSICAL_ALIGN # SectionAlignment + .long 0x20 # SectionAlignment .long 0x20 # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion @@ -414,7 +414,7 @@ xloadflags: # define XLF23 0 #endif -#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC) +#if defined(CONFIG_X86_64) && defined(CONFIG_EFI) && defined(CONFIG_KEXEC_CORE) # define XLF4 XLF_EFI_KEXEC #else # define XLF4 0 diff --git a/kernel/arch/x86/boot/main.c b/kernel/arch/x86/boot/main.c index fd6c9f236..9bcea386d 100644 --- a/kernel/arch/x86/boot/main.c +++ b/kernel/arch/x86/boot/main.c @@ -161,9 +161,6 @@ void main(void) /* Set keyboard repeat rate (why?) and query the lock flags */ keyboard_init(); - /* Query MCA information */ - query_mca(); - /* Query Intel SpeedStep (IST) information */ query_ist(); diff --git a/kernel/arch/x86/boot/mca.c b/kernel/arch/x86/boot/mca.c deleted file mode 100644 index a95a53114..000000000 --- a/kernel/arch/x86/boot/mca.c +++ /dev/null @@ -1,38 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright 2007 rPath, Inc. - All Rights Reserved - * Copyright 2009 Intel Corporation; author H. Peter Anvin - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2. - * - * ----------------------------------------------------------------------- */ - -/* - * Get the MCA system description table - */ - -#include "boot.h" - -int query_mca(void) -{ - struct biosregs ireg, oreg; - u16 len; - - initregs(&ireg); - ireg.ah = 0xc0; - intcall(0x15, &ireg, &oreg); - - if (oreg.eflags & X86_EFLAGS_CF) - return -1; /* No MCA present */ - - set_fs(oreg.es); - len = rdfs16(oreg.bx); - - if (len > sizeof(boot_params.sys_desc_table)) - len = sizeof(boot_params.sys_desc_table); - - copy_from_fs(&boot_params.sys_desc_table, oreg.bx, len); - return 0; -} diff --git a/kernel/arch/x86/boot/video-mode.c b/kernel/arch/x86/boot/video-mode.c index aa8a96b05..95c7a818c 100644 --- a/kernel/arch/x86/boot/video-mode.c +++ b/kernel/arch/x86/boot/video-mode.c @@ -19,6 +19,8 @@ #include "video.h" #include "vesa.h" +#include <uapi/asm/boot.h> + /* * Common variables */ diff --git a/kernel/arch/x86/boot/video.c b/kernel/arch/x86/boot/video.c index 05111bb8d..77780e386 100644 --- a/kernel/arch/x86/boot/video.c +++ b/kernel/arch/x86/boot/video.c @@ -13,6 +13,8 @@ * Select video mode */ +#include <uapi/asm/boot.h> + #include "boot.h" #include "video.h" #include "vesa.h" diff --git a/kernel/arch/x86/configs/i386_defconfig b/kernel/arch/x86/configs/i386_defconfig index aaa1118bf..028be48c8 100644 --- a/kernel/arch/x86/configs/i386_defconfig +++ b/kernel/arch/x86/configs/i386_defconfig @@ -23,6 +23,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y diff --git a/kernel/arch/x86/configs/x86_64_defconfig b/kernel/arch/x86/configs/x86_64_defconfig index 315b86106..cb5b3ab5b 100644 --- a/kernel/arch/x86/configs/x86_64_defconfig +++ b/kernel/arch/x86/configs/x86_64_defconfig @@ -22,6 +22,7 @@ CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y @@ -207,7 +208,6 @@ CONFIG_AGP_AMD64=y CONFIG_AGP_INTEL=y CONFIG_DRM=y CONFIG_DRM_I915=y -CONFIG_DRM_I915_KMS=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y diff --git a/kernel/arch/x86/configs/xen.config b/kernel/arch/x86/configs/xen.config new file mode 100644 index 000000000..d9fc7139f --- /dev/null +++ b/kernel/arch/x86/configs/xen.config @@ -0,0 +1,28 @@ +# global x86 required specific stuff +# On 32-bit HIGHMEM4G is not allowed +CONFIG_HIGHMEM64G=y +CONFIG_64BIT=y + +# These enable us to allow some of the +# not so generic stuff below +CONFIG_HYPERVISOR_GUEST=y +CONFIG_PCI=y +CONFIG_PCI_MSI=y +CONFIG_X86_MCE=y +CONFIG_ACPI_PROCESSOR=y +CONFIG_CPU_FREQ=y + +# x86 xen specific config options +CONFIG_XEN_PVH=y +CONFIG_XEN_MAX_DOMAIN_MEMORY=500 +CONFIG_XEN_SAVE_RESTORE=y +# CONFIG_XEN_DEBUG_FS is not set +CONFIG_XEN_MCE_LOG=y +CONFIG_XEN_ACPI_PROCESSOR=m +# x86 specific backend drivers +CONFIG_XEN_PCIDEV_BACKEND=m +# x86 specific frontend drivers +CONFIG_XEN_PCIDEV_FRONTEND=m +# depends on MEMORY_HOTPLUG, arm64 doesn't enable this yet, +# move to generic config if it ever does. +CONFIG_XEN_BALLOON_MEMORY_HOTPLUG=y diff --git a/kernel/arch/x86/crypto/Makefile b/kernel/arch/x86/crypto/Makefile index 5a4a089e8..b9b912a44 100644 --- a/kernel/arch/x86/crypto/Makefile +++ b/kernel/arch/x86/crypto/Makefile @@ -5,6 +5,8 @@ avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no) avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) +sha1_ni_supported :=$(call as-instr,sha1msg1 %xmm0$(comma)%xmm1,yes,no) +sha256_ni_supported :=$(call as-instr,sha256msg1 %xmm0$(comma)%xmm1,yes,no) obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o @@ -20,6 +22,7 @@ obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o +obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o @@ -30,6 +33,7 @@ obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o +obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o # These modules require assembler to support AVX. ifeq ($(avx_supported),yes) @@ -60,6 +64,7 @@ blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o +chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o ifeq ($(avx_supported),yes) @@ -75,6 +80,7 @@ endif ifeq ($(avx2_supported),yes) camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o + chacha20-x86_64-y += chacha20-avx2-x86_64.o serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o endif @@ -82,12 +88,20 @@ aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o +poly1305-x86_64-y := poly1305-sse2-x86_64.o poly1305_glue.o ifeq ($(avx2_supported),yes) sha1-ssse3-y += sha1_avx2_x86_64_asm.o +poly1305-x86_64-y += poly1305-avx2-x86_64.o +endif +ifeq ($(sha1_ni_supported),yes) +sha1-ssse3-y += sha1_ni_asm.o endif crc32c-intel-y := crc32c-intel_glue.o crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o +ifeq ($(sha256_ni_supported),yes) +sha256-ssse3-y += sha256_ni_asm.o +endif sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o diff --git a/kernel/arch/x86/crypto/aesni-intel_glue.c b/kernel/arch/x86/crypto/aesni-intel_glue.c index 3fd3b1634..c6d5458ee 100644 --- a/kernel/arch/x86/crypto/aesni-intel_glue.c +++ b/kernel/arch/x86/crypto/aesni-intel_glue.c @@ -32,7 +32,7 @@ #include <crypto/lrw.h> #include <crypto/xts.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/crypto/aes.h> #include <crypto/ablk_helper.h> #include <crypto/scatterwalk.h> @@ -44,15 +44,19 @@ #endif +#define AESNI_ALIGN 16 +#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE - 1)) +#define RFC4106_HASH_SUBKEY_SIZE 16 + /* This data is stored at the end of the crypto_tfm struct. * It's a type of per "session" data storage location. * This needs to be 16 byte aligned. */ struct aesni_rfc4106_gcm_ctx { - u8 hash_subkey[16]; - struct crypto_aes_ctx aes_key_expanded; + u8 hash_subkey[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + struct crypto_aes_ctx aes_key_expanded + __attribute__ ((__aligned__(AESNI_ALIGN))); u8 nonce[4]; - struct cryptd_aead *cryptd_tfm; }; struct aesni_gcm_set_hash_subkey_result { @@ -66,10 +70,6 @@ struct aesni_hash_subkey_req_data { struct scatterlist sg; }; -#define AESNI_ALIGN (16) -#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1)) -#define RFC4106_HASH_SUBKEY_SIZE 16 - struct aesni_lrw_ctx { struct lrw_table_ctx lrw_table; u8 raw_aes_ctx[sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1]; @@ -283,10 +283,11 @@ static void (*aesni_gcm_dec_tfm)(void *ctx, u8 *out, static inline struct aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) { - return - (struct aesni_rfc4106_gcm_ctx *) - PTR_ALIGN((u8 *) - crypto_tfm_ctx(crypto_aead_tfm(tfm)), AESNI_ALIGN); + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return PTR_ALIGN(crypto_aead_ctx(tfm), align); } #endif @@ -792,36 +793,27 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst, #endif #ifdef CONFIG_X86_64 -static int rfc4106_init(struct crypto_tfm *tfm) +static int rfc4106_init(struct crypto_aead *aead) { struct cryptd_aead *cryptd_tfm; - struct aesni_rfc4106_gcm_ctx *ctx = (struct aesni_rfc4106_gcm_ctx *) - PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN); - struct crypto_aead *cryptd_child; - struct aesni_rfc4106_gcm_ctx *child_ctx; + struct cryptd_aead **ctx = crypto_aead_ctx(aead); + cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni", CRYPTO_ALG_INTERNAL, CRYPTO_ALG_INTERNAL); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); - cryptd_child = cryptd_aead_child(cryptd_tfm); - child_ctx = aesni_rfc4106_gcm_ctx_get(cryptd_child); - memcpy(child_ctx, ctx, sizeof(*ctx)); - ctx->cryptd_tfm = cryptd_tfm; - tfm->crt_aead.reqsize = sizeof(struct aead_request) - + crypto_aead_reqsize(&cryptd_tfm->base); + *ctx = cryptd_tfm; + crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base)); return 0; } -static void rfc4106_exit(struct crypto_tfm *tfm) +static void rfc4106_exit(struct crypto_aead *aead) { - struct aesni_rfc4106_gcm_ctx *ctx = - (struct aesni_rfc4106_gcm_ctx *) - PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN); - if (!IS_ERR(ctx->cryptd_tfm)) - cryptd_free_aead(ctx->cryptd_tfm); - return; + struct cryptd_aead **ctx = crypto_aead_ctx(aead); + + cryptd_free_aead(*ctx); } static void @@ -847,8 +839,6 @@ rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) if (IS_ERR(ctr_tfm)) return PTR_ERR(ctr_tfm); - crypto_ablkcipher_clear_flags(ctr_tfm, ~0); - ret = crypto_ablkcipher_setkey(ctr_tfm, key, key_len); if (ret) goto out_free_ablkcipher; @@ -897,73 +887,29 @@ out_free_ablkcipher: static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key, unsigned int key_len) { - int ret = 0; - struct crypto_tfm *tfm = crypto_aead_tfm(aead); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead); - u8 *new_key_align, *new_key_mem = NULL; if (key_len < 4) { - crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } /*Account for 4 byte nonce at the end.*/ key_len -= 4; - if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256) { - crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); - return -EINVAL; - } memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce)); - /*This must be on a 16 byte boundary!*/ - if ((unsigned long)(&(ctx->aes_key_expanded.key_enc[0])) % AESNI_ALIGN) - return -EINVAL; - - if ((unsigned long)key % AESNI_ALIGN) { - /*key is not aligned: use an auxuliar aligned pointer*/ - new_key_mem = kmalloc(key_len+AESNI_ALIGN, GFP_KERNEL); - if (!new_key_mem) - return -ENOMEM; - - new_key_align = PTR_ALIGN(new_key_mem, AESNI_ALIGN); - memcpy(new_key_align, key, key_len); - key = new_key_align; - } - if (!irq_fpu_usable()) - ret = crypto_aes_expand_key(&(ctx->aes_key_expanded), - key, key_len); - else { - kernel_fpu_begin(); - ret = aesni_set_key(&(ctx->aes_key_expanded), key, key_len); - kernel_fpu_end(); - } - /*This must be on a 16 byte boundary!*/ - if ((unsigned long)(&(ctx->hash_subkey[0])) % AESNI_ALIGN) { - ret = -EINVAL; - goto exit; - } - ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); -exit: - kfree(new_key_mem); - return ret; + return aes_set_key_common(crypto_aead_tfm(aead), + &ctx->aes_key_expanded, key, key_len) ?: + rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); } static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, unsigned int key_len) { - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); - struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm); - struct aesni_rfc4106_gcm_ctx *c_ctx = aesni_rfc4106_gcm_ctx_get(child); - struct cryptd_aead *cryptd_tfm = ctx->cryptd_tfm; - int ret; + struct cryptd_aead **ctx = crypto_aead_ctx(parent); + struct cryptd_aead *cryptd_tfm = *ctx; - ret = crypto_aead_setkey(child, key, key_len); - if (!ret) { - memcpy(ctx, c_ctx, sizeof(*ctx)); - ctx->cryptd_tfm = cryptd_tfm; - } - return ret; + return crypto_aead_setkey(&cryptd_tfm->base, key, key_len); } static int common_rfc4106_set_authsize(struct crypto_aead *aead, @@ -977,7 +923,7 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead, default: return -EINVAL; } - crypto_aead_crt(aead)->authsize = authsize; + return 0; } @@ -986,44 +932,31 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead, static int rfc4106_set_authsize(struct crypto_aead *parent, unsigned int authsize) { - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); - struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm); - int ret; + struct cryptd_aead **ctx = crypto_aead_ctx(parent); + struct cryptd_aead *cryptd_tfm = *ctx; - ret = crypto_aead_setauthsize(child, authsize); - if (!ret) - crypto_aead_crt(parent)->authsize = authsize; - return ret; + return crypto_aead_setauthsize(&cryptd_tfm->base, authsize); } -static int __driver_rfc4106_encrypt(struct aead_request *req) +static int helper_rfc4106_encrypt(struct aead_request *req) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; __be32 counter = cpu_to_be32(1); struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - u32 key_len = ctx->aes_key_expanded.key_length; void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv_tab[16+AESNI_ALIGN]; - u8* iv = (u8 *) PTR_ALIGN((u8 *)iv_tab, AESNI_ALIGN); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); struct scatter_walk src_sg_walk; - struct scatter_walk assoc_sg_walk; struct scatter_walk dst_sg_walk; unsigned int i; /* Assuming we are supporting rfc4106 64-bit extended */ /* sequence numbers We need to have the AAD length equal */ - /* to 8 or 12 bytes */ - if (unlikely(req->assoclen != 8 && req->assoclen != 12)) + /* to 16 or 20 bytes */ + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) return -EINVAL; - if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16)) - return -EINVAL; - if (unlikely(key_len != AES_KEYSIZE_128 && - key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256)) - return -EINVAL; /* IV below built */ for (i = 0; i < 4; i++) @@ -1032,55 +965,57 @@ static int __driver_rfc4106_encrypt(struct aead_request *req) *(iv+4+i) = req->iv[i]; *((__be32 *)(iv+12)) = counter; - if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) { + if (sg_is_last(req->src) && + req->src->offset + req->src->length <= PAGE_SIZE && + sg_is_last(req->dst) && + req->dst->offset + req->dst->length <= PAGE_SIZE) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); - scatterwalk_start(&assoc_sg_walk, req->assoc); - src = scatterwalk_map(&src_sg_walk); - assoc = scatterwalk_map(&assoc_sg_walk); + assoc = scatterwalk_map(&src_sg_walk); + src = assoc + req->assoclen; dst = src; if (unlikely(req->src != req->dst)) { scatterwalk_start(&dst_sg_walk, req->dst); - dst = scatterwalk_map(&dst_sg_walk); + dst = scatterwalk_map(&dst_sg_walk) + req->assoclen; } - } else { /* Allocate memory for src, dst, assoc */ - src = kmalloc(req->cryptlen + auth_tag_len + req->assoclen, + assoc = kmalloc(req->cryptlen + auth_tag_len + req->assoclen, GFP_ATOMIC); - if (unlikely(!src)) + if (unlikely(!assoc)) return -ENOMEM; - assoc = (src + req->cryptlen + auth_tag_len); - scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); - scatterwalk_map_and_copy(assoc, req->assoc, 0, - req->assoclen, 0); + scatterwalk_map_and_copy(assoc, req->src, 0, + req->assoclen + req->cryptlen, 0); + src = assoc + req->assoclen; dst = src; } - aesni_gcm_enc_tfm(aes_ctx, dst, src, (unsigned long)req->cryptlen, iv, - ctx->hash_subkey, assoc, (unsigned long)req->assoclen, dst - + ((unsigned long)req->cryptlen), auth_tag_len); + kernel_fpu_begin(); + aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv, + ctx->hash_subkey, assoc, req->assoclen - 8, + dst + req->cryptlen, auth_tag_len); + kernel_fpu_end(); /* The authTag (aka the Integrity Check Value) needs to be written * back to the packet. */ if (one_entry_in_sg) { if (unlikely(req->src != req->dst)) { - scatterwalk_unmap(dst); - scatterwalk_done(&dst_sg_walk, 0, 0); + scatterwalk_unmap(dst - req->assoclen); + scatterwalk_advance(&dst_sg_walk, req->dst->length); + scatterwalk_done(&dst_sg_walk, 1, 0); } - scatterwalk_unmap(src); scatterwalk_unmap(assoc); - scatterwalk_done(&src_sg_walk, 0, 0); - scatterwalk_done(&assoc_sg_walk, 0, 0); + scatterwalk_advance(&src_sg_walk, req->src->length); + scatterwalk_done(&src_sg_walk, req->src == req->dst, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, - req->cryptlen + auth_tag_len, 1); - kfree(src); + scatterwalk_map_and_copy(dst, req->dst, req->assoclen, + req->cryptlen + auth_tag_len, 1); + kfree(assoc); } return 0; } -static int __driver_rfc4106_decrypt(struct aead_request *req) +static int helper_rfc4106_decrypt(struct aead_request *req) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; @@ -1089,30 +1024,20 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) int retval = 0; struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - u32 key_len = ctx->aes_key_expanded.key_length; void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv_and_authTag[32+AESNI_ALIGN]; - u8 *iv = (u8 *) PTR_ALIGN((u8 *)iv_and_authTag, AESNI_ALIGN); - u8 *authTag = iv + 16; + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + u8 authTag[16]; struct scatter_walk src_sg_walk; - struct scatter_walk assoc_sg_walk; struct scatter_walk dst_sg_walk; unsigned int i; - if (unlikely((req->cryptlen < auth_tag_len) || - (req->assoclen != 8 && req->assoclen != 12))) + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) return -EINVAL; - if (unlikely(auth_tag_len != 8 && auth_tag_len != 12 && auth_tag_len != 16)) - return -EINVAL; - if (unlikely(key_len != AES_KEYSIZE_128 && - key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256)) - return -EINVAL; /* Assuming we are supporting rfc4106 64-bit extended */ /* sequence numbers We need to have the AAD length */ - /* equal to 8 or 12 bytes */ + /* equal to 16 or 20 bytes */ tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len); /* IV below built */ @@ -1122,33 +1047,36 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) *(iv+4+i) = req->iv[i]; *((__be32 *)(iv+12)) = counter; - if ((sg_is_last(req->src)) && (sg_is_last(req->assoc))) { + if (sg_is_last(req->src) && + req->src->offset + req->src->length <= PAGE_SIZE && + sg_is_last(req->dst) && + req->dst->offset + req->dst->length <= PAGE_SIZE) { one_entry_in_sg = 1; scatterwalk_start(&src_sg_walk, req->src); - scatterwalk_start(&assoc_sg_walk, req->assoc); - src = scatterwalk_map(&src_sg_walk); - assoc = scatterwalk_map(&assoc_sg_walk); + assoc = scatterwalk_map(&src_sg_walk); + src = assoc + req->assoclen; dst = src; if (unlikely(req->src != req->dst)) { scatterwalk_start(&dst_sg_walk, req->dst); - dst = scatterwalk_map(&dst_sg_walk); + dst = scatterwalk_map(&dst_sg_walk) + req->assoclen; } } else { /* Allocate memory for src, dst, assoc */ - src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); - if (!src) + assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); + if (!assoc) return -ENOMEM; - assoc = (src + req->cryptlen); - scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); - scatterwalk_map_and_copy(assoc, req->assoc, 0, - req->assoclen, 0); + scatterwalk_map_and_copy(assoc, req->src, 0, + req->assoclen + req->cryptlen, 0); + src = assoc + req->assoclen; dst = src; } + kernel_fpu_begin(); aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv, - ctx->hash_subkey, assoc, (unsigned long)req->assoclen, - authTag, auth_tag_len); + ctx->hash_subkey, assoc, req->assoclen - 8, + authTag, auth_tag_len); + kernel_fpu_end(); /* Compare generated tag with passed in tag. */ retval = crypto_memneq(src + tempCipherLen, authTag, auth_tag_len) ? @@ -1156,90 +1084,45 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) if (one_entry_in_sg) { if (unlikely(req->src != req->dst)) { - scatterwalk_unmap(dst); - scatterwalk_done(&dst_sg_walk, 0, 0); + scatterwalk_unmap(dst - req->assoclen); + scatterwalk_advance(&dst_sg_walk, req->dst->length); + scatterwalk_done(&dst_sg_walk, 1, 0); } - scatterwalk_unmap(src); scatterwalk_unmap(assoc); - scatterwalk_done(&src_sg_walk, 0, 0); - scatterwalk_done(&assoc_sg_walk, 0, 0); + scatterwalk_advance(&src_sg_walk, req->src->length); + scatterwalk_done(&src_sg_walk, req->src == req->dst, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1); - kfree(src); + scatterwalk_map_and_copy(dst, req->dst, req->assoclen, + tempCipherLen, 1); + kfree(assoc); } return retval; } static int rfc4106_encrypt(struct aead_request *req) { - int ret; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + struct cryptd_aead **ctx = crypto_aead_ctx(tfm); + struct cryptd_aead *cryptd_tfm = *ctx; - if (!irq_fpu_usable()) { - struct aead_request *cryptd_req = - (struct aead_request *) aead_request_ctx(req); + aead_request_set_tfm(req, irq_fpu_usable() ? + cryptd_aead_child(cryptd_tfm) : + &cryptd_tfm->base); - memcpy(cryptd_req, req, sizeof(*req)); - aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); - ret = crypto_aead_encrypt(cryptd_req); - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_encrypt(req); - kernel_fpu_end(); - } - return ret; + return crypto_aead_encrypt(req); } static int rfc4106_decrypt(struct aead_request *req) { - int ret; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - - if (!irq_fpu_usable()) { - struct aead_request *cryptd_req = - (struct aead_request *) aead_request_ctx(req); - - memcpy(cryptd_req, req, sizeof(*req)); - aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); - ret = crypto_aead_decrypt(cryptd_req); - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_decrypt(req); - kernel_fpu_end(); - } - return ret; -} - -static int helper_rfc4106_encrypt(struct aead_request *req) -{ - int ret; - - if (unlikely(!irq_fpu_usable())) { - WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context"); - ret = -EINVAL; - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_encrypt(req); - kernel_fpu_end(); - } - return ret; -} + struct cryptd_aead **ctx = crypto_aead_ctx(tfm); + struct cryptd_aead *cryptd_tfm = *ctx; -static int helper_rfc4106_decrypt(struct aead_request *req) -{ - int ret; + aead_request_set_tfm(req, irq_fpu_usable() ? + cryptd_aead_child(cryptd_tfm) : + &cryptd_tfm->base); - if (unlikely(!irq_fpu_usable())) { - WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context"); - ret = -EINVAL; - } else { - kernel_fpu_begin(); - ret = __driver_rfc4106_decrypt(req); - kernel_fpu_end(); - } - return ret; + return crypto_aead_decrypt(req); } #endif @@ -1412,51 +1295,6 @@ static struct crypto_alg aesni_algs[] = { { .geniv = "chainiv", }, }, -}, { - .cra_name = "__gcm-aes-aesni", - .cra_driver_name = "__driver-gcm-aes-aesni", - .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_INTERNAL, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) + - AESNI_ALIGN, - .cra_alignmask = 0, - .cra_type = &crypto_aead_type, - .cra_module = THIS_MODULE, - .cra_u = { - .aead = { - .setkey = common_rfc4106_set_key, - .setauthsize = common_rfc4106_set_authsize, - .encrypt = helper_rfc4106_encrypt, - .decrypt = helper_rfc4106_decrypt, - .ivsize = 8, - .maxauthsize = 16, - }, - }, -}, { - .cra_name = "rfc4106(gcm(aes))", - .cra_driver_name = "rfc4106-gcm-aesni", - .cra_priority = 400, - .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) + - AESNI_ALIGN, - .cra_alignmask = 0, - .cra_type = &crypto_nivaead_type, - .cra_module = THIS_MODULE, - .cra_init = rfc4106_init, - .cra_exit = rfc4106_exit, - .cra_u = { - .aead = { - .setkey = rfc4106_set_key, - .setauthsize = rfc4106_set_authsize, - .encrypt = rfc4106_encrypt, - .decrypt = rfc4106_decrypt, - .geniv = "seqiv", - .ivsize = 8, - .maxauthsize = 16, - }, - }, #endif #if IS_ENABLED(CONFIG_CRYPTO_PCBC) }, { @@ -1571,6 +1409,46 @@ static struct crypto_alg aesni_algs[] = { { }, } }; +#ifdef CONFIG_X86_64 +static struct aead_alg aesni_aead_algs[] = { { + .setkey = common_rfc4106_set_key, + .setauthsize = common_rfc4106_set_authsize, + .encrypt = helper_rfc4106_encrypt, + .decrypt = helper_rfc4106_decrypt, + .ivsize = 8, + .maxauthsize = 16, + .base = { + .cra_name = "__gcm-aes-aesni", + .cra_driver_name = "__driver-gcm-aes-aesni", + .cra_flags = CRYPTO_ALG_INTERNAL, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx), + .cra_alignmask = AESNI_ALIGN - 1, + .cra_module = THIS_MODULE, + }, +}, { + .init = rfc4106_init, + .exit = rfc4106_exit, + .setkey = rfc4106_set_key, + .setauthsize = rfc4106_set_authsize, + .encrypt = rfc4106_encrypt, + .decrypt = rfc4106_decrypt, + .ivsize = 8, + .maxauthsize = 16, + .base = { + .cra_name = "rfc4106(gcm(aes))", + .cra_driver_name = "rfc4106-gcm-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct cryptd_aead *), + .cra_module = THIS_MODULE, + }, +} }; +#else +static struct aead_alg aesni_aead_algs[0]; +#endif + static const struct x86_cpu_id aesni_cpu_id[] = { X86_FEATURE_MATCH(X86_FEATURE_AES), @@ -1618,17 +1496,33 @@ static int __init aesni_init(void) if (err) return err; - return crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); + err = crypto_register_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); + if (err) + goto fpu_exit; + + err = crypto_register_aeads(aesni_aead_algs, + ARRAY_SIZE(aesni_aead_algs)); + if (err) + goto unregister_algs; + + return err; + +unregister_algs: + crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); +fpu_exit: + crypto_fpu_exit(); + return err; } static void __exit aesni_exit(void) { + crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs)); crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs)); crypto_fpu_exit(); } -module_init(aesni_init); +late_initcall(aesni_init); module_exit(aesni_exit); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); diff --git a/kernel/arch/x86/crypto/camellia_aesni_avx2_glue.c b/kernel/arch/x86/crypto/camellia_aesni_avx2_glue.c index baf0ac21a..d84456924 100644 --- a/kernel/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/kernel/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -19,8 +19,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/camellia.h> #include <asm/crypto/glue_helper.h> @@ -561,16 +560,16 @@ static struct crypto_alg cmll_algs[10] = { { static int __init camellia_aesni_init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx2 || !cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { pr_info("AVX2 or AES-NI instructions are not detected.\n"); return -ENODEV; } - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX2 detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/crypto/camellia_aesni_avx_glue.c b/kernel/arch/x86/crypto/camellia_aesni_avx_glue.c index 78818a1e7..93d8f2957 100644 --- a/kernel/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/kernel/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -19,8 +19,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/camellia.h> #include <asm/crypto/glue_helper.h> @@ -553,16 +552,16 @@ static struct crypto_alg cmll_algs[10] = { { static int __init camellia_aesni_init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx || !cpu_has_aes || !cpu_has_osxsave) { pr_info("AVX or AES-NI instructions are not detected.\n"); return -ENODEV; } - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/crypto/cast5_avx_glue.c b/kernel/arch/x86/crypto/cast5_avx_glue.c index f799ec36b..d7699130e 100644 --- a/kernel/arch/x86/crypto/cast5_avx_glue.c +++ b/kernel/arch/x86/crypto/cast5_avx_glue.c @@ -31,8 +31,7 @@ #include <crypto/cast5.h> #include <crypto/cryptd.h> #include <crypto/ctr.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/glue_helper.h> #define CAST5_PARALLEL_BLOCKS 16 @@ -465,16 +464,11 @@ static struct crypto_alg cast5_algs[6] = { { static int __init cast5_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - pr_info("AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/crypto/cast6_avx_glue.c b/kernel/arch/x86/crypto/cast6_avx_glue.c index f448810ca..fca459578 100644 --- a/kernel/arch/x86/crypto/cast6_avx_glue.c +++ b/kernel/arch/x86/crypto/cast6_avx_glue.c @@ -36,8 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/glue_helper.h> #define CAST6_PARALLEL_BLOCKS 8 @@ -590,16 +589,11 @@ static struct crypto_alg cast6_algs[10] = { { static int __init cast6_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - pr_info("AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/crypto/chacha20-avx2-x86_64.S b/kernel/arch/x86/crypto/chacha20-avx2-x86_64.S new file mode 100644 index 000000000..16694e625 --- /dev/null +++ b/kernel/arch/x86/crypto/chacha20-avx2-x86_64.S @@ -0,0 +1,443 @@ +/* + * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX2 functions + * + * Copyright (C) 2015 Martin Willi + * + * 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. + */ + +#include <linux/linkage.h> + +.data +.align 32 + +ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003 + .octa 0x0e0d0c0f0a09080b0605040702010003 +ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302 + .octa 0x0d0c0f0e09080b0a0504070601000302 +CTRINC: .octa 0x00000003000000020000000100000000 + .octa 0x00000007000000060000000500000004 + +.text + +ENTRY(chacha20_8block_xor_avx2) + # %rdi: Input state matrix, s + # %rsi: 8 data blocks output, o + # %rdx: 8 data blocks input, i + + # This function encrypts eight consecutive ChaCha20 blocks by loading + # the state matrix in AVX registers eight times. As we need some + # scratch registers, we save the first four registers on the stack. The + # algorithm performs each operation on the corresponding word of each + # state matrix, hence requires no word shuffling. For final XORing step + # we transpose the matrix by interleaving 32-, 64- and then 128-bit + # words, which allows us to do XOR in AVX registers. 8/16-bit word + # rotation is done with the slightly better performing byte shuffling, + # 7/12-bit word rotation uses traditional shift+OR. + + vzeroupper + # 4 * 32 byte stack, 32-byte aligned + mov %rsp, %r8 + and $~31, %rsp + sub $0x80, %rsp + + # x0..15[0-7] = s[0..15] + vpbroadcastd 0x00(%rdi),%ymm0 + vpbroadcastd 0x04(%rdi),%ymm1 + vpbroadcastd 0x08(%rdi),%ymm2 + vpbroadcastd 0x0c(%rdi),%ymm3 + vpbroadcastd 0x10(%rdi),%ymm4 + vpbroadcastd 0x14(%rdi),%ymm5 + vpbroadcastd 0x18(%rdi),%ymm6 + vpbroadcastd 0x1c(%rdi),%ymm7 + vpbroadcastd 0x20(%rdi),%ymm8 + vpbroadcastd 0x24(%rdi),%ymm9 + vpbroadcastd 0x28(%rdi),%ymm10 + vpbroadcastd 0x2c(%rdi),%ymm11 + vpbroadcastd 0x30(%rdi),%ymm12 + vpbroadcastd 0x34(%rdi),%ymm13 + vpbroadcastd 0x38(%rdi),%ymm14 + vpbroadcastd 0x3c(%rdi),%ymm15 + # x0..3 on stack + vmovdqa %ymm0,0x00(%rsp) + vmovdqa %ymm1,0x20(%rsp) + vmovdqa %ymm2,0x40(%rsp) + vmovdqa %ymm3,0x60(%rsp) + + vmovdqa CTRINC(%rip),%ymm1 + vmovdqa ROT8(%rip),%ymm2 + vmovdqa ROT16(%rip),%ymm3 + + # x12 += counter values 0-3 + vpaddd %ymm1,%ymm12,%ymm12 + + mov $10,%ecx + +.Ldoubleround8: + # x0 += x4, x12 = rotl32(x12 ^ x0, 16) + vpaddd 0x00(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm3,%ymm12,%ymm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 16) + vpaddd 0x20(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm3,%ymm13,%ymm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 16) + vpaddd 0x40(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm3,%ymm14,%ymm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 16) + vpaddd 0x60(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm3,%ymm15,%ymm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 12) + vpaddd %ymm12,%ymm8,%ymm8 + vpxor %ymm8,%ymm4,%ymm4 + vpslld $12,%ymm4,%ymm0 + vpsrld $20,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 12) + vpaddd %ymm13,%ymm9,%ymm9 + vpxor %ymm9,%ymm5,%ymm5 + vpslld $12,%ymm5,%ymm0 + vpsrld $20,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 12) + vpaddd %ymm14,%ymm10,%ymm10 + vpxor %ymm10,%ymm6,%ymm6 + vpslld $12,%ymm6,%ymm0 + vpsrld $20,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 12) + vpaddd %ymm15,%ymm11,%ymm11 + vpxor %ymm11,%ymm7,%ymm7 + vpslld $12,%ymm7,%ymm0 + vpsrld $20,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + + # x0 += x4, x12 = rotl32(x12 ^ x0, 8) + vpaddd 0x00(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm2,%ymm12,%ymm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 8) + vpaddd 0x20(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm2,%ymm13,%ymm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 8) + vpaddd 0x40(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm2,%ymm14,%ymm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 8) + vpaddd 0x60(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm2,%ymm15,%ymm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 7) + vpaddd %ymm12,%ymm8,%ymm8 + vpxor %ymm8,%ymm4,%ymm4 + vpslld $7,%ymm4,%ymm0 + vpsrld $25,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 7) + vpaddd %ymm13,%ymm9,%ymm9 + vpxor %ymm9,%ymm5,%ymm5 + vpslld $7,%ymm5,%ymm0 + vpsrld $25,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 7) + vpaddd %ymm14,%ymm10,%ymm10 + vpxor %ymm10,%ymm6,%ymm6 + vpslld $7,%ymm6,%ymm0 + vpsrld $25,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 7) + vpaddd %ymm15,%ymm11,%ymm11 + vpxor %ymm11,%ymm7,%ymm7 + vpslld $7,%ymm7,%ymm0 + vpsrld $25,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 16) + vpaddd 0x00(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm3,%ymm15,%ymm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 16)%ymm0 + vpaddd 0x20(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm3,%ymm12,%ymm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 16) + vpaddd 0x40(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm3,%ymm13,%ymm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 16) + vpaddd 0x60(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm3,%ymm14,%ymm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 12) + vpaddd %ymm15,%ymm10,%ymm10 + vpxor %ymm10,%ymm5,%ymm5 + vpslld $12,%ymm5,%ymm0 + vpsrld $20,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 12) + vpaddd %ymm12,%ymm11,%ymm11 + vpxor %ymm11,%ymm6,%ymm6 + vpslld $12,%ymm6,%ymm0 + vpsrld $20,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 12) + vpaddd %ymm13,%ymm8,%ymm8 + vpxor %ymm8,%ymm7,%ymm7 + vpslld $12,%ymm7,%ymm0 + vpsrld $20,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 12) + vpaddd %ymm14,%ymm9,%ymm9 + vpxor %ymm9,%ymm4,%ymm4 + vpslld $12,%ymm4,%ymm0 + vpsrld $20,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 8) + vpaddd 0x00(%rsp),%ymm5,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpxor %ymm0,%ymm15,%ymm15 + vpshufb %ymm2,%ymm15,%ymm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 8) + vpaddd 0x20(%rsp),%ymm6,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpxor %ymm0,%ymm12,%ymm12 + vpshufb %ymm2,%ymm12,%ymm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 8) + vpaddd 0x40(%rsp),%ymm7,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpxor %ymm0,%ymm13,%ymm13 + vpshufb %ymm2,%ymm13,%ymm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 8) + vpaddd 0x60(%rsp),%ymm4,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpxor %ymm0,%ymm14,%ymm14 + vpshufb %ymm2,%ymm14,%ymm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 7) + vpaddd %ymm15,%ymm10,%ymm10 + vpxor %ymm10,%ymm5,%ymm5 + vpslld $7,%ymm5,%ymm0 + vpsrld $25,%ymm5,%ymm5 + vpor %ymm0,%ymm5,%ymm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 7) + vpaddd %ymm12,%ymm11,%ymm11 + vpxor %ymm11,%ymm6,%ymm6 + vpslld $7,%ymm6,%ymm0 + vpsrld $25,%ymm6,%ymm6 + vpor %ymm0,%ymm6,%ymm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 7) + vpaddd %ymm13,%ymm8,%ymm8 + vpxor %ymm8,%ymm7,%ymm7 + vpslld $7,%ymm7,%ymm0 + vpsrld $25,%ymm7,%ymm7 + vpor %ymm0,%ymm7,%ymm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 7) + vpaddd %ymm14,%ymm9,%ymm9 + vpxor %ymm9,%ymm4,%ymm4 + vpslld $7,%ymm4,%ymm0 + vpsrld $25,%ymm4,%ymm4 + vpor %ymm0,%ymm4,%ymm4 + + dec %ecx + jnz .Ldoubleround8 + + # x0..15[0-3] += s[0..15] + vpbroadcastd 0x00(%rdi),%ymm0 + vpaddd 0x00(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x00(%rsp) + vpbroadcastd 0x04(%rdi),%ymm0 + vpaddd 0x20(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x20(%rsp) + vpbroadcastd 0x08(%rdi),%ymm0 + vpaddd 0x40(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x40(%rsp) + vpbroadcastd 0x0c(%rdi),%ymm0 + vpaddd 0x60(%rsp),%ymm0,%ymm0 + vmovdqa %ymm0,0x60(%rsp) + vpbroadcastd 0x10(%rdi),%ymm0 + vpaddd %ymm0,%ymm4,%ymm4 + vpbroadcastd 0x14(%rdi),%ymm0 + vpaddd %ymm0,%ymm5,%ymm5 + vpbroadcastd 0x18(%rdi),%ymm0 + vpaddd %ymm0,%ymm6,%ymm6 + vpbroadcastd 0x1c(%rdi),%ymm0 + vpaddd %ymm0,%ymm7,%ymm7 + vpbroadcastd 0x20(%rdi),%ymm0 + vpaddd %ymm0,%ymm8,%ymm8 + vpbroadcastd 0x24(%rdi),%ymm0 + vpaddd %ymm0,%ymm9,%ymm9 + vpbroadcastd 0x28(%rdi),%ymm0 + vpaddd %ymm0,%ymm10,%ymm10 + vpbroadcastd 0x2c(%rdi),%ymm0 + vpaddd %ymm0,%ymm11,%ymm11 + vpbroadcastd 0x30(%rdi),%ymm0 + vpaddd %ymm0,%ymm12,%ymm12 + vpbroadcastd 0x34(%rdi),%ymm0 + vpaddd %ymm0,%ymm13,%ymm13 + vpbroadcastd 0x38(%rdi),%ymm0 + vpaddd %ymm0,%ymm14,%ymm14 + vpbroadcastd 0x3c(%rdi),%ymm0 + vpaddd %ymm0,%ymm15,%ymm15 + + # x12 += counter values 0-3 + vpaddd %ymm1,%ymm12,%ymm12 + + # interleave 32-bit words in state n, n+1 + vmovdqa 0x00(%rsp),%ymm0 + vmovdqa 0x20(%rsp),%ymm1 + vpunpckldq %ymm1,%ymm0,%ymm2 + vpunpckhdq %ymm1,%ymm0,%ymm1 + vmovdqa %ymm2,0x00(%rsp) + vmovdqa %ymm1,0x20(%rsp) + vmovdqa 0x40(%rsp),%ymm0 + vmovdqa 0x60(%rsp),%ymm1 + vpunpckldq %ymm1,%ymm0,%ymm2 + vpunpckhdq %ymm1,%ymm0,%ymm1 + vmovdqa %ymm2,0x40(%rsp) + vmovdqa %ymm1,0x60(%rsp) + vmovdqa %ymm4,%ymm0 + vpunpckldq %ymm5,%ymm0,%ymm4 + vpunpckhdq %ymm5,%ymm0,%ymm5 + vmovdqa %ymm6,%ymm0 + vpunpckldq %ymm7,%ymm0,%ymm6 + vpunpckhdq %ymm7,%ymm0,%ymm7 + vmovdqa %ymm8,%ymm0 + vpunpckldq %ymm9,%ymm0,%ymm8 + vpunpckhdq %ymm9,%ymm0,%ymm9 + vmovdqa %ymm10,%ymm0 + vpunpckldq %ymm11,%ymm0,%ymm10 + vpunpckhdq %ymm11,%ymm0,%ymm11 + vmovdqa %ymm12,%ymm0 + vpunpckldq %ymm13,%ymm0,%ymm12 + vpunpckhdq %ymm13,%ymm0,%ymm13 + vmovdqa %ymm14,%ymm0 + vpunpckldq %ymm15,%ymm0,%ymm14 + vpunpckhdq %ymm15,%ymm0,%ymm15 + + # interleave 64-bit words in state n, n+2 + vmovdqa 0x00(%rsp),%ymm0 + vmovdqa 0x40(%rsp),%ymm2 + vpunpcklqdq %ymm2,%ymm0,%ymm1 + vpunpckhqdq %ymm2,%ymm0,%ymm2 + vmovdqa %ymm1,0x00(%rsp) + vmovdqa %ymm2,0x40(%rsp) + vmovdqa 0x20(%rsp),%ymm0 + vmovdqa 0x60(%rsp),%ymm2 + vpunpcklqdq %ymm2,%ymm0,%ymm1 + vpunpckhqdq %ymm2,%ymm0,%ymm2 + vmovdqa %ymm1,0x20(%rsp) + vmovdqa %ymm2,0x60(%rsp) + vmovdqa %ymm4,%ymm0 + vpunpcklqdq %ymm6,%ymm0,%ymm4 + vpunpckhqdq %ymm6,%ymm0,%ymm6 + vmovdqa %ymm5,%ymm0 + vpunpcklqdq %ymm7,%ymm0,%ymm5 + vpunpckhqdq %ymm7,%ymm0,%ymm7 + vmovdqa %ymm8,%ymm0 + vpunpcklqdq %ymm10,%ymm0,%ymm8 + vpunpckhqdq %ymm10,%ymm0,%ymm10 + vmovdqa %ymm9,%ymm0 + vpunpcklqdq %ymm11,%ymm0,%ymm9 + vpunpckhqdq %ymm11,%ymm0,%ymm11 + vmovdqa %ymm12,%ymm0 + vpunpcklqdq %ymm14,%ymm0,%ymm12 + vpunpckhqdq %ymm14,%ymm0,%ymm14 + vmovdqa %ymm13,%ymm0 + vpunpcklqdq %ymm15,%ymm0,%ymm13 + vpunpckhqdq %ymm15,%ymm0,%ymm15 + + # interleave 128-bit words in state n, n+4 + vmovdqa 0x00(%rsp),%ymm0 + vperm2i128 $0x20,%ymm4,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm4,%ymm0,%ymm4 + vmovdqa %ymm1,0x00(%rsp) + vmovdqa 0x20(%rsp),%ymm0 + vperm2i128 $0x20,%ymm5,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm5,%ymm0,%ymm5 + vmovdqa %ymm1,0x20(%rsp) + vmovdqa 0x40(%rsp),%ymm0 + vperm2i128 $0x20,%ymm6,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm6,%ymm0,%ymm6 + vmovdqa %ymm1,0x40(%rsp) + vmovdqa 0x60(%rsp),%ymm0 + vperm2i128 $0x20,%ymm7,%ymm0,%ymm1 + vperm2i128 $0x31,%ymm7,%ymm0,%ymm7 + vmovdqa %ymm1,0x60(%rsp) + vperm2i128 $0x20,%ymm12,%ymm8,%ymm0 + vperm2i128 $0x31,%ymm12,%ymm8,%ymm12 + vmovdqa %ymm0,%ymm8 + vperm2i128 $0x20,%ymm13,%ymm9,%ymm0 + vperm2i128 $0x31,%ymm13,%ymm9,%ymm13 + vmovdqa %ymm0,%ymm9 + vperm2i128 $0x20,%ymm14,%ymm10,%ymm0 + vperm2i128 $0x31,%ymm14,%ymm10,%ymm14 + vmovdqa %ymm0,%ymm10 + vperm2i128 $0x20,%ymm15,%ymm11,%ymm0 + vperm2i128 $0x31,%ymm15,%ymm11,%ymm15 + vmovdqa %ymm0,%ymm11 + + # xor with corresponding input, write to output + vmovdqa 0x00(%rsp),%ymm0 + vpxor 0x0000(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x0000(%rsi) + vmovdqa 0x20(%rsp),%ymm0 + vpxor 0x0080(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x0080(%rsi) + vmovdqa 0x40(%rsp),%ymm0 + vpxor 0x0040(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x0040(%rsi) + vmovdqa 0x60(%rsp),%ymm0 + vpxor 0x00c0(%rdx),%ymm0,%ymm0 + vmovdqu %ymm0,0x00c0(%rsi) + vpxor 0x0100(%rdx),%ymm4,%ymm4 + vmovdqu %ymm4,0x0100(%rsi) + vpxor 0x0180(%rdx),%ymm5,%ymm5 + vmovdqu %ymm5,0x00180(%rsi) + vpxor 0x0140(%rdx),%ymm6,%ymm6 + vmovdqu %ymm6,0x0140(%rsi) + vpxor 0x01c0(%rdx),%ymm7,%ymm7 + vmovdqu %ymm7,0x01c0(%rsi) + vpxor 0x0020(%rdx),%ymm8,%ymm8 + vmovdqu %ymm8,0x0020(%rsi) + vpxor 0x00a0(%rdx),%ymm9,%ymm9 + vmovdqu %ymm9,0x00a0(%rsi) + vpxor 0x0060(%rdx),%ymm10,%ymm10 + vmovdqu %ymm10,0x0060(%rsi) + vpxor 0x00e0(%rdx),%ymm11,%ymm11 + vmovdqu %ymm11,0x00e0(%rsi) + vpxor 0x0120(%rdx),%ymm12,%ymm12 + vmovdqu %ymm12,0x0120(%rsi) + vpxor 0x01a0(%rdx),%ymm13,%ymm13 + vmovdqu %ymm13,0x01a0(%rsi) + vpxor 0x0160(%rdx),%ymm14,%ymm14 + vmovdqu %ymm14,0x0160(%rsi) + vpxor 0x01e0(%rdx),%ymm15,%ymm15 + vmovdqu %ymm15,0x01e0(%rsi) + + vzeroupper + mov %r8,%rsp + ret +ENDPROC(chacha20_8block_xor_avx2) diff --git a/kernel/arch/x86/crypto/chacha20-ssse3-x86_64.S b/kernel/arch/x86/crypto/chacha20-ssse3-x86_64.S new file mode 100644 index 000000000..3a33124e9 --- /dev/null +++ b/kernel/arch/x86/crypto/chacha20-ssse3-x86_64.S @@ -0,0 +1,627 @@ +/* + * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions + * + * Copyright (C) 2015 Martin Willi + * + * 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. + */ + +#include <linux/linkage.h> + +.data +.align 16 + +ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003 +ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302 +CTRINC: .octa 0x00000003000000020000000100000000 + +.text + +ENTRY(chacha20_block_xor_ssse3) + # %rdi: Input state matrix, s + # %rsi: 1 data block output, o + # %rdx: 1 data block input, i + + # This function encrypts one ChaCha20 block by loading the state matrix + # in four SSE registers. It performs matrix operation on four words in + # parallel, but requireds shuffling to rearrange the words after each + # round. 8/16-bit word rotation is done with the slightly better + # performing SSSE3 byte shuffling, 7/12-bit word rotation uses + # traditional shift+OR. + + # x0..3 = s0..3 + movdqa 0x00(%rdi),%xmm0 + movdqa 0x10(%rdi),%xmm1 + movdqa 0x20(%rdi),%xmm2 + movdqa 0x30(%rdi),%xmm3 + movdqa %xmm0,%xmm8 + movdqa %xmm1,%xmm9 + movdqa %xmm2,%xmm10 + movdqa %xmm3,%xmm11 + + movdqa ROT8(%rip),%xmm4 + movdqa ROT16(%rip),%xmm5 + + mov $10,%ecx + +.Ldoubleround: + + # x0 += x1, x3 = rotl32(x3 ^ x0, 16) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm5,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 12) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm6 + pslld $12,%xmm6 + psrld $20,%xmm1 + por %xmm6,%xmm1 + + # x0 += x1, x3 = rotl32(x3 ^ x0, 8) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm4,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 7) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm7 + pslld $7,%xmm7 + psrld $25,%xmm1 + por %xmm7,%xmm1 + + # x1 = shuffle32(x1, MASK(0, 3, 2, 1)) + pshufd $0x39,%xmm1,%xmm1 + # x2 = shuffle32(x2, MASK(1, 0, 3, 2)) + pshufd $0x4e,%xmm2,%xmm2 + # x3 = shuffle32(x3, MASK(2, 1, 0, 3)) + pshufd $0x93,%xmm3,%xmm3 + + # x0 += x1, x3 = rotl32(x3 ^ x0, 16) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm5,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 12) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm6 + pslld $12,%xmm6 + psrld $20,%xmm1 + por %xmm6,%xmm1 + + # x0 += x1, x3 = rotl32(x3 ^ x0, 8) + paddd %xmm1,%xmm0 + pxor %xmm0,%xmm3 + pshufb %xmm4,%xmm3 + + # x2 += x3, x1 = rotl32(x1 ^ x2, 7) + paddd %xmm3,%xmm2 + pxor %xmm2,%xmm1 + movdqa %xmm1,%xmm7 + pslld $7,%xmm7 + psrld $25,%xmm1 + por %xmm7,%xmm1 + + # x1 = shuffle32(x1, MASK(2, 1, 0, 3)) + pshufd $0x93,%xmm1,%xmm1 + # x2 = shuffle32(x2, MASK(1, 0, 3, 2)) + pshufd $0x4e,%xmm2,%xmm2 + # x3 = shuffle32(x3, MASK(0, 3, 2, 1)) + pshufd $0x39,%xmm3,%xmm3 + + dec %ecx + jnz .Ldoubleround + + # o0 = i0 ^ (x0 + s0) + movdqu 0x00(%rdx),%xmm4 + paddd %xmm8,%xmm0 + pxor %xmm4,%xmm0 + movdqu %xmm0,0x00(%rsi) + # o1 = i1 ^ (x1 + s1) + movdqu 0x10(%rdx),%xmm5 + paddd %xmm9,%xmm1 + pxor %xmm5,%xmm1 + movdqu %xmm1,0x10(%rsi) + # o2 = i2 ^ (x2 + s2) + movdqu 0x20(%rdx),%xmm6 + paddd %xmm10,%xmm2 + pxor %xmm6,%xmm2 + movdqu %xmm2,0x20(%rsi) + # o3 = i3 ^ (x3 + s3) + movdqu 0x30(%rdx),%xmm7 + paddd %xmm11,%xmm3 + pxor %xmm7,%xmm3 + movdqu %xmm3,0x30(%rsi) + + ret +ENDPROC(chacha20_block_xor_ssse3) + +ENTRY(chacha20_4block_xor_ssse3) + # %rdi: Input state matrix, s + # %rsi: 4 data blocks output, o + # %rdx: 4 data blocks input, i + + # This function encrypts four consecutive ChaCha20 blocks by loading the + # the state matrix in SSE registers four times. As we need some scratch + # registers, we save the first four registers on the stack. The + # algorithm performs each operation on the corresponding word of each + # state matrix, hence requires no word shuffling. For final XORing step + # we transpose the matrix by interleaving 32- and then 64-bit words, + # which allows us to do XOR in SSE registers. 8/16-bit word rotation is + # done with the slightly better performing SSSE3 byte shuffling, + # 7/12-bit word rotation uses traditional shift+OR. + + mov %rsp,%r11 + sub $0x80,%rsp + and $~63,%rsp + + # x0..15[0-3] = s0..3[0..3] + movq 0x00(%rdi),%xmm1 + pshufd $0x00,%xmm1,%xmm0 + pshufd $0x55,%xmm1,%xmm1 + movq 0x08(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + movq 0x10(%rdi),%xmm5 + pshufd $0x00,%xmm5,%xmm4 + pshufd $0x55,%xmm5,%xmm5 + movq 0x18(%rdi),%xmm7 + pshufd $0x00,%xmm7,%xmm6 + pshufd $0x55,%xmm7,%xmm7 + movq 0x20(%rdi),%xmm9 + pshufd $0x00,%xmm9,%xmm8 + pshufd $0x55,%xmm9,%xmm9 + movq 0x28(%rdi),%xmm11 + pshufd $0x00,%xmm11,%xmm10 + pshufd $0x55,%xmm11,%xmm11 + movq 0x30(%rdi),%xmm13 + pshufd $0x00,%xmm13,%xmm12 + pshufd $0x55,%xmm13,%xmm13 + movq 0x38(%rdi),%xmm15 + pshufd $0x00,%xmm15,%xmm14 + pshufd $0x55,%xmm15,%xmm15 + # x0..3 on stack + movdqa %xmm0,0x00(%rsp) + movdqa %xmm1,0x10(%rsp) + movdqa %xmm2,0x20(%rsp) + movdqa %xmm3,0x30(%rsp) + + movdqa CTRINC(%rip),%xmm1 + movdqa ROT8(%rip),%xmm2 + movdqa ROT16(%rip),%xmm3 + + # x12 += counter values 0-3 + paddd %xmm1,%xmm12 + + mov $10,%ecx + +.Ldoubleround4: + # x0 += x4, x12 = rotl32(x12 ^ x0, 16) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm3,%xmm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 16) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm3,%xmm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 16) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm3,%xmm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 16) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm3,%xmm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 12) + paddd %xmm12,%xmm8 + pxor %xmm8,%xmm4 + movdqa %xmm4,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm4 + por %xmm0,%xmm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 12) + paddd %xmm13,%xmm9 + pxor %xmm9,%xmm5 + movdqa %xmm5,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm5 + por %xmm0,%xmm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 12) + paddd %xmm14,%xmm10 + pxor %xmm10,%xmm6 + movdqa %xmm6,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm6 + por %xmm0,%xmm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 12) + paddd %xmm15,%xmm11 + pxor %xmm11,%xmm7 + movdqa %xmm7,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm7 + por %xmm0,%xmm7 + + # x0 += x4, x12 = rotl32(x12 ^ x0, 8) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm2,%xmm12 + # x1 += x5, x13 = rotl32(x13 ^ x1, 8) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm2,%xmm13 + # x2 += x6, x14 = rotl32(x14 ^ x2, 8) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm2,%xmm14 + # x3 += x7, x15 = rotl32(x15 ^ x3, 8) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm2,%xmm15 + + # x8 += x12, x4 = rotl32(x4 ^ x8, 7) + paddd %xmm12,%xmm8 + pxor %xmm8,%xmm4 + movdqa %xmm4,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm4 + por %xmm0,%xmm4 + # x9 += x13, x5 = rotl32(x5 ^ x9, 7) + paddd %xmm13,%xmm9 + pxor %xmm9,%xmm5 + movdqa %xmm5,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm5 + por %xmm0,%xmm5 + # x10 += x14, x6 = rotl32(x6 ^ x10, 7) + paddd %xmm14,%xmm10 + pxor %xmm10,%xmm6 + movdqa %xmm6,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm6 + por %xmm0,%xmm6 + # x11 += x15, x7 = rotl32(x7 ^ x11, 7) + paddd %xmm15,%xmm11 + pxor %xmm11,%xmm7 + movdqa %xmm7,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm7 + por %xmm0,%xmm7 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 16) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm3,%xmm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 16) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm3,%xmm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 16) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm3,%xmm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 16) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm3,%xmm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 12) + paddd %xmm15,%xmm10 + pxor %xmm10,%xmm5 + movdqa %xmm5,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm5 + por %xmm0,%xmm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 12) + paddd %xmm12,%xmm11 + pxor %xmm11,%xmm6 + movdqa %xmm6,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm6 + por %xmm0,%xmm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 12) + paddd %xmm13,%xmm8 + pxor %xmm8,%xmm7 + movdqa %xmm7,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm7 + por %xmm0,%xmm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 12) + paddd %xmm14,%xmm9 + pxor %xmm9,%xmm4 + movdqa %xmm4,%xmm0 + pslld $12,%xmm0 + psrld $20,%xmm4 + por %xmm0,%xmm4 + + # x0 += x5, x15 = rotl32(x15 ^ x0, 8) + movdqa 0x00(%rsp),%xmm0 + paddd %xmm5,%xmm0 + movdqa %xmm0,0x00(%rsp) + pxor %xmm0,%xmm15 + pshufb %xmm2,%xmm15 + # x1 += x6, x12 = rotl32(x12 ^ x1, 8) + movdqa 0x10(%rsp),%xmm0 + paddd %xmm6,%xmm0 + movdqa %xmm0,0x10(%rsp) + pxor %xmm0,%xmm12 + pshufb %xmm2,%xmm12 + # x2 += x7, x13 = rotl32(x13 ^ x2, 8) + movdqa 0x20(%rsp),%xmm0 + paddd %xmm7,%xmm0 + movdqa %xmm0,0x20(%rsp) + pxor %xmm0,%xmm13 + pshufb %xmm2,%xmm13 + # x3 += x4, x14 = rotl32(x14 ^ x3, 8) + movdqa 0x30(%rsp),%xmm0 + paddd %xmm4,%xmm0 + movdqa %xmm0,0x30(%rsp) + pxor %xmm0,%xmm14 + pshufb %xmm2,%xmm14 + + # x10 += x15, x5 = rotl32(x5 ^ x10, 7) + paddd %xmm15,%xmm10 + pxor %xmm10,%xmm5 + movdqa %xmm5,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm5 + por %xmm0,%xmm5 + # x11 += x12, x6 = rotl32(x6 ^ x11, 7) + paddd %xmm12,%xmm11 + pxor %xmm11,%xmm6 + movdqa %xmm6,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm6 + por %xmm0,%xmm6 + # x8 += x13, x7 = rotl32(x7 ^ x8, 7) + paddd %xmm13,%xmm8 + pxor %xmm8,%xmm7 + movdqa %xmm7,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm7 + por %xmm0,%xmm7 + # x9 += x14, x4 = rotl32(x4 ^ x9, 7) + paddd %xmm14,%xmm9 + pxor %xmm9,%xmm4 + movdqa %xmm4,%xmm0 + pslld $7,%xmm0 + psrld $25,%xmm4 + por %xmm0,%xmm4 + + dec %ecx + jnz .Ldoubleround4 + + # x0[0-3] += s0[0] + # x1[0-3] += s0[1] + movq 0x00(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd 0x00(%rsp),%xmm2 + movdqa %xmm2,0x00(%rsp) + paddd 0x10(%rsp),%xmm3 + movdqa %xmm3,0x10(%rsp) + # x2[0-3] += s0[2] + # x3[0-3] += s0[3] + movq 0x08(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd 0x20(%rsp),%xmm2 + movdqa %xmm2,0x20(%rsp) + paddd 0x30(%rsp),%xmm3 + movdqa %xmm3,0x30(%rsp) + + # x4[0-3] += s1[0] + # x5[0-3] += s1[1] + movq 0x10(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm4 + paddd %xmm3,%xmm5 + # x6[0-3] += s1[2] + # x7[0-3] += s1[3] + movq 0x18(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm6 + paddd %xmm3,%xmm7 + + # x8[0-3] += s2[0] + # x9[0-3] += s2[1] + movq 0x20(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm8 + paddd %xmm3,%xmm9 + # x10[0-3] += s2[2] + # x11[0-3] += s2[3] + movq 0x28(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm10 + paddd %xmm3,%xmm11 + + # x12[0-3] += s3[0] + # x13[0-3] += s3[1] + movq 0x30(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm12 + paddd %xmm3,%xmm13 + # x14[0-3] += s3[2] + # x15[0-3] += s3[3] + movq 0x38(%rdi),%xmm3 + pshufd $0x00,%xmm3,%xmm2 + pshufd $0x55,%xmm3,%xmm3 + paddd %xmm2,%xmm14 + paddd %xmm3,%xmm15 + + # x12 += counter values 0-3 + paddd %xmm1,%xmm12 + + # interleave 32-bit words in state n, n+1 + movdqa 0x00(%rsp),%xmm0 + movdqa 0x10(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpckldq %xmm1,%xmm2 + punpckhdq %xmm1,%xmm0 + movdqa %xmm2,0x00(%rsp) + movdqa %xmm0,0x10(%rsp) + movdqa 0x20(%rsp),%xmm0 + movdqa 0x30(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpckldq %xmm1,%xmm2 + punpckhdq %xmm1,%xmm0 + movdqa %xmm2,0x20(%rsp) + movdqa %xmm0,0x30(%rsp) + movdqa %xmm4,%xmm0 + punpckldq %xmm5,%xmm4 + punpckhdq %xmm5,%xmm0 + movdqa %xmm0,%xmm5 + movdqa %xmm6,%xmm0 + punpckldq %xmm7,%xmm6 + punpckhdq %xmm7,%xmm0 + movdqa %xmm0,%xmm7 + movdqa %xmm8,%xmm0 + punpckldq %xmm9,%xmm8 + punpckhdq %xmm9,%xmm0 + movdqa %xmm0,%xmm9 + movdqa %xmm10,%xmm0 + punpckldq %xmm11,%xmm10 + punpckhdq %xmm11,%xmm0 + movdqa %xmm0,%xmm11 + movdqa %xmm12,%xmm0 + punpckldq %xmm13,%xmm12 + punpckhdq %xmm13,%xmm0 + movdqa %xmm0,%xmm13 + movdqa %xmm14,%xmm0 + punpckldq %xmm15,%xmm14 + punpckhdq %xmm15,%xmm0 + movdqa %xmm0,%xmm15 + + # interleave 64-bit words in state n, n+2 + movdqa 0x00(%rsp),%xmm0 + movdqa 0x20(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpcklqdq %xmm1,%xmm2 + punpckhqdq %xmm1,%xmm0 + movdqa %xmm2,0x00(%rsp) + movdqa %xmm0,0x20(%rsp) + movdqa 0x10(%rsp),%xmm0 + movdqa 0x30(%rsp),%xmm1 + movdqa %xmm0,%xmm2 + punpcklqdq %xmm1,%xmm2 + punpckhqdq %xmm1,%xmm0 + movdqa %xmm2,0x10(%rsp) + movdqa %xmm0,0x30(%rsp) + movdqa %xmm4,%xmm0 + punpcklqdq %xmm6,%xmm4 + punpckhqdq %xmm6,%xmm0 + movdqa %xmm0,%xmm6 + movdqa %xmm5,%xmm0 + punpcklqdq %xmm7,%xmm5 + punpckhqdq %xmm7,%xmm0 + movdqa %xmm0,%xmm7 + movdqa %xmm8,%xmm0 + punpcklqdq %xmm10,%xmm8 + punpckhqdq %xmm10,%xmm0 + movdqa %xmm0,%xmm10 + movdqa %xmm9,%xmm0 + punpcklqdq %xmm11,%xmm9 + punpckhqdq %xmm11,%xmm0 + movdqa %xmm0,%xmm11 + movdqa %xmm12,%xmm0 + punpcklqdq %xmm14,%xmm12 + punpckhqdq %xmm14,%xmm0 + movdqa %xmm0,%xmm14 + movdqa %xmm13,%xmm0 + punpcklqdq %xmm15,%xmm13 + punpckhqdq %xmm15,%xmm0 + movdqa %xmm0,%xmm15 + + # xor with corresponding input, write to output + movdqa 0x00(%rsp),%xmm0 + movdqu 0x00(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0x00(%rsi) + movdqa 0x10(%rsp),%xmm0 + movdqu 0x80(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0x80(%rsi) + movdqa 0x20(%rsp),%xmm0 + movdqu 0x40(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0x40(%rsi) + movdqa 0x30(%rsp),%xmm0 + movdqu 0xc0(%rdx),%xmm1 + pxor %xmm1,%xmm0 + movdqu %xmm0,0xc0(%rsi) + movdqu 0x10(%rdx),%xmm1 + pxor %xmm1,%xmm4 + movdqu %xmm4,0x10(%rsi) + movdqu 0x90(%rdx),%xmm1 + pxor %xmm1,%xmm5 + movdqu %xmm5,0x90(%rsi) + movdqu 0x50(%rdx),%xmm1 + pxor %xmm1,%xmm6 + movdqu %xmm6,0x50(%rsi) + movdqu 0xd0(%rdx),%xmm1 + pxor %xmm1,%xmm7 + movdqu %xmm7,0xd0(%rsi) + movdqu 0x20(%rdx),%xmm1 + pxor %xmm1,%xmm8 + movdqu %xmm8,0x20(%rsi) + movdqu 0xa0(%rdx),%xmm1 + pxor %xmm1,%xmm9 + movdqu %xmm9,0xa0(%rsi) + movdqu 0x60(%rdx),%xmm1 + pxor %xmm1,%xmm10 + movdqu %xmm10,0x60(%rsi) + movdqu 0xe0(%rdx),%xmm1 + pxor %xmm1,%xmm11 + movdqu %xmm11,0xe0(%rsi) + movdqu 0x30(%rdx),%xmm1 + pxor %xmm1,%xmm12 + movdqu %xmm12,0x30(%rsi) + movdqu 0xb0(%rdx),%xmm1 + pxor %xmm1,%xmm13 + movdqu %xmm13,0xb0(%rsi) + movdqu 0x70(%rdx),%xmm1 + pxor %xmm1,%xmm14 + movdqu %xmm14,0x70(%rsi) + movdqu 0xf0(%rdx),%xmm1 + pxor %xmm1,%xmm15 + movdqu %xmm15,0xf0(%rsi) + + mov %r11,%rsp + ret +ENDPROC(chacha20_4block_xor_ssse3) diff --git a/kernel/arch/x86/crypto/chacha20_glue.c b/kernel/arch/x86/crypto/chacha20_glue.c new file mode 100644 index 000000000..722bacea0 --- /dev/null +++ b/kernel/arch/x86/crypto/chacha20_glue.c @@ -0,0 +1,150 @@ +/* + * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code + * + * Copyright (C) 2015 Martin Willi + * + * 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. + */ + +#include <crypto/algapi.h> +#include <crypto/chacha20.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/fpu/api.h> +#include <asm/simd.h> + +#define CHACHA20_STATE_ALIGN 16 + +asmlinkage void chacha20_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src); +asmlinkage void chacha20_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src); +#ifdef CONFIG_AS_AVX2 +asmlinkage void chacha20_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src); +static bool chacha20_use_avx2; +#endif + +static void chacha20_dosimd(u32 *state, u8 *dst, const u8 *src, + unsigned int bytes) +{ + u8 buf[CHACHA20_BLOCK_SIZE]; + +#ifdef CONFIG_AS_AVX2 + if (chacha20_use_avx2) { + while (bytes >= CHACHA20_BLOCK_SIZE * 8) { + chacha20_8block_xor_avx2(state, dst, src); + bytes -= CHACHA20_BLOCK_SIZE * 8; + src += CHACHA20_BLOCK_SIZE * 8; + dst += CHACHA20_BLOCK_SIZE * 8; + state[12] += 8; + } + } +#endif + while (bytes >= CHACHA20_BLOCK_SIZE * 4) { + chacha20_4block_xor_ssse3(state, dst, src); + bytes -= CHACHA20_BLOCK_SIZE * 4; + src += CHACHA20_BLOCK_SIZE * 4; + dst += CHACHA20_BLOCK_SIZE * 4; + state[12] += 4; + } + while (bytes >= CHACHA20_BLOCK_SIZE) { + chacha20_block_xor_ssse3(state, dst, src); + bytes -= CHACHA20_BLOCK_SIZE; + src += CHACHA20_BLOCK_SIZE; + dst += CHACHA20_BLOCK_SIZE; + state[12]++; + } + if (bytes) { + memcpy(buf, src, bytes); + chacha20_block_xor_ssse3(state, buf, buf); + memcpy(dst, buf, bytes); + } +} + +static int chacha20_simd(struct blkcipher_desc *desc, struct scatterlist *dst, + struct scatterlist *src, unsigned int nbytes) +{ + u32 *state, state_buf[16 + (CHACHA20_STATE_ALIGN / sizeof(u32)) - 1]; + struct blkcipher_walk walk; + int err; + + if (!may_use_simd()) + return crypto_chacha20_crypt(desc, dst, src, nbytes); + + state = (u32 *)roundup((uintptr_t)state_buf, CHACHA20_STATE_ALIGN); + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt_block(desc, &walk, CHACHA20_BLOCK_SIZE); + + crypto_chacha20_init(state, crypto_blkcipher_ctx(desc->tfm), walk.iv); + + kernel_fpu_begin(); + + while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); + err = blkcipher_walk_done(desc, &walk, + walk.nbytes % CHACHA20_BLOCK_SIZE); + } + + if (walk.nbytes) { + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes); + err = blkcipher_walk_done(desc, &walk, 0); + } + + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg alg = { + .cra_name = "chacha20", + .cra_driver_name = "chacha20-simd", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = 1, + .cra_type = &crypto_blkcipher_type, + .cra_ctxsize = sizeof(struct chacha20_ctx), + .cra_alignmask = sizeof(u32) - 1, + .cra_module = THIS_MODULE, + .cra_u = { + .blkcipher = { + .min_keysize = CHACHA20_KEY_SIZE, + .max_keysize = CHACHA20_KEY_SIZE, + .ivsize = CHACHA20_IV_SIZE, + .geniv = "seqiv", + .setkey = crypto_chacha20_setkey, + .encrypt = chacha20_simd, + .decrypt = chacha20_simd, + }, + }, +}; + +static int __init chacha20_simd_mod_init(void) +{ + if (!cpu_has_ssse3) + return -ENODEV; + +#ifdef CONFIG_AS_AVX2 + chacha20_use_avx2 = cpu_has_avx && cpu_has_avx2 && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); +#endif + return crypto_register_alg(&alg); +} + +static void __exit chacha20_simd_mod_fini(void) +{ + crypto_unregister_alg(&alg); +} + +module_init(chacha20_simd_mod_init); +module_exit(chacha20_simd_mod_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_DESCRIPTION("chacha20 cipher algorithm, SIMD accelerated"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-simd"); diff --git a/kernel/arch/x86/crypto/crc32-pclmul_glue.c b/kernel/arch/x86/crypto/crc32-pclmul_glue.c index 1937fc1d8..07d2c6c86 100644 --- a/kernel/arch/x86/crypto/crc32-pclmul_glue.c +++ b/kernel/arch/x86/crypto/crc32-pclmul_glue.c @@ -35,7 +35,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 diff --git a/kernel/arch/x86/crypto/crc32c-intel_glue.c b/kernel/arch/x86/crypto/crc32c-intel_glue.c index 28640c3d6..81a595d75 100644 --- a/kernel/arch/x86/crypto/crc32c-intel_glue.c +++ b/kernel/arch/x86/crypto/crc32c-intel_glue.c @@ -32,8 +32,7 @@ #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #define CHKSUM_BLOCK_SIZE 1 #define CHKSUM_DIGEST_SIZE 4 diff --git a/kernel/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/kernel/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 225be06ed..4fe27e074 100644 --- a/kernel/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/kernel/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -330,7 +330,7 @@ ENDPROC(crc_pcl) ## PCLMULQDQ tables ## Table is 128 entries x 2 words (8 bytes) each ################################################################ -.section .rotata, "a", %progbits +.section .rodata, "a", %progbits .align 8 K_table: .long 0x493c7d27, 0x00000001 diff --git a/kernel/arch/x86/crypto/crct10dif-pclmul_glue.c b/kernel/arch/x86/crypto/crct10dif-pclmul_glue.c index b6c67bf30..a3fcfc97a 100644 --- a/kernel/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/kernel/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -29,7 +29,7 @@ #include <linux/init.h> #include <linux/string.h> #include <linux/kernel.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/cpufeature.h> #include <asm/cpu_device_id.h> diff --git a/kernel/arch/x86/crypto/fpu.c b/kernel/arch/x86/crypto/fpu.c index f368ba261..e7d679e2a 100644 --- a/kernel/arch/x86/crypto/fpu.c +++ b/kernel/arch/x86/crypto/fpu.c @@ -18,7 +18,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/crypto.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> struct crypto_fpu_ctx { struct crypto_blkcipher *child; @@ -156,7 +156,7 @@ int __init crypto_fpu_init(void) return crypto_register_template(&crypto_fpu_tmpl); } -void __exit crypto_fpu_exit(void) +void crypto_fpu_exit(void) { crypto_unregister_template(&crypto_fpu_tmpl); } diff --git a/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c b/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c index daf8d2b9a..440df0c7a 100644 --- a/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/kernel/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -19,7 +19,7 @@ #include <crypto/cryptd.h> #include <crypto/gf128mul.h> #include <crypto/internal/hash.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/cpu_device_id.h> #define GHASH_BLOCK_SIZE 16 diff --git a/kernel/arch/x86/crypto/poly1305-avx2-x86_64.S b/kernel/arch/x86/crypto/poly1305-avx2-x86_64.S new file mode 100644 index 000000000..eff2f414e --- /dev/null +++ b/kernel/arch/x86/crypto/poly1305-avx2-x86_64.S @@ -0,0 +1,386 @@ +/* + * Poly1305 authenticator algorithm, RFC7539, x64 AVX2 functions + * + * Copyright (C) 2015 Martin Willi + * + * 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. + */ + +#include <linux/linkage.h> + +.data +.align 32 + +ANMASK: .octa 0x0000000003ffffff0000000003ffffff + .octa 0x0000000003ffffff0000000003ffffff +ORMASK: .octa 0x00000000010000000000000001000000 + .octa 0x00000000010000000000000001000000 + +.text + +#define h0 0x00(%rdi) +#define h1 0x04(%rdi) +#define h2 0x08(%rdi) +#define h3 0x0c(%rdi) +#define h4 0x10(%rdi) +#define r0 0x00(%rdx) +#define r1 0x04(%rdx) +#define r2 0x08(%rdx) +#define r3 0x0c(%rdx) +#define r4 0x10(%rdx) +#define u0 0x00(%r8) +#define u1 0x04(%r8) +#define u2 0x08(%r8) +#define u3 0x0c(%r8) +#define u4 0x10(%r8) +#define w0 0x14(%r8) +#define w1 0x18(%r8) +#define w2 0x1c(%r8) +#define w3 0x20(%r8) +#define w4 0x24(%r8) +#define y0 0x28(%r8) +#define y1 0x2c(%r8) +#define y2 0x30(%r8) +#define y3 0x34(%r8) +#define y4 0x38(%r8) +#define m %rsi +#define hc0 %ymm0 +#define hc1 %ymm1 +#define hc2 %ymm2 +#define hc3 %ymm3 +#define hc4 %ymm4 +#define hc0x %xmm0 +#define hc1x %xmm1 +#define hc2x %xmm2 +#define hc3x %xmm3 +#define hc4x %xmm4 +#define t1 %ymm5 +#define t2 %ymm6 +#define t1x %xmm5 +#define t2x %xmm6 +#define ruwy0 %ymm7 +#define ruwy1 %ymm8 +#define ruwy2 %ymm9 +#define ruwy3 %ymm10 +#define ruwy4 %ymm11 +#define ruwy0x %xmm7 +#define ruwy1x %xmm8 +#define ruwy2x %xmm9 +#define ruwy3x %xmm10 +#define ruwy4x %xmm11 +#define svxz1 %ymm12 +#define svxz2 %ymm13 +#define svxz3 %ymm14 +#define svxz4 %ymm15 +#define d0 %r9 +#define d1 %r10 +#define d2 %r11 +#define d3 %r12 +#define d4 %r13 + +ENTRY(poly1305_4block_avx2) + # %rdi: Accumulator h[5] + # %rsi: 64 byte input block m + # %rdx: Poly1305 key r[5] + # %rcx: Quadblock count + # %r8: Poly1305 derived key r^2 u[5], r^3 w[5], r^4 y[5], + + # This four-block variant uses loop unrolled block processing. It + # requires 4 Poly1305 keys: r, r^2, r^3 and r^4: + # h = (h + m) * r => h = (h + m1) * r^4 + m2 * r^3 + m3 * r^2 + m4 * r + + vzeroupper + push %rbx + push %r12 + push %r13 + + # combine r0,u0,w0,y0 + vmovd y0,ruwy0x + vmovd w0,t1x + vpunpcklqdq t1,ruwy0,ruwy0 + vmovd u0,t1x + vmovd r0,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy0,ruwy0 + + # combine r1,u1,w1,y1 and s1=r1*5,v1=u1*5,x1=w1*5,z1=y1*5 + vmovd y1,ruwy1x + vmovd w1,t1x + vpunpcklqdq t1,ruwy1,ruwy1 + vmovd u1,t1x + vmovd r1,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy1,ruwy1 + vpslld $2,ruwy1,svxz1 + vpaddd ruwy1,svxz1,svxz1 + + # combine r2,u2,w2,y2 and s2=r2*5,v2=u2*5,x2=w2*5,z2=y2*5 + vmovd y2,ruwy2x + vmovd w2,t1x + vpunpcklqdq t1,ruwy2,ruwy2 + vmovd u2,t1x + vmovd r2,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy2,ruwy2 + vpslld $2,ruwy2,svxz2 + vpaddd ruwy2,svxz2,svxz2 + + # combine r3,u3,w3,y3 and s3=r3*5,v3=u3*5,x3=w3*5,z3=y3*5 + vmovd y3,ruwy3x + vmovd w3,t1x + vpunpcklqdq t1,ruwy3,ruwy3 + vmovd u3,t1x + vmovd r3,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy3,ruwy3 + vpslld $2,ruwy3,svxz3 + vpaddd ruwy3,svxz3,svxz3 + + # combine r4,u4,w4,y4 and s4=r4*5,v4=u4*5,x4=w4*5,z4=y4*5 + vmovd y4,ruwy4x + vmovd w4,t1x + vpunpcklqdq t1,ruwy4,ruwy4 + vmovd u4,t1x + vmovd r4,t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,ruwy4,ruwy4 + vpslld $2,ruwy4,svxz4 + vpaddd ruwy4,svxz4,svxz4 + +.Ldoblock4: + # hc0 = [m[48-51] & 0x3ffffff, m[32-35] & 0x3ffffff, + # m[16-19] & 0x3ffffff, m[ 0- 3] & 0x3ffffff + h0] + vmovd 0x00(m),hc0x + vmovd 0x10(m),t1x + vpunpcklqdq t1,hc0,hc0 + vmovd 0x20(m),t1x + vmovd 0x30(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc0,hc0 + vpand ANMASK(%rip),hc0,hc0 + vmovd h0,t1x + vpaddd t1,hc0,hc0 + # hc1 = [(m[51-54] >> 2) & 0x3ffffff, (m[35-38] >> 2) & 0x3ffffff, + # (m[19-22] >> 2) & 0x3ffffff, (m[ 3- 6] >> 2) & 0x3ffffff + h1] + vmovd 0x03(m),hc1x + vmovd 0x13(m),t1x + vpunpcklqdq t1,hc1,hc1 + vmovd 0x23(m),t1x + vmovd 0x33(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc1,hc1 + vpsrld $2,hc1,hc1 + vpand ANMASK(%rip),hc1,hc1 + vmovd h1,t1x + vpaddd t1,hc1,hc1 + # hc2 = [(m[54-57] >> 4) & 0x3ffffff, (m[38-41] >> 4) & 0x3ffffff, + # (m[22-25] >> 4) & 0x3ffffff, (m[ 6- 9] >> 4) & 0x3ffffff + h2] + vmovd 0x06(m),hc2x + vmovd 0x16(m),t1x + vpunpcklqdq t1,hc2,hc2 + vmovd 0x26(m),t1x + vmovd 0x36(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc2,hc2 + vpsrld $4,hc2,hc2 + vpand ANMASK(%rip),hc2,hc2 + vmovd h2,t1x + vpaddd t1,hc2,hc2 + # hc3 = [(m[57-60] >> 6) & 0x3ffffff, (m[41-44] >> 6) & 0x3ffffff, + # (m[25-28] >> 6) & 0x3ffffff, (m[ 9-12] >> 6) & 0x3ffffff + h3] + vmovd 0x09(m),hc3x + vmovd 0x19(m),t1x + vpunpcklqdq t1,hc3,hc3 + vmovd 0x29(m),t1x + vmovd 0x39(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc3,hc3 + vpsrld $6,hc3,hc3 + vpand ANMASK(%rip),hc3,hc3 + vmovd h3,t1x + vpaddd t1,hc3,hc3 + # hc4 = [(m[60-63] >> 8) | (1<<24), (m[44-47] >> 8) | (1<<24), + # (m[28-31] >> 8) | (1<<24), (m[12-15] >> 8) | (1<<24) + h4] + vmovd 0x0c(m),hc4x + vmovd 0x1c(m),t1x + vpunpcklqdq t1,hc4,hc4 + vmovd 0x2c(m),t1x + vmovd 0x3c(m),t2x + vpunpcklqdq t2,t1,t1 + vperm2i128 $0x20,t1,hc4,hc4 + vpsrld $8,hc4,hc4 + vpor ORMASK(%rip),hc4,hc4 + vmovd h4,t1x + vpaddd t1,hc4,hc4 + + # t1 = [ hc0[3] * r0, hc0[2] * u0, hc0[1] * w0, hc0[0] * y0 ] + vpmuludq hc0,ruwy0,t1 + # t1 += [ hc1[3] * s4, hc1[2] * v4, hc1[1] * x4, hc1[0] * z4 ] + vpmuludq hc1,svxz4,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * s3, hc2[2] * v3, hc2[1] * x3, hc2[0] * z3 ] + vpmuludq hc2,svxz3,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * s2, hc3[2] * v2, hc3[1] * x2, hc3[0] * z2 ] + vpmuludq hc3,svxz2,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s1, hc4[2] * v1, hc4[1] * x1, hc4[0] * z1 ] + vpmuludq hc4,svxz1,t2 + vpaddq t2,t1,t1 + # d0 = t1[0] + t1[1] + t[2] + t[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d0 + + # t1 = [ hc0[3] * r1, hc0[2] * u1,hc0[1] * w1, hc0[0] * y1 ] + vpmuludq hc0,ruwy1,t1 + # t1 += [ hc1[3] * r0, hc1[2] * u0, hc1[1] * w0, hc1[0] * y0 ] + vpmuludq hc1,ruwy0,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * s4, hc2[2] * v4, hc2[1] * x4, hc2[0] * z4 ] + vpmuludq hc2,svxz4,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * s3, hc3[2] * v3, hc3[1] * x3, hc3[0] * z3 ] + vpmuludq hc3,svxz3,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s2, hc4[2] * v2, hc4[1] * x2, hc4[0] * z2 ] + vpmuludq hc4,svxz2,t2 + vpaddq t2,t1,t1 + # d1 = t1[0] + t1[1] + t1[3] + t1[4] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d1 + + # t1 = [ hc0[3] * r2, hc0[2] * u2, hc0[1] * w2, hc0[0] * y2 ] + vpmuludq hc0,ruwy2,t1 + # t1 += [ hc1[3] * r1, hc1[2] * u1, hc1[1] * w1, hc1[0] * y1 ] + vpmuludq hc1,ruwy1,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * r0, hc2[2] * u0, hc2[1] * w0, hc2[0] * y0 ] + vpmuludq hc2,ruwy0,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * s4, hc3[2] * v4, hc3[1] * x4, hc3[0] * z4 ] + vpmuludq hc3,svxz4,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s3, hc4[2] * v3, hc4[1] * x3, hc4[0] * z3 ] + vpmuludq hc4,svxz3,t2 + vpaddq t2,t1,t1 + # d2 = t1[0] + t1[1] + t1[2] + t1[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d2 + + # t1 = [ hc0[3] * r3, hc0[2] * u3, hc0[1] * w3, hc0[0] * y3 ] + vpmuludq hc0,ruwy3,t1 + # t1 += [ hc1[3] * r2, hc1[2] * u2, hc1[1] * w2, hc1[0] * y2 ] + vpmuludq hc1,ruwy2,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * r1, hc2[2] * u1, hc2[1] * w1, hc2[0] * y1 ] + vpmuludq hc2,ruwy1,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * r0, hc3[2] * u0, hc3[1] * w0, hc3[0] * y0 ] + vpmuludq hc3,ruwy0,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * s4, hc4[2] * v4, hc4[1] * x4, hc4[0] * z4 ] + vpmuludq hc4,svxz4,t2 + vpaddq t2,t1,t1 + # d3 = t1[0] + t1[1] + t1[2] + t1[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d3 + + # t1 = [ hc0[3] * r4, hc0[2] * u4, hc0[1] * w4, hc0[0] * y4 ] + vpmuludq hc0,ruwy4,t1 + # t1 += [ hc1[3] * r3, hc1[2] * u3, hc1[1] * w3, hc1[0] * y3 ] + vpmuludq hc1,ruwy3,t2 + vpaddq t2,t1,t1 + # t1 += [ hc2[3] * r2, hc2[2] * u2, hc2[1] * w2, hc2[0] * y2 ] + vpmuludq hc2,ruwy2,t2 + vpaddq t2,t1,t1 + # t1 += [ hc3[3] * r1, hc3[2] * u1, hc3[1] * w1, hc3[0] * y1 ] + vpmuludq hc3,ruwy1,t2 + vpaddq t2,t1,t1 + # t1 += [ hc4[3] * r0, hc4[2] * u0, hc4[1] * w0, hc4[0] * y0 ] + vpmuludq hc4,ruwy0,t2 + vpaddq t2,t1,t1 + # d4 = t1[0] + t1[1] + t1[2] + t1[3] + vpermq $0xee,t1,t2 + vpaddq t2,t1,t1 + vpsrldq $8,t1,t2 + vpaddq t2,t1,t1 + vmovq t1x,d4 + + # d1 += d0 >> 26 + mov d0,%rax + shr $26,%rax + add %rax,d1 + # h0 = d0 & 0x3ffffff + mov d0,%rbx + and $0x3ffffff,%ebx + + # d2 += d1 >> 26 + mov d1,%rax + shr $26,%rax + add %rax,d2 + # h1 = d1 & 0x3ffffff + mov d1,%rax + and $0x3ffffff,%eax + mov %eax,h1 + + # d3 += d2 >> 26 + mov d2,%rax + shr $26,%rax + add %rax,d3 + # h2 = d2 & 0x3ffffff + mov d2,%rax + and $0x3ffffff,%eax + mov %eax,h2 + + # d4 += d3 >> 26 + mov d3,%rax + shr $26,%rax + add %rax,d4 + # h3 = d3 & 0x3ffffff + mov d3,%rax + and $0x3ffffff,%eax + mov %eax,h3 + + # h0 += (d4 >> 26) * 5 + mov d4,%rax + shr $26,%rax + lea (%eax,%eax,4),%eax + add %eax,%ebx + # h4 = d4 & 0x3ffffff + mov d4,%rax + and $0x3ffffff,%eax + mov %eax,h4 + + # h1 += h0 >> 26 + mov %ebx,%eax + shr $26,%eax + add %eax,h1 + # h0 = h0 & 0x3ffffff + andl $0x3ffffff,%ebx + mov %ebx,h0 + + add $0x40,m + dec %rcx + jnz .Ldoblock4 + + vzeroupper + pop %r13 + pop %r12 + pop %rbx + ret +ENDPROC(poly1305_4block_avx2) diff --git a/kernel/arch/x86/crypto/poly1305-sse2-x86_64.S b/kernel/arch/x86/crypto/poly1305-sse2-x86_64.S new file mode 100644 index 000000000..338c74805 --- /dev/null +++ b/kernel/arch/x86/crypto/poly1305-sse2-x86_64.S @@ -0,0 +1,582 @@ +/* + * Poly1305 authenticator algorithm, RFC7539, x64 SSE2 functions + * + * Copyright (C) 2015 Martin Willi + * + * 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. + */ + +#include <linux/linkage.h> + +.data +.align 16 + +ANMASK: .octa 0x0000000003ffffff0000000003ffffff +ORMASK: .octa 0x00000000010000000000000001000000 + +.text + +#define h0 0x00(%rdi) +#define h1 0x04(%rdi) +#define h2 0x08(%rdi) +#define h3 0x0c(%rdi) +#define h4 0x10(%rdi) +#define r0 0x00(%rdx) +#define r1 0x04(%rdx) +#define r2 0x08(%rdx) +#define r3 0x0c(%rdx) +#define r4 0x10(%rdx) +#define s1 0x00(%rsp) +#define s2 0x04(%rsp) +#define s3 0x08(%rsp) +#define s4 0x0c(%rsp) +#define m %rsi +#define h01 %xmm0 +#define h23 %xmm1 +#define h44 %xmm2 +#define t1 %xmm3 +#define t2 %xmm4 +#define t3 %xmm5 +#define t4 %xmm6 +#define mask %xmm7 +#define d0 %r8 +#define d1 %r9 +#define d2 %r10 +#define d3 %r11 +#define d4 %r12 + +ENTRY(poly1305_block_sse2) + # %rdi: Accumulator h[5] + # %rsi: 16 byte input block m + # %rdx: Poly1305 key r[5] + # %rcx: Block count + + # This single block variant tries to improve performance by doing two + # multiplications in parallel using SSE instructions. There is quite + # some quardword packing involved, hence the speedup is marginal. + + push %rbx + push %r12 + sub $0x10,%rsp + + # s1..s4 = r1..r4 * 5 + mov r1,%eax + lea (%eax,%eax,4),%eax + mov %eax,s1 + mov r2,%eax + lea (%eax,%eax,4),%eax + mov %eax,s2 + mov r3,%eax + lea (%eax,%eax,4),%eax + mov %eax,s3 + mov r4,%eax + lea (%eax,%eax,4),%eax + mov %eax,s4 + + movdqa ANMASK(%rip),mask + +.Ldoblock: + # h01 = [0, h1, 0, h0] + # h23 = [0, h3, 0, h2] + # h44 = [0, h4, 0, h4] + movd h0,h01 + movd h1,t1 + movd h2,h23 + movd h3,t2 + movd h4,h44 + punpcklqdq t1,h01 + punpcklqdq t2,h23 + punpcklqdq h44,h44 + + # h01 += [ (m[3-6] >> 2) & 0x3ffffff, m[0-3] & 0x3ffffff ] + movd 0x00(m),t1 + movd 0x03(m),t2 + psrld $2,t2 + punpcklqdq t2,t1 + pand mask,t1 + paddd t1,h01 + # h23 += [ (m[9-12] >> 6) & 0x3ffffff, (m[6-9] >> 4) & 0x3ffffff ] + movd 0x06(m),t1 + movd 0x09(m),t2 + psrld $4,t1 + psrld $6,t2 + punpcklqdq t2,t1 + pand mask,t1 + paddd t1,h23 + # h44 += [ (m[12-15] >> 8) | (1 << 24), (m[12-15] >> 8) | (1 << 24) ] + mov 0x0c(m),%eax + shr $8,%eax + or $0x01000000,%eax + movd %eax,t1 + pshufd $0xc4,t1,t1 + paddd t1,h44 + + # t1[0] = h0 * r0 + h2 * s3 + # t1[1] = h1 * s4 + h3 * s2 + movd r0,t1 + movd s4,t2 + punpcklqdq t2,t1 + pmuludq h01,t1 + movd s3,t2 + movd s2,t3 + punpcklqdq t3,t2 + pmuludq h23,t2 + paddq t2,t1 + # t2[0] = h0 * r1 + h2 * s4 + # t2[1] = h1 * r0 + h3 * s3 + movd r1,t2 + movd r0,t3 + punpcklqdq t3,t2 + pmuludq h01,t2 + movd s4,t3 + movd s3,t4 + punpcklqdq t4,t3 + pmuludq h23,t3 + paddq t3,t2 + # t3[0] = h4 * s1 + # t3[1] = h4 * s2 + movd s1,t3 + movd s2,t4 + punpcklqdq t4,t3 + pmuludq h44,t3 + # d0 = t1[0] + t1[1] + t3[0] + # d1 = t2[0] + t2[1] + t3[1] + movdqa t1,t4 + punpcklqdq t2,t4 + punpckhqdq t2,t1 + paddq t4,t1 + paddq t3,t1 + movq t1,d0 + psrldq $8,t1 + movq t1,d1 + + # t1[0] = h0 * r2 + h2 * r0 + # t1[1] = h1 * r1 + h3 * s4 + movd r2,t1 + movd r1,t2 + punpcklqdq t2,t1 + pmuludq h01,t1 + movd r0,t2 + movd s4,t3 + punpcklqdq t3,t2 + pmuludq h23,t2 + paddq t2,t1 + # t2[0] = h0 * r3 + h2 * r1 + # t2[1] = h1 * r2 + h3 * r0 + movd r3,t2 + movd r2,t3 + punpcklqdq t3,t2 + pmuludq h01,t2 + movd r1,t3 + movd r0,t4 + punpcklqdq t4,t3 + pmuludq h23,t3 + paddq t3,t2 + # t3[0] = h4 * s3 + # t3[1] = h4 * s4 + movd s3,t3 + movd s4,t4 + punpcklqdq t4,t3 + pmuludq h44,t3 + # d2 = t1[0] + t1[1] + t3[0] + # d3 = t2[0] + t2[1] + t3[1] + movdqa t1,t4 + punpcklqdq t2,t4 + punpckhqdq t2,t1 + paddq t4,t1 + paddq t3,t1 + movq t1,d2 + psrldq $8,t1 + movq t1,d3 + + # t1[0] = h0 * r4 + h2 * r2 + # t1[1] = h1 * r3 + h3 * r1 + movd r4,t1 + movd r3,t2 + punpcklqdq t2,t1 + pmuludq h01,t1 + movd r2,t2 + movd r1,t3 + punpcklqdq t3,t2 + pmuludq h23,t2 + paddq t2,t1 + # t3[0] = h4 * r0 + movd r0,t3 + pmuludq h44,t3 + # d4 = t1[0] + t1[1] + t3[0] + movdqa t1,t4 + psrldq $8,t4 + paddq t4,t1 + paddq t3,t1 + movq t1,d4 + + # d1 += d0 >> 26 + mov d0,%rax + shr $26,%rax + add %rax,d1 + # h0 = d0 & 0x3ffffff + mov d0,%rbx + and $0x3ffffff,%ebx + + # d2 += d1 >> 26 + mov d1,%rax + shr $26,%rax + add %rax,d2 + # h1 = d1 & 0x3ffffff + mov d1,%rax + and $0x3ffffff,%eax + mov %eax,h1 + + # d3 += d2 >> 26 + mov d2,%rax + shr $26,%rax + add %rax,d3 + # h2 = d2 & 0x3ffffff + mov d2,%rax + and $0x3ffffff,%eax + mov %eax,h2 + + # d4 += d3 >> 26 + mov d3,%rax + shr $26,%rax + add %rax,d4 + # h3 = d3 & 0x3ffffff + mov d3,%rax + and $0x3ffffff,%eax + mov %eax,h3 + + # h0 += (d4 >> 26) * 5 + mov d4,%rax + shr $26,%rax + lea (%eax,%eax,4),%eax + add %eax,%ebx + # h4 = d4 & 0x3ffffff + mov d4,%rax + and $0x3ffffff,%eax + mov %eax,h4 + + # h1 += h0 >> 26 + mov %ebx,%eax + shr $26,%eax + add %eax,h1 + # h0 = h0 & 0x3ffffff + andl $0x3ffffff,%ebx + mov %ebx,h0 + + add $0x10,m + dec %rcx + jnz .Ldoblock + + add $0x10,%rsp + pop %r12 + pop %rbx + ret +ENDPROC(poly1305_block_sse2) + + +#define u0 0x00(%r8) +#define u1 0x04(%r8) +#define u2 0x08(%r8) +#define u3 0x0c(%r8) +#define u4 0x10(%r8) +#define hc0 %xmm0 +#define hc1 %xmm1 +#define hc2 %xmm2 +#define hc3 %xmm5 +#define hc4 %xmm6 +#define ru0 %xmm7 +#define ru1 %xmm8 +#define ru2 %xmm9 +#define ru3 %xmm10 +#define ru4 %xmm11 +#define sv1 %xmm12 +#define sv2 %xmm13 +#define sv3 %xmm14 +#define sv4 %xmm15 +#undef d0 +#define d0 %r13 + +ENTRY(poly1305_2block_sse2) + # %rdi: Accumulator h[5] + # %rsi: 16 byte input block m + # %rdx: Poly1305 key r[5] + # %rcx: Doubleblock count + # %r8: Poly1305 derived key r^2 u[5] + + # This two-block variant further improves performance by using loop + # unrolled block processing. This is more straight forward and does + # less byte shuffling, but requires a second Poly1305 key r^2: + # h = (h + m) * r => h = (h + m1) * r^2 + m2 * r + + push %rbx + push %r12 + push %r13 + + # combine r0,u0 + movd u0,ru0 + movd r0,t1 + punpcklqdq t1,ru0 + + # combine r1,u1 and s1=r1*5,v1=u1*5 + movd u1,ru1 + movd r1,t1 + punpcklqdq t1,ru1 + movdqa ru1,sv1 + pslld $2,sv1 + paddd ru1,sv1 + + # combine r2,u2 and s2=r2*5,v2=u2*5 + movd u2,ru2 + movd r2,t1 + punpcklqdq t1,ru2 + movdqa ru2,sv2 + pslld $2,sv2 + paddd ru2,sv2 + + # combine r3,u3 and s3=r3*5,v3=u3*5 + movd u3,ru3 + movd r3,t1 + punpcklqdq t1,ru3 + movdqa ru3,sv3 + pslld $2,sv3 + paddd ru3,sv3 + + # combine r4,u4 and s4=r4*5,v4=u4*5 + movd u4,ru4 + movd r4,t1 + punpcklqdq t1,ru4 + movdqa ru4,sv4 + pslld $2,sv4 + paddd ru4,sv4 + +.Ldoblock2: + # hc0 = [ m[16-19] & 0x3ffffff, h0 + m[0-3] & 0x3ffffff ] + movd 0x00(m),hc0 + movd 0x10(m),t1 + punpcklqdq t1,hc0 + pand ANMASK(%rip),hc0 + movd h0,t1 + paddd t1,hc0 + # hc1 = [ (m[19-22] >> 2) & 0x3ffffff, h1 + (m[3-6] >> 2) & 0x3ffffff ] + movd 0x03(m),hc1 + movd 0x13(m),t1 + punpcklqdq t1,hc1 + psrld $2,hc1 + pand ANMASK(%rip),hc1 + movd h1,t1 + paddd t1,hc1 + # hc2 = [ (m[22-25] >> 4) & 0x3ffffff, h2 + (m[6-9] >> 4) & 0x3ffffff ] + movd 0x06(m),hc2 + movd 0x16(m),t1 + punpcklqdq t1,hc2 + psrld $4,hc2 + pand ANMASK(%rip),hc2 + movd h2,t1 + paddd t1,hc2 + # hc3 = [ (m[25-28] >> 6) & 0x3ffffff, h3 + (m[9-12] >> 6) & 0x3ffffff ] + movd 0x09(m),hc3 + movd 0x19(m),t1 + punpcklqdq t1,hc3 + psrld $6,hc3 + pand ANMASK(%rip),hc3 + movd h3,t1 + paddd t1,hc3 + # hc4 = [ (m[28-31] >> 8) | (1<<24), h4 + (m[12-15] >> 8) | (1<<24) ] + movd 0x0c(m),hc4 + movd 0x1c(m),t1 + punpcklqdq t1,hc4 + psrld $8,hc4 + por ORMASK(%rip),hc4 + movd h4,t1 + paddd t1,hc4 + + # t1 = [ hc0[1] * r0, hc0[0] * u0 ] + movdqa ru0,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * s4, hc1[0] * v4 ] + movdqa sv4,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * s3, hc2[0] * v3 ] + movdqa sv3,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * s2, hc3[0] * v2 ] + movdqa sv2,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s1, hc4[0] * v1 ] + movdqa sv1,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d0 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d0 + + # t1 = [ hc0[1] * r1, hc0[0] * u1 ] + movdqa ru1,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r0, hc1[0] * u0 ] + movdqa ru0,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * s4, hc2[0] * v4 ] + movdqa sv4,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * s3, hc3[0] * v3 ] + movdqa sv3,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s2, hc4[0] * v2 ] + movdqa sv2,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d1 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d1 + + # t1 = [ hc0[1] * r2, hc0[0] * u2 ] + movdqa ru2,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r1, hc1[0] * u1 ] + movdqa ru1,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * r0, hc2[0] * u0 ] + movdqa ru0,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * s4, hc3[0] * v4 ] + movdqa sv4,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s3, hc4[0] * v3 ] + movdqa sv3,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d2 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d2 + + # t1 = [ hc0[1] * r3, hc0[0] * u3 ] + movdqa ru3,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r2, hc1[0] * u2 ] + movdqa ru2,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * r1, hc2[0] * u1 ] + movdqa ru1,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * r0, hc3[0] * u0 ] + movdqa ru0,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * s4, hc4[0] * v4 ] + movdqa sv4,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d3 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d3 + + # t1 = [ hc0[1] * r4, hc0[0] * u4 ] + movdqa ru4,t1 + pmuludq hc0,t1 + # t1 += [ hc1[1] * r3, hc1[0] * u3 ] + movdqa ru3,t2 + pmuludq hc1,t2 + paddq t2,t1 + # t1 += [ hc2[1] * r2, hc2[0] * u2 ] + movdqa ru2,t2 + pmuludq hc2,t2 + paddq t2,t1 + # t1 += [ hc3[1] * r1, hc3[0] * u1 ] + movdqa ru1,t2 + pmuludq hc3,t2 + paddq t2,t1 + # t1 += [ hc4[1] * r0, hc4[0] * u0 ] + movdqa ru0,t2 + pmuludq hc4,t2 + paddq t2,t1 + # d4 = t1[0] + t1[1] + movdqa t1,t2 + psrldq $8,t2 + paddq t2,t1 + movq t1,d4 + + # d1 += d0 >> 26 + mov d0,%rax + shr $26,%rax + add %rax,d1 + # h0 = d0 & 0x3ffffff + mov d0,%rbx + and $0x3ffffff,%ebx + + # d2 += d1 >> 26 + mov d1,%rax + shr $26,%rax + add %rax,d2 + # h1 = d1 & 0x3ffffff + mov d1,%rax + and $0x3ffffff,%eax + mov %eax,h1 + + # d3 += d2 >> 26 + mov d2,%rax + shr $26,%rax + add %rax,d3 + # h2 = d2 & 0x3ffffff + mov d2,%rax + and $0x3ffffff,%eax + mov %eax,h2 + + # d4 += d3 >> 26 + mov d3,%rax + shr $26,%rax + add %rax,d4 + # h3 = d3 & 0x3ffffff + mov d3,%rax + and $0x3ffffff,%eax + mov %eax,h3 + + # h0 += (d4 >> 26) * 5 + mov d4,%rax + shr $26,%rax + lea (%eax,%eax,4),%eax + add %eax,%ebx + # h4 = d4 & 0x3ffffff + mov d4,%rax + and $0x3ffffff,%eax + mov %eax,h4 + + # h1 += h0 >> 26 + mov %ebx,%eax + shr $26,%eax + add %eax,h1 + # h0 = h0 & 0x3ffffff + andl $0x3ffffff,%ebx + mov %ebx,h0 + + add $0x20,m + dec %rcx + jnz .Ldoblock2 + + pop %r13 + pop %r12 + pop %rbx + ret +ENDPROC(poly1305_2block_sse2) diff --git a/kernel/arch/x86/crypto/poly1305_glue.c b/kernel/arch/x86/crypto/poly1305_glue.c new file mode 100644 index 000000000..4264a3d59 --- /dev/null +++ b/kernel/arch/x86/crypto/poly1305_glue.c @@ -0,0 +1,207 @@ +/* + * Poly1305 authenticator algorithm, RFC7539, SIMD glue code + * + * Copyright (C) 2015 Martin Willi + * + * 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. + */ + +#include <crypto/algapi.h> +#include <crypto/internal/hash.h> +#include <crypto/poly1305.h> +#include <linux/crypto.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <asm/fpu/api.h> +#include <asm/simd.h> + +struct poly1305_simd_desc_ctx { + struct poly1305_desc_ctx base; + /* derived key u set? */ + bool uset; +#ifdef CONFIG_AS_AVX2 + /* derived keys r^3, r^4 set? */ + bool wset; +#endif + /* derived Poly1305 key r^2 */ + u32 u[5]; + /* ... silently appended r^3 and r^4 when using AVX2 */ +}; + +asmlinkage void poly1305_block_sse2(u32 *h, const u8 *src, + const u32 *r, unsigned int blocks); +asmlinkage void poly1305_2block_sse2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); +#ifdef CONFIG_AS_AVX2 +asmlinkage void poly1305_4block_avx2(u32 *h, const u8 *src, const u32 *r, + unsigned int blocks, const u32 *u); +static bool poly1305_use_avx2; +#endif + +static int poly1305_simd_init(struct shash_desc *desc) +{ + struct poly1305_simd_desc_ctx *sctx = shash_desc_ctx(desc); + + sctx->uset = false; +#ifdef CONFIG_AS_AVX2 + sctx->wset = false; +#endif + + return crypto_poly1305_init(desc); +} + +static void poly1305_simd_mult(u32 *a, const u32 *b) +{ + u8 m[POLY1305_BLOCK_SIZE]; + + memset(m, 0, sizeof(m)); + /* The poly1305 block function adds a hi-bit to the accumulator which + * we don't need for key multiplication; compensate for it. */ + a[4] -= 1 << 24; + poly1305_block_sse2(a, m, b, 1); +} + +static unsigned int poly1305_simd_blocks(struct poly1305_desc_ctx *dctx, + const u8 *src, unsigned int srclen) +{ + struct poly1305_simd_desc_ctx *sctx; + unsigned int blocks, datalen; + + BUILD_BUG_ON(offsetof(struct poly1305_simd_desc_ctx, base)); + sctx = container_of(dctx, struct poly1305_simd_desc_ctx, base); + + if (unlikely(!dctx->sset)) { + datalen = crypto_poly1305_setdesckey(dctx, src, srclen); + src += srclen - datalen; + srclen = datalen; + } + +#ifdef CONFIG_AS_AVX2 + if (poly1305_use_avx2 && srclen >= POLY1305_BLOCK_SIZE * 4) { + if (unlikely(!sctx->wset)) { + if (!sctx->uset) { + memcpy(sctx->u, dctx->r, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u, dctx->r); + sctx->uset = true; + } + memcpy(sctx->u + 5, sctx->u, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u + 5, dctx->r); + memcpy(sctx->u + 10, sctx->u + 5, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u + 10, dctx->r); + sctx->wset = true; + } + blocks = srclen / (POLY1305_BLOCK_SIZE * 4); + poly1305_4block_avx2(dctx->h, src, dctx->r, blocks, sctx->u); + src += POLY1305_BLOCK_SIZE * 4 * blocks; + srclen -= POLY1305_BLOCK_SIZE * 4 * blocks; + } +#endif + if (likely(srclen >= POLY1305_BLOCK_SIZE * 2)) { + if (unlikely(!sctx->uset)) { + memcpy(sctx->u, dctx->r, sizeof(sctx->u)); + poly1305_simd_mult(sctx->u, dctx->r); + sctx->uset = true; + } + blocks = srclen / (POLY1305_BLOCK_SIZE * 2); + poly1305_2block_sse2(dctx->h, src, dctx->r, blocks, sctx->u); + src += POLY1305_BLOCK_SIZE * 2 * blocks; + srclen -= POLY1305_BLOCK_SIZE * 2 * blocks; + } + if (srclen >= POLY1305_BLOCK_SIZE) { + poly1305_block_sse2(dctx->h, src, dctx->r, 1); + srclen -= POLY1305_BLOCK_SIZE; + } + return srclen; +} + +static int poly1305_simd_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc); + unsigned int bytes; + + /* kernel_fpu_begin/end is costly, use fallback for small updates */ + if (srclen <= 288 || !may_use_simd()) + return crypto_poly1305_update(desc, src, srclen); + + kernel_fpu_begin(); + + if (unlikely(dctx->buflen)) { + bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen); + memcpy(dctx->buf + dctx->buflen, src, bytes); + src += bytes; + srclen -= bytes; + dctx->buflen += bytes; + + if (dctx->buflen == POLY1305_BLOCK_SIZE) { + poly1305_simd_blocks(dctx, dctx->buf, + POLY1305_BLOCK_SIZE); + dctx->buflen = 0; + } + } + + if (likely(srclen >= POLY1305_BLOCK_SIZE)) { + bytes = poly1305_simd_blocks(dctx, src, srclen); + src += srclen - bytes; + srclen = bytes; + } + + kernel_fpu_end(); + + if (unlikely(srclen)) { + dctx->buflen = srclen; + memcpy(dctx->buf, src, srclen); + } + + return 0; +} + +static struct shash_alg alg = { + .digestsize = POLY1305_DIGEST_SIZE, + .init = poly1305_simd_init, + .update = poly1305_simd_update, + .final = crypto_poly1305_final, + .setkey = crypto_poly1305_setkey, + .descsize = sizeof(struct poly1305_simd_desc_ctx), + .base = { + .cra_name = "poly1305", + .cra_driver_name = "poly1305-simd", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_alignmask = sizeof(u32) - 1, + .cra_blocksize = POLY1305_BLOCK_SIZE, + .cra_module = THIS_MODULE, + }, +}; + +static int __init poly1305_simd_mod_init(void) +{ + if (!cpu_has_xmm2) + return -ENODEV; + +#ifdef CONFIG_AS_AVX2 + poly1305_use_avx2 = cpu_has_avx && cpu_has_avx2 && + cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL); + alg.descsize = sizeof(struct poly1305_simd_desc_ctx); + if (poly1305_use_avx2) + alg.descsize += 10 * sizeof(u32); +#endif + return crypto_register_shash(&alg); +} + +static void __exit poly1305_simd_mod_exit(void) +{ + crypto_unregister_shash(&alg); +} + +module_init(poly1305_simd_mod_init); +module_exit(poly1305_simd_mod_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Martin Willi <martin@strongswan.org>"); +MODULE_DESCRIPTION("Poly1305 authenticator"); +MODULE_ALIAS_CRYPTO("poly1305"); +MODULE_ALIAS_CRYPTO("poly1305-simd"); diff --git a/kernel/arch/x86/crypto/serpent_avx2_glue.c b/kernel/arch/x86/crypto/serpent_avx2_glue.c index 2f63dc89e..6d198342e 100644 --- a/kernel/arch/x86/crypto/serpent_avx2_glue.c +++ b/kernel/arch/x86/crypto/serpent_avx2_glue.c @@ -20,8 +20,7 @@ #include <crypto/lrw.h> #include <crypto/xts.h> #include <crypto/serpent.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/serpent-avx.h> #include <asm/crypto/glue_helper.h> @@ -537,16 +536,15 @@ static struct crypto_alg srp_algs[10] = { { static int __init init(void) { - u64 xcr0; + const char *feature_name; if (!cpu_has_avx2 || !cpu_has_osxsave) { pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/crypto/serpent_avx_glue.c b/kernel/arch/x86/crypto/serpent_avx_glue.c index c8d478af8..5dc37026c 100644 --- a/kernel/arch/x86/crypto/serpent_avx_glue.c +++ b/kernel/arch/x86/crypto/serpent_avx_glue.c @@ -36,8 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/serpent-avx.h> #include <asm/crypto/glue_helper.h> @@ -596,16 +595,11 @@ static struct crypto_alg serpent_algs[10] = { { static int __init serpent_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - printk(KERN_INFO "AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - printk(KERN_INFO "AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, + &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/crypto/sha-mb/sha1_mb.c b/kernel/arch/x86/crypto/sha-mb/sha1_mb.c index e510b1c5d..a841e9765 100644 --- a/kernel/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/kernel/arch/x86/crypto/sha-mb/sha1_mb.c @@ -65,11 +65,8 @@ #include <crypto/mcryptd.h> #include <crypto/crypto_wq.h> #include <asm/byteorder.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> #include <linux/hardirq.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/api.h> #include "sha_mb_ctx.h" #define FLUSH_INTERVAL 1000 /* in usec */ @@ -885,7 +882,8 @@ static int __init sha1_mb_mod_init(void) INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher); cpu_state->cpu = cpu; cpu_state->alg_state = &sha1_mb_alg_state; - cpu_state->mgr = (struct sha1_ctx_mgr *) kzalloc(sizeof(struct sha1_ctx_mgr), GFP_KERNEL); + cpu_state->mgr = kzalloc(sizeof(struct sha1_ctx_mgr), + GFP_KERNEL); if (!cpu_state->mgr) goto err2; sha1_ctx_mgr_init(cpu_state->mgr); diff --git a/kernel/arch/x86/crypto/sha1_ni_asm.S b/kernel/arch/x86/crypto/sha1_ni_asm.S new file mode 100644 index 000000000..874a651b9 --- /dev/null +++ b/kernel/arch/x86/crypto/sha1_ni_asm.S @@ -0,0 +1,302 @@ +/* + * Intel SHA Extensions optimized implementation of a SHA-1 update function + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2015 Intel Corporation. + * + * 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. + * + * Contact Information: + * Sean Gulley <sean.m.gulley@intel.com> + * Tim Chen <tim.c.chen@linux.intel.com> + * + * BSD LICENSE + * + * Copyright(c) 2015 Intel Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#include <linux/linkage.h> + +#define DIGEST_PTR %rdi /* 1st arg */ +#define DATA_PTR %rsi /* 2nd arg */ +#define NUM_BLKS %rdx /* 3rd arg */ + +#define RSPSAVE %rax + +/* gcc conversion */ +#define FRAME_SIZE 32 /* space for 2x16 bytes */ + +#define ABCD %xmm0 +#define E0 %xmm1 /* Need two E's b/c they ping pong */ +#define E1 %xmm2 +#define MSG0 %xmm3 +#define MSG1 %xmm4 +#define MSG2 %xmm5 +#define MSG3 %xmm6 +#define SHUF_MASK %xmm7 + + +/* + * Intel SHA Extensions optimized implementation of a SHA-1 update function + * + * The function takes a pointer to the current hash values, a pointer to the + * input data, and a number of 64 byte blocks to process. Once all blocks have + * been processed, the digest pointer is updated with the resulting hash value. + * The function only processes complete blocks, there is no functionality to + * store partial blocks. All message padding and hash value initialization must + * be done outside the update function. + * + * The indented lines in the loop are instructions related to rounds processing. + * The non-indented lines are instructions related to the message schedule. + * + * void sha1_ni_transform(uint32_t *digest, const void *data, + uint32_t numBlocks) + * digest : pointer to digest + * data: pointer to input data + * numBlocks: Number of blocks to process + */ +.text +.align 32 +ENTRY(sha1_ni_transform) + mov %rsp, RSPSAVE + sub $FRAME_SIZE, %rsp + and $~0xF, %rsp + + shl $6, NUM_BLKS /* convert to bytes */ + jz .Ldone_hash + add DATA_PTR, NUM_BLKS /* pointer to end of data */ + + /* load initial hash values */ + pinsrd $3, 1*16(DIGEST_PTR), E0 + movdqu 0*16(DIGEST_PTR), ABCD + pand UPPER_WORD_MASK(%rip), E0 + pshufd $0x1B, ABCD, ABCD + + movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK + +.Lloop0: + /* Save hash values for addition after rounds */ + movdqa E0, (0*16)(%rsp) + movdqa ABCD, (1*16)(%rsp) + + /* Rounds 0-3 */ + movdqu 0*16(DATA_PTR), MSG0 + pshufb SHUF_MASK, MSG0 + paddd MSG0, E0 + movdqa ABCD, E1 + sha1rnds4 $0, E0, ABCD + + /* Rounds 4-7 */ + movdqu 1*16(DATA_PTR), MSG1 + pshufb SHUF_MASK, MSG1 + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1rnds4 $0, E1, ABCD + sha1msg1 MSG1, MSG0 + + /* Rounds 8-11 */ + movdqu 2*16(DATA_PTR), MSG2 + pshufb SHUF_MASK, MSG2 + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1rnds4 $0, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 12-15 */ + movdqu 3*16(DATA_PTR), MSG3 + pshufb SHUF_MASK, MSG3 + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $0, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 16-19 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $0, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 20-23 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $1, E1, ABCD + sha1msg1 MSG1, MSG0 + pxor MSG1, MSG3 + + /* Rounds 24-27 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $1, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 28-31 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $1, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 32-35 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $1, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 36-39 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $1, E1, ABCD + sha1msg1 MSG1, MSG0 + pxor MSG1, MSG3 + + /* Rounds 40-43 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $2, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 44-47 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $2, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 48-51 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $2, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 52-55 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $2, E1, ABCD + sha1msg1 MSG1, MSG0 + pxor MSG1, MSG3 + + /* Rounds 56-59 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $2, E0, ABCD + sha1msg1 MSG2, MSG1 + pxor MSG2, MSG0 + + /* Rounds 60-63 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1msg2 MSG3, MSG0 + sha1rnds4 $3, E1, ABCD + sha1msg1 MSG3, MSG2 + pxor MSG3, MSG1 + + /* Rounds 64-67 */ + sha1nexte MSG0, E0 + movdqa ABCD, E1 + sha1msg2 MSG0, MSG1 + sha1rnds4 $3, E0, ABCD + sha1msg1 MSG0, MSG3 + pxor MSG0, MSG2 + + /* Rounds 68-71 */ + sha1nexte MSG1, E1 + movdqa ABCD, E0 + sha1msg2 MSG1, MSG2 + sha1rnds4 $3, E1, ABCD + pxor MSG1, MSG3 + + /* Rounds 72-75 */ + sha1nexte MSG2, E0 + movdqa ABCD, E1 + sha1msg2 MSG2, MSG3 + sha1rnds4 $3, E0, ABCD + + /* Rounds 76-79 */ + sha1nexte MSG3, E1 + movdqa ABCD, E0 + sha1rnds4 $3, E1, ABCD + + /* Add current hash values with previously saved */ + sha1nexte (0*16)(%rsp), E0 + paddd (1*16)(%rsp), ABCD + + /* Increment data pointer and loop if more to process */ + add $64, DATA_PTR + cmp NUM_BLKS, DATA_PTR + jne .Lloop0 + + /* Write hash values back in the correct order */ + pshufd $0x1B, ABCD, ABCD + movdqu ABCD, 0*16(DIGEST_PTR) + pextrd $3, E0, 1*16(DIGEST_PTR) + +.Ldone_hash: + mov RSPSAVE, %rsp + + ret +ENDPROC(sha1_ni_transform) + +.data + +.align 64 +PSHUFFLE_BYTE_FLIP_MASK: + .octa 0x000102030405060708090a0b0c0d0e0f +UPPER_WORD_MASK: + .octa 0xFFFFFFFF000000000000000000000000 diff --git a/kernel/arch/x86/crypto/sha1_ssse3_glue.c b/kernel/arch/x86/crypto/sha1_ssse3_glue.c index 33d1b9dc1..dd14616b7 100644 --- a/kernel/arch/x86/crypto/sha1_ssse3_glue.c +++ b/kernel/arch/x86/crypto/sha1_ssse3_glue.c @@ -29,28 +29,13 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha1_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> +typedef void (sha1_transform_fn)(u32 *digest, const char *data, + unsigned int rounds); -asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, - unsigned int rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha1_transform_avx(u32 *digest, const char *data, - unsigned int rounds); -#endif -#ifdef CONFIG_AS_AVX2 -#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ - -asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, - unsigned int rounds); -#endif - -static void (*sha1_transform_asm)(u32 *, const char *, unsigned int); - -static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha1_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha1_transform_fn *sha1_xform) { struct sha1_state *sctx = shash_desc_ctx(desc); @@ -63,14 +48,14 @@ static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); sha1_base_do_update(desc, data, len, - (sha1_block_fn *)sha1_transform_asm); + (sha1_block_fn *)sha1_xform); kernel_fpu_end(); return 0; } -static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int sha1_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha1_transform_fn *sha1_xform) { if (!irq_fpu_usable()) return crypto_sha1_finup(desc, data, len, out); @@ -78,32 +63,37 @@ static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); if (len) sha1_base_do_update(desc, data, len, - (sha1_block_fn *)sha1_transform_asm); - sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_transform_asm); + (sha1_block_fn *)sha1_xform); + sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_xform); kernel_fpu_end(); return sha1_base_finish(desc, out); } -/* Add padding and return the message digest. */ -static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) +asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, + unsigned int rounds); + +static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - return sha1_ssse3_finup(desc, NULL, 0, out); + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_transform_ssse3); } -#ifdef CONFIG_AS_AVX2 -static void sha1_apply_transform_avx2(u32 *digest, const char *data, - unsigned int rounds) +static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - /* Select the optimal transform based on data block size */ - if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE) - sha1_transform_avx2(digest, data, rounds); - else - sha1_transform_avx(digest, data, rounds); + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_transform_ssse3); +} + +/* Add padding and return the message digest. */ +static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) +{ + return sha1_ssse3_finup(desc, NULL, 0, out); } -#endif -static struct shash_alg alg = { +static struct shash_alg sha1_ssse3_alg = { .digestsize = SHA1_DIGEST_SIZE, .init = sha1_base_init, .update = sha1_ssse3_update, @@ -112,7 +102,7 @@ static struct shash_alg alg = { .descsize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", - .cra_driver_name= "sha1-ssse3", + .cra_driver_name = "sha1-ssse3", .cra_priority = 150, .cra_flags = CRYPTO_ALG_TYPE_SHASH, .cra_blocksize = SHA1_BLOCK_SIZE, @@ -120,73 +110,261 @@ static struct shash_alg alg = { } }; +static int register_sha1_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shash(&sha1_ssse3_alg); + return 0; +} + +static void unregister_sha1_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shash(&sha1_ssse3_alg); +} + #ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +asmlinkage void sha1_transform_avx(u32 *digest, const char *data, + unsigned int rounds); + +static int sha1_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - u64 xcr0; + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_transform_avx); +} - if (!cpu_has_avx || !cpu_has_osxsave) - return false; +static int sha1_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_transform_avx); +} - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); +static int sha1_avx_final(struct shash_desc *desc, u8 *out) +{ + return sha1_avx_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha1_avx_alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_base_init, + .update = sha1_avx_update, + .final = sha1_avx_final, + .finup = sha1_avx_finup, + .descsize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; +static bool avx_usable(void) +{ + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } return true; } -#ifdef CONFIG_AS_AVX2 -static bool __init avx2_usable(void) +static int register_sha1_avx(void) { - if (avx_usable() && cpu_has_avx2 && boot_cpu_has(X86_FEATURE_BMI1) && - boot_cpu_has(X86_FEATURE_BMI2)) + if (avx_usable()) + return crypto_register_shash(&sha1_avx_alg); + return 0; +} + +static void unregister_sha1_avx(void) +{ + if (avx_usable()) + crypto_unregister_shash(&sha1_avx_alg); +} + +#else /* CONFIG_AS_AVX */ +static inline int register_sha1_avx(void) { return 0; } +static inline void unregister_sha1_avx(void) { } +#endif /* CONFIG_AS_AVX */ + + +#if defined(CONFIG_AS_AVX2) && (CONFIG_AS_AVX) +#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ + +asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, + unsigned int rounds); + +static bool avx2_usable(void) +{ + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + && boot_cpu_has(X86_FEATURE_BMI1) + && boot_cpu_has(X86_FEATURE_BMI2)) return true; return false; } + +static void sha1_apply_transform_avx2(u32 *digest, const char *data, + unsigned int rounds) +{ + /* Select the optimal transform based on data block size */ + if (rounds >= SHA1_AVX2_BLOCK_OPTSIZE) + sha1_transform_avx2(digest, data, rounds); + else + sha1_transform_avx(digest, data, rounds); +} + +static int sha1_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_apply_transform_avx2); +} + +static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_apply_transform_avx2); +} + +static int sha1_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha1_avx2_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha1_avx2_alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_base_init, + .update = sha1_avx2_update, + .final = sha1_avx2_final, + .finup = sha1_avx2_finup, + .descsize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int register_sha1_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shash(&sha1_avx2_alg); + return 0; +} + +static void unregister_sha1_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shash(&sha1_avx2_alg); +} + +#else +static inline int register_sha1_avx2(void) { return 0; } +static inline void unregister_sha1_avx2(void) { } #endif + +#ifdef CONFIG_AS_SHA1_NI +asmlinkage void sha1_ni_transform(u32 *digest, const char *data, + unsigned int rounds); + +static int sha1_ni_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha1_update(desc, data, len, + (sha1_transform_fn *) sha1_ni_transform); +} + +static int sha1_ni_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha1_finup(desc, data, len, out, + (sha1_transform_fn *) sha1_ni_transform); +} + +static int sha1_ni_final(struct shash_desc *desc, u8 *out) +{ + return sha1_ni_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha1_ni_alg = { + .digestsize = SHA1_DIGEST_SIZE, + .init = sha1_base_init, + .update = sha1_ni_update, + .final = sha1_ni_final, + .finup = sha1_ni_finup, + .descsize = sizeof(struct sha1_state), + .base = { + .cra_name = "sha1", + .cra_driver_name = "sha1-ni", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA1_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}; + +static int register_sha1_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + return crypto_register_shash(&sha1_ni_alg); + return 0; +} + +static void unregister_sha1_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + crypto_unregister_shash(&sha1_ni_alg); +} + +#else +static inline int register_sha1_ni(void) { return 0; } +static inline void unregister_sha1_ni(void) { } #endif static int __init sha1_ssse3_mod_init(void) { - char *algo_name; + if (register_sha1_ssse3()) + goto fail; - /* test for SSSE3 first */ - if (cpu_has_ssse3) { - sha1_transform_asm = sha1_transform_ssse3; - algo_name = "SSSE3"; + if (register_sha1_avx()) { + unregister_sha1_ssse3(); + goto fail; } -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { - sha1_transform_asm = sha1_transform_avx; - algo_name = "AVX"; -#ifdef CONFIG_AS_AVX2 - /* allow AVX2 to override AVX, it's a little faster */ - if (avx2_usable()) { - sha1_transform_asm = sha1_apply_transform_avx2; - algo_name = "AVX2"; - } -#endif + if (register_sha1_avx2()) { + unregister_sha1_avx(); + unregister_sha1_ssse3(); + goto fail; } -#endif - if (sha1_transform_asm) { - pr_info("Using %s optimized SHA-1 implementation\n", algo_name); - return crypto_register_shash(&alg); + if (register_sha1_ni()) { + unregister_sha1_avx2(); + unregister_sha1_avx(); + unregister_sha1_ssse3(); + goto fail; } - pr_info("Neither AVX nor AVX2 nor SSSE3 is available/usable.\n"); + return 0; +fail: return -ENODEV; } static void __exit sha1_ssse3_mod_fini(void) { - crypto_unregister_shash(&alg); + unregister_sha1_ni(); + unregister_sha1_avx2(); + unregister_sha1_avx(); + unregister_sha1_ssse3(); } module_init(sha1_ssse3_mod_init); diff --git a/kernel/arch/x86/crypto/sha256_ni_asm.S b/kernel/arch/x86/crypto/sha256_ni_asm.S new file mode 100644 index 000000000..748cdf21a --- /dev/null +++ b/kernel/arch/x86/crypto/sha256_ni_asm.S @@ -0,0 +1,353 @@ +/* + * Intel SHA Extensions optimized implementation of a SHA-256 update function + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2015 Intel Corporation. + * + * 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. + * + * Contact Information: + * Sean Gulley <sean.m.gulley@intel.com> + * Tim Chen <tim.c.chen@linux.intel.com> + * + * BSD LICENSE + * + * Copyright(c) 2015 Intel Corporation. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + */ + +#include <linux/linkage.h> + +#define DIGEST_PTR %rdi /* 1st arg */ +#define DATA_PTR %rsi /* 2nd arg */ +#define NUM_BLKS %rdx /* 3rd arg */ + +#define SHA256CONSTANTS %rax + +#define MSG %xmm0 +#define STATE0 %xmm1 +#define STATE1 %xmm2 +#define MSGTMP0 %xmm3 +#define MSGTMP1 %xmm4 +#define MSGTMP2 %xmm5 +#define MSGTMP3 %xmm6 +#define MSGTMP4 %xmm7 + +#define SHUF_MASK %xmm8 + +#define ABEF_SAVE %xmm9 +#define CDGH_SAVE %xmm10 + +/* + * Intel SHA Extensions optimized implementation of a SHA-256 update function + * + * The function takes a pointer to the current hash values, a pointer to the + * input data, and a number of 64 byte blocks to process. Once all blocks have + * been processed, the digest pointer is updated with the resulting hash value. + * The function only processes complete blocks, there is no functionality to + * store partial blocks. All message padding and hash value initialization must + * be done outside the update function. + * + * The indented lines in the loop are instructions related to rounds processing. + * The non-indented lines are instructions related to the message schedule. + * + * void sha256_ni_transform(uint32_t *digest, const void *data, + uint32_t numBlocks); + * digest : pointer to digest + * data: pointer to input data + * numBlocks: Number of blocks to process + */ + +.text +.align 32 +ENTRY(sha256_ni_transform) + + shl $6, NUM_BLKS /* convert to bytes */ + jz .Ldone_hash + add DATA_PTR, NUM_BLKS /* pointer to end of data */ + + /* + * load initial hash values + * Need to reorder these appropriately + * DCBA, HGFE -> ABEF, CDGH + */ + movdqu 0*16(DIGEST_PTR), STATE0 + movdqu 1*16(DIGEST_PTR), STATE1 + + pshufd $0xB1, STATE0, STATE0 /* CDAB */ + pshufd $0x1B, STATE1, STATE1 /* EFGH */ + movdqa STATE0, MSGTMP4 + palignr $8, STATE1, STATE0 /* ABEF */ + pblendw $0xF0, MSGTMP4, STATE1 /* CDGH */ + + movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK + lea K256(%rip), SHA256CONSTANTS + +.Lloop0: + /* Save hash values for addition after rounds */ + movdqa STATE0, ABEF_SAVE + movdqa STATE1, CDGH_SAVE + + /* Rounds 0-3 */ + movdqu 0*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP0 + paddd 0*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Rounds 4-7 */ + movdqu 1*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP1 + paddd 1*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP1, MSGTMP0 + + /* Rounds 8-11 */ + movdqu 2*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP2 + paddd 2*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP2, MSGTMP1 + + /* Rounds 12-15 */ + movdqu 3*16(DATA_PTR), MSG + pshufb SHUF_MASK, MSG + movdqa MSG, MSGTMP3 + paddd 3*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP3, MSGTMP4 + palignr $4, MSGTMP2, MSGTMP4 + paddd MSGTMP4, MSGTMP0 + sha256msg2 MSGTMP3, MSGTMP0 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP3, MSGTMP2 + + /* Rounds 16-19 */ + movdqa MSGTMP0, MSG + paddd 4*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP0, MSGTMP4 + palignr $4, MSGTMP3, MSGTMP4 + paddd MSGTMP4, MSGTMP1 + sha256msg2 MSGTMP0, MSGTMP1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP0, MSGTMP3 + + /* Rounds 20-23 */ + movdqa MSGTMP1, MSG + paddd 5*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP1, MSGTMP4 + palignr $4, MSGTMP0, MSGTMP4 + paddd MSGTMP4, MSGTMP2 + sha256msg2 MSGTMP1, MSGTMP2 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP1, MSGTMP0 + + /* Rounds 24-27 */ + movdqa MSGTMP2, MSG + paddd 6*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP2, MSGTMP4 + palignr $4, MSGTMP1, MSGTMP4 + paddd MSGTMP4, MSGTMP3 + sha256msg2 MSGTMP2, MSGTMP3 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP2, MSGTMP1 + + /* Rounds 28-31 */ + movdqa MSGTMP3, MSG + paddd 7*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP3, MSGTMP4 + palignr $4, MSGTMP2, MSGTMP4 + paddd MSGTMP4, MSGTMP0 + sha256msg2 MSGTMP3, MSGTMP0 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP3, MSGTMP2 + + /* Rounds 32-35 */ + movdqa MSGTMP0, MSG + paddd 8*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP0, MSGTMP4 + palignr $4, MSGTMP3, MSGTMP4 + paddd MSGTMP4, MSGTMP1 + sha256msg2 MSGTMP0, MSGTMP1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP0, MSGTMP3 + + /* Rounds 36-39 */ + movdqa MSGTMP1, MSG + paddd 9*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP1, MSGTMP4 + palignr $4, MSGTMP0, MSGTMP4 + paddd MSGTMP4, MSGTMP2 + sha256msg2 MSGTMP1, MSGTMP2 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP1, MSGTMP0 + + /* Rounds 40-43 */ + movdqa MSGTMP2, MSG + paddd 10*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP2, MSGTMP4 + palignr $4, MSGTMP1, MSGTMP4 + paddd MSGTMP4, MSGTMP3 + sha256msg2 MSGTMP2, MSGTMP3 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP2, MSGTMP1 + + /* Rounds 44-47 */ + movdqa MSGTMP3, MSG + paddd 11*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP3, MSGTMP4 + palignr $4, MSGTMP2, MSGTMP4 + paddd MSGTMP4, MSGTMP0 + sha256msg2 MSGTMP3, MSGTMP0 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP3, MSGTMP2 + + /* Rounds 48-51 */ + movdqa MSGTMP0, MSG + paddd 12*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP0, MSGTMP4 + palignr $4, MSGTMP3, MSGTMP4 + paddd MSGTMP4, MSGTMP1 + sha256msg2 MSGTMP0, MSGTMP1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + sha256msg1 MSGTMP0, MSGTMP3 + + /* Rounds 52-55 */ + movdqa MSGTMP1, MSG + paddd 13*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP1, MSGTMP4 + palignr $4, MSGTMP0, MSGTMP4 + paddd MSGTMP4, MSGTMP2 + sha256msg2 MSGTMP1, MSGTMP2 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Rounds 56-59 */ + movdqa MSGTMP2, MSG + paddd 14*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + movdqa MSGTMP2, MSGTMP4 + palignr $4, MSGTMP1, MSGTMP4 + paddd MSGTMP4, MSGTMP3 + sha256msg2 MSGTMP2, MSGTMP3 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Rounds 60-63 */ + movdqa MSGTMP3, MSG + paddd 15*16(SHA256CONSTANTS), MSG + sha256rnds2 STATE0, STATE1 + pshufd $0x0E, MSG, MSG + sha256rnds2 STATE1, STATE0 + + /* Add current hash values with previously saved */ + paddd ABEF_SAVE, STATE0 + paddd CDGH_SAVE, STATE1 + + /* Increment data pointer and loop if more to process */ + add $64, DATA_PTR + cmp NUM_BLKS, DATA_PTR + jne .Lloop0 + + /* Write hash values back in the correct order */ + pshufd $0x1B, STATE0, STATE0 /* FEBA */ + pshufd $0xB1, STATE1, STATE1 /* DCHG */ + movdqa STATE0, MSGTMP4 + pblendw $0xF0, STATE1, STATE0 /* DCBA */ + palignr $8, MSGTMP4, STATE1 /* HGFE */ + + movdqu STATE0, 0*16(DIGEST_PTR) + movdqu STATE1, 1*16(DIGEST_PTR) + +.Ldone_hash: + + ret +ENDPROC(sha256_ni_transform) + +.data +.align 64 +K256: + .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5 + .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5 + .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3 + .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174 + .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc + .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da + .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7 + .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967 + .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13 + .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85 + .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3 + .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070 + .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5 + .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3 + .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208 + .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2 + +PSHUFFLE_BYTE_FLIP_MASK: + .octa 0x0c0d0e0f08090a0b0405060700010203 diff --git a/kernel/arch/x86/crypto/sha256_ssse3_glue.c b/kernel/arch/x86/crypto/sha256_ssse3_glue.c index ccc338881..5f4d6086d 100644 --- a/kernel/arch/x86/crypto/sha256_ssse3_glue.c +++ b/kernel/arch/x86/crypto/sha256_ssse3_glue.c @@ -37,26 +37,15 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha256_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <linux/string.h> asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, u64 rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha256_transform_avx(u32 *digest, const char *data, - u64 rounds); -#endif -#ifdef CONFIG_AS_AVX2 -asmlinkage void sha256_transform_rorx(u32 *digest, const char *data, - u64 rounds); -#endif - -static void (*sha256_transform_asm)(u32 *, const char *, u64); +typedef void (sha256_transform_fn)(u32 *digest, const char *data, u64 rounds); -static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha256_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha256_transform_fn *sha256_xform) { struct sha256_state *sctx = shash_desc_ctx(desc); @@ -69,14 +58,14 @@ static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_transform_asm); + (sha256_block_fn *)sha256_xform); kernel_fpu_end(); return 0; } -static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int sha256_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha256_transform_fn *sha256_xform) { if (!irq_fpu_usable()) return crypto_sha256_finup(desc, data, len, out); @@ -84,20 +73,32 @@ static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); if (len) sha256_base_do_update(desc, data, len, - (sha256_block_fn *)sha256_transform_asm); - sha256_base_do_finalize(desc, (sha256_block_fn *)sha256_transform_asm); + (sha256_block_fn *)sha256_xform); + sha256_base_do_finalize(desc, (sha256_block_fn *)sha256_xform); kernel_fpu_end(); return sha256_base_finish(desc, out); } +static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_transform_ssse3); +} + +static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_transform_ssse3); +} + /* Add padding and return the message digest. */ static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) { return sha256_ssse3_finup(desc, NULL, 0, out); } -static struct shash_alg algs[] = { { +static struct shash_alg sha256_ssse3_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ssse3_update, @@ -129,64 +130,294 @@ static struct shash_alg algs[] = { { } } }; +static int register_sha256_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shashes(sha256_ssse3_algs, + ARRAY_SIZE(sha256_ssse3_algs)); + return 0; +} + +static void unregister_sha256_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(sha256_ssse3_algs, + ARRAY_SIZE(sha256_ssse3_algs)); +} + #ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +asmlinkage void sha256_transform_avx(u32 *digest, const char *data, + u64 rounds); + +static int sha256_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - u64 xcr0; + return sha256_update(desc, data, len, sha256_transform_avx); +} - if (!cpu_has_avx || !cpu_has_osxsave) - return false; +static int sha256_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_transform_avx); +} - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); +static int sha256_avx_final(struct shash_desc *desc, u8 *out) +{ + return sha256_avx_finup(desc, NULL, 0, out); +} +static struct shash_alg sha256_avx_algs[] = { { + .digestsize = SHA256_DIGEST_SIZE, + .init = sha256_base_init, + .update = sha256_avx_update, + .final = sha256_avx_final, + .finup = sha256_avx_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_base_init, + .update = sha256_avx_update, + .final = sha256_avx_final, + .finup = sha256_avx_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static bool avx_usable(void) +{ + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } return true; } -#endif -static int __init sha256_ssse3_mod_init(void) +static int register_sha256_avx(void) { - /* test for SSSE3 first */ - if (cpu_has_ssse3) - sha256_transform_asm = sha256_transform_ssse3; + if (avx_usable()) + return crypto_register_shashes(sha256_avx_algs, + ARRAY_SIZE(sha256_avx_algs)); + return 0; +} -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { -#ifdef CONFIG_AS_AVX2 - if (boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI2)) - sha256_transform_asm = sha256_transform_rorx; - else +static void unregister_sha256_avx(void) +{ + if (avx_usable()) + crypto_unregister_shashes(sha256_avx_algs, + ARRAY_SIZE(sha256_avx_algs)); +} + +#else +static inline int register_sha256_avx(void) { return 0; } +static inline void unregister_sha256_avx(void) { } #endif - sha256_transform_asm = sha256_transform_avx; + +#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) +asmlinkage void sha256_transform_rorx(u32 *digest, const char *data, + u64 rounds); + +static int sha256_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_transform_rorx); +} + +static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_transform_rorx); +} + +static int sha256_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha256_avx2_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha256_avx2_algs[] = { { + .digestsize = SHA256_DIGEST_SIZE, + .init = sha256_base_init, + .update = sha256_avx2_update, + .final = sha256_avx2_final, + .finup = sha256_avx2_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, } -#endif +}, { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_base_init, + .update = sha256_avx2_update, + .final = sha256_avx2_final, + .finup = sha256_avx2_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; - if (sha256_transform_asm) { -#ifdef CONFIG_AS_AVX - if (sha256_transform_asm == sha256_transform_avx) - pr_info("Using AVX optimized SHA-256 implementation\n"); -#ifdef CONFIG_AS_AVX2 - else if (sha256_transform_asm == sha256_transform_rorx) - pr_info("Using AVX2 optimized SHA-256 implementation\n"); +static bool avx2_usable(void) +{ + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && + boot_cpu_has(X86_FEATURE_BMI2)) + return true; + + return false; +} + +static int register_sha256_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shashes(sha256_avx2_algs, + ARRAY_SIZE(sha256_avx2_algs)); + return 0; +} + +static void unregister_sha256_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shashes(sha256_avx2_algs, + ARRAY_SIZE(sha256_avx2_algs)); +} + +#else +static inline int register_sha256_avx2(void) { return 0; } +static inline void unregister_sha256_avx2(void) { } #endif - else + +#ifdef CONFIG_AS_SHA256_NI +asmlinkage void sha256_ni_transform(u32 *digest, const char *data, + u64 rounds); /*unsigned int rounds);*/ + +static int sha256_ni_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha256_update(desc, data, len, sha256_ni_transform); +} + +static int sha256_ni_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_finup(desc, data, len, out, sha256_ni_transform); +} + +static int sha256_ni_final(struct shash_desc *desc, u8 *out) +{ + return sha256_ni_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha256_ni_algs[] = { { + .digestsize = SHA256_DIGEST_SIZE, + .init = sha256_base_init, + .update = sha256_ni_update, + .final = sha256_ni_final, + .finup = sha256_ni_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha256", + .cra_driver_name = "sha256-ni", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA256_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA224_DIGEST_SIZE, + .init = sha224_base_init, + .update = sha256_ni_update, + .final = sha256_ni_final, + .finup = sha256_ni_finup, + .descsize = sizeof(struct sha256_state), + .base = { + .cra_name = "sha224", + .cra_driver_name = "sha224-ni", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA224_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static int register_sha256_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + return crypto_register_shashes(sha256_ni_algs, + ARRAY_SIZE(sha256_ni_algs)); + return 0; +} + +static void unregister_sha256_ni(void) +{ + if (boot_cpu_has(X86_FEATURE_SHA_NI)) + crypto_unregister_shashes(sha256_ni_algs, + ARRAY_SIZE(sha256_ni_algs)); +} + +#else +static inline int register_sha256_ni(void) { return 0; } +static inline void unregister_sha256_ni(void) { } #endif - pr_info("Using SSSE3 optimized SHA-256 implementation\n"); - return crypto_register_shashes(algs, ARRAY_SIZE(algs)); + +static int __init sha256_ssse3_mod_init(void) +{ + if (register_sha256_ssse3()) + goto fail; + + if (register_sha256_avx()) { + unregister_sha256_ssse3(); + goto fail; } - pr_info("Neither AVX nor SSSE3 is available/usable.\n"); + if (register_sha256_avx2()) { + unregister_sha256_avx(); + unregister_sha256_ssse3(); + goto fail; + } + + if (register_sha256_ni()) { + unregister_sha256_avx2(); + unregister_sha256_avx(); + unregister_sha256_ssse3(); + goto fail; + } + + return 0; +fail: return -ENODEV; } static void __exit sha256_ssse3_mod_fini(void) { - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); + unregister_sha256_ni(); + unregister_sha256_avx2(); + unregister_sha256_avx(); + unregister_sha256_ssse3(); } module_init(sha256_ssse3_mod_init); diff --git a/kernel/arch/x86/crypto/sha512_ssse3_glue.c b/kernel/arch/x86/crypto/sha512_ssse3_glue.c index d9fa4c1e0..34e5083d6 100644 --- a/kernel/arch/x86/crypto/sha512_ssse3_glue.c +++ b/kernel/arch/x86/crypto/sha512_ssse3_glue.c @@ -35,27 +35,17 @@ #include <linux/types.h> #include <crypto/sha.h> #include <crypto/sha512_base.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <linux/string.h> asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data, u64 rounds); -#ifdef CONFIG_AS_AVX -asmlinkage void sha512_transform_avx(u64 *digest, const char *data, - u64 rounds); -#endif -#ifdef CONFIG_AS_AVX2 -asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, - u64 rounds); -#endif -static void (*sha512_transform_asm)(u64 *, const char *, u64); +typedef void (sha512_transform_fn)(u64 *digest, const char *data, u64 rounds); -static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha512_update(struct shash_desc *desc, const u8 *data, + unsigned int len, sha512_transform_fn *sha512_xform) { struct sha512_state *sctx = shash_desc_ctx(desc); @@ -68,14 +58,14 @@ static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_transform_asm); + (sha512_block_fn *)sha512_xform); kernel_fpu_end(); return 0; } -static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, - unsigned int len, u8 *out) +static int sha512_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out, sha512_transform_fn *sha512_xform) { if (!irq_fpu_usable()) return crypto_sha512_finup(desc, data, len, out); @@ -83,20 +73,32 @@ static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, kernel_fpu_begin(); if (len) sha512_base_do_update(desc, data, len, - (sha512_block_fn *)sha512_transform_asm); - sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_transform_asm); + (sha512_block_fn *)sha512_xform); + sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_xform); kernel_fpu_end(); return sha512_base_finish(desc, out); } +static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_ssse3); +} + +static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_ssse3); +} + /* Add padding and return the message digest. */ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) { return sha512_ssse3_finup(desc, NULL, 0, out); } -static struct shash_alg algs[] = { { +static struct shash_alg sha512_ssse3_algs[] = { { .digestsize = SHA512_DIGEST_SIZE, .init = sha512_base_init, .update = sha512_ssse3_update, @@ -128,64 +130,213 @@ static struct shash_alg algs[] = { { } } }; -#ifdef CONFIG_AS_AVX -static bool __init avx_usable(void) +static int register_sha512_ssse3(void) { - u64 xcr0; - - if (!cpu_has_avx || !cpu_has_osxsave) - return false; + if (boot_cpu_has(X86_FEATURE_SSSE3)) + return crypto_register_shashes(sha512_ssse3_algs, + ARRAY_SIZE(sha512_ssse3_algs)); + return 0; +} - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - pr_info("AVX detected but unusable.\n"); +static void unregister_sha512_ssse3(void) +{ + if (boot_cpu_has(X86_FEATURE_SSSE3)) + crypto_unregister_shashes(sha512_ssse3_algs, + ARRAY_SIZE(sha512_ssse3_algs)); +} +#ifdef CONFIG_AS_AVX +asmlinkage void sha512_transform_avx(u64 *digest, const char *data, + u64 rounds); +static bool avx_usable(void) +{ + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) { + if (cpu_has_avx) + pr_info("AVX detected but unusable.\n"); return false; } return true; } -#endif -static int __init sha512_ssse3_mod_init(void) +static int sha512_avx_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { - /* test for SSSE3 first */ - if (cpu_has_ssse3) - sha512_transform_asm = sha512_transform_ssse3; + return sha512_update(desc, data, len, sha512_transform_avx); +} -#ifdef CONFIG_AS_AVX - /* allow AVX to override SSSE3, it's a little faster */ - if (avx_usable()) { -#ifdef CONFIG_AS_AVX2 - if (boot_cpu_has(X86_FEATURE_AVX2)) - sha512_transform_asm = sha512_transform_rorx; - else -#endif - sha512_transform_asm = sha512_transform_avx; +static int sha512_avx_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_avx); +} + +/* Add padding and return the message digest. */ +static int sha512_avx_final(struct shash_desc *desc, u8 *out) +{ + return sha512_avx_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha512_avx_algs[] = { { + .digestsize = SHA512_DIGEST_SIZE, + .init = sha512_base_init, + .update = sha512_avx_update, + .final = sha512_avx_final, + .finup = sha512_avx_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, } -#endif +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_avx_update, + .final = sha512_avx_final, + .finup = sha512_avx_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-avx", + .cra_priority = 160, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; - if (sha512_transform_asm) { -#ifdef CONFIG_AS_AVX - if (sha512_transform_asm == sha512_transform_avx) - pr_info("Using AVX optimized SHA-512 implementation\n"); -#ifdef CONFIG_AS_AVX2 - else if (sha512_transform_asm == sha512_transform_rorx) - pr_info("Using AVX2 optimized SHA-512 implementation\n"); +static int register_sha512_avx(void) +{ + if (avx_usable()) + return crypto_register_shashes(sha512_avx_algs, + ARRAY_SIZE(sha512_avx_algs)); + return 0; +} + +static void unregister_sha512_avx(void) +{ + if (avx_usable()) + crypto_unregister_shashes(sha512_avx_algs, + ARRAY_SIZE(sha512_avx_algs)); +} +#else +static inline int register_sha512_avx(void) { return 0; } +static inline void unregister_sha512_avx(void) { } #endif - else + +#if defined(CONFIG_AS_AVX2) && defined(CONFIG_AS_AVX) +asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, + u64 rounds); + +static int sha512_avx2_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_update(desc, data, len, sha512_transform_rorx); +} + +static int sha512_avx2_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha512_finup(desc, data, len, out, sha512_transform_rorx); +} + +/* Add padding and return the message digest. */ +static int sha512_avx2_final(struct shash_desc *desc, u8 *out) +{ + return sha512_avx2_finup(desc, NULL, 0, out); +} + +static struct shash_alg sha512_avx2_algs[] = { { + .digestsize = SHA512_DIGEST_SIZE, + .init = sha512_base_init, + .update = sha512_avx2_update, + .final = sha512_avx2_final, + .finup = sha512_avx2_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .digestsize = SHA384_DIGEST_SIZE, + .init = sha384_base_init, + .update = sha512_avx2_update, + .final = sha512_avx2_final, + .finup = sha512_avx2_finup, + .descsize = sizeof(struct sha512_state), + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-avx2", + .cra_priority = 170, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static bool avx2_usable(void) +{ + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && + boot_cpu_has(X86_FEATURE_BMI2)) + return true; + + return false; +} + +static int register_sha512_avx2(void) +{ + if (avx2_usable()) + return crypto_register_shashes(sha512_avx2_algs, + ARRAY_SIZE(sha512_avx2_algs)); + return 0; +} + +static void unregister_sha512_avx2(void) +{ + if (avx2_usable()) + crypto_unregister_shashes(sha512_avx2_algs, + ARRAY_SIZE(sha512_avx2_algs)); +} +#else +static inline int register_sha512_avx2(void) { return 0; } +static inline void unregister_sha512_avx2(void) { } #endif - pr_info("Using SSSE3 optimized SHA-512 implementation\n"); - return crypto_register_shashes(algs, ARRAY_SIZE(algs)); + +static int __init sha512_ssse3_mod_init(void) +{ + + if (register_sha512_ssse3()) + goto fail; + + if (register_sha512_avx()) { + unregister_sha512_ssse3(); + goto fail; } - pr_info("Neither AVX nor SSSE3 is available/usable.\n"); + if (register_sha512_avx2()) { + unregister_sha512_avx(); + unregister_sha512_ssse3(); + goto fail; + } + + return 0; +fail: return -ENODEV; } static void __exit sha512_ssse3_mod_fini(void) { - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); + unregister_sha512_avx2(); + unregister_sha512_avx(); + unregister_sha512_ssse3(); } module_init(sha512_ssse3_mod_init); diff --git a/kernel/arch/x86/crypto/twofish_avx_glue.c b/kernel/arch/x86/crypto/twofish_avx_glue.c index b5e2d5651..b7a3904b9 100644 --- a/kernel/arch/x86/crypto/twofish_avx_glue.c +++ b/kernel/arch/x86/crypto/twofish_avx_glue.c @@ -36,9 +36,7 @@ #include <crypto/ctr.h> #include <crypto/lrw.h> #include <crypto/xts.h> -#include <asm/i387.h> -#include <asm/xcr.h> -#include <asm/xsave.h> +#include <asm/fpu/api.h> #include <asm/crypto/twofish.h> #include <asm/crypto/glue_helper.h> #include <crypto/scatterwalk.h> @@ -558,16 +556,10 @@ static struct crypto_alg twofish_algs[10] = { { static int __init twofish_init(void) { - u64 xcr0; + const char *feature_name; - if (!cpu_has_avx || !cpu_has_osxsave) { - printk(KERN_INFO "AVX instructions are not detected.\n"); - return -ENODEV; - } - - xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) { - printk(KERN_INFO "AVX detected but unusable.\n"); + if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, &feature_name)) { + pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } diff --git a/kernel/arch/x86/entry/Makefile b/kernel/arch/x86/entry/Makefile new file mode 100644 index 000000000..bd55dedd7 --- /dev/null +++ b/kernel/arch/x86/entry/Makefile @@ -0,0 +1,11 @@ +# +# Makefile for the x86 low level entry code +# +obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y += common.o + +obj-y += vdso/ +obj-y += vsyscall/ + +obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o + diff --git a/kernel/arch/x86/include/asm/calling.h b/kernel/arch/x86/entry/calling.h index 1c8b50edb..3c71dd947 100644 --- a/kernel/arch/x86/include/asm/calling.h +++ b/kernel/arch/x86/entry/calling.h @@ -46,8 +46,6 @@ For 32-bit we have the following conventions - kernel is built with */ -#include <asm/dwarf2.h> - #ifdef CONFIG_X86_64 /* @@ -91,28 +89,27 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro ALLOC_PT_GPREGS_ON_STACK addskip=0 - subq $15*8+\addskip, %rsp - CFI_ADJUST_CFA_OFFSET 15*8+\addskip + addq $-(15*8+\addskip), %rsp .endm .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 .if \r11 - movq_cfi r11, 6*8+\offset + movq %r11, 6*8+\offset(%rsp) .endif .if \r8910 - movq_cfi r10, 7*8+\offset - movq_cfi r9, 8*8+\offset - movq_cfi r8, 9*8+\offset + movq %r10, 7*8+\offset(%rsp) + movq %r9, 8*8+\offset(%rsp) + movq %r8, 9*8+\offset(%rsp) .endif .if \rax - movq_cfi rax, 10*8+\offset + movq %rax, 10*8+\offset(%rsp) .endif .if \rcx - movq_cfi rcx, 11*8+\offset + movq %rcx, 11*8+\offset(%rsp) .endif - movq_cfi rdx, 12*8+\offset - movq_cfi rsi, 13*8+\offset - movq_cfi rdi, 14*8+\offset + movq %rdx, 12*8+\offset(%rsp) + movq %rsi, 13*8+\offset(%rsp) + movq %rdi, 14*8+\offset(%rsp) .endm .macro SAVE_C_REGS offset=0 SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 @@ -131,24 +128,21 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro SAVE_EXTRA_REGS offset=0 - movq_cfi r15, 0*8+\offset - movq_cfi r14, 1*8+\offset - movq_cfi r13, 2*8+\offset - movq_cfi r12, 3*8+\offset - movq_cfi rbp, 4*8+\offset - movq_cfi rbx, 5*8+\offset - .endm - .macro SAVE_EXTRA_REGS_RBP offset=0 - movq_cfi rbp, 4*8+\offset + movq %r15, 0*8+\offset(%rsp) + movq %r14, 1*8+\offset(%rsp) + movq %r13, 2*8+\offset(%rsp) + movq %r12, 3*8+\offset(%rsp) + movq %rbp, 4*8+\offset(%rsp) + movq %rbx, 5*8+\offset(%rsp) .endm .macro RESTORE_EXTRA_REGS offset=0 - movq_cfi_restore 0*8+\offset, r15 - movq_cfi_restore 1*8+\offset, r14 - movq_cfi_restore 2*8+\offset, r13 - movq_cfi_restore 3*8+\offset, r12 - movq_cfi_restore 4*8+\offset, rbp - movq_cfi_restore 5*8+\offset, rbx + movq 0*8+\offset(%rsp), %r15 + movq 1*8+\offset(%rsp), %r14 + movq 2*8+\offset(%rsp), %r13 + movq 3*8+\offset(%rsp), %r12 + movq 4*8+\offset(%rsp), %rbp + movq 5*8+\offset(%rsp), %rbx .endm .macro ZERO_EXTRA_REGS @@ -162,24 +156,24 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1 .if \rstor_r11 - movq_cfi_restore 6*8, r11 + movq 6*8(%rsp), %r11 .endif .if \rstor_r8910 - movq_cfi_restore 7*8, r10 - movq_cfi_restore 8*8, r9 - movq_cfi_restore 9*8, r8 + movq 7*8(%rsp), %r10 + movq 8*8(%rsp), %r9 + movq 9*8(%rsp), %r8 .endif .if \rstor_rax - movq_cfi_restore 10*8, rax + movq 10*8(%rsp), %rax .endif .if \rstor_rcx - movq_cfi_restore 11*8, rcx + movq 11*8(%rsp), %rcx .endif .if \rstor_rdx - movq_cfi_restore 12*8, rdx + movq 12*8(%rsp), %rdx .endif - movq_cfi_restore 13*8, rsi - movq_cfi_restore 14*8, rdi + movq 13*8(%rsp), %rsi + movq 14*8(%rsp), %rdi .endm .macro RESTORE_C_REGS RESTORE_C_REGS_HELPER 1,1,1,1,1 @@ -196,16 +190,9 @@ For 32-bit we have the following conventions - kernel is built with .macro RESTORE_C_REGS_EXCEPT_RCX_R11 RESTORE_C_REGS_HELPER 1,0,0,1,1 .endm - .macro RESTORE_RSI_RDI - RESTORE_C_REGS_HELPER 0,0,0,0,0 - .endm - .macro RESTORE_RSI_RDI_RDX - RESTORE_C_REGS_HELPER 0,0,0,0,1 - .endm .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 - addq $15*8+\addskip, %rsp - CFI_ADJUST_CFA_OFFSET -(15*8+\addskip) + subq $-(15*8+\addskip), %rsp .endm .macro icebp @@ -224,23 +211,23 @@ For 32-bit we have the following conventions - kernel is built with */ .macro SAVE_ALL - pushl_cfi_reg eax - pushl_cfi_reg ebp - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg edx - pushl_cfi_reg ecx - pushl_cfi_reg ebx + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx .endm .macro RESTORE_ALL - popl_cfi_reg ebx - popl_cfi_reg ecx - popl_cfi_reg edx - popl_cfi_reg esi - popl_cfi_reg edi - popl_cfi_reg ebp - popl_cfi_reg eax + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax .endm #endif /* CONFIG_X86_64 */ diff --git a/kernel/arch/x86/entry/common.c b/kernel/arch/x86/entry/common.c new file mode 100644 index 000000000..3ec240f39 --- /dev/null +++ b/kernel/arch/x86/entry/common.c @@ -0,0 +1,493 @@ +/* + * common.c - C code for kernel entry and exit + * Copyright (c) 2015 Andrew Lutomirski + * GPL v2 + * + * Based on asm and ptrace code by many authors. The code here originated + * in ptrace.c and signal.c. + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/tracehook.h> +#include <linux/audit.h> +#include <linux/seccomp.h> +#include <linux/signal.h> +#include <linux/export.h> +#include <linux/context_tracking.h> +#include <linux/user-return-notifier.h> +#include <linux/uprobes.h> + +#include <asm/desc.h> +#include <asm/traps.h> +#include <asm/vdso.h> +#include <asm/uaccess.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs) +{ + unsigned long top_of_stack = + (unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING; + return (struct thread_info *)(top_of_stack - THREAD_SIZE); +} + +#ifdef CONFIG_CONTEXT_TRACKING +/* Called on entry from user mode with IRQs off. */ +__visible void enter_from_user_mode(void) +{ + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit(); +} +#endif + +static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) +{ +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + audit_syscall_entry(regs->orig_ax, regs->di, + regs->si, regs->dx, regs->r10); + } else +#endif + { + audit_syscall_entry(regs->orig_ax, regs->bx, + regs->cx, regs->dx, regs->si); + } +} + +/* + * We can return 0 to resume the syscall or anything else to go to phase + * 2. If we resume the syscall, we need to put something appropriate in + * regs->orig_ax. + * + * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax + * are fully functional. + * + * For phase 2's benefit, our return value is: + * 0: resume the syscall + * 1: go to phase 2; no seccomp phase 2 needed + * anything else: go to phase 2; pass return value to seccomp + */ +unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + unsigned long ret = 0; + u32 work; + + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + BUG_ON(regs != task_pt_regs(current)); + + work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + +#ifdef CONFIG_CONTEXT_TRACKING + /* + * If TIF_NOHZ is set, we are required to call user_exit() before + * doing anything that could touch RCU. + */ + if (work & _TIF_NOHZ) { + enter_from_user_mode(); + work &= ~_TIF_NOHZ; + } +#endif + +#ifdef CONFIG_SECCOMP + /* + * Do seccomp first -- it should minimize exposure of other + * code, and keeping seccomp fast is probably more valuable + * than the rest of this. + */ + if (work & _TIF_SECCOMP) { + struct seccomp_data sd; + + sd.arch = arch; + sd.nr = regs->orig_ax; + sd.instruction_pointer = regs->ip; +#ifdef CONFIG_X86_64 + if (arch == AUDIT_ARCH_X86_64) { + sd.args[0] = regs->di; + sd.args[1] = regs->si; + sd.args[2] = regs->dx; + sd.args[3] = regs->r10; + sd.args[4] = regs->r8; + sd.args[5] = regs->r9; + } else +#endif + { + sd.args[0] = regs->bx; + sd.args[1] = regs->cx; + sd.args[2] = regs->dx; + sd.args[3] = regs->si; + sd.args[4] = regs->di; + sd.args[5] = regs->bp; + } + + BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); + BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); + + ret = seccomp_phase1(&sd); + if (ret == SECCOMP_PHASE1_SKIP) { + regs->orig_ax = -1; + ret = 0; + } else if (ret != SECCOMP_PHASE1_OK) { + return ret; /* Go directly to phase 2 */ + } + + work &= ~_TIF_SECCOMP; + } +#endif + + /* Do our best to finish without phase 2. */ + if (work == 0) + return ret; /* seccomp and/or nohz only (ret == 0 here) */ + +#ifdef CONFIG_AUDITSYSCALL + if (work == _TIF_SYSCALL_AUDIT) { + /* + * If there is no more work to be done except auditing, + * then audit in phase 1. Phase 2 always audits, so, if + * we audit here, then we can't go on to phase 2. + */ + do_audit_syscall_entry(regs, arch); + return 0; + } +#endif + + return 1; /* Something is enabled that we can't handle in phase 1 */ +} + +/* Returns the syscall nr to run (which should match regs->orig_ax). */ +long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, + unsigned long phase1_result) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + long ret = 0; + u32 work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY; + + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) + BUG_ON(regs != task_pt_regs(current)); + + /* + * If we stepped into a sysenter/syscall insn, it trapped in + * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. + * If user-mode had set TF itself, then it's still clear from + * do_debug() and we need to set it again to restore the user + * state. If we entered on the slow path, TF was already set. + */ + if (work & _TIF_SINGLESTEP) + regs->flags |= X86_EFLAGS_TF; + +#ifdef CONFIG_SECCOMP + /* + * Call seccomp_phase2 before running the other hooks so that + * they can see any changes made by a seccomp tracer. + */ + if (phase1_result > 1 && seccomp_phase2(phase1_result)) { + /* seccomp failures shouldn't expose any additional code. */ + return -1; + } +#endif + + if (unlikely(work & _TIF_SYSCALL_EMU)) + ret = -1L; + + if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && + tracehook_report_syscall_entry(regs)) + ret = -1L; + + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) + trace_sys_enter(regs, regs->orig_ax); + + do_audit_syscall_entry(regs, arch); + + return ret ?: regs->orig_ax; +} + +long syscall_trace_enter(struct pt_regs *regs) +{ + u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; + unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); + + if (phase1_result == 0) + return regs->orig_ax; + else + return syscall_trace_enter_phase2(regs, arch, phase1_result); +} + +#define EXIT_TO_USERMODE_LOOP_FLAGS \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ + _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY) + +static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) +{ + /* + * In order to return to user mode, we need to have IRQs off with + * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY, + * _TIF_UPROBE, or _TIF_NEED_RESCHED set. Several of these flags + * can be set at any time on preemptable kernels if we have IRQs on, + * so we need to loop. Disabling preemption wouldn't help: doing the + * work to clear some of the flags can sleep. + */ + while (true) { + /* We have work to do. */ + local_irq_enable(); + + if (cached_flags & _TIF_NEED_RESCHED_MASK) + schedule(); + +#ifdef ARCH_RT_DELAYS_SIGNAL_SEND + if (unlikely(current->forced_info.si_signo)) { + struct task_struct *t = current; + force_sig_info(t->forced_info.si_signo, &t->forced_info, t); + t->forced_info.si_signo = 0; + } +#endif + if (cached_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + /* deal with pending signal delivery */ + if (cached_flags & _TIF_SIGPENDING) + do_signal(regs); + + if (cached_flags & _TIF_NOTIFY_RESUME) { + clear_thread_flag(TIF_NOTIFY_RESUME); + tracehook_notify_resume(regs); + } + + if (cached_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); + + /* Disable IRQs and retry */ + local_irq_disable(); + + cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags); + + if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) + break; + + } +} + +/* Called with IRQs disabled. */ +__visible inline void prepare_exit_to_usermode(struct pt_regs *regs) +{ + u32 cached_flags; + + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) + local_irq_disable(); + + lockdep_sys_exit(); + + cached_flags = + READ_ONCE(pt_regs_to_thread_info(regs)->flags); + + if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) + exit_to_usermode_loop(regs, cached_flags); + + user_enter(); +} + +#define SYSCALL_EXIT_WORK_FLAGS \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT) + +static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) +{ + bool step; + + audit_syscall_exit(regs); + + if (cached_flags & _TIF_SYSCALL_TRACEPOINT) + trace_sys_exit(regs, regs->ax); + + /* + * If TIF_SYSCALL_EMU is set, we only get here because of + * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). + * We already reported this syscall instruction in + * syscall_trace_enter(). + */ + step = unlikely( + (cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU)) + == _TIF_SINGLESTEP); + if (step || cached_flags & _TIF_SYSCALL_TRACE) + tracehook_report_syscall_exit(regs, step); +} + +/* + * Called with IRQs on and fully valid regs. Returns with IRQs off in a + * state such that we can immediately switch to user mode. + */ +__visible inline void syscall_return_slowpath(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + u32 cached_flags = READ_ONCE(ti->flags); + + CT_WARN_ON(ct_state() != CONTEXT_KERNEL); + + if (IS_ENABLED(CONFIG_PROVE_LOCKING) && + WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax)) + local_irq_enable(); + + /* + * First do one-time work. If these work items are enabled, we + * want to run them exactly once per syscall exit with IRQs on. + */ + if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS)) + syscall_slow_exit_work(regs, cached_flags); + +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. + */ + ti->status &= ~TS_COMPAT; +#endif + + local_irq_disable(); + prepare_exit_to_usermode(regs); +} + +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +/* + * Does a 32-bit syscall. Called with IRQs on and does all entry and + * exit work and returns with IRQs off. This function is extremely hot + * in workloads that use it, and it's usually called from + * do_fast_syscall_32, so forcibly inline it to improve performance. + */ +#ifdef CONFIG_X86_32 +/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */ +__visible +#else +/* 64-bit kernels use do_syscall_32_irqs_off() instead. */ +static +#endif +__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) +{ + struct thread_info *ti = pt_regs_to_thread_info(regs); + unsigned int nr = (unsigned int)regs->orig_ax; + +#ifdef CONFIG_IA32_EMULATION + ti->status |= TS_COMPAT; +#endif + + if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { + /* + * Subtlety here: if ptrace pokes something larger than + * 2^32-1 into orig_ax, this truncates it. This may or + * may not be necessary, but it matches the old asm + * behavior. + */ + nr = syscall_trace_enter(regs); + } + + if (likely(nr < IA32_NR_syscalls)) { + /* + * It's possible that a 32-bit syscall implementation + * takes a 64-bit parameter but nonetheless assumes that + * the high bits are zero. Make sure we zero-extend all + * of the args. + */ + regs->ax = ia32_sys_call_table[nr]( + (unsigned int)regs->bx, (unsigned int)regs->cx, + (unsigned int)regs->dx, (unsigned int)regs->si, + (unsigned int)regs->di, (unsigned int)regs->bp); + } + + syscall_return_slowpath(regs); +} + +#ifdef CONFIG_X86_64 +/* Handles INT80 on 64-bit kernels */ +__visible void do_syscall_32_irqs_off(struct pt_regs *regs) +{ + local_irq_enable(); + do_syscall_32_irqs_on(regs); +} +#endif + +/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ +__visible long do_fast_syscall_32(struct pt_regs *regs) +{ + /* + * Called using the internal vDSO SYSENTER/SYSCALL32 calling + * convention. Adjust regs so it looks like we entered using int80. + */ + + unsigned long landing_pad = (unsigned long)current->mm->context.vdso + + vdso_image_32.sym_int80_landing_pad; + + /* + * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward + * so that 'regs->ip -= 2' lands back on an int $0x80 instruction. + * Fix it up. + */ + regs->ip = landing_pad; + + /* + * Fetch EBP from where the vDSO stashed it. + * + * WARNING: We are in CONTEXT_USER and RCU isn't paying attention! + */ + local_irq_enable(); + if ( +#ifdef CONFIG_X86_64 + /* + * Micro-optimization: the pointer we're following is explicitly + * 32 bits, so it can't be out of range. + */ + __get_user(*(u32 *)®s->bp, + (u32 __user __force *)(unsigned long)(u32)regs->sp) +#else + get_user(*(u32 *)®s->bp, + (u32 __user __force *)(unsigned long)(u32)regs->sp) +#endif + ) { + + /* User code screwed up. */ + local_irq_disable(); + regs->ax = -EFAULT; +#ifdef CONFIG_CONTEXT_TRACKING + enter_from_user_mode(); +#endif + prepare_exit_to_usermode(regs); + return 0; /* Keep it simple: use IRET. */ + } + + /* Now this is just like a normal syscall. */ + do_syscall_32_irqs_on(regs); + +#ifdef CONFIG_X86_64 + /* + * Opportunistic SYSRETL: if possible, try to return using SYSRETL. + * SYSRETL is available on all 64-bit CPUs, so we don't need to + * bother with SYSEXIT. + * + * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP, + * because the ECX fixup above will ensure that this is essentially + * never the case. + */ + return regs->cs == __USER32_CS && regs->ss == __USER_DS && + regs->ip == landing_pad && + (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0; +#else + /* + * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT. + * + * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP, + * because the ECX fixup above will ensure that this is essentially + * never the case. + * + * We don't allow syscalls at all from VM86 mode, but we still + * need to check VM, because we might be returning from sys_vm86. + */ + return static_cpu_has(X86_FEATURE_SEP) && + regs->cs == __USER_CS && regs->ss == __USER_DS && + regs->ip == landing_pad && + (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; +#endif +} +#endif diff --git a/kernel/arch/x86/entry/entry_32.S b/kernel/arch/x86/entry/entry_32.S new file mode 100644 index 000000000..2d722ee01 --- /dev/null +++ b/kernel/arch/x86/entry/entry_32.S @@ -0,0 +1,1097 @@ +/* + * Copyright (C) 1991,1992 Linus Torvalds + * + * entry_32.S contains the system-call and low-level fault and trap handling routines. + * + * Stack layout while running C code: + * ptrace needs to have all registers on the stack. + * If the order here is changed, it needs to be + * updated in fork.c:copy_process(), signal.c:do_signal(), + * ptrace.c and ptrace.h + * + * 0(%esp) - %ebx + * 4(%esp) - %ecx + * 8(%esp) - %edx + * C(%esp) - %esi + * 10(%esp) - %edi + * 14(%esp) - %ebp + * 18(%esp) - %eax + * 1C(%esp) - %ds + * 20(%esp) - %es + * 24(%esp) - %fs + * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS + * 2C(%esp) - orig_eax + * 30(%esp) - %eip + * 34(%esp) - %cs + * 38(%esp) - %eflags + * 3C(%esp) - %oldesp + * 40(%esp) - %oldss + */ + +#include <linux/linkage.h> +#include <linux/err.h> +#include <asm/thread_info.h> +#include <asm/irqflags.h> +#include <asm/errno.h> +#include <asm/segment.h> +#include <asm/smp.h> +#include <asm/page_types.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> +#include <asm/ftrace.h> +#include <asm/irq_vectors.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> +#include <asm/asm.h> +#include <asm/smap.h> + + .section .entry.text, "ax" + +/* + * We use macros for low-level operations which need to be overridden + * for paravirtualization. The following will never clobber any registers: + * INTERRUPT_RETURN (aka. "iret") + * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") + * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). + * + * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must + * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). + * Allowing a register to be clobbered can shrink the paravirt replacement + * enough to patch inline, increasing performance. + */ + +#ifdef CONFIG_PREEMPT +# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF +#else +# define preempt_stop(clobbers) +# define resume_kernel restore_all +#endif + +.macro TRACE_IRQS_IRET +#ifdef CONFIG_TRACE_IRQFLAGS + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off? + jz 1f + TRACE_IRQS_ON +1: +#endif +.endm + +/* + * User gs save/restore + * + * %gs is used for userland TLS and kernel only uses it for stack + * canary which is required to be at %gs:20 by gcc. Read the comment + * at the top of stackprotector.h for more info. + * + * Local labels 98 and 99 are used. + */ +#ifdef CONFIG_X86_32_LAZY_GS + + /* unfortunately push/pop can't be no-op */ +.macro PUSH_GS + pushl $0 +.endm +.macro POP_GS pop=0 + addl $(4 + \pop), %esp +.endm +.macro POP_GS_EX +.endm + + /* all the rest are no-op */ +.macro PTGS_TO_GS +.endm +.macro PTGS_TO_GS_EX +.endm +.macro GS_TO_REG reg +.endm +.macro REG_TO_PTGS reg +.endm +.macro SET_KERNEL_GS reg +.endm + +#else /* CONFIG_X86_32_LAZY_GS */ + +.macro PUSH_GS + pushl %gs +.endm + +.macro POP_GS pop=0 +98: popl %gs + .if \pop <> 0 + add $\pop, %esp + .endif +.endm +.macro POP_GS_EX +.pushsection .fixup, "ax" +99: movl $0, (%esp) + jmp 98b +.popsection + _ASM_EXTABLE(98b, 99b) +.endm + +.macro PTGS_TO_GS +98: mov PT_GS(%esp), %gs +.endm +.macro PTGS_TO_GS_EX +.pushsection .fixup, "ax" +99: movl $0, PT_GS(%esp) + jmp 98b +.popsection + _ASM_EXTABLE(98b, 99b) +.endm + +.macro GS_TO_REG reg + movl %gs, \reg +.endm +.macro REG_TO_PTGS reg + movl \reg, PT_GS(%esp) +.endm +.macro SET_KERNEL_GS reg + movl $(__KERNEL_STACK_CANARY), \reg + movl \reg, %gs +.endm + +#endif /* CONFIG_X86_32_LAZY_GS */ + +.macro SAVE_ALL pt_regs_ax=%eax + cld + PUSH_GS + pushl %fs + pushl %es + pushl %ds + pushl \pt_regs_ax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + movl $(__USER_DS), %edx + movl %edx, %ds + movl %edx, %es + movl $(__KERNEL_PERCPU), %edx + movl %edx, %fs + SET_KERNEL_GS %edx +.endm + +.macro RESTORE_INT_REGS + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax +.endm + +.macro RESTORE_REGS pop=0 + RESTORE_INT_REGS +1: popl %ds +2: popl %es +3: popl %fs + POP_GS \pop +.pushsection .fixup, "ax" +4: movl $0, (%esp) + jmp 1b +5: movl $0, (%esp) + jmp 2b +6: movl $0, (%esp) + jmp 3b +.popsection + _ASM_EXTABLE(1b, 4b) + _ASM_EXTABLE(2b, 5b) + _ASM_EXTABLE(3b, 6b) + POP_GS_EX +.endm + +ENTRY(ret_from_fork) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + pushl $0x0202 # Reset kernel eflags + popfl + + /* When we fork, we trace the syscall return in the child, too. */ + movl %esp, %eax + call syscall_return_slowpath + jmp restore_all +END(ret_from_fork) + +ENTRY(ret_from_kernel_thread) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + pushl $0x0202 # Reset kernel eflags + popfl + movl PT_EBP(%esp), %eax + call *PT_EBX(%esp) + movl $0, PT_EAX(%esp) + + /* + * Kernel threads return to userspace as if returning from a syscall. + * We should check whether anything actually uses this path and, if so, + * consider switching it over to ret_from_fork. + */ + movl %esp, %eax + call syscall_return_slowpath + jmp restore_all +ENDPROC(ret_from_kernel_thread) + +/* + * Return to user mode is not as complex as all this looks, + * but we want the default path for a system call return to + * go as quickly as possible which is why some of this is + * less clear than it otherwise should be. + */ + + # userspace resumption stub bypassing syscall exit tracing + ALIGN +ret_from_exception: + preempt_stop(CLBR_ANY) +ret_from_intr: + GET_THREAD_INFO(%ebp) +#ifdef CONFIG_VM86 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax +#else + /* + * We can be coming here from child spawned by kernel_thread(). + */ + movl PT_CS(%esp), %eax + andl $SEGMENT_RPL_MASK, %eax +#endif + cmpl $USER_RPL, %eax + jb resume_kernel # not returning to v8086 or userspace + +ENTRY(resume_userspace) + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + movl %esp, %eax + call prepare_exit_to_usermode + jmp restore_all +END(ret_from_exception) + +#ifdef CONFIG_PREEMPT +ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) +need_resched: + # preempt count == 0 + NEED_RS set? + cmpl $0, PER_CPU_VAR(__preempt_count) +#ifndef CONFIG_PREEMPT_LAZY + jnz restore_all +#else + jz test_int_off + + # atleast preempt count == 0 ? + cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) + jne restore_all + + cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? + jnz restore_all + + testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp) + jz restore_all +test_int_off: +#endif + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq + jmp need_resched +END(resume_kernel) +#endif + + # SYSENTER call handler stub +ENTRY(entry_SYSENTER_32) + movl TSS_sysenter_sp0(%esp), %esp +sysenter_past_esp: + pushl $__USER_DS /* pt_regs->ss */ + pushl %ebp /* pt_regs->sp (stashed in bp) */ + pushfl /* pt_regs->flags (except IF = 0) */ + orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ + pushl $__USER_CS /* pt_regs->cs */ + pushl $0 /* pt_regs->ip = 0 (placeholder) */ + pushl %eax /* pt_regs->orig_ax */ + SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + + /* + * User mode is traced as though IRQs are on, and SYSENTER + * turned them off. + */ + TRACE_IRQS_OFF + + movl %esp, %eax + call do_fast_syscall_32 + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + +/* Opportunistic SYSEXIT */ + TRACE_IRQS_ON /* User mode traces as IRQs on. */ + movl PT_EIP(%esp), %edx /* pt_regs->ip */ + movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */ +1: mov PT_FS(%esp), %fs + PTGS_TO_GS + popl %ebx /* pt_regs->bx */ + addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */ + popl %esi /* pt_regs->si */ + popl %edi /* pt_regs->di */ + popl %ebp /* pt_regs->bp */ + popl %eax /* pt_regs->ax */ + + /* + * Return back to the vDSO, which will pop ecx and edx. + * Don't bother with DS and ES (they already contain __USER_DS). + */ + ENABLE_INTERRUPTS_SYSEXIT + +.pushsection .fixup, "ax" +2: movl $0, PT_FS(%esp) + jmp 1b +.popsection + _ASM_EXTABLE(1b, 2b) + PTGS_TO_GS_EX +ENDPROC(entry_SYSENTER_32) + + # system call handler stub +ENTRY(entry_INT80_32) + ASM_CLAC + pushl %eax /* pt_regs->orig_ax */ + SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */ + + /* + * User mode is traced as though IRQs are on. Unlike the 64-bit + * case, INT80 is a trap gate on 32-bit kernels, so interrupts + * are already on (unless user code is messing around with iopl). + */ + + movl %esp, %eax + call do_syscall_32_irqs_on +.Lsyscall_32_done: + +restore_all: + TRACE_IRQS_IRET +restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + /* + * Warning: PT_OLDSS(%esp) contains the wrong/random values if we + * are returning to the kernel. + * See comments in process.c:copy_thread() for details. + */ + movb PT_OLDSS(%esp), %ah + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax + cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax + je ldt_ss # returning to user-space with LDT SS +#endif +restore_nocheck: + RESTORE_REGS 4 # skip orig_eax/error_code +irq_return: + INTERRUPT_RETURN +.section .fixup, "ax" +ENTRY(iret_exc ) + pushl $0 # no error code + pushl $do_iret_error + jmp error_code +.previous + _ASM_EXTABLE(irq_return, iret_exc) + +#ifdef CONFIG_X86_ESPFIX32 +ldt_ss: +#ifdef CONFIG_PARAVIRT + /* + * The kernel can't run on a non-flat stack if paravirt mode + * is active. Rather than try to fixup the high bits of + * ESP, bypass this code entirely. This may break DOSemu + * and/or Wine support in a paravirt VM, although the option + * is still available to implement the setting of the high + * 16-bits in the INTERRUPT_RETURN paravirt-op. + */ + cmpl $0, pv_info+PARAVIRT_enabled + jne restore_nocheck +#endif + +/* + * Setup and switch to ESPFIX stack + * + * We're returning to userspace with a 16 bit stack. The CPU will not + * restore the high word of ESP for us on executing iret... This is an + * "official" bug of all the x86-compatible CPUs, which we can work + * around to make dosemu and wine happy. We do this by preloading the + * high word of ESP with the high word of the userspace ESP while + * compensating for the offset by changing to the ESPFIX segment with + * a base address that matches for the difference. + */ +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) + mov %esp, %edx /* load kernel esp */ + mov PT_OLDESP(%esp), %eax /* load userspace esp */ + mov %dx, %ax /* eax: new kernel esp */ + sub %eax, %edx /* offset (low word is 0) */ + shr $16, %edx + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ + pushl $__ESPFIX_SS + pushl %eax /* new kernel esp */ + /* + * Disable interrupts, but do not irqtrace this section: we + * will soon execute iret and the tracer was already set to + * the irqstate after the IRET: + */ + DISABLE_INTERRUPTS(CLBR_EAX) + lss (%esp), %esp /* switch to espfix segment */ + jmp restore_nocheck +#endif +ENDPROC(entry_INT80_32) + +.macro FIXUP_ESPFIX_STACK +/* + * Switch back for ESPFIX stack to the normal zerobased stack + * + * We can't call C functions using the ESPFIX stack. This code reads + * the high word of the segment base from the GDT and swiches to the + * normal stack and adjusts ESP with the matching offset. + */ +#ifdef CONFIG_X86_ESPFIX32 + /* fixup the stack */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ + shl $16, %eax + addl %esp, %eax /* the adjusted stack pointer */ + pushl $__KERNEL_DS + pushl %eax + lss (%esp), %esp /* switch to the normal stack segment */ +#endif +.endm +.macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 + movl %ss, %eax + /* see if on espfix stack */ + cmpw $__ESPFIX_SS, %ax + jne 27f + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + /* switch to normal stack */ + FIXUP_ESPFIX_STACK +27: +#endif +.endm + +/* + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. + */ + .align 8 +ENTRY(irq_entries_start) + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushl $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt + .align 8 + .endr +END(irq_entries_start) + +/* + * the CPU automatically disables interrupts when executing an IRQ vector, + * so IRQ-flags tracing has to follow that: + */ + .p2align CONFIG_X86_L1_CACHE_SHIFT +common_interrupt: + ASM_CLAC + addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */ + SAVE_ALL + TRACE_IRQS_OFF + movl %esp, %eax + call do_IRQ + jmp ret_from_intr +ENDPROC(common_interrupt) + +#define BUILD_INTERRUPT3(name, nr, fn) \ +ENTRY(name) \ + ASM_CLAC; \ + pushl $~(nr); \ + SAVE_ALL; \ + TRACE_IRQS_OFF \ + movl %esp, %eax; \ + call fn; \ + jmp ret_from_intr; \ +ENDPROC(name) + + +#ifdef CONFIG_TRACING +# define TRACE_BUILD_INTERRUPT(name, nr) BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) +#else +# define TRACE_BUILD_INTERRUPT(name, nr) +#endif + +#define BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(name, nr, smp_##name); \ + TRACE_BUILD_INTERRUPT(name, nr) + +/* The include is where all of the SMP etc. interrupts come from */ +#include <asm/entry_arch.h> + +ENTRY(coprocessor_error) + ASM_CLAC + pushl $0 + pushl $do_coprocessor_error + jmp error_code +END(coprocessor_error) + +ENTRY(simd_coprocessor_error) + ASM_CLAC + pushl $0 +#ifdef CONFIG_X86_INVD_BUG + /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ + ALTERNATIVE "pushl $do_general_protection", \ + "pushl $do_simd_coprocessor_error", \ + X86_FEATURE_XMM +#else + pushl $do_simd_coprocessor_error +#endif + jmp error_code +END(simd_coprocessor_error) + +ENTRY(device_not_available) + ASM_CLAC + pushl $-1 # mark this as an int + pushl $do_device_not_available + jmp error_code +END(device_not_available) + +#ifdef CONFIG_PARAVIRT +ENTRY(native_iret) + iret + _ASM_EXTABLE(native_iret, iret_exc) +END(native_iret) + +ENTRY(native_irq_enable_sysexit) + sti + sysexit +END(native_irq_enable_sysexit) +#endif + +ENTRY(overflow) + ASM_CLAC + pushl $0 + pushl $do_overflow + jmp error_code +END(overflow) + +ENTRY(bounds) + ASM_CLAC + pushl $0 + pushl $do_bounds + jmp error_code +END(bounds) + +ENTRY(invalid_op) + ASM_CLAC + pushl $0 + pushl $do_invalid_op + jmp error_code +END(invalid_op) + +ENTRY(coprocessor_segment_overrun) + ASM_CLAC + pushl $0 + pushl $do_coprocessor_segment_overrun + jmp error_code +END(coprocessor_segment_overrun) + +ENTRY(invalid_TSS) + ASM_CLAC + pushl $do_invalid_TSS + jmp error_code +END(invalid_TSS) + +ENTRY(segment_not_present) + ASM_CLAC + pushl $do_segment_not_present + jmp error_code +END(segment_not_present) + +ENTRY(stack_segment) + ASM_CLAC + pushl $do_stack_segment + jmp error_code +END(stack_segment) + +ENTRY(alignment_check) + ASM_CLAC + pushl $do_alignment_check + jmp error_code +END(alignment_check) + +ENTRY(divide_error) + ASM_CLAC + pushl $0 # no error code + pushl $do_divide_error + jmp error_code +END(divide_error) + +#ifdef CONFIG_X86_MCE +ENTRY(machine_check) + ASM_CLAC + pushl $0 + pushl machine_check_vector + jmp error_code +END(machine_check) +#endif + +ENTRY(spurious_interrupt_bug) + ASM_CLAC + pushl $0 + pushl $do_spurious_interrupt_bug + jmp error_code +END(spurious_interrupt_bug) + +#ifdef CONFIG_XEN +/* + * Xen doesn't set %esp to be precisely what the normal SYSENTER + * entry point expects, so fix it up before using the normal path. + */ +ENTRY(xen_sysenter_target) + addl $5*4, %esp /* remove xen-provided frame */ + jmp sysenter_past_esp + +ENTRY(xen_hypervisor_callback) + pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + TRACE_IRQS_OFF + + /* + * Check to see if we got the event in the critical + * region in xen_iret_direct, after we've reenabled + * events and checked for pending events. This simulates + * iret instruction's behaviour where it delivers a + * pending interrupt when enabling interrupts: + */ + movl PT_EIP(%esp), %eax + cmpl $xen_iret_start_crit, %eax + jb 1f + cmpl $xen_iret_end_crit, %eax + jae 1f + + jmp xen_iret_crit_fixup + +ENTRY(xen_do_upcall) +1: mov %esp, %eax + call xen_evtchn_do_upcall +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif + jmp ret_from_intr +ENDPROC(xen_hypervisor_callback) + +/* + * Hypervisor uses this for application faults while it executes. + * We get here for two reasons: + * 1. Fault while reloading DS, ES, FS or GS + * 2. Fault while executing IRET + * Category 1 we fix up by reattempting the load, and zeroing the segment + * register if the load fails. + * Category 2 we fix up by jumping to do_iret_error. We cannot use the + * normal Linux return path in this case because if we use the IRET hypercall + * to pop the stack frame we end up in an infinite loop of failsafe callbacks. + * We distinguish between categories by maintaining a status value in EAX. + */ +ENTRY(xen_failsafe_callback) + pushl %eax + movl $1, %eax +1: mov 4(%esp), %ds +2: mov 8(%esp), %es +3: mov 12(%esp), %fs +4: mov 16(%esp), %gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ + testl %eax, %eax + popl %eax + lea 16(%esp), %esp + jz 5f + jmp iret_exc +5: pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + jmp ret_from_exception + +.section .fixup, "ax" +6: xorl %eax, %eax + movl %eax, 4(%esp) + jmp 1b +7: xorl %eax, %eax + movl %eax, 8(%esp) + jmp 2b +8: xorl %eax, %eax + movl %eax, 12(%esp) + jmp 3b +9: xorl %eax, %eax + movl %eax, 16(%esp) + jmp 4b +.previous + _ASM_EXTABLE(1b, 6b) + _ASM_EXTABLE(2b, 7b) + _ASM_EXTABLE(3b, 8b) + _ASM_EXTABLE(4b, 9b) +ENDPROC(xen_failsafe_callback) + +BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + xen_evtchn_do_upcall) + +#endif /* CONFIG_XEN */ + +#if IS_ENABLED(CONFIG_HYPERV) + +BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + hyperv_vector_handler) + +#endif /* CONFIG_HYPERV */ + +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(mcount) + ret +END(mcount) + +ENTRY(ftrace_caller) + pushl %eax + pushl %ecx + pushl %edx + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax + movl 0x4(%ebp), %edx + movl function_trace_op, %ecx + subl $MCOUNT_INSN_SIZE, %eax + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + addl $4, %esp /* skip NULL pointer */ + popl %edx + popl %ecx + popl %eax +ftrace_ret: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.globl ftrace_graph_call +ftrace_graph_call: + jmp ftrace_stub +#endif + +.globl ftrace_stub +ftrace_stub: + ret +END(ftrace_caller) + +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS, 13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + + popf + jmp ftrace_stub +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(mcount) + cmpl $__PAGE_OFFSET, %esp + jb ftrace_stub /* Paging not enabled yet? */ + + cmpl $ftrace_stub, ftrace_trace_function + jnz trace +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + cmpl $ftrace_stub, ftrace_graph_return + jnz ftrace_graph_caller + + cmpl $ftrace_graph_entry_stub, ftrace_graph_entry + jnz ftrace_graph_caller +#endif +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +trace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + subl $MCOUNT_INSN_SIZE, %eax + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + lea 0x4(%ebp), %edx + movl (%ebp), %ecx + subl $MCOUNT_INSN_SIZE, %eax + call prepare_ftrace_return + popl %edx + popl %ecx + popl %eax + ret +END(ftrace_graph_caller) + +.globl return_to_handler +return_to_handler: + pushl %eax + pushl %edx + movl %ebp, %eax + call ftrace_return_to_handler + movl %eax, %ecx + popl %edx + popl %eax + jmp *%ecx +#endif + +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + ASM_CLAC + pushl $trace_do_page_fault + jmp error_code +END(trace_page_fault) +#endif + +ENTRY(page_fault) + ASM_CLAC + pushl $do_page_fault + ALIGN +error_code: + /* the function address is in %gs's slot on the stack */ + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + cld + movl $(__KERNEL_PERCPU), %ecx + movl %ecx, %fs + UNWIND_ESPFIX_STACK + GS_TO_REG %ecx + movl PT_GS(%esp), %edi # get the function address + movl PT_ORIG_EAX(%esp), %edx # get the error code + movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart + REG_TO_PTGS %ecx + SET_KERNEL_GS %ecx + movl $(__USER_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + TRACE_IRQS_OFF + movl %esp, %eax # pt_regs pointer + call *%edi + jmp ret_from_exception +END(page_fault) + +/* + * Debug traps and NMI can happen at the one SYSENTER instruction + * that sets up the real kernel stack. Check here, since we can't + * allow the wrong stack to be used. + * + * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have + * already pushed 3 words if it hits on the sysenter instruction: + * eflags, cs and eip. + * + * We just load the right stack, and push the three (known) values + * by hand onto the new stack - while updating the return eip past + * the instruction that would have done it for sysenter. + */ +.macro FIX_STACK offset ok label + cmpw $__KERNEL_CS, 4(%esp) + jne \ok +\label: + movl TSS_sysenter_sp0 + \offset(%esp), %esp + pushfl + pushl $__KERNEL_CS + pushl $sysenter_past_esp +.endm + +ENTRY(debug) + ASM_CLAC + cmpl $entry_SYSENTER_32, (%esp) + jne debug_stack_correct + FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn +debug_stack_correct: + pushl $-1 # mark this as an int + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx, %edx # error code 0 + movl %esp, %eax # pt_regs pointer + call do_debug + jmp ret_from_exception +END(debug) + +/* + * NMI is doubly nasty. It can happen _while_ we're handling + * a debug fault, and the debug fault hasn't yet been able to + * clear up the stack. So we first check whether we got an + * NMI on the sysenter entry path, but after that we need to + * check whether we got an NMI on the debug path where the debug + * fault happened on the sysenter path. + */ +ENTRY(nmi) + ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 + pushl %eax + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl %eax + je nmi_espfix_stack +#endif + cmpl $entry_SYSENTER_32, (%esp) + je nmi_stack_fixup + pushl %eax + movl %esp, %eax + /* + * Do not access memory above the end of our stack page, + * it might not exist. + */ + andl $(THREAD_SIZE-1), %eax + cmpl $(THREAD_SIZE-20), %eax + popl %eax + jae nmi_stack_correct + cmpl $entry_SYSENTER_32, 12(%esp) + je nmi_debug_stack_check +nmi_stack_correct: + pushl %eax + SAVE_ALL + xorl %edx, %edx # zero error code + movl %esp, %eax # pt_regs pointer + call do_nmi + jmp restore_all_notrace + +nmi_stack_fixup: + FIX_STACK 12, nmi_stack_correct, 1 + jmp nmi_stack_correct + +nmi_debug_stack_check: + cmpw $__KERNEL_CS, 16(%esp) + jne nmi_stack_correct + cmpl $debug, (%esp) + jb nmi_stack_correct + cmpl $debug_esp_fix_insn, (%esp) + ja nmi_stack_correct + FIX_STACK 24, nmi_stack_correct, 1 + jmp nmi_stack_correct + +#ifdef CONFIG_X86_ESPFIX32 +nmi_espfix_stack: + /* + * create the pointer to lss back + */ + pushl %ss + pushl %esp + addl $4, (%esp) + /* copy the iret frame of 12 bytes */ + .rept 3 + pushl 16(%esp) + .endr + pushl %eax + SAVE_ALL + FIXUP_ESPFIX_STACK # %eax == %esp + xorl %edx, %edx # zero error code + call do_nmi + RESTORE_REGS + lss 12+4(%esp), %esp # back to espfix stack + jmp irq_return +#endif +END(nmi) + +ENTRY(int3) + ASM_CLAC + pushl $-1 # mark this as an int + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx, %edx # zero error code + movl %esp, %eax # pt_regs pointer + call do_int3 + jmp ret_from_exception +END(int3) + +ENTRY(general_protection) + pushl $do_general_protection + jmp error_code +END(general_protection) + +#ifdef CONFIG_KVM_GUEST +ENTRY(async_page_fault) + ASM_CLAC + pushl $do_async_page_fault + jmp error_code +END(async_page_fault) +#endif diff --git a/kernel/arch/x86/kernel/entry_64.S b/kernel/arch/x86/entry/entry_64.S index 8a3445bdf..316081a2c 100644 --- a/kernel/arch/x86/kernel/entry_64.S +++ b/kernel/arch/x86/entry/entry_64.S @@ -4,34 +4,25 @@ * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> - */ - -/* + * * entry.S contains the system-call and fault low-level handling routines. * * Some of this is documented in Documentation/x86/entry_64.txt * - * NOTE: This code handles signal-recognition, which happens every time - * after an interrupt and after each system call. - * * A note on terminology: - * - iret frame: Architecture defined interrupt frame from SS to RIP - * at the top of the kernel process stack. + * - iret frame: Architecture defined interrupt frame from SS to RIP + * at the top of the kernel process stack. * * Some macro usage: - * - CFI macros are used to generate dwarf2 unwind information for better - * backtraces. They don't change any code. - * - ENTRY/END Define functions in the symbol table. - * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. - * - idtentry - Define exception entry points. + * - ENTRY/END: Define functions in the symbol table. + * - TRACE_IRQ_*: Trace hardirq state for lock debugging. + * - idtentry: Define exception entry points. */ - #include <linux/linkage.h> #include <asm/segment.h> #include <asm/cache.h> #include <asm/errno.h> -#include <asm/dwarf2.h> -#include <asm/calling.h> +#include "calling.h" #include <asm/asm-offsets.h> #include <asm/msr.h> #include <asm/unistd.h> @@ -42,20 +33,18 @@ #include <asm/paravirt.h> #include <asm/percpu.h> #include <asm/asm.h> -#include <asm/context_tracking.h> #include <asm/smap.h> #include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ #include <linux/elf-em.h> -#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_64BIT 0x80000000 -#define __AUDIT_ARCH_LE 0x40000000 - - .code64 - .section .entry.text, "ax" +#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_64BIT 0x80000000 +#define __AUDIT_ARCH_LE 0x40000000 +.code64 +.section .entry.text, "ax" #ifdef CONFIG_PARAVIRT ENTRY(native_usergs_sysret64) @@ -64,11 +53,10 @@ ENTRY(native_usergs_sysret64) ENDPROC(native_usergs_sysret64) #endif /* CONFIG_PARAVIRT */ - .macro TRACE_IRQS_IRETQ #ifdef CONFIG_TRACE_IRQFLAGS - bt $9,EFLAGS(%rsp) /* interrupts off? */ - jnc 1f + bt $9, EFLAGS(%rsp) /* interrupts off? */ + jnc 1f TRACE_IRQS_ON 1: #endif @@ -88,89 +76,34 @@ ENDPROC(native_usergs_sysret64) #if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS) .macro TRACE_IRQS_OFF_DEBUG - call debug_stack_set_zero + call debug_stack_set_zero TRACE_IRQS_OFF - call debug_stack_reset + call debug_stack_reset .endm .macro TRACE_IRQS_ON_DEBUG - call debug_stack_set_zero + call debug_stack_set_zero TRACE_IRQS_ON - call debug_stack_reset + call debug_stack_reset .endm .macro TRACE_IRQS_IRETQ_DEBUG - bt $9,EFLAGS(%rsp) /* interrupts off? */ - jnc 1f + bt $9, EFLAGS(%rsp) /* interrupts off? */ + jnc 1f TRACE_IRQS_ON_DEBUG 1: .endm #else -# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF -# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON -# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ +# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF +# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON +# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ #endif /* - * empty frame - */ - .macro EMPTY_FRAME start=1 offset=0 - .if \start - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,8+\offset - .else - CFI_DEF_CFA_OFFSET 8+\offset - .endif - .endm - -/* - * initial frame state for interrupts (and exceptions without error code) - */ - .macro INTR_FRAME start=1 offset=0 - EMPTY_FRAME \start, 5*8+\offset - /*CFI_REL_OFFSET ss, 4*8+\offset*/ - CFI_REL_OFFSET rsp, 3*8+\offset - /*CFI_REL_OFFSET rflags, 2*8+\offset*/ - /*CFI_REL_OFFSET cs, 1*8+\offset*/ - CFI_REL_OFFSET rip, 0*8+\offset - .endm - -/* - * initial frame state for exceptions with error code (and interrupts - * with vector already pushed) - */ - .macro XCPT_FRAME start=1 offset=0 - INTR_FRAME \start, 1*8+\offset - .endm - -/* - * frame that enables passing a complete pt_regs to a C function. - */ - .macro DEFAULT_FRAME start=1 offset=0 - XCPT_FRAME \start, ORIG_RAX+\offset - CFI_REL_OFFSET rdi, RDI+\offset - CFI_REL_OFFSET rsi, RSI+\offset - CFI_REL_OFFSET rdx, RDX+\offset - CFI_REL_OFFSET rcx, RCX+\offset - CFI_REL_OFFSET rax, RAX+\offset - CFI_REL_OFFSET r8, R8+\offset - CFI_REL_OFFSET r9, R9+\offset - CFI_REL_OFFSET r10, R10+\offset - CFI_REL_OFFSET r11, R11+\offset - CFI_REL_OFFSET rbx, RBX+\offset - CFI_REL_OFFSET rbp, RBP+\offset - CFI_REL_OFFSET r12, R12+\offset - CFI_REL_OFFSET r13, R13+\offset - CFI_REL_OFFSET r14, R14+\offset - CFI_REL_OFFSET r15, R15+\offset - .endm - -/* - * 64bit SYSCALL instruction entry. Up to 6 arguments in registers. + * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers. * - * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, * then loads new ss, cs, and rip from previously programmed MSRs. * rflags gets masked by a value from another MSR (so CLD and CLAC * are not needed). SYSCALL does not save anything on the stack @@ -186,7 +119,7 @@ ENDPROC(native_usergs_sysret64) * r10 arg3 (needs to be moved to rcx to conform to C ABI) * r8 arg4 * r9 arg5 - * (note: r12-r15,rbp,rbx are callee-preserved in C ABI) + * (note: r12-r15, rbp, rbx are callee-preserved in C ABI) * * Only called from user space. * @@ -195,13 +128,7 @@ ENDPROC(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ -ENTRY(system_call) - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rip,rcx - /*CFI_REGISTER rflags,r11*/ - +ENTRY(entry_SYSCALL_64) /* * Interrupts are off on entry. * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, @@ -213,14 +140,14 @@ ENTRY(system_call) * after the swapgs, so that it can do the swapgs * for the guest and jump here on syscall. */ -GLOBAL(system_call_after_swapgs) +GLOBAL(entry_SYSCALL_64_after_swapgs) - movq %rsp,PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack),%rsp + movq %rsp, PER_CPU_VAR(rsp_scratch) + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* Construct struct pt_regs on stack */ - pushq_cfi $__USER_DS /* pt_regs->ss */ - pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ + pushq $__USER_DS /* pt_regs->ss */ + pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ /* * Re-enable interrupts. * We use 'rsp_scratch' as a scratch space, hence irq-off block above @@ -229,36 +156,34 @@ GLOBAL(system_call_after_swapgs) * with using rsp_scratch: */ ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %r11 /* pt_regs->flags */ - pushq_cfi $__USER_CS /* pt_regs->cs */ - pushq_cfi %rcx /* pt_regs->ip */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi $-ENOSYS /* pt_regs->ax */ - pushq_cfi_reg r8 /* pt_regs->r8 */ - pushq_cfi_reg r9 /* pt_regs->r9 */ - pushq_cfi_reg r10 /* pt_regs->r10 */ - pushq_cfi_reg r11 /* pt_regs->r11 */ - sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 6*8 - - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz tracesys -system_call_fastpath: + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */ + + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz tracesys +entry_SYSCALL_64_fastpath: #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max,%rax + cmpq $__NR_syscall_max, %rax #else - andl $__SYSCALL_MASK,%eax - cmpl $__NR_syscall_max,%eax + andl $__SYSCALL_MASK, %eax + cmpl $__NR_syscall_max, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10,%rcx - call *sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + movq %r10, %rcx + call *sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) 1: /* * Syscall return path ending with SYSRET (fast path). @@ -279,19 +204,15 @@ system_call_fastpath: * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is * very bad. */ - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ - - CFI_REMEMBER_STATE + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ RESTORE_C_REGS_EXCEPT_RCX_R11 - movq RIP(%rsp),%rcx - CFI_REGISTER rip,rcx - movq EFLAGS(%rsp),%r11 - /*CFI_REGISTER rflags,r11*/ - movq RSP(%rsp),%rsp + movq RIP(%rsp), %rcx + movq EFLAGS(%rsp), %r11 + movq RSP(%rsp), %rsp /* - * 64bit SYSRET restores rip from rcx, + * 64-bit SYSRET restores rip from rcx, * rflags from r11 (but RF and VM bits are forced to 0), * cs and ss are loaded from MSRs. * Restoration of rflags re-enables interrupts. @@ -307,25 +228,28 @@ system_call_fastpath: */ USERGS_SYSRET64 - CFI_RESTORE_STATE +GLOBAL(int_ret_from_sys_call_irqs_off) + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + jmp int_ret_from_sys_call /* Do syscall entry tracing */ tracesys: - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - call syscall_trace_enter_phase1 - test %rax, %rax - jnz tracesys_phase2 /* if needed, run the slow path */ - RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ - movq ORIG_RAX(%rsp), %rax - jmp system_call_fastpath /* and return to the fast path */ + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ + movq ORIG_RAX(%rsp), %rax + jmp entry_SYSCALL_64_fastpath /* and return to the fast path */ tracesys_phase2: SAVE_EXTRA_REGS - movq %rsp, %rdi - movl $AUDIT_ARCH_X86_64, %esi - movq %rax,%rdx - call syscall_trace_enter_phase2 + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi + movq %rax, %rdx + call syscall_trace_enter_phase2 /* * Reload registers from stack in case ptrace changed them. @@ -335,15 +259,15 @@ tracesys_phase2: RESTORE_C_REGS_EXCEPT_RAX RESTORE_EXTRA_REGS #if __SYSCALL_MASK == ~0 - cmpq $__NR_syscall_max,%rax + cmpq $__NR_syscall_max, %rax #else - andl $__SYSCALL_MASK,%eax - cmpl $__NR_syscall_max,%eax + andl $__SYSCALL_MASK, %eax + cmpl $__NR_syscall_max, %eax #endif - ja 1f /* return -ENOSYS (already in pt_regs->ax) */ - movq %r10,%rcx /* fixup for C */ - call *sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + movq %r10, %rcx /* fixup for C */ + call *sys_call_table(, %rax, 8) + movq %rax, RAX(%rsp) 1: /* Use IRET because user could have changed pt_regs->foo */ @@ -352,100 +276,47 @@ tracesys_phase2: * Has correct iret frame. */ GLOBAL(int_ret_from_sys_call) - DISABLE_INTERRUPTS(CLBR_NONE) -int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */ - TRACE_IRQS_OFF - movl $_TIF_ALLWORK_MASK,%edi - /* edi: mask to check */ -GLOBAL(int_with_check) - LOCKDEP_SYS_EXIT_IRQ - GET_THREAD_INFO(%rcx) - movl TI_flags(%rcx),%edx - andl %edi,%edx - jnz int_careful - andl $~TS_COMPAT,TI_status(%rcx) - jmp syscall_return - - /* Either reschedule or signal or syscall exit tracking needed. */ - /* First do a reschedule test. */ - /* edx: work, edi: workmask */ -int_careful: - testl $_TIF_NEED_RESCHED_MASK,%edx - jz int_very_careful - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi - SCHEDULE_USER - popq_cfi %rdi - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - - /* handle signals and tracing -- both require a full pt_regs */ -int_very_careful: - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) SAVE_EXTRA_REGS - /* Check for syscall exit trace */ - testl $_TIF_WORK_SYSCALL_EXIT,%edx - jz int_signal - pushq_cfi %rdi - leaq 8(%rsp),%rdi # &ptregs -> arg1 - call syscall_trace_leave - popq_cfi %rdi - andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi - jmp int_restore_rest - -int_signal: - testl $_TIF_DO_NOTIFY_MASK,%edx - jz 1f - movq %rsp,%rdi # &ptregs -> arg1 - xorl %esi,%esi # oldset -> arg2 - call do_notify_resume -1: movl $_TIF_WORK_MASK,%edi -int_restore_rest: + movq %rsp, %rdi + call syscall_return_slowpath /* returns with IRQs disabled */ RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp int_with_check - -syscall_return: - /* The IRETQ could re-enable interrupts: */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_IRETQ + TRACE_IRQS_IRETQ /* we're about to change IF */ /* * Try to use SYSRET instead of IRET if we're returning to * a completely clean 64-bit userspace context. */ - movq RCX(%rsp),%rcx - cmpq %rcx,RIP(%rsp) /* RCX == RIP */ - jne opportunistic_sysret_failed + movq RCX(%rsp), %rcx + movq RIP(%rsp), %r11 + cmpq %rcx, %r11 /* RCX == RIP */ + jne opportunistic_sysret_failed /* * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP * in kernel space. This essentially lets the user take over - * the kernel, since userspace controls RSP. It's not worth - * testing for canonicalness exactly -- this check detects any - * of the 17 high bits set, which is true for non-canonical - * or kernel addresses. (This will pessimize vsyscall=native. - * Big deal.) + * the kernel, since userspace controls RSP. * - * If virtual addresses ever become wider, this will need + * If width of "canonical tail" ever becomes variable, this will need * to be updated to remain correct on both old and new CPUs. */ .ifne __VIRTUAL_MASK_SHIFT - 47 .error "virtual address width changed -- SYSRET checks need update" .endif - shr $__VIRTUAL_MASK_SHIFT, %rcx - jnz opportunistic_sysret_failed - cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */ - jne opportunistic_sysret_failed + /* Change top 16 bits to be the sign-extension of 47th bit */ + shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx + sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx - movq R11(%rsp),%r11 - cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */ - jne opportunistic_sysret_failed + /* If this changed %rcx, it was not canonical */ + cmpq %rcx, %r11 + jne opportunistic_sysret_failed + + cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */ + jne opportunistic_sysret_failed + + movq R11(%rsp), %r11 + cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */ + jne opportunistic_sysret_failed /* * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, @@ -454,47 +325,41 @@ syscall_return: * with register state that satisfies the opportunistic SYSRET * conditions. For example, single-stepping this user code: * - * movq $stuck_here,%rcx + * movq $stuck_here, %rcx * pushfq * popq %r11 * stuck_here: * * would never get past 'stuck_here'. */ - testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz opportunistic_sysret_failed + testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 + jnz opportunistic_sysret_failed /* nothing to check for RSP */ - cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */ - jne opportunistic_sysret_failed + cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */ + jne opportunistic_sysret_failed /* - * We win! This label is here just for ease of understanding - * perf profiles. Nothing jumps here. + * We win! This label is here just for ease of understanding + * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: - CFI_REMEMBER_STATE - /* r11 is already restored (see code above) */ - RESTORE_C_REGS_EXCEPT_R11 - movq RSP(%rsp),%rsp + /* rcx and r11 are already restored (see code above) */ + RESTORE_C_REGS_EXCEPT_RCX_R11 + movq RSP(%rsp), %rsp USERGS_SYSRET64 - CFI_RESTORE_STATE opportunistic_sysret_failed: SWAPGS jmp restore_c_regs_and_iret - CFI_ENDPROC -END(system_call) +END(entry_SYSCALL_64) .macro FORK_LIKE func ENTRY(stub_\func) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 /* offset 8: return address */ SAVE_EXTRA_REGS 8 - jmp sys_\func - CFI_ENDPROC + jmp sys_\func END(stub_\func) .endm @@ -503,8 +368,6 @@ END(stub_\func) FORK_LIKE vfork ENTRY(stub_execve) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 call sys_execve return_from_execve: testl %eax, %eax @@ -514,11 +377,9 @@ return_from_execve: 1: /* must use IRET code path (pt_regs->cs may have changed) */ addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 ZERO_EXTRA_REGS - movq %rax,RAX(%rsp) + movq %rax, RAX(%rsp) jmp int_ret_from_sys_call - CFI_ENDPROC END(stub_execve) /* * Remaining execve stubs are only 7 bytes long. @@ -526,56 +387,28 @@ END(stub_execve) */ .align 8 GLOBAL(stub_execveat) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 call sys_execveat jmp return_from_execve - CFI_ENDPROC END(stub_execveat) -#ifdef CONFIG_X86_X32_ABI +#if defined(CONFIG_X86_X32_ABI) .align 8 GLOBAL(stub_x32_execve) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 call compat_sys_execve jmp return_from_execve - CFI_ENDPROC END(stub_x32_execve) .align 8 GLOBAL(stub_x32_execveat) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 call compat_sys_execveat jmp return_from_execve - CFI_ENDPROC END(stub_x32_execveat) #endif -#ifdef CONFIG_IA32_EMULATION - .align 8 -GLOBAL(stub32_execve) - CFI_STARTPROC - call compat_sys_execve - jmp return_from_execve - CFI_ENDPROC -END(stub32_execve) - .align 8 -GLOBAL(stub32_execveat) - CFI_STARTPROC - call compat_sys_execveat - jmp return_from_execve - CFI_ENDPROC -END(stub32_execveat) -#endif - /* * sigreturn is special because it needs to restore all registers on return. * This cannot be done with SYSRET, so use the IRET return path instead. */ ENTRY(stub_rt_sigreturn) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 /* * SAVE_EXTRA_REGS result is not normally needed: * sigreturn overwrites all pt_regs->GPREGS. @@ -584,24 +417,19 @@ ENTRY(stub_rt_sigreturn) * we SAVE_EXTRA_REGS here. */ SAVE_EXTRA_REGS 8 - call sys_rt_sigreturn + call sys_rt_sigreturn return_from_stub: addq $8, %rsp - CFI_ADJUST_CFA_OFFSET -8 RESTORE_EXTRA_REGS - movq %rax,RAX(%rsp) - jmp int_ret_from_sys_call - CFI_ENDPROC + movq %rax, RAX(%rsp) + jmp int_ret_from_sys_call END(stub_rt_sigreturn) #ifdef CONFIG_X86_X32_ABI ENTRY(stub_x32_rt_sigreturn) - CFI_STARTPROC - DEFAULT_FRAME 0, 8 SAVE_EXTRA_REGS 8 - call sys32_x32_rt_sigreturn - jmp return_from_stub - CFI_ENDPROC + call sys32_x32_rt_sigreturn + jmp return_from_stub END(stub_x32_rt_sigreturn) #endif @@ -611,36 +439,36 @@ END(stub_x32_rt_sigreturn) * rdi: prev task we switched from */ ENTRY(ret_from_fork) - DEFAULT_FRAME - LOCK ; btr $TIF_FORK,TI_flags(%r8) + LOCK ; btr $TIF_FORK, TI_flags(%r8) - pushq_cfi $0x0002 - popfq_cfi # reset kernel eflags + pushq $0x0002 + popfq /* reset kernel eflags */ - call schedule_tail # rdi: 'prev' task parameter + call schedule_tail /* rdi: 'prev' task parameter */ RESTORE_EXTRA_REGS - testl $3,CS(%rsp) # from kernel_thread? + testb $3, CS(%rsp) /* from kernel_thread? */ /* * By the time we get here, we have no idea whether our pt_regs, * ti flags, and ti status came from the 64-bit SYSCALL fast path, - * the slow path, or one of the ia32entry paths. + * the slow path, or one of the 32-bit compat paths. * Use IRET code path to return, since it can safely handle * all of the above. */ jnz int_ret_from_sys_call - /* We came from kernel_thread */ - /* nb: we depend on RESTORE_EXTRA_REGS above */ - movq %rbp, %rdi - call *%rbx - movl $0, RAX(%rsp) + /* + * We came from kernel_thread + * nb: we depend on RESTORE_EXTRA_REGS above + */ + movq %rbp, %rdi + call *%rbx + movl $0, RAX(%rsp) RESTORE_EXTRA_REGS - jmp int_ret_from_sys_call - CFI_ENDPROC + jmp int_ret_from_sys_call END(ret_from_fork) /* @@ -649,16 +477,13 @@ END(ret_from_fork) */ .align 8 ENTRY(irq_entries_start) - INTR_FRAME vector=FIRST_EXTERNAL_VECTOR .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) - pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */ + pushq $(~vector+0x80) /* Note: always in signed byte range */ vector=vector+1 jmp common_interrupt - CFI_ADJUST_CFA_OFFSET -8 .align 8 .endr - CFI_ENDPROC END(irq_entries_start) /* @@ -672,23 +497,33 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + ALLOC_PT_GPREGS_ON_STACK + SAVE_C_REGS + SAVE_EXTRA_REGS + + testb $3, CS(%rsp) + jz 1f + + /* + * IRQ from user mode. Switch to kernel gsbase and inform context + * tracking that we're in kernel mode. + */ + SWAPGS + /* - * Since nothing in interrupt handling code touches r12...r15 members - * of "struct pt_regs", and since interrupts can nest, we can save - * four stack slots and simultaneously provide - * an unwind-friendly stack layout by saving "truncated" pt_regs - * exactly up to rbp slot, without these members. + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). Since TRACE_IRQS_OFF idempotent, + * the simplest way to handle it is to just call it twice if + * we enter from user mode. There's no reason to optimize this since + * TRACE_IRQS_OFF is a no-op if lockdep is off. */ - ALLOC_PT_GPREGS_ON_STACK -RBP - SAVE_C_REGS -RBP - /* this goes to 0(%rsp) for unwinder, not for saving the value: */ - SAVE_EXTRA_REGS_RBP -RBP + TRACE_IRQS_OFF - leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */ +#ifdef CONFIG_CONTEXT_TRACKING + call enter_from_user_mode +#endif - testl $3, CS-RBP(%rsp) - je 1f - SWAPGS 1: /* * Save previous stack pointer, optionally switch to interrupt stack. @@ -697,24 +532,14 @@ END(irq_entries_start) * a little cheaper to use a separate counter in the PDA (short of * moving irq_enter into assembly, which would be too much work) */ - movq %rsp, %rsi - incl PER_CPU_VAR(irq_count) - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - CFI_DEF_CFA_REGISTER rsi - pushq %rsi - /* - * For debugger: - * "CFA (Current Frame Address) is the value on stack + offset" - */ - CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ - 0x77 /* DW_OP_breg7 (rsp) */, 0, \ - 0x06 /* DW_OP_deref */, \ - 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \ - 0x22 /* DW_OP_plus */ + movq %rsp, %rdi + incl PER_CPU_VAR(irq_count) + cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp + pushq %rdi /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF - call \func + call \func /* rdi points to pt_regs */ .endm /* @@ -723,59 +548,37 @@ END(irq_entries_start) */ .p2align CONFIG_X86_L1_CACHE_SHIFT common_interrupt: - XCPT_FRAME ASM_CLAC - addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ + addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */ interrupt do_IRQ /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - decl PER_CPU_VAR(irq_count) + decl PER_CPU_VAR(irq_count) /* Restore saved previous stack */ - popq %rsi - CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */ - /* return code expects complete pt_regs - adjust rsp accordingly: */ - leaq -RBP(%rsi),%rsp - CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET RBP - - testl $3,CS(%rsp) - je retint_kernel - /* Interrupt came from user space */ + popq %rsp - GET_THREAD_INFO(%rcx) - /* - * %rcx: thread info. Interrupts off. - */ -retint_with_reschedule: - movl $_TIF_WORK_MASK,%edi -retint_check: - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - andl %edi,%edx - CFI_REMEMBER_STATE - jnz retint_careful - -retint_swapgs: /* return to user-space */ - /* - * The iretq could re-enable interrupts: - */ - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_IRETQ + testb $3, CS(%rsp) + jz retint_kernel + /* Interrupt came from user space */ +GLOBAL(retint_user) + mov %rsp,%rdi + call prepare_exit_to_usermode + TRACE_IRQS_IRETQ SWAPGS - jmp restore_c_regs_and_iret + jmp restore_regs_and_iret /* Returning to kernel space */ retint_kernel: #ifdef CONFIG_PREEMPT /* Interrupts are off */ /* Check if we need preemption */ - bt $9,EFLAGS(%rsp) /* interrupts were off? */ + bt $9, EFLAGS(%rsp) /* were interrupts off? */ jnc 1f -0: cmpl $0,PER_CPU_VAR(__preempt_count) +0: cmpl $0, PER_CPU_VAR(__preempt_count) #ifndef CONFIG_PREEMPT_LAZY jnz 1f #else @@ -806,6 +609,8 @@ do_preempt_schedule_irq: * At this label, code paths which return to kernel and to user, * which come from interrupts/exception and from syscalls, merge. */ +GLOBAL(restore_regs_and_iret) + RESTORE_EXTRA_REGS restore_c_regs_and_iret: RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 @@ -817,8 +622,8 @@ ENTRY(native_iret) * 64-bit mode SS:RSP on the exception stack is always valid. */ #ifdef CONFIG_X86_ESPFIX64 - testb $4,(SS-RIP)(%rsp) - jnz native_irq_return_ldt + testb $4, (SS-RIP)(%rsp) + jnz native_irq_return_ldt #endif .global native_irq_return_iret @@ -833,62 +638,29 @@ native_irq_return_iret: #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: - pushq_cfi %rax - pushq_cfi %rdi + pushq %rax + pushq %rdi SWAPGS - movq PER_CPU_VAR(espfix_waddr),%rdi - movq %rax,(0*8)(%rdi) /* RAX */ - movq (2*8)(%rsp),%rax /* RIP */ - movq %rax,(1*8)(%rdi) - movq (3*8)(%rsp),%rax /* CS */ - movq %rax,(2*8)(%rdi) - movq (4*8)(%rsp),%rax /* RFLAGS */ - movq %rax,(3*8)(%rdi) - movq (6*8)(%rsp),%rax /* SS */ - movq %rax,(5*8)(%rdi) - movq (5*8)(%rsp),%rax /* RSP */ - movq %rax,(4*8)(%rdi) - andl $0xffff0000,%eax - popq_cfi %rdi - orq PER_CPU_VAR(espfix_stack),%rax + movq PER_CPU_VAR(espfix_waddr), %rdi + movq %rax, (0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp), %rax /* RIP */ + movq %rax, (1*8)(%rdi) + movq (3*8)(%rsp), %rax /* CS */ + movq %rax, (2*8)(%rdi) + movq (4*8)(%rsp), %rax /* RFLAGS */ + movq %rax, (3*8)(%rdi) + movq (6*8)(%rsp), %rax /* SS */ + movq %rax, (5*8)(%rdi) + movq (5*8)(%rsp), %rax /* RSP */ + movq %rax, (4*8)(%rdi) + andl $0xffff0000, %eax + popq %rdi + orq PER_CPU_VAR(espfix_stack), %rax SWAPGS - movq %rax,%rsp - popq_cfi %rax - jmp native_irq_return_iret + movq %rax, %rsp + popq %rax + jmp native_irq_return_iret #endif - - /* edi: workmask, edx: work */ -retint_careful: - CFI_RESTORE_STATE - testl $_TIF_NEED_RESCHED_MASK,%edx - jz retint_signal - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - pushq_cfi %rdi - SCHEDULE_USER - popq_cfi %rdi - GET_THREAD_INFO(%rcx) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - jmp retint_check - -retint_signal: - testl $_TIF_DO_NOTIFY_MASK,%edx - jz retint_swapgs - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_EXTRA_REGS - movq $-1,ORIG_RAX(%rsp) - xorl %esi,%esi # oldset - movq %rsp,%rdi # &pt_regs - call do_notify_resume - RESTORE_EXTRA_REGS - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - jmp retint_with_reschedule - - CFI_ENDPROC END(common_interrupt) /* @@ -896,13 +668,11 @@ END(common_interrupt) */ .macro apicinterrupt3 num sym do_sym ENTRY(\sym) - INTR_FRAME ASM_CLAC - pushq_cfi $~(\num) + pushq $~(\num) .Lcommon_\sym: interrupt \do_sym - jmp ret_from_intr - CFI_ENDPROC + jmp ret_from_intr END(\sym) .endm @@ -924,53 +694,45 @@ trace_apicinterrupt \num \sym .endm #ifdef CONFIG_SMP -apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \ - irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt -apicinterrupt3 REBOOT_VECTOR \ - reboot_interrupt smp_reboot_interrupt +apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt +apicinterrupt3 REBOOT_VECTOR reboot_interrupt smp_reboot_interrupt #endif #ifdef CONFIG_X86_UV -apicinterrupt3 UV_BAU_MESSAGE \ - uv_bau_message_intr1 uv_bau_message_interrupt +apicinterrupt3 UV_BAU_MESSAGE uv_bau_message_intr1 uv_bau_message_interrupt #endif -apicinterrupt LOCAL_TIMER_VECTOR \ - apic_timer_interrupt smp_apic_timer_interrupt -apicinterrupt X86_PLATFORM_IPI_VECTOR \ - x86_platform_ipi smp_x86_platform_ipi + +apicinterrupt LOCAL_TIMER_VECTOR apic_timer_interrupt smp_apic_timer_interrupt +apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_HAVE_KVM -apicinterrupt3 POSTED_INTR_VECTOR \ - kvm_posted_intr_ipi smp_kvm_posted_intr_ipi +apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi +apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi #endif #ifdef CONFIG_X86_MCE_THRESHOLD -apicinterrupt THRESHOLD_APIC_VECTOR \ - threshold_interrupt smp_threshold_interrupt +apicinterrupt THRESHOLD_APIC_VECTOR threshold_interrupt smp_threshold_interrupt +#endif + +#ifdef CONFIG_X86_MCE_AMD +apicinterrupt DEFERRED_ERROR_VECTOR deferred_error_interrupt smp_deferred_error_interrupt #endif #ifdef CONFIG_X86_THERMAL_VECTOR -apicinterrupt THERMAL_APIC_VECTOR \ - thermal_interrupt smp_thermal_interrupt +apicinterrupt THERMAL_APIC_VECTOR thermal_interrupt smp_thermal_interrupt #endif #ifdef CONFIG_SMP -apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ - call_function_single_interrupt smp_call_function_single_interrupt -apicinterrupt CALL_FUNCTION_VECTOR \ - call_function_interrupt smp_call_function_interrupt -apicinterrupt RESCHEDULE_VECTOR \ - reschedule_interrupt smp_reschedule_interrupt +apicinterrupt CALL_FUNCTION_SINGLE_VECTOR call_function_single_interrupt smp_call_function_single_interrupt +apicinterrupt CALL_FUNCTION_VECTOR call_function_interrupt smp_call_function_interrupt +apicinterrupt RESCHEDULE_VECTOR reschedule_interrupt smp_reschedule_interrupt #endif -apicinterrupt ERROR_APIC_VECTOR \ - error_interrupt smp_error_interrupt -apicinterrupt SPURIOUS_APIC_VECTOR \ - spurious_interrupt smp_spurious_interrupt +apicinterrupt ERROR_APIC_VECTOR error_interrupt smp_error_interrupt +apicinterrupt SPURIOUS_APIC_VECTOR spurious_interrupt smp_spurious_interrupt #ifdef CONFIG_IRQ_WORK -apicinterrupt IRQ_WORK_VECTOR \ - irq_work_interrupt smp_irq_work_interrupt +apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt #endif /* @@ -985,100 +747,87 @@ ENTRY(\sym) .error "using shift_ist requires paranoid=1" .endif - .if \has_error_code - XCPT_FRAME - .else - INTR_FRAME - .endif - ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME .ifeq \has_error_code - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + pushq $-1 /* ORIG_RAX: no syscall to restart */ .endif ALLOC_PT_GPREGS_ON_STACK .if \paranoid .if \paranoid == 1 - CFI_REMEMBER_STATE - testl $3, CS(%rsp) /* If coming from userspace, switch */ - jnz 1f /* stacks. */ + testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ + jnz 1f .endif - call paranoid_entry + call paranoid_entry .else - call error_entry + call error_entry .endif /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ - DEFAULT_FRAME 0 - .if \paranoid .if \shift_ist != -1 - TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ + TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ .else TRACE_IRQS_OFF .endif .endif - movq %rsp,%rdi /* pt_regs pointer */ + movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + movq ORIG_RAX(%rsp), %rsi /* get error code */ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ .else - xorl %esi,%esi /* no error code */ + xorl %esi, %esi /* no error code */ .endif .if \shift_ist != -1 - subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) .endif - call \do_sym + call \do_sym .if \shift_ist != -1 - addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) .endif /* these procedures expect "no swapgs" flag in ebx */ .if \paranoid - jmp paranoid_exit + jmp paranoid_exit .else - jmp error_exit + jmp error_exit .endif .if \paranoid == 1 - CFI_RESTORE_STATE /* * Paranoid entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ 1: - call error_entry + call error_entry - DEFAULT_FRAME 0 - movq %rsp,%rdi /* pt_regs pointer */ - call sync_regs - movq %rax,%rsp /* switch stack */ + movq %rsp, %rdi /* pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ - movq %rsp,%rdi /* pt_regs pointer */ + movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + movq ORIG_RAX(%rsp), %rsi /* get error code */ + movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ .else - xorl %esi,%esi /* no error code */ + xorl %esi, %esi /* no error code */ .endif - call \do_sym + call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit /* %ebx: no swapgs flag */ .endif - - CFI_ENDPROC END(\sym) .endm @@ -1093,66 +842,59 @@ idtentry \sym \do_sym has_error_code=\has_error_code .endm #endif -idtentry divide_error do_divide_error has_error_code=0 -idtentry overflow do_overflow has_error_code=0 -idtentry bounds do_bounds has_error_code=0 -idtentry invalid_op do_invalid_op has_error_code=0 -idtentry device_not_available do_device_not_available has_error_code=0 -idtentry double_fault do_double_fault has_error_code=1 paranoid=2 -idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 -idtentry invalid_TSS do_invalid_TSS has_error_code=1 -idtentry segment_not_present do_segment_not_present has_error_code=1 -idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 -idtentry coprocessor_error do_coprocessor_error has_error_code=0 -idtentry alignment_check do_alignment_check has_error_code=1 -idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 - - - /* Reload gs selector with exception handling */ - /* edi: new selector */ +idtentry divide_error do_divide_error has_error_code=0 +idtentry overflow do_overflow has_error_code=0 +idtentry bounds do_bounds has_error_code=0 +idtentry invalid_op do_invalid_op has_error_code=0 +idtentry device_not_available do_device_not_available has_error_code=0 +idtentry double_fault do_double_fault has_error_code=1 paranoid=2 +idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 +idtentry invalid_TSS do_invalid_TSS has_error_code=1 +idtentry segment_not_present do_segment_not_present has_error_code=1 +idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 +idtentry coprocessor_error do_coprocessor_error has_error_code=0 +idtentry alignment_check do_alignment_check has_error_code=1 +idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 + + + /* + * Reload gs selector with exception handling + * edi: new selector + */ ENTRY(native_load_gs_index) - CFI_STARTPROC - pushfq_cfi + pushfq DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) SWAPGS gs_change: - movl %edi,%gs -2: mfence /* workaround */ + movl %edi, %gs +2: mfence /* workaround */ SWAPGS - popfq_cfi + popfq ret - CFI_ENDPROC END(native_load_gs_index) - _ASM_EXTABLE(gs_change,bad_gs) - .section .fixup,"ax" + _ASM_EXTABLE(gs_change, bad_gs) + .section .fixup, "ax" /* running with kernelgs */ bad_gs: - SWAPGS /* switch back to user gs */ - xorl %eax,%eax - movl %eax,%gs - jmp 2b + SWAPGS /* switch back to user gs */ + xorl %eax, %eax + movl %eax, %gs + jmp 2b .previous #ifndef CONFIG_PREEMPT_RT_FULL /* Call softirq on interrupt stack. Interrupts are off. */ ENTRY(do_softirq_own_stack) - CFI_STARTPROC - pushq_cfi %rbp - CFI_REL_OFFSET rbp,0 - mov %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - incl PER_CPU_VAR(irq_count) - cmove PER_CPU_VAR(irq_stack_ptr),%rsp - push %rbp # backlink for old unwinder - call __do_softirq + pushq %rbp + mov %rsp, %rbp + incl PER_CPU_VAR(irq_count) + cmove PER_CPU_VAR(irq_stack_ptr), %rsp + push %rbp /* frame pointer backlink */ + call __do_softirq leaveq - CFI_RESTORE rbp - CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET -8 - decl PER_CPU_VAR(irq_count) + decl PER_CPU_VAR(irq_count) ret - CFI_ENDPROC END(do_softirq_own_stack) #endif @@ -1172,29 +914,24 @@ idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 * existing activation in its critical region -- if so, we pop the current * activation and restart the handler using the previous one. */ -ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) - CFI_STARTPROC +ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */ + /* * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will * see the correct pointer to the pt_regs */ - movq %rdi, %rsp # we don't return, adjust the stack frame - CFI_ENDPROC - DEFAULT_FRAME -11: incl PER_CPU_VAR(irq_count) - movq %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp - cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp - pushq %rbp # backlink for old unwinder - call xen_evtchn_do_upcall - popq %rsp - CFI_DEF_CFA_REGISTER rsp - decl PER_CPU_VAR(irq_count) + movq %rdi, %rsp /* we don't return, adjust the stack frame */ +11: incl PER_CPU_VAR(irq_count) + movq %rsp, %rbp + cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp + pushq %rbp /* frame pointer backlink */ + call xen_evtchn_do_upcall + popq %rsp + decl PER_CPU_VAR(irq_count) #ifndef CONFIG_PREEMPT - call xen_maybe_preempt_hcall + call xen_maybe_preempt_hcall #endif - jmp error_exit - CFI_ENDPROC + jmp error_exit END(xen_do_hypervisor_callback) /* @@ -1211,51 +948,35 @@ END(xen_do_hypervisor_callback) * with its current contents: any discrepancy means we in category 1. */ ENTRY(xen_failsafe_callback) - INTR_FRAME 1 (6*8) - /*CFI_REL_OFFSET gs,GS*/ - /*CFI_REL_OFFSET fs,FS*/ - /*CFI_REL_OFFSET es,ES*/ - /*CFI_REL_OFFSET ds,DS*/ - CFI_REL_OFFSET r11,8 - CFI_REL_OFFSET rcx,0 - movw %ds,%cx - cmpw %cx,0x10(%rsp) - CFI_REMEMBER_STATE - jne 1f - movw %es,%cx - cmpw %cx,0x18(%rsp) - jne 1f - movw %fs,%cx - cmpw %cx,0x20(%rsp) - jne 1f - movw %gs,%cx - cmpw %cx,0x28(%rsp) - jne 1f + movl %ds, %ecx + cmpw %cx, 0x10(%rsp) + jne 1f + movl %es, %ecx + cmpw %cx, 0x18(%rsp) + jne 1f + movl %fs, %ecx + cmpw %cx, 0x20(%rsp) + jne 1f + movl %gs, %ecx + cmpw %cx, 0x28(%rsp) + jne 1f /* All segments match their saved values => Category 2 (Bad IRET). */ - movq (%rsp),%rcx - CFI_RESTORE rcx - movq 8(%rsp),%r11 - CFI_RESTORE r11 - addq $0x30,%rsp - CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $0 /* RIP */ - pushq_cfi %r11 - pushq_cfi %rcx - jmp general_protection - CFI_RESTORE_STATE + movq (%rsp), %rcx + movq 8(%rsp), %r11 + addq $0x30, %rsp + pushq $0 /* RIP */ + pushq %r11 + pushq %rcx + jmp general_protection 1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ - movq (%rsp),%rcx - CFI_RESTORE rcx - movq 8(%rsp),%r11 - CFI_RESTORE r11 - addq $0x30,%rsp - CFI_ADJUST_CFA_OFFSET -0x30 - pushq_cfi $-1 /* orig_ax = -1 => not a system call */ + movq (%rsp), %rcx + movq 8(%rsp), %r11 + addq $0x30, %rsp + pushq $-1 /* orig_ax = -1 => not a system call */ ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS - jmp error_exit - CFI_ENDPROC + jmp error_exit END(xen_failsafe_callback) apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ @@ -1268,21 +989,25 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler #endif /* CONFIG_HYPERV */ -idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK -idtentry stack_segment do_stack_segment has_error_code=1 +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry stack_segment do_stack_segment has_error_code=1 + #ifdef CONFIG_XEN -idtentry xen_debug do_debug has_error_code=0 -idtentry xen_int3 do_int3 has_error_code=0 -idtentry xen_stack_segment do_stack_segment has_error_code=1 +idtentry xen_debug do_debug has_error_code=0 +idtentry xen_int3 do_int3 has_error_code=0 +idtentry xen_stack_segment do_stack_segment has_error_code=1 #endif -idtentry general_protection do_general_protection has_error_code=1 -trace_idtentry page_fault do_page_fault has_error_code=1 + +idtentry general_protection do_general_protection has_error_code=1 +trace_idtentry page_fault do_page_fault has_error_code=1 + #ifdef CONFIG_KVM_GUEST -idtentry async_page_fault do_async_page_fault has_error_code=1 +idtentry async_page_fault do_async_page_fault has_error_code=1 #endif + #ifdef CONFIG_X86_MCE -idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) #endif /* @@ -1291,19 +1016,17 @@ idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector( * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(paranoid_entry) - XCPT_FRAME 1 15*8 cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 - movl $1,%ebx - movl $MSR_GS_BASE,%ecx + movl $1, %ebx + movl $MSR_GS_BASE, %ecx rdmsr - testl %edx,%edx - js 1f /* negative -> in kernel */ + testl %edx, %edx + js 1f /* negative -> in kernel */ SWAPGS - xorl %ebx,%ebx + xorl %ebx, %ebx 1: ret - CFI_ENDPROC END(paranoid_entry) /* @@ -1315,17 +1038,17 @@ END(paranoid_entry) * in syscall entry), so checking for preemption here would * be complicated. Fortunately, we there's no good reason * to try to handle preemption here. + * + * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ -/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ ENTRY(paranoid_exit) - DEFAULT_FRAME DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF_DEBUG - testl %ebx,%ebx /* swapgs needed? */ - jnz paranoid_exit_no_swapgs + testl %ebx, %ebx /* swapgs needed? */ + jnz paranoid_exit_no_swapgs TRACE_IRQS_IRETQ SWAPGS_UNSAFE_STACK - jmp paranoid_exit_restore + jmp paranoid_exit_restore paranoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG paranoid_exit_restore: @@ -1333,24 +1056,40 @@ paranoid_exit_restore: RESTORE_C_REGS REMOVE_PT_GPREGS_FROM_STACK 8 INTERRUPT_RETURN - CFI_ENDPROC END(paranoid_exit) /* * Save all registers in pt_regs, and switch gs if needed. - * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) - XCPT_FRAME 1 15*8 cld SAVE_C_REGS 8 SAVE_EXTRA_REGS 8 - xorl %ebx,%ebx - testl $3,CS+8(%rsp) - je error_kernelspace -error_swapgs: + xorl %ebx, %ebx + testb $3, CS+8(%rsp) + jz .Lerror_kernelspace + +.Lerror_entry_from_usermode_swapgs: + /* + * We entered from user mode or we're pretending to have entered + * from user mode due to an IRET fault. + */ SWAPGS -error_sti: + +.Lerror_entry_from_usermode_after_swapgs: + /* + * We need to tell lockdep that IRQs are off. We can't do this until + * we fix gsbase, and we should do it before enter_from_user_mode + * (which can take locks). + */ + TRACE_IRQS_OFF +#ifdef CONFIG_CONTEXT_TRACKING + call enter_from_user_mode +#endif + ret + +.Lerror_entry_done: TRACE_IRQS_OFF ret @@ -1360,58 +1099,77 @@ error_sti: * truncated RIP for IRET exceptions returning to compat mode. Check * for these here too. */ -error_kernelspace: - CFI_REL_OFFSET rcx, RCX+8 - incl %ebx - leaq native_irq_return_iret(%rip),%rcx - cmpq %rcx,RIP+8(%rsp) - je error_bad_iret - movl %ecx,%eax /* zero extend */ - cmpq %rax,RIP+8(%rsp) - je bstep_iret - cmpq $gs_change,RIP+8(%rsp) - je error_swapgs - jmp error_sti - -bstep_iret: +.Lerror_kernelspace: + incl %ebx + leaq native_irq_return_iret(%rip), %rcx + cmpq %rcx, RIP+8(%rsp) + je .Lerror_bad_iret + movl %ecx, %eax /* zero extend */ + cmpq %rax, RIP+8(%rsp) + je .Lbstep_iret + cmpq $gs_change, RIP+8(%rsp) + jne .Lerror_entry_done + + /* + * hack: gs_change can fail with user gsbase. If this happens, fix up + * gsbase and proceed. We'll fix up the exception and land in + * gs_change's error handler with kernel gsbase. + */ + jmp .Lerror_entry_from_usermode_swapgs + +.Lbstep_iret: /* Fix truncated RIP */ - movq %rcx,RIP+8(%rsp) + movq %rcx, RIP+8(%rsp) /* fall through */ -error_bad_iret: +.Lerror_bad_iret: + /* + * We came from an IRET to user mode, so we have user gsbase. + * Switch to kernel gsbase: + */ SWAPGS - mov %rsp,%rdi - call fixup_bad_iret - mov %rax,%rsp - decl %ebx /* Return to usergs */ - jmp error_sti - CFI_ENDPROC + + /* + * Pretend that the exception came from user mode: set up pt_regs + * as if we faulted immediately after IRET and clear EBX so that + * error_exit knows that we will be returning to user mode. + */ + mov %rsp, %rdi + call fixup_bad_iret + mov %rax, %rsp + decl %ebx + jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) -/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ +/* + * On entry, EBS is a "return to kernel mode" flag: + * 1: already in kernel mode, don't need SWAPGS + * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode + */ ENTRY(error_exit) - DEFAULT_FRAME - movl %ebx,%eax - RESTORE_EXTRA_REGS + movl %ebx, %eax DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - GET_THREAD_INFO(%rcx) - testl %eax,%eax - jne retint_kernel - LOCKDEP_SYS_EXIT_IRQ - movl TI_flags(%rcx),%edx - movl $_TIF_WORK_MASK,%edi - andl %edi,%edx - jnz retint_careful - jmp retint_swapgs - CFI_ENDPROC + testl %eax, %eax + jnz retint_kernel + jmp retint_user END(error_exit) /* Runs on exception stack */ ENTRY(nmi) - INTR_FRAME + /* + * Fix up the exception frame if we're on Xen. + * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most + * one value to the stack on native, so it may clobber the rdx + * scratch slot, but it won't clobber any of the important + * slots past it. + * + * Xen is a different story, because the Xen frame itself overlaps + * the "NMI executing" variable. + */ PARAVIRT_ADJUST_EXCEPTION_FRAME + /* * We allow breakpoints in NMIs. If a breakpoint occurs, then * the iretq it performs will take us out of NMI context. @@ -1451,8 +1209,7 @@ ENTRY(nmi) */ /* Use %rdx as our temp variable throughout */ - pushq_cfi %rdx - CFI_REL_OFFSET rdx, 0 + pushq %rdx testb $3, CS-RIP+8(%rsp) jz .Lnmi_from_kernel @@ -1463,12 +1220,15 @@ ENTRY(nmi) * we don't want to enable interrupts, because then we'll end * up in an awkward situation in which IRQs are on but NMIs * are off. + * + * We also must not push anything to the stack before switching + * stacks lest we corrupt the "NMI executing" variable. */ - SWAPGS + SWAPGS_UNSAFE_STACK cld movq %rsp, %rdx - movq PER_CPU_VAR(kernel_stack), %rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq 5*8(%rdx) /* pt_regs->ss */ pushq 4*8(%rdx) /* pt_regs->rsp */ pushq 3*8(%rdx) /* pt_regs->flags */ @@ -1496,6 +1256,7 @@ ENTRY(nmi) * due to nesting -- we're on the normal thread stack and we're * done with the NMI stack. */ + movq %rsp, %rdi movq $-1, %rsi call do_nmi @@ -1574,8 +1335,8 @@ ENTRY(nmi) * This will not detect if we interrupted an outer NMI just * before IRET. */ - cmpl $1, -8(%rsp) - je nested_nmi + cmpl $1, -8(%rsp) + je nested_nmi /* * Now test if the previous stack was an NMI stack. This covers @@ -1594,6 +1355,7 @@ ENTRY(nmi) cmpq %rdx, 4*8(%rsp) /* If the stack pointer is above the NMI stack, this is a normal NMI */ ja first_nmi + subq $EXCEPTION_STKSZ, %rdx cmpq %rdx, 4*8(%rsp) /* If it is below the NMI stack, it is a normal NMI */ @@ -1606,55 +1368,60 @@ ENTRY(nmi) /* This is a nested NMI. */ - CFI_REMEMBER_STATE - nested_nmi: /* * Modify the "iret" frame to point to repeat_nmi, forcing another * iteration of NMI handling. */ - leaq -1*8(%rsp), %rdx - movq %rdx, %rsp - CFI_ADJUST_CFA_OFFSET 1*8 - leaq -10*8(%rsp), %rdx - pushq_cfi $__KERNEL_DS - pushq_cfi %rdx - pushfq_cfi - pushq_cfi $__KERNEL_CS - pushq_cfi $repeat_nmi + subq $8, %rsp + leaq -10*8(%rsp), %rdx + pushq $__KERNEL_DS + pushq %rdx + pushfq + pushq $__KERNEL_CS + pushq $repeat_nmi /* Put stack back */ - addq $(6*8), %rsp - CFI_ADJUST_CFA_OFFSET -6*8 + addq $(6*8), %rsp nested_nmi_out: - popq_cfi %rdx - CFI_RESTORE rdx + popq %rdx /* We are returning to kernel mode, so this cannot result in a fault. */ INTERRUPT_RETURN - CFI_RESTORE_STATE first_nmi: /* Restore rdx. */ - movq (%rsp), %rdx - CFI_RESTORE rdx + movq (%rsp), %rdx - /* Set "NMI executing" on the stack. */ - pushq_cfi $1 + /* Make room for "NMI executing". */ + pushq $0 /* Leave room for the "iret" frame */ - subq $(5*8), %rsp - CFI_ADJUST_CFA_OFFSET 5*8 + subq $(5*8), %rsp /* Copy the "original" frame to the "outermost" frame */ .rept 5 - pushq_cfi 11*8(%rsp) + pushq 11*8(%rsp) .endr - CFI_DEF_CFA_OFFSET 5*8 /* Everything up to here is safe from nested NMIs */ +#ifdef CONFIG_DEBUG_ENTRY + /* + * For ease of testing, unmask NMIs right away. Disabled by + * default because IRET is very expensive. + */ + pushq $0 /* SS */ + pushq %rsp /* RSP (minus 8 because of the previous push) */ + addq $8, (%rsp) /* Fix up RSP */ + pushfq /* RFLAGS */ + pushq $__KERNEL_CS /* CS */ + pushq $1f /* RIP */ + INTERRUPT_RETURN /* continues at repeat_nmi below */ +1: +#endif + repeat_nmi: /* * If there was a nested NMI, the first NMI's iret will return @@ -1668,24 +1435,21 @@ repeat_nmi: * RSP is pointing to "outermost RIP". gsbase is unknown, but, if * we're repeating an NMI, gsbase has the same value that it had on * the first iteration. paranoid_entry will load the kernel - * gsbase if needed before we call do_nmi. - * - * Set "NMI executing" in case we came back here via IRET. + * gsbase if needed before we call do_nmi. "NMI executing" + * is zero. */ - movq $1, 10*8(%rsp) + movq $1, 10*8(%rsp) /* Set "NMI executing". */ /* * Copy the "outermost" frame to the "iret" frame. NMIs that nest * here must not modify the "iret" frame while we're writing to * it or it will end up containing garbage. */ - addq $(10*8), %rsp - CFI_ADJUST_CFA_OFFSET -10*8 + addq $(10*8), %rsp .rept 5 - pushq_cfi -6*8(%rsp) + pushq -6*8(%rsp) .endr - subq $(5*8), %rsp - CFI_DEF_CFA_OFFSET 5*8 + subq $(5*8), %rsp end_repeat_nmi: /* @@ -1693,7 +1457,7 @@ end_repeat_nmi: * If this happens, then the inner NMI will change the "iret" * frame to point back to repeat_nmi. */ - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + pushq $-1 /* ORIG_RAX: no syscall to restart */ ALLOC_PT_GPREGS_ON_STACK /* @@ -1703,16 +1467,15 @@ end_repeat_nmi: * setting NEED_RESCHED or anything that normal interrupts and * exceptions might do. */ - call paranoid_entry - DEFAULT_FRAME 0 + call paranoid_entry /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ - movq %rsp,%rdi - movq $-1,%rsi - call do_nmi + movq %rsp, %rdi + movq $-1, %rsi + call do_nmi - testl %ebx,%ebx /* swapgs needed? */ - jnz nmi_restore + testl %ebx, %ebx /* swapgs needed? */ + jnz nmi_restore nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: @@ -1739,13 +1502,9 @@ nmi_restore: * mode, so this cannot result in a fault. */ INTERRUPT_RETURN - CFI_ENDPROC END(nmi) ENTRY(ignore_sysret) - CFI_STARTPROC - mov $-ENOSYS,%eax + mov $-ENOSYS, %eax sysret - CFI_ENDPROC END(ignore_sysret) - diff --git a/kernel/arch/x86/entry/entry_64_compat.S b/kernel/arch/x86/entry/entry_64_compat.S new file mode 100644 index 000000000..15cfebaa7 --- /dev/null +++ b/kernel/arch/x86/entry/entry_64_compat.S @@ -0,0 +1,328 @@ +/* + * Compatibility mode system call entry point for x86-64. + * + * Copyright 2000-2002 Andi Kleen, SuSE Labs. + */ +#include "calling.h" +#include <asm/asm-offsets.h> +#include <asm/current.h> +#include <asm/errno.h> +#include <asm/ia32_unistd.h> +#include <asm/thread_info.h> +#include <asm/segment.h> +#include <asm/irqflags.h> +#include <asm/asm.h> +#include <asm/smap.h> +#include <linux/linkage.h> +#include <linux/err.h> + + .section .entry.text, "ax" + +#ifdef CONFIG_PARAVIRT +ENTRY(native_usergs_sysret32) + swapgs + sysretl +ENDPROC(native_usergs_sysret32) +#endif + +/* + * 32-bit SYSENTER instruction entry. + * + * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs. + * IF and VM in rflags are cleared (IOW: interrupts are off). + * SYSENTER does not save anything on the stack, + * and does not save old rip (!!!) and rflags. + * + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp user stack + * 0(%ebp) arg6 + * + * This is purely a fast path. For anything complicated we use the int 0x80 + * path below. We set up a complete hardware stack frame to share code + * with the int 0x80 path. + */ +ENTRY(entry_SYSENTER_compat) + /* Interrupts are off on entry. */ + SWAPGS_UNSAFE_STACK + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ + movl %eax, %eax + + /* Construct struct pt_regs on stack */ + pushq $__USER32_DS /* pt_regs->ss */ + pushq %rbp /* pt_regs->sp (stashed in bp) */ + + /* + * Push flags. This is nasty. First, interrupts are currently + * off, but we need pt_regs->flags to have IF set. Second, even + * if TF was set when SYSENTER started, it's clear by now. We fix + * that later using TIF_SINGLESTEP. + */ + pushfq /* pt_regs->flags (except IF = 0) */ + orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ + ASM_CLAC /* Clear AC after saving FLAGS */ + + pushq $__USER32_CS /* pt_regs->cs */ + xorq %r8,%r8 + pushq %r8 /* pt_regs->ip = 0 (placeholder) */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r9 = 0 */ + pushq %r8 /* pt_regs->r10 = 0 */ + pushq %r8 /* pt_regs->r11 = 0 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ + pushq %r8 /* pt_regs->r12 = 0 */ + pushq %r8 /* pt_regs->r13 = 0 */ + pushq %r8 /* pt_regs->r14 = 0 */ + pushq %r8 /* pt_regs->r15 = 0 */ + cld + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + * This needs to happen before enabling interrupts so that + * we don't get preempted with NT set. + * + * NB.: sysenter_fix_flags is a label with the code under it moved + * out-of-line as an optimization: NT is unlikely to be set in the + * majority of the cases and instead of polluting the I$ unnecessarily, + * we're keeping that code behind a branch which will predict as + * not-taken and therefore its instructions won't be fetched. + */ + testl $X86_EFLAGS_NT, EFLAGS(%rsp) + jnz sysenter_fix_flags +sysenter_flags_fixed: + + /* + * User mode is traced as though IRQs are on, and SYSENTER + * turned them off. + */ + TRACE_IRQS_OFF + + movq %rsp, %rdi + call do_fast_syscall_32 + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + jmp sysret32_from_system_call + +sysenter_fix_flags: + pushq $X86_EFLAGS_FIXED + popfq + jmp sysenter_flags_fixed +ENDPROC(entry_SYSENTER_compat) + +/* + * 32-bit SYSCALL instruction entry. + * + * 32-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * then loads new ss, cs, and rip from previously programmed MSRs. + * rflags gets masked by a value from another MSR (so CLD and CLAC + * are not needed). SYSCALL does not save anything on the stack + * and does not change rsp. + * + * Note: rflags saving+masking-with-MSR happens only in Long mode + * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it). + * Don't get confused: rflags saving+masking depends on Long Mode Active bit + * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes + * or target CS descriptor's L bit (SYSCALL does not read segment descriptors). + * + * Arguments: + * eax system call number + * ecx return address + * ebx arg1 + * ebp arg2 (note: not saved in the stack frame, should not be touched) + * edx arg3 + * esi arg4 + * edi arg5 + * esp user stack + * 0(%esp) arg6 + */ +ENTRY(entry_SYSCALL_compat) + /* Interrupts are off on entry. */ + SWAPGS_UNSAFE_STACK + + /* Stash user ESP and switch to the kernel stack. */ + movl %esp, %r8d + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + /* Zero-extending 32-bit regs, do not remove */ + movl %eax, %eax + + /* Construct struct pt_regs on stack */ + pushq $__USER32_DS /* pt_regs->ss */ + pushq %r8 /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER32_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rbp /* pt_regs->cx (stashed in bp) */ + pushq $-ENOSYS /* pt_regs->ax */ + xorq %r8,%r8 + pushq %r8 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r9 = 0 */ + pushq %r8 /* pt_regs->r10 = 0 */ + pushq %r8 /* pt_regs->r11 = 0 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp (will be overwritten) */ + pushq %r8 /* pt_regs->r12 = 0 */ + pushq %r8 /* pt_regs->r13 = 0 */ + pushq %r8 /* pt_regs->r14 = 0 */ + pushq %r8 /* pt_regs->r15 = 0 */ + + /* + * User mode is traced as though IRQs are on, and SYSENTER + * turned them off. + */ + TRACE_IRQS_OFF + + movq %rsp, %rdi + call do_fast_syscall_32 + /* XEN PV guests always use IRET path */ + ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ + "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + + /* Opportunistic SYSRET */ +sysret32_from_system_call: + TRACE_IRQS_ON /* User mode traces as IRQs on. */ + movq RBX(%rsp), %rbx /* pt_regs->rbx */ + movq RBP(%rsp), %rbp /* pt_regs->rbp */ + movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ + movq RIP(%rsp), %rcx /* pt_regs->ip (in rcx) */ + addq $RAX, %rsp /* Skip r8-r15 */ + popq %rax /* pt_regs->rax */ + popq %rdx /* Skip pt_regs->cx */ + popq %rdx /* pt_regs->dx */ + popq %rsi /* pt_regs->si */ + popq %rdi /* pt_regs->di */ + + /* + * USERGS_SYSRET32 does: + * GSBASE = user's GS base + * EIP = ECX + * RFLAGS = R11 + * CS = __USER32_CS + * SS = __USER_DS + * + * ECX will not match pt_regs->cx, but we're returning to a vDSO + * trampoline that will fix up RCX, so this is okay. + * + * R12-R15 are callee-saved, so they contain whatever was in them + * when the system call started, which is already known to user + * code. We zero R8-R10 to avoid info leaks. + */ + xorq %r8, %r8 + xorq %r9, %r9 + xorq %r10, %r10 + movq RSP-ORIG_RAX(%rsp), %rsp + USERGS_SYSRET32 +END(entry_SYSCALL_compat) + +/* + * Emulated IA32 system calls via int 0x80. + * + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp arg6 (note: not saved in the stack frame, should not be touched) + * + * Notes: + * Uses the same stack frame as the x86-64 version. + * All registers except eax must be saved (but ptrace may violate that). + * Arguments are zero extended. For system calls that want sign extension and + * take long arguments a wrapper is needed. Most calls can just be called + * directly. + * Assumes it is only called from user space and entered with interrupts off. + */ + +ENTRY(entry_INT80_compat) + /* + * Interrupts are off on entry. + */ + PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ + SWAPGS + + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ + movl %eax, %eax + + /* Construct struct pt_regs on stack (iret frame is already on stack) */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + xorq %r8,%r8 + pushq %r8 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r9 = 0 */ + pushq %r8 /* pt_regs->r10 = 0 */ + pushq %r8 /* pt_regs->r11 = 0 */ + pushq %rbx /* pt_regs->rbx */ + pushq %rbp /* pt_regs->rbp */ + pushq %r12 /* pt_regs->r12 */ + pushq %r13 /* pt_regs->r13 */ + pushq %r14 /* pt_regs->r14 */ + pushq %r15 /* pt_regs->r15 */ + cld + + /* + * User mode is traced as though IRQs are on, and the interrupt + * gate turned them off. + */ + TRACE_IRQS_OFF + + movq %rsp, %rdi + call do_syscall_32_irqs_off +.Lsyscall_32_done: + + /* Go back to user mode. */ + TRACE_IRQS_ON + SWAPGS + jmp restore_regs_and_iret +END(entry_INT80_compat) + + ALIGN +GLOBAL(stub32_clone) + /* + * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr). + * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val). + * + * The native 64-bit kernel's sys_clone() implements the latter, + * so we need to swap arguments here before calling it: + */ + xchg %r8, %rcx + jmp sys_clone diff --git a/kernel/arch/x86/kernel/syscall_32.c b/kernel/arch/x86/entry/syscall_32.c index 3777189c4..9a6649857 100644 --- a/kernel/arch/x86/kernel/syscall_32.c +++ b/kernel/arch/x86/entry/syscall_32.c @@ -4,30 +4,27 @@ #include <linux/sys.h> #include <linux/cache.h> #include <asm/asm-offsets.h> +#include <asm/syscall.h> #ifdef CONFIG_IA32_EMULATION #define SYM(sym, compat) compat #else #define SYM(sym, compat) sym -#define ia32_sys_call_table sys_call_table -#define __NR_ia32_syscall_max __NR_syscall_max #endif -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ; +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 #define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat), -typedef asmlinkage void (*sys_call_ptr_t)(void); +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); -extern asmlinkage void sys_ni_syscall(void); - -__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { +__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall, + [0 ... __NR_syscall_compat_max] = &sys_ni_syscall, #include <asm/syscalls_32.h> }; diff --git a/kernel/arch/x86/kernel/syscall_64.c b/kernel/arch/x86/entry/syscall_64.c index 4ac730b37..41283d22b 100644 --- a/kernel/arch/x86/kernel/syscall_64.c +++ b/kernel/arch/x86/entry/syscall_64.c @@ -14,13 +14,13 @@ # define __SYSCALL_X32(nr, sym, compat) /* nothing */ #endif -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_64.h> #undef __SYSCALL_64 #define __SYSCALL_64(nr, sym, compat) [nr] = sym, -extern void sys_ni_syscall(void); +extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* diff --git a/kernel/arch/x86/syscalls/Makefile b/kernel/arch/x86/entry/syscalls/Makefile index a55abb9f6..57aa59fd1 100644 --- a/kernel/arch/x86/syscalls/Makefile +++ b/kernel/arch/x86/entry/syscalls/Makefile @@ -1,5 +1,5 @@ -out := $(obj)/../include/generated/asm -uapi := $(obj)/../include/generated/uapi/asm +out := $(obj)/../../include/generated/asm +uapi := $(obj)/../../include/generated/uapi/asm # Create output directory if not already present _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \ diff --git a/kernel/arch/x86/syscalls/syscall_32.tbl b/kernel/arch/x86/entry/syscalls/syscall_32.tbl index ef8187f9d..f17705e13 100644 --- a/kernel/arch/x86/syscalls/syscall_32.tbl +++ b/kernel/arch/x86/entry/syscalls/syscall_32.tbl @@ -8,7 +8,7 @@ # 0 i386 restart_syscall sys_restart_syscall 1 i386 exit sys_exit -2 i386 fork sys_fork stub32_fork +2 i386 fork sys_fork sys_fork 3 i386 read sys_read 4 i386 write sys_write 5 i386 open sys_open compat_sys_open @@ -17,7 +17,7 @@ 8 i386 creat sys_creat 9 i386 link sys_link 10 i386 unlink sys_unlink -11 i386 execve sys_execve stub32_execve +11 i386 execve sys_execve compat_sys_execve 12 i386 chdir sys_chdir 13 i386 time sys_time compat_sys_time 14 i386 mknod sys_mknod @@ -125,7 +125,7 @@ 116 i386 sysinfo sys_sysinfo compat_sys_sysinfo 117 i386 ipc sys_ipc compat_sys_ipc 118 i386 fsync sys_fsync -119 i386 sigreturn sys_sigreturn stub32_sigreturn +119 i386 sigreturn sys_sigreturn sys32_sigreturn 120 i386 clone sys_clone stub32_clone 121 i386 setdomainname sys_setdomainname 122 i386 uname sys_newuname @@ -179,7 +179,7 @@ 170 i386 setresgid sys_setresgid16 171 i386 getresgid sys_getresgid16 172 i386 prctl sys_prctl -173 i386 rt_sigreturn sys_rt_sigreturn stub32_rt_sigreturn +173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction 175 i386 rt_sigprocmask sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending @@ -196,7 +196,7 @@ 187 i386 sendfile sys_sendfile compat_sys_sendfile 188 i386 getpmsg 189 i386 putpmsg -190 i386 vfork sys_vfork stub32_vfork +190 i386 vfork sys_vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit 192 i386 mmap2 sys_mmap_pgoff 193 i386 truncate64 sys_truncate64 sys32_truncate64 @@ -364,4 +364,22 @@ 355 i386 getrandom sys_getrandom 356 i386 memfd_create sys_memfd_create 357 i386 bpf sys_bpf -358 i386 execveat sys_execveat stub32_execveat +358 i386 execveat sys_execveat compat_sys_execveat +359 i386 socket sys_socket +360 i386 socketpair sys_socketpair +361 i386 bind sys_bind +362 i386 connect sys_connect +363 i386 listen sys_listen +364 i386 accept4 sys_accept4 +365 i386 getsockopt sys_getsockopt compat_sys_getsockopt +366 i386 setsockopt sys_setsockopt compat_sys_setsockopt +367 i386 getsockname sys_getsockname +368 i386 getpeername sys_getpeername +369 i386 sendto sys_sendto +370 i386 sendmsg sys_sendmsg compat_sys_sendmsg +371 i386 recvfrom sys_recvfrom compat_sys_recvfrom +372 i386 recvmsg sys_recvmsg compat_sys_recvmsg +373 i386 shutdown sys_shutdown +374 i386 userfaultfd sys_userfaultfd +375 i386 membarrier sys_membarrier +376 i386 mlock2 sys_mlock2 diff --git a/kernel/arch/x86/syscalls/syscall_64.tbl b/kernel/arch/x86/entry/syscalls/syscall_64.tbl index 9ef32d5f1..314a90bfc 100644 --- a/kernel/arch/x86/syscalls/syscall_64.tbl +++ b/kernel/arch/x86/entry/syscalls/syscall_64.tbl @@ -329,6 +329,9 @@ 320 common kexec_file_load sys_kexec_file_load 321 common bpf sys_bpf 322 64 execveat stub_execveat +323 common userfaultfd sys_userfaultfd +324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/kernel/arch/x86/syscalls/syscallhdr.sh b/kernel/arch/x86/entry/syscalls/syscallhdr.sh index 31fd5f1f3..31fd5f1f3 100644 --- a/kernel/arch/x86/syscalls/syscallhdr.sh +++ b/kernel/arch/x86/entry/syscalls/syscallhdr.sh diff --git a/kernel/arch/x86/syscalls/syscalltbl.sh b/kernel/arch/x86/entry/syscalls/syscalltbl.sh index 0e7f8ec07..0e7f8ec07 100644 --- a/kernel/arch/x86/syscalls/syscalltbl.sh +++ b/kernel/arch/x86/entry/syscalls/syscalltbl.sh diff --git a/kernel/arch/x86/lib/thunk_32.S b/kernel/arch/x86/entry/thunk_32.S index 5eb715087..e5a17114a 100644 --- a/kernel/arch/x86/lib/thunk_32.S +++ b/kernel/arch/x86/entry/thunk_32.S @@ -6,16 +6,14 @@ */ #include <linux/linkage.h> #include <asm/asm.h> - #include <asm/dwarf2.h> /* put return address in eax (arg1) */ .macro THUNK name, func, put_ret_addr_in_eax=0 .globl \name \name: - CFI_STARTPROC - pushl_cfi_reg eax - pushl_cfi_reg ecx - pushl_cfi_reg edx + pushl %eax + pushl %ecx + pushl %edx .if \put_ret_addr_in_eax /* Place EIP in the arg1 */ @@ -23,11 +21,10 @@ .endif call \func - popl_cfi_reg edx - popl_cfi_reg ecx - popl_cfi_reg eax + popl %edx + popl %ecx + popl %eax ret - CFI_ENDPROC _ASM_NOKPROBE(\name) .endm @@ -38,8 +35,6 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif diff --git a/kernel/arch/x86/lib/thunk_64.S b/kernel/arch/x86/entry/thunk_64.S index f89ba4e93..efb2b932b 100644 --- a/kernel/arch/x86/lib/thunk_64.S +++ b/kernel/arch/x86/entry/thunk_64.S @@ -6,35 +6,32 @@ * Subject to the GNU public license, v.2. No warranty of any kind. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> -#include <asm/calling.h> +#include "calling.h" #include <asm/asm.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func, put_ret_addr_in_rdi=0 .globl \name \name: - CFI_STARTPROC /* this one pushes 9 elems, the next one would be %rIP */ - pushq_cfi_reg rdi - pushq_cfi_reg rsi - pushq_cfi_reg rdx - pushq_cfi_reg rcx - pushq_cfi_reg rax - pushq_cfi_reg r8 - pushq_cfi_reg r9 - pushq_cfi_reg r10 - pushq_cfi_reg r11 + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %rax + pushq %r8 + pushq %r9 + pushq %r10 + pushq %r11 .if \put_ret_addr_in_rdi /* 9*8(%rsp) is return addr on stack */ - movq_cfi_restore 9*8, rdi + movq 9*8(%rsp), %rdi .endif call \func jmp restore - CFI_ENDPROC _ASM_NOKPROBE(\name) .endm @@ -49,27 +46,22 @@ #ifdef CONFIG_PREEMPT THUNK ___preempt_schedule, preempt_schedule -#ifdef CONFIG_CONTEXT_TRACKING - THUNK ___preempt_schedule_context, preempt_schedule_context -#endif + THUNK ___preempt_schedule_notrace, preempt_schedule_notrace #endif #if defined(CONFIG_TRACE_IRQFLAGS) \ || defined(CONFIG_DEBUG_LOCK_ALLOC) \ || defined(CONFIG_PREEMPT) - CFI_STARTPROC - CFI_ADJUST_CFA_OFFSET 9*8 restore: - popq_cfi_reg r11 - popq_cfi_reg r10 - popq_cfi_reg r9 - popq_cfi_reg r8 - popq_cfi_reg rax - popq_cfi_reg rcx - popq_cfi_reg rdx - popq_cfi_reg rsi - popq_cfi_reg rdi + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi ret - CFI_ENDPROC _ASM_NOKPROBE(restore) #endif diff --git a/kernel/arch/x86/vdso/.gitignore b/kernel/arch/x86/entry/vdso/.gitignore index aae8ffdd5..aae8ffdd5 100644 --- a/kernel/arch/x86/vdso/.gitignore +++ b/kernel/arch/x86/entry/vdso/.gitignore diff --git a/kernel/arch/x86/vdso/Makefile b/kernel/arch/x86/entry/vdso/Makefile index e97032069..265c0ed68 100644 --- a/kernel/arch/x86/vdso/Makefile +++ b/kernel/arch/x86/entry/vdso/Makefile @@ -8,7 +8,7 @@ KASAN_SANITIZE := n VDSO64-$(CONFIG_X86_64) := y VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y -VDSO32-$(CONFIG_COMPAT) := y +VDSO32-$(CONFIG_IA32_EMULATION) := y # files to link into the vdso vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o @@ -19,9 +19,7 @@ obj-y += vma.o # vDSO images to build vdso_img-$(VDSO64-y) += 64 vdso_img-$(VDSOX32-y) += x32 -vdso_img-$(VDSO32-y) += 32-int80 -vdso_img-$(CONFIG_COMPAT) += 32-syscall -vdso_img-$(VDSO32-y) += 32-sysenter +vdso_img-$(VDSO32-y) += 32 obj-$(VDSO32-y) += vdso32-setup.o @@ -69,7 +67,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ -fno-omit-frame-pointer -foptimize-sibling-calls \ - -DDISABLE_BRANCH_PROFILING + -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(vobjs): KBUILD_CFLAGS += $(CFL) @@ -122,15 +120,6 @@ $(obj)/%.so: $(obj)/%.so.dbg $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) -# -# Build multiple 32-bit vDSO images to choose from at boot time. -# -vdso32.so-$(VDSO32-y) += int80 -vdso32.so-$(CONFIG_COMPAT) += syscall -vdso32.so-$(VDSO32-y) += sysenter - -vdso32-images = $(vdso32.so-y:%=vdso32-%.so) - CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 @@ -139,14 +128,12 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ targets += vdso32/vdso32.lds -targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) +targets += vdso32/note.o vdso32/vclock_gettime.o vdso32/system_call.o targets += vdso32/vclock_gettime.o -$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%) - -KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32) -$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32 +KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO +$(obj)/vdso32.so.dbg: KBUILD_AFLAGS = $(KBUILD_AFLAGS_32) +$(obj)/vdso32.so.dbg: asflags-$(CONFIG_X86_64) += -m32 KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32)) @@ -157,13 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) +$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32) -$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \ - $(obj)/vdso32/vdso32.lds \ - $(obj)/vdso32/vclock_gettime.o \ - $(obj)/vdso32/note.o \ - $(obj)/vdso32/%.o +$(obj)/vdso32.so.dbg: FORCE \ + $(obj)/vdso32/vdso32.lds \ + $(obj)/vdso32/vclock_gettime.o \ + $(obj)/vdso32/note.o \ + $(obj)/vdso32/system_call.o $(call if_changed,vdso) # @@ -175,7 +162,7 @@ quiet_cmd_vdso = VDSO $@ -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' -VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ +VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \ $(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS) GCOV_PROFILE := n @@ -206,4 +193,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE PHONY += vdso_install $(vdso_img_insttargets) vdso_install: $(vdso_img_insttargets) FORCE -clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so* +clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/kernel/arch/x86/vdso/checkundef.sh b/kernel/arch/x86/entry/vdso/checkundef.sh index 7ee90a9b5..7ee90a9b5 100755 --- a/kernel/arch/x86/vdso/checkundef.sh +++ b/kernel/arch/x86/entry/vdso/checkundef.sh diff --git a/kernel/arch/x86/vdso/vclock_gettime.c b/kernel/arch/x86/entry/vdso/vclock_gettime.c index 979332275..ca94fa649 100644 --- a/kernel/arch/x86/vdso/vclock_gettime.c +++ b/kernel/arch/x86/entry/vdso/vclock_gettime.c @@ -175,20 +175,8 @@ static notrace cycle_t vread_pvclock(int *mode) notrace static cycle_t vread_tsc(void) { - cycle_t ret; - u64 last; - - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)__native_read_tsc(); - - last = gtod->cycle_last; + cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 last = gtod->cycle_last; if (likely(ret >= last)) return ret; diff --git a/kernel/arch/x86/vdso/vdso-layout.lds.S b/kernel/arch/x86/entry/vdso/vdso-layout.lds.S index de2c92102..de2c92102 100644 --- a/kernel/arch/x86/vdso/vdso-layout.lds.S +++ b/kernel/arch/x86/entry/vdso/vdso-layout.lds.S diff --git a/kernel/arch/x86/vdso/vdso-note.S b/kernel/arch/x86/entry/vdso/vdso-note.S index 79a071e43..79a071e43 100644 --- a/kernel/arch/x86/vdso/vdso-note.S +++ b/kernel/arch/x86/entry/vdso/vdso-note.S diff --git a/kernel/arch/x86/vdso/vdso.lds.S b/kernel/arch/x86/entry/vdso/vdso.lds.S index 680793264..680793264 100644 --- a/kernel/arch/x86/vdso/vdso.lds.S +++ b/kernel/arch/x86/entry/vdso/vdso.lds.S diff --git a/kernel/arch/x86/vdso/vdso2c.c b/kernel/arch/x86/entry/vdso/vdso2c.c index 8627db24a..785d9922b 100644 --- a/kernel/arch/x86/vdso/vdso2c.c +++ b/kernel/arch/x86/entry/vdso/vdso2c.c @@ -98,10 +98,10 @@ struct vdso_sym required_syms[] = { "VDSO_FAKE_SECTION_TABLE_END", false }, {"VDSO32_NOTE_MASK", true}, - {"VDSO32_SYSENTER_RETURN", true}, {"__kernel_vsyscall", true}, {"__kernel_sigreturn", true}, {"__kernel_rt_sigreturn", true}, + {"int80_landing_pad", true}, }; __attribute__((format(printf, 1, 2))) __attribute__((noreturn)) diff --git a/kernel/arch/x86/vdso/vdso2c.h b/kernel/arch/x86/entry/vdso/vdso2c.h index 022498755..022498755 100644 --- a/kernel/arch/x86/vdso/vdso2c.h +++ b/kernel/arch/x86/entry/vdso/vdso2c.h diff --git a/kernel/arch/x86/vdso/vdso32-setup.c b/kernel/arch/x86/entry/vdso/vdso32-setup.c index e904c2705..08a317a9a 100644 --- a/kernel/arch/x86/vdso/vdso32-setup.c +++ b/kernel/arch/x86/entry/vdso/vdso32-setup.c @@ -48,35 +48,9 @@ __setup("vdso32=", vdso32_setup); __setup_param("vdso=", vdso_setup, vdso32_setup, 0); #endif -#ifdef CONFIG_X86_64 - -#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32)) -#define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32)) - -#else /* CONFIG_X86_32 */ - -#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP)) -#define vdso32_syscall() (0) - -#endif /* CONFIG_X86_64 */ - -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) -const struct vdso_image *selected_vdso32; -#endif - int __init sysenter_setup(void) { -#ifdef CONFIG_COMPAT - if (vdso32_syscall()) - selected_vdso32 = &vdso_image_32_syscall; - else -#endif - if (vdso32_sysenter()) - selected_vdso32 = &vdso_image_32_sysenter; - else - selected_vdso32 = &vdso_image_32_int80; - - init_vdso_image(selected_vdso32); + init_vdso_image(&vdso_image_32); return 0; } diff --git a/kernel/arch/x86/vdso/vdso32/.gitignore b/kernel/arch/x86/entry/vdso/vdso32/.gitignore index e45fba9d0..e45fba9d0 100644 --- a/kernel/arch/x86/vdso/vdso32/.gitignore +++ b/kernel/arch/x86/entry/vdso/vdso32/.gitignore diff --git a/kernel/arch/x86/vdso/vdso32/note.S b/kernel/arch/x86/entry/vdso/vdso32/note.S index c83f25734..c83f25734 100644 --- a/kernel/arch/x86/vdso/vdso32/note.S +++ b/kernel/arch/x86/entry/vdso/vdso32/note.S diff --git a/kernel/arch/x86/vdso/vdso32/sigreturn.S b/kernel/arch/x86/entry/vdso/vdso32/sigreturn.S index d7ec4e251..d7ec4e251 100644 --- a/kernel/arch/x86/vdso/vdso32/sigreturn.S +++ b/kernel/arch/x86/entry/vdso/vdso32/sigreturn.S diff --git a/kernel/arch/x86/entry/vdso/vdso32/system_call.S b/kernel/arch/x86/entry/vdso/vdso32/system_call.S new file mode 100644 index 000000000..3a1d92970 --- /dev/null +++ b/kernel/arch/x86/entry/vdso/vdso32/system_call.S @@ -0,0 +1,89 @@ +/* + * AT_SYSINFO entry point +*/ + +#include <asm/dwarf2.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> + +/* + * First get the common code for the sigreturn entry points. + * This must come first. + */ +#include "sigreturn.S" + + .text + .globl __kernel_vsyscall + .type __kernel_vsyscall,@function + ALIGN +__kernel_vsyscall: + CFI_STARTPROC + /* + * Reshuffle regs so that all of any of the entry instructions + * will preserve enough state. + * + * A really nice entry sequence would be: + * pushl %edx + * pushl %ecx + * movl %esp, %ecx + * + * Unfortunately, naughty Android versions between July and December + * 2015 actually hardcode the traditional Linux SYSENTER entry + * sequence. That is severely broken for a number of reasons (ask + * anyone with an AMD CPU, for example). Nonetheless, we try to keep + * it working approximately as well as it ever worked. + * + * This link may eludicate some of the history: + * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 + * personally, I find it hard to understand what's going on there. + * + * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE. + * Execute an indirect call to the address in the AT_SYSINFO auxv + * entry. That is the ONLY correct way to make a fast 32-bit system + * call on Linux. (Open-coding int $0x80 is also fine, but it's + * slow.) + */ + pushl %ecx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ecx, 0 + pushl %edx + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET edx, 0 + pushl %ebp + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET ebp, 0 + + #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter" + #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall" + +#ifdef CONFIG_X86_64 + /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */ + ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \ + SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32 +#else + ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP +#endif + + /* Enter using int $0x80 */ + int $0x80 +GLOBAL(int80_landing_pad) + + /* + * Restore EDX and ECX in case they were clobbered. EBP is not + * clobbered (the kernel restores it), but it's cleaner and + * probably faster to pop it than to adjust ESP using addl. + */ + popl %ebp + CFI_RESTORE ebp + CFI_ADJUST_CFA_OFFSET -4 + popl %edx + CFI_RESTORE edx + CFI_ADJUST_CFA_OFFSET -4 + popl %ecx + CFI_RESTORE ecx + CFI_ADJUST_CFA_OFFSET -4 + ret + CFI_ENDPROC + + .size __kernel_vsyscall,.-__kernel_vsyscall + .previous diff --git a/kernel/arch/x86/vdso/vdso32/vclock_gettime.c b/kernel/arch/x86/entry/vdso/vdso32/vclock_gettime.c index 175cc72c0..87a86e017 100644 --- a/kernel/arch/x86/vdso/vdso32/vclock_gettime.c +++ b/kernel/arch/x86/entry/vdso/vdso32/vclock_gettime.c @@ -14,11 +14,13 @@ */ #undef CONFIG_64BIT #undef CONFIG_X86_64 +#undef CONFIG_PGTABLE_LEVELS #undef CONFIG_ILLEGAL_POINTER_VALUE #undef CONFIG_SPARSEMEM_VMEMMAP #undef CONFIG_NR_CPUS #define CONFIG_X86_32 1 +#define CONFIG_PGTABLE_LEVELS 2 #define CONFIG_PAGE_OFFSET 0 #define CONFIG_ILLEGAL_POINTER_VALUE 0 #define CONFIG_NR_CPUS 1 diff --git a/kernel/arch/x86/vdso/vdso32/vdso-fakesections.c b/kernel/arch/x86/entry/vdso/vdso32/vdso-fakesections.c index 541468e25..541468e25 100644 --- a/kernel/arch/x86/vdso/vdso32/vdso-fakesections.c +++ b/kernel/arch/x86/entry/vdso/vdso32/vdso-fakesections.c diff --git a/kernel/arch/x86/vdso/vdso32/vdso32.lds.S b/kernel/arch/x86/entry/vdso/vdso32/vdso32.lds.S index 31056cf29..31056cf29 100644 --- a/kernel/arch/x86/vdso/vdso32/vdso32.lds.S +++ b/kernel/arch/x86/entry/vdso/vdso32/vdso32.lds.S diff --git a/kernel/arch/x86/vdso/vdsox32.lds.S b/kernel/arch/x86/entry/vdso/vdsox32.lds.S index 697c11ece..697c11ece 100644 --- a/kernel/arch/x86/vdso/vdsox32.lds.S +++ b/kernel/arch/x86/entry/vdso/vdsox32.lds.S diff --git a/kernel/arch/x86/vdso/vgetcpu.c b/kernel/arch/x86/entry/vdso/vgetcpu.c index 8ec3d1f4c..8ec3d1f4c 100644 --- a/kernel/arch/x86/vdso/vgetcpu.c +++ b/kernel/arch/x86/entry/vdso/vgetcpu.c diff --git a/kernel/arch/x86/vdso/vma.c b/kernel/arch/x86/entry/vdso/vma.c index 1c9f750c3..64df47148 100644 --- a/kernel/arch/x86/vdso/vma.c +++ b/kernel/arch/x86/entry/vdso/vma.c @@ -177,24 +177,13 @@ up_fail: return ret; } -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static int load_vdso32(void) { - int ret; - if (vdso32_enabled != 1) /* Other values all mean "disabled" */ return 0; - ret = map_vdso(selected_vdso32, false); - if (ret) - return ret; - - if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN) - current_thread_info()->sysenter_return = - current->mm->context.vdso + - selected_vdso32->sym_VDSO32_SYSENTER_RETURN; - - return 0; + return map_vdso(&vdso_image_32, false); } #endif @@ -219,8 +208,11 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, return map_vdso(&vdso_image_x32, true); } #endif - +#ifdef CONFIG_IA32_EMULATION return load_vdso32(); +#else + return 0; +#endif } #endif #else diff --git a/kernel/arch/x86/entry/vsyscall/Makefile b/kernel/arch/x86/entry/vsyscall/Makefile new file mode 100644 index 000000000..a9f4856f6 --- /dev/null +++ b/kernel/arch/x86/entry/vsyscall/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the x86 low level vsyscall code +# +obj-y := vsyscall_gtod.o + +obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o + diff --git a/kernel/arch/x86/kernel/vsyscall_64.c b/kernel/arch/x86/entry/vsyscall/vsyscall_64.c index 2dcc6ff6f..174c25499 100644 --- a/kernel/arch/x86/kernel/vsyscall_64.c +++ b/kernel/arch/x86/entry/vsyscall/vsyscall_64.c @@ -38,7 +38,14 @@ #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" -static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE; +static enum { EMULATE, NATIVE, NONE } vsyscall_mode = +#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE) + NATIVE; +#elif defined(CONFIG_LEGACY_VSYSCALL_NONE) + NONE; +#else + EMULATE; +#endif static int __init vsyscall_setup(char *str) { @@ -277,7 +284,7 @@ static const char *gate_vma_name(struct vm_area_struct *vma) { return "[vsyscall]"; } -static struct vm_operations_struct gate_vma_ops = { +static const struct vm_operations_struct gate_vma_ops = { .name = gate_vma_name, }; static struct vm_area_struct gate_vma = { @@ -290,7 +297,7 @@ static struct vm_area_struct gate_vma = { struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { -#ifdef CONFIG_IA32_EMULATION +#ifdef CONFIG_COMPAT if (!mm || mm->context.ia32_compat) return NULL; #endif diff --git a/kernel/arch/x86/kernel/vsyscall_emu_64.S b/kernel/arch/x86/entry/vsyscall/vsyscall_emu_64.S index c9596a9af..c9596a9af 100644 --- a/kernel/arch/x86/kernel/vsyscall_emu_64.S +++ b/kernel/arch/x86/entry/vsyscall/vsyscall_emu_64.S diff --git a/kernel/arch/x86/kernel/vsyscall_gtod.c b/kernel/arch/x86/entry/vsyscall/vsyscall_gtod.c index 51e330416..51e330416 100644 --- a/kernel/arch/x86/kernel/vsyscall_gtod.c +++ b/kernel/arch/x86/entry/vsyscall/vsyscall_gtod.c diff --git a/kernel/arch/x86/kernel/vsyscall_trace.h b/kernel/arch/x86/entry/vsyscall/vsyscall_trace.h index a8b2edec5..9dd7359a3 100644 --- a/kernel/arch/x86/kernel/vsyscall_trace.h +++ b/kernel/arch/x86/entry/vsyscall/vsyscall_trace.h @@ -24,6 +24,6 @@ TRACE_EVENT(emulate_vsyscall, #endif #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../arch/x86/kernel +#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/ #define TRACE_INCLUDE_FILE vsyscall_trace #include <trace/define_trace.h> diff --git a/kernel/arch/x86/ia32/Makefile b/kernel/arch/x86/ia32/Makefile index bb635c641..cd4339bae 100644 --- a/kernel/arch/x86/ia32/Makefile +++ b/kernel/arch/x86/ia32/Makefile @@ -2,7 +2,7 @@ # Makefile for the ia32 kernel emulation subsystem. # -obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o +obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_signal.o obj-$(CONFIG_IA32_AOUT) += ia32_aout.o diff --git a/kernel/arch/x86/ia32/ia32_signal.c b/kernel/arch/x86/ia32/ia32_signal.c index c81d35e6c..0552884da 100644 --- a/kernel/arch/x86/ia32/ia32_signal.c +++ b/kernel/arch/x86/ia32/ia32_signal.c @@ -21,12 +21,12 @@ #include <linux/binfmts.h> #include <asm/ucontext.h> #include <asm/uaccess.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/ptrace.h> #include <asm/ia32_unistd.h> #include <asm/user32.h> -#include <asm/sigcontext32.h> +#include <uapi/asm/sigcontext.h> #include <asm/proto.h> #include <asm/vdso.h> #include <asm/sigframe.h> @@ -34,99 +34,6 @@ #include <asm/sys_ia32.h> #include <asm/smap.h> -int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) -{ - int err = 0; - bool ia32 = test_thread_flag(TIF_IA32); - - if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) - return -EFAULT; - - put_user_try { - /* If you change siginfo_t structure, please make sure that - this code is fixed accordingly. - 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. */ - put_user_ex(from->si_signo, &to->si_signo); - put_user_ex(from->si_errno, &to->si_errno); - put_user_ex((short)from->si_code, &to->si_code); - - if (from->si_code < 0) { - put_user_ex(from->si_pid, &to->si_pid); - put_user_ex(from->si_uid, &to->si_uid); - put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); - } else { - /* - * First 32bits of unions are always present: - * si_pid === si_band === si_tid === si_addr(LS half) - */ - put_user_ex(from->_sifields._pad[0], - &to->_sifields._pad[0]); - switch (from->si_code >> 16) { - case __SI_FAULT >> 16: - break; - case __SI_SYS >> 16: - put_user_ex(from->si_syscall, &to->si_syscall); - put_user_ex(from->si_arch, &to->si_arch); - break; - case __SI_CHLD >> 16: - if (ia32) { - put_user_ex(from->si_utime, &to->si_utime); - put_user_ex(from->si_stime, &to->si_stime); - } else { - put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); - put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); - } - put_user_ex(from->si_status, &to->si_status); - /* FALL THROUGH */ - default: - case __SI_KILL >> 16: - put_user_ex(from->si_uid, &to->si_uid); - break; - case __SI_POLL >> 16: - put_user_ex(from->si_fd, &to->si_fd); - break; - case __SI_TIMER >> 16: - put_user_ex(from->si_overrun, &to->si_overrun); - put_user_ex(ptr_to_compat(from->si_ptr), - &to->si_ptr); - break; - /* This is not generated by the kernel as of now. */ - case __SI_RT >> 16: - case __SI_MESGQ >> 16: - put_user_ex(from->si_uid, &to->si_uid); - put_user_ex(from->si_int, &to->si_int); - break; - } - } - } put_user_catch(err); - - return err; -} - -int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) -{ - int err = 0; - u32 ptr32; - - if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) - return -EFAULT; - - get_user_try { - get_user_ex(to->si_signo, &from->si_signo); - get_user_ex(to->si_errno, &from->si_errno); - get_user_ex(to->si_code, &from->si_code); - - get_user_ex(to->si_pid, &from->si_pid); - get_user_ex(to->si_uid, &from->si_uid); - get_user_ex(ptr32, &from->si_ptr); - to->si_ptr = compat_ptr(ptr32); - } get_user_catch(err); - - return err; -} - /* * Do a signal return; undo the signal stack. */ @@ -161,7 +68,7 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) } static int ia32_restore_sigcontext(struct pt_regs *regs, - struct sigcontext_ia32 __user *sc) + struct sigcontext_32 __user *sc) { unsigned int tmpflags, err = 0; void __user *buf; @@ -198,7 +105,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, buf = compat_ptr(tmp); } get_user_catch(err); - err |= restore_xstate_sig(buf, 1); + err |= fpu__restore_sig(buf, 1); force_iret(); @@ -263,7 +170,7 @@ badframe: * Set up a signal frame. */ -static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc, +static int ia32_setup_sigcontext(struct sigcontext_32 __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned int mask) { @@ -308,6 +215,7 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { + struct fpu *fpu = ¤t->thread.fpu; unsigned long sp; /* Default to using normal stack */ @@ -322,12 +230,12 @@ static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, ksig->ka.sa.sa_restorer) sp = (unsigned long) ksig->ka.sa.sa_restorer; - if (used_math()) { + if (fpu->fpstate_active) { unsigned long fx_aligned, math_size; - sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size); - *fpstate = (struct _fpstate_ia32 __user *) sp; - if (save_xstate_sig(*fpstate, (void __user *)fx_aligned, + sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); + *fpstate = (struct _fpstate_32 __user *) sp; + if (copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, math_size) < 0) return (void __user *) -1L; } @@ -381,7 +289,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, /* Return stub is in 32bit vsyscall page */ if (current->mm->context.vdso) restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_sigreturn; + vdso_image_32.sym___kernel_sigreturn; else restorer = &frame->retcode; } @@ -460,7 +368,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, restorer = ksig->ka.sa.sa_restorer; else restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_rt_sigreturn; + vdso_image_32.sym___kernel_rt_sigreturn; put_user_ex(ptr_to_compat(restorer), &frame->pretcode); /* diff --git a/kernel/arch/x86/ia32/ia32entry.S b/kernel/arch/x86/ia32/ia32entry.S deleted file mode 100644 index 72bf2680f..000000000 --- a/kernel/arch/x86/ia32/ia32entry.S +++ /dev/null @@ -1,611 +0,0 @@ -/* - * Compatibility mode system call entry point for x86-64. - * - * Copyright 2000-2002 Andi Kleen, SuSE Labs. - */ - -#include <asm/dwarf2.h> -#include <asm/calling.h> -#include <asm/asm-offsets.h> -#include <asm/current.h> -#include <asm/errno.h> -#include <asm/ia32_unistd.h> -#include <asm/thread_info.h> -#include <asm/segment.h> -#include <asm/irqflags.h> -#include <asm/asm.h> -#include <asm/smap.h> -#include <linux/linkage.h> -#include <linux/err.h> - -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_LE 0x40000000 - -#ifndef CONFIG_AUDITSYSCALL -#define sysexit_audit ia32_ret_from_sys_call -#define sysretl_audit ia32_ret_from_sys_call -#endif - - .section .entry.text, "ax" - - /* clobbers %rax */ - .macro CLEAR_RREGS _r9=rax - xorl %eax,%eax - movq %rax,R11(%rsp) - movq %rax,R10(%rsp) - movq %\_r9,R9(%rsp) - movq %rax,R8(%rsp) - .endm - - /* - * Reload arg registers from stack in case ptrace changed them. - * We don't reload %eax because syscall_trace_enter() returned - * the %rax value we should see. Instead, we just truncate that - * value to 32 bits again as we did on entry from user mode. - * If it's a new value set by user_regset during entry tracing, - * this matches the normal truncation of the user-mode value. - * If it's -1 to make us punt the syscall, then (u32)-1 is still - * an appropriately invalid value. - */ - .macro LOAD_ARGS32 _r9=0 - .if \_r9 - movl R9(%rsp),%r9d - .endif - movl RCX(%rsp),%ecx - movl RDX(%rsp),%edx - movl RSI(%rsp),%esi - movl RDI(%rsp),%edi - movl %eax,%eax /* zero extension */ - .endm - - .macro CFI_STARTPROC32 simple - CFI_STARTPROC \simple - CFI_UNDEFINED r8 - CFI_UNDEFINED r9 - CFI_UNDEFINED r10 - CFI_UNDEFINED r11 - CFI_UNDEFINED r12 - CFI_UNDEFINED r13 - CFI_UNDEFINED r14 - CFI_UNDEFINED r15 - .endm - -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) - -ENTRY(native_irq_enable_sysexit) - swapgs - sti - sysexit -ENDPROC(native_irq_enable_sysexit) -#endif - -/* - * 32bit SYSENTER instruction entry. - * - * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs. - * IF and VM in rflags are cleared (IOW: interrupts are off). - * SYSENTER does not save anything on the stack, - * and does not save old rip (!!!) and rflags. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp user stack - * 0(%ebp) arg6 - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. We set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ -ENTRY(ia32_sysenter_target) - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rsp,rbp - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - SWAPGS_UNSAFE_STACK - movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp - ENABLE_INTERRUPTS(CLBR_NONE) - - /* Zero-extending 32-bit regs, do not remove */ - movl %ebp, %ebp - movl %eax, %eax - - movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d - CFI_REGISTER rip,r10 - - /* Construct struct pt_regs on stack */ - pushq_cfi $__USER32_DS /* pt_regs->ss */ - pushq_cfi %rbp /* pt_regs->sp */ - CFI_REL_OFFSET rsp,0 - pushfq_cfi /* pt_regs->flags */ - pushq_cfi $__USER32_CS /* pt_regs->cs */ - pushq_cfi %r10 /* pt_regs->ip = thread_info->sysenter_return */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi_reg rax /* pt_regs->ax */ - cld - sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 10*8 - - /* - * no need to do an access_ok check here because rbp has been - * 32bit zero extended - */ - ASM_STAC -1: movl (%rbp),%ebp - _ASM_EXTABLE(1b,ia32_badarg) - ASM_CLAC - - /* - * Sysenter doesn't filter flags, so we need to clear NT - * ourselves. To save a few cycles, we can check whether - * NT was set instead of doing an unconditional popfq. - */ - testl $X86_EFLAGS_NT,EFLAGS(%rsp) - jnz sysenter_fix_flags -sysenter_flags_fixed: - - orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - CFI_REMEMBER_STATE - jnz sysenter_tracesys - cmpq $(IA32_NR_syscalls-1),%rax - ja ia32_badsys -sysenter_do_call: - /* 32bit syscall -> 64bit C ABI argument conversion */ - movl %edi,%r8d /* arg5 */ - movl %ebp,%r9d /* arg6 */ - xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ - movl %ebx,%edi /* arg1 */ - movl %edx,%edx /* arg3 (zero extension) */ -sysenter_dispatch: - call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz sysexit_audit -sysexit_from_sys_call: - /* - * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an - * NMI between STI and SYSEXIT has poorly specified behavior, - * and and NMI followed by an IRQ with usergs is fatal. So - * we just pretend we're using SYSEXIT but we really use - * SYSRETL instead. - * - * This code path is still called 'sysexit' because it pairs - * with 'sysenter' and it uses the SYSENTER calling convention. - */ - andl $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - movl RIP(%rsp),%ecx /* User %eip */ - CFI_REGISTER rip,rcx - RESTORE_RSI_RDI - xorl %edx,%edx /* avoid info leaks */ - xorq %r8,%r8 - xorq %r9,%r9 - xorq %r10,%r10 - movl EFLAGS(%rsp),%r11d /* User eflags */ - /*CFI_RESTORE rflags*/ - TRACE_IRQS_ON - - /* - * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT, - * since it avoids a dicey window with interrupts enabled. - */ - movl RSP(%rsp),%esp - - /* - * USERGS_SYSRET32 does: - * gsbase = user's gs base - * eip = ecx - * rflags = r11 - * cs = __USER32_CS - * ss = __USER_DS - * - * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does: - * - * pop %ebp - * pop %edx - * pop %ecx - * - * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to - * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's - * address (already known to user code), and R12-R15 are - * callee-saved and therefore don't contain any interesting - * kernel data. - */ - USERGS_SYSRET32 - - CFI_RESTORE_STATE - -#ifdef CONFIG_AUDITSYSCALL - .macro auditsys_entry_common - movl %esi,%r8d /* 5th arg: 4th syscall arg */ - movl %ecx,%r9d /*swap with edx*/ - movl %edx,%ecx /* 4th arg: 3rd syscall arg */ - movl %r9d,%edx /* 3rd arg: 2nd syscall arg */ - movl %ebx,%esi /* 2nd arg: 1st syscall arg */ - movl %eax,%edi /* 1st arg: syscall number */ - call __audit_syscall_entry - movl RAX(%rsp),%eax /* reload syscall number */ - cmpq $(IA32_NR_syscalls-1),%rax - ja ia32_badsys - movl %ebx,%edi /* reload 1st syscall arg */ - movl RCX(%rsp),%esi /* reload 2nd syscall arg */ - movl RDX(%rsp),%edx /* reload 3rd syscall arg */ - movl RSI(%rsp),%ecx /* reload 4th syscall arg */ - movl RDI(%rsp),%r8d /* reload 5th syscall arg */ - .endm - - .macro auditsys_exit exit - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz ia32_ret_from_sys_call - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - movl %eax,%esi /* second arg, syscall return value */ - cmpl $-MAX_ERRNO,%eax /* is it an error ? */ - jbe 1f - movslq %eax, %rsi /* if error sign extend to 64 bits */ -1: setbe %al /* 1 if error, 0 if not */ - movzbl %al,%edi /* zero-extend that into %edi */ - call __audit_syscall_exit - movq RAX(%rsp),%rax /* reload syscall return value */ - movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jz \exit - CLEAR_RREGS - jmp int_with_check - .endm - -sysenter_auditsys: - auditsys_entry_common - movl %ebp,%r9d /* reload 6th syscall arg */ - jmp sysenter_dispatch - -sysexit_audit: - auditsys_exit sysexit_from_sys_call -#endif - -sysenter_fix_flags: - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) - popfq_cfi - jmp sysenter_flags_fixed - -sysenter_tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jz sysenter_auditsys -#endif - SAVE_EXTRA_REGS - CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS32 /* reload args from stack in case ptrace changed it */ - RESTORE_EXTRA_REGS - cmpq $(IA32_NR_syscalls-1),%rax - ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ - jmp sysenter_do_call - CFI_ENDPROC -ENDPROC(ia32_sysenter_target) - -/* - * 32bit SYSCALL instruction entry. - * - * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, - * then loads new ss, cs, and rip from previously programmed MSRs. - * rflags gets masked by a value from another MSR (so CLD and CLAC - * are not needed). SYSCALL does not save anything on the stack - * and does not change rsp. - * - * Note: rflags saving+masking-with-MSR happens only in Long mode - * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it). - * Don't get confused: rflags saving+masking depends on Long Mode Active bit - * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes - * or target CS descriptor's L bit (SYSCALL does not read segment descriptors). - * - * Arguments: - * eax system call number - * ecx return address - * ebx arg1 - * ebp arg2 (note: not saved in the stack frame, should not be touched) - * edx arg3 - * esi arg4 - * edi arg5 - * esp user stack - * 0(%esp) arg6 - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. We set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ -ENTRY(ia32_cstar_target) - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,0 - CFI_REGISTER rip,rcx - /*CFI_REGISTER rflags,r11*/ - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - SWAPGS_UNSAFE_STACK - movl %esp,%r8d - CFI_REGISTER rsp,r8 - movq PER_CPU_VAR(kernel_stack),%rsp - ENABLE_INTERRUPTS(CLBR_NONE) - - /* Zero-extending 32-bit regs, do not remove */ - movl %eax,%eax - - /* Construct struct pt_regs on stack */ - pushq_cfi $__USER32_DS /* pt_regs->ss */ - pushq_cfi %r8 /* pt_regs->sp */ - CFI_REL_OFFSET rsp,0 - pushq_cfi %r11 /* pt_regs->flags */ - pushq_cfi $__USER32_CS /* pt_regs->cs */ - pushq_cfi %rcx /* pt_regs->ip */ - CFI_REL_OFFSET rip,0 - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rbp /* pt_regs->cx */ - movl %ebp,%ecx - pushq_cfi_reg rax /* pt_regs->ax */ - sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 10*8 - - /* - * no need to do an access_ok check here because r8 has been - * 32bit zero extended - */ - ASM_STAC -1: movl (%r8),%r9d - _ASM_EXTABLE(1b,ia32_badarg) - ASM_CLAC - orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - CFI_REMEMBER_STATE - jnz cstar_tracesys - cmpq $IA32_NR_syscalls-1,%rax - ja ia32_badsys -cstar_do_call: - /* 32bit syscall -> 64bit C ABI argument conversion */ - movl %edi,%r8d /* arg5 */ - /* r9 already loaded */ /* arg6 */ - xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ - movl %ebx,%edi /* arg1 */ - movl %edx,%edx /* arg3 (zero extension) */ -cstar_dispatch: - call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX(%rsp) - DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz sysretl_audit -sysretl_from_sys_call: - andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - RESTORE_RSI_RDI_RDX - movl RIP(%rsp),%ecx - CFI_REGISTER rip,rcx - movl EFLAGS(%rsp),%r11d - /*CFI_REGISTER rflags,r11*/ - xorq %r10,%r10 - xorq %r9,%r9 - xorq %r8,%r8 - TRACE_IRQS_ON - movl RSP(%rsp),%esp - CFI_RESTORE rsp - /* - * 64bit->32bit SYSRET restores eip from ecx, - * eflags from r11 (but RF and VM bits are forced to 0), - * cs and ss are loaded from MSRs. - * (Note: 32bit->32bit SYSRET is different: since r11 - * does not exist, it merely sets eflags.IF=1). - * - * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss - * descriptor is not reinitialized. This means that we must - * avoid SYSRET with SS == NULL, which could happen if we schedule, - * exit the kernel, and re-enter using an interrupt vector. (All - * interrupt entries on x86_64 set SS to NULL.) We prevent that - * from happening by reloading SS in __switch_to. - */ - USERGS_SYSRET32 - -#ifdef CONFIG_AUDITSYSCALL -cstar_auditsys: - CFI_RESTORE_STATE - movl %r9d,R9(%rsp) /* register to be clobbered by call */ - auditsys_entry_common - movl R9(%rsp),%r9d /* reload 6th syscall arg */ - jmp cstar_dispatch - -sysretl_audit: - auditsys_exit sysretl_from_sys_call -#endif - -cstar_tracesys: -#ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jz cstar_auditsys -#endif - xchgl %r9d,%ebp - SAVE_EXTRA_REGS - CLEAR_RREGS r9 - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */ - RESTORE_EXTRA_REGS - xchgl %ebp,%r9d - cmpq $(IA32_NR_syscalls-1),%rax - ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ - jmp cstar_do_call -END(ia32_cstar_target) - -ia32_badarg: - ASM_CLAC - movq $-EFAULT,%rax - jmp ia32_sysret - CFI_ENDPROC - -/* - * Emulated IA32 system calls via int 0x80. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp arg6 (note: not saved in the stack frame, should not be touched) - * - * Notes: - * Uses the same stack frame as the x86-64 version. - * All registers except eax must be saved (but ptrace may violate that). - * Arguments are zero extended. For system calls that want sign extension and - * take long arguments a wrapper is needed. Most calls can just be called - * directly. - * Assumes it is only called from user space and entered with interrupts off. - */ - -ENTRY(ia32_syscall) - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,5*8 - /*CFI_REL_OFFSET ss,4*8 */ - CFI_REL_OFFSET rsp,3*8 - /*CFI_REL_OFFSET rflags,2*8 */ - /*CFI_REL_OFFSET cs,1*8 */ - CFI_REL_OFFSET rip,0*8 - - /* - * Interrupts are off on entry. - * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, - * it is too small to ever cause noticeable irq latency. - */ - PARAVIRT_ADJUST_EXCEPTION_FRAME - SWAPGS - ENABLE_INTERRUPTS(CLBR_NONE) - - /* Zero-extending 32-bit regs, do not remove */ - movl %eax,%eax - - /* Construct struct pt_regs on stack (iret frame is already on stack) */ - pushq_cfi_reg rax /* pt_regs->orig_ax */ - pushq_cfi_reg rdi /* pt_regs->di */ - pushq_cfi_reg rsi /* pt_regs->si */ - pushq_cfi_reg rdx /* pt_regs->dx */ - pushq_cfi_reg rcx /* pt_regs->cx */ - pushq_cfi_reg rax /* pt_regs->ax */ - cld - sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ - CFI_ADJUST_CFA_OFFSET 10*8 - - orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) - testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) - jnz ia32_tracesys - cmpq $(IA32_NR_syscalls-1),%rax - ja ia32_badsys -ia32_do_call: - /* 32bit syscall -> 64bit C ABI argument conversion */ - movl %edi,%r8d /* arg5 */ - movl %ebp,%r9d /* arg6 */ - xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ - movl %ebx,%edi /* arg1 */ - movl %edx,%edx /* arg3 (zero extension) */ - call *ia32_sys_call_table(,%rax,8) # xxx: rip relative -ia32_sysret: - movq %rax,RAX(%rsp) -ia32_ret_from_sys_call: - CLEAR_RREGS - jmp int_ret_from_sys_call - -ia32_tracesys: - SAVE_EXTRA_REGS - CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS32 /* reload args from stack in case ptrace changed it */ - RESTORE_EXTRA_REGS - cmpq $(IA32_NR_syscalls-1),%rax - ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */ - jmp ia32_do_call -END(ia32_syscall) - -ia32_badsys: - movq $0,ORIG_RAX(%rsp) - movq $-ENOSYS,%rax - jmp ia32_sysret - - CFI_ENDPROC - - .macro PTREGSCALL label, func - ALIGN -GLOBAL(\label) - leaq \func(%rip),%rax - jmp ia32_ptregs_common - .endm - - CFI_STARTPROC32 - - PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn - PTREGSCALL stub32_sigreturn, sys32_sigreturn - PTREGSCALL stub32_fork, sys_fork - PTREGSCALL stub32_vfork, sys_vfork - - ALIGN -GLOBAL(stub32_clone) - leaq sys_clone(%rip),%rax - mov %r8, %rcx - jmp ia32_ptregs_common - - ALIGN -ia32_ptregs_common: - CFI_ENDPROC - CFI_STARTPROC32 simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,SIZEOF_PTREGS - CFI_REL_OFFSET rax,RAX - CFI_REL_OFFSET rcx,RCX - CFI_REL_OFFSET rdx,RDX - CFI_REL_OFFSET rsi,RSI - CFI_REL_OFFSET rdi,RDI - CFI_REL_OFFSET rip,RIP -/* CFI_REL_OFFSET cs,CS*/ -/* CFI_REL_OFFSET rflags,EFLAGS*/ - CFI_REL_OFFSET rsp,RSP -/* CFI_REL_OFFSET ss,SS*/ - SAVE_EXTRA_REGS 8 - call *%rax - RESTORE_EXTRA_REGS 8 - ret - CFI_ENDPROC -END(ia32_ptregs_common) diff --git a/kernel/arch/x86/include/asm/Kbuild b/kernel/arch/x86/include/asm/Kbuild index d55a210a4..aeac434c9 100644 --- a/kernel/arch/x86/include/asm/Kbuild +++ b/kernel/arch/x86/include/asm/Kbuild @@ -9,4 +9,4 @@ generic-y += cputime.h generic-y += dma-contiguous.h generic-y += early_ioremap.h generic-y += mcs_spinlock.h -generic-y += scatterlist.h +generic-y += mm-arch-hooks.h diff --git a/kernel/arch/x86/include/asm/acpi.h b/kernel/arch/x86/include/asm/acpi.h index 3a45668f6..94c18ebfd 100644 --- a/kernel/arch/x86/include/asm/acpi.h +++ b/kernel/arch/x86/include/asm/acpi.h @@ -32,6 +32,10 @@ #include <asm/mpspec.h> #include <asm/realmode.h> +#ifdef CONFIG_ACPI_APEI +# include <asm/pgtable_types.h> +#endif + #ifdef CONFIG_ACPI extern int acpi_lapic; extern int acpi_ioapic; @@ -147,4 +151,23 @@ extern int x86_acpi_numa_init(void); #define acpi_unlazy_tlb(x) leave_mm(x) +#ifdef CONFIG_ACPI_APEI +static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) +{ + /* + * We currently have no way to look up the EFI memory map + * attributes for a region in a consistent way, because the + * memmap is discarded after efi_free_boot_services(). So if + * you call efi_mem_attributes() during boot and at runtime, + * you could theoretically see different attributes. + * + * Since we are yet to see any x86 platforms that require + * anything other than PAGE_KERNEL (some arm64 platforms + * require the equivalent of PAGE_KERNEL_NOCACHE), return that + * until we know differently. + */ + return PAGE_KERNEL; +} +#endif + #endif /* _ASM_X86_ACPI_H */ diff --git a/kernel/arch/x86/include/asm/alternative-asm.h b/kernel/arch/x86/include/asm/alternative-asm.h index bdf02eeee..e7636bac7 100644 --- a/kernel/arch/x86/include/asm/alternative-asm.h +++ b/kernel/arch/x86/include/asm/alternative-asm.h @@ -18,6 +18,12 @@ .endm #endif +/* + * Issue one struct alt_instr descriptor entry (need to put it into + * the section .altinstructions, see below). This entry contains + * enough information for the alternatives patching code to patch an + * instruction. See apply_alternatives(). + */ .macro altinstruction_entry orig alt feature orig_len alt_len pad_len .long \orig - . .long \alt - . @@ -27,6 +33,12 @@ .byte \pad_len .endm +/* + * Define an alternative between two instructions. If @feature is + * present, early code in apply_alternatives() replaces @oldinstr with + * @newinstr. ".skip" directive takes care of proper instruction padding + * in case @newinstr is longer than @oldinstr. + */ .macro ALTERNATIVE oldinstr, newinstr, feature 140: \oldinstr @@ -55,6 +67,12 @@ */ #define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) + +/* + * Same as ALTERNATIVE macro above but for two alternatives. If CPU + * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has + * @feature2, it replaces @oldinstr with @feature2. + */ .macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 140: \oldinstr diff --git a/kernel/arch/x86/include/asm/alternative.h b/kernel/arch/x86/include/asm/alternative.h index ba32af062..7bfc85bbb 100644 --- a/kernel/arch/x86/include/asm/alternative.h +++ b/kernel/arch/x86/include/asm/alternative.h @@ -52,6 +52,12 @@ struct alt_instr { u8 padlen; /* length of build-time padding */ } __packed; +/* + * Debug flag that can be tested to see whether alternative + * instructions were patched in already: + */ +extern int alternatives_patched; + extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); diff --git a/kernel/arch/x86/include/asm/amd_nb.h b/kernel/arch/x86/include/asm/amd_nb.h index aaac3b2fb..3c56ef1ae 100644 --- a/kernel/arch/x86/include/asm/amd_nb.h +++ b/kernel/arch/x86/include/asm/amd_nb.h @@ -81,7 +81,7 @@ static inline struct amd_northbridge *node_to_amd_nb(int node) return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL; } -static inline u16 amd_get_node_id(struct pci_dev *pdev) +static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) { struct pci_dev *misc; int i; @@ -98,11 +98,22 @@ static inline u16 amd_get_node_id(struct pci_dev *pdev) return 0; } +static inline bool amd_gart_present(void) +{ + /* GART present only on Fam15h, upto model 0fh */ + if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + return true; + + return false; +} + #else #define amd_nb_num(x) 0 #define amd_nb_has_feature(x) false #define node_to_amd_nb(x) NULL +#define amd_gart_present(x) false #endif diff --git a/kernel/arch/x86/include/asm/apic.h b/kernel/arch/x86/include/asm/apic.h index 976b86a32..a30316bf8 100644 --- a/kernel/arch/x86/include/asm/apic.h +++ b/kernel/arch/x86/include/asm/apic.h @@ -115,6 +115,59 @@ static inline bool apic_is_x2apic_enabled(void) return msr & X2APIC_ENABLE; } +extern void enable_IR_x2apic(void); + +extern int get_physical_broadcast(void); + +extern int lapic_get_maxlvt(void); +extern void clear_local_APIC(void); +extern void disconnect_bsp_APIC(int virt_wire_setup); +extern void disable_local_APIC(void); +extern void lapic_shutdown(void); +extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); +extern void setup_local_APIC(void); +extern void init_apic_mappings(void); +void register_lapic_address(unsigned long address); +extern void setup_boot_APIC_clock(void); +extern void setup_secondary_APIC_clock(void); +extern int APIC_init_uniprocessor(void); + +#ifdef CONFIG_X86_64 +static inline int apic_force_enable(unsigned long addr) +{ + return -1; +} +#else +extern int apic_force_enable(unsigned long addr); +#endif + +extern int apic_bsp_setup(bool upmode); +extern void apic_ap_setup(void); + +/* + * On 32bit this is mach-xxx local + */ +#ifdef CONFIG_X86_64 +extern int apic_is_clustered_box(void); +#else +static inline int apic_is_clustered_box(void) +{ + return 0; +} +#endif + +extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); + +#else /* !CONFIG_X86_LOCAL_APIC */ +static inline void lapic_shutdown(void) { } +#define local_apic_timer_c2_ok 1 +static inline void init_apic_mappings(void) { } +static inline void disable_local_APIC(void) { } +# define setup_boot_APIC_clock x86_init_noop +# define setup_secondary_APIC_clock x86_init_noop +#endif /* !CONFIG_X86_LOCAL_APIC */ + #ifdef CONFIG_X86_X2APIC /* * Make previous memory operations globally visible before @@ -186,67 +239,14 @@ static inline int x2apic_enabled(void) } #define x2apic_supported() (cpu_has_x2apic) -#else +#else /* !CONFIG_X86_X2APIC */ static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } static inline int x2apic_enabled(void) { return 0; } #define x2apic_mode (0) #define x2apic_supported() (0) -#endif - -extern void enable_IR_x2apic(void); - -extern int get_physical_broadcast(void); - -extern int lapic_get_maxlvt(void); -extern void clear_local_APIC(void); -extern void disconnect_bsp_APIC(int virt_wire_setup); -extern void disable_local_APIC(void); -extern void lapic_shutdown(void); -extern void sync_Arb_IDs(void); -extern void init_bsp_APIC(void); -extern void setup_local_APIC(void); -extern void init_apic_mappings(void); -void register_lapic_address(unsigned long address); -extern void setup_boot_APIC_clock(void); -extern void setup_secondary_APIC_clock(void); -extern int APIC_init_uniprocessor(void); - -#ifdef CONFIG_X86_64 -static inline int apic_force_enable(unsigned long addr) -{ - return -1; -} -#else -extern int apic_force_enable(unsigned long addr); -#endif - -extern int apic_bsp_setup(bool upmode); -extern void apic_ap_setup(void); - -/* - * On 32bit this is mach-xxx local - */ -#ifdef CONFIG_X86_64 -extern int apic_is_clustered_box(void); -#else -static inline int apic_is_clustered_box(void) -{ - return 0; -} -#endif - -extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); - -#else /* !CONFIG_X86_LOCAL_APIC */ -static inline void lapic_shutdown(void) { } -#define local_apic_timer_c2_ok 1 -static inline void init_apic_mappings(void) { } -static inline void disable_local_APIC(void) { } -# define setup_boot_APIC_clock x86_init_noop -# define setup_secondary_APIC_clock x86_init_noop -#endif /* !CONFIG_X86_LOCAL_APIC */ +#endif /* !CONFIG_X86_X2APIC */ #ifdef CONFIG_X86_64 #define SET_APIC_ID(x) (apic->set_apic_id(x)) @@ -313,7 +313,6 @@ struct apic { /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); - bool wait_for_init_deassert; void (*inquire_remote_apic)(int apicid); /* apic ops */ @@ -378,7 +377,6 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[]; * APIC functionality to boot other CPUs - only used on SMP: */ #ifdef CONFIG_SMP -extern atomic_t init_deasserted; extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip); #endif @@ -644,6 +642,12 @@ static inline void entering_ack_irq(void) entering_irq(); } +static inline void ipi_entering_ack_irq(void) +{ + ack_APIC_irq(); + irq_enter(); +} + static inline void exiting_irq(void) { irq_exit(); diff --git a/kernel/arch/x86/include/asm/arch_hweight.h b/kernel/arch/x86/include/asm/arch_hweight.h index 9686c3d9f..259a7c1ef 100644 --- a/kernel/arch/x86/include/asm/arch_hweight.h +++ b/kernel/arch/x86/include/asm/arch_hweight.h @@ -21,7 +21,7 @@ * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective * compiler switches. */ -static inline unsigned int __arch_hweight32(unsigned int w) +static __always_inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res = 0; @@ -42,20 +42,23 @@ static inline unsigned int __arch_hweight8(unsigned int w) return __arch_hweight32(w & 0xff); } +#ifdef CONFIG_X86_32 static inline unsigned long __arch_hweight64(__u64 w) { - unsigned long res = 0; - -#ifdef CONFIG_X86_32 return __arch_hweight32((u32)w) + __arch_hweight32((u32)(w >> 32)); +} #else +static __always_inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res = 0; + asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); -#endif /* CONFIG_X86_32 */ return res; } +#endif /* CONFIG_X86_32 */ #endif diff --git a/kernel/arch/x86/include/asm/asm.h b/kernel/arch/x86/include/asm/asm.h index 7730c1c5c..189679aba 100644 --- a/kernel/arch/x86/include/asm/asm.h +++ b/kernel/arch/x86/include/asm/asm.h @@ -63,6 +63,31 @@ _ASM_ALIGN ; \ _ASM_PTR (entry); \ .popsection + +.macro ALIGN_DESTINATION + /* check for bad alignment of destination */ + movl %edi,%ecx + andl $7,%ecx + jz 102f /* already aligned */ + subl $8,%ecx + negl %ecx + subl %ecx,%edx +100: movb (%rsi),%al +101: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz 100b +102: + .section .fixup,"ax" +103: addl %ecx,%edx /* ecx is zerorest also */ + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE(100b,103b) + _ASM_EXTABLE(101b,103b) + .endm + #else # define _ASM_EXTABLE(from,to) \ " .pushsection \"__ex_table\",\"a\"\n" \ diff --git a/kernel/arch/x86/include/asm/atomic.h b/kernel/arch/x86/include/asm/atomic.h index 5e5cd123f..ae5fb83e6 100644 --- a/kernel/arch/x86/include/asm/atomic.h +++ b/kernel/arch/x86/include/asm/atomic.h @@ -22,9 +22,9 @@ * * Atomically reads the value of @v. */ -static inline int atomic_read(const atomic_t *v) +static __always_inline int atomic_read(const atomic_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** @@ -34,9 +34,9 @@ static inline int atomic_read(const atomic_t *v) * * Atomically sets the value of @v to @i. */ -static inline void atomic_set(atomic_t *v, int i) +static __always_inline void atomic_set(atomic_t *v, int i) { - v->counter = i; + WRITE_ONCE(v->counter, i); } /** @@ -46,7 +46,7 @@ static inline void atomic_set(atomic_t *v, int i) * * Atomically adds @i to @v. */ -static inline void atomic_add(int i, atomic_t *v) +static __always_inline void atomic_add(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "addl %1,%0" : "+m" (v->counter) @@ -60,7 +60,7 @@ static inline void atomic_add(int i, atomic_t *v) * * Atomically subtracts @i from @v. */ -static inline void atomic_sub(int i, atomic_t *v) +static __always_inline void atomic_sub(int i, atomic_t *v) { asm volatile(LOCK_PREFIX "subl %1,%0" : "+m" (v->counter) @@ -76,7 +76,7 @@ static inline void atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -static inline int atomic_sub_and_test(int i, atomic_t *v) +static __always_inline int atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e"); } @@ -87,7 +87,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -static inline void atomic_inc(atomic_t *v) +static __always_inline void atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); @@ -99,7 +99,7 @@ static inline void atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -static inline void atomic_dec(atomic_t *v) +static __always_inline void atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); @@ -113,7 +113,7 @@ static inline void atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -static inline int atomic_dec_and_test(atomic_t *v) +static __always_inline int atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e"); } @@ -126,7 +126,7 @@ static inline int atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -static inline int atomic_inc_and_test(atomic_t *v) +static __always_inline int atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e"); } @@ -140,7 +140,7 @@ static inline int atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -static inline int atomic_add_negative(int i, atomic_t *v) +static __always_inline int atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s"); } @@ -152,7 +152,7 @@ static inline int atomic_add_negative(int i, atomic_t *v) * * Atomically adds @i to @v and returns @i + @v */ -static inline int atomic_add_return(int i, atomic_t *v) +static __always_inline int atomic_add_return(int i, atomic_t *v) { return i + xadd(&v->counter, i); } @@ -164,7 +164,7 @@ static inline int atomic_add_return(int i, atomic_t *v) * * Atomically subtracts @i from @v and returns @v - @i */ -static inline int atomic_sub_return(int i, atomic_t *v) +static __always_inline int atomic_sub_return(int i, atomic_t *v) { return atomic_add_return(-i, v); } @@ -172,7 +172,7 @@ static inline int atomic_sub_return(int i, atomic_t *v) #define atomic_inc_return(v) (atomic_add_return(1, v)) #define atomic_dec_return(v) (atomic_sub_return(1, v)) -static inline int atomic_cmpxchg(atomic_t *v, int old, int new) +static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { return cmpxchg(&v->counter, old, new); } @@ -182,6 +182,21 @@ static inline int atomic_xchg(atomic_t *v, int new) return xchg(&v->counter, new); } +#define ATOMIC_OP(op) \ +static inline void atomic_##op(int i, atomic_t *v) \ +{ \ + asm volatile(LOCK_PREFIX #op"l %1,%0" \ + : "+m" (v->counter) \ + : "ir" (i) \ + : "memory"); \ +} + +ATOMIC_OP(and) +ATOMIC_OP(or) +ATOMIC_OP(xor) + +#undef ATOMIC_OP + /** * __atomic_add_unless - add unless the number is already a given value * @v: pointer of type atomic_t @@ -191,7 +206,7 @@ static inline int atomic_xchg(atomic_t *v, int new) * Atomically adds @a to @v, so long as @v was not already @u. * Returns the old value of @v. */ -static inline int __atomic_add_unless(atomic_t *v, int a, int u) +static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) { int c, old; c = atomic_read(v); @@ -213,22 +228,12 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u) * Atomically adds 1 to @v * Returns the new value of @u */ -static inline short int atomic_inc_short(short int *v) +static __always_inline short int atomic_inc_short(short int *v) { asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v)); return *v; } -/* These are x86-specific, used by some header files */ -#define atomic_clear_mask(mask, addr) \ - asm volatile(LOCK_PREFIX "andl %0,%1" \ - : : "r" (~(mask)), "m" (*(addr)) : "memory") - -#define atomic_set_mask(mask, addr) \ - asm volatile(LOCK_PREFIX "orl %0,%1" \ - : : "r" ((unsigned)(mask)), "m" (*(addr)) \ - : "memory") - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/kernel/arch/x86/include/asm/atomic64_32.h b/kernel/arch/x86/include/asm/atomic64_32.h index b154de75c..a11c30b77 100644 --- a/kernel/arch/x86/include/asm/atomic64_32.h +++ b/kernel/arch/x86/include/asm/atomic64_32.h @@ -313,4 +313,18 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v) #undef alternative_atomic64 #undef __alternative_atomic64 +#define ATOMIC64_OP(op, c_op) \ +static inline void atomic64_##op(long long i, atomic64_t *v) \ +{ \ + long long old, c = 0; \ + while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c) \ + c = old; \ +} + +ATOMIC64_OP(and, &) +ATOMIC64_OP(or, |) +ATOMIC64_OP(xor, ^) + +#undef ATOMIC64_OP + #endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/kernel/arch/x86/include/asm/atomic64_64.h b/kernel/arch/x86/include/asm/atomic64_64.h index f8d273e18..037351022 100644 --- a/kernel/arch/x86/include/asm/atomic64_64.h +++ b/kernel/arch/x86/include/asm/atomic64_64.h @@ -18,7 +18,7 @@ */ static inline long atomic64_read(const atomic64_t *v) { - return ACCESS_ONCE((v)->counter); + return READ_ONCE((v)->counter); } /** @@ -30,7 +30,7 @@ static inline long atomic64_read(const atomic64_t *v) */ static inline void atomic64_set(atomic64_t *v, long i) { - v->counter = i; + WRITE_ONCE(v->counter, i); } /** @@ -40,7 +40,7 @@ static inline void atomic64_set(atomic64_t *v, long i) * * Atomically adds @i to @v. */ -static inline void atomic64_add(long i, atomic64_t *v) +static __always_inline void atomic64_add(long i, atomic64_t *v) { asm volatile(LOCK_PREFIX "addq %1,%0" : "=m" (v->counter) @@ -81,7 +81,7 @@ static inline int atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -static inline void atomic64_inc(atomic64_t *v) +static __always_inline void atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) @@ -94,7 +94,7 @@ static inline void atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -static inline void atomic64_dec(atomic64_t *v) +static __always_inline void atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) @@ -148,7 +148,7 @@ static inline int atomic64_add_negative(long i, atomic64_t *v) * * Atomically adds @i to @v and returns @i + @v */ -static inline long atomic64_add_return(long i, atomic64_t *v) +static __always_inline long atomic64_add_return(long i, atomic64_t *v) { return i + xadd(&v->counter, i); } @@ -220,4 +220,19 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) return dec; } +#define ATOMIC64_OP(op) \ +static inline void atomic64_##op(long i, atomic64_t *v) \ +{ \ + asm volatile(LOCK_PREFIX #op"q %1,%0" \ + : "+m" (v->counter) \ + : "er" (i) \ + : "memory"); \ +} + +ATOMIC64_OP(and) +ATOMIC64_OP(or) +ATOMIC64_OP(xor) + +#undef ATOMIC64_OP + #endif /* _ASM_X86_ATOMIC64_64_H */ diff --git a/kernel/arch/x86/include/asm/barrier.h b/kernel/arch/x86/include/asm/barrier.h index 959e45b81..0681d2532 100644 --- a/kernel/arch/x86/include/asm/barrier.h +++ b/kernel/arch/x86/include/asm/barrier.h @@ -35,12 +35,12 @@ #define smp_mb() mb() #define smp_rmb() dma_rmb() #define smp_wmb() barrier() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) +#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) #else /* !SMP */ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() -#define set_mb(var, value) do { var = value; barrier(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) #endif /* SMP */ #define read_barrier_depends() do { } while (0) @@ -57,12 +57,12 @@ do { \ compiletime_assert_atomic_type(*p); \ smp_mb(); \ - ACCESS_ONCE(*p) = (v); \ + WRITE_ONCE(*p, v); \ } while (0) #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ smp_mb(); \ ___p1; \ @@ -74,12 +74,12 @@ do { \ do { \ compiletime_assert_atomic_type(*p); \ barrier(); \ - ACCESS_ONCE(*p) = (v); \ + WRITE_ONCE(*p, v); \ } while (0) #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ + typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ barrier(); \ ___p1; \ @@ -91,15 +91,4 @@ do { \ #define smp_mb__before_atomic() barrier() #define smp_mb__after_atomic() barrier() -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - */ -static __always_inline void rdtsc_barrier(void) -{ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); -} - #endif /* _ASM_X86_BARRIER_H */ diff --git a/kernel/arch/x86/include/asm/boot.h b/kernel/arch/x86/include/asm/boot.h index 4fa687a47..6b8d6e8cd 100644 --- a/kernel/arch/x86/include/asm/boot.h +++ b/kernel/arch/x86/include/asm/boot.h @@ -27,7 +27,7 @@ #define BOOT_HEAP_SIZE 0x400000 #else /* !CONFIG_KERNEL_BZIP2 */ -#define BOOT_HEAP_SIZE 0x8000 +#define BOOT_HEAP_SIZE 0x10000 #endif /* !CONFIG_KERNEL_BZIP2 */ diff --git a/kernel/arch/x86/include/asm/cacheflush.h b/kernel/arch/x86/include/asm/cacheflush.h index 47c8e32f6..e63aa38e8 100644 --- a/kernel/arch/x86/include/asm/cacheflush.h +++ b/kernel/arch/x86/include/asm/cacheflush.h @@ -4,11 +4,12 @@ /* Caches aren't brain-dead on the intel. */ #include <asm-generic/cacheflush.h> #include <asm/special_insns.h> +#include <asm/uaccess.h> /* * The set_memory_* API can be used to change various attributes of a virtual * address range. The attributes include: - * Cachability : UnCached, WriteCombining, WriteBack + * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack * Executability : eXeutable, NoteXecutable * Read/Write : ReadOnly, ReadWrite * Presence : NotPresent @@ -35,9 +36,11 @@ int _set_memory_uc(unsigned long addr, int numpages); int _set_memory_wc(unsigned long addr, int numpages); +int _set_memory_wt(unsigned long addr, int numpages); int _set_memory_wb(unsigned long addr, int numpages); int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); +int set_memory_wt(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_x(unsigned long addr, int numpages); int set_memory_nx(unsigned long addr, int numpages); @@ -48,10 +51,12 @@ int set_memory_4k(unsigned long addr, int numpages); int set_memory_array_uc(unsigned long *addr, int addrinarray); int set_memory_array_wc(unsigned long *addr, int addrinarray); +int set_memory_array_wt(unsigned long *addr, int addrinarray); int set_memory_array_wb(unsigned long *addr, int addrinarray); int set_pages_array_uc(struct page **pages, int addrinarray); int set_pages_array_wc(struct page **pages, int addrinarray); +int set_pages_array_wt(struct page **pages, int addrinarray); int set_pages_array_wb(struct page **pages, int addrinarray); /* @@ -84,6 +89,8 @@ int set_pages_rw(struct page *page, int numpages); void clflush_cache_range(void *addr, unsigned int size); +#define mmio_flush_range(addr, size) clflush_cache_range(addr, size) + #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; diff --git a/kernel/arch/x86/include/asm/cmpxchg.h b/kernel/arch/x86/include/asm/cmpxchg.h index 99c105d78..ad19841ed 100644 --- a/kernel/arch/x86/include/asm/cmpxchg.h +++ b/kernel/arch/x86/include/asm/cmpxchg.h @@ -4,8 +4,6 @@ #include <linux/compiler.h> #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __HAVE_ARCH_CMPXCHG 1 - /* * Non-existant functions to indicate usage errors at link time * (or compile-time if the compiler implements __compiletime_error(). diff --git a/kernel/arch/x86/include/asm/context_tracking.h b/kernel/arch/x86/include/asm/context_tracking.h deleted file mode 100644 index 1fe49704b..000000000 --- a/kernel/arch/x86/include/asm/context_tracking.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef _ASM_X86_CONTEXT_TRACKING_H -#define _ASM_X86_CONTEXT_TRACKING_H - -#ifdef CONFIG_CONTEXT_TRACKING -# define SCHEDULE_USER call schedule_user -#else -# define SCHEDULE_USER call schedule -#endif - -#endif diff --git a/kernel/arch/x86/include/asm/cpufeature.h b/kernel/arch/x86/include/asm/cpufeature.h index 3d6606fb9..f7ba9fbf1 100644 --- a/kernel/arch/x86/include/asm/cpufeature.h +++ b/kernel/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include <asm/disabled-features.h> #endif -#define NCAPINTS 13 /* N 32-bit words worth of info */ +#define NCAPINTS 14 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -119,6 +119,7 @@ #define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ #define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ #define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ #define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ #define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ #define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ @@ -176,6 +177,7 @@ #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ /* * Auxiliary flags: Linux defined - For features scattered in various @@ -191,7 +193,7 @@ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOITFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ +#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ #define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ #define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ @@ -214,6 +216,7 @@ #define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ @@ -239,6 +242,7 @@ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ /* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ #define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ @@ -252,6 +256,9 @@ /* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ +/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ +#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ + /* * BUG word(s) */ diff --git a/kernel/arch/x86/include/asm/crypto/glue_helper.h b/kernel/arch/x86/include/asm/crypto/glue_helper.h index 1eef55596..03bb1065c 100644 --- a/kernel/arch/x86/include/asm/crypto/glue_helper.h +++ b/kernel/arch/x86/include/asm/crypto/glue_helper.h @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <linux/crypto.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <crypto/b128ops.h> typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src); diff --git a/kernel/arch/x86/include/asm/delay.h b/kernel/arch/x86/include/asm/delay.h index 9b3b4f275..36a760bda 100644 --- a/kernel/arch/x86/include/asm/delay.h +++ b/kernel/arch/x86/include/asm/delay.h @@ -4,5 +4,6 @@ #include <asm-generic/delay.h> void use_tsc_delay(void); +void use_mwaitx_delay(void); #endif /* _ASM_X86_DELAY_H */ diff --git a/kernel/arch/x86/include/asm/dma-mapping.h b/kernel/arch/x86/include/asm/dma-mapping.h index 808dae63e..953b7263f 100644 --- a/kernel/arch/x86/include/asm/dma-mapping.h +++ b/kernel/arch/x86/include/asm/dma-mapping.h @@ -12,7 +12,6 @@ #include <linux/dma-attrs.h> #include <asm/io.h> #include <asm/swiotlb.h> -#include <asm-generic/dma-coherent.h> #include <linux/dma-contiguous.h> #ifdef CONFIG_ISA @@ -41,24 +40,13 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) #endif } -#include <asm-generic/dma-mapping-common.h> - -/* Make sure we keep the same behaviour */ -static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - debug_dma_mapping_error(dev, dma_addr); - if (ops->mapping_error) - return ops->mapping_error(dev, dma_addr); - - return (dma_addr == DMA_ERROR_CODE); -} - -#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) -#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) +bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp); +#define arch_dma_alloc_attrs arch_dma_alloc_attrs +#define HAVE_ARCH_DMA_SUPPORTED 1 extern int dma_supported(struct device *hwdev, u64 mask); -extern int dma_set_mask(struct device *dev, u64 mask); + +#include <asm-generic/dma-mapping-common.h> extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, @@ -125,52 +113,4 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) return gfp; } -#define dma_alloc_coherent(d,s,h,f) dma_alloc_attrs(d,s,h,f,NULL) - -static inline void * -dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - void *memory; - - gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); - - if (dma_alloc_from_coherent(dev, size, dma_handle, &memory)) - return memory; - - if (!dev) - dev = &x86_dma_fallback_dev; - - if (!is_device_dma_capable(dev)) - return NULL; - - if (!ops->alloc) - return NULL; - - memory = ops->alloc(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp), attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, memory); - - return memory; -} - -#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL) - -static inline void dma_free_attrs(struct device *dev, size_t size, - void *vaddr, dma_addr_t bus, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - - WARN_ON(irqs_disabled()); /* for portability */ - - if (dma_release_from_coherent(dev, get_order(size), vaddr)) - return; - - debug_dma_free_coherent(dev, size, vaddr, bus); - if (ops->free) - ops->free(dev, size, vaddr, bus, attrs); -} - #endif diff --git a/kernel/arch/x86/include/asm/dwarf2.h b/kernel/arch/x86/include/asm/dwarf2.h index de1cdaf4d..b7a1ab865 100644 --- a/kernel/arch/x86/include/asm/dwarf2.h +++ b/kernel/arch/x86/include/asm/dwarf2.h @@ -36,15 +36,22 @@ #endif #if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__) +#ifndef BUILD_VDSO /* * Emit CFI data in .debug_frame sections, not .eh_frame sections. * The latter we currently just discard since we don't do DWARF * unwinding at runtime. So only the offline DWARF information is - * useful to anyone. Note we should not use this directive if this - * file is used in the vDSO assembly, or if vmlinux.lds.S gets - * changed so it doesn't discard .eh_frame. + * useful to anyone. Note we should not use this directive if + * vmlinux.lds.S gets changed so it doesn't discard .eh_frame. */ .cfi_sections .debug_frame +#else + /* + * For the vDSO, emit both runtime unwind information and debug + * symbols for the .dbg file. + */ + .cfi_sections .eh_frame, .debug_frame +#endif #endif #else @@ -74,97 +81,4 @@ #endif -/* - * An attempt to make CFI annotations more or less - * correct and shorter. It is implied that you know - * what you're doing if you use them. - */ -#ifdef __ASSEMBLY__ -#ifdef CONFIG_X86_64 - .macro pushq_cfi reg - pushq \reg - CFI_ADJUST_CFA_OFFSET 8 - .endm - - .macro pushq_cfi_reg reg - pushq %\reg - CFI_ADJUST_CFA_OFFSET 8 - CFI_REL_OFFSET \reg, 0 - .endm - - .macro popq_cfi reg - popq \reg - CFI_ADJUST_CFA_OFFSET -8 - .endm - - .macro popq_cfi_reg reg - popq %\reg - CFI_ADJUST_CFA_OFFSET -8 - CFI_RESTORE \reg - .endm - - .macro pushfq_cfi - pushfq - CFI_ADJUST_CFA_OFFSET 8 - .endm - - .macro popfq_cfi - popfq - CFI_ADJUST_CFA_OFFSET -8 - .endm - - .macro movq_cfi reg offset=0 - movq %\reg, \offset(%rsp) - CFI_REL_OFFSET \reg, \offset - .endm - - .macro movq_cfi_restore offset reg - movq \offset(%rsp), %\reg - CFI_RESTORE \reg - .endm -#else /*!CONFIG_X86_64*/ - .macro pushl_cfi reg - pushl \reg - CFI_ADJUST_CFA_OFFSET 4 - .endm - - .macro pushl_cfi_reg reg - pushl %\reg - CFI_ADJUST_CFA_OFFSET 4 - CFI_REL_OFFSET \reg, 0 - .endm - - .macro popl_cfi reg - popl \reg - CFI_ADJUST_CFA_OFFSET -4 - .endm - - .macro popl_cfi_reg reg - popl %\reg - CFI_ADJUST_CFA_OFFSET -4 - CFI_RESTORE \reg - .endm - - .macro pushfl_cfi - pushfl - CFI_ADJUST_CFA_OFFSET 4 - .endm - - .macro popfl_cfi - popfl - CFI_ADJUST_CFA_OFFSET -4 - .endm - - .macro movl_cfi reg offset=0 - movl %\reg, \offset(%esp) - CFI_REL_OFFSET \reg, \offset - .endm - - .macro movl_cfi_restore offset reg - movl \offset(%esp), %\reg - CFI_RESTORE \reg - .endm -#endif /*!CONFIG_X86_64*/ -#endif /*__ASSEMBLY__*/ - #endif /* _ASM_X86_DWARF2_H */ diff --git a/kernel/arch/x86/include/asm/edac.h b/kernel/arch/x86/include/asm/edac.h index e9b57ecc7..cf8fdf83b 100644 --- a/kernel/arch/x86/include/asm/edac.h +++ b/kernel/arch/x86/include/asm/edac.h @@ -3,7 +3,7 @@ /* ECC atomic, DMA, SMP and interrupt safe scrub function */ -static inline void atomic_scrub(void *va, u32 size) +static inline void edac_atomic_scrub(void *va, u32 size) { u32 i, *virt_addr = va; diff --git a/kernel/arch/x86/include/asm/efi.h b/kernel/arch/x86/include/asm/efi.h index 3738b138b..0010c78c4 100644 --- a/kernel/arch/x86/include/asm/efi.h +++ b/kernel/arch/x86/include/asm/efi.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/pgtable.h> /* @@ -86,6 +86,18 @@ extern u64 asmlinkage efi_call(void *fp, ...); extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); +#ifdef CONFIG_KASAN +/* + * CONFIG_KASAN may redefine memset to __memset. __memset function is present + * only in kernel binary. Since the EFI stub linked into a separate binary it + * doesn't have __memset(). So we should use standard memset from + * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove. + */ +#undef memcpy +#undef memset +#undef memmove +#endif + #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; @@ -93,6 +105,7 @@ extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern pgd_t * __init efi_call_phys_prolog(void); extern void __init efi_call_phys_epilog(pgd_t *save_pgd); +extern void __init efi_print_memmap(void); extern void __init efi_unmap_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); diff --git a/kernel/arch/x86/include/asm/elf.h b/kernel/arch/x86/include/asm/elf.h index f161c189c..1514753fd 100644 --- a/kernel/arch/x86/include/asm/elf.h +++ b/kernel/arch/x86/include/asm/elf.h @@ -78,7 +78,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t; #ifdef CONFIG_X86_64 extern unsigned int vdso64_enabled; #endif -#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) extern unsigned int vdso32_enabled; #endif @@ -171,11 +171,11 @@ do { \ static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { - /* Commented-out registers are cleared in stub_execve */ - /*regs->ax = regs->bx =*/ regs->cx = regs->dx = 0; - regs->si = regs->di /*= regs->bp*/ = 0; + /* ax gets execve's return value. */ + /*regs->ax = */ regs->bx = regs->cx = regs->dx = 0; + regs->si = regs->di = regs->bp = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; - /*regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;*/ + regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; t->fs = t->gs = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; @@ -187,8 +187,8 @@ static inline void elf_common_init(struct thread_struct *t, #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) -void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); -#define compat_start_thread start_thread_ia32 +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp); +#define compat_start_thread compat_start_thread void set_personality_ia32(bool); #define COMPAT_SET_PERSONALITY(ex) \ @@ -328,7 +328,7 @@ else \ #define VDSO_ENTRY \ ((unsigned long)current->mm->context.vdso + \ - selected_vdso32->sym___kernel_vsyscall) + vdso_image_32.sym___kernel_vsyscall) struct linux_binprm; @@ -344,14 +344,9 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, */ static inline int mmap_is_ia32(void) { -#ifdef CONFIG_X86_32 - return 1; -#endif -#ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_ADDR32)) - return 1; -#endif - return 0; + return config_enabled(CONFIG_X86_32) || + (config_enabled(CONFIG_COMPAT) && + test_thread_flag(TIF_ADDR32)); } /* Do not change the values. See get_align_mask() */ diff --git a/kernel/arch/x86/include/asm/entry_arch.h b/kernel/arch/x86/include/asm/entry_arch.h index dc5fa6614..df002992d 100644 --- a/kernel/arch/x86/include/asm/entry_arch.h +++ b/kernel/arch/x86/include/asm/entry_arch.h @@ -23,6 +23,8 @@ BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) #ifdef CONFIG_HAVE_KVM BUILD_INTERRUPT3(kvm_posted_intr_ipi, POSTED_INTR_VECTOR, smp_kvm_posted_intr_ipi) +BUILD_INTERRUPT3(kvm_posted_intr_wakeup_ipi, POSTED_INTR_WAKEUP_VECTOR, + smp_kvm_posted_intr_wakeup_ipi) #endif /* @@ -50,4 +52,7 @@ BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR) BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR) #endif +#ifdef CONFIG_X86_MCE_AMD +BUILD_INTERRUPT(deferred_error_interrupt, DEFERRED_ERROR_VECTOR) +#endif #endif diff --git a/kernel/arch/x86/include/asm/espfix.h b/kernel/arch/x86/include/asm/espfix.h index 99efebb2f..ca3ce9ab9 100644 --- a/kernel/arch/x86/include/asm/espfix.h +++ b/kernel/arch/x86/include/asm/espfix.h @@ -9,7 +9,7 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); extern void init_espfix_bsp(void); -extern void init_espfix_ap(void); +extern void init_espfix_ap(int cpu); #endif /* CONFIG_X86_64 */ diff --git a/kernel/arch/x86/include/asm/fpu-internal.h b/kernel/arch/x86/include/asm/fpu-internal.h deleted file mode 100644 index da5e96756..000000000 --- a/kernel/arch/x86/include/asm/fpu-internal.h +++ /dev/null @@ -1,626 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _FPU_INTERNAL_H -#define _FPU_INTERNAL_H - -#include <linux/kernel_stat.h> -#include <linux/regset.h> -#include <linux/compat.h> -#include <linux/slab.h> -#include <asm/asm.h> -#include <asm/cpufeature.h> -#include <asm/processor.h> -#include <asm/sigcontext.h> -#include <asm/user.h> -#include <asm/uaccess.h> -#include <asm/xsave.h> -#include <asm/smap.h> - -#ifdef CONFIG_X86_64 -# include <asm/sigcontext32.h> -# include <asm/user32.h> -struct ksignal; -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -#else -# define user_i387_ia32_struct user_i387_struct -# define user32_fxsr_struct user_fxsr_struct -# define ia32_setup_frame __setup_frame -# define ia32_setup_rt_frame __setup_rt_frame -#endif - -extern unsigned int mxcsr_feature_mask; -extern void fpu_init(void); -extern void eager_fpu_init(void); - -DECLARE_PER_CPU(struct task_struct *, fpu_owner_task); - -extern void convert_from_fxsr(struct user_i387_ia32_struct *env, - struct task_struct *tsk); -extern void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env); - -extern user_regset_active_fn fpregs_active, xfpregs_active; -extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, - xstateregs_get; -extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, - xstateregs_set; - -/* - * xstateregs_active == fpregs_active. Please refer to the comment - * at the definition of fpregs_active. - */ -#define xstateregs_active fpregs_active - -#ifdef CONFIG_MATH_EMULATION -extern void finit_soft_fpu(struct i387_soft_struct *soft); -#else -static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} -#endif - -/* - * Must be run with preemption disabled: this clears the fpu_owner_task, - * on this CPU. - * - * This will disable any lazy FPU state restore of the current FPU state, - * but if the current thread owns the FPU, it will still be saved by. - */ -static inline void __cpu_disable_lazy_restore(unsigned int cpu) -{ - per_cpu(fpu_owner_task, cpu) = NULL; -} - -/* - * Used to indicate that the FPU state in memory is newer than the FPU - * state in registers, and the FPU state should be reloaded next time the - * task is run. Only safe on the current task, or non-running tasks. - */ -static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk) -{ - tsk->thread.fpu.last_cpu = ~0; -} - -static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) -{ - return new == this_cpu_read_stable(fpu_owner_task) && - cpu == new->thread.fpu.last_cpu; -} - -static inline int is_ia32_compat_frame(void) -{ - return config_enabled(CONFIG_IA32_EMULATION) && - test_thread_flag(TIF_IA32); -} - -static inline int is_ia32_frame(void) -{ - return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); -} - -static inline int is_x32_frame(void) -{ - return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); -} - -#define X87_FSW_ES (1 << 7) /* Exception Summary */ - -static __always_inline __pure bool use_eager_fpu(void) -{ - return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); -} - -static __always_inline __pure bool use_xsaveopt(void) -{ - return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); -} - -static __always_inline __pure bool use_xsave(void) -{ - return static_cpu_has_safe(X86_FEATURE_XSAVE); -} - -static __always_inline __pure bool use_fxsr(void) -{ - return static_cpu_has_safe(X86_FEATURE_FXSR); -} - -static inline void fx_finit(struct i387_fxsave_struct *fx) -{ - fx->cwd = 0x37f; - fx->mxcsr = MXCSR_DEFAULT; -} - -extern void __sanitize_i387_state(struct task_struct *); - -static inline void sanitize_i387_state(struct task_struct *tsk) -{ - if (!use_xsaveopt()) - return; - __sanitize_i387_state(tsk); -} - -#define user_insn(insn, output, input...) \ -({ \ - int err; \ - asm volatile(ASM_STAC "\n" \ - "1:" #insn "\n\t" \ - "2: " ASM_CLAC "\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -#define check_insn(insn, output, input...) \ -({ \ - int err; \ - asm volatile("1:" #insn "\n\t" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err), output \ - : "0"(0), input); \ - err; \ -}) - -static inline int fsave_user(struct i387_fsave_struct __user *fx) -{ - return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); -} - -static inline int fxsave_user(struct i387_fxsave_struct __user *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); -} - -static inline int fxrstor_checking(struct i387_fxsave_struct *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); -} - -static inline int fxrstor_user(struct i387_fxsave_struct __user *fx) -{ - if (config_enabled(CONFIG_X86_32)) - return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in fpu_fxsave() below. */ - return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); -} - -static inline int frstor_checking(struct i387_fsave_struct *fx) -{ - return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline int frstor_user(struct i387_fsave_struct __user *fx) -{ - return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); -} - -static inline void fpu_fxsave(struct fpu *fpu) -{ - if (config_enabled(CONFIG_X86_32)) - asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave)); - else if (config_enabled(CONFIG_AS_FXSAVEQ)) - asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state->fxsave)); - else { - /* Using "rex64; fxsave %0" is broken because, if the memory - * operand uses any extended registers for addressing, a second - * REX prefix will be generated (to the assembler, rex64 - * followed by semicolon is a separate instruction), and hence - * the 64-bitness is lost. - * - * Using "fxsaveq %0" would be the ideal choice, but is only - * supported starting with gas 2.16. - * - * Using, as a workaround, the properly prefixed form below - * isn't accepted by any binutils version so far released, - * complaining that the same type of prefix is used twice if - * an extended register is needed for addressing (fix submitted - * to mainline 2005-11-21). - * - * asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave)); - * - * This, however, we can work around by forcing the compiler to - * select an addressing mode that doesn't require extended - * registers. - */ - asm volatile( "rex64/fxsave (%[fx])" - : "=m" (fpu->state->fxsave) - : [fx] "R" (&fpu->state->fxsave)); - } -} - -/* - * These must be called with preempt disabled. Returns - * 'true' if the FPU state is still intact. - */ -static inline int fpu_save_init(struct fpu *fpu) -{ - if (use_xsave()) { - fpu_xsave(fpu); - - /* - * xsave header may indicate the init state of the FP. - */ - if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP)) - return 1; - } else if (use_fxsr()) { - fpu_fxsave(fpu); - } else { - asm volatile("fnsave %[fx]; fwait" - : [fx] "=m" (fpu->state->fsave)); - return 0; - } - - /* - * If exceptions are pending, we need to clear them so - * that we don't randomly get exceptions later. - * - * FIXME! Is this perhaps only true for the old-style - * irq13 case? Maybe we could leave the x87 state - * intact otherwise? - */ - if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) { - asm volatile("fnclex"); - return 0; - } - return 1; -} - -static inline int __save_init_fpu(struct task_struct *tsk) -{ - return fpu_save_init(&tsk->thread.fpu); -} - -static inline int fpu_restore_checking(struct fpu *fpu) -{ - if (use_xsave()) - return fpu_xrstor_checking(&fpu->state->xsave); - else if (use_fxsr()) - return fxrstor_checking(&fpu->state->fxsave); - else - return frstor_checking(&fpu->state->fsave); -} - -static inline int restore_fpu_checking(struct task_struct *tsk) -{ - /* - * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is - * pending. Clear the x87 state here by setting it to fixed values. - * "m" is a random variable that should be in L1. - */ - if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { - asm volatile( - "fnclex\n\t" - "emms\n\t" - "fildl %P[addr]" /* set F?P to defined value */ - : : [addr] "m" (tsk->thread.fpu.has_fpu)); - } - - return fpu_restore_checking(&tsk->thread.fpu); -} - -/* - * Software FPU state helpers. Careful: these need to - * be preemption protection *and* they need to be - * properly paired with the CR0.TS changes! - */ -static inline int __thread_has_fpu(struct task_struct *tsk) -{ - return tsk->thread.fpu.has_fpu; -} - -/* Must be paired with an 'stts' after! */ -static inline void __thread_clear_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 0; - this_cpu_write(fpu_owner_task, NULL); -} - -/* Must be paired with a 'clts' before! */ -static inline void __thread_set_has_fpu(struct task_struct *tsk) -{ - tsk->thread.fpu.has_fpu = 1; - this_cpu_write(fpu_owner_task, tsk); -} - -/* - * Encapsulate the CR0.TS handling together with the - * software flag. - * - * These generally need preemption protection to work, - * do try to avoid using these on their own. - */ -static inline void __thread_fpu_end(struct task_struct *tsk) -{ - __thread_clear_has_fpu(tsk); - if (!use_eager_fpu()) - stts(); -} - -static inline void __thread_fpu_begin(struct task_struct *tsk) -{ - if (!use_eager_fpu()) - clts(); - __thread_set_has_fpu(tsk); -} - -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - preempt_disable(); - tsk->thread.fpu_counter = 0; - - if (__thread_has_fpu(tsk)) { - /* Ignore delayed exceptions from user space */ - asm volatile("1: fwait\n" - "2:\n" - _ASM_EXTABLE(1b, 2b)); - __thread_fpu_end(tsk); - } - - clear_stopped_child_used_math(tsk); - preempt_enable(); -} - -static inline void restore_init_xstate(void) -{ - if (use_xsave()) - xrstor_state(init_xstate_buf, -1); - else - fxrstor_checking(&init_xstate_buf->i387); -} - -/* - * Reset the FPU state in the eager case and drop it in the lazy case (later use - * will reinit it). - */ -static inline void fpu_reset_state(struct task_struct *tsk) -{ - if (!use_eager_fpu()) - drop_fpu(tsk); - else - restore_init_xstate(); -} - -/* - * FPU state switching for scheduling. - * - * This is a two-stage process: - * - * - switch_fpu_prepare() saves the old state and - * sets the new state of the CR0.TS bit. This is - * done within the context of the old process. - * - * - switch_fpu_finish() restores the new state as - * necessary. - */ -typedef struct { int preload; } fpu_switch_t; - -static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) -{ - fpu_switch_t fpu; - - /* - * If the task has used the math, pre-load the FPU on xsave processors - * or if the past 5 consecutive context-switches used math. - */ - fpu.preload = tsk_used_math(new) && - (use_eager_fpu() || new->thread.fpu_counter > 5); - - if (__thread_has_fpu(old)) { - if (!__save_init_fpu(old)) - task_disable_lazy_fpu_restore(old); - else - old->thread.fpu.last_cpu = cpu; - - /* But leave fpu_owner_task! */ - old->thread.fpu.has_fpu = 0; - - /* Don't change CR0.TS if we just switch! */ - if (fpu.preload) { - new->thread.fpu_counter++; - __thread_set_has_fpu(new); - prefetch(new->thread.fpu.state); - } else if (!use_eager_fpu()) - stts(); - } else { - old->thread.fpu_counter = 0; - task_disable_lazy_fpu_restore(old); - if (fpu.preload) { - new->thread.fpu_counter++; - if (fpu_lazy_restore(new, cpu)) - fpu.preload = 0; - else - prefetch(new->thread.fpu.state); - __thread_fpu_begin(new); - } - } - return fpu; -} - -/* - * By the time this gets called, we've already cleared CR0.TS and - * given the process the FPU if we are going to preload the FPU - * state - all we need to do is to conditionally restore the register - * state itself. - */ -static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) -{ - if (fpu.preload) { - if (unlikely(restore_fpu_checking(new))) - fpu_reset_state(new); - } -} - -/* - * Signal frame handlers... - */ -extern int save_xstate_sig(void __user *buf, void __user *fx, int size); -extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size); - -static inline int xstate_sigframe_size(void) -{ - return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; -} - -static inline int restore_xstate_sig(void __user *buf, int ia32_frame) -{ - void __user *buf_fx = buf; - int size = xstate_sigframe_size(); - - if (ia32_frame && use_fxsr()) { - buf_fx = buf + sizeof(struct i387_fsave_struct); - size += sizeof(struct i387_fsave_struct); - } - - return __restore_xstate_sig(buf, buf_fx, size); -} - -/* - * Needs to be preemption-safe. - * - * NOTE! user_fpu_begin() must be used only immediately before restoring - * the save state. It does not do any saving/restoring on its own. In - * lazy FPU mode, it is just an optimization to avoid a #NM exception, - * the task can lose the FPU right after preempt_enable(). - */ -static inline void user_fpu_begin(void) -{ - preempt_disable(); - if (!user_has_fpu()) - __thread_fpu_begin(current); - preempt_enable(); -} - -static inline void __save_fpu(struct task_struct *tsk) -{ - if (use_xsave()) { - if (unlikely(system_state == SYSTEM_BOOTING)) - xsave_state_booting(&tsk->thread.fpu.state->xsave, -1); - else - xsave_state(&tsk->thread.fpu.state->xsave, -1); - } else - fpu_fxsave(&tsk->thread.fpu); -} - -/* - * i387 state interaction - */ -static inline unsigned short get_fpu_cwd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.cwd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.cwd; - } -} - -static inline unsigned short get_fpu_swd(struct task_struct *tsk) -{ - if (cpu_has_fxsr) { - return tsk->thread.fpu.state->fxsave.swd; - } else { - return (unsigned short)tsk->thread.fpu.state->fsave.swd; - } -} - -static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) -{ - if (cpu_has_xmm) { - return tsk->thread.fpu.state->fxsave.mxcsr; - } else { - return MXCSR_DEFAULT; - } -} - -static bool fpu_allocated(struct fpu *fpu) -{ - return fpu->state != NULL; -} - -static inline int fpu_alloc(struct fpu *fpu) -{ - if (fpu_allocated(fpu)) - return 0; - fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); - if (!fpu->state) - return -ENOMEM; - WARN_ON((unsigned long)fpu->state & 15); - return 0; -} - -static inline void fpu_free(struct fpu *fpu) -{ - if (fpu->state) { - kmem_cache_free(task_xstate_cachep, fpu->state); - fpu->state = NULL; - } -} - -static inline void fpu_copy(struct task_struct *dst, struct task_struct *src) -{ - if (use_eager_fpu()) { - memset(&dst->thread.fpu.state->xsave, 0, xstate_size); - __save_fpu(dst); - } else { - struct fpu *dfpu = &dst->thread.fpu; - struct fpu *sfpu = &src->thread.fpu; - - unlazy_fpu(src); - memcpy(dfpu->state, sfpu->state, xstate_size); - } -} - -static inline unsigned long -alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx, - unsigned long *size) -{ - unsigned long frame_size = xstate_sigframe_size(); - - *buf_fx = sp = round_down(sp - frame_size, 64); - if (ia32_frame && use_fxsr()) { - frame_size += sizeof(struct i387_fsave_struct); - sp -= sizeof(struct i387_fsave_struct); - } - - *size = frame_size; - return sp; -} - -#endif diff --git a/kernel/arch/x86/include/asm/fpu/api.h b/kernel/arch/x86/include/asm/fpu/api.h new file mode 100644 index 000000000..1429a7c73 --- /dev/null +++ b/kernel/arch/x86/include/asm/fpu/api.h @@ -0,0 +1,48 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_API_H +#define _ASM_X86_FPU_API_H + +/* + * Careful: __kernel_fpu_begin/end() must be called with preempt disabled + * and they don't touch the preempt state on their own. + * If you enable preemption after __kernel_fpu_begin(), preempt notifier + * should call the __kernel_fpu_end() to prevent the kernel/user FPU + * state from getting corrupted. KVM for example uses this model. + * + * All other cases use kernel_fpu_begin/end() which disable preemption + * during kernel FPU usage. + */ +extern void __kernel_fpu_begin(void); +extern void __kernel_fpu_end(void); +extern void kernel_fpu_begin(void); +extern void kernel_fpu_end(void); +extern bool irq_fpu_usable(void); + +/* + * Some instructions like VIA's padlock instructions generate a spurious + * DNA fault but don't modify SSE registers. And these instructions + * get used from interrupt context as well. To prevent these kernel instructions + * in interrupt context interacting wrongly with other user/kernel fpu usage, we + * should use them only in the context of irq_ts_save/restore() + */ +extern int irq_ts_save(void); +extern void irq_ts_restore(int TS_state); + +/* + * Query the presence of one or more xfeatures. Works on any legacy CPU as well. + * + * If 'feature_name' is set then put a human-readable description of + * the feature there as well - this can be used to print error (or success) + * messages. + */ +extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); + +#endif /* _ASM_X86_FPU_API_H */ diff --git a/kernel/arch/x86/include/asm/fpu/internal.h b/kernel/arch/x86/include/asm/fpu/internal.h new file mode 100644 index 000000000..3c3550c3a --- /dev/null +++ b/kernel/arch/x86/include/asm/fpu/internal.h @@ -0,0 +1,694 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_INTERNAL_H +#define _ASM_X86_FPU_INTERNAL_H + +#include <linux/compat.h> +#include <linux/sched.h> +#include <linux/slab.h> + +#include <asm/user.h> +#include <asm/fpu/api.h> +#include <asm/fpu/xstate.h> + +/* + * High level FPU state handling functions: + */ +extern void fpu__activate_curr(struct fpu *fpu); +extern void fpu__activate_fpstate_read(struct fpu *fpu); +extern void fpu__activate_fpstate_write(struct fpu *fpu); +extern void fpu__save(struct fpu *fpu); +extern void fpu__restore(struct fpu *fpu); +extern int fpu__restore_sig(void __user *buf, int ia32_frame); +extern void fpu__drop(struct fpu *fpu); +extern int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu); +extern void fpu__clear(struct fpu *fpu); +extern int fpu__exception_code(struct fpu *fpu, int trap_nr); +extern int dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate); + +/* + * Boot time FPU initialization functions: + */ +extern void fpu__init_cpu(void); +extern void fpu__init_system_xstate(void); +extern void fpu__init_cpu_xstate(void); +extern void fpu__init_system(struct cpuinfo_x86 *c); +extern void fpu__init_check_bugs(void); +extern void fpu__resume_cpu(void); + +/* + * Debugging facility: + */ +#ifdef CONFIG_X86_DEBUG_FPU +# define WARN_ON_FPU(x) WARN_ON_ONCE(x) +#else +# define WARN_ON_FPU(x) ({ (void)(x); 0; }) +#endif + +/* + * FPU related CPU feature flag helper routines: + */ +static __always_inline __pure bool use_eager_fpu(void) +{ + return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); +} + +static __always_inline __pure bool use_xsaveopt(void) +{ + return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); +} + +static __always_inline __pure bool use_xsave(void) +{ + return static_cpu_has_safe(X86_FEATURE_XSAVE); +} + +static __always_inline __pure bool use_fxsr(void) +{ + return static_cpu_has_safe(X86_FEATURE_FXSR); +} + +/* + * fpstate handling functions: + */ + +extern union fpregs_state init_fpstate; + +extern void fpstate_init(union fpregs_state *state); +#ifdef CONFIG_MATH_EMULATION +extern void fpstate_init_soft(struct swregs_state *soft); +#else +static inline void fpstate_init_soft(struct swregs_state *soft) {} +#endif +static inline void fpstate_init_fxstate(struct fxregs_state *fx) +{ + fx->cwd = 0x37f; + fx->mxcsr = MXCSR_DEFAULT; +} +extern void fpstate_sanitize_xstate(struct fpu *fpu); + +#define user_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile(ASM_STAC "\n" \ + "1:" #insn "\n\t" \ + "2: " ASM_CLAC "\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +#define check_insn(insn, output, input...) \ +({ \ + int err; \ + asm volatile("1:" #insn "\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err), output \ + : "0"(0), input); \ + err; \ +}) + +static inline int copy_fregs_to_user(struct fregs_state __user *fx) +{ + return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx)); +} + +static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); + + /* See comment in copy_fxregs_to_kernel() below. */ + return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); +} + +static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) +{ + int err; + + if (config_enabled(CONFIG_X86_32)) { + err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + } else { + if (config_enabled(CONFIG_AS_FXSAVEQ)) { + err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + } else { + /* See comment in copy_fxregs_to_kernel() below. */ + err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); + } + } + /* Copying from a kernel buffer to FPU registers should never fail: */ + WARN_ON_FPU(err); +} + +static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) +{ + if (config_enabled(CONFIG_X86_32)) + return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); + + /* See comment in copy_fxregs_to_kernel() below. */ + return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), + "m" (*fx)); +} + +static inline void copy_kernel_to_fregs(struct fregs_state *fx) +{ + int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); + + WARN_ON_FPU(err); +} + +static inline int copy_user_to_fregs(struct fregs_state __user *fx) +{ + return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx)); +} + +static inline void copy_fxregs_to_kernel(struct fpu *fpu) +{ + if (config_enabled(CONFIG_X86_32)) + asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); + else if (config_enabled(CONFIG_AS_FXSAVEQ)) + asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); + else { + /* Using "rex64; fxsave %0" is broken because, if the memory + * operand uses any extended registers for addressing, a second + * REX prefix will be generated (to the assembler, rex64 + * followed by semicolon is a separate instruction), and hence + * the 64-bitness is lost. + * + * Using "fxsaveq %0" would be the ideal choice, but is only + * supported starting with gas 2.16. + * + * Using, as a workaround, the properly prefixed form below + * isn't accepted by any binutils version so far released, + * complaining that the same type of prefix is used twice if + * an extended register is needed for addressing (fix submitted + * to mainline 2005-11-21). + * + * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave)); + * + * This, however, we can work around by forcing the compiler to + * select an addressing mode that doesn't require extended + * registers. + */ + asm volatile( "rex64/fxsave (%[fx])" + : "=m" (fpu->state.fxsave) + : [fx] "R" (&fpu->state.fxsave)); + } +} + +/* These macros all use (%edi)/(%rdi) as the single memory argument. */ +#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" +#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" +#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" +#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" + +/* xstate instruction fault handler: */ +#define xstate_fault(__err) \ + \ + ".section .fixup,\"ax\"\n" \ + \ + "3: movl $-2,%[_err]\n" \ + " jmp 2b\n" \ + \ + ".previous\n" \ + \ + _ASM_EXTABLE(1b, 3b) \ + : [_err] "=r" (__err) + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XSAVES"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + else + asm volatile("1:"XSAVE"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XRSTORS"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + else + asm volatile("1:"XRSTOR"\n\t" + "2:\n\t" + xstate_fault(err) + : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); + + /* We should never fault when copying from a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Save processor xstate to xsave area. + */ +static inline void copy_xregs_to_kernel(struct xregs_state *xstate) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(!alternatives_patched); + + /* + * If xsaves is enabled, xsaves replaces xsaveopt because + * it supports compact format and supervisor states in addition to + * modified optimization in xsaveopt. + * + * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave + * because xsaveopt supports modified optimization which is not + * supported by xsave. + * + * If none of xsaves and xsaveopt is enabled, use xsave. + */ + alternative_input_2( + "1:"XSAVE, + XSAVEOPT, + X86_FEATURE_XSAVEOPT, + XSAVES, + X86_FEATURE_XSAVES, + [xstate] "D" (xstate), "a" (lmask), "d" (hmask) : + "memory"); + asm volatile("2:\n\t" + xstate_fault(err) + : "0" (err) + : "memory"); + + /* We should never fault when copying to a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Restore processor xstate from xsave area. + */ +static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + /* + * Use xrstors to restore context if it is enabled. xrstors supports + * compacted format of xsave area which is not supported by xrstor. + */ + alternative_input( + "1: " XRSTOR, + XRSTORS, + X86_FEATURE_XSAVES, + "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile("2:\n" + xstate_fault(err) + : "0" (err) + : "memory"); + + /* We should never fault when copying from a kernel buffer: */ + WARN_ON_FPU(err); +} + +/* + * Save xstate to user space xsave area. + * + * We don't use modified optimization because xrstor/xrstors might track + * a different application. + * + * We don't use compacted format xsave area for + * backward compatibility for old applications which don't understand + * compacted format of xsave area. + */ +static inline int copy_xregs_to_user(struct xregs_state __user *buf) +{ + int err; + + /* + * Clear the xsave header first, so that reserved fields are + * initialized to zero. + */ + err = __clear_user(&buf->header, sizeof(buf->header)); + if (unlikely(err)) + return -EFAULT; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XSAVE"\n" + "2: " ASM_CLAC "\n" + xstate_fault(err) + : "D" (buf), "a" (-1), "d" (-1), "0" (err) + : "memory"); + return err; +} + +/* + * Restore xstate from user space xsave area. + */ +static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) +{ + struct xregs_state *xstate = ((__force struct xregs_state *)buf); + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XRSTOR"\n" + "2: " ASM_CLAC "\n" + xstate_fault(err) + : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err) + : "memory"); /* memory required? */ + return err; +} + +/* + * These must be called with preempt disabled. Returns + * 'true' if the FPU state is still intact and we can + * keep registers active. + * + * The legacy FNSAVE instruction cleared all FPU state + * unconditionally, so registers are essentially destroyed. + * Modern FPU state can be kept in registers, if there are + * no pending FP exceptions. + */ +static inline int copy_fpregs_to_fpstate(struct fpu *fpu) +{ + if (likely(use_xsave())) { + copy_xregs_to_kernel(&fpu->state.xsave); + return 1; + } + + if (likely(use_fxsr())) { + copy_fxregs_to_kernel(fpu); + return 1; + } + + /* + * Legacy FPU register saving, FNSAVE always clears FPU registers, + * so we have to mark them inactive: + */ + asm volatile("fnsave %[fp]; fwait" : [fp] "=m" (fpu->state.fsave)); + + return 0; +} + +static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate) +{ + if (use_xsave()) { + copy_kernel_to_xregs(&fpstate->xsave, -1); + } else { + if (use_fxsr()) + copy_kernel_to_fxregs(&fpstate->fxsave); + else + copy_kernel_to_fregs(&fpstate->fsave); + } +} + +static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) +{ + /* + * AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is + * pending. Clear the x87 state here by setting it to fixed values. + * "m" is a random variable that should be in L1. + */ + if (unlikely(static_cpu_has_bug_safe(X86_BUG_FXSAVE_LEAK))) { + asm volatile( + "fnclex\n\t" + "emms\n\t" + "fildl %P[addr]" /* set F?P to defined value */ + : : [addr] "m" (fpstate)); + } + + __copy_kernel_to_fpregs(fpstate); +} + +extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); + +/* + * FPU context switch related helper methods: + */ + +DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +/* + * Must be run with preemption disabled: this clears the fpu_fpregs_owner_ctx, + * on this CPU. + * + * This will disable any lazy FPU state restore of the current FPU state, + * but if the current thread owns the FPU, it will still be saved by. + */ +static inline void __cpu_disable_lazy_restore(unsigned int cpu) +{ + per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL; +} + +static inline int fpu_want_lazy_restore(struct fpu *fpu, unsigned int cpu) +{ + return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; +} + + +/* + * Wrap lazy FPU TS handling in a 'hw fpregs activation/deactivation' + * idiom, which is then paired with the sw-flag (fpregs_active) later on: + */ + +static inline void __fpregs_activate_hw(void) +{ + if (!use_eager_fpu()) + clts(); +} + +static inline void __fpregs_deactivate_hw(void) +{ + if (!use_eager_fpu()) + stts(); +} + +/* Must be paired with an 'stts' (fpregs_deactivate_hw()) after! */ +static inline void __fpregs_deactivate(struct fpu *fpu) +{ + WARN_ON_FPU(!fpu->fpregs_active); + + fpu->fpregs_active = 0; + this_cpu_write(fpu_fpregs_owner_ctx, NULL); +} + +/* Must be paired with a 'clts' (fpregs_activate_hw()) before! */ +static inline void __fpregs_activate(struct fpu *fpu) +{ + WARN_ON_FPU(fpu->fpregs_active); + + fpu->fpregs_active = 1; + this_cpu_write(fpu_fpregs_owner_ctx, fpu); +} + +/* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + */ +static inline int fpregs_active(void) +{ + return current->thread.fpu.fpregs_active; +} + +/* + * Encapsulate the CR0.TS handling together with the + * software flag. + * + * These generally need preemption protection to work, + * do try to avoid using these on their own. + */ +static inline void fpregs_activate(struct fpu *fpu) +{ + __fpregs_activate_hw(); + __fpregs_activate(fpu); +} + +static inline void fpregs_deactivate(struct fpu *fpu) +{ + __fpregs_deactivate(fpu); + __fpregs_deactivate_hw(); +} + +/* + * FPU state switching for scheduling. + * + * This is a two-stage process: + * + * - switch_fpu_prepare() saves the old state and + * sets the new state of the CR0.TS bit. This is + * done within the context of the old process. + * + * - switch_fpu_finish() restores the new state as + * necessary. + */ +typedef struct { int preload; } fpu_switch_t; + +static inline fpu_switch_t +switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu) +{ + fpu_switch_t fpu; + + /* + * If the task has used the math, pre-load the FPU on xsave processors + * or if the past 5 consecutive context-switches used math. + */ + fpu.preload = new_fpu->fpstate_active && + (use_eager_fpu() || new_fpu->counter > 5); + + if (old_fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(old_fpu)) + old_fpu->last_cpu = -1; + else + old_fpu->last_cpu = cpu; + + /* But leave fpu_fpregs_owner_ctx! */ + old_fpu->fpregs_active = 0; + + /* Don't change CR0.TS if we just switch! */ + if (fpu.preload) { + new_fpu->counter++; + __fpregs_activate(new_fpu); + prefetch(&new_fpu->state); + } else { + __fpregs_deactivate_hw(); + } + } else { + old_fpu->counter = 0; + old_fpu->last_cpu = -1; + if (fpu.preload) { + new_fpu->counter++; + if (fpu_want_lazy_restore(new_fpu, cpu)) + fpu.preload = 0; + else + prefetch(&new_fpu->state); + fpregs_activate(new_fpu); + } + } + return fpu; +} + +/* + * Misc helper functions: + */ + +/* + * By the time this gets called, we've already cleared CR0.TS and + * given the process the FPU if we are going to preload the FPU + * state - all we need to do is to conditionally restore the register + * state itself. + */ +static inline void switch_fpu_finish(struct fpu *new_fpu, fpu_switch_t fpu_switch) +{ + if (fpu_switch.preload) + copy_kernel_to_fpregs(&new_fpu->state); +} + +/* + * Needs to be preemption-safe. + * + * NOTE! user_fpu_begin() must be used only immediately before restoring + * the save state. It does not do any saving/restoring on its own. In + * lazy FPU mode, it is just an optimization to avoid a #NM exception, + * the task can lose the FPU right after preempt_enable(). + */ +static inline void user_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + preempt_disable(); + if (!fpregs_active()) + fpregs_activate(fpu); + preempt_enable(); +} + +/* + * MXCSR and XCR definitions: + */ + +extern unsigned int mxcsr_feature_mask; + +#define XCR_XFEATURE_ENABLED_MASK 0x00000000 + +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ + : "=a" (eax), "=d" (edx) + : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ + : : "a" (eax), "d" (edx), "c" (index)); +} + +#endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/kernel/arch/x86/include/asm/fpu/regset.h b/kernel/arch/x86/include/asm/fpu/regset.h new file mode 100644 index 000000000..39d3107ac --- /dev/null +++ b/kernel/arch/x86/include/asm/fpu/regset.h @@ -0,0 +1,21 @@ +/* + * FPU regset handling methods: + */ +#ifndef _ASM_X86_FPU_REGSET_H +#define _ASM_X86_FPU_REGSET_H + +#include <linux/regset.h> + +extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active; +extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get; +extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, + xstateregs_set; + +/* + * xstateregs_active == regset_fpregs_active. Please refer to the comment + * at the definition of regset_fpregs_active. + */ +#define xstateregs_active regset_fpregs_active + +#endif /* _ASM_X86_FPU_REGSET_H */ diff --git a/kernel/arch/x86/include/asm/fpu/signal.h b/kernel/arch/x86/include/asm/fpu/signal.h new file mode 100644 index 000000000..0e970d00d --- /dev/null +++ b/kernel/arch/x86/include/asm/fpu/signal.h @@ -0,0 +1,33 @@ +/* + * x86 FPU signal frame handling methods: + */ +#ifndef _ASM_X86_FPU_SIGNAL_H +#define _ASM_X86_FPU_SIGNAL_H + +#ifdef CONFIG_X86_64 +# include <uapi/asm/sigcontext.h> +# include <asm/user32.h> +struct ksignal; +int ia32_setup_rt_frame(int sig, struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs); +int ia32_setup_frame(int sig, struct ksignal *ksig, + compat_sigset_t *set, struct pt_regs *regs); +#else +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct +# define ia32_setup_frame __setup_frame +# define ia32_setup_rt_frame __setup_rt_frame +#endif + +extern void convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk); +extern void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env); + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size); + +extern void fpu__init_prepare_fx_sw_frame(void); + +#endif /* _ASM_X86_FPU_SIGNAL_H */ diff --git a/kernel/arch/x86/include/asm/fpu/types.h b/kernel/arch/x86/include/asm/fpu/types.h new file mode 100644 index 000000000..1c6f6ac52 --- /dev/null +++ b/kernel/arch/x86/include/asm/fpu/types.h @@ -0,0 +1,355 @@ +/* + * FPU data structures: + */ +#ifndef _ASM_X86_FPU_H +#define _ASM_X86_FPU_H + +/* + * The legacy x87 FPU state format, as saved by FSAVE and + * restored by the FRSTOR instructions: + */ +struct fregs_state { + u32 cwd; /* FPU Control Word */ + u32 swd; /* FPU Status Word */ + u32 twd; /* FPU Tag Word */ + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Pointer Offset */ + u32 fos; /* FPU Operand Pointer Selector */ + + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + + /* Software status information [not touched by FSAVE]: */ + u32 status; +}; + +/* + * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and + * restored by the FXRSTOR instructions. It's similar to the FSAVE + * format, but differs in some areas, plus has extensions at + * the end for the XMM registers. + */ +struct fxregs_state { + u16 cwd; /* Control Word */ + u16 swd; /* Status Word */ + u16 twd; /* Tag Word */ + u16 fop; /* Last Instruction Opcode */ + union { + struct { + u64 rip; /* Instruction Pointer */ + u64 rdp; /* Data Pointer */ + }; + struct { + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Offset */ + u32 fos; /* FPU Operand Selector */ + }; + }; + u32 mxcsr; /* MXCSR Register State */ + u32 mxcsr_mask; /* MXCSR Mask */ + + /* 8*16 bytes for each FP-reg = 128 bytes: */ + u32 st_space[32]; + + /* 16*16 bytes for each XMM-reg = 256 bytes: */ + u32 xmm_space[64]; + + u32 padding[12]; + + union { + u32 padding1[12]; + u32 sw_reserved[12]; + }; + +} __attribute__((aligned(16))); + +/* Default value for fxregs_state.mxcsr: */ +#define MXCSR_DEFAULT 0x1f80 + +/* + * Software based FPU emulation state. This is arbitrary really, + * it matches the x87 format to make it easier to understand: + */ +struct swregs_state { + u32 cwd; + u32 swd; + u32 twd; + u32 fip; + u32 fcs; + u32 foo; + u32 fos; + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + u8 ftop; + u8 changed; + u8 lookahead; + u8 no_update; + u8 rm; + u8 alimit; + struct math_emu_info *info; + u32 entry_eip; +}; + +/* + * List of XSAVE features Linux knows about: + */ +enum xfeature { + XFEATURE_FP, + XFEATURE_SSE, + /* + * Values above here are "legacy states". + * Those below are "extended states". + */ + XFEATURE_YMM, + XFEATURE_BNDREGS, + XFEATURE_BNDCSR, + XFEATURE_OPMASK, + XFEATURE_ZMM_Hi256, + XFEATURE_Hi16_ZMM, + + XFEATURE_MAX, +}; + +#define XFEATURE_MASK_FP (1 << XFEATURE_FP) +#define XFEATURE_MASK_SSE (1 << XFEATURE_SSE) +#define XFEATURE_MASK_YMM (1 << XFEATURE_YMM) +#define XFEATURE_MASK_BNDREGS (1 << XFEATURE_BNDREGS) +#define XFEATURE_MASK_BNDCSR (1 << XFEATURE_BNDCSR) +#define XFEATURE_MASK_OPMASK (1 << XFEATURE_OPMASK) +#define XFEATURE_MASK_ZMM_Hi256 (1 << XFEATURE_ZMM_Hi256) +#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM) + +#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) +#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \ + | XFEATURE_MASK_ZMM_Hi256 \ + | XFEATURE_MASK_Hi16_ZMM) + +#define FIRST_EXTENDED_XFEATURE XFEATURE_YMM + +struct reg_128_bit { + u8 regbytes[128/8]; +}; +struct reg_256_bit { + u8 regbytes[256/8]; +}; +struct reg_512_bit { + u8 regbytes[512/8]; +}; + +/* + * State component 2: + * + * There are 16x 256-bit AVX registers named YMM0-YMM15. + * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15) + * and are stored in 'struct fxregs_state::xmm_space[]' in the + * "legacy" area. + * + * The high 128 bits are stored here. + */ +struct ymmh_struct { + struct reg_128_bit hi_ymm[16]; +} __packed; + +/* Intel MPX support: */ + +struct mpx_bndreg { + u64 lower_bound; + u64 upper_bound; +} __packed; +/* + * State component 3 is used for the 4 128-bit bounds registers + */ +struct mpx_bndreg_state { + struct mpx_bndreg bndreg[4]; +} __packed; + +/* + * State component 4 is used for the 64-bit user-mode MPX + * configuration register BNDCFGU and the 64-bit MPX status + * register BNDSTATUS. We call the pair "BNDCSR". + */ +struct mpx_bndcsr { + u64 bndcfgu; + u64 bndstatus; +} __packed; + +/* + * The BNDCSR state is padded out to be 64-bytes in size. + */ +struct mpx_bndcsr_state { + union { + struct mpx_bndcsr bndcsr; + u8 pad_to_64_bytes[64]; + }; +} __packed; + +/* AVX-512 Components: */ + +/* + * State component 5 is used for the 8 64-bit opmask registers + * k0-k7 (opmask state). + */ +struct avx_512_opmask_state { + u64 opmask_reg[8]; +} __packed; + +/* + * State component 6 is used for the upper 256 bits of the + * registers ZMM0-ZMM15. These 16 256-bit values are denoted + * ZMM0_H-ZMM15_H (ZMM_Hi256 state). + */ +struct avx_512_zmm_uppers_state { + struct reg_256_bit zmm_upper[16]; +} __packed; + +/* + * State component 7 is used for the 16 512-bit registers + * ZMM16-ZMM31 (Hi16_ZMM state). + */ +struct avx_512_hi16_state { + struct reg_512_bit hi16_zmm[16]; +} __packed; + +struct xstate_header { + u64 xfeatures; + u64 xcomp_bv; + u64 reserved[6]; +} __attribute__((packed)); + +/* + * This is our most modern FPU state format, as saved by the XSAVE + * and restored by the XRSTOR instructions. + * + * It consists of a legacy fxregs portion, an xstate header and + * subsequent areas as defined by the xstate header. Not all CPUs + * support all the extensions, so the size of the extended area + * can vary quite a bit between CPUs. + */ +struct xregs_state { + struct fxregs_state i387; + struct xstate_header header; + u8 extended_state_area[0]; +} __attribute__ ((packed, aligned (64))); + +/* + * This is a union of all the possible FPU state formats + * put together, so that we can pick the right one runtime. + * + * The size of the structure is determined by the largest + * member - which is the xsave area. The padding is there + * to ensure that statically-allocated task_structs (just + * the init_task today) have enough space. + */ +union fpregs_state { + struct fregs_state fsave; + struct fxregs_state fxsave; + struct swregs_state soft; + struct xregs_state xsave; + u8 __padding[PAGE_SIZE]; +}; + +/* + * Highest level per task FPU state data structure that + * contains the FPU register state plus various FPU + * state fields: + */ +struct fpu { + /* + * @last_cpu: + * + * Records the last CPU on which this context was loaded into + * FPU registers. (In the lazy-restore case we might be + * able to reuse FPU registers across multiple context switches + * this way, if no intermediate task used the FPU.) + * + * A value of -1 is used to indicate that the FPU state in context + * memory is newer than the FPU state in registers, and that the + * FPU state should be reloaded next time the task is run. + */ + unsigned int last_cpu; + + /* + * @fpstate_active: + * + * This flag indicates whether this context is active: if the task + * is not running then we can restore from this context, if the task + * is running then we should save into this context. + */ + unsigned char fpstate_active; + + /* + * @fpregs_active: + * + * This flag determines whether a given context is actively + * loaded into the FPU's registers and that those registers + * represent the task's current FPU state. + * + * Note the interaction with fpstate_active: + * + * # task does not use the FPU: + * fpstate_active == 0 + * + * # task uses the FPU and regs are active: + * fpstate_active == 1 && fpregs_active == 1 + * + * # the regs are inactive but still match fpstate: + * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu + * + * The third state is what we use for the lazy restore optimization + * on lazy-switching CPUs. + */ + unsigned char fpregs_active; + + /* + * @counter: + * + * This counter contains the number of consecutive context switches + * during which the FPU stays used. If this is over a threshold, the + * lazy FPU restore logic becomes eager, to save the trap overhead. + * This is an unsigned char so that after 256 iterations the counter + * wraps and the context switch behavior turns lazy again; this is to + * deal with bursty apps that only use the FPU for a short time: + */ + unsigned char counter; + /* + * @state: + * + * In-memory copy of all FPU registers that we save/restore + * over context switches. If the task is using the FPU then + * the registers in the FPU are more recent than this state + * copy. If the task context-switches away then they get + * saved here and represent the FPU state. + * + * After context switches there may be a (short) time period + * during which the in-FPU hardware registers are unchanged + * and still perfectly match this state, if the tasks + * scheduled afterwards are not using the FPU. + * + * This is the 'lazy restore' window of optimization, which + * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'. + * + * We detect whether a subsequent task uses the FPU via setting + * CR0::TS to 1, which causes any FPU use to raise a #NM fault. + * + * During this window, if the task gets scheduled again, we + * might be able to skip having to do a restore from this + * memory buffer to the hardware registers - at the cost of + * incurring the overhead of #NM fault traps. + * + * Note that on modern CPUs that support the XSAVEOPT (or other + * optimized XSAVE instructions), we don't use #NM traps anymore, + * as the hardware can track whether FPU registers need saving + * or not. On such CPUs we activate the non-lazy ('eagerfpu') + * logic, which unconditionally saves/restores all FPU state + * across context switches. (if FPU state exists.) + */ + union fpregs_state state; + /* + * WARNING: 'state' is dynamically-sized. Do not put + * anything after it here. + */ +}; + +#endif /* _ASM_X86_FPU_H */ diff --git a/kernel/arch/x86/include/asm/fpu/xstate.h b/kernel/arch/x86/include/asm/fpu/xstate.h new file mode 100644 index 000000000..3a6c89b70 --- /dev/null +++ b/kernel/arch/x86/include/asm/fpu/xstate.h @@ -0,0 +1,51 @@ +#ifndef __ASM_X86_XSAVE_H +#define __ASM_X86_XSAVE_H + +#include <linux/types.h> +#include <asm/processor.h> +#include <linux/uaccess.h> + +/* Bit 63 of XCR0 is reserved for future expansion */ +#define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) + +#define XSTATE_CPUID 0x0000000d + +#define FXSAVE_SIZE 512 + +#define XSAVE_HDR_SIZE 64 +#define XSAVE_HDR_OFFSET FXSAVE_SIZE + +#define XSAVE_YMM_SIZE 256 +#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) + +/* Supported features which support lazy state saving */ +#define XFEATURE_MASK_LAZY (XFEATURE_MASK_FP | \ + XFEATURE_MASK_SSE | \ + XFEATURE_MASK_YMM | \ + XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM) + +/* Supported features which require eager state saving */ +#define XFEATURE_MASK_EAGER (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR) + +/* All currently supported features */ +#define XCNTXT_MASK (XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER) + +#ifdef CONFIG_X86_64 +#define REX_PREFIX "0x48, " +#else +#define REX_PREFIX +#endif + +extern unsigned int xstate_size; +extern u64 xfeatures_mask; +extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; + +extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); + +void fpu__xstate_clear_all_cpu_caps(void); +void *get_xsave_addr(struct xregs_state *xsave, int xstate); +const void *get_xsave_field_ptr(int xstate_field); + +#endif diff --git a/kernel/arch/x86/include/asm/frame.h b/kernel/arch/x86/include/asm/frame.h index 3b629f47e..793179cf8 100644 --- a/kernel/arch/x86/include/asm/frame.h +++ b/kernel/arch/x86/include/asm/frame.h @@ -1,20 +1,17 @@ #ifdef __ASSEMBLY__ #include <asm/asm.h> -#include <asm/dwarf2.h> /* The annotation hides the frame from the unwinder and makes it look like a ordinary ebp save/restore. This avoids some special cases for frame pointer later */ #ifdef CONFIG_FRAME_POINTER .macro FRAME - __ASM_SIZE(push,_cfi) %__ASM_REG(bp) - CFI_REL_OFFSET __ASM_REG(bp), 0 + __ASM_SIZE(push,) %__ASM_REG(bp) __ASM_SIZE(mov) %__ASM_REG(sp), %__ASM_REG(bp) .endm .macro ENDFRAME - __ASM_SIZE(pop,_cfi) %__ASM_REG(bp) - CFI_RESTORE __ASM_REG(bp) + __ASM_SIZE(pop,) %__ASM_REG(bp) .endm #else .macro FRAME diff --git a/kernel/arch/x86/include/asm/ftrace.h b/kernel/arch/x86/include/asm/ftrace.h index f45acad3c..24938852d 100644 --- a/kernel/arch/x86/include/asm/ftrace.h +++ b/kernel/arch/x86/include/asm/ftrace.h @@ -3,9 +3,9 @@ #ifdef CONFIG_FUNCTION_TRACER #ifdef CC_USING_FENTRY -# define MCOUNT_ADDR ((long)(__fentry__)) +# define MCOUNT_ADDR ((unsigned long)(__fentry__)) #else -# define MCOUNT_ADDR ((long)(mcount)) +# define MCOUNT_ADDR ((unsigned long)(mcount)) #endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ diff --git a/kernel/arch/x86/include/asm/hardirq.h b/kernel/arch/x86/include/asm/hardirq.h index 0f5fb6b65..7178043b0 100644 --- a/kernel/arch/x86/include/asm/hardirq.h +++ b/kernel/arch/x86/include/asm/hardirq.h @@ -14,6 +14,7 @@ typedef struct { #endif #ifdef CONFIG_HAVE_KVM unsigned int kvm_posted_intr_ipis; + unsigned int kvm_posted_intr_wakeup_ipis; #endif unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; @@ -33,6 +34,9 @@ typedef struct { #ifdef CONFIG_X86_MCE_THRESHOLD unsigned int irq_threshold_count; #endif +#ifdef CONFIG_X86_MCE_AMD + unsigned int irq_deferred_error_count; +#endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) unsigned int irq_hv_callback_count; #endif diff --git a/kernel/arch/x86/include/asm/highmem.h b/kernel/arch/x86/include/asm/highmem.h index 04e9d0231..1c0b43724 100644 --- a/kernel/arch/x86/include/asm/highmem.h +++ b/kernel/arch/x86/include/asm/highmem.h @@ -68,7 +68,6 @@ void *kmap_atomic(struct page *page); void __kunmap_atomic(void *kvaddr); void *kmap_atomic_pfn(unsigned long pfn); void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot); -struct page *kmap_atomic_to_page(void *ptr); #define flush_cache_kmaps() do { } while (0) diff --git a/kernel/arch/x86/include/asm/hpet.h b/kernel/arch/x86/include/asm/hpet.h index 36f712594..cc285ec4b 100644 --- a/kernel/arch/x86/include/asm/hpet.h +++ b/kernel/arch/x86/include/asm/hpet.h @@ -63,10 +63,10 @@ /* hpet memory map physical address */ extern unsigned long hpet_address; extern unsigned long force_hpet_address; -extern int boot_hpet_disable; +extern bool boot_hpet_disable; extern u8 hpet_blockid; -extern int hpet_force_user; -extern u8 hpet_msi_disable; +extern bool hpet_force_user; +extern bool hpet_msi_disable; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); @@ -74,20 +74,16 @@ extern unsigned int hpet_readl(unsigned int a); extern void force_hpet_resume(void); struct irq_data; +struct hpet_dev; +struct irq_domain; + extern void hpet_msi_unmask(struct irq_data *data); extern void hpet_msi_mask(struct irq_data *data); -struct hpet_dev; extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg); extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg); - -#ifdef CONFIG_PCI_MSI -extern int default_setup_hpet_msi(unsigned int irq, unsigned int id); -#else -static inline int default_setup_hpet_msi(unsigned int irq, unsigned int id) -{ - return -EINVAL; -} -#endif +extern struct irq_domain *hpet_create_irq_domain(int hpet_id); +extern int hpet_assign_irq(struct irq_domain *domain, + struct hpet_dev *dev, int dev_num); #ifdef CONFIG_HPET_EMULATE_RTC diff --git a/kernel/arch/x86/include/asm/hugetlb.h b/kernel/arch/x86/include/asm/hugetlb.h index 68c05398b..f8a29d2c9 100644 --- a/kernel/arch/x86/include/asm/hugetlb.h +++ b/kernel/arch/x86/include/asm/hugetlb.h @@ -26,9 +26,6 @@ static inline int prepare_hugepage_range(struct file *file, return 0; } -static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) { -} - static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, @@ -83,15 +80,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline int arch_prepare_hugepage(struct page *page) -{ - return 0; -} - -static inline void arch_release_hugepage(struct page *page) -{ -} - static inline void arch_clear_hugepage_flags(struct page *page) { } diff --git a/kernel/arch/x86/include/asm/hw_irq.h b/kernel/arch/x86/include/asm/hw_irq.h index e9571ddab..1e3408e88 100644 --- a/kernel/arch/x86/include/asm/hw_irq.h +++ b/kernel/arch/x86/include/asm/hw_irq.h @@ -29,6 +29,7 @@ extern asmlinkage void apic_timer_interrupt(void); extern asmlinkage void x86_platform_ipi(void); extern asmlinkage void kvm_posted_intr_ipi(void); +extern asmlinkage void kvm_posted_intr_wakeup_ipi(void); extern asmlinkage void error_interrupt(void); extern asmlinkage void irq_work_interrupt(void); @@ -36,43 +37,10 @@ extern asmlinkage void spurious_interrupt(void); extern asmlinkage void thermal_interrupt(void); extern asmlinkage void reschedule_interrupt(void); -extern asmlinkage void invalidate_interrupt(void); -extern asmlinkage void invalidate_interrupt0(void); -extern asmlinkage void invalidate_interrupt1(void); -extern asmlinkage void invalidate_interrupt2(void); -extern asmlinkage void invalidate_interrupt3(void); -extern asmlinkage void invalidate_interrupt4(void); -extern asmlinkage void invalidate_interrupt5(void); -extern asmlinkage void invalidate_interrupt6(void); -extern asmlinkage void invalidate_interrupt7(void); -extern asmlinkage void invalidate_interrupt8(void); -extern asmlinkage void invalidate_interrupt9(void); -extern asmlinkage void invalidate_interrupt10(void); -extern asmlinkage void invalidate_interrupt11(void); -extern asmlinkage void invalidate_interrupt12(void); -extern asmlinkage void invalidate_interrupt13(void); -extern asmlinkage void invalidate_interrupt14(void); -extern asmlinkage void invalidate_interrupt15(void); -extern asmlinkage void invalidate_interrupt16(void); -extern asmlinkage void invalidate_interrupt17(void); -extern asmlinkage void invalidate_interrupt18(void); -extern asmlinkage void invalidate_interrupt19(void); -extern asmlinkage void invalidate_interrupt20(void); -extern asmlinkage void invalidate_interrupt21(void); -extern asmlinkage void invalidate_interrupt22(void); -extern asmlinkage void invalidate_interrupt23(void); -extern asmlinkage void invalidate_interrupt24(void); -extern asmlinkage void invalidate_interrupt25(void); -extern asmlinkage void invalidate_interrupt26(void); -extern asmlinkage void invalidate_interrupt27(void); -extern asmlinkage void invalidate_interrupt28(void); -extern asmlinkage void invalidate_interrupt29(void); -extern asmlinkage void invalidate_interrupt30(void); -extern asmlinkage void invalidate_interrupt31(void); - extern asmlinkage void irq_move_cleanup_interrupt(void); extern asmlinkage void reboot_interrupt(void); extern asmlinkage void threshold_interrupt(void); +extern asmlinkage void deferred_error_interrupt(void); extern asmlinkage void call_function_interrupt(void); extern asmlinkage void call_function_single_interrupt(void); @@ -87,60 +55,93 @@ extern void trace_spurious_interrupt(void); extern void trace_thermal_interrupt(void); extern void trace_reschedule_interrupt(void); extern void trace_threshold_interrupt(void); +extern void trace_deferred_error_interrupt(void); extern void trace_call_function_interrupt(void); extern void trace_call_function_single_interrupt(void); #define trace_irq_move_cleanup_interrupt irq_move_cleanup_interrupt #define trace_reboot_interrupt reboot_interrupt #define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi +#define trace_kvm_posted_intr_wakeup_ipi kvm_posted_intr_wakeup_ipi #endif /* CONFIG_TRACING */ -#ifdef CONFIG_IRQ_REMAP -/* Intel specific interrupt remapping information */ -struct irq_2_iommu { - struct intel_iommu *iommu; - u16 irte_index; - u16 sub_handle; - u8 irte_mask; -}; - -/* AMD specific interrupt remapping information */ -struct irq_2_irte { - u16 devid; /* Device ID for IRTE table */ - u16 index; /* Index into IRTE table*/ -}; -#endif /* CONFIG_IRQ_REMAP */ - #ifdef CONFIG_X86_LOCAL_APIC struct irq_data; +struct pci_dev; +struct msi_desc; + +enum irq_alloc_type { + X86_IRQ_ALLOC_TYPE_IOAPIC = 1, + X86_IRQ_ALLOC_TYPE_HPET, + X86_IRQ_ALLOC_TYPE_MSI, + X86_IRQ_ALLOC_TYPE_MSIX, + X86_IRQ_ALLOC_TYPE_DMAR, + X86_IRQ_ALLOC_TYPE_UV, +}; -struct irq_cfg { - cpumask_var_t domain; - cpumask_var_t old_domain; - u8 vector; - u8 move_in_progress : 1; -#ifdef CONFIG_IRQ_REMAP - u8 remapped : 1; +struct irq_alloc_info { + enum irq_alloc_type type; + u32 flags; + const struct cpumask *mask; /* CPU mask for vector allocation */ union { - struct irq_2_iommu irq_2_iommu; - struct irq_2_irte irq_2_irte; - }; + int unused; +#ifdef CONFIG_HPET_TIMER + struct { + int hpet_id; + int hpet_index; + void *hpet_data; + }; #endif - union { -#ifdef CONFIG_X86_IO_APIC +#ifdef CONFIG_PCI_MSI struct { - struct list_head irq_2_pin; + struct pci_dev *msi_dev; + irq_hw_number_t msi_hwirq; + }; +#endif +#ifdef CONFIG_X86_IO_APIC + struct { + int ioapic_id; + int ioapic_pin; + int ioapic_node; + u32 ioapic_trigger : 1; + u32 ioapic_polarity : 1; + u32 ioapic_valid : 1; + struct IO_APIC_route_entry *ioapic_entry; + }; +#endif +#ifdef CONFIG_DMAR_TABLE + struct { + int dmar_id; + void *dmar_data; + }; +#endif +#ifdef CONFIG_HT_IRQ + struct { + int ht_pos; + int ht_idx; + struct pci_dev *ht_dev; + void *ht_update; + }; +#endif +#ifdef CONFIG_X86_UV + struct { + int uv_limit; + int uv_blade; + unsigned long uv_offset; + char *uv_name; }; #endif }; }; +struct irq_cfg { + unsigned int dest_apicid; + u8 vector; +}; + extern struct irq_cfg *irq_cfg(unsigned int irq); extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); -extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node); extern void lock_vector_lock(void); extern void unlock_vector_lock(void); -extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *); -extern void clear_irq_vector(int irq, struct irq_cfg *cfg); extern void setup_vector_irq(int cpu); #ifdef CONFIG_SMP extern void send_cleanup_vector(struct irq_cfg *); @@ -150,10 +151,7 @@ static inline void send_cleanup_vector(struct irq_cfg *c) { } static inline void irq_complete_move(struct irq_cfg *c) { } #endif -extern int apic_retrigger_irq(struct irq_data *data); extern void apic_ack_edge(struct irq_data *data); -extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id); #else /* CONFIG_X86_LOCAL_APIC */ static inline void lock_vector_lock(void) {} static inline void unlock_vector_lock(void) {} @@ -163,8 +161,7 @@ static inline void unlock_vector_lock(void) {} extern atomic_t irq_err_count; extern atomic_t irq_mis_count; -/* EISA */ -extern void eisa_set_level_irq(unsigned int irq); +extern void elcr_set_level_irq(unsigned int irq); /* SMP */ extern __visible void smp_apic_timer_interrupt(struct pt_regs *); @@ -178,7 +175,6 @@ extern asmlinkage void smp_irq_move_cleanup_interrupt(void); extern __visible void smp_reschedule_interrupt(struct pt_regs *); extern __visible void smp_call_function_interrupt(struct pt_regs *); extern __visible void smp_call_function_single_interrupt(struct pt_regs *); -extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif extern char irq_entries_start[]; @@ -186,10 +182,10 @@ extern char irq_entries_start[]; #define trace_irq_entries_start irq_entries_start #endif -#define VECTOR_UNDEFINED (-1) -#define VECTOR_RETRIGGERED (-2) +#define VECTOR_UNUSED NULL +#define VECTOR_RETRIGGERED ((void *)~0UL) -typedef int vector_irq_t[NR_VECTORS]; +typedef struct irq_desc* vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); #endif /* !ASSEMBLY_ */ diff --git a/kernel/arch/x86/include/asm/i387.h b/kernel/arch/x86/include/asm/i387.h deleted file mode 100644 index 6eb6fcb83..000000000 --- a/kernel/arch/x86/include/asm/i387.h +++ /dev/null @@ -1,108 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - * x86-64 work by Andi Kleen 2002 - */ - -#ifndef _ASM_X86_I387_H -#define _ASM_X86_I387_H - -#ifndef __ASSEMBLY__ - -#include <linux/sched.h> -#include <linux/hardirq.h> - -struct pt_regs; -struct user_i387_struct; - -extern int init_fpu(struct task_struct *child); -extern void fpu_finit(struct fpu *fpu); -extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); -extern void math_state_restore(void); - -extern bool irq_fpu_usable(void); - -/* - * Careful: __kernel_fpu_begin/end() must be called with preempt disabled - * and they don't touch the preempt state on their own. - * If you enable preemption after __kernel_fpu_begin(), preempt notifier - * should call the __kernel_fpu_end() to prevent the kernel/user FPU - * state from getting corrupted. KVM for example uses this model. - * - * All other cases use kernel_fpu_begin/end() which disable preemption - * during kernel FPU usage. - */ -extern void __kernel_fpu_begin(void); -extern void __kernel_fpu_end(void); - -static inline void kernel_fpu_begin(void) -{ - preempt_disable(); - WARN_ON_ONCE(!irq_fpu_usable()); - __kernel_fpu_begin(); -} - -static inline void kernel_fpu_end(void) -{ - __kernel_fpu_end(); - preempt_enable(); -} - -/* Must be called with preempt disabled */ -extern void kernel_fpu_disable(void); -extern void kernel_fpu_enable(void); - -/* - * Some instructions like VIA's padlock instructions generate a spurious - * DNA fault but don't modify SSE registers. And these instructions - * get used from interrupt context as well. To prevent these kernel instructions - * in interrupt context interacting wrongly with other user/kernel fpu usage, we - * should use them only in the context of irq_ts_save/restore() - */ -static inline int irq_ts_save(void) -{ - /* - * If in process context and not atomic, we can take a spurious DNA fault. - * Otherwise, doing clts() in process context requires disabling preemption - * or some heavy lifting like kernel_fpu_begin() - */ - if (!in_atomic()) - return 0; - - if (read_cr0() & X86_CR0_TS) { - clts(); - return 1; - } - - return 0; -} - -static inline void irq_ts_restore(int TS_state) -{ - if (TS_state) - stts(); -} - -/* - * The question "does this thread have fpu access?" - * is slightly racy, since preemption could come in - * and revoke it immediately after the test. - * - * However, even in that very unlikely scenario, - * we can just assume we have FPU access - typically - * to save the FP state - we'll just take a #NM - * fault and get the FPU access back. - */ -static inline int user_has_fpu(void) -{ - return current->thread.fpu.has_fpu; -} - -extern void unlazy_fpu(struct task_struct *tsk); - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_I387_H */ diff --git a/kernel/arch/x86/include/asm/i8259.h b/kernel/arch/x86/include/asm/i8259.h index ccffa5375..39bcefc20 100644 --- a/kernel/arch/x86/include/asm/i8259.h +++ b/kernel/arch/x86/include/asm/i8259.h @@ -60,6 +60,7 @@ struct legacy_pic { void (*mask_all)(void); void (*restore_mask)(void); void (*init)(int auto_eoi); + int (*probe)(void); int (*irq_pending)(unsigned int irq); void (*make_irq)(unsigned int irq); }; diff --git a/kernel/arch/x86/include/asm/ia32.h b/kernel/arch/x86/include/asm/ia32.h index d0e8e0141..a9bdf5569 100644 --- a/kernel/arch/x86/include/asm/ia32.h +++ b/kernel/arch/x86/include/asm/ia32.h @@ -10,7 +10,7 @@ * 32 bit structures for IA32 support. */ -#include <asm/sigcontext32.h> +#include <uapi/asm/sigcontext.h> /* signal.h */ @@ -18,16 +18,7 @@ struct ucontext_ia32 { unsigned int uc_flags; unsigned int uc_link; compat_stack_t uc_stack; - struct sigcontext_ia32 uc_mcontext; - compat_sigset_t uc_sigmask; /* mask last for extensibility */ -}; - -struct ucontext_x32 { - unsigned int uc_flags; - unsigned int uc_link; - compat_stack_t uc_stack; - unsigned int uc__pad0; /* needed for alignment */ - struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + struct sigcontext_32 uc_mcontext; compat_sigset_t uc_sigmask; /* mask last for extensibility */ }; diff --git a/kernel/arch/x86/include/asm/intel_pmc_ipc.h b/kernel/arch/x86/include/asm/intel_pmc_ipc.h new file mode 100644 index 000000000..cd0310e18 --- /dev/null +++ b/kernel/arch/x86/include/asm/intel_pmc_ipc.h @@ -0,0 +1,55 @@ +#ifndef _ASM_X86_INTEL_PMC_IPC_H_ +#define _ASM_X86_INTEL_PMC_IPC_H_ + +/* Commands */ +#define PMC_IPC_PMIC_ACCESS 0xFF +#define PMC_IPC_PMIC_ACCESS_READ 0x0 +#define PMC_IPC_PMIC_ACCESS_WRITE 0x1 +#define PMC_IPC_USB_PWR_CTRL 0xF0 +#define PMC_IPC_PMIC_BLACKLIST_SEL 0xEF +#define PMC_IPC_PHY_CONFIG 0xEE +#define PMC_IPC_NORTHPEAK_CTRL 0xED +#define PMC_IPC_PM_DEBUG 0xEC +#define PMC_IPC_PMC_TELEMTRY 0xEB +#define PMC_IPC_PMC_FW_MSG_CTRL 0xEA + +/* IPC return code */ +#define IPC_ERR_NONE 0 +#define IPC_ERR_CMD_NOT_SUPPORTED 1 +#define IPC_ERR_CMD_NOT_SERVICED 2 +#define IPC_ERR_UNABLE_TO_SERVICE 3 +#define IPC_ERR_CMD_INVALID 4 +#define IPC_ERR_CMD_FAILED 5 +#define IPC_ERR_EMSECURITY 6 +#define IPC_ERR_UNSIGNEDKERNEL 7 + +#if IS_ENABLED(CONFIG_INTEL_PMC_IPC) + +int intel_pmc_ipc_simple_command(int cmd, int sub); +int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen, u32 dptr, u32 sptr); +int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen); + +#else + +static inline int intel_pmc_ipc_simple_command(int cmd, int sub) +{ + return -EINVAL; +} + +static inline int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen, u32 dptr, u32 sptr) +{ + return -EINVAL; +} + +static inline int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen, + u32 *out, u32 outlen) +{ + return -EINVAL; +} + +#endif /*CONFIG_INTEL_PMC_IPC*/ + +#endif diff --git a/kernel/arch/x86/include/asm/io.h b/kernel/arch/x86/include/asm/io.h index 34a5b9370..de25aad07 100644 --- a/kernel/arch/x86/include/asm/io.h +++ b/kernel/arch/x86/include/asm/io.h @@ -35,11 +35,13 @@ */ #define ARCH_HAS_IOREMAP_WC +#define ARCH_HAS_IOREMAP_WT #include <linux/string.h> #include <linux/compiler.h> #include <asm/page.h> #include <asm/early_ioremap.h> +#include <asm/pgtable_types.h> #define build_mmio_read(name, size, type, reg, barrier) \ static inline type name(const volatile void __iomem *addr) \ @@ -177,6 +179,9 @@ static inline unsigned int isa_virt_to_bus(volatile void *address) * look at pci_iomap(). */ extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); +#define ioremap_uc ioremap_uc + extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val); @@ -197,8 +202,6 @@ extern void set_iounmap_nonlazy(void); #include <asm-generic/iomap.h> -#include <linux/vmalloc.h> - /* * Convert a virtual cached pointer to an uncached pointer */ @@ -320,6 +323,7 @@ extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, enum page_cache_mode pcm); extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); +extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); extern bool is_early_ioremap_ptep(pte_t *ptep); @@ -338,6 +342,9 @@ extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, #define IO_SPACE_LIMIT 0xffff #ifdef CONFIG_MTRR +extern int __must_check arch_phys_wc_index(int handle); +#define arch_phys_wc_index arch_phys_wc_index + extern int __must_check arch_phys_wc_add(unsigned long base, unsigned long size); extern void arch_phys_wc_del(int handle); diff --git a/kernel/arch/x86/include/asm/io_apic.h b/kernel/arch/x86/include/asm/io_apic.h index 2f91685fe..6cbf2cfb3 100644 --- a/kernel/arch/x86/include/asm/io_apic.h +++ b/kernel/arch/x86/include/asm/io_apic.h @@ -95,9 +95,22 @@ struct IR_IO_APIC_route_entry { index : 15; } __attribute__ ((packed)); -#define IOAPIC_AUTO -1 -#define IOAPIC_EDGE 0 -#define IOAPIC_LEVEL 1 +struct irq_alloc_info; +struct ioapic_domain_cfg; + +#define IOAPIC_AUTO -1 +#define IOAPIC_EDGE 0 +#define IOAPIC_LEVEL 1 + +#define IOAPIC_MASKED 1 +#define IOAPIC_UNMASKED 0 + +#define IOAPIC_POL_HIGH 0 +#define IOAPIC_POL_LOW 1 + +#define IOAPIC_DEST_MODE_PHYSICAL 0 +#define IOAPIC_DEST_MODE_LOGICAL 1 + #define IOAPIC_MAP_ALLOC 0x1 #define IOAPIC_MAP_CHECK 0x2 @@ -110,9 +123,6 @@ extern int nr_ioapics; extern int mpc_ioapic_id(int ioapic); extern unsigned int mpc_ioapic_addr(int ioapic); -extern struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic); - -#define MP_MAX_IOAPIC_PIN 127 /* # of MP IRQ source entries */ extern int mp_irq_entries; @@ -120,9 +130,6 @@ extern int mp_irq_entries; /* MP IRQ source entries */ extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; -/* Older SiS APIC requires we rewrite the index register */ -extern int sis_apic_bug; - /* 1 if "noapic" boot option passed */ extern int skip_ioapic_setup; @@ -132,6 +139,8 @@ extern int noioapicquirk; /* -1 if "noapic" boot option passed */ extern int noioapicreroute; +extern u32 gsi_top; + extern unsigned long io_apic_irqs; #define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs)) @@ -147,13 +156,6 @@ struct irq_cfg; extern void ioapic_insert_resources(void); extern int arch_early_ioapic_init(void); -extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *, - unsigned int, int, - struct io_apic_irq_attr *); -extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg); - -extern void native_eoi_ioapic_pin(int apic, int pin, int vector); - extern int save_ioapic_entries(void); extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); @@ -161,82 +163,32 @@ extern int restore_ioapic_entries(void); extern void setup_ioapic_ids_from_mpc(void); extern void setup_ioapic_ids_from_mpc_nocheck(void); -struct io_apic_irq_attr { - int ioapic; - int ioapic_pin; - int trigger; - int polarity; -}; - -enum ioapic_domain_type { - IOAPIC_DOMAIN_INVALID, - IOAPIC_DOMAIN_LEGACY, - IOAPIC_DOMAIN_STRICT, - IOAPIC_DOMAIN_DYNAMIC, -}; - -struct device_node; -struct irq_domain; -struct irq_domain_ops; - -struct ioapic_domain_cfg { - enum ioapic_domain_type type; - const struct irq_domain_ops *ops; - struct device_node *dev; -}; - -struct mp_ioapic_gsi{ - u32 gsi_base; - u32 gsi_end; -}; -extern u32 gsi_top; - extern int mp_find_ioapic(u32 gsi); extern int mp_find_ioapic_pin(int ioapic, u32 gsi); -extern u32 mp_pin_to_gsi(int ioapic, int pin); -extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags); +extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, + struct irq_alloc_info *info); extern void mp_unmap_irq(int irq); extern int mp_register_ioapic(int id, u32 address, u32 gsi_base, struct ioapic_domain_cfg *cfg); extern int mp_unregister_ioapic(u32 gsi_base); extern int mp_ioapic_registered(u32 gsi_base); -extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq); -extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq); -extern int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node); -extern void __init pre_init_apic_IRQ0(void); + +extern void ioapic_set_alloc_attr(struct irq_alloc_info *info, + int node, int trigger, int polarity); extern void mp_save_irq(struct mpc_intsrc *m); extern void disable_ioapic_support(void); -extern void __init native_io_apic_init_mappings(void); +extern void __init io_apic_init_mappings(void); extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg); -extern void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int val); -extern void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int val); extern void native_disable_io_apic(void); -extern void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries); -extern void intel_ir_io_apic_print_entries(unsigned int apic, unsigned int nr_entries); -extern int native_ioapic_set_affinity(struct irq_data *, - const struct cpumask *, - bool); static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) { return x86_io_apic_ops.read(apic, reg); } -static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) -{ - x86_io_apic_ops.write(apic, reg, value); -} -static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) -{ - x86_io_apic_ops.modify(apic, reg, value); -} - -extern void io_apic_eoi(unsigned int apic, unsigned int vector); - extern void setup_IO_APIC(void); extern void enable_IO_APIC(void); extern void disable_IO_APIC(void); @@ -253,8 +205,12 @@ static inline int arch_early_ioapic_init(void) { return 0; } static inline void print_IO_APICs(void) {} #define gsi_top (NR_IRQS_LEGACY) static inline int mp_find_ioapic(u32 gsi) { return 0; } -static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; } -static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; } +static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, + struct irq_alloc_info *info) +{ + return gsi; +} + static inline void mp_unmap_irq(int irq) { } static inline int save_ioapic_entries(void) @@ -268,17 +224,11 @@ static inline int restore_ioapic_entries(void) return -ENOMEM; } -static inline void mp_save_irq(struct mpc_intsrc *m) { }; +static inline void mp_save_irq(struct mpc_intsrc *m) { } static inline void disable_ioapic_support(void) { } -#define native_io_apic_init_mappings NULL +static inline void io_apic_init_mappings(void) { } #define native_io_apic_read NULL -#define native_io_apic_write NULL -#define native_io_apic_modify NULL #define native_disable_io_apic NULL -#define native_io_apic_print_entries NULL -#define native_ioapic_set_affinity NULL -#define native_setup_ioapic_entry NULL -#define native_eoi_ioapic_pin NULL static inline void setup_IO_APIC(void) { } static inline void enable_IO_APIC(void) { } diff --git a/kernel/arch/x86/include/asm/iosf_mbi.h b/kernel/arch/x86/include/asm/iosf_mbi.h index 57995f059..b72ad0faa 100644 --- a/kernel/arch/x86/include/asm/iosf_mbi.h +++ b/kernel/arch/x86/include/asm/iosf_mbi.h @@ -52,20 +52,20 @@ /* Quark available units */ #define QRK_MBI_UNIT_HBA 0x00 -#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_HB 0x03 #define QRK_MBI_UNIT_RMU 0x04 -#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MM 0x05 #define QRK_MBI_UNIT_MMESRAM 0x05 #define QRK_MBI_UNIT_SOC 0x31 /* Quark read/write opcodes */ #define QRK_MBI_HBA_READ 0x10 #define QRK_MBI_HBA_WRITE 0x11 -#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_READ 0x10 #define QRK_MBI_HB_WRITE 0x11 #define QRK_MBI_RMU_READ 0x10 #define QRK_MBI_RMU_WRITE 0x11 -#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_READ 0x10 #define QRK_MBI_MM_WRITE 0x11 #define QRK_MBI_MMESRAM_READ 0x12 #define QRK_MBI_MMESRAM_WRITE 0x13 diff --git a/kernel/arch/x86/include/asm/irq.h b/kernel/arch/x86/include/asm/irq.h index a80cbb88e..e7de5c9a4 100644 --- a/kernel/arch/x86/include/asm/irq.h +++ b/kernel/arch/x86/include/asm/irq.h @@ -23,16 +23,23 @@ extern void irq_ctx_init(int cpu); #define __ARCH_HAS_DO_SOFTIRQ +struct irq_desc; + #ifdef CONFIG_HOTPLUG_CPU #include <linux/cpumask.h> extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(int); +extern void irq_force_complete_move(struct irq_desc *desc); +#endif + +#ifdef CONFIG_HAVE_KVM +extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); #endif extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); -extern bool handle_irq(unsigned irq, struct pt_regs *regs); + +extern bool handle_irq(struct irq_desc *desc, struct pt_regs *regs); extern __visible unsigned int do_IRQ(struct pt_regs *regs); diff --git a/kernel/arch/x86/include/asm/irq_remapping.h b/kernel/arch/x86/include/asm/irq_remapping.h index 6224d316c..a210eba27 100644 --- a/kernel/arch/x86/include/asm/irq_remapping.h +++ b/kernel/arch/x86/include/asm/irq_remapping.h @@ -22,84 +22,72 @@ #ifndef __X86_IRQ_REMAPPING_H #define __X86_IRQ_REMAPPING_H +#include <asm/irqdomain.h> +#include <asm/hw_irq.h> #include <asm/io_apic.h> -struct IO_APIC_route_entry; -struct io_apic_irq_attr; -struct irq_chip; struct msi_msg; -struct pci_dev; -struct irq_cfg; +struct irq_alloc_info; + +enum irq_remap_cap { + IRQ_POSTING_CAP = 0, +}; + +struct vcpu_data { + u64 pi_desc_addr; /* Physical address of PI Descriptor */ + u32 vector; /* Guest vector of the interrupt */ +}; #ifdef CONFIG_IRQ_REMAP +extern bool irq_remapping_cap(enum irq_remap_cap cap); extern void set_irq_remapping_broken(void); extern int irq_remapping_prepare(void); extern int irq_remapping_enable(void); extern void irq_remapping_disable(void); extern int irq_remapping_reenable(int); extern int irq_remap_enable_fault_handling(void); -extern int setup_ioapic_remapped_entry(int irq, - struct IO_APIC_route_entry *entry, - unsigned int destination, - int vector, - struct io_apic_irq_attr *attr); -extern void free_remapped_irq(int irq); -extern void compose_remapped_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id); -extern int setup_hpet_msi_remapped(unsigned int irq, unsigned int id); extern void panic_if_irq_remap(const char *msg); -extern bool setup_remapped_irq(int irq, - struct irq_cfg *cfg, - struct irq_chip *chip); -void irq_remap_modify_chip_defaults(struct irq_chip *chip); +extern struct irq_domain * +irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info); +extern struct irq_domain * +irq_remapping_get_irq_domain(struct irq_alloc_info *info); + +/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ +extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent); + +/* Get parent irqdomain for interrupt remapping irqdomain */ +static inline struct irq_domain *arch_get_ir_parent_domain(void) +{ + return x86_vector_domain; +} #else /* CONFIG_IRQ_REMAP */ +static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; } static inline void set_irq_remapping_broken(void) { } static inline int irq_remapping_prepare(void) { return -ENODEV; } static inline int irq_remapping_enable(void) { return -ENODEV; } static inline void irq_remapping_disable(void) { } static inline int irq_remapping_reenable(int eim) { return -ENODEV; } static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; } -static inline int setup_ioapic_remapped_entry(int irq, - struct IO_APIC_route_entry *entry, - unsigned int destination, - int vector, - struct io_apic_irq_attr *attr) -{ - return -ENODEV; -} -static inline void free_remapped_irq(int irq) { } -static inline void compose_remapped_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id) -{ -} -static inline int setup_hpet_msi_remapped(unsigned int irq, unsigned int id) -{ - return -ENODEV; -} static inline void panic_if_irq_remap(const char *msg) { } -static inline void irq_remap_modify_chip_defaults(struct irq_chip *chip) +static inline struct irq_domain * +irq_remapping_get_ir_irq_domain(struct irq_alloc_info *info) { + return NULL; } -static inline bool setup_remapped_irq(int irq, - struct irq_cfg *cfg, - struct irq_chip *chip) +static inline struct irq_domain * +irq_remapping_get_irq_domain(struct irq_alloc_info *info) { - return false; + return NULL; } -#endif /* CONFIG_IRQ_REMAP */ - -#define dmar_alloc_hwirq() irq_alloc_hwirq(-1) -#define dmar_free_hwirq irq_free_hwirq +#endif /* CONFIG_IRQ_REMAP */ #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/kernel/arch/x86/include/asm/irq_vectors.h b/kernel/arch/x86/include/asm/irq_vectors.h index 666c89ec4..6ca9fd623 100644 --- a/kernel/arch/x86/include/asm/irq_vectors.h +++ b/kernel/arch/x86/include/asm/irq_vectors.h @@ -47,31 +47,12 @@ #define IRQ_MOVE_CLEANUP_VECTOR FIRST_EXTERNAL_VECTOR #define IA32_SYSCALL_VECTOR 0x80 -#ifdef CONFIG_X86_32 -# define SYSCALL_VECTOR 0x80 -#endif /* * Vectors 0x30-0x3f are used for ISA interrupts. * round up to the next 16-vector boundary */ -#define IRQ0_VECTOR ((FIRST_EXTERNAL_VECTOR + 16) & ~15) - -#define IRQ1_VECTOR (IRQ0_VECTOR + 1) -#define IRQ2_VECTOR (IRQ0_VECTOR + 2) -#define IRQ3_VECTOR (IRQ0_VECTOR + 3) -#define IRQ4_VECTOR (IRQ0_VECTOR + 4) -#define IRQ5_VECTOR (IRQ0_VECTOR + 5) -#define IRQ6_VECTOR (IRQ0_VECTOR + 6) -#define IRQ7_VECTOR (IRQ0_VECTOR + 7) -#define IRQ8_VECTOR (IRQ0_VECTOR + 8) -#define IRQ9_VECTOR (IRQ0_VECTOR + 9) -#define IRQ10_VECTOR (IRQ0_VECTOR + 10) -#define IRQ11_VECTOR (IRQ0_VECTOR + 11) -#define IRQ12_VECTOR (IRQ0_VECTOR + 12) -#define IRQ13_VECTOR (IRQ0_VECTOR + 13) -#define IRQ14_VECTOR (IRQ0_VECTOR + 14) -#define IRQ15_VECTOR (IRQ0_VECTOR + 15) +#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq) /* * Special IRQ vectors used by the SMP architecture, 0xf0-0xff @@ -102,21 +83,23 @@ */ #define X86_PLATFORM_IPI_VECTOR 0xf7 -/* Vector for KVM to deliver posted interrupt IPI */ -#ifdef CONFIG_HAVE_KVM -#define POSTED_INTR_VECTOR 0xf2 -#endif - +#define POSTED_INTR_WAKEUP_VECTOR 0xf1 /* * IRQ work vector: */ #define IRQ_WORK_VECTOR 0xf6 #define UV_BAU_MESSAGE 0xf5 +#define DEFERRED_ERROR_VECTOR 0xf4 /* Vector on which hypervisor callbacks will be delivered */ #define HYPERVISOR_CALLBACK_VECTOR 0xf3 +/* Vector for KVM to deliver posted interrupt IPI */ +#ifdef CONFIG_HAVE_KVM +#define POSTED_INTR_VECTOR 0xf2 +#endif + /* * Local APIC timer IRQ vector is on a different priority level, * to work around the 'lost local interrupt if more than 2 IRQ @@ -134,16 +117,6 @@ #define FPU_IRQ 13 -#define FIRST_VM86_IRQ 3 -#define LAST_VM86_IRQ 15 - -#ifndef __ASSEMBLY__ -static inline int invalid_vm86_irq(int irq) -{ - return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; -} -#endif - /* * Size the maximum number of interrupts. * @@ -155,18 +128,22 @@ static inline int invalid_vm86_irq(int irq) * static arrays. */ -#define NR_IRQS_LEGACY 16 +#define NR_IRQS_LEGACY 16 -#define IO_APIC_VECTOR_LIMIT ( 32 * MAX_IO_APICS ) +#define CPU_VECTOR_LIMIT (64 * NR_CPUS) +#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS) -#ifdef CONFIG_X86_IO_APIC -# define CPU_VECTOR_LIMIT (64 * NR_CPUS) -# define NR_IRQS \ +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI) +#define NR_IRQS \ (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \ (NR_VECTORS + CPU_VECTOR_LIMIT) : \ (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) -#else /* !CONFIG_X86_IO_APIC: */ -# define NR_IRQS NR_IRQS_LEGACY +#elif defined(CONFIG_X86_IO_APIC) +#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT) +#elif defined(CONFIG_PCI_MSI) +#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT) +#else +#define NR_IRQS NR_IRQS_LEGACY #endif #endif /* _ASM_X86_IRQ_VECTORS_H */ diff --git a/kernel/arch/x86/include/asm/irqdomain.h b/kernel/arch/x86/include/asm/irqdomain.h new file mode 100644 index 000000000..d26075b52 --- /dev/null +++ b/kernel/arch/x86/include/asm/irqdomain.h @@ -0,0 +1,63 @@ +#ifndef _ASM_IRQDOMAIN_H +#define _ASM_IRQDOMAIN_H + +#include <linux/irqdomain.h> +#include <asm/hw_irq.h> + +#ifdef CONFIG_X86_LOCAL_APIC +enum { + /* Allocate contiguous CPU vectors */ + X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1, +}; + +extern struct irq_domain *x86_vector_domain; + +extern void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask); +extern void copy_irq_alloc_info(struct irq_alloc_info *dst, + struct irq_alloc_info *src); +#endif /* CONFIG_X86_LOCAL_APIC */ + +#ifdef CONFIG_X86_IO_APIC +struct device_node; +struct irq_data; + +enum ioapic_domain_type { + IOAPIC_DOMAIN_INVALID, + IOAPIC_DOMAIN_LEGACY, + IOAPIC_DOMAIN_STRICT, + IOAPIC_DOMAIN_DYNAMIC, +}; + +struct ioapic_domain_cfg { + enum ioapic_domain_type type; + const struct irq_domain_ops *ops; + struct device_node *dev; +}; + +extern const struct irq_domain_ops mp_ioapic_irqdomain_ops; + +extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg); +extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +extern void mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data); +extern void mp_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data); +extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); +#endif /* CONFIG_X86_IO_APIC */ + +#ifdef CONFIG_PCI_MSI +extern void arch_init_msi_domain(struct irq_domain *domain); +#else +static inline void arch_init_msi_domain(struct irq_domain *domain) { } +#endif + +#ifdef CONFIG_HT_IRQ +extern void arch_init_htirq_domain(struct irq_domain *domain); +#else +static inline void arch_init_htirq_domain(struct irq_domain *domain) { } +#endif + +#endif diff --git a/kernel/arch/x86/include/asm/jump_label.h b/kernel/arch/x86/include/asm/jump_label.h index a4c1cf7e9..5daeca3d0 100644 --- a/kernel/arch/x86/include/asm/jump_label.h +++ b/kernel/arch/x86/include/asm/jump_label.h @@ -16,15 +16,32 @@ # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif -static __always_inline bool arch_static_branch(struct static_key *key) +static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t" ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" - _ASM_PTR "1b, %l[l_yes], %c0 \n\t" + _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t" ".popsection \n\t" - : : "i" (key) : : l_yes); + : : "i" (key), "i" (branch) : : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) +{ + asm_volatile_goto("1:" + ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t" + "2:\n\t" + ".pushsection __jump_table, \"aw\" \n\t" + _ASM_ALIGN "\n\t" + _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t" + ".popsection \n\t" + : : "i" (key), "i" (branch) : : l_yes); + return false; l_yes: return true; diff --git a/kernel/arch/x86/include/asm/kasan.h b/kernel/arch/x86/include/asm/kasan.h index 74a2a8dc9..1410b567e 100644 --- a/kernel/arch/x86/include/asm/kasan.h +++ b/kernel/arch/x86/include/asm/kasan.h @@ -1,6 +1,9 @@ #ifndef _ASM_X86_KASAN_H #define _ASM_X86_KASAN_H +#include <linux/const.h> +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) + /* * Compiler uses shadow offset assuming that addresses start * from 0. Kernel addresses don't start from 0, so shadow diff --git a/kernel/arch/x86/include/asm/kdebug.h b/kernel/arch/x86/include/asm/kdebug.h index 32ce71375..e5f5dc978 100644 --- a/kernel/arch/x86/include/asm/kdebug.h +++ b/kernel/arch/x86/include/asm/kdebug.h @@ -29,11 +29,5 @@ extern void show_trace(struct task_struct *t, struct pt_regs *regs, extern void __show_regs(struct pt_regs *regs, int all); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); -#ifdef CONFIG_KEXEC -extern int in_crash_kexec; -#else -/* no crash dump is ever in progress if no crash kernel can be kexec'd */ -#define in_crash_kexec 0 -#endif #endif /* _ASM_X86_KDEBUG_H */ diff --git a/kernel/arch/x86/include/asm/kvm_emulate.h b/kernel/arch/x86/include/asm/kvm_emulate.h index 57a9d94fe..e9cd7befc 100644 --- a/kernel/arch/x86/include/asm/kvm_emulate.h +++ b/kernel/arch/x86/include/asm/kvm_emulate.h @@ -112,6 +112,16 @@ struct x86_emulate_ops { struct x86_exception *fault); /* + * read_phys: Read bytes of standard (non-emulated/special) memory. + * Used for descriptor reading. + * @addr: [IN ] Physical address from which to read. + * @val: [OUT] Value read from memory. + * @bytes: [IN ] Number of bytes to read from memory. + */ + int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr, + void *val, unsigned int bytes); + + /* * write_std: Write bytes of standard (non-emulated/special) memory. * Used for descriptor writing. * @addr: [IN ] Linear address to which to write. @@ -193,6 +203,8 @@ struct x86_emulate_ops { int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); + u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); + void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); @@ -262,6 +274,11 @@ enum x86emul_mode { X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */ }; +/* These match some of the HF_* flags defined in kvm_host.h */ +#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define X86EMUL_SMM_MASK (1 << 6) +#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -273,8 +290,8 @@ struct x86_emulate_ctxt { /* interruptibility state, as a result of execution of STI or MOV SS */ int interruptibility; + int emul_flags; - bool guest_mode; /* guest running a nested guest */ bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ diff --git a/kernel/arch/x86/include/asm/kvm_host.h b/kernel/arch/x86/include/asm/kvm_host.h index 41b06fca3..30cfd6429 100644 --- a/kernel/arch/x86/include/asm/kvm_host.h +++ b/kernel/arch/x86/include/asm/kvm_host.h @@ -24,6 +24,7 @@ #include <linux/perf_event.h> #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> +#include <linux/irqbypass.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> @@ -40,6 +41,7 @@ #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS @@ -175,6 +177,8 @@ enum { */ #define KVM_APIC_PV_EOI_PENDING 1 +struct kvm_kernel_irq_routing_entry; + /* * We don't want allocation failures within the mmu code, so we preallocate * enough memory for a single page fault in a cache. @@ -184,23 +188,12 @@ struct kvm_mmu_memory_cache { void *objects[KVM_NR_MEM_OBJS]; }; -/* - * kvm_mmu_page_role, below, is defined as: - * - * bits 0:3 - total guest paging levels (2-4, or zero for real mode) - * bits 4:7 - page table level for this shadow (1-4) - * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - direct mapping of virtual to physical mapping at gfn - * used for real mode and two-dimensional paging - * bits 17:19 - common access permissions for all ptes in this shadow page - */ union kvm_mmu_page_role { unsigned word; struct { unsigned level:4; unsigned cr4_pae:1; unsigned quadrant:2; - unsigned pad_for_nice_hex_output:6; unsigned direct:1; unsigned access:3; unsigned invalid:1; @@ -208,6 +201,15 @@ union kvm_mmu_page_role { unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; + unsigned :8; + + /* + * This is left at the top of the word so that + * kvm_memslots_for_spte_role can extract it with a + * simple shift. While there is room, give it a whole + * byte so it is also faster to load it from memory. + */ + unsigned smm:8; }; }; @@ -254,6 +256,11 @@ struct kvm_pio_request { int size; }; +struct rsvd_bits_validate { + u64 rsvd_bits_mask[2][4]; + u64 bad_mt_xwr; +}; + /* * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level * 32-bit). The kvm_mmu structure abstracts the details of the current mmu @@ -291,8 +298,15 @@ struct kvm_mmu { u64 *pae_root; u64 *lm_root; - u64 rsvd_bits_mask[2][4]; - u64 bad_mt_xwr; + + /* + * check zero bits on shadow page table entries, these + * bits include not only hardware reserved bits but also + * the bits spte never used. + */ + struct rsvd_bits_validate shadow_zero_check; + + struct rsvd_bits_validate guest_rsvd_check; /* * Bitmap: bit set = last pte in walk @@ -338,12 +352,34 @@ struct kvm_pmu { u64 reprogram_pmi; }; +struct kvm_pmu_ops; + enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, KVM_DEBUGREG_RELOAD = 4, }; +struct kvm_mtrr_range { + u64 base; + u64 mask; + struct list_head node; +}; + +struct kvm_mtrr { + struct kvm_mtrr_range var_ranges[KVM_NR_VAR_MTRR]; + mtrr_type fixed_ranges[KVM_NR_FIXED_MTRR_REGION]; + u64 deftype; + + struct list_head head; +}; + +/* Hyper-V per vcpu emulation context */ +struct kvm_vcpu_hv { + u64 hv_vapic; + s64 runtime_offset; +}; + struct kvm_vcpu_arch { /* * rip and regs accesses must go through @@ -364,10 +400,12 @@ struct kvm_vcpu_arch { u64 efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ + u64 eoi_exit_bitmap[4]; unsigned long apic_attention; int32_t apic_arb_prio; int mp_state; u64 ia32_misc_enable_msr; + u64 smbase; bool tpr_access_reporting; u64 ia32_xss; @@ -467,12 +505,14 @@ struct kvm_vcpu_arch { u32 virtual_tsc_mult; u32 virtual_tsc_khz; s64 ia32_tsc_adjust_msr; + u64 tsc_scaling_ratio; atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ unsigned nmi_pending; /* NMI queued after currently running handler */ bool nmi_injected; /* Trying to inject an NMI this entry */ + bool smi_pending; /* SMI queued after currently running handler */ - struct mtrr_state_type mtrr_state; + struct kvm_mtrr mtrr_state; u64 pat; unsigned switch_db_regs; @@ -498,8 +538,7 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; - /* fields used by HYPER-V emulation */ - u64 hv_vapic; + struct kvm_vcpu_hv hyperv; cpumask_var_t wbinvd_dirty_mask; @@ -540,6 +579,9 @@ struct kvm_vcpu_arch { struct { bool pv_unhalted; } pv; + + int pending_ioapic_eoi; + int pending_external_vector; }; struct kvm_lpage_info { @@ -570,6 +612,17 @@ struct kvm_apic_map { struct kvm_lapic *logical_map[16][16]; }; +/* Hyper-V emulation context */ +struct kvm_hv { + u64 hv_guest_os_id; + u64 hv_hypercall; + u64 hv_tsc_page; + + /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ + u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; + u64 hv_crash_ctl; +}; + struct kvm_arch { unsigned int n_used_mmu_pages; unsigned int n_requested_mmu_pages; @@ -588,6 +641,8 @@ struct kvm_arch { bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA atomic_t noncoherent_dma_count; +#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE + atomic_t assigned_device_count; struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; @@ -627,16 +682,19 @@ struct kvm_arch { /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; - /* fields used by HYPER-V emulation */ - u64 hv_guest_os_id; - u64 hv_hypercall; - u64 hv_tsc_page; + struct kvm_hv hyperv; #ifdef CONFIG_KVM_MMU_AUDIT int audit_point; #endif bool boot_vcpu_runs_old_kvmclock; + u32 bsp_vcpu_id; + + u64 disabled_quirks; + + bool irqchip_split; + u8 nr_reserved_ioapic_pins; }; struct kvm_vm_stat { @@ -666,6 +724,7 @@ struct kvm_vcpu_stat { u32 nmi_window_exits; u32 halt_exits; u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; u32 request_irq_exits; u32 irq_exits; @@ -689,12 +748,13 @@ struct msr_data { struct kvm_lapic_irq { u32 vector; - u32 delivery_mode; - u32 dest_mode; - u32 level; - u32 trig_mode; + u16 delivery_mode; + u16 dest_mode; + bool level; + u16 trig_mode; u32 shorthand; u32 dest_id; + bool msi_redir_hint; }; struct kvm_x86_ops { @@ -706,19 +766,20 @@ struct kvm_x86_ops { int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ bool (*cpu_has_accelerated_tpr)(void); + bool (*cpu_has_high_real_mode_segbase)(void); void (*cpuid_update)(struct kvm_vcpu *vcpu); /* Create, but do not attach this VCPU */ struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id); void (*vcpu_free)(struct kvm_vcpu *vcpu); - void (*vcpu_reset)(struct kvm_vcpu *vcpu); + void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); void (*prepare_guest_switch)(struct kvm_vcpu *vcpu); void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); - void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu); - int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); + void (*update_bp_intercept)(struct kvm_vcpu *vcpu); + int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); void (*get_segment)(struct kvm_vcpu *vcpu, @@ -770,10 +831,10 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - int (*vm_has_apicv)(struct kvm *kvm); + int (*cpu_uses_apicv)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm *kvm, int isr); - void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); + void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu); void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); @@ -784,7 +845,7 @@ struct kvm_x86_ops { int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); bool (*invpcid_supported)(void); - void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host); + void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -792,11 +853,9 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); - void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale); u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu); void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); - u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc); u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); @@ -836,6 +895,22 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); + /* pmu operations of sub-arch */ + const struct kvm_pmu_ops *pmu_ops; + + /* + * Architecture specific hooks for vCPU blocking due to + * HLT instruction. + * Returns for .pre_block(): + * - 0 means continue to block the vCPU. + * - 1 means we cannot block the vCPU since some event + * happens during this period, such as, 'ON' bit in + * posted-interrupts descriptor is set. + */ + int (*pre_block)(struct kvm_vcpu *vcpu); + void (*post_block)(struct kvm_vcpu *vcpu); + int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set); }; struct kvm_arch_async_pf { @@ -847,17 +922,6 @@ struct kvm_arch_async_pf { extern struct kvm_x86_ops *kvm_x86_ops; -static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, - s64 adjustment) -{ - kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false); -} - -static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) -{ - kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true); -} - int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); @@ -871,7 +935,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - struct kvm_memory_slot *memslot); + const struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, @@ -882,7 +946,7 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); @@ -890,7 +954,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, const void *val, int bytes); -u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); struct kvm_irq_mask_notifier { void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked); @@ -911,10 +974,12 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); /* control of guest tsc rate supported? */ extern bool kvm_has_tsc_control; -/* minimum supported tsc_khz for guests */ -extern u32 kvm_min_guest_tsc_khz; /* maximum supported tsc_khz for guests */ extern u32 kvm_max_guest_tsc_khz; +/* number of bits of the fractional part of the TSC scaling ratio */ +extern u8 kvm_tsc_scaling_ratio_frac_bits; +/* maximum allowed value of TSC scaling ratio */ +extern u64 kvm_max_tsc_scaling_ratio; enum emulation_result { EMULATE_DONE, /* no further processing */ @@ -938,7 +1003,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu, void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data); +int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr); struct x86_emulate_ctxt; @@ -967,7 +1032,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr); unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); @@ -1002,8 +1067,6 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -int fx_init(struct kvm_vcpu *vcpu); - void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes); int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn); @@ -1112,6 +1175,14 @@ enum { #define HF_NMI_MASK (1 << 3) #define HF_IRET_MASK (1 << 4) #define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define HF_SMM_MASK (1 << 6) +#define HF_SMM_INSIDE_NMI_MASK (1 << 7) + +#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +#define KVM_ADDRESS_SPACE_NUM 2 + +#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) +#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) /* * Hardware virtualization extension instructions may fault if a @@ -1146,7 +1217,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); -void kvm_vcpu_reset(struct kvm_vcpu *vcpu); +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, unsigned long address); @@ -1154,6 +1225,9 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc); +u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); + unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); @@ -1170,16 +1244,18 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); int kvm_is_in_guest(void); -void kvm_pmu_init(struct kvm_vcpu *vcpu); -void kvm_pmu_destroy(struct kvm_vcpu *vcpu); -void kvm_pmu_reset(struct kvm_vcpu *vcpu); -void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu); -bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr); -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); -int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); -int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc); -int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -void kvm_handle_pmu_event(struct kvm_vcpu *vcpu); -void kvm_deliver_pmi(struct kvm_vcpu *vcpu); +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); +bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu); +bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu); + +bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu); + +void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm_lapic_irq *irq); + +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/kernel/arch/x86/include/asm/livepatch.h b/kernel/arch/x86/include/asm/livepatch.h index 2d29197bd..19c099afa 100644 --- a/kernel/arch/x86/include/asm/livepatch.h +++ b/kernel/arch/x86/include/asm/livepatch.h @@ -21,6 +21,7 @@ #ifndef _ASM_X86_LIVEPATCH_H #define _ASM_X86_LIVEPATCH_H +#include <asm/setup.h> #include <linux/module.h> #include <linux/ftrace.h> diff --git a/kernel/arch/x86/include/asm/math_emu.h b/kernel/arch/x86/include/asm/math_emu.h index 031f6266f..0d9b14f60 100644 --- a/kernel/arch/x86/include/asm/math_emu.h +++ b/kernel/arch/x86/include/asm/math_emu.h @@ -2,7 +2,6 @@ #define _ASM_X86_MATH_EMU_H #include <asm/ptrace.h> -#include <asm/vm86.h> /* This structure matches the layout of the data saved to the stack following a device-not-present interrupt, part of it saved @@ -10,9 +9,6 @@ */ struct math_emu_info { long ___orig_eip; - union { - struct pt_regs *regs; - struct kernel_vm86_regs *vm86; - }; + struct pt_regs *regs; }; #endif /* _ASM_X86_MATH_EMU_H */ diff --git a/kernel/arch/x86/include/asm/mce.h b/kernel/arch/x86/include/asm/mce.h index 1f5a86d51..2ea4527e4 100644 --- a/kernel/arch/x86/include/asm/mce.h +++ b/kernel/arch/x86/include/asm/mce.h @@ -17,11 +17,16 @@ #define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) #define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ #define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */ +#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */ /* MCG_STATUS register defines */ #define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ #define MCG_STATUS_EIPV (1ULL<<1) /* ip points to correct instruction */ #define MCG_STATUS_MCIP (1ULL<<2) /* machine check in progress */ +#define MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */ + +/* MCG_EXT_CTL register defines */ +#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */ /* MCi_STATUS register defines */ #define MCI_STATUS_VAL (1ULL<<63) /* valid error */ @@ -104,6 +109,7 @@ struct mce_log { struct mca_config { bool dont_log_ce; bool cmci_disabled; + bool lmce_disabled; bool ignore_ce; bool disabled; bool ser; @@ -117,8 +123,27 @@ struct mca_config { }; struct mce_vendor_flags { - __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */ - __reserved_0 : 63; + /* + * Indicates that overflow conditions are not fatal, when set. + */ + __u64 overflow_recov : 1, + + /* + * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and + * Recovery. It indicates support for data poisoning in HW and deferred + * error interrupts. + */ + succor : 1, + + /* + * (AMD) SMCA: This bit indicates support for Scalable MCA which expands + * the register space for each MCA bank and also increases number of + * banks. Also, to accommodate the new banks and registers, the MCA + * register space is moved to a new MSR range. + */ + smca : 1, + + __reserved_0 : 61; }; extern struct mce_vendor_flags mce_flags; @@ -134,10 +159,12 @@ extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); +void mcheck_cpu_clear(struct cpuinfo_x86 *c); void mcheck_vendor_init_severity(void); #else static inline int mcheck_init(void) { return 0; } static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} +static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {} static inline void mcheck_vendor_init_severity(void) {} #endif @@ -164,12 +191,14 @@ DECLARE_PER_CPU(struct device *, mce_device); #ifdef CONFIG_X86_MCE_INTEL void mce_intel_feature_init(struct cpuinfo_x86 *c); +void mce_intel_feature_clear(struct cpuinfo_x86 *c); void cmci_clear(void); void cmci_reenable(void); void cmci_rediscover(void); void cmci_recheck(void); #else static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { } +static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { } static inline void cmci_clear(void) {} static inline void cmci_reenable(void) {} static inline void cmci_rediscover(void) {} @@ -223,6 +252,9 @@ void do_machine_check(struct pt_regs *, long); extern void (*mce_threshold_vector)(void); extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu); +/* Deferred error interrupt handler */ +extern void (*deferred_error_int_vector)(void); + /* * Thermal handler */ diff --git a/kernel/arch/x86/include/asm/microcode.h b/kernel/arch/x86/include/asm/microcode.h index 2fb20d6f7..34e62b1dc 100644 --- a/kernel/arch/x86/include/asm/microcode.h +++ b/kernel/arch/x86/include/asm/microcode.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <linux/earlycpio.h> + #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ @@ -25,7 +27,6 @@ struct cpu_signature { struct device; enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; -extern bool dis_ucode_ldr; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, @@ -53,6 +54,12 @@ struct ucode_cpu_info { }; extern struct ucode_cpu_info ucode_cpu_info[]; +#ifdef CONFIG_MICROCODE +int __init microcode_init(void); +#else +static inline int __init microcode_init(void) { return 0; }; +#endif + #ifdef CONFIG_MICROCODE_INTEL extern struct microcode_ops * __init init_intel_microcode(void); #else @@ -73,7 +80,6 @@ static inline struct microcode_ops * __init init_amd_microcode(void) static inline void __exit exit_amd_microcode(void) {} #endif -#ifdef CONFIG_MICROCODE_EARLY #define MAX_UCODE_COUNT 128 #define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) @@ -148,18 +154,18 @@ static inline unsigned int x86_model(unsigned int sig) return model; } +#ifdef CONFIG_MICROCODE extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); void reload_early_microcode(void); +extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); #else -static inline void __init load_ucode_bsp(void) {} -static inline void load_ucode_ap(void) {} -static inline int __init save_microcode_in_initrd(void) -{ - return 0; -} -static inline void reload_early_microcode(void) {} +static inline void __init load_ucode_bsp(void) { } +static inline void load_ucode_ap(void) { } +static inline int __init save_microcode_in_initrd(void) { return 0; } +static inline void reload_early_microcode(void) { } +static inline bool +get_builtin_firmware(struct cpio_data *cd, const char *name) { return false; } #endif - #endif /* _ASM_X86_MICROCODE_H */ diff --git a/kernel/arch/x86/include/asm/microcode_amd.h b/kernel/arch/x86/include/asm/microcode_amd.h index af935397e..adfc847a3 100644 --- a/kernel/arch/x86/include/asm/microcode_amd.h +++ b/kernel/arch/x86/include/asm/microcode_amd.h @@ -64,16 +64,17 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s #define PATCH_MAX_SIZE PAGE_SIZE extern u8 amd_ucode_patch[PATCH_MAX_SIZE]; -#ifdef CONFIG_MICROCODE_AMD_EARLY -extern void __init load_ucode_amd_bsp(void); +#ifdef CONFIG_MICROCODE_AMD +extern void __init load_ucode_amd_bsp(unsigned int family); extern void load_ucode_amd_ap(void); extern int __init save_microcode_in_initrd_amd(void); void reload_ucode_amd(void); #else -static inline void __init load_ucode_amd_bsp(void) {} +static inline void __init load_ucode_amd_bsp(unsigned int family) {} static inline void load_ucode_amd_ap(void) {} static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; } void reload_ucode_amd(void) {} #endif +extern bool check_current_patch_level(u32 *rev, bool early); #endif /* _ASM_X86_MICROCODE_AMD_H */ diff --git a/kernel/arch/x86/include/asm/microcode_intel.h b/kernel/arch/x86/include/asm/microcode_intel.h index 2b9209c46..8559b0102 100644 --- a/kernel/arch/x86/include/asm/microcode_intel.h +++ b/kernel/arch/x86/include/asm/microcode_intel.h @@ -51,22 +51,13 @@ struct extended_sigtable { (((struct microcode_intel *)mc)->hdr.datasize ? \ ((struct microcode_intel *)mc)->hdr.datasize : DEFAULT_UCODE_DATASIZE) -#define sigmatch(s1, s2, p1, p2) \ - (((s1) == (s2)) && (((p1) & (p2)) || (((p1) == 0) && ((p2) == 0)))) - #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) -extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc); +extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev); extern int microcode_sanity_check(void *mc, int print_err); -extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc); - -static inline int -revision_is_newer(struct microcode_header_intel *mc_header, int rev) -{ - return (mc_header->rev <= rev) ? 0 : 1; -} +extern int find_matching_signature(void *mc, unsigned int csig, int cpf); -#ifdef CONFIG_MICROCODE_INTEL_EARLY +#ifdef CONFIG_MICROCODE_INTEL extern void __init load_ucode_intel_bsp(void); extern void load_ucode_intel_ap(void); extern void show_ucode_info_early(void); @@ -80,13 +71,9 @@ static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; static inline void reload_ucode_intel(void) {} #endif -#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) +#ifdef CONFIG_HOTPLUG_CPU extern int save_mc_for_early(u8 *mc); #else -static inline int save_mc_for_early(u8 *mc) -{ - return 0; -} +static inline int save_mc_for_early(u8 *mc) { return 0; } #endif - #endif /* _ASM_X86_MICROCODE_INTEL_H */ diff --git a/kernel/arch/x86/include/asm/mmu.h b/kernel/arch/x86/include/asm/mmu.h index 364d27481..55234d5e7 100644 --- a/kernel/arch/x86/include/asm/mmu.h +++ b/kernel/arch/x86/include/asm/mmu.h @@ -9,7 +9,9 @@ * we put the segment information here. */ typedef struct { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; +#endif #ifdef CONFIG_X86_64 /* True if mm supports a task running in 32 bit compatibility mode. */ diff --git a/kernel/arch/x86/include/asm/mmu_context.h b/kernel/arch/x86/include/asm/mmu_context.h index 80d67dd80..bfd9b2a35 100644 --- a/kernel/arch/x86/include/asm/mmu_context.h +++ b/kernel/arch/x86/include/asm/mmu_context.h @@ -33,6 +33,7 @@ static inline void load_mm_cr4(struct mm_struct *mm) static inline void load_mm_cr4(struct mm_struct *mm) {} #endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * ldt_structs can be allocated, used, and freed, but they are never * modified while live. @@ -48,8 +49,23 @@ struct ldt_struct { int size; }; +/* + * Used for LDT copy/destruction. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context(struct mm_struct *mm); +#else /* CONFIG_MODIFY_LDT_SYSCALL */ +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ + return 0; +} +static inline void destroy_context(struct mm_struct *mm) {} +#endif + static inline void load_mm_ldt(struct mm_struct *mm) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; /* lockless_dereference synchronizes with smp_store_release */ @@ -73,17 +89,13 @@ static inline void load_mm_ldt(struct mm_struct *mm) set_ldt(ldt->entries, ldt->size); else clear_LDT(); +#else + clear_LDT(); +#endif DEBUG_LOCKS_WARN_ON(preemptible()); } -/* - * Used for LDT copy/destruction. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); - - static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { #ifdef CONFIG_SMP @@ -104,8 +116,36 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, #endif cpumask_set_cpu(cpu, mm_cpumask(next)); - /* Re-load page tables */ + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + * + */ load_cr3(next->pgd); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); /* Stop flush ipis for the previous mm */ @@ -114,6 +154,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Load per-mm CR4 state */ load_mm_cr4(next); +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * Load the LDT, if the LDT is different. * @@ -128,6 +169,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ if (unlikely(prev->context.ldt != next->context.ldt)) load_mm_ldt(next); +#endif } #ifdef CONFIG_SMP else { @@ -142,10 +184,14 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, * schedule, protecting us from simultaneous changes. */ cpumask_set_cpu(cpu, mm_cpumask(next)); + /* * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. + * + * As above, load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask write. */ load_cr3(next->pgd); trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); @@ -186,6 +232,19 @@ static inline void arch_exit_mmap(struct mm_struct *mm) paravirt_arch_exit_mmap(mm); } +#ifdef CONFIG_X86_64 +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return !config_enabled(CONFIG_IA32_EMULATION) || + !(mm->context.ia32_compat == TIF_IA32); +} +#else +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return false; +} +#endif + static inline void arch_bprm_mm_init(struct mm_struct *mm, struct vm_area_struct *vma) { diff --git a/kernel/arch/x86/include/asm/mpx.h b/kernel/arch/x86/include/asm/mpx.h index a952a13d5..7a3549527 100644 --- a/kernel/arch/x86/include/asm/mpx.h +++ b/kernel/arch/x86/include/asm/mpx.h @@ -13,55 +13,50 @@ #define MPX_BNDCFG_ENABLE_FLAG 0x1 #define MPX_BD_ENTRY_VALID_FLAG 0x1 -#ifdef CONFIG_X86_64 - -/* upper 28 bits [47:20] of the virtual address in 64-bit used to - * index into bounds directory (BD). - */ -#define MPX_BD_ENTRY_OFFSET 28 -#define MPX_BD_ENTRY_SHIFT 3 -/* bits [19:3] of the virtual address in 64-bit used to index into - * bounds table (BT). +/* + * The upper 28 bits [47:20] of the virtual address in 64-bit + * are used to index into bounds directory (BD). + * + * The directory is 2G (2^31) in size, and with 8-byte entries + * it has 2^28 entries. */ -#define MPX_BT_ENTRY_OFFSET 17 -#define MPX_BT_ENTRY_SHIFT 5 -#define MPX_IGN_BITS 3 -#define MPX_BD_ENTRY_TAIL 3 +#define MPX_BD_SIZE_BYTES_64 (1UL<<31) +#define MPX_BD_ENTRY_BYTES_64 8 +#define MPX_BD_NR_ENTRIES_64 (MPX_BD_SIZE_BYTES_64/MPX_BD_ENTRY_BYTES_64) -#else - -#define MPX_BD_ENTRY_OFFSET 20 -#define MPX_BD_ENTRY_SHIFT 2 -#define MPX_BT_ENTRY_OFFSET 10 -#define MPX_BT_ENTRY_SHIFT 4 -#define MPX_IGN_BITS 2 -#define MPX_BD_ENTRY_TAIL 2 +/* + * The 32-bit directory is 4MB (2^22) in size, and with 4-byte + * entries it has 2^20 entries. + */ +#define MPX_BD_SIZE_BYTES_32 (1UL<<22) +#define MPX_BD_ENTRY_BYTES_32 4 +#define MPX_BD_NR_ENTRIES_32 (MPX_BD_SIZE_BYTES_32/MPX_BD_ENTRY_BYTES_32) -#endif +/* + * A 64-bit table is 4MB total in size, and an entry is + * 4 64-bit pointers in size. + */ +#define MPX_BT_SIZE_BYTES_64 (1UL<<22) +#define MPX_BT_ENTRY_BYTES_64 32 +#define MPX_BT_NR_ENTRIES_64 (MPX_BT_SIZE_BYTES_64/MPX_BT_ENTRY_BYTES_64) -#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT)) -#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT)) +/* + * A 32-bit table is 16kB total in size, and an entry is + * 4 32-bit pointers in size. + */ +#define MPX_BT_SIZE_BYTES_32 (1UL<<14) +#define MPX_BT_ENTRY_BYTES_32 16 +#define MPX_BT_NR_ENTRIES_32 (MPX_BT_SIZE_BYTES_32/MPX_BT_ENTRY_BYTES_32) #define MPX_BNDSTA_TAIL 2 #define MPX_BNDCFG_TAIL 12 #define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1)) #define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) -#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1)) - -#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1)) #define MPX_BNDSTA_ERROR_CODE 0x3 -#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1) -#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1) -#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \ - MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT) -#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \ - MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT) - #ifdef CONFIG_X86_INTEL_MPX -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf); -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf); +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs); +int mpx_handle_bd_fault(void); static inline int kernel_managing_mpx_tables(struct mm_struct *mm) { return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR); @@ -77,12 +72,11 @@ static inline void mpx_mm_init(struct mm_struct *mm) void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long start, unsigned long end); #else -static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { return NULL; } -static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +static inline int mpx_handle_bd_fault(void) { return -EINVAL; } diff --git a/kernel/arch/x86/include/asm/mshyperv.h b/kernel/arch/x86/include/asm/mshyperv.h index c163215ab..aaf59b7da 100644 --- a/kernel/arch/x86/include/asm/mshyperv.h +++ b/kernel/arch/x86/include/asm/mshyperv.h @@ -7,6 +7,7 @@ struct ms_hyperv_info { u32 features; + u32 misc_features; u32 hints; }; @@ -20,4 +21,8 @@ void hyperv_vector_handler(struct pt_regs *regs); void hv_setup_vmbus_irq(void (*handler)(void)); void hv_remove_vmbus_irq(void); +void hv_setup_kexec_handler(void (*handler)(void)); +void hv_remove_kexec_handler(void); +void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)); +void hv_remove_crash_handler(void); #endif diff --git a/kernel/arch/x86/include/asm/msi.h b/kernel/arch/x86/include/asm/msi.h new file mode 100644 index 000000000..93724cc62 --- /dev/null +++ b/kernel/arch/x86/include/asm/msi.h @@ -0,0 +1,7 @@ +#ifndef _ASM_X86_MSI_H +#define _ASM_X86_MSI_H +#include <asm/hw_irq.h> + +typedef struct irq_alloc_info msi_alloc_info_t; + +#endif /* _ASM_X86_MSI_H */ diff --git a/kernel/arch/x86/include/uapi/asm/msr-index.h b/kernel/arch/x86/include/asm/msr-index.h index 3c6bb342a..690b4027e 100644 --- a/kernel/arch/x86/include/uapi/asm/msr-index.h +++ b/kernel/arch/x86/include/asm/msr-index.h @@ -35,7 +35,7 @@ #define MSR_IA32_PERFCTR0 0x000000c1 #define MSR_IA32_PERFCTR1 0x000000c2 #define MSR_FSB_FREQ 0x000000cd -#define MSR_NHM_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO 0x000000ce #define MSR_NHM_SNB_PKG_CST_CFG_CTL 0x000000e2 #define NHM_C3_AUTO_DEMOTE (1UL << 25) @@ -44,7 +44,6 @@ #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) -#define MSR_PLATFORM_INFO 0x000000ce #define MSR_MTRRcap 0x000000fe #define MSR_IA32_BBL_CR_CTL 0x00000119 #define MSR_IA32_BBL_CR_CTL3 0x0000011e @@ -56,6 +55,7 @@ #define MSR_IA32_MCG_CAP 0x00000179 #define MSR_IA32_MCG_STATUS 0x0000017a #define MSR_IA32_MCG_CTL 0x0000017b +#define MSR_IA32_MCG_EXT_CTL 0x000004d0 #define MSR_OFFCORE_RSP_0 0x000001a6 #define MSR_OFFCORE_RSP_1 0x000001a7 @@ -72,6 +72,12 @@ #define MSR_LBR_CORE_FROM 0x00000040 #define MSR_LBR_CORE_TO 0x00000060 +#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */ +#define LBR_INFO_MISPRED BIT_ULL(63) +#define LBR_INFO_IN_TX BIT_ULL(62) +#define LBR_INFO_ABORT BIT_ULL(61) +#define LBR_INFO_CYCLES 0xffff + #define MSR_IA32_PEBS_ENABLE 0x000003f1 #define MSR_IA32_DS_AREA 0x00000600 #define MSR_IA32_PERF_CAPABILITIES 0x00000345 @@ -79,13 +85,21 @@ #define MSR_IA32_RTIT_CTL 0x00000570 #define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) #define RTIT_CTL_OS BIT(2) #define RTIT_CTL_USR BIT(3) #define RTIT_CTL_CR3EN BIT(7) #define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) #define RTIT_CTL_TSC_EN BIT(10) #define RTIT_CTL_DISRETC BIT(11) #define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) #define MSR_IA32_RTIT_STATUS 0x00000571 #define RTIT_STATUS_CONTEXTEN BIT(1) #define RTIT_STATUS_TRIGGEREN BIT(2) @@ -126,6 +140,8 @@ #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define MSR_PEBS_FRONTEND 0x000003f7 + #define MSR_IA32_POWER_CTL 0x000001fc #define MSR_IA32_MC0_CTL 0x00000400 @@ -169,6 +185,12 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 +#define MSR_CONFIG_TDP_NOMINAL 0x00000648 +#define MSR_CONFIG_TDP_LEVEL_1 0x00000649 +#define MSR_CONFIG_TDP_LEVEL_2 0x0000064A +#define MSR_CONFIG_TDP_CONTROL 0x0000064B +#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C + #define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 #define MSR_PKG_ANY_CORE_C0_RES 0x00000659 #define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A @@ -183,6 +205,13 @@ #define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 #define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 +/* Config TDP MSRs */ +#define MSR_CONFIG_TDP_NOMINAL 0x00000648 +#define MSR_CONFIG_TDP_LEVEL1 0x00000649 +#define MSR_CONFIG_TDP_LEVEL2 0x0000064A +#define MSR_CONFIG_TDP_CONTROL 0x0000064B +#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C + /* Hardware P state interface */ #define MSR_PPERF 0x0000064e #define MSR_PERF_LIMIT_REASONS 0x0000064f @@ -310,6 +339,7 @@ /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 #define MSR_K8_TSEG_ADDR 0xc0010112 +#define MSR_K8_TSEG_MASK 0xc0010113 #define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */ #define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */ #define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */ @@ -380,6 +410,7 @@ #define FEATURE_CONTROL_LOCKED (1<<0) #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1) #define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2) +#define FEATURE_CONTROL_LMCE (1<<20) #define MSR_IA32_APICBASE 0x0000001b #define MSR_IA32_APICBASE_BSP (1<<8) diff --git a/kernel/arch/x86/include/asm/msr.h b/kernel/arch/x86/include/asm/msr.h index de36f22eb..77d8b284e 100644 --- a/kernel/arch/x86/include/asm/msr.h +++ b/kernel/arch/x86/include/asm/msr.h @@ -1,13 +1,14 @@ #ifndef _ASM_X86_MSR_H #define _ASM_X86_MSR_H -#include <uapi/asm/msr.h> +#include "msr-index.h" #ifndef __ASSEMBLY__ #include <asm/asm.h> #include <asm/errno.h> #include <asm/cpumask.h> +#include <uapi/asm/msr.h> struct msr { union { @@ -46,14 +47,13 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) * it means rax *or* rdx. */ #ifdef CONFIG_X86_64 -#define DECLARE_ARGS(val, low, high) unsigned low, high -#define EAX_EDX_VAL(val, low, high) ((low) | ((u64)(high) << 32)) -#define EAX_EDX_ARGS(val, low, high) "a" (low), "d" (high) +/* Using 64-bit values saves one instruction clearing the high half of low */ +#define DECLARE_ARGS(val, low, high) unsigned long low, high +#define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32) #define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high) #else #define DECLARE_ARGS(val, low, high) unsigned long long val #define EAX_EDX_VAL(val, low, high) (val) -#define EAX_EDX_ARGS(val, low, high) "A" (val) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif @@ -105,12 +105,19 @@ notrace static inline int native_write_msr_safe(unsigned int msr, return err; } -extern unsigned long long native_read_tsc(void); - extern int rdmsr_safe_regs(u32 regs[8]); extern int wrmsr_safe_regs(u32 regs[8]); -static __always_inline unsigned long long __native_read_tsc(void) +/** + * rdtsc() - returns the current TSC without ordering constraints + * + * rdtsc() returns the result of RDTSC as a 64-bit integer. The + * only ordering constraint it supplies is the ordering implied by + * "asm volatile": it will put the RDTSC in the place you expect. The + * CPU can and will speculatively execute that RDTSC, though, so the + * results can be non-monotonic if compared on different CPUs. + */ +static __always_inline unsigned long long rdtsc(void) { DECLARE_ARGS(val, low, high); @@ -119,6 +126,35 @@ static __always_inline unsigned long long __native_read_tsc(void) return EAX_EDX_VAL(val, low, high); } +/** + * rdtsc_ordered() - read the current TSC in program order + * + * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer. + * It is ordered like a load to a global in-memory counter. It should + * be impossible to observe non-monotonic rdtsc_unordered() behavior + * across multiple CPUs as long as the TSC is synced. + */ +static __always_inline unsigned long long rdtsc_ordered(void) +{ + /* + * The RDTSC instruction is not ordered relative to memory + * access. The Intel SDM and the AMD APM are both vague on this + * point, but empirically an RDTSC instruction can be + * speculatively executed before prior loads. An RDTSC + * immediately after an appropriate barrier appears to be + * ordered as a normal load, that is, it provides the same + * ordering guarantees as reading from a global memory location + * that some other imaginary CPU is updating continuously with a + * time stamp. + */ + alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, + "lfence", X86_FEATURE_LFENCE_RDTSC); + return rdtsc(); +} + +/* Deprecated, keep it for a cycle for easier merging: */ +#define rdtscll(now) do { (now) = rdtsc_ordered(); } while (0) + static inline unsigned long long native_read_pmc(int counter) { DECLARE_ARGS(val, low, high); @@ -152,8 +188,10 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high) #define rdmsrl(msr, val) \ ((val) = native_read_msr((msr))) -#define wrmsrl(msr, val) \ - native_write_msr((msr), (u32)((u64)(val)), (u32)((u64)(val) >> 32)) +static inline void wrmsrl(unsigned msr, u64 val) +{ + native_write_msr(msr, (u32)val, (u32)(val >> 32)); +} /* wrmsr with exception handling */ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high) @@ -179,12 +217,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -#define rdtscl(low) \ - ((low) = (u32)__native_read_tsc()) - -#define rdtscll(val) \ - ((val) = __native_read_tsc()) - #define rdpmc(counter, low, high) \ do { \ u64 _l = native_read_pmc((counter)); \ @@ -194,19 +226,15 @@ do { \ #define rdpmcl(counter, val) ((val) = native_read_pmc(counter)) -#define rdtscp(low, high, aux) \ -do { \ - unsigned long long _val = native_read_tscp(&(aux)); \ - (low) = (u32)_val; \ - (high) = (u32)(_val >> 32); \ -} while (0) - -#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux)) - #endif /* !CONFIG_PARAVIRT */ -#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val), \ - (u32)((val) >> 32)) +/* + * 64-bit version of wrmsr_safe(): + */ +static inline int wrmsrl_safe(u32 msr, u64 val) +{ + return wrmsr_safe(msr, (u32)val, (u32)(val >> 32)); +} #define write_tsc(low, high) wrmsr(MSR_IA32_TSC, (low), (high)) diff --git a/kernel/arch/x86/include/asm/mtrr.h b/kernel/arch/x86/include/asm/mtrr.h index f768f6298..b94f6f64e 100644 --- a/kernel/arch/x86/include/asm/mtrr.h +++ b/kernel/arch/x86/include/asm/mtrr.h @@ -31,7 +31,7 @@ * arch_phys_wc_add and arch_phys_wc_del. */ # ifdef CONFIG_MTRR -extern u8 mtrr_type_lookup(u64 addr, u64 end); +extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); extern int mtrr_add(unsigned long base, unsigned long size, @@ -48,14 +48,13 @@ extern void mtrr_aps_init(void); extern void mtrr_bp_restore(void); extern int mtrr_trim_uncached_memory(unsigned long end_pfn); extern int amd_special_default_mtrr(void); -extern int phys_wc_to_mtrr_index(int handle); # else -static inline u8 mtrr_type_lookup(u64 addr, u64 end) +static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform) { /* * Return no-MTRRs: */ - return 0xff; + return MTRR_TYPE_INVALID; } #define mtrr_save_fixed_ranges(arg) do {} while (0) #define mtrr_save_state() do {} while (0) @@ -84,10 +83,6 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } -static inline int phys_wc_to_mtrr_index(int handle) -{ - return -1; -} #define mtrr_ap_init() do {} while (0) #define mtrr_bp_init() do {} while (0) @@ -127,4 +122,8 @@ struct mtrr_gentry32 { _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry32) #endif /* CONFIG_COMPAT */ +/* Bit fields for enabled in struct mtrr_state_type */ +#define MTRR_STATE_MTRR_FIXED_ENABLED 0x01 +#define MTRR_STATE_MTRR_ENABLED 0x02 + #endif /* _ASM_X86_MTRR_H */ diff --git a/kernel/arch/x86/include/asm/mwait.h b/kernel/arch/x86/include/asm/mwait.h index 653dfa766..c70689b5e 100644 --- a/kernel/arch/x86/include/asm/mwait.h +++ b/kernel/arch/x86/include/asm/mwait.h @@ -14,6 +14,9 @@ #define CPUID5_ECX_INTERRUPT_BREAK 0x2 #define MWAIT_ECX_INTERRUPT_BREAK 0x1 +#define MWAITX_ECX_TIMER_ENABLE BIT(1) +#define MWAITX_MAX_LOOPS ((u32)-1) +#define MWAITX_DISABLE_CSTATES 0xf static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) @@ -23,6 +26,14 @@ static inline void __monitor(const void *eax, unsigned long ecx, :: "a" (eax), "c" (ecx), "d"(edx)); } +static inline void __monitorx(const void *eax, unsigned long ecx, + unsigned long edx) +{ + /* "monitorx %eax, %ecx, %edx;" */ + asm volatile(".byte 0x0f, 0x01, 0xfa;" + :: "a" (eax), "c" (ecx), "d"(edx)); +} + static inline void __mwait(unsigned long eax, unsigned long ecx) { /* "mwait %eax, %ecx;" */ @@ -30,6 +41,40 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +/* + * MWAITX allows for a timer expiration to get the core out a wait state in + * addition to the default MWAIT exit condition of a store appearing at a + * monitored virtual address. + * + * Registers: + * + * MWAITX ECX[1]: enable timer if set + * MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks. The software P0 + * frequency is the same as the TSC frequency. + * + * Below is a comparison between MWAIT and MWAITX on AMD processors: + * + * MWAIT MWAITX + * opcode 0f 01 c9 | 0f 01 fb + * ECX[0] value of RFLAGS.IF seen by instruction + * ECX[1] unused/#GP if set | enable timer if set + * ECX[31:2] unused/#GP if set + * EAX unused (reserve for hint) + * EBX[31:0] unused | max wait time (P0 clocks) + * + * MONITOR MONITORX + * opcode 0f 01 c8 | 0f 01 fa + * EAX (logical) address to monitor + * ECX #GP if not zero + */ +static inline void __mwaitx(unsigned long eax, unsigned long ebx, + unsigned long ecx) +{ + /* "mwaitx %eax, %ebx, %ecx;" */ + asm volatile(".byte 0x0f, 0x01, 0xfb;" + :: "a" (eax), "b" (ebx), "c" (ecx)); +} + static inline void __sti_mwait(unsigned long eax, unsigned long ecx) { trace_hardirqs_on(); diff --git a/kernel/arch/x86/include/asm/numachip/numachip.h b/kernel/arch/x86/include/asm/numachip/numachip.h index 1c6f7f621..c64373a2d 100644 --- a/kernel/arch/x86/include/asm/numachip/numachip.h +++ b/kernel/arch/x86/include/asm/numachip/numachip.h @@ -14,6 +14,7 @@ #ifndef _ASM_X86_NUMACHIP_NUMACHIP_H #define _ASM_X86_NUMACHIP_NUMACHIP_H +extern u8 numachip_system; extern int __init pci_numachip_init(void); #endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */ diff --git a/kernel/arch/x86/include/asm/numachip/numachip_csr.h b/kernel/arch/x86/include/asm/numachip/numachip_csr.h index 660f843df..29719eecd 100644 --- a/kernel/arch/x86/include/asm/numachip/numachip_csr.h +++ b/kernel/arch/x86/include/asm/numachip/numachip_csr.h @@ -14,12 +14,8 @@ #ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H #define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H -#include <linux/numa.h> -#include <linux/percpu.h> +#include <linux/smp.h> #include <linux/io.h> -#include <linux/swab.h> -#include <asm/types.h> -#include <asm/processor.h> #define CSR_NODE_SHIFT 16 #define CSR_NODE_BITS(p) (((unsigned long)(p)) << CSR_NODE_SHIFT) @@ -27,11 +23,8 @@ /* 32K CSR space, b15 indicates geo/non-geo */ #define CSR_OFFSET_MASK 0x7fffUL - -/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */ -#define NUMACHIP_GCSR_BASE 0x3fff00000000ULL -#define NUMACHIP_GCSR_LIM 0x3fff0fffffffULL -#define NUMACHIP_GCSR_SIZE (NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1) +#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) +#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) /* * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however @@ -41,12 +34,7 @@ #define NUMACHIP_LCSR_BASE 0x3ffffe000000ULL #define NUMACHIP_LCSR_LIM 0x3fffffffffffULL #define NUMACHIP_LCSR_SIZE (NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1) - -static inline void *gcsr_address(int node, unsigned long offset) -{ - return __va(NUMACHIP_GCSR_BASE | (1UL << 15) | - CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK)); -} +#define NUMACHIP_LAPIC_BITS 8 static inline void *lcsr_address(unsigned long offset) { @@ -54,114 +42,57 @@ static inline void *lcsr_address(unsigned long offset) CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK)); } -static inline unsigned int read_gcsr(int node, unsigned long offset) +static inline unsigned int read_lcsr(unsigned long offset) { - return swab32(readl(gcsr_address(node, offset))); + return swab32(readl(lcsr_address(offset))); } -static inline void write_gcsr(int node, unsigned long offset, unsigned int val) +static inline void write_lcsr(unsigned long offset, unsigned int val) { - writel(swab32(val), gcsr_address(node, offset)); + writel(swab32(val), lcsr_address(offset)); } -static inline unsigned int read_lcsr(unsigned long offset) +/* + * On NumaChip2, local CSR space is 16MB and starts at fixed offset below 4G + */ + +#define NUMACHIP2_LCSR_BASE 0xf0000000UL +#define NUMACHIP2_LCSR_SIZE 0x1000000UL +#define NUMACHIP2_APIC_ICR 0x100000 +#define NUMACHIP2_TIMER_DEADLINE 0x200000 +#define NUMACHIP2_TIMER_INT 0x200008 +#define NUMACHIP2_TIMER_NOW 0x200018 +#define NUMACHIP2_TIMER_RESET 0x200020 + +static inline void __iomem *numachip2_lcsr_address(unsigned long offset) { - return swab32(readl(lcsr_address(offset))); + return (void __iomem *)__va(NUMACHIP2_LCSR_BASE | + (offset & (NUMACHIP2_LCSR_SIZE - 1))); } -static inline void write_lcsr(unsigned long offset, unsigned int val) +static inline u32 numachip2_read32_lcsr(unsigned long offset) { - writel(swab32(val), lcsr_address(offset)); + return readl(numachip2_lcsr_address(offset)); } -/* ========================================================================= */ -/* CSR_G0_STATE_CLEAR */ -/* ========================================================================= */ - -#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12)) -union numachip_csr_g0_state_clear { - unsigned int v; - struct numachip_csr_g0_state_clear_s { - unsigned int _state:2; - unsigned int _rsvd_2_6:5; - unsigned int _lost:1; - unsigned int _rsvd_8_31:24; - } s; -}; - -/* ========================================================================= */ -/* CSR_G0_NODE_IDS */ -/* ========================================================================= */ +static inline u64 numachip2_read64_lcsr(unsigned long offset) +{ + return readq(numachip2_lcsr_address(offset)); +} -#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) -union numachip_csr_g0_node_ids { - unsigned int v; - struct numachip_csr_g0_node_ids_s { - unsigned int _initialid:16; - unsigned int _nodeid:12; - unsigned int _rsvd_28_31:4; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_EXT_IRQ_GEN */ -/* ========================================================================= */ +static inline void numachip2_write32_lcsr(unsigned long offset, u32 val) +{ + writel(val, numachip2_lcsr_address(offset)); +} -#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) -union numachip_csr_g3_ext_irq_gen { - unsigned int v; - struct numachip_csr_g3_ext_irq_gen_s { - unsigned int _vector:8; - unsigned int _msgtype:3; - unsigned int _index:5; - unsigned int _destination_apic_id:16; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_EXT_IRQ_STATUS */ -/* ========================================================================= */ - -#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12)) -union numachip_csr_g3_ext_irq_status { - unsigned int v; - struct numachip_csr_g3_ext_irq_status_s { - unsigned int _result:32; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_EXT_IRQ_DEST */ -/* ========================================================================= */ - -#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12)) -union numachip_csr_g3_ext_irq_dest { - unsigned int v; - struct numachip_csr_g3_ext_irq_dest_s { - unsigned int _irq:8; - unsigned int _rsvd_8_31:24; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_NC_ATT_MAP_SELECT */ -/* ========================================================================= */ - -#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12)) -union numachip_csr_g3_nc_att_map_select { - unsigned int v; - struct numachip_csr_g3_nc_att_map_select_s { - unsigned int _upper_address_bits:4; - unsigned int _select_ram:4; - unsigned int _rsvd_8_31:24; - } s; -}; - -/* ========================================================================= */ -/* CSR_G3_NC_ATT_MAP_SELECT_0-255 */ -/* ========================================================================= */ - -#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12)) +static inline void numachip2_write64_lcsr(unsigned long offset, u64 val) +{ + writeq(val, numachip2_lcsr_address(offset)); +} -#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ +static inline unsigned int numachip2_timer(void) +{ + return (smp_processor_id() % 48) << 6; +} +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ diff --git a/kernel/arch/x86/include/asm/page_64_types.h b/kernel/arch/x86/include/asm/page_64_types.h index 4edd53b79..4928cf0d5 100644 --- a/kernel/arch/x86/include/asm/page_64_types.h +++ b/kernel/arch/x86/include/asm/page_64_types.h @@ -26,9 +26,6 @@ #define MCE_STACK 4 #define N_EXCEPTION_STACKS 4 /* hw limit: 7 */ -#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) -#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) - /* * Set __PAGE_OFFSET to the most negative possible address + * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a diff --git a/kernel/arch/x86/include/asm/page_types.h b/kernel/arch/x86/include/asm/page_types.h index c7c712f26..cc071c6f7 100644 --- a/kernel/arch/x86/include/asm/page_types.h +++ b/kernel/arch/x86/include/asm/page_types.h @@ -9,16 +9,21 @@ #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) +#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) + +#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) + #define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) #define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) -/* Cast PAGE_MASK to a signed type so that it is sign-extended if +/* Cast *PAGE_MASK to a signed type so that it is sign-extended if virtual addresses are 32-bits but physical addresses are larger (ie, 32-bit PAE). */ #define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) - -#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) -#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) +#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK) #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1,UL) << HPAGE_SHIFT) diff --git a/kernel/arch/x86/include/asm/paravirt.h b/kernel/arch/x86/include/asm/paravirt.h index 8957810ad..c759b3cca 100644 --- a/kernel/arch/x86/include/asm/paravirt.h +++ b/kernel/arch/x86/include/asm/paravirt.h @@ -19,6 +19,12 @@ static inline int paravirt_enabled(void) return pv_info.paravirt_enabled; } +static inline int paravirt_has_feature(unsigned int feature) +{ + WARN_ON_ONCE(!pv_info.paravirt_enabled); + return (pv_info.features & feature); +} + static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -153,7 +159,11 @@ do { \ val = paravirt_read_msr(msr, &_err); \ } while (0) -#define wrmsrl(msr, val) wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32) +static inline void wrmsrl(unsigned msr, u64 val) +{ + wrmsr(msr, (u32)val, (u32)(val>>32)); +} + #define wrmsr_safe(msr, a, b) paravirt_write_msr(msr, a, b) /* rdmsr with exception handling */ @@ -174,19 +184,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) return err; } -static inline u64 paravirt_read_tsc(void) -{ - return PVOP_CALL0(u64, pv_cpu_ops.read_tsc); -} - -#define rdtscl(low) \ -do { \ - u64 _l = paravirt_read_tsc(); \ - low = (int)_l; \ -} while (0) - -#define rdtscll(val) (val = paravirt_read_tsc()) - static inline unsigned long long paravirt_sched_clock(void) { return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock); @@ -215,27 +212,6 @@ do { \ #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) -static inline unsigned long long paravirt_rdtscp(unsigned int *aux) -{ - return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux); -} - -#define rdtscp(low, high, aux) \ -do { \ - int __aux; \ - unsigned long __val = paravirt_rdtscp(&__aux); \ - (low) = (u32)__val; \ - (high) = (u32)(__val >> 32); \ - (aux) = __aux; \ -} while (0) - -#define rdtscpll(val, aux) \ -do { \ - unsigned long __aux; \ - val = paravirt_rdtscp(&__aux); \ - (aux) = __aux; \ -} while (0) - static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries); @@ -712,6 +688,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) +#ifdef CONFIG_QUEUED_SPINLOCKS + +static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, + u32 val) +{ + PVOP_VCALL2(pv_lock_ops.queued_spin_lock_slowpath, lock, val); +} + +static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) +{ + PVOP_VCALLEE1(pv_lock_ops.queued_spin_unlock, lock); +} + +static __always_inline void pv_wait(u8 *ptr, u8 val) +{ + PVOP_VCALL2(pv_lock_ops.wait, ptr, val); +} + +static __always_inline void pv_kick(int cpu) +{ + PVOP_VCALL1(pv_lock_ops.kick, cpu); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket) { @@ -724,7 +725,9 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); } -#endif +#endif /* CONFIG_QUEUED_SPINLOCKS */ + +#endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;" diff --git a/kernel/arch/x86/include/asm/paravirt_types.h b/kernel/arch/x86/include/asm/paravirt_types.h index f7b0b5c11..3d4419118 100644 --- a/kernel/arch/x86/include/asm/paravirt_types.h +++ b/kernel/arch/x86/include/asm/paravirt_types.h @@ -70,9 +70,14 @@ struct pv_info { #endif int paravirt_enabled; + unsigned int features; /* valid only if paravirt_enabled is set */ const char *name; }; +#define paravirt_has(x) paravirt_has_feature(PV_SUPPORTED_##x) +/* Supported features */ +#define PV_SUPPORTED_RTC (1<<0) + struct pv_init_ops { /* * Patch may replace one of the defined code sequences with @@ -97,7 +102,6 @@ struct pv_lazy_ops { struct pv_time_ops { unsigned long long (*sched_clock)(void); unsigned long long (*steal_clock)(int cpu); - unsigned long (*get_tsc_khz)(void); }; struct pv_cpu_ops { @@ -156,17 +160,16 @@ struct pv_cpu_ops { u64 (*read_msr)(unsigned int msr, int *err); int (*write_msr)(unsigned int msr, unsigned low, unsigned high); - u64 (*read_tsc)(void); u64 (*read_pmc)(int counter); - unsigned long long (*read_tscp)(unsigned int *aux); +#ifdef CONFIG_X86_32 /* * Atomically enable interrupts and return to userspace. This - * is only ever used to return to 32-bit processes; in a - * 64-bit kernel, it's used for 32-on-64 compat processes, but - * never native 64-bit processes. (Jump, not call.) + * is only used in 32-bit kernels. 64-bit kernels use + * usergs_sysret32 instead. */ void (*irq_enable_sysexit)(void); +#endif /* * Switch to usermode gs and return to 64-bit usermode using @@ -333,9 +336,19 @@ struct arch_spinlock; typedef u16 __ticket_t; #endif +struct qspinlock; + struct pv_lock_ops { +#ifdef CONFIG_QUEUED_SPINLOCKS + void (*queued_spin_lock_slowpath)(struct qspinlock *lock, u32 val); + struct paravirt_callee_save queued_spin_unlock; + + void (*wait)(u8 *ptr, u8 val); + void (*kick)(int cpu); +#else /* !CONFIG_QUEUED_SPINLOCKS */ struct paravirt_callee_save lock_spinning; void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); +#endif /* !CONFIG_QUEUED_SPINLOCKS */ }; /* This contains all the paravirt structures: we get a convenient diff --git a/kernel/arch/x86/include/asm/pat.h b/kernel/arch/x86/include/asm/pat.h index 91bc4ba95..ca6c228d5 100644 --- a/kernel/arch/x86/include/asm/pat.h +++ b/kernel/arch/x86/include/asm/pat.h @@ -4,14 +4,9 @@ #include <linux/types.h> #include <asm/pgtable_types.h> -#ifdef CONFIG_X86_PAT -extern int pat_enabled; -#else -static const int pat_enabled; -#endif - +bool pat_enabled(void); extern void pat_init(void); -void pat_init_cache_modes(void); +void pat_init_cache_modes(u64); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/kernel/arch/x86/include/asm/pci.h b/kernel/arch/x86/include/asm/pci.h index 4e370a5d8..462594320 100644 --- a/kernel/arch/x86/include/asm/pci.h +++ b/kernel/arch/x86/include/asm/pci.h @@ -5,7 +5,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/string.h> -#include <asm/scatterlist.h> +#include <linux/scatterlist.h> #include <asm/io.h> #include <asm/x86_init.h> @@ -80,13 +80,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, #ifdef CONFIG_PCI extern void early_quirks(void); -static inline void pci_dma_burst_advice(struct pci_dev *pdev, - enum pci_dma_burst_strategy *strat, - unsigned long *strategy_parameter) -{ - *strat = PCI_DMA_BURST_INFINITY; - *strategy_parameter = ~0UL; -} #else static inline void early_quirks(void) { } #endif @@ -96,15 +89,10 @@ extern void pci_iommu_alloc(void); #ifdef CONFIG_PCI_MSI /* implemented in arch/x86/kernel/apic/io_apic. */ struct msi_desc; -void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq, - unsigned int dest, struct msi_msg *msg, u8 hpet_id); int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void native_teardown_msi_irq(unsigned int irq); void native_restore_msi_irqs(struct pci_dev *dev); -int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset); #else -#define native_compose_msi_msg NULL #define native_setup_msi_irqs NULL #define native_teardown_msi_irq NULL #endif diff --git a/kernel/arch/x86/include/asm/pci_x86.h b/kernel/arch/x86/include/asm/pci_x86.h index 164e3f8d3..fa1195dae 100644 --- a/kernel/arch/x86/include/asm/pci_x86.h +++ b/kernel/arch/x86/include/asm/pci_x86.h @@ -93,8 +93,6 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); -extern bool mp_should_keep_irq(struct device *dev); - struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/kernel/arch/x86/include/asm/perf_event.h b/kernel/arch/x86/include/asm/perf_event.h index dc0f6ed35..7bcb861a0 100644 --- a/kernel/arch/x86/include/asm/perf_event.h +++ b/kernel/arch/x86/include/asm/perf_event.h @@ -159,6 +159,13 @@ struct x86_pmu_capability { */ #define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 16) +#define GLOBAL_STATUS_COND_CHG BIT_ULL(63) +#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(62) +#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) +#define GLOBAL_STATUS_ASIF BIT_ULL(60) +#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) +#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(58) + /* * IBS cpuid feature detection */ diff --git a/kernel/arch/x86/include/asm/pgtable.h b/kernel/arch/x86/include/asm/pgtable.h index fe57e7a98..6ec0c8b2e 100644 --- a/kernel/arch/x86/include/asm/pgtable.h +++ b/kernel/arch/x86/include/asm/pgtable.h @@ -19,6 +19,13 @@ #include <asm/x86_init.h> void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); +void ptdump_walk_pgd_level_checkwx(void); + +#ifdef CONFIG_DEBUG_WX +#define debug_checkwx() ptdump_walk_pgd_level_checkwx() +#else +#define debug_checkwx() do { } while (0) +#endif /* * ZERO_PAGE is a global shared page that is always zero: used @@ -142,12 +149,12 @@ static inline unsigned long pte_pfn(pte_t pte) static inline unsigned long pmd_pfn(pmd_t pmd) { - return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT; + return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; } static inline unsigned long pud_pfn(pud_t pud) { - return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT; + return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT; } #define pte_page(pte) pfn_to_page(pte_pfn(pte)) @@ -318,6 +325,16 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); } +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); +} + #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ /* @@ -379,7 +396,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) return __pgprot(preservebits | addbits); } -#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK) +#define pte_pgprot(x) __pgprot(pte_flags(x)) +#define pmd_pgprot(x) __pgprot(pmd_flags(x)) +#define pud_pgprot(x) __pgprot(pud_flags(x)) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) @@ -398,11 +417,17 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, * requested memtype: * - request is uncached, return cannot be write-back * - request is write-combine, return cannot be write-back + * - request is write-through, return cannot be write-back + * - request is write-through, return cannot be write-combine */ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && new_pcm == _PAGE_CACHE_MODE_WB) || (pcm == _PAGE_CACHE_MODE_WC && - new_pcm == _PAGE_CACHE_MODE_WB)) { + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WT && + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WT && + new_pcm == _PAGE_CACHE_MODE_WC)) { return 0; } @@ -496,14 +521,15 @@ static inline int pmd_none(pmd_t pmd) static inline unsigned long pmd_page_vaddr(pmd_t pmd) { - return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK); + return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pmd_page(pmd) pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT) +#define pmd_page(pmd) \ + pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT) /* * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] @@ -564,14 +590,15 @@ static inline int pud_present(pud_t pud) static inline unsigned long pud_page_vaddr(pud_t pud) { - return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK); + return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud)); } /* * Currently stuck as a macro due to indirect forward reference to * linux/mmzone.h's __section_mem_map_addr() definition: */ -#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT) +#define pud_page(pud) \ + pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT) /* Find an entry in the second-level page table.. */ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) @@ -799,8 +826,8 @@ static inline int pmd_write(pmd_t pmd) return pmd_flags(pmd) & _PAGE_RW; } -#define __HAVE_ARCH_PMDP_GET_AND_CLEAR -static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, unsigned long addr, +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { pmd_t pmd = native_pmdp_get_and_clear(pmdp); diff --git a/kernel/arch/x86/include/asm/pgtable_types.h b/kernel/arch/x86/include/asm/pgtable_types.h index 78f0c8cbe..79c91853e 100644 --- a/kernel/arch/x86/include/asm/pgtable_types.h +++ b/kernel/arch/x86/include/asm/pgtable_types.h @@ -209,10 +209,10 @@ enum page_cache_mode { #include <linux/types.h> -/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ +/* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */ #define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) -/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */ +/* Extracts the flags from a (pte|pmd|pud|pgd)val_t of a 4KB page */ #define PTE_FLAGS_MASK (~PTE_PFN_MASK) typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; @@ -276,14 +276,40 @@ static inline pmdval_t native_pmd_val(pmd_t pmd) } #endif +static inline pudval_t pud_pfn_mask(pud_t pud) +{ + if (native_pud_val(pud) & _PAGE_PSE) + return PHYSICAL_PUD_PAGE_MASK; + else + return PTE_PFN_MASK; +} + +static inline pudval_t pud_flags_mask(pud_t pud) +{ + return ~pud_pfn_mask(pud); +} + static inline pudval_t pud_flags(pud_t pud) { - return native_pud_val(pud) & PTE_FLAGS_MASK; + return native_pud_val(pud) & pud_flags_mask(pud); +} + +static inline pmdval_t pmd_pfn_mask(pmd_t pmd) +{ + if (native_pmd_val(pmd) & _PAGE_PSE) + return PHYSICAL_PMD_PAGE_MASK; + else + return PTE_PFN_MASK; +} + +static inline pmdval_t pmd_flags_mask(pmd_t pmd) +{ + return ~pmd_pfn_mask(pmd); } static inline pmdval_t pmd_flags(pmd_t pmd) { - return native_pmd_val(pmd) & PTE_FLAGS_MASK; + return native_pmd_val(pmd) & pmd_flags_mask(pmd); } static inline pte_t native_make_pte(pteval_t val) @@ -337,20 +363,18 @@ static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) } static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); return new; } static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) { + pgprotval_t val = pgprot_val(pgprot); pgprot_t new; - unsigned long val; - val = pgprot_val(pgprot); pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | ((val & _PAGE_PAT_LARGE) >> (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); @@ -367,6 +391,9 @@ extern int nx_enabled; #define pgprot_writecombine pgprot_writecombine extern pgprot_t pgprot_writecombine(pgprot_t prot); +#define pgprot_writethrough pgprot_writethrough +extern pgprot_t pgprot_writethrough(pgprot_t prot); + /* Indicate that x86 has its own track and untrack pfn vma functions */ #define __HAVE_PFNMAP_TRACKING diff --git a/kernel/arch/x86/include/asm/pmc_atom.h b/kernel/arch/x86/include/asm/pmc_atom.h index bc0fc0866..aa8744c77 100644 --- a/kernel/arch/x86/include/asm/pmc_atom.h +++ b/kernel/arch/x86/include/asm/pmc_atom.h @@ -18,6 +18,8 @@ /* ValleyView Power Control Unit PCI Device ID */ #define PCI_DEVICE_ID_VLV_PMC 0x0F1C +/* CherryTrail Power Control Unit PCI Device ID */ +#define PCI_DEVICE_ID_CHT_PMC 0x229C /* PMC Memory mapped IO registers */ #define PMC_BASE_ADDR_OFFSET 0x44 @@ -29,6 +31,10 @@ #define PMC_FUNC_DIS 0x34 #define PMC_FUNC_DIS_2 0x38 +/* CHT specific bits in FUNC_DIS2 register */ +#define BIT_FD_GMM BIT(3) +#define BIT_FD_ISH BIT(4) + /* S0ix wake event control */ #define PMC_S0IX_WAKE_EN 0x3C @@ -75,6 +81,21 @@ #define PMC_PSS_BIT_USB BIT(16) #define PMC_PSS_BIT_USB_SUS BIT(17) +/* CHT specific bits in PSS register */ +#define PMC_PSS_BIT_CHT_UFS BIT(7) +#define PMC_PSS_BIT_CHT_UXD BIT(11) +#define PMC_PSS_BIT_CHT_UXD_FD BIT(12) +#define PMC_PSS_BIT_CHT_UX_ENG BIT(15) +#define PMC_PSS_BIT_CHT_USB_SUS BIT(16) +#define PMC_PSS_BIT_CHT_GMM BIT(17) +#define PMC_PSS_BIT_CHT_ISH BIT(18) +#define PMC_PSS_BIT_CHT_DFX_MASTER BIT(26) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER1 BIT(27) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER2 BIT(28) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER3 BIT(29) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER4 BIT(30) +#define PMC_PSS_BIT_CHT_DFX_CLUSTER5 BIT(31) + /* These registers reflect D3 status of functions */ #define PMC_D3_STS_0 0xA0 @@ -117,6 +138,10 @@ #define BIT_USH_SS_PHY BIT(2) #define BIT_DFX BIT(3) +/* CHT specific bits in PMC_D3_STS_1 register */ +#define BIT_STS_GMM BIT(1) +#define BIT_STS_ISH BIT(2) + /* PMC I/O Registers */ #define ACPI_BASE_ADDR_OFFSET 0x40 #define ACPI_BASE_ADDR_MASK 0xFFFFFE00 @@ -126,4 +151,8 @@ #define SLEEP_TYPE_MASK 0xFFFFECFF #define SLEEP_TYPE_S5 0x1C00 #define SLEEP_ENABLE 0x2000 + +extern int pmc_atom_read(int offset, u32 *value); +extern int pmc_atom_write(int offset, u32 value); + #endif /* PMC_ATOM_H */ diff --git a/kernel/arch/x86/include/asm/pmem.h b/kernel/arch/x86/include/asm/pmem.h new file mode 100644 index 000000000..d8ce3ec81 --- /dev/null +++ b/kernel/arch/x86/include/asm/pmem.h @@ -0,0 +1,153 @@ +/* + * Copyright(c) 2015 Intel Corporation. All rights reserved. + * + * 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. + */ +#ifndef __ASM_X86_PMEM_H__ +#define __ASM_X86_PMEM_H__ + +#include <linux/uaccess.h> +#include <asm/cacheflush.h> +#include <asm/cpufeature.h> +#include <asm/special_insns.h> + +#ifdef CONFIG_ARCH_HAS_PMEM_API +/** + * arch_memcpy_to_pmem - copy data to persistent memory + * @dst: destination buffer for the copy + * @src: source buffer for the copy + * @n: length of the copy in bytes + * + * Copy data to persistent memory media via non-temporal stores so that + * a subsequent arch_wmb_pmem() can flush cpu and memory controller + * write buffers to guarantee durability. + */ +static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t n) +{ + int unwritten; + + /* + * We are copying between two kernel buffers, if + * __copy_from_user_inatomic_nocache() returns an error (page + * fault) we would have already reported a general protection fault + * before the WARN+BUG. + */ + unwritten = __copy_from_user_inatomic_nocache((void __force *) dst, + (void __user *) src, n); + if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n", + __func__, dst, src, unwritten)) + BUG(); +} + +/** + * arch_wmb_pmem - synchronize writes to persistent memory + * + * After a series of arch_memcpy_to_pmem() operations this drains data + * from cpu write buffers and any platform (memory controller) buffers + * to ensure that written data is durable on persistent memory media. + */ +static inline void arch_wmb_pmem(void) +{ + /* + * wmb() to 'sfence' all previous writes such that they are + * architecturally visible to 'pcommit'. Note, that we've + * already arranged for pmem writes to avoid the cache via + * arch_memcpy_to_pmem(). + */ + wmb(); + pcommit_sfence(); +} + +/** + * __arch_wb_cache_pmem - write back a cache range with CLWB + * @vaddr: virtual start address + * @size: number of bytes to write back + * + * Write back a cache range using the CLWB (cache line write back) + * instruction. This function requires explicit ordering with an + * arch_wmb_pmem() call. This API is internal to the x86 PMEM implementation. + */ +static inline void __arch_wb_cache_pmem(void *vaddr, size_t size) +{ + u16 x86_clflush_size = boot_cpu_data.x86_clflush_size; + unsigned long clflush_mask = x86_clflush_size - 1; + void *vend = vaddr + size; + void *p; + + for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + p < vend; p += x86_clflush_size) + clwb(p); +} + +/* + * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec + * iterators, so for other types (bvec & kvec) we must do a cache write-back. + */ +static inline bool __iter_needs_pmem_wb(struct iov_iter *i) +{ + return iter_is_iovec(i) == false; +} + +/** + * arch_copy_from_iter_pmem - copy data from an iterator to PMEM + * @addr: PMEM destination address + * @bytes: number of bytes to copy + * @i: iterator with source data + * + * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. + * This function requires explicit ordering with an arch_wmb_pmem() call. + */ +static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, + struct iov_iter *i) +{ + void *vaddr = (void __force *)addr; + size_t len; + + /* TODO: skip the write-back by always using non-temporal stores */ + len = copy_from_iter_nocache(vaddr, bytes, i); + + if (__iter_needs_pmem_wb(i)) + __arch_wb_cache_pmem(vaddr, bytes); + + return len; +} + +/** + * arch_clear_pmem - zero a PMEM memory range + * @addr: virtual start address + * @size: number of bytes to zero + * + * Write zeros into the memory range starting at 'addr' for 'size' bytes. + * This function requires explicit ordering with an arch_wmb_pmem() call. + */ +static inline void arch_clear_pmem(void __pmem *addr, size_t size) +{ + void *vaddr = (void __force *)addr; + + /* TODO: implement the zeroing via non-temporal writes */ + if (size == PAGE_SIZE && ((unsigned long)vaddr & ~PAGE_MASK) == 0) + clear_page(vaddr); + else + memset(vaddr, 0, size); + + __arch_wb_cache_pmem(vaddr, size); +} + +static inline bool __arch_has_wmb_pmem(void) +{ + /* + * We require that wmb() be an 'sfence', that is only guaranteed on + * 64-bit builds + */ + return static_cpu_has(X86_FEATURE_PCOMMIT); +} +#endif /* CONFIG_ARCH_HAS_PMEM_API */ +#endif /* __ASM_X86_PMEM_H__ */ diff --git a/kernel/arch/x86/include/asm/preempt.h b/kernel/arch/x86/include/asm/preempt.h index 6ef9a161d..5dbd2d0f9 100644 --- a/kernel/arch/x86/include/asm/preempt.h +++ b/kernel/arch/x86/include/asm/preempt.h @@ -30,12 +30,9 @@ static __always_inline void preempt_count_set(int pc) /* * must be macros to avoid header recursion hell */ -#define init_task_preempt_count(p) do { \ - task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \ -} while (0) +#define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ - task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \ per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \ } while (0) @@ -101,13 +98,13 @@ static __always_inline bool __preempt_count_dec_and_test(void) /* * Returns true when we need to resched and can (barring IRQ state). */ -static __always_inline bool should_resched(void) +static __always_inline bool should_resched(int preempt_offset) { #ifdef CONFIG_PREEMPT_LAZY - return unlikely(!raw_cpu_read_4(__preempt_count) || \ + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset || test_thread_flag(TIF_NEED_RESCHED_LAZY)); #else - return unlikely(!raw_cpu_read_4(__preempt_count)); + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); #endif } @@ -115,11 +112,9 @@ static __always_inline bool should_resched(void) extern asmlinkage void ___preempt_schedule(void); # define __preempt_schedule() asm ("call ___preempt_schedule") extern asmlinkage void preempt_schedule(void); -# ifdef CONFIG_CONTEXT_TRACKING - extern asmlinkage void ___preempt_schedule_context(void); -# define __preempt_schedule_context() asm ("call ___preempt_schedule_context") - extern asmlinkage void preempt_schedule_context(void); -# endif + extern asmlinkage void ___preempt_schedule_notrace(void); +# define __preempt_schedule_notrace() asm ("call ___preempt_schedule_notrace") + extern asmlinkage void preempt_schedule_notrace(void); #endif #endif /* __ASM_PREEMPT_H */ diff --git a/kernel/arch/x86/include/asm/processor.h b/kernel/arch/x86/include/asm/processor.h index 23ba6765b..2d5a50cb6 100644 --- a/kernel/arch/x86/include/asm/processor.h +++ b/kernel/arch/x86/include/asm/processor.h @@ -6,12 +6,12 @@ /* Forward declaration, a strange C thing */ struct task_struct; struct mm_struct; +struct vm86; -#include <asm/vm86.h> #include <asm/math_emu.h> #include <asm/segment.h> #include <asm/types.h> -#include <asm/sigcontext.h> +#include <uapi/asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeature.h> #include <asm/page.h> @@ -21,6 +21,7 @@ struct mm_struct; #include <asm/desc_defs.h> #include <asm/nops.h> #include <asm/special_insns.h> +#include <asm/fpu/types.h> #include <linux/personality.h> #include <linux/cpumask.h> @@ -52,11 +53,16 @@ static inline void *current_text_addr(void) return pc; } +/* + * These alignment constraints are for performance in the vSMP case, + * but in the task_struct case we must also meet hardware imposed + * alignment requirements of the FPU state: + */ #ifdef CONFIG_X86_VSMP # define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT) # define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT) #else -# define ARCH_MIN_TASKALIGN 16 +# define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state) # define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif @@ -166,7 +172,6 @@ extern const struct seq_operations cpuinfo_op; #define cache_line_size() (boot_cpu_data.x86_cache_alignment) extern void cpu_detect(struct cpuinfo_x86 *c); -extern void fpu_detect(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_boot_cpu(void); @@ -313,128 +318,6 @@ struct orig_ist { unsigned long ist[7]; }; -#define MXCSR_DEFAULT 0x1f80 - -struct i387_fsave_struct { - u32 cwd; /* FPU Control Word */ - u32 swd; /* FPU Status Word */ - u32 twd; /* FPU Tag Word */ - u32 fip; /* FPU IP Offset */ - u32 fcs; /* FPU IP Selector */ - u32 foo; /* FPU Operand Pointer Offset */ - u32 fos; /* FPU Operand Pointer Selector */ - - /* 8*10 bytes for each FP-reg = 80 bytes: */ - u32 st_space[20]; - - /* Software status information [not touched by FSAVE ]: */ - u32 status; -}; - -struct i387_fxsave_struct { - u16 cwd; /* Control Word */ - u16 swd; /* Status Word */ - u16 twd; /* Tag Word */ - u16 fop; /* Last Instruction Opcode */ - union { - struct { - u64 rip; /* Instruction Pointer */ - u64 rdp; /* Data Pointer */ - }; - struct { - u32 fip; /* FPU IP Offset */ - u32 fcs; /* FPU IP Selector */ - u32 foo; /* FPU Operand Offset */ - u32 fos; /* FPU Operand Selector */ - }; - }; - u32 mxcsr; /* MXCSR Register State */ - u32 mxcsr_mask; /* MXCSR Mask */ - - /* 8*16 bytes for each FP-reg = 128 bytes: */ - u32 st_space[32]; - - /* 16*16 bytes for each XMM-reg = 256 bytes: */ - u32 xmm_space[64]; - - u32 padding[12]; - - union { - u32 padding1[12]; - u32 sw_reserved[12]; - }; - -} __attribute__((aligned(16))); - -struct i387_soft_struct { - u32 cwd; - u32 swd; - u32 twd; - u32 fip; - u32 fcs; - u32 foo; - u32 fos; - /* 8*10 bytes for each FP-reg = 80 bytes: */ - u32 st_space[20]; - u8 ftop; - u8 changed; - u8 lookahead; - u8 no_update; - u8 rm; - u8 alimit; - struct math_emu_info *info; - u32 entry_eip; -}; - -struct ymmh_struct { - /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ - u32 ymmh_space[64]; -}; - -/* We don't support LWP yet: */ -struct lwp_struct { - u8 reserved[128]; -}; - -struct bndreg { - u64 lower_bound; - u64 upper_bound; -} __packed; - -struct bndcsr { - u64 bndcfgu; - u64 bndstatus; -} __packed; - -struct xsave_hdr_struct { - u64 xstate_bv; - u64 xcomp_bv; - u64 reserved[6]; -} __attribute__((packed)); - -struct xsave_struct { - struct i387_fxsave_struct i387; - struct xsave_hdr_struct xsave_hdr; - struct ymmh_struct ymmh; - struct lwp_struct lwp; - struct bndreg bndreg[4]; - struct bndcsr bndcsr; - /* new processor state extensions will go here */ -} __attribute__ ((packed, aligned (64))); - -union thread_xstate { - struct i387_fsave_struct fsave; - struct i387_fxsave_struct fxsave; - struct i387_soft_struct soft; - struct xsave_struct xsave; -}; - -struct fpu { - unsigned int last_cpu; - unsigned int has_fpu; - union thread_xstate *state; -}; - #ifdef CONFIG_X86_64 DECLARE_PER_CPU(struct orig_ist, orig_ist); @@ -483,8 +366,6 @@ DECLARE_PER_CPU(struct irq_stack *, softirq_stack); #endif /* X86_64 */ extern unsigned int xstate_size; -extern void free_thread_xstate(struct task_struct *); -extern struct kmem_cache *task_xstate_cachep; struct perf_event; @@ -508,6 +389,7 @@ struct thread_struct { unsigned long fs; #endif unsigned long gs; + /* Save middle states of ptrace breakpoints */ struct perf_event *ptrace_bps[HBP_NUM]; /* Debug status used for traps, single steps, etc... */ @@ -518,32 +400,22 @@ struct thread_struct { unsigned long cr2; unsigned long trap_nr; unsigned long error_code; - /* floating point and extended processor state */ - struct fpu fpu; -#ifdef CONFIG_X86_32 +#ifdef CONFIG_VM86 /* Virtual 86 mode info */ - struct vm86_struct __user *vm86_info; - unsigned long screen_bitmap; - unsigned long v86flags; - unsigned long v86mask; - unsigned long saved_sp0; - unsigned int saved_fs; - unsigned int saved_gs; + struct vm86 *vm86; #endif /* IO permissions: */ unsigned long *io_bitmap_ptr; unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + + /* Floating point and extended processor state */ + struct fpu fpu; /* - * fpu_counter contains the number of consecutive context switches - * that the FPU is used. If this is over a threshold, the lazy fpu - * saving becomes unlazy to save the trap. This is an unsigned char - * so that after 256 times the counter wraps and the behavior turns - * lazy again; this to deal with bursty apps that only use FPU for - * a short time + * WARNING: 'fpu' is dynamically-sized. It *MUST* be at + * the end. */ - unsigned char fpu_counter; }; /* @@ -600,6 +472,7 @@ static inline unsigned long current_top_of_stack(void) #else #define __cpuid native_cpuid #define paravirt_enabled() 0 +#define paravirt_has(x) 0 static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) @@ -684,12 +557,12 @@ static inline unsigned int cpuid_edx(unsigned int op) } /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) +static __always_inline void rep_nop(void) { asm volatile("rep; nop" ::: "memory"); } -static inline void cpu_relax(void) +static __always_inline void cpu_relax(void) { rep_nop(); } @@ -773,14 +646,6 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) extern void set_task_blockstep(struct task_struct *task, bool on); -/* - * from system description table in BIOS. Mostly for MCA use, but - * others may find it useful: - */ -extern unsigned int machine_id; -extern unsigned int machine_submodel_id; -extern unsigned int BIOS_revision; - /* Boot loader type from the setup header: */ extern int bootloader_type; extern int bootloader_version; @@ -842,7 +707,6 @@ static inline void spin_lock_prefetch(const void *x) #define INIT_THREAD { \ .sp0 = TOP_OF_INIT_STACK, \ - .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ } @@ -928,24 +792,25 @@ extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); /* Register/unregister a process' MPX related resource */ -#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk)) -#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk)) +#define MPX_ENABLE_MANAGEMENT() mpx_enable_management() +#define MPX_DISABLE_MANAGEMENT() mpx_disable_management() #ifdef CONFIG_X86_INTEL_MPX -extern int mpx_enable_management(struct task_struct *tsk); -extern int mpx_disable_management(struct task_struct *tsk); +extern int mpx_enable_management(void); +extern int mpx_disable_management(void); #else -static inline int mpx_enable_management(struct task_struct *tsk) +static inline int mpx_enable_management(void) { return -EINVAL; } -static inline int mpx_disable_management(struct task_struct *tsk) +static inline int mpx_disable_management(void) { return -EINVAL; } #endif /* CONFIG_X86_INTEL_MPX */ extern u16 amd_get_nb_id(int cpu); +extern u32 amd_get_nodes_per_socket(void); static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { diff --git a/kernel/arch/x86/include/asm/proto.h b/kernel/arch/x86/include/asm/proto.h index a90f8972d..a4a77286c 100644 --- a/kernel/arch/x86/include/asm/proto.h +++ b/kernel/arch/x86/include/asm/proto.h @@ -5,12 +5,14 @@ /* misc architecture specific prototypes */ -void system_call(void); void syscall_init(void); -void ia32_syscall(void); -void ia32_cstar_target(void); -void ia32_sysenter_target(void); +void entry_SYSCALL_64(void); +void entry_SYSCALL_compat(void); +void entry_INT80_32(void); +void entry_INT80_compat(void); +void entry_SYSENTER_32(void); +void entry_SYSENTER_compat(void); void x86_configure_nx(void); void x86_report_nx(void); diff --git a/kernel/arch/x86/include/asm/ptrace.h b/kernel/arch/x86/include/asm/ptrace.h index 5fabf1362..6271281f9 100644 --- a/kernel/arch/x86/include/asm/ptrace.h +++ b/kernel/arch/x86/include/asm/ptrace.h @@ -88,7 +88,6 @@ extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch, unsigned long phase1_result); extern long syscall_trace_enter(struct pt_regs *); -extern void syscall_trace_leave(struct pt_regs *); static inline unsigned long regs_return_value(struct pt_regs *regs) { diff --git a/kernel/arch/x86/include/asm/pvclock-abi.h b/kernel/arch/x86/include/asm/pvclock-abi.h index 6167fd798..67f082301 100644 --- a/kernel/arch/x86/include/asm/pvclock-abi.h +++ b/kernel/arch/x86/include/asm/pvclock-abi.h @@ -41,5 +41,7 @@ struct pvclock_wall_clock { #define PVCLOCK_TSC_STABLE_BIT (1 << 0) #define PVCLOCK_GUEST_STOPPED (1 << 1) +/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */ +#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PVCLOCK_ABI_H */ diff --git a/kernel/arch/x86/include/asm/pvclock.h b/kernel/arch/x86/include/asm/pvclock.h index d6b078e9f..7a6bed5c0 100644 --- a/kernel/arch/x86/include/asm/pvclock.h +++ b/kernel/arch/x86/include/asm/pvclock.h @@ -62,7 +62,7 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) static __always_inline u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src) { - u64 delta = __native_read_tsc() - src->tsc_timestamp; + u64 delta = rdtsc_ordered() - src->tsc_timestamp; return pvclock_scale_delta(delta, src->tsc_to_system_mul, src->tsc_shift); } @@ -76,17 +76,10 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u8 ret_flags; version = src->version; - /* Note: emulated platforms which do not advertise SSE2 support - * result in kvmclock not using the necessary RDTSC barriers. - * Without barriers, it is possible that RDTSC instruction reads from - * the time stamp counter outside rdtsc_barrier protected section - * below, resulting in violation of monotonicity. - */ - rdtsc_barrier(); + offset = pvclock_get_nsec_offset(src); ret = src->system_time + offset; ret_flags = src->flags; - rdtsc_barrier(); *cycles = ret; *flags = ret_flags; diff --git a/kernel/arch/x86/include/asm/qrwlock.h b/kernel/arch/x86/include/asm/qrwlock.h index ae0e241e2..c537cbb03 100644 --- a/kernel/arch/x86/include/asm/qrwlock.h +++ b/kernel/arch/x86/include/asm/qrwlock.h @@ -2,16 +2,6 @@ #define _ASM_X86_QRWLOCK_H #include <asm-generic/qrwlock_types.h> - -#ifndef CONFIG_X86_PPRO_FENCE -#define queue_write_unlock queue_write_unlock -static inline void queue_write_unlock(struct qrwlock *lock) -{ - barrier(); - ACCESS_ONCE(*(u8 *)&lock->cnts) = 0; -} -#endif - #include <asm-generic/qrwlock.h> #endif /* _ASM_X86_QRWLOCK_H */ diff --git a/kernel/arch/x86/include/asm/qspinlock.h b/kernel/arch/x86/include/asm/qspinlock.h new file mode 100644 index 000000000..eaba08076 --- /dev/null +++ b/kernel/arch/x86/include/asm/qspinlock.h @@ -0,0 +1,66 @@ +#ifndef _ASM_X86_QSPINLOCK_H +#define _ASM_X86_QSPINLOCK_H + +#include <asm/cpufeature.h> +#include <asm-generic/qspinlock_types.h> +#include <asm/paravirt.h> + +#define queued_spin_unlock queued_spin_unlock +/** + * queued_spin_unlock - release a queued spinlock + * @lock : Pointer to queued spinlock structure + * + * A smp_store_release() on the least-significant byte. + */ +static inline void native_queued_spin_unlock(struct qspinlock *lock) +{ + smp_store_release((u8 *)lock, 0); +} + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_init_lock_hash(void); +extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock); + +static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) +{ + pv_queued_spin_lock_slowpath(lock, val); +} + +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + pv_queued_spin_unlock(lock); +} +#else +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} +#endif + +#ifdef CONFIG_PARAVIRT +#define virt_spin_lock virt_spin_lock +static inline bool virt_spin_lock(struct qspinlock *lock) +{ + if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) + return false; + + /* + * On hypervisors without PARAVIRT_SPINLOCKS support we fall + * back to a Test-and-Set spinlock, because fair locks have + * horrible lock 'holder' preemption issues. + */ + + do { + while (atomic_read(&lock->val) != 0) + cpu_relax(); + } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0); + + return true; +} +#endif /* CONFIG_PARAVIRT */ + +#include <asm-generic/qspinlock.h> + +#endif /* _ASM_X86_QSPINLOCK_H */ diff --git a/kernel/arch/x86/include/asm/qspinlock_paravirt.h b/kernel/arch/x86/include/asm/qspinlock_paravirt.h new file mode 100644 index 000000000..b002e711b --- /dev/null +++ b/kernel/arch/x86/include/asm/qspinlock_paravirt.h @@ -0,0 +1,6 @@ +#ifndef __ASM_QSPINLOCK_PARAVIRT_H +#define __ASM_QSPINLOCK_PARAVIRT_H + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); + +#endif diff --git a/kernel/arch/x86/include/asm/serial.h b/kernel/arch/x86/include/asm/serial.h index 8378b8c91..bb658211e 100644 --- a/kernel/arch/x86/include/asm/serial.h +++ b/kernel/arch/x86/include/asm/serial.h @@ -11,7 +11,7 @@ #define BASE_BAUD (1843200/16) /* Standard COM flags (except for COM4, because of the 8514 problem) */ -#ifdef CONFIG_SERIAL_DETECT_IRQ +#ifdef CONFIG_SERIAL_8250_DETECT_IRQ # define STD_COMX_FLAGS (UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_AUTO_IRQ) # define STD_COM4_FLAGS (UPF_BOOT_AUTOCONF | 0 | UPF_AUTO_IRQ) #else diff --git a/kernel/arch/x86/include/asm/setup.h b/kernel/arch/x86/include/asm/setup.h index f69e06b28..11af24e09 100644 --- a/kernel/arch/x86/include/asm/setup.h +++ b/kernel/arch/x86/include/asm/setup.h @@ -60,17 +60,24 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP #include <asm/espfix.h> +#include <linux/kernel.h> /* * This is set up by the setup-routine at boot-time */ extern struct boot_params boot_params; +extern char _text[]; static inline bool kaslr_enabled(void) { return !!(boot_params.hdr.loadflags & KASLR_FLAG); } +static inline unsigned long kaslr_offset(void) +{ + return (unsigned long)&_text - __START_KERNEL; +} + /* * Do NOT EVER look at the BIOS memory size location. * It does not work on many machines. diff --git a/kernel/arch/x86/include/asm/sigcontext.h b/kernel/arch/x86/include/asm/sigcontext.h index 9dfce4e04..e6cd2c489 100644 --- a/kernel/arch/x86/include/asm/sigcontext.h +++ b/kernel/arch/x86/include/asm/sigcontext.h @@ -1,79 +1,8 @@ #ifndef _ASM_X86_SIGCONTEXT_H #define _ASM_X86_SIGCONTEXT_H -#include <uapi/asm/sigcontext.h> - -#ifdef __i386__ -struct sigcontext { - unsigned short gs, __gsh; - unsigned short fs, __fsh; - unsigned short es, __esh; - unsigned short ds, __dsh; - unsigned long di; - unsigned long si; - unsigned long bp; - unsigned long sp; - unsigned long bx; - unsigned long dx; - unsigned long cx; - unsigned long ax; - unsigned long trapno; - unsigned long err; - unsigned long ip; - unsigned short cs, __csh; - unsigned long flags; - unsigned long sp_at_signal; - unsigned short ss, __ssh; +/* This is a legacy header - all kernel code includes <uapi/asm/sigcontext.h> directly. */ - /* - * fpstate is really (struct _fpstate *) or (struct _xstate *) - * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved - * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end - * of extended memory layout. See comments at the definition of - * (struct _fpx_sw_bytes) - */ - void __user *fpstate; /* zero when no FPU/extended context */ - unsigned long oldmask; - unsigned long cr2; -}; -#else /* __i386__ */ -struct sigcontext { - unsigned long r8; - unsigned long r9; - unsigned long r10; - unsigned long r11; - unsigned long r12; - unsigned long r13; - unsigned long r14; - unsigned long r15; - unsigned long di; - unsigned long si; - unsigned long bp; - unsigned long bx; - unsigned long dx; - unsigned long ax; - unsigned long cx; - unsigned long sp; - unsigned long ip; - unsigned long flags; - unsigned short cs; - unsigned short gs; - unsigned short fs; - unsigned short __pad0; - unsigned long err; - unsigned long trapno; - unsigned long oldmask; - unsigned long cr2; +#include <uapi/asm/sigcontext.h> - /* - * fpstate is really (struct _fpstate *) or (struct _xstate *) - * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved - * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end - * of extended memory layout. See comments at the definition of - * (struct _fpx_sw_bytes) - */ - void __user *fpstate; /* zero when no FPU/extended context */ - unsigned long reserved1[8]; -}; -#endif /* !__i386__ */ #endif /* _ASM_X86_SIGCONTEXT_H */ diff --git a/kernel/arch/x86/include/asm/sigframe.h b/kernel/arch/x86/include/asm/sigframe.h index 7c7c27c97..34edd1650 100644 --- a/kernel/arch/x86/include/asm/sigframe.h +++ b/kernel/arch/x86/include/asm/sigframe.h @@ -1,15 +1,14 @@ #ifndef _ASM_X86_SIGFRAME_H #define _ASM_X86_SIGFRAME_H -#include <asm/sigcontext.h> +#include <uapi/asm/sigcontext.h> #include <asm/siginfo.h> #include <asm/ucontext.h> +#include <linux/compat.h> #ifdef CONFIG_X86_32 #define sigframe_ia32 sigframe #define rt_sigframe_ia32 rt_sigframe -#define sigcontext_ia32 sigcontext -#define _fpstate_ia32 _fpstate #define ucontext_ia32 ucontext #else /* !CONFIG_X86_32 */ @@ -23,7 +22,7 @@ struct sigframe_ia32 { u32 pretcode; int sig; - struct sigcontext_ia32 sc; + struct sigcontext_32 sc; /* * fpstate is unused. fpstate is moved/allocated after * retcode[] below. This movement allows to have the FP state and the @@ -32,7 +31,7 @@ struct sigframe_ia32 { * the offset of extramask[] in the sigframe and thus prevent any * legacy application accessing/modifying it. */ - struct _fpstate_ia32 fpstate_unused; + struct _fpstate_32 fpstate_unused; #ifdef CONFIG_IA32_EMULATION unsigned int extramask[_COMPAT_NSIG_WORDS-1]; #else /* !CONFIG_IA32_EMULATION */ @@ -69,6 +68,15 @@ struct rt_sigframe { #ifdef CONFIG_X86_X32_ABI +struct ucontext_x32 { + unsigned int uc_flags; + unsigned int uc_link; + compat_stack_t uc_stack; + unsigned int uc__pad0; /* needed for alignment */ + struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + struct rt_sigframe_x32 { u64 pretcode; struct ucontext_x32 uc; diff --git a/kernel/arch/x86/include/asm/signal.h b/kernel/arch/x86/include/asm/signal.h index b1b08a28c..3f5b4ee2e 100644 --- a/kernel/arch/x86/include/asm/signal.h +++ b/kernel/arch/x86/include/asm/signal.h @@ -32,7 +32,7 @@ typedef struct { * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the * trap. */ -#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) +#if defined(CONFIG_PREEMPT_RT_FULL) #define ARCH_RT_DELAYS_SIGNAL_SEND #endif @@ -43,11 +43,11 @@ typedef sigset_t compat_sigset_t; #endif /* __ASSEMBLY__ */ #include <uapi/asm/signal.h> #ifndef __ASSEMBLY__ -extern void do_notify_resume(struct pt_regs *, void *, __u32); +extern void do_signal(struct pt_regs *regs); #define __ARCH_HAS_SA_RESTORER -#include <asm/sigcontext.h> +#include <uapi/asm/sigcontext.h> #ifdef __i386__ diff --git a/kernel/arch/x86/include/asm/simd.h b/kernel/arch/x86/include/asm/simd.h index ee80b92f0..6c8a7ed13 100644 --- a/kernel/arch/x86/include/asm/simd.h +++ b/kernel/arch/x86/include/asm/simd.h @@ -1,5 +1,5 @@ -#include <asm/i387.h> +#include <asm/fpu/api.h> /* * may_use_simd - whether it is allowable at this time to issue SIMD diff --git a/kernel/arch/x86/include/asm/smp.h b/kernel/arch/x86/include/asm/smp.h index 17a8dced1..222a6a3ca 100644 --- a/kernel/arch/x86/include/asm/smp.h +++ b/kernel/arch/x86/include/asm/smp.h @@ -37,16 +37,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); -static inline struct cpumask *cpu_sibling_mask(int cpu) -{ - return per_cpu(cpu_sibling_map, cpu); -} - -static inline struct cpumask *cpu_core_mask(int cpu) -{ - return per_cpu(cpu_core_map, cpu); -} - static inline struct cpumask *cpu_llc_shared_mask(int cpu) { return per_cpu(cpu_llc_shared_map, cpu); diff --git a/kernel/arch/x86/include/asm/special_insns.h b/kernel/arch/x86/include/asm/special_insns.h index aeb4666e0..2270e41b3 100644 --- a/kernel/arch/x86/include/asm/special_insns.h +++ b/kernel/arch/x86/include/asm/special_insns.h @@ -215,6 +215,44 @@ static inline void clwb(volatile void *__p) : [pax] "a" (p)); } +/** + * pcommit_sfence() - persistent commit and fence + * + * The PCOMMIT instruction ensures that data that has been flushed from the + * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to + * memory and is durable on the DIMM. The primary use case for this is + * persistent memory. + * + * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT + * with appropriate fencing. + * + * Example: + * void flush_and_commit_buffer(void *vaddr, unsigned int size) + * { + * unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + * void *vend = vaddr + size; + * void *p; + * + * for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + * p < vend; p += boot_cpu_data.x86_clflush_size) + * clwb(p); + * + * // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes + * // MFENCE via mb() also works + * wmb(); + * + * // PCOMMIT and the required SFENCE for ordering + * pcommit_sfence(); + * } + * + * After this function completes the data pointed to by 'vaddr' has been + * accepted to memory and will be durable if the 'vaddr' points to persistent + * memory. + * + * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify + * things we include both the PCOMMIT and the required SFENCE in the + * alternatives generated by pcommit_sfence(). + */ static inline void pcommit_sfence(void) { alternative(ASM_NOP7, diff --git a/kernel/arch/x86/include/asm/spinlock.h b/kernel/arch/x86/include/asm/spinlock.h index 64b611782..be0a05913 100644 --- a/kernel/arch/x86/include/asm/spinlock.h +++ b/kernel/arch/x86/include/asm/spinlock.h @@ -42,6 +42,10 @@ extern struct static_key paravirt_ticketlocks_enabled; static __always_inline bool static_key_false(struct static_key *key); +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#else + #ifdef CONFIG_PARAVIRT_SPINLOCKS static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) @@ -196,6 +200,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) cpu_relax(); } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ /* * Read-write spinlocks, allowing multiple readers diff --git a/kernel/arch/x86/include/asm/spinlock_types.h b/kernel/arch/x86/include/asm/spinlock_types.h index 5f9d7572d..65c3e37f8 100644 --- a/kernel/arch/x86/include/asm/spinlock_types.h +++ b/kernel/arch/x86/include/asm/spinlock_types.h @@ -23,6 +23,9 @@ typedef u32 __ticketpair_t; #define TICKET_SHIFT (sizeof(__ticket_t) * 8) +#ifdef CONFIG_QUEUED_SPINLOCKS +#include <asm-generic/qspinlock_types.h> +#else typedef struct arch_spinlock { union { __ticketpair_t head_tail; @@ -33,6 +36,7 @@ typedef struct arch_spinlock { } arch_spinlock_t; #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ #include <asm-generic/qrwlock_types.h> diff --git a/kernel/arch/x86/include/asm/stackprotector.h b/kernel/arch/x86/include/asm/stackprotector.h index 64fb5cbe5..02fa39652 100644 --- a/kernel/arch/x86/include/asm/stackprotector.h +++ b/kernel/arch/x86/include/asm/stackprotector.h @@ -39,7 +39,9 @@ #include <asm/processor.h> #include <asm/percpu.h> #include <asm/desc.h> + #include <linux/random.h> +#include <linux/sched.h> /* * 24 byte read-only segment initializer for stack canary. Linker @@ -72,13 +74,12 @@ static __always_inline void boot_init_stack_canary(void) * For preempt-rt we need to weaken the randomness a bit, as * we can't call into the random generator from atomic context * due to locking constraints. We just leave canary - * uninitialized and use the TSC based randomness on top of - * it. + * uninitialized and use the TSC based randomness on top of it. */ #ifndef CONFIG_PREEMPT_RT_FULL get_random_bytes(&canary, sizeof(canary)); #endif - tsc = __native_read_tsc(); + tsc = rdtsc(); canary += tsc + (tsc << 32UL); current->stack_canary = canary; diff --git a/kernel/arch/x86/include/asm/string_64.h b/kernel/arch/x86/include/asm/string_64.h index e46611969..ff8b9a17d 100644 --- a/kernel/arch/x86/include/asm/string_64.h +++ b/kernel/arch/x86/include/asm/string_64.h @@ -27,12 +27,11 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t function. */ #define __HAVE_ARCH_MEMCPY 1 +extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #ifndef CONFIG_KMEMCHECK -#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4 -extern void *memcpy(void *to, const void *from, size_t len); -#else +#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ ({ \ size_t __len = (len); \ diff --git a/kernel/arch/x86/include/asm/suspend_32.h b/kernel/arch/x86/include/asm/suspend_32.h index 552d6c90a..d1793f068 100644 --- a/kernel/arch/x86/include/asm/suspend_32.h +++ b/kernel/arch/x86/include/asm/suspend_32.h @@ -7,7 +7,7 @@ #define _ASM_X86_SUSPEND_32_H #include <asm/desc.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> /* image of the saved processor state */ struct saved_context { diff --git a/kernel/arch/x86/include/asm/suspend_64.h b/kernel/arch/x86/include/asm/suspend_64.h index bc6232834..7ebf0ebe4 100644 --- a/kernel/arch/x86/include/asm/suspend_64.h +++ b/kernel/arch/x86/include/asm/suspend_64.h @@ -7,7 +7,7 @@ #define _ASM_X86_SUSPEND_64_H #include <asm/desc.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> /* * Image of the saved processor state, used by the low level ACPI suspend to diff --git a/kernel/arch/x86/include/asm/syscall.h b/kernel/arch/x86/include/asm/syscall.h index d6a756ae0..999b7cd2e 100644 --- a/kernel/arch/x86/include/asm/syscall.h +++ b/kernel/arch/x86/include/asm/syscall.h @@ -20,9 +20,21 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> -typedef void (*sys_call_ptr_t)(void); +typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); extern const sys_call_ptr_t sys_call_table[]; +#if defined(CONFIG_X86_32) +#define ia32_sys_call_table sys_call_table +#define __NR_syscall_compat_max __NR_syscall_max +#define IA32_NR_syscalls NR_syscalls +#endif + +#if defined(CONFIG_IA32_EMULATION) +extern const sys_call_ptr_t ia32_sys_call_table[]; +#endif + /* * Only the low 32 bits of orig_ax are meaningful, so we return int. * This importantly ignores the high bits on 64-bit, so comparisons diff --git a/kernel/arch/x86/include/asm/syscalls.h b/kernel/arch/x86/include/asm/syscalls.h index 592a6a672..91dfcafe2 100644 --- a/kernel/arch/x86/include/asm/syscalls.h +++ b/kernel/arch/x86/include/asm/syscalls.h @@ -37,6 +37,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *); asmlinkage unsigned long sys_sigreturn(void); /* kernel/vm86_32.c */ +struct vm86_struct; asmlinkage long sys_vm86old(struct vm86_struct __user *); asmlinkage long sys_vm86(unsigned long, unsigned long); diff --git a/kernel/arch/x86/include/asm/thread_info.h b/kernel/arch/x86/include/asm/thread_info.h index 606144afb..ddb63bd90 100644 --- a/kernel/arch/x86/include/asm/thread_info.h +++ b/kernel/arch/x86/include/asm/thread_info.h @@ -27,14 +27,17 @@ * Without this offset, that can result in a page fault. (We are * careful that, in this case, the value we read doesn't matter.) * - * In vm86 mode, the hardware frame is much longer still, but we neither - * access the extra members from NMI context, nor do we write such a - * frame at sp0 at all. + * In vm86 mode, the hardware frame is much longer still, so add 16 + * bytes to make room for the real-mode segments. * * x86_64 has a fixed-length stack frame. */ #ifdef CONFIG_X86_32 -# define TOP_OF_KERNEL_STACK_PADDING 8 +# ifdef CONFIG_VM86 +# define TOP_OF_KERNEL_STACK_PADDING 16 +# else +# define TOP_OF_KERNEL_STACK_PADDING 8 +# endif #else # define TOP_OF_KERNEL_STACK_PADDING 0 #endif @@ -54,11 +57,9 @@ struct thread_info { __u32 flags; /* low level flags */ __u32 status; /* thread synchronous flags */ __u32 cpu; /* current CPU */ - int saved_preempt_count; - int preempt_lazy_count; /* 0 => lazy preemptable - <0 => BUG */ mm_segment_t addr_limit; - void __user *sysenter_return; + int preempt_lazy_count; /* 0 => lazy preemptable + <0 => BUG */ unsigned int sig_on_uaccess_error:1; unsigned int uaccess_err:1; /* uaccess failed */ }; @@ -68,7 +69,6 @@ struct thread_info { .task = &tsk, \ .flags = 0, \ .cpu = 0, \ - .saved_preempt_count = INIT_PREEMPT_COUNT, \ .addr_limit = KERNEL_DS, \ } @@ -144,27 +144,11 @@ struct thread_info { _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* work to do in syscall_trace_leave() */ -#define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ - _TIF_SYSCALL_TRACEPOINT | _TIF_NOHZ) - -/* work to do on interrupt/exception return */ -#define _TIF_WORK_MASK \ - (0x0000FFFF & \ - ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT| \ - _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) - /* work to do on any return to user space */ #define _TIF_ALLWORK_MASK \ ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* Only used for 64 bit */ -#define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | \ - _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) - /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_NOTSC|_TIF_BLOCKSTEP) @@ -183,8 +167,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -DECLARE_PER_CPU(unsigned long, kernel_stack); - static inline struct thread_info *current_thread_info(void) { return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); @@ -203,9 +185,13 @@ static inline unsigned long current_stack_pointer(void) #else /* !__ASSEMBLY__ */ +#ifdef CONFIG_X86_64 +# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +#endif + /* Load thread_info address into "reg" */ #define GET_THREAD_INFO(reg) \ - _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \ + _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ _ASM_SUB $(THREAD_SIZE),reg ; /* diff --git a/kernel/arch/x86/include/asm/tlbflush.h b/kernel/arch/x86/include/asm/tlbflush.h index cd791948b..6df202940 100644 --- a/kernel/arch/x86/include/asm/tlbflush.h +++ b/kernel/arch/x86/include/asm/tlbflush.h @@ -261,6 +261,12 @@ static inline void reset_lazy_tlbstate(void) #endif /* SMP */ +/* Not inlined due to inc_irq_stat not being defined yet */ +#define flush_tlb_local() { \ + inc_irq_stat(irq_tlb_count); \ + local_flush_tlb(); \ +} + #ifndef CONFIG_PARAVIRT #define flush_tlb_others(mask, mm, start, end) \ native_flush_tlb_others(mask, mm, start, end) diff --git a/kernel/arch/x86/include/asm/topology.h b/kernel/arch/x86/include/asm/topology.h index 0e8f04f2c..0fb46482d 100644 --- a/kernel/arch/x86/include/asm/topology.h +++ b/kernel/arch/x86/include/asm/topology.h @@ -26,7 +26,7 @@ #define _ASM_X86_TOPOLOGY_H #ifdef CONFIG_X86_32 -# ifdef CONFIG_X86_HT +# ifdef CONFIG_SMP # define ENABLE_TOPO_DEFINES # endif #else @@ -124,7 +124,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) +#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/kernel/arch/x86/include/asm/trace/irq_vectors.h b/kernel/arch/x86/include/asm/trace/irq_vectors.h index 4cab89000..38a09a13a 100644 --- a/kernel/arch/x86/include/asm/trace/irq_vectors.h +++ b/kernel/arch/x86/include/asm/trace/irq_vectors.h @@ -101,6 +101,12 @@ DEFINE_IRQ_VECTOR_EVENT(call_function_single); DEFINE_IRQ_VECTOR_EVENT(threshold_apic); /* + * deferred_error_apic - called when entering/exiting a deferred apic interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic); + +/* * thermal_apic - called when entering/exiting a thermal apic interrupt * vector handler */ diff --git a/kernel/arch/x86/include/asm/trace/mpx.h b/kernel/arch/x86/include/asm/trace/mpx.h new file mode 100644 index 000000000..0f492fc50 --- /dev/null +++ b/kernel/arch/x86/include/asm/trace/mpx.h @@ -0,0 +1,133 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mpx + +#if !defined(_TRACE_MPX_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MPX_H + +#include <linux/tracepoint.h> + +#ifdef CONFIG_X86_INTEL_MPX + +TRACE_EVENT(mpx_bounds_register_exception, + + TP_PROTO(void *addr_referenced, + const struct mpx_bndreg *bndreg), + TP_ARGS(addr_referenced, bndreg), + + TP_STRUCT__entry( + __field(void *, addr_referenced) + __field(u64, lower_bound) + __field(u64, upper_bound) + ), + + TP_fast_assign( + __entry->addr_referenced = addr_referenced; + __entry->lower_bound = bndreg->lower_bound; + __entry->upper_bound = bndreg->upper_bound; + ), + /* + * Note that we are printing out the '~' of the upper + * bounds register here. It is actually stored in its + * one's complement form so that its 'init' state + * corresponds to all 0's. But, that looks like + * gibberish when printed out, so print out the 1's + * complement instead of the actual value here. Note + * though that you still need to specify filters for the + * actual value, not the displayed one. + */ + TP_printk("address referenced: 0x%p bounds: lower: 0x%llx ~upper: 0x%llx", + __entry->addr_referenced, + __entry->lower_bound, + ~__entry->upper_bound + ) +); + +TRACE_EVENT(bounds_exception_mpx, + + TP_PROTO(const struct mpx_bndcsr *bndcsr), + TP_ARGS(bndcsr), + + TP_STRUCT__entry( + __field(u64, bndcfgu) + __field(u64, bndstatus) + ), + + TP_fast_assign( + /* need to get rid of the 'const' on bndcsr */ + __entry->bndcfgu = (u64)bndcsr->bndcfgu; + __entry->bndstatus = (u64)bndcsr->bndstatus; + ), + + TP_printk("bndcfgu:0x%llx bndstatus:0x%llx", + __entry->bndcfgu, + __entry->bndstatus) +); + +DECLARE_EVENT_CLASS(mpx_range_trace, + + TP_PROTO(unsigned long start, + unsigned long end), + TP_ARGS(start, end), + + TP_STRUCT__entry( + __field(unsigned long, start) + __field(unsigned long, end) + ), + + TP_fast_assign( + __entry->start = start; + __entry->end = end; + ), + + TP_printk("[0x%p:0x%p]", + (void *)__entry->start, + (void *)__entry->end + ) +); + +DEFINE_EVENT(mpx_range_trace, mpx_unmap_zap, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end) +); + +DEFINE_EVENT(mpx_range_trace, mpx_unmap_search, + TP_PROTO(unsigned long start, unsigned long end), + TP_ARGS(start, end) +); + +TRACE_EVENT(mpx_new_bounds_table, + + TP_PROTO(unsigned long table_vaddr), + TP_ARGS(table_vaddr), + + TP_STRUCT__entry( + __field(unsigned long, table_vaddr) + ), + + TP_fast_assign( + __entry->table_vaddr = table_vaddr; + ), + + TP_printk("table vaddr:%p", (void *)__entry->table_vaddr) +); + +#else + +/* + * This gets used outside of MPX-specific code, so we need a stub. + */ +static inline +void trace_bounds_exception_mpx(const struct mpx_bndcsr *bndcsr) +{ +} + +#endif /* CONFIG_X86_INTEL_MPX */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/trace/ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE mpx +#endif /* _TRACE_MPX_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/kernel/arch/x86/include/asm/traps.h b/kernel/arch/x86/include/asm/traps.h index 4e49d7dff..c34966197 100644 --- a/kernel/arch/x86/include/asm/traps.h +++ b/kernel/arch/x86/include/asm/traps.h @@ -108,11 +108,12 @@ extern int panic_on_unrecovered_nmi; void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 asmlinkage void smp_thermal_interrupt(void); -asmlinkage void mce_threshold_interrupt(void); +asmlinkage void smp_threshold_interrupt(void); +asmlinkage void smp_deferred_error_interrupt(void); #endif -extern enum ctx_state ist_enter(struct pt_regs *regs); -extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state); +extern void ist_enter(struct pt_regs *regs); +extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); extern void ist_end_non_atomic(void); diff --git a/kernel/arch/x86/include/asm/tsc.h b/kernel/arch/x86/include/asm/tsc.h index 94605c0e9..6d7c5479b 100644 --- a/kernel/arch/x86/include/asm/tsc.h +++ b/kernel/arch/x86/include/asm/tsc.h @@ -21,28 +21,12 @@ extern void disable_TSC(void); static inline cycles_t get_cycles(void) { - unsigned long long ret = 0; - #ifndef CONFIG_X86_TSC if (!cpu_has_tsc) return 0; #endif - rdtscll(ret); - - return ret; -} -static __always_inline cycles_t vget_cycles(void) -{ - /* - * We only do VDSOs on TSC capable CPUs, so this shouldn't - * access boot_cpu_data (which is not VDSO-safe): - */ -#ifndef CONFIG_X86_TSC - if (!cpu_has_tsc) - return 0; -#endif - return (cycles_t)__native_read_tsc(); + return rdtsc(); } extern void tsc_init(void); @@ -51,6 +35,7 @@ extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); extern int check_tsc_disabled(void); extern unsigned long native_calibrate_tsc(void); +extern unsigned long long native_sched_clock_from_tsc(u64 tsc); extern int tsc_clocksource_reliable; diff --git a/kernel/arch/x86/include/asm/uaccess.h b/kernel/arch/x86/include/asm/uaccess.h index a8df874f3..09b1b0ab9 100644 --- a/kernel/arch/x86/include/asm/uaccess.h +++ b/kernel/arch/x86/include/asm/uaccess.h @@ -51,13 +51,13 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * limit, not add it to the address). */ if (__builtin_constant_p(size)) - return addr > limit - size; + return unlikely(addr > limit - size); /* Arbitrary sizes? Be careful about overflow */ addr += size; - if (addr < size) + if (unlikely(addr < size)) return true; - return addr > limit; + return unlikely(addr > limit); } #define __range_not_ok(addr, size, limit) \ @@ -182,7 +182,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) : "=a" (__ret_gu), "=r" (__val_gu) \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ - __ret_gu; \ + __builtin_expect(__ret_gu, 0); \ }) #define __put_user_x(size, x, ptr, __ret_pu) \ @@ -278,7 +278,7 @@ extern void __put_user_8(void); __put_user_x(X, __pu_val, ptr, __ret_pu); \ break; \ } \ - __ret_pu; \ + __builtin_expect(__ret_pu, 0); \ }) #define __put_user_size(x, ptr, size, retval, errret) \ @@ -401,7 +401,7 @@ do { \ ({ \ int __pu_err; \ __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ - __pu_err; \ + __builtin_expect(__pu_err, 0); \ }) #define __get_user_nocheck(x, ptr, size) \ @@ -410,7 +410,7 @@ do { \ unsigned long __gu_val; \ __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __gu_err; \ + __builtin_expect(__gu_err, 0); \ }) /* FIXME: this hack is definitely wrong -AK */ diff --git a/kernel/arch/x86/include/asm/uaccess_32.h b/kernel/arch/x86/include/asm/uaccess_32.h index 7c8ad3451..f5dcb5204 100644 --- a/kernel/arch/x86/include/asm/uaccess_32.h +++ b/kernel/arch/x86/include/asm/uaccess_32.h @@ -59,6 +59,10 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); return ret; + case 8: + __put_user_size(*(u64 *)from, (u64 __user *)to, + 8, ret, 8); + return ret; } } return __copy_to_user_ll(to, from, n); diff --git a/kernel/arch/x86/include/asm/user.h b/kernel/arch/x86/include/asm/user.h index ccab4af16..59a54e869 100644 --- a/kernel/arch/x86/include/asm/user.h +++ b/kernel/arch/x86/include/asm/user.h @@ -14,8 +14,8 @@ struct user_ymmh_regs { __u32 ymmh_space[64]; }; -struct user_xsave_hdr { - __u64 xstate_bv; +struct user_xstate_header { + __u64 xfeatures; __u64 reserved1[2]; __u64 reserved2[5]; }; @@ -41,11 +41,11 @@ struct user_xsave_hdr { * particular process/thread. * * Also when the user modifies certain state FP/SSE/etc through the - * ptrace interface, they must ensure that the xsave_hdr.xstate_bv + * ptrace interface, they must ensure that the header.xfeatures * bytes[512..519] of the memory layout are updated correspondingly. * i.e., for example when FP state is modified to a non-init state, - * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to - * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc. + * header.xfeatures's bit 0 must be set to '1', when SSE is modified to + * non-init state, header.xfeatures's bit 1 must to be set to '1', etc. */ #define USER_XSTATE_FX_SW_WORDS 6 #define USER_XSTATE_XCR0_WORD 0 @@ -55,7 +55,7 @@ struct user_xstateregs { __u64 fpx_space[58]; __u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS]; } i387; - struct user_xsave_hdr xsave_hdr; + struct user_xstate_header header; struct user_ymmh_regs ymmh; /* further processor state extensions go here */ }; diff --git a/kernel/arch/x86/include/asm/uv/uv_hub.h b/kernel/arch/x86/include/asm/uv/uv_hub.h index c2729abe0..01ec643ce 100644 --- a/kernel/arch/x86/include/asm/uv/uv_hub.h +++ b/kernel/arch/x86/include/asm/uv/uv_hub.h @@ -609,7 +609,7 @@ struct uv_cpu_nmi_s { DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi); -#define uv_hub_nmi (uv_cpu_nmi.hub) +#define uv_hub_nmi this_cpu_read(uv_cpu_nmi.hub) #define uv_cpu_nmi_per(cpu) (per_cpu(uv_cpu_nmi, cpu)) #define uv_hub_nmi_per(cpu) (uv_cpu_nmi_per(cpu).hub) diff --git a/kernel/arch/x86/include/asm/vdso.h b/kernel/arch/x86/include/asm/vdso.h index 8021bd28c..756de9190 100644 --- a/kernel/arch/x86/include/asm/vdso.h +++ b/kernel/arch/x86/include/asm/vdso.h @@ -26,7 +26,7 @@ struct vdso_image { long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; long sym___kernel_vsyscall; - long sym_VDSO32_SYSENTER_RETURN; + long sym_int80_landing_pad; }; #ifdef CONFIG_X86_64 @@ -38,13 +38,7 @@ extern const struct vdso_image vdso_image_x32; #endif #if defined CONFIG_X86_32 || defined CONFIG_COMPAT -extern const struct vdso_image vdso_image_32_int80; -#ifdef CONFIG_COMPAT -extern const struct vdso_image vdso_image_32_syscall; -#endif -extern const struct vdso_image vdso_image_32_sysenter; - -extern const struct vdso_image *selected_vdso32; +extern const struct vdso_image vdso_image_32; #endif extern void __init init_vdso_image(const struct vdso_image *image); diff --git a/kernel/arch/x86/include/asm/vm86.h b/kernel/arch/x86/include/asm/vm86.h index 1d8de3f3f..1e491f3af 100644 --- a/kernel/arch/x86/include/asm/vm86.h +++ b/kernel/arch/x86/include/asm/vm86.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_VM86_H #define _ASM_X86_VM86_H - #include <asm/ptrace.h> #include <uapi/asm/vm86.h> @@ -28,43 +27,49 @@ struct kernel_vm86_regs { unsigned short gs, __gsh; }; -struct kernel_vm86_struct { - struct kernel_vm86_regs regs; -/* - * the below part remains on the kernel stack while we are in VM86 mode. - * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we - * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above - * 'struct kernel_vm86_regs' with the then actual values. - * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct' - * in kernelspace, hence we need not reget the data from userspace. - */ -#define VM86_TSS_ESP0 flags +struct vm86 { + struct vm86plus_struct __user *user_vm86; + struct pt_regs regs32; + unsigned long veflags; + unsigned long veflags_mask; + unsigned long saved_sp0; + unsigned long flags; unsigned long screen_bitmap; unsigned long cpu_type; struct revectored_struct int_revectored; struct revectored_struct int21_revectored; struct vm86plus_info_struct vm86plus; - struct pt_regs *regs32; /* here we save the pointer to the old regs */ -/* - * The below is not part of the structure, but the stack layout continues - * this way. In front of 'return-eip' may be some data, depending on - * compilation, so we don't rely on this and save the pointer to 'oldregs' - * in 'regs32' above. - * However, with GCC-2.7.2 and the current CFLAGS you see exactly this: - - long return-eip; from call to vm86() - struct pt_regs oldregs; user space registers as saved by syscall - */ }; #ifdef CONFIG_VM86 void handle_vm86_fault(struct kernel_vm86_regs *, long); int handle_vm86_trap(struct kernel_vm86_regs *, long, int); -struct pt_regs *save_v86_state(struct kernel_vm86_regs *); +void save_v86_state(struct kernel_vm86_regs *, int); struct task_struct; + +#define free_vm86(t) do { \ + struct thread_struct *__t = (t); \ + if (__t->vm86 != NULL) { \ + kfree(__t->vm86); \ + __t->vm86 = NULL; \ + } \ +} while (0) + +/* + * Support for VM86 programs to request interrupts for + * real mode hardware drivers: + */ +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 + +static inline int invalid_vm86_irq(int irq) +{ + return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; +} + void release_vm86_irqs(struct task_struct *); #else @@ -77,6 +82,10 @@ static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c) return 0; } +static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { } + +#define free_vm86(t) do { } while(0) + #endif /* CONFIG_VM86 */ #endif /* _ASM_X86_VM86_H */ diff --git a/kernel/arch/x86/include/asm/vmx.h b/kernel/arch/x86/include/asm/vmx.h index da772edd1..14c63c7e8 100644 --- a/kernel/arch/x86/include/asm/vmx.h +++ b/kernel/arch/x86/include/asm/vmx.h @@ -47,6 +47,7 @@ #define CPU_BASED_MOV_DR_EXITING 0x00800000 #define CPU_BASED_UNCOND_IO_EXITING 0x01000000 #define CPU_BASED_USE_IO_BITMAPS 0x02000000 +#define CPU_BASED_MONITOR_TRAP_FLAG 0x08000000 #define CPU_BASED_USE_MSR_BITMAPS 0x10000000 #define CPU_BASED_MONITOR_EXITING 0x20000000 #define CPU_BASED_PAUSE_EXITING 0x40000000 @@ -71,7 +72,8 @@ #define SECONDARY_EXEC_SHADOW_VMCS 0x00004000 #define SECONDARY_EXEC_ENABLE_PML 0x00020000 #define SECONDARY_EXEC_XSAVES 0x00100000 - +#define SECONDARY_EXEC_PCOMMIT 0x00200000 +#define SECONDARY_EXEC_TSC_SCALING 0x02000000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 #define PIN_BASED_NMI_EXITING 0x00000008 @@ -166,6 +168,8 @@ enum vmcs_field { VMWRITE_BITMAP = 0x00002028, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, + TSC_MULTIPLIER = 0x00002032, + TSC_MULTIPLIER_HIGH = 0x00002033, GUEST_PHYSICAL_ADDRESS = 0x00002400, GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401, VMCS_LINK_POINTER = 0x00002800, @@ -367,29 +371,29 @@ enum vmcs_field { #define TYPE_PHYSICAL_APIC_EVENT (10 << 12) #define TYPE_PHYSICAL_APIC_INST (15 << 12) -/* segment AR */ -#define SEGMENT_AR_L_MASK (1 << 13) - -#define AR_TYPE_ACCESSES_MASK 1 -#define AR_TYPE_READABLE_MASK (1 << 1) -#define AR_TYPE_WRITEABLE_MASK (1 << 2) -#define AR_TYPE_CODE_MASK (1 << 3) -#define AR_TYPE_MASK 0x0f -#define AR_TYPE_BUSY_64_TSS 11 -#define AR_TYPE_BUSY_32_TSS 11 -#define AR_TYPE_BUSY_16_TSS 3 -#define AR_TYPE_LDT 2 - -#define AR_UNUSABLE_MASK (1 << 16) -#define AR_S_MASK (1 << 4) -#define AR_P_MASK (1 << 7) -#define AR_L_MASK (1 << 13) -#define AR_DB_MASK (1 << 14) -#define AR_G_MASK (1 << 15) -#define AR_DPL_SHIFT 5 -#define AR_DPL(ar) (((ar) >> AR_DPL_SHIFT) & 3) - -#define AR_RESERVD_MASK 0xfffe0f00 +/* segment AR in VMCS -- these are different from what LAR reports */ +#define VMX_SEGMENT_AR_L_MASK (1 << 13) + +#define VMX_AR_TYPE_ACCESSES_MASK 1 +#define VMX_AR_TYPE_READABLE_MASK (1 << 1) +#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2) +#define VMX_AR_TYPE_CODE_MASK (1 << 3) +#define VMX_AR_TYPE_MASK 0x0f +#define VMX_AR_TYPE_BUSY_64_TSS 11 +#define VMX_AR_TYPE_BUSY_32_TSS 11 +#define VMX_AR_TYPE_BUSY_16_TSS 3 +#define VMX_AR_TYPE_LDT 2 + +#define VMX_AR_UNUSABLE_MASK (1 << 16) +#define VMX_AR_S_MASK (1 << 4) +#define VMX_AR_P_MASK (1 << 7) +#define VMX_AR_L_MASK (1 << 13) +#define VMX_AR_DB_MASK (1 << 14) +#define VMX_AR_G_MASK (1 << 15) +#define VMX_AR_DPL_SHIFT 5 +#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3) + +#define VMX_AR_RESERVD_MASK 0xfffe0f00 #define TSS_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 0) #define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 1) @@ -415,6 +419,7 @@ enum vmcs_field { #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) +#define VMX_VPID_INVVPID_BIT (1ull << 0) /* (32 - 32) */ #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT (1ull << 9) /* (41 - 32) */ #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */ diff --git a/kernel/arch/x86/include/asm/x86_init.h b/kernel/arch/x86/include/asm/x86_init.h index f58a9c7a3..cd0fc0cc7 100644 --- a/kernel/arch/x86/include/asm/x86_init.h +++ b/kernel/arch/x86/include/asm/x86_init.h @@ -1,7 +1,6 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H -#include <asm/pgtable_types.h> #include <asm/bootparam.h> struct mpc_bus; @@ -171,38 +170,17 @@ struct x86_platform_ops { }; struct pci_dev; -struct msi_msg; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); - void (*compose_msi_msg)(struct pci_dev *dev, unsigned int irq, - unsigned int dest, struct msi_msg *msg, - u8 hpet_id); void (*teardown_msi_irq)(unsigned int irq); void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev); - int (*setup_hpet_msi)(unsigned int irq, unsigned int id); }; -struct IO_APIC_route_entry; -struct io_apic_irq_attr; -struct irq_data; -struct cpumask; - struct x86_io_apic_ops { - void (*init) (void); unsigned int (*read) (unsigned int apic, unsigned int reg); - void (*write) (unsigned int apic, unsigned int reg, unsigned int value); - void (*modify) (unsigned int apic, unsigned int reg, unsigned int value); void (*disable)(void); - void (*print_entries)(unsigned int apic, unsigned int nr_entries); - int (*set_affinity)(struct irq_data *data, - const struct cpumask *mask, - bool force); - int (*setup_entry)(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr); - void (*eoi_ioapic_pin)(int apic, int pin, int vector); }; extern struct x86_init_ops x86_init; diff --git a/kernel/arch/x86/include/asm/xcr.h b/kernel/arch/x86/include/asm/xcr.h deleted file mode 100644 index f2cba4e79..000000000 --- a/kernel/arch/x86/include/asm/xcr.h +++ /dev/null @@ -1,49 +0,0 @@ -/* -*- linux-c -*- ------------------------------------------------------- * - * - * Copyright 2008 rPath, Inc. - All Rights Reserved - * - * This file is part of the Linux kernel, and is made available under - * the terms of the GNU General Public License version 2 or (at your - * option) any later version; incorporated herein by reference. - * - * ----------------------------------------------------------------------- */ - -/* - * asm-x86/xcr.h - * - * Definitions for the eXtended Control Register instructions - */ - -#ifndef _ASM_X86_XCR_H -#define _ASM_X86_XCR_H - -#define XCR_XFEATURE_ENABLED_MASK 0x00000000 - -#ifdef __KERNEL__ -# ifndef __ASSEMBLY__ - -#include <linux/types.h> - -static inline u64 xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ - : "=a" (eax), "=d" (edx) - : "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ - : : "a" (eax), "d" (edx), "c" (index)); -} - -# endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_XCR_H */ diff --git a/kernel/arch/x86/include/asm/xen/events.h b/kernel/arch/x86/include/asm/xen/events.h index 608a79d5a..e6911caf5 100644 --- a/kernel/arch/x86/include/asm/xen/events.h +++ b/kernel/arch/x86/include/asm/xen/events.h @@ -20,4 +20,15 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) /* No need for a barrier -- XCHG is a barrier on x86. */ #define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) +extern int xen_have_vector_callback; + +/* + * Events delivered via platform PCI interrupts are always + * routed to vcpu 0 and hence cannot be rebound. + */ +static inline bool xen_support_evtchn_rebind(void) +{ + return (!xen_hvm_domain() || xen_have_vector_callback); +} + #endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/kernel/arch/x86/include/asm/xen/hypercall.h b/kernel/arch/x86/include/asm/xen/hypercall.h index ca08a27b9..4c20dd333 100644 --- a/kernel/arch/x86/include/asm/xen/hypercall.h +++ b/kernel/arch/x86/include/asm/xen/hypercall.h @@ -336,10 +336,10 @@ HYPERVISOR_update_descriptor(u64 ma, u64 desc) return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); } -static inline int +static inline long HYPERVISOR_memory_op(unsigned int cmd, void *arg) { - return _hypercall2(int, memory_op, cmd, arg); + return _hypercall2(long, memory_op, cmd, arg); } static inline int @@ -465,6 +465,12 @@ HYPERVISOR_tmem_op( return _hypercall1(int, tmem_op, op); } +static inline int +HYPERVISOR_xenpmu_op(unsigned int op, void *arg) +{ + return _hypercall2(int, xenpmu_op, op, arg); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/kernel/arch/x86/include/asm/xen/hypervisor.h b/kernel/arch/x86/include/asm/xen/hypervisor.h index d866959e5..8b2d4bea9 100644 --- a/kernel/arch/x86/include/asm/xen/hypervisor.h +++ b/kernel/arch/x86/include/asm/xen/hypervisor.h @@ -57,4 +57,9 @@ static inline bool xen_x2apic_para_available(void) } #endif +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num); +void xen_arch_unregister_cpu(int num); +#endif + #endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/kernel/arch/x86/include/asm/xen/interface.h b/kernel/arch/x86/include/asm/xen/interface.h index 3400dbaec..62ca03ef5 100644 --- a/kernel/arch/x86/include/asm/xen/interface.h +++ b/kernel/arch/x86/include/asm/xen/interface.h @@ -3,12 +3,38 @@ * * Guest OS interface to x86 Xen. * - * Copyright (c) 2004, K A Fraser + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004-2006, K A Fraser */ #ifndef _ASM_X86_XEN_INTERFACE_H #define _ASM_X86_XEN_INTERFACE_H +/* + * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field + * in a struct in memory. + * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an + * hypercall argument. + * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but + * they might not be on other architectures. + */ #ifdef __XEN__ #define __DEFINE_GUEST_HANDLE(name, type) \ typedef struct { type *p; } __guest_handle_ ## name @@ -88,13 +114,16 @@ DEFINE_GUEST_HANDLE(xen_ulong_t); * start of the GDT because some stupid OSes export hard-coded selector values * in their ABI. These hard-coded values are always near the start of the GDT, * so Xen places itself out of the way, at the far end of the GDT. + * + * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op */ #define FIRST_RESERVED_GDT_PAGE 14 #define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) /* - * Send an array of these to HYPERVISOR_set_trap_table() + * Send an array of these to HYPERVISOR_set_trap_table(). + * Terminate the array with a sentinel entry, with traps[].address==0. * The privilege level specifies which modes may enter a trap via a software * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate * privilege levels as follows: @@ -118,10 +147,41 @@ struct trap_info { DEFINE_GUEST_HANDLE_STRUCT(trap_info); struct arch_shared_info { - unsigned long max_pfn; /* max pfn that appears in table */ - /* Frame containing list of mfns containing list of mfns containing p2m. */ - unsigned long pfn_to_mfn_frame_list_list; - unsigned long nmi_reason; + /* + * Number of valid entries in the p2m table(s) anchored at + * pfn_to_mfn_frame_list_list and/or p2m_vaddr. + */ + unsigned long max_pfn; + /* + * Frame containing list of mfns containing list of mfns containing p2m. + * A value of 0 indicates it has not yet been set up, ~0 indicates it + * has been set to invalid e.g. due to the p2m being too large for the + * 3-level p2m tree. In this case the linear mapper p2m list anchored + * at p2m_vaddr is to be used. + */ + xen_pfn_t pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; + /* + * Following three fields are valid if p2m_cr3 contains a value + * different from 0. + * p2m_cr3 is the root of the address space where p2m_vaddr is valid. + * p2m_cr3 is in the same format as a cr3 value in the vcpu register + * state and holds the folded machine frame number (via xen_pfn_to_cr3) + * of a L3 or L4 page table. + * p2m_vaddr holds the virtual address of the linear p2m list. All + * entries in the range [0...max_pfn[ are accessible via this pointer. + * p2m_generation will be incremented by the guest before and after each + * change of the mappings of the p2m list. p2m_generation starts at 0 + * and a value with the least significant bit set indicates that a + * mapping update is in progress. This allows guest external software + * (e.g. in Dom0) to verify that read mappings are consistent and + * whether they have changed since the last check. + * Modifying a p2m element in the linear p2m list is allowed via an + * atomic write only. + */ + unsigned long p2m_cr3; /* cr3 value of the p2m address space */ + unsigned long p2m_vaddr; /* virtual address of the p2m list */ + unsigned long p2m_generation; /* generation count of p2m mapping */ }; #endif /* !__ASSEMBLY__ */ @@ -137,13 +197,31 @@ struct arch_shared_info { /* * The following is all CPU context. Note that the fpu_ctxt block is filled * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + * + * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise + * for HVM and PVH guests, not all information in this structure is updated: + * + * - For HVM guests, the structures read include: fpu_ctxt (if + * VGCT_I387_VALID is set), flags, user_regs, debugreg[*] + * + * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to + * set cr3. All other fields not used should be set to 0. */ struct vcpu_guest_context { /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */ -#define VGCF_I387_VALID (1<<0) -#define VGCF_HVM_GUEST (1<<1) -#define VGCF_IN_KERNEL (1<<2) +#define VGCF_I387_VALID (1<<0) +#define VGCF_IN_KERNEL (1<<2) +#define _VGCF_i387_valid 0 +#define VGCF_i387_valid (1<<_VGCF_i387_valid) +#define _VGCF_in_kernel 2 +#define VGCF_in_kernel (1<<_VGCF_in_kernel) +#define _VGCF_failsafe_disables_events 3 +#define VGCF_failsafe_disables_events (1<<_VGCF_failsafe_disables_events) +#define _VGCF_syscall_disables_events 4 +#define VGCF_syscall_disables_events (1<<_VGCF_syscall_disables_events) +#define _VGCF_online 5 +#define VGCF_online (1<<_VGCF_online) unsigned long flags; /* VGCF_* flags */ struct cpu_user_regs user_regs; /* User-level CPU registers */ struct trap_info trap_ctxt[256]; /* Virtual IDT */ @@ -172,6 +250,129 @@ struct vcpu_guest_context { #endif }; DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context); + +/* AMD PMU registers and structures */ +struct xen_pmu_amd_ctxt { + /* + * Offsets to counter and control MSRs (relative to xen_pmu_arch.c.amd). + * For PV(H) guests these fields are RO. + */ + uint32_t counters; + uint32_t ctrls; + + /* Counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; + +/* Intel PMU registers and structures */ +struct xen_pmu_cntr_pair { + uint64_t counter; + uint64_t control; +}; + +struct xen_pmu_intel_ctxt { + /* + * Offsets to fixed and architectural counter MSRs (relative to + * xen_pmu_arch.c.intel). + * For PV(H) guests these fields are RO. + */ + uint32_t fixed_counters; + uint32_t arch_counters; + + /* PMU registers */ + uint64_t global_ctrl; + uint64_t global_ovf_ctrl; + uint64_t global_status; + uint64_t fixed_ctrl; + uint64_t ds_area; + uint64_t pebs_enable; + uint64_t debugctl; + + /* Fixed and architectural counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; + +/* Sampled domain's registers */ +struct xen_pmu_regs { + uint64_t ip; + uint64_t sp; + uint64_t flags; + uint16_t cs; + uint16_t ss; + uint8_t cpl; + uint8_t pad[3]; +}; + +/* PMU flags */ +#define PMU_CACHED (1<<0) /* PMU MSRs are cached in the context */ +#define PMU_SAMPLE_USER (1<<1) /* Sample is from user or kernel mode */ +#define PMU_SAMPLE_REAL (1<<2) /* Sample is from realmode */ +#define PMU_SAMPLE_PV (1<<3) /* Sample from a PV guest */ + +/* + * Architecture-specific information describing state of the processor at + * the time of PMU interrupt. + * Fields of this structure marked as RW for guest should only be written by + * the guest when PMU_CACHED bit in pmu_flags is set (which is done by the + * hypervisor during PMU interrupt). Hypervisor will read updated data in + * XENPMU_flush hypercall and clear PMU_CACHED bit. + */ +struct xen_pmu_arch { + union { + /* + * Processor's registers at the time of interrupt. + * WO for hypervisor, RO for guests. + */ + struct xen_pmu_regs regs; + /* + * Padding for adding new registers to xen_pmu_regs in + * the future + */ +#define XENPMU_REGS_PAD_SZ 64 + uint8_t pad[XENPMU_REGS_PAD_SZ]; + } r; + + /* WO for hypervisor, RO for guest */ + uint64_t pmu_flags; + + /* + * APIC LVTPC register. + * RW for both hypervisor and guest. + * Only APIC_LVT_MASKED bit is loaded by the hypervisor into hardware + * during XENPMU_flush or XENPMU_lvtpc_set. + */ + union { + uint32_t lapic_lvtpc; + uint64_t pad; + } l; + + /* + * Vendor-specific PMU registers. + * RW for both hypervisor and guest (see exceptions above). + * Guest's updates to this field are verified and then loaded by the + * hypervisor into hardware during XENPMU_flush + */ + union { + struct xen_pmu_amd_ctxt amd; + struct xen_pmu_intel_ctxt intel; + + /* + * Padding for contexts (fixed parts only, does not include + * MSR banks that are specified by offsets) + */ +#define XENPMU_CTXT_PAD_SZ 128 + uint8_t pad[XENPMU_CTXT_PAD_SZ]; + } c; +}; + #endif /* !__ASSEMBLY__ */ /* diff --git a/kernel/arch/x86/include/asm/xen/page.h b/kernel/arch/x86/include/asm/xen/page.h index c44a5d53e..f5fb840b4 100644 --- a/kernel/arch/x86/include/asm/xen/page.h +++ b/kernel/arch/x86/include/asm/xen/page.h @@ -12,7 +12,7 @@ #include <asm/pgtable.h> #include <xen/interface/xen.h> -#include <xen/grant_table.h> +#include <xen/interface/grant_table.h> #include <xen/features.h> /* Xen machine address */ @@ -35,9 +35,7 @@ typedef struct xpaddr { #define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) #define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT) -/* Maximum amount of memory we can handle in a domain in pages */ -#define MAX_DOMAIN_PAGES \ - ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) +#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) extern unsigned long *machine_to_phys_mapping; extern unsigned long machine_to_phys_nr; @@ -45,11 +43,13 @@ extern unsigned long *xen_p2m_addr; extern unsigned long xen_p2m_size; extern unsigned long xen_max_p2m_pfn; +extern int xen_alloc_p2m_entry(unsigned long pfn); + extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); -extern unsigned long set_phys_range_identity(unsigned long pfn_s, - unsigned long pfn_e); +extern unsigned long __init set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e); extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, struct gnttab_map_grant_ref *kmap_ops, @@ -103,6 +103,11 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn) { unsigned long mfn; + /* + * Some x86 code are still using pfn_to_mfn instead of + * pfn_to_mfn. This will have to be removed when we figured + * out which call. + */ if (xen_feature(XENFEAT_auto_translated_physmap)) return pfn; @@ -149,6 +154,11 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) { unsigned long pfn; + /* + * Some x86 code are still using mfn_to_pfn instead of + * gfn_to_pfn. This will have to be removed when we figure + * out which call. + */ if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; @@ -178,6 +188,27 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset); } +/* Pseudo-physical <-> Guest conversion */ +static inline unsigned long pfn_to_gfn(unsigned long pfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return pfn; + else + return pfn_to_mfn(pfn); +} + +static inline unsigned long gfn_to_pfn(unsigned long gfn) +{ + if (xen_feature(XENFEAT_auto_translated_physmap)) + return gfn; + else + return mfn_to_pfn(gfn); +} + +/* Pseudo-physical <-> Bus conversion */ +#define pfn_to_bfn(pfn) pfn_to_gfn(pfn) +#define bfn_to_pfn(bfn) gfn_to_pfn(bfn) + /* * We detect special mappings in one of two ways: * 1. If the MFN is an I/O page then Xen will set the m2p entry @@ -198,7 +229,7 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) * require. In all the cases we care about, the FOREIGN_FRAME bit is * masked (e.g., pfn_to_mfn()) so behaviour there is correct. */ -static inline unsigned long mfn_to_local_pfn(unsigned long mfn) +static inline unsigned long bfn_to_local_pfn(unsigned long mfn) { unsigned long pfn; @@ -217,6 +248,10 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) #define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) +/* VIRT <-> GUEST conversion */ +#define virt_to_gfn(v) (pfn_to_gfn(virt_to_pfn(v))) +#define gfn_to_virt(g) (__va(gfn_to_pfn(g) << PAGE_SHIFT)) + static inline unsigned long pte_mfn(pte_t pte) { return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; @@ -263,8 +298,8 @@ void make_lowmem_page_readwrite(void *vaddr); #define xen_unmap(cookie) iounmap((cookie)) static inline bool xen_arch_need_swiotlb(struct device *dev, - unsigned long pfn, - unsigned long mfn) + phys_addr_t phys, + dma_addr_t dev_addr) { return false; } diff --git a/kernel/arch/x86/include/asm/xor.h b/kernel/arch/x86/include/asm/xor.h index d8829751b..1f5c5161e 100644 --- a/kernel/arch/x86/include/asm/xor.h +++ b/kernel/arch/x86/include/asm/xor.h @@ -36,7 +36,7 @@ * no advantages to be gotten from x86-64 here anyways. */ -#include <asm/i387.h> +#include <asm/fpu/api.h> #ifdef CONFIG_X86_32 /* reduce register pressure */ diff --git a/kernel/arch/x86/include/asm/xor_32.h b/kernel/arch/x86/include/asm/xor_32.h index ce05722e3..5a08bc8bf 100644 --- a/kernel/arch/x86/include/asm/xor_32.h +++ b/kernel/arch/x86/include/asm/xor_32.h @@ -26,7 +26,7 @@ #define XO3(x, y) " pxor 8*("#x")(%4), %%mm"#y" ;\n" #define XO4(x, y) " pxor 8*("#x")(%5), %%mm"#y" ;\n" -#include <asm/i387.h> +#include <asm/fpu/api.h> static void xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) diff --git a/kernel/arch/x86/include/asm/xor_avx.h b/kernel/arch/x86/include/asm/xor_avx.h index 492b29802..7c0a517ec 100644 --- a/kernel/arch/x86/include/asm/xor_avx.h +++ b/kernel/arch/x86/include/asm/xor_avx.h @@ -18,7 +18,7 @@ #ifdef CONFIG_AS_AVX #include <linux/compiler.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #define BLOCK4(i) \ BLOCK(32 * i, 0) \ diff --git a/kernel/arch/x86/include/asm/xsave.h b/kernel/arch/x86/include/asm/xsave.h deleted file mode 100644 index c9a6d68b8..000000000 --- a/kernel/arch/x86/include/asm/xsave.h +++ /dev/null @@ -1,257 +0,0 @@ -#ifndef __ASM_X86_XSAVE_H -#define __ASM_X86_XSAVE_H - -#include <linux/types.h> -#include <asm/processor.h> - -#define XSTATE_CPUID 0x0000000d - -#define XSTATE_FP 0x1 -#define XSTATE_SSE 0x2 -#define XSTATE_YMM 0x4 -#define XSTATE_BNDREGS 0x8 -#define XSTATE_BNDCSR 0x10 -#define XSTATE_OPMASK 0x20 -#define XSTATE_ZMM_Hi256 0x40 -#define XSTATE_Hi16_ZMM 0x80 - -#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) -#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) -/* Bit 63 of XCR0 is reserved for future expansion */ -#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) - -#define FXSAVE_SIZE 512 - -#define XSAVE_HDR_SIZE 64 -#define XSAVE_HDR_OFFSET FXSAVE_SIZE - -#define XSAVE_YMM_SIZE 256 -#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) - -/* Supported features which support lazy state saving */ -#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ - | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) - -/* Supported features which require eager state saving */ -#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) - -/* All currently supported features */ -#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) - -#ifdef CONFIG_X86_64 -#define REX_PREFIX "0x48, " -#else -#define REX_PREFIX -#endif - -extern unsigned int xstate_size; -extern u64 pcntxt_mask; -extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern struct xsave_struct *init_xstate_buf; - -extern void xsave_init(void); -extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); -extern int init_fpu(struct task_struct *child); - -/* These macros all use (%edi)/(%rdi) as the single memory argument. */ -#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" -#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" -#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" -#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" -#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" - -#define xstate_fault ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err) - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * Save processor xstate to xsave area. - */ -static inline int xsave_state(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [fx] "D" (fx), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Restore processor xstate from xsave area. - */ -static inline int xrstor_state(struct xsave_struct *fx, u64 mask) -{ - int err = 0; - u32 lmask = mask; - u32 hmask = mask >> 32; - - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Save xstate context for old process during context switch. - */ -static inline void fpu_xsave(struct fpu *fpu) -{ - xsave_state(&fpu->state->xsave, -1); -} - -/* - * Restore xstate context for new process during context switch. - */ -static inline int fpu_xrstor_checking(struct xsave_struct *fx) -{ - return xrstor_state(fx, -1); -} - -/* - * Save xstate to user space xsave area. - * - * We don't use modified optimization because xrstor/xrstors might track - * a different application. - * - * We don't use compacted format xsave area for - * backward compatibility for old applications which don't understand - * compacted format of xsave area. - */ -static inline int xsave_user(struct xsave_struct __user *buf) -{ - int err; - - /* - * Clear the xsave header first, so that reserved fields are - * initialized to zero. - */ - err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr)); - if (unlikely(err)) - return -EFAULT; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (buf), "a" (-1), "d" (-1), "0" (0) - : "memory"); - return err; -} - -/* - * Restore xstate from user space xsave area. - */ -static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) -{ - int err = 0; - struct xsave_struct *xstate = ((__force struct xsave_struct *)buf); - u32 lmask = mask; - u32 hmask = mask >> 32; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0) - : "memory"); /* memory required? */ - return err; -} - -void *get_xsave_addr(struct xsave_struct *xsave, int xstate); -void setup_xstate_comp(void); - -#endif diff --git a/kernel/arch/x86/include/uapi/asm/bitsperlong.h b/kernel/arch/x86/include/uapi/asm/bitsperlong.h index b0ae1c4dc..217909b4d 100644 --- a/kernel/arch/x86/include/uapi/asm/bitsperlong.h +++ b/kernel/arch/x86/include/uapi/asm/bitsperlong.h @@ -1,7 +1,7 @@ #ifndef __ASM_X86_BITSPERLONG_H #define __ASM_X86_BITSPERLONG_H -#ifdef __x86_64__ +#if defined(__x86_64__) && !defined(__ILP32__) # define __BITS_PER_LONG 64 #else # define __BITS_PER_LONG 32 diff --git a/kernel/arch/x86/include/uapi/asm/bootparam.h b/kernel/arch/x86/include/uapi/asm/bootparam.h index ab456dc23..329254373 100644 --- a/kernel/arch/x86/include/uapi/asm/bootparam.h +++ b/kernel/arch/x86/include/uapi/asm/bootparam.h @@ -120,7 +120,7 @@ struct boot_params { __u8 _pad3[16]; /* 0x070 */ __u8 hd0_info[16]; /* obsolete! */ /* 0x080 */ __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ - struct sys_desc_table sys_desc_table; /* 0x0a0 */ + struct sys_desc_table sys_desc_table; /* obsolete! */ /* 0x0a0 */ struct olpc_ofw_header olpc_ofw_header; /* 0x0b0 */ __u32 ext_ramdisk_image; /* 0x0c0 */ __u32 ext_ramdisk_size; /* 0x0c4 */ diff --git a/kernel/arch/x86/include/uapi/asm/e820.h b/kernel/arch/x86/include/uapi/asm/e820.h index 960a8a9dc..9dafe59cf 100644 --- a/kernel/arch/x86/include/uapi/asm/e820.h +++ b/kernel/arch/x86/include/uapi/asm/e820.h @@ -32,11 +32,12 @@ #define E820_ACPI 3 #define E820_NVS 4 #define E820_UNUSABLE 5 +#define E820_PMEM 7 /* * This is a non-standardized way to represent ADR or NVDIMM regions that * persist over a reboot. The kernel will ignore their special capabilities - * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * unless the CONFIG_X86_PMEM_LEGACY option is set. * * ( Note that older platforms also used 6 for the same type of memory, * but newer versions switched to 12 as 6 was assigned differently. Some diff --git a/kernel/arch/x86/include/uapi/asm/hyperv.h b/kernel/arch/x86/include/uapi/asm/hyperv.h index ce6068dbc..040d4083c 100644 --- a/kernel/arch/x86/include/uapi/asm/hyperv.h +++ b/kernel/arch/x86/include/uapi/asm/hyperv.h @@ -27,6 +27,8 @@ #define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0) /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/ #define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) +/* Partition reference TSC MSR is available */ +#define HV_X64_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) /* A partition's reference time stamp counter (TSC) page */ #define HV_X64_MSR_REFERENCE_TSC 0x40000021 @@ -108,6 +110,8 @@ #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4) /* Support for a virtual guest idle state is available */ #define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5) +/* Guest crash data handler available */ +#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10) /* * Implementation recommendations. Indicates which behaviors the hypervisor @@ -149,6 +153,12 @@ /* MSR used to provide vcpu index */ #define HV_X64_MSR_VP_INDEX 0x40000002 +/* MSR used to reset the guest OS. */ +#define HV_X64_MSR_RESET 0x40000003 + +/* MSR used to provide vcpu runtime in 100ns units */ +#define HV_X64_MSR_VP_RUNTIME 0x40000010 + /* MSR used to read the per-partition time reference counter */ #define HV_X64_MSR_TIME_REF_COUNT 0x40000020 @@ -199,6 +209,17 @@ #define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 #define HV_X64_MSR_STIMER3_COUNT 0x400000B7 +/* Hyper-V guest crash notification MSR's */ +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 +#define HV_X64_MSR_CRASH_CTL_NOTIFY (1ULL << 63) +#define HV_X64_MSR_CRASH_PARAMS \ + (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ @@ -236,4 +257,16 @@ typedef struct _HV_REFERENCE_TSC_PAGE { __s64 tsc_offset; } HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE; +/* Define the number of synthetic interrupt sources. */ +#define HV_SYNIC_SINT_COUNT (16) +/* Define the expected SynIC version. */ +#define HV_SYNIC_VERSION_1 (0x1) + +#define HV_SYNIC_CONTROL_ENABLE (1ULL << 0) +#define HV_SYNIC_SIMP_ENABLE (1ULL << 0) +#define HV_SYNIC_SIEFP_ENABLE (1ULL << 0) +#define HV_SYNIC_SINT_MASKED (1ULL << 16) +#define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17) +#define HV_SYNIC_SINT_VECTOR_MASK (0xFF) + #endif diff --git a/kernel/arch/x86/include/uapi/asm/kvm.h b/kernel/arch/x86/include/uapi/asm/kvm.h index d7dcef58a..cd54147cb 100644 --- a/kernel/arch/x86/include/uapi/asm/kvm.h +++ b/kernel/arch/x86/include/uapi/asm/kvm.h @@ -106,6 +106,8 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_IOAPIC 2 #define KVM_NR_IRQCHIPS 3 +#define KVM_RUN_X86_SMM (1 << 0) + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* out (KVM_GET_REGS) / in (KVM_SET_REGS) */ @@ -281,6 +283,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002 #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 +#define KVM_VCPUEVENT_VALID_SMM 0x00000008 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -309,7 +312,13 @@ struct kvm_vcpu_events { } nmi; __u32 sipi_vector; __u32 flags; - __u32 reserved[10]; + struct { + __u8 smm; + __u8 pending; + __u8 smm_inside_nmi; + __u8 latched_init; + } smi; + __u32 reserved[9]; }; /* for KVM_GET/SET_DEBUGREGS */ @@ -345,4 +354,7 @@ struct kvm_xcrs { struct kvm_sync_regs { }; +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) + #endif /* _ASM_X86_KVM_H */ diff --git a/kernel/arch/x86/include/uapi/asm/mce.h b/kernel/arch/x86/include/uapi/asm/mce.h index a0eab85ce..03429da2f 100644 --- a/kernel/arch/x86/include/uapi/asm/mce.h +++ b/kernel/arch/x86/include/uapi/asm/mce.h @@ -2,7 +2,7 @@ #define _UAPI_ASM_X86_MCE_H #include <linux/types.h> -#include <asm/ioctls.h> +#include <linux/ioctl.h> /* Fields are zero when not available */ struct mce { @@ -15,7 +15,8 @@ struct mce { __u64 time; /* wall time_t when error was detected */ __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ - __u16 pad; + __u8 severity; + __u8 usable_addr; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/kernel/arch/x86/include/uapi/asm/msr.h b/kernel/arch/x86/include/uapi/asm/msr.h index 155e51048..c41f4fe25 100644 --- a/kernel/arch/x86/include/uapi/asm/msr.h +++ b/kernel/arch/x86/include/uapi/asm/msr.h @@ -1,8 +1,6 @@ #ifndef _UAPI_ASM_X86_MSR_H #define _UAPI_ASM_X86_MSR_H -#include <asm/msr-index.h> - #ifndef __ASSEMBLY__ #include <linux/types.h> diff --git a/kernel/arch/x86/include/uapi/asm/mtrr.h b/kernel/arch/x86/include/uapi/asm/mtrr.h index d0acb658c..7528dcf59 100644 --- a/kernel/arch/x86/include/uapi/asm/mtrr.h +++ b/kernel/arch/x86/include/uapi/asm/mtrr.h @@ -103,7 +103,7 @@ struct mtrr_state_type { #define MTRRIOC_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry) #define MTRRIOC_KILL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry) -/* These are the region types */ +/* MTRR memory types, which are defined in SDM */ #define MTRR_TYPE_UNCACHABLE 0 #define MTRR_TYPE_WRCOMB 1 /*#define MTRR_TYPE_ 2*/ @@ -113,5 +113,11 @@ struct mtrr_state_type { #define MTRR_TYPE_WRBACK 6 #define MTRR_NUM_TYPES 7 +/* + * Invalid MTRR memory type. mtrr_type_lookup() returns this value when + * MTRRs are disabled. Note, this value is allocated from the reserved + * values (0x7-0xff) of the MTRR memory types. + */ +#define MTRR_TYPE_INVALID 0xff #endif /* _UAPI_ASM_X86_MTRR_H */ diff --git a/kernel/arch/x86/include/uapi/asm/processor-flags.h b/kernel/arch/x86/include/uapi/asm/processor-flags.h index 180a0c3c2..79887abcb 100644 --- a/kernel/arch/x86/include/uapi/asm/processor-flags.h +++ b/kernel/arch/x86/include/uapi/asm/processor-flags.h @@ -37,8 +37,6 @@ #define X86_EFLAGS_VM _BITUL(X86_EFLAGS_VM_BIT) #define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */ #define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT) -#define X86_EFLAGS_AC_BIT 18 /* Alignment Check/Access Control */ -#define X86_EFLAGS_AC _BITUL(X86_EFLAGS_AC_BIT) #define X86_EFLAGS_VIF_BIT 19 /* Virtual Interrupt Flag */ #define X86_EFLAGS_VIF _BITUL(X86_EFLAGS_VIF_BIT) #define X86_EFLAGS_VIP_BIT 20 /* Virtual Interrupt Pending */ diff --git a/kernel/arch/x86/include/uapi/asm/sigcontext.h b/kernel/arch/x86/include/uapi/asm/sigcontext.h index d8b9f9081..d485232f1 100644 --- a/kernel/arch/x86/include/uapi/asm/sigcontext.h +++ b/kernel/arch/x86/include/uapi/asm/sigcontext.h @@ -1,221 +1,360 @@ #ifndef _UAPI_ASM_X86_SIGCONTEXT_H #define _UAPI_ASM_X86_SIGCONTEXT_H +/* + * Linux signal context definitions. The sigcontext includes a complex + * hierarchy of CPU and FPU state, available to user-space (on the stack) when + * a signal handler is executed. + * + * As over the years this ABI grew from its very simple roots towards + * supporting more and more CPU state organically, some of the details (which + * were rather clever hacks back in the days) became a bit quirky by today. + * + * The current ABI includes flexible provisions for future extensions, so we + * won't have to grow new quirks for quite some time. Promise! + */ + #include <linux/compiler.h> #include <linux/types.h> -#define FP_XSTATE_MAGIC1 0x46505853U -#define FP_XSTATE_MAGIC2 0x46505845U -#define FP_XSTATE_MAGIC2_SIZE sizeof(FP_XSTATE_MAGIC2) +#define FP_XSTATE_MAGIC1 0x46505853U +#define FP_XSTATE_MAGIC2 0x46505845U +#define FP_XSTATE_MAGIC2_SIZE sizeof(FP_XSTATE_MAGIC2) /* - * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame - * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes - * are used to extended the fpstate pointer in the sigcontext, which now - * includes the extended state information along with fpstate information. + * Bytes 464..511 in the current 512-byte layout of the FXSAVE/FXRSTOR frame + * are reserved for SW usage. On CPUs supporting XSAVE/XRSTOR, these bytes are + * used to extend the fpstate pointer in the sigcontext, which now includes the + * extended state information along with fpstate information. + * + * If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then there's a + * sw_reserved.extended_size bytes large extended context area present. (The + * last 32-bit word of this extended area (at the + * fpstate+extended_size-FP_XSTATE_MAGIC2_SIZE address) is set to + * FP_XSTATE_MAGIC2 so that you can sanity check your size calculations.) * - * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved - * area and FP_XSTATE_MAGIC2 at the end of memory layout - * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the - * extended state information in the memory layout pointed by the fpstate - * pointer in sigcontext. + * This extended area typically grows with newer CPUs that have larger and + * larger XSAVE areas. */ struct _fpx_sw_bytes { - __u32 magic1; /* FP_XSTATE_MAGIC1 */ - __u32 extended_size; /* total size of the layout referred by - * fpstate pointer in the sigcontext. - */ - __u64 xstate_bv; - /* feature bit mask (including fp/sse/extended - * state) that is present in the memory - * layout. - */ - __u32 xstate_size; /* actual xsave state size, based on the - * features saved in the layout. - * 'extended_size' will be greater than - * 'xstate_size'. - */ - __u32 padding[7]; /* for future use. */ + /* + * If set to FP_XSTATE_MAGIC1 then this is an xstate context. + * 0 if a legacy frame. + */ + __u32 magic1; + + /* + * Total size of the fpstate area: + * + * - if magic1 == 0 then it's sizeof(struct _fpstate) + * - if magic1 == FP_XSTATE_MAGIC1 then it's sizeof(struct _xstate) + * plus extensions (if any) + */ + __u32 extended_size; + + /* + * Feature bit mask (including FP/SSE/extended state) that is present + * in the memory layout: + */ + __u64 xfeatures; + + /* + * Actual XSAVE state size, based on the xfeatures saved in the layout. + * 'extended_size' is greater than 'xstate_size': + */ + __u32 xstate_size; + + /* For future use: */ + __u32 padding[7]; }; -#ifdef __i386__ /* - * As documented in the iBCS2 standard.. - * - * The first part of "struct _fpstate" is just the normal i387 - * hardware setup, the extra "status" word is used to save the - * coprocessor status word before entering the handler. + * As documented in the iBCS2 standard: * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@valinux.com>, May 2000 + * The first part of "struct _fpstate" is just the normal i387 hardware setup, + * the extra "status" word is used to save the coprocessor status word before + * entering the handler. * - * The FPU state data structure has had to grow to accommodate the - * extended FPU state required by the Streaming SIMD Extensions. - * There is no documented standard to accomplish this at the moment. + * The FPU state data structure has had to grow to accommodate the extended FPU + * state required by the Streaming SIMD Extensions. There is no documented + * standard to accomplish this at the moment. */ + +/* 10-byte legacy floating point register: */ struct _fpreg { - unsigned short significand[4]; - unsigned short exponent; + __u16 significand[4]; + __u16 exponent; }; +/* 16-byte floating point register: */ struct _fpxreg { - unsigned short significand[4]; - unsigned short exponent; - unsigned short padding[3]; + __u16 significand[4]; + __u16 exponent; + __u16 padding[3]; }; +/* 16-byte XMM register: */ struct _xmmreg { - unsigned long element[4]; + __u32 element[4]; }; -struct _fpstate { - /* Regular FPU environment */ - unsigned long cw; - unsigned long sw; - unsigned long tag; - unsigned long ipoff; - unsigned long cssel; - unsigned long dataoff; - unsigned long datasel; - struct _fpreg _st[8]; - unsigned short status; - unsigned short magic; /* 0xffff = regular FPU data only */ +#define X86_FXSR_MAGIC 0x0000 + +/* + * The 32-bit FPU frame: + */ +struct _fpstate_32 { + /* Legacy FPU environment: */ + __u32 cw; + __u32 sw; + __u32 tag; + __u32 ipoff; + __u32 cssel; + __u32 dataoff; + __u32 datasel; + struct _fpreg _st[8]; + __u16 status; + __u16 magic; /* 0xffff: regular FPU data only */ + /* 0x0000: FXSR FPU data */ /* FXSR FPU environment */ - unsigned long _fxsr_env[6]; /* FXSR FPU env is ignored */ - unsigned long mxcsr; - unsigned long reserved; - struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */ - struct _xmmreg _xmm[8]; - unsigned long padding1[44]; + __u32 _fxsr_env[6]; /* FXSR FPU env is ignored */ + __u32 mxcsr; + __u32 reserved; + struct _fpxreg _fxsr_st[8]; /* FXSR FPU reg data is ignored */ + struct _xmmreg _xmm[8]; /* First 8 XMM registers */ + union { + __u32 padding1[44]; /* Second 8 XMM registers plus padding */ + __u32 padding[44]; /* Alias name for old user-space */ + }; union { - unsigned long padding2[12]; - struct _fpx_sw_bytes sw_reserved; /* represents the extended - * state info */ + __u32 padding2[12]; + struct _fpx_sw_bytes sw_reserved; /* Potential extended state is encoded here */ }; }; -#define X86_FXSR_MAGIC 0x0000 - -#ifndef __KERNEL__ /* - * User-space might still rely on the old definition: + * The 64-bit FPU frame. (FXSAVE format and later) + * + * Note1: If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then the structure is + * larger: 'struct _xstate'. Note that 'struct _xstate' embedds + * 'struct _fpstate' so that you can always assume the _fpstate portion + * exists so that you can check the magic value. + * + * Note2: Reserved fields may someday contain valuable data. Always + * save/restore them when you change signal frames. */ -struct sigcontext { - unsigned short gs, __gsh; - unsigned short fs, __fsh; - unsigned short es, __esh; - unsigned short ds, __dsh; - unsigned long edi; - unsigned long esi; - unsigned long ebp; - unsigned long esp; - unsigned long ebx; - unsigned long edx; - unsigned long ecx; - unsigned long eax; - unsigned long trapno; - unsigned long err; - unsigned long eip; - unsigned short cs, __csh; - unsigned long eflags; - unsigned long esp_at_signal; - unsigned short ss, __ssh; - struct _fpstate __user *fpstate; - unsigned long oldmask; - unsigned long cr2; -}; -#endif /* !__KERNEL__ */ - -#else /* __i386__ */ - -/* FXSAVE frame */ -/* Note: reserved1/2 may someday contain valuable data. Always save/restore - them when you change signal frames. */ -struct _fpstate { - __u16 cwd; - __u16 swd; - __u16 twd; /* Note this is not the same as the - 32bit/x87/FSAVE twd */ - __u16 fop; - __u64 rip; - __u64 rdp; - __u32 mxcsr; - __u32 mxcsr_mask; - __u32 st_space[32]; /* 8*16 bytes for each FP-reg */ - __u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg */ - __u32 reserved2[12]; +struct _fpstate_64 { + __u16 cwd; + __u16 swd; + /* Note this is not the same as the 32-bit/x87/FSAVE twd: */ + __u16 twd; + __u16 fop; + __u64 rip; + __u64 rdp; + __u32 mxcsr; + __u32 mxcsr_mask; + __u32 st_space[32]; /* 8x FP registers, 16 bytes each */ + __u32 xmm_space[64]; /* 16x XMM registers, 16 bytes each */ + __u32 reserved2[12]; union { - __u32 reserved3[12]; - struct _fpx_sw_bytes sw_reserved; /* represents the extended - * state information */ + __u32 reserved3[12]; + struct _fpx_sw_bytes sw_reserved; /* Potential extended state is encoded here */ }; }; -#ifndef __KERNEL__ +#ifdef __i386__ +# define _fpstate _fpstate_32 +#else +# define _fpstate _fpstate_64 +#endif + +struct _header { + __u64 xfeatures; + __u64 reserved1[2]; + __u64 reserved2[5]; +}; + +struct _ymmh_state { + /* 16x YMM registers, 16 bytes each: */ + __u32 ymmh_space[64]; +}; + /* - * User-space might still rely on the old definition: + * Extended state pointed to by sigcontext::fpstate. + * + * In addition to the fpstate, information encoded in _xstate::xstate_hdr + * indicates the presence of other extended state information supported + * by the CPU and kernel: */ -struct sigcontext { - __u64 r8; - __u64 r9; - __u64 r10; - __u64 r11; - __u64 r12; - __u64 r13; - __u64 r14; - __u64 r15; - __u64 rdi; - __u64 rsi; - __u64 rbp; - __u64 rbx; - __u64 rdx; - __u64 rax; - __u64 rcx; - __u64 rsp; - __u64 rip; - __u64 eflags; /* RFLAGS */ - __u16 cs; - __u16 gs; - __u16 fs; - __u16 __pad0; - __u64 err; - __u64 trapno; - __u64 oldmask; - __u64 cr2; - struct _fpstate __user *fpstate; /* zero when no FPU context */ -#ifdef __ILP32__ - __u32 __fpstate_pad; -#endif - __u64 reserved1[8]; +struct _xstate { + struct _fpstate fpstate; + struct _header xstate_hdr; + struct _ymmh_state ymmh; + /* New processor state extensions go here: */ }; -#endif /* !__KERNEL__ */ -#endif /* !__i386__ */ +/* + * The 32-bit signal frame: + */ +struct sigcontext_32 { + __u16 gs, __gsh; + __u16 fs, __fsh; + __u16 es, __esh; + __u16 ds, __dsh; + __u32 di; + __u32 si; + __u32 bp; + __u32 sp; + __u32 bx; + __u32 dx; + __u32 cx; + __u32 ax; + __u32 trapno; + __u32 err; + __u32 ip; + __u16 cs, __csh; + __u32 flags; + __u32 sp_at_signal; + __u16 ss, __ssh; -struct _xsave_hdr { - __u64 xstate_bv; - __u64 reserved1[2]; - __u64 reserved2[5]; + /* + * fpstate is really (struct _fpstate *) or (struct _xstate *) + * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved + * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end + * of extended memory layout. See comments at the definition of + * (struct _fpx_sw_bytes) + */ + __u32 fpstate; /* Zero when no FPU/extended context */ + __u32 oldmask; + __u32 cr2; }; -struct _ymmh_state { - /* 16 * 16 bytes for each YMMH-reg */ - __u32 ymmh_space[64]; +/* + * The 64-bit signal frame: + */ +struct sigcontext_64 { + __u64 r8; + __u64 r9; + __u64 r10; + __u64 r11; + __u64 r12; + __u64 r13; + __u64 r14; + __u64 r15; + __u64 di; + __u64 si; + __u64 bp; + __u64 bx; + __u64 dx; + __u64 ax; + __u64 cx; + __u64 sp; + __u64 ip; + __u64 flags; + __u16 cs; + __u16 gs; + __u16 fs; + __u16 __pad0; + __u64 err; + __u64 trapno; + __u64 oldmask; + __u64 cr2; + + /* + * fpstate is really (struct _fpstate *) or (struct _xstate *) + * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved + * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end + * of extended memory layout. See comments at the definition of + * (struct _fpx_sw_bytes) + */ + __u64 fpstate; /* Zero when no FPU/extended context */ + __u64 reserved1[8]; }; /* - * Extended state pointed by the fpstate pointer in the sigcontext. - * In addition to the fpstate, information encoded in the xstate_hdr - * indicates the presence of other extended state information - * supported by the processor and OS. + * Create the real 'struct sigcontext' type: */ -struct _xstate { - struct _fpstate fpstate; - struct _xsave_hdr xstate_hdr; - struct _ymmh_state ymmh; - /* new processor state extensions go here */ +#ifdef __KERNEL__ +# ifdef __i386__ +# define sigcontext sigcontext_32 +# else +# define sigcontext sigcontext_64 +# endif +#endif + +/* + * The old user-space sigcontext definition, just in case user-space still + * relies on it. The kernel definition (in asm/sigcontext.h) has unified + * field names but otherwise the same layout. + */ +#ifndef __KERNEL__ + +#define _fpstate_ia32 _fpstate_32 +#define sigcontext_ia32 sigcontext_32 + + +# ifdef __i386__ +struct sigcontext { + __u16 gs, __gsh; + __u16 fs, __fsh; + __u16 es, __esh; + __u16 ds, __dsh; + __u32 edi; + __u32 esi; + __u32 ebp; + __u32 esp; + __u32 ebx; + __u32 edx; + __u32 ecx; + __u32 eax; + __u32 trapno; + __u32 err; + __u32 eip; + __u16 cs, __csh; + __u32 eflags; + __u32 esp_at_signal; + __u16 ss, __ssh; + struct _fpstate __user *fpstate; + __u32 oldmask; + __u32 cr2; }; +# else /* __x86_64__: */ +struct sigcontext { + __u64 r8; + __u64 r9; + __u64 r10; + __u64 r11; + __u64 r12; + __u64 r13; + __u64 r14; + __u64 r15; + __u64 rdi; + __u64 rsi; + __u64 rbp; + __u64 rbx; + __u64 rdx; + __u64 rax; + __u64 rcx; + __u64 rsp; + __u64 rip; + __u64 eflags; /* RFLAGS */ + __u16 cs; + __u16 gs; + __u16 fs; + __u16 __pad0; + __u64 err; + __u64 trapno; + __u64 oldmask; + __u64 cr2; + struct _fpstate __user *fpstate; /* Zero when no FPU context */ +# ifdef __ILP32__ + __u32 __fpstate_pad; +# endif + __u64 reserved1[8]; +}; +# endif /* __x86_64__ */ +#endif /* !__KERNEL__ */ #endif /* _UAPI_ASM_X86_SIGCONTEXT_H */ diff --git a/kernel/arch/x86/include/uapi/asm/sigcontext32.h b/kernel/arch/x86/include/uapi/asm/sigcontext32.h index ad1478c4a..a92b0f0dc 100644 --- a/kernel/arch/x86/include/uapi/asm/sigcontext32.h +++ b/kernel/arch/x86/include/uapi/asm/sigcontext32.h @@ -1,77 +1,8 @@ #ifndef _ASM_X86_SIGCONTEXT32_H #define _ASM_X86_SIGCONTEXT32_H -#include <linux/types.h> +/* This is a legacy file - all the type definitions are in sigcontext.h: */ -/* signal context for 32bit programs. */ - -#define X86_FXSR_MAGIC 0x0000 - -struct _fpreg { - unsigned short significand[4]; - unsigned short exponent; -}; - -struct _fpxreg { - unsigned short significand[4]; - unsigned short exponent; - unsigned short padding[3]; -}; - -struct _xmmreg { - __u32 element[4]; -}; - -/* FSAVE frame with extensions */ -struct _fpstate_ia32 { - /* Regular FPU environment */ - __u32 cw; - __u32 sw; - __u32 tag; /* not compatible to 64bit twd */ - __u32 ipoff; - __u32 cssel; - __u32 dataoff; - __u32 datasel; - struct _fpreg _st[8]; - unsigned short status; - unsigned short magic; /* 0xffff = regular FPU data only */ - - /* FXSR FPU environment */ - __u32 _fxsr_env[6]; - __u32 mxcsr; - __u32 reserved; - struct _fpxreg _fxsr_st[8]; - struct _xmmreg _xmm[8]; /* It's actually 16 */ - __u32 padding[44]; - union { - __u32 padding2[12]; - struct _fpx_sw_bytes sw_reserved; - }; -}; - -struct sigcontext_ia32 { - unsigned short gs, __gsh; - unsigned short fs, __fsh; - unsigned short es, __esh; - unsigned short ds, __dsh; - unsigned int di; - unsigned int si; - unsigned int bp; - unsigned int sp; - unsigned int bx; - unsigned int dx; - unsigned int cx; - unsigned int ax; - unsigned int trapno; - unsigned int err; - unsigned int ip; - unsigned short cs, __csh; - unsigned int flags; - unsigned int sp_at_signal; - unsigned short ss, __ssh; - unsigned int fpstate; /* really (struct _fpstate_ia32 *) */ - unsigned int oldmask; - unsigned int cr2; -}; +#include <asm/sigcontext.h> #endif /* _ASM_X86_SIGCONTEXT32_H */ diff --git a/kernel/arch/x86/include/uapi/asm/svm.h b/kernel/arch/x86/include/uapi/asm/svm.h index b5d7640ab..8a4add8e4 100644 --- a/kernel/arch/x86/include/uapi/asm/svm.h +++ b/kernel/arch/x86/include/uapi/asm/svm.h @@ -100,6 +100,7 @@ { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, \ { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, \ { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, \ + { SVM_EXIT_EXCP_BASE + AC_VECTOR, "AC excp" }, \ { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, \ { SVM_EXIT_INTR, "interrupt" }, \ { SVM_EXIT_NMI, "nmi" }, \ diff --git a/kernel/arch/x86/include/uapi/asm/vmx.h b/kernel/arch/x86/include/uapi/asm/vmx.h index 1fe92181e..5b15d94a3 100644 --- a/kernel/arch/x86/include/uapi/asm/vmx.h +++ b/kernel/arch/x86/include/uapi/asm/vmx.h @@ -58,6 +58,7 @@ #define EXIT_REASON_INVALID_STATE 33 #define EXIT_REASON_MSR_LOAD_FAIL 34 #define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_MONITOR_TRAP_FLAG 37 #define EXIT_REASON_MONITOR_INSTRUCTION 39 #define EXIT_REASON_PAUSE_INSTRUCTION 40 #define EXIT_REASON_MCE_DURING_VMENTRY 41 @@ -77,6 +78,7 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 +#define EXIT_REASON_PCOMMIT 65 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -106,6 +108,7 @@ { EXIT_REASON_MSR_READ, "MSR_READ" }, \ { EXIT_REASON_MSR_WRITE, "MSR_WRITE" }, \ { EXIT_REASON_MWAIT_INSTRUCTION, "MWAIT_INSTRUCTION" }, \ + { EXIT_REASON_MONITOR_TRAP_FLAG, "MONITOR_TRAP_FLAG" }, \ { EXIT_REASON_MONITOR_INSTRUCTION, "MONITOR_INSTRUCTION" }, \ { EXIT_REASON_PAUSE_INSTRUCTION, "PAUSE_INSTRUCTION" }, \ { EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \ @@ -124,7 +127,8 @@ { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" } + { EXIT_REASON_XRSTORS, "XRSTORS" }, \ + { EXIT_REASON_PCOMMIT, "PCOMMIT" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/kernel/arch/x86/kernel/Makefile b/kernel/arch/x86/kernel/Makefile index 9bcd0b56c..b1b78ffe0 100644 --- a/kernel/arch/x86/kernel/Makefile +++ b/kernel/arch/x86/kernel/Makefile @@ -22,18 +22,17 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n CFLAGS_irq.o := -I$(src)/../include/asm/trace -obj-y := process_$(BITS).o signal.o entry_$(BITS).o +obj-y := process_$(BITS).o signal.o +obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o -obj-y += time.o ioport.o ldt.o dumpstack.o nmi.o +obj-y += time.o ioport.o dumpstack.o nmi.o +obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-y += setup.o x86_init.o i8259.o irqinit.o jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o -obj-y += syscall_$(BITS).o vsyscall_gtod.o -obj-$(CONFIG_IA32_EMULATION) += syscall_32.o -obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o @@ -44,7 +43,7 @@ obj-y += pci-iommu_table.o obj-y += resource.o obj-y += process.o -obj-y += i387.o xsave.o +obj-y += fpu/ obj-y += ptrace.o obj-$(CONFIG_X86_32) += tls.o obj-$(CONFIG_IA32_EMULATION) += tls.o @@ -72,8 +71,8 @@ obj-$(CONFIG_LIVEPATCH) += livepatch.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o -obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o -obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o +obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o +obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ @@ -95,7 +94,7 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o -obj-$(CONFIG_X86_PMEM_LEGACY) += pmem.o +obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o @@ -110,8 +109,6 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o -obj-$(CONFIG_IOSF_MBI) += iosf_mbi.o -obj-$(CONFIG_PMC_ATOM) += pmc_atom.o ### # 64 bit specific files diff --git a/kernel/arch/x86/kernel/acpi/boot.c b/kernel/arch/x86/kernel/acpi/boot.c index 07bea8022..e75907601 100644 --- a/kernel/arch/x86/kernel/acpi/boot.c +++ b/kernel/arch/x86/kernel/acpi/boot.c @@ -31,12 +31,12 @@ #include <linux/module.h> #include <linux/dmi.h> #include <linux/irq.h> -#include <linux/irqdomain.h> #include <linux/slab.h> #include <linux/bootmem.h> #include <linux/ioport.h> #include <linux/pci.h> +#include <asm/irqdomain.h> #include <asm/pci_x86.h> #include <asm/pgtable.h> #include <asm/io_apic.h> @@ -400,57 +400,13 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger, return 0; } -static int mp_register_gsi(struct device *dev, u32 gsi, int trigger, - int polarity) -{ - int irq, node; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; - - trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; - polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; - node = dev ? dev_to_node(dev) : NUMA_NO_NODE; - if (mp_set_gsi_attr(gsi, trigger, polarity, node)) { - pr_warn("Failed to set pin attr for GSI%d\n", gsi); - return -1; - } - - irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC); - if (irq < 0) - return irq; - - /* Don't set up the ACPI SCI because it's already set up */ - if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi) - mp_config_acpi_gsi(dev, gsi, trigger, polarity); - - return irq; -} - -static void mp_unregister_gsi(u32 gsi) -{ - int irq; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return; - - irq = mp_map_gsi_to_irq(gsi, 0); - if (irq > 0) - mp_unmap_irq(irq); -} - -static struct irq_domain_ops acpi_irqdomain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, -}; - static int __init acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_io_apic *ioapic = NULL; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_DYNAMIC, - .ops = &acpi_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; ioapic = (struct acpi_madt_io_apic *)header; @@ -653,7 +609,7 @@ static int acpi_register_gsi_pic(struct device *dev, u32 gsi, * Make sure all (legacy) PCI IRQs are set as level-triggered. */ if (trigger == ACPI_LEVEL_SENSITIVE) - eisa_set_level_irq(gsi); + elcr_set_level_irq(gsi); #endif return gsi; @@ -664,10 +620,21 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, int trigger, int polarity) { int irq = gsi; - #ifdef CONFIG_X86_IO_APIC + int node; + struct irq_alloc_info info; + + node = dev ? dev_to_node(dev) : NUMA_NO_NODE; + trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1; + polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1; + ioapic_set_alloc_attr(&info, node, trigger, polarity); + mutex_lock(&acpi_ioapic_lock); - irq = mp_register_gsi(dev, gsi, trigger, polarity); + irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info); + /* Don't set up the ACPI SCI because it's already set up */ + if (irq >= 0 && enable_update_mptable && + acpi_gbl_FADT.sci_interrupt != gsi) + mp_config_acpi_gsi(dev, gsi, trigger, polarity); mutex_unlock(&acpi_ioapic_lock); #endif @@ -677,8 +644,12 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi, static void acpi_unregister_gsi_ioapic(u32 gsi) { #ifdef CONFIG_X86_IO_APIC + int irq; + mutex_lock(&acpi_ioapic_lock); - mp_unregister_gsi(gsi); + irq = mp_map_gsi_to_irq(gsi, 0, NULL); + if (irq > 0) + mp_unmap_irq(irq); mutex_unlock(&acpi_ioapic_lock); #endif } @@ -740,7 +711,7 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) #endif } -static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) { int cpu; @@ -756,12 +727,6 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu) *pcpu = cpu; return 0; } - -/* wrapper to silence section mismatch warning */ -int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu) -{ - return _acpi_map_lsapic(handle, physid, pcpu); -} EXPORT_SYMBOL(acpi_map_cpu); int acpi_unmap_cpu(int cpu) @@ -787,7 +752,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) u64 addr; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_DYNAMIC, - .ops = &acpi_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr); @@ -1011,6 +976,8 @@ static int __init acpi_parse_madt_lapic_entries(void) { int count; int x2count = 0; + int ret; + struct acpi_subtable_proc madt_proc[2]; if (!cpu_has_apic) return -ENODEV; @@ -1034,10 +1001,22 @@ static int __init acpi_parse_madt_lapic_entries(void) acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { - x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_LOCAL_APIC); - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_LOCAL_APIC); + memset(madt_proc, 0, sizeof(madt_proc)); + madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC; + madt_proc[0].handler = acpi_parse_lapic; + madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC; + madt_proc[1].handler = acpi_parse_x2apic; + ret = acpi_table_parse_entries_array(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); + if (ret < 0) { + printk(KERN_ERR PREFIX + "Error parsing LAPIC/X2APIC entries\n"); + return ret; + } + + x2count = madt_proc[0].count; + count = madt_proc[1].count; } if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); diff --git a/kernel/arch/x86/kernel/acpi/sleep.c b/kernel/arch/x86/kernel/acpi/sleep.c index d1daead5f..adb3eaf8f 100644 --- a/kernel/arch/x86/kernel/acpi/sleep.c +++ b/kernel/arch/x86/kernel/acpi/sleep.c @@ -16,6 +16,7 @@ #include <asm/cacheflush.h> #include <asm/realmode.h> +#include <linux/ftrace.h> #include "../../realmode/rm/wakeup.h" #include "sleep.h" @@ -107,7 +108,13 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x123456789abcdef0L; #endif /* CONFIG_64BIT */ + /* + * Pause/unpause graph tracing around do_suspend_lowlevel as it has + * inconsistent call/return info after it jumps to the wakeup vector. + */ + pause_graph_tracing(); do_suspend_lowlevel(); + unpause_graph_tracing(); return 0; } diff --git a/kernel/arch/x86/kernel/acpi/wakeup_32.S b/kernel/arch/x86/kernel/acpi/wakeup_32.S index 665c6b7d2..0c26b1b44 100644 --- a/kernel/arch/x86/kernel/acpi/wakeup_32.S +++ b/kernel/arch/x86/kernel/acpi/wakeup_32.S @@ -12,11 +12,13 @@ ENTRY(wakeup_pmode_return) wakeup_pmode_return: movw $__KERNEL_DS, %ax movw %ax, %ss - movw %ax, %ds - movw %ax, %es movw %ax, %fs movw %ax, %gs + movw $__USER_DS, %ax + movw %ax, %ds + movw %ax, %es + # reload the gdt, as we need the full 32 bit address lidt saved_idt lldt saved_ldt diff --git a/kernel/arch/x86/kernel/acpi/wakeup_64.S b/kernel/arch/x86/kernel/acpi/wakeup_64.S index ae693b51e..8c35df468 100644 --- a/kernel/arch/x86/kernel/acpi/wakeup_64.S +++ b/kernel/arch/x86/kernel/acpi/wakeup_64.S @@ -62,7 +62,7 @@ ENTRY(do_suspend_lowlevel) pushfq popq pt_regs_flags(%rax) - movq $resume_point, saved_rip(%rip) + movq $.Lresume_point, saved_rip(%rip) movq %rsp, saved_rsp movq %rbp, saved_rbp @@ -75,10 +75,10 @@ ENTRY(do_suspend_lowlevel) xorl %eax, %eax call x86_acpi_enter_sleep_state /* in case something went wrong, restore the machine status and go on */ - jmp resume_point + jmp .Lresume_point .align 4 -resume_point: +.Lresume_point: /* We don't restore %rax, it must be 0 anyway */ movq $saved_context, %rax movq saved_context_cr4(%rax), %rbx diff --git a/kernel/arch/x86/kernel/alternative.c b/kernel/arch/x86/kernel/alternative.c index aef653193..25f909362 100644 --- a/kernel/arch/x86/kernel/alternative.c +++ b/kernel/arch/x86/kernel/alternative.c @@ -21,6 +21,10 @@ #include <asm/io.h> #include <asm/fixmap.h> +int __read_mostly alternatives_patched; + +EXPORT_SYMBOL_GPL(alternatives_patched); + #define MAX_PATCH_LEN (255-1) static int __initdata_or_module debug_alternative; @@ -227,6 +231,15 @@ void __init arch_init_ideal_nops(void) #endif } break; + + case X86_VENDOR_AMD: + if (boot_cpu_data.x86 > 0xf) { + ideal_nops = p6_nops; + return; + } + + /* fall through */ + default: #ifdef CONFIG_X86_64 ideal_nops = k8_nops; @@ -325,10 +338,15 @@ done: static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) { + unsigned long flags; + if (instr[0] != 0x90) return; + local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); + sync_core(); + local_irq_restore(flags); DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", instr, a->instrlen - a->padlen, a->padlen); @@ -627,6 +645,7 @@ void __init alternative_instructions(void) apply_paravirt(__parainstructions, __parainstructions_end); restart_nmi(); + alternatives_patched = 1; } /** diff --git a/kernel/arch/x86/kernel/amd_nb.c b/kernel/arch/x86/kernel/amd_nb.c index 5caed1dd7..29fa475ec 100644 --- a/kernel/arch/x86/kernel/amd_nb.c +++ b/kernel/arch/x86/kernel/amd_nb.c @@ -89,9 +89,7 @@ int amd_cache_northbridges(void) next_northbridge(link, amd_nb_link_ids); } - /* GART present only on Fam15h upto model 0fh */ - if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + if (amd_gart_present()) amd_northbridges.flags |= AMD_NB_GART; /* diff --git a/kernel/arch/x86/kernel/apb_timer.c b/kernel/arch/x86/kernel/apb_timer.c index 6a7c23ff2..222a57076 100644 --- a/kernel/arch/x86/kernel/apb_timer.c +++ b/kernel/arch/x86/kernel/apb_timer.c @@ -171,10 +171,6 @@ static int __init apbt_clockevent_register(void) static void apbt_setup_irq(struct apbt_dev *adev) { - /* timer0 irq has been setup early */ - if (adev->irq == 0) - return; - irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT); irq_set_affinity(adev->irq, cpumask_of(adev->cpu)); } @@ -267,7 +263,7 @@ static int apbt_clocksource_register(void) /* Verify whether apbt counter works */ t1 = dw_apb_clocksource_read(clocksource_apbt); - rdtscll(start); + start = rdtsc(); /* * We don't know the TSC frequency yet, but waiting for @@ -277,7 +273,7 @@ static int apbt_clocksource_register(void) */ do { rep_nop(); - rdtscll(now); + now = rdtsc(); } while ((now - start) < 200000UL); /* APBT is the only always on clocksource, it has to work! */ @@ -394,13 +390,13 @@ unsigned long apbt_quick_calibrate(void) old = dw_apb_clocksource_read(clocksource_apbt); old += loop; - t1 = __native_read_tsc(); + t1 = rdtsc(); do { new = dw_apb_clocksource_read(clocksource_apbt); } while (new < old); - t2 = __native_read_tsc(); + t2 = rdtsc(); shift = 5; if (unlikely(loop >> shift == 0)) { diff --git a/kernel/arch/x86/kernel/aperture_64.c b/kernel/arch/x86/kernel/aperture_64.c index 76164e173..6e85f7136 100644 --- a/kernel/arch/x86/kernel/aperture_64.c +++ b/kernel/arch/x86/kernel/aperture_64.c @@ -262,6 +262,9 @@ void __init early_gart_iommu_check(void) u64 aper_base = 0, last_aper_base = 0; int aper_enabled = 0, last_aper_enabled = 0, last_valid = 0; + if (!amd_gart_present()) + return; + if (!early_pci_allowed()) return; @@ -355,6 +358,9 @@ int __init gart_iommu_hole_init(void) int fix, slot, valid_agp = 0; int i, node; + if (!amd_gart_present()) + return -ENODEV; + if (gart_iommu_aperture_disabled || !fix_aperture || !early_pci_allowed()) return -ENODEV; @@ -452,7 +458,7 @@ out: force_iommu || valid_agp || fallback_aper_force) { - pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Your BIOS doesn't leave an aperture memory hole\n"); pr_info("Please enable the IOMMU option in the BIOS setup\n"); pr_info("This costs you %dMB of RAM\n", 32 << fallback_aper_order); diff --git a/kernel/arch/x86/kernel/apic/apic.c b/kernel/arch/x86/kernel/apic/apic.c index cde732c1b..2f69e3b18 100644 --- a/kernel/arch/x86/kernel/apic/apic.c +++ b/kernel/arch/x86/kernel/apic/apic.c @@ -336,6 +336,13 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) apic_write(APIC_LVTT, lvtt_value); if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) { + /* + * See Intel SDM: TSC-Deadline Mode chapter. In xAPIC mode, + * writing to the APIC LVTT and TSC_DEADLINE MSR isn't serialized. + * According to Intel, MFENCE can do the serialization here. + */ + asm volatile("mfence" : : : "memory"); + printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -457,45 +464,45 @@ static int lapic_next_deadline(unsigned long delta, { u64 tsc; - rdtscll(tsc); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; } -/* - * Setup the lapic timer in periodic or oneshot mode - */ -static void lapic_timer_setup(enum clock_event_mode mode, - struct clock_event_device *evt) +static int lapic_timer_shutdown(struct clock_event_device *evt) { - unsigned long flags; unsigned int v; /* Lapic used as dummy for broadcast ? */ if (evt->features & CLOCK_EVT_FEAT_DUMMY) - return; + return 0; - local_irq_save(flags); + v = apic_read(APIC_LVTT); + v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); + apic_write(APIC_LVTT, v); + apic_write(APIC_TMICT, 0); + return 0; +} - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - case CLOCK_EVT_MODE_ONESHOT: - __setup_APIC_LVTT(lapic_timer_frequency, - mode != CLOCK_EVT_MODE_PERIODIC, 1); - break; - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - v = apic_read(APIC_LVTT); - v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); - apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); - break; - case CLOCK_EVT_MODE_RESUME: - /* Nothing to do here */ - break; - } +static inline int +lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot) +{ + /* Lapic used as dummy for broadcast ? */ + if (evt->features & CLOCK_EVT_FEAT_DUMMY) + return 0; - local_irq_restore(flags); + __setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1); + return 0; +} + +static int lapic_timer_set_periodic(struct clock_event_device *evt) +{ + return lapic_timer_set_periodic_oneshot(evt, false); +} + +static int lapic_timer_set_oneshot(struct clock_event_device *evt) +{ + return lapic_timer_set_periodic_oneshot(evt, true); } /* @@ -513,15 +520,18 @@ static void lapic_timer_broadcast(const struct cpumask *mask) * The local apic timer can be used for any function which is CPU local. */ static struct clock_event_device lapic_clockevent = { - .name = "lapic", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT - | CLOCK_EVT_FEAT_C3STOP | CLOCK_EVT_FEAT_DUMMY, - .shift = 32, - .set_mode = lapic_timer_setup, - .set_next_event = lapic_next_event, - .broadcast = lapic_timer_broadcast, - .rating = 100, - .irq = -1, + .name = "lapic", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP + | CLOCK_EVT_FEAT_DUMMY, + .shift = 32, + .set_state_shutdown = lapic_timer_shutdown, + .set_state_periodic = lapic_timer_set_periodic, + .set_state_oneshot = lapic_timer_set_oneshot, + .set_next_event = lapic_next_event, + .broadcast = lapic_timer_broadcast, + .rating = 100, + .irq = -1, }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); @@ -592,7 +602,7 @@ static void __init lapic_cal_handler(struct clock_event_device *dev) unsigned long pm = acpi_pm_read_early(); if (cpu_has_tsc) - rdtscll(tsc); + tsc = rdtsc(); switch (lapic_cal_loops++) { case 0: @@ -778,7 +788,7 @@ static int __init calibrate_APIC_clock(void) * Setup the apic timer manually */ levt->event_handler = lapic_cal_handler; - lapic_timer_setup(CLOCK_EVT_MODE_PERIODIC, levt); + lapic_timer_set_periodic(levt); lapic_cal_loops = -1; /* Let the interrupts run */ @@ -788,7 +798,8 @@ static int __init calibrate_APIC_clock(void) cpu_relax(); /* Stop the lapic timer */ - lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt); + local_irq_disable(); + lapic_timer_shutdown(levt); /* Jiffies delta */ deltaj = lapic_cal_j2 - lapic_cal_j1; @@ -799,8 +810,8 @@ static int __init calibrate_APIC_clock(void) apic_printk(APIC_VERBOSE, "... jiffies result ok\n"); else levt->features |= CLOCK_EVT_FEAT_DUMMY; - } else - local_irq_enable(); + } + local_irq_enable(); if (levt->features & CLOCK_EVT_FEAT_DUMMY) { pr_warning("APIC timer disabled due to verification failure\n"); @@ -878,7 +889,7 @@ static void local_apic_timer_interrupt(void) if (!evt->event_handler) { pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu); /* Switch it off */ - lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt); + lapic_timer_shutdown(evt); return; } @@ -1209,7 +1220,7 @@ void setup_local_APIC(void) long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) - rdtscll(tsc); + tsc = rdtsc(); if (disable_apic) { disable_ioapic_support(); @@ -1293,7 +1304,7 @@ void setup_local_APIC(void) } if (queued) { if (cpu_has_tsc && cpu_khz) { - rdtscll(ntsc); + ntsc = rdtsc(); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else max_loops--; @@ -1420,7 +1431,7 @@ enum { }; static int x2apic_state; -static inline void __x2apic_disable(void) +static void __x2apic_disable(void) { u64 msr; @@ -1436,7 +1447,7 @@ static inline void __x2apic_disable(void) printk_once(KERN_INFO "x2apic disabled\n"); } -static inline void __x2apic_enable(void) +static void __x2apic_enable(void) { u64 msr; @@ -1796,7 +1807,7 @@ int apic_version[MAX_LOCAL_APIC]; /* * This interrupt should _never_ happen with our APIC/SMP architecture */ -static inline void __smp_spurious_interrupt(u8 vector) +static void __smp_spurious_interrupt(u8 vector) { u32 v; @@ -1837,7 +1848,7 @@ __visible void smp_trace_spurious_interrupt(struct pt_regs *regs) /* * This interrupt should never happen with our APIC/SMP architecture */ -static inline void __smp_error_interrupt(struct pt_regs *regs) +static void __smp_error_interrupt(struct pt_regs *regs) { u32 v; u32 i = 0; diff --git a/kernel/arch/x86/kernel/apic/apic_flat_64.c b/kernel/arch/x86/kernel/apic/apic_flat_64.c index de918c410..f92ab3697 100644 --- a/kernel/arch/x86/kernel/apic/apic_flat_64.c +++ b/kernel/arch/x86/kernel/apic/apic_flat_64.c @@ -191,7 +191,6 @@ static struct apic apic_flat = { .send_IPI_all = flat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, @@ -299,7 +298,6 @@ static struct apic apic_physflat = { .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/kernel/arch/x86/kernel/apic/apic_noop.c b/kernel/arch/x86/kernel/apic/apic_noop.c index b205cdbdb..0d96749cf 100644 --- a/kernel/arch/x86/kernel/apic/apic_noop.c +++ b/kernel/arch/x86/kernel/apic/apic_noop.c @@ -152,7 +152,6 @@ struct apic apic_noop = { .wakeup_secondary_cpu = noop_wakeup_secondary_cpu, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = noop_apic_read, diff --git a/kernel/arch/x86/kernel/apic/apic_numachip.c b/kernel/arch/x86/kernel/apic/apic_numachip.c index 017149cde..2bd2292a3 100644 --- a/kernel/arch/x86/kernel/apic/apic_numachip.c +++ b/kernel/arch/x86/kernel/apic/apic_numachip.c @@ -11,30 +11,21 @@ * */ -#include <linux/errno.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/ctype.h> #include <linux/init.h> -#include <linux/hardirq.h> -#include <linux/delay.h> #include <asm/numachip/numachip.h> #include <asm/numachip/numachip_csr.h> -#include <asm/smp.h> -#include <asm/apic.h> #include <asm/ipi.h> #include <asm/apic_flat_64.h> #include <asm/pgtable.h> +#include <asm/pci_x86.h> -static int numachip_system __read_mostly; +u8 numachip_system __read_mostly; +static const struct apic apic_numachip1; +static const struct apic apic_numachip2; +static void (*numachip_apic_icr_write)(int apicid, unsigned int val) __read_mostly; -static const struct apic apic_numachip; - -static unsigned int get_apic_id(unsigned long x) +static unsigned int numachip1_get_apic_id(unsigned long x) { unsigned long value; unsigned int id = (x >> 24) & 0xff; @@ -47,7 +38,7 @@ static unsigned int get_apic_id(unsigned long x) return id; } -static unsigned long set_apic_id(unsigned int id) +static unsigned long numachip1_set_apic_id(unsigned int id) { unsigned long x; @@ -55,9 +46,17 @@ static unsigned long set_apic_id(unsigned int id) return x; } -static unsigned int read_xapic_id(void) +static unsigned int numachip2_get_apic_id(unsigned long x) +{ + u64 mcfg; + + rdmsrl(MSR_FAM10H_MMIO_CONF_BASE, mcfg); + return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); +} + +static unsigned long numachip2_set_apic_id(unsigned int id) { - return get_apic_id(apic_read(APIC_ID)); + return id << 24; } static int numachip_apic_id_valid(int apicid) @@ -68,7 +67,7 @@ static int numachip_apic_id_valid(int apicid) static int numachip_apic_id_registered(void) { - return physid_isset(read_xapic_id(), phys_cpu_present_map); + return 1; } static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) @@ -76,37 +75,48 @@ static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } -static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +static void numachip1_apic_icr_write(int apicid, unsigned int val) { - union numachip_csr_g3_ext_irq_gen int_gen; - - int_gen.s._destination_apic_id = phys_apicid; - int_gen.s._vector = 0; - int_gen.s._msgtype = APIC_DM_INIT >> 8; - int_gen.s._index = 0; - - write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); + write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val); +} - int_gen.s._msgtype = APIC_DM_STARTUP >> 8; - int_gen.s._vector = start_rip >> 12; +static void numachip2_apic_icr_write(int apicid, unsigned int val) +{ + numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val); +} - write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); +static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +{ + numachip_apic_icr_write(phys_apicid, APIC_DM_INIT); + numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP | + (start_rip >> 12)); - atomic_set(&init_deasserted, 1); return 0; } static void numachip_send_IPI_one(int cpu, int vector) { - union numachip_csr_g3_ext_irq_gen int_gen; - int apicid = per_cpu(x86_cpu_to_apicid, cpu); - - int_gen.s._destination_apic_id = apicid; - int_gen.s._vector = vector; - int_gen.s._msgtype = (vector == NMI_VECTOR ? APIC_DM_NMI : APIC_DM_FIXED) >> 8; - int_gen.s._index = 0; + int local_apicid, apicid = per_cpu(x86_cpu_to_apicid, cpu); + unsigned int dmode; + + preempt_disable(); + local_apicid = __this_cpu_read(x86_cpu_to_apicid); + + /* Send via local APIC where non-local part matches */ + if (!((apicid ^ local_apicid) >> NUMACHIP_LAPIC_BITS)) { + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(apicid, vector, + APIC_DEST_PHYSICAL); + local_irq_restore(flags); + preempt_enable(); + return; + } + preempt_enable(); - write_lcsr(CSR_G3_EXT_IRQ_GEN, int_gen.v); + dmode = (vector == NMI_VECTOR) ? APIC_DM_NMI : APIC_DM_FIXED; + numachip_apic_icr_write(apicid, dmode | vector); } static void numachip_send_IPI_mask(const struct cpumask *mask, int vector) @@ -150,9 +160,14 @@ static void numachip_send_IPI_self(int vector) apic_write(APIC_SELF_IPI, vector); } -static int __init numachip_probe(void) +static int __init numachip1_probe(void) { - return apic == &apic_numachip; + return apic == &apic_numachip1; +} + +static int __init numachip2_probe(void) +{ + return apic == &apic_numachip2; } static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) @@ -173,11 +188,19 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) static int __init numachip_system_init(void) { - if (!numachip_system) + /* Map the LCSR area and set up the apic_icr_write function */ + switch (numachip_system) { + case 1: + init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); + numachip_apic_icr_write = numachip1_apic_icr_write; + break; + case 2: + init_extra_mapping_uc(NUMACHIP2_LCSR_BASE, NUMACHIP2_LCSR_SIZE); + numachip_apic_icr_write = numachip2_apic_icr_write; + break; + default: return 0; - - init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE); - init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE); + } x86_cpuinit.fixup_cpu_id = fixup_cpu_id; x86_init.pci.arch_init = pci_numachip_init; @@ -186,21 +209,94 @@ static int __init numachip_system_init(void) } early_initcall(numachip_system_init); -static int numachip_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +static int numachip1_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - if (!strncmp(oem_id, "NUMASC", 6)) { - numachip_system = 1; - return 1; - } + if ((strncmp(oem_id, "NUMASC", 6) != 0) || + (strncmp(oem_table_id, "NCONNECT", 8) != 0)) + return 0; - return 0; + numachip_system = 1; + + return 1; +} + +static int numachip2_acpi_madt_oem_check(char *oem_id, char *oem_table_id) +{ + if ((strncmp(oem_id, "NUMASC", 6) != 0) || + (strncmp(oem_table_id, "NCONECT2", 8) != 0)) + return 0; + + numachip_system = 2; + + return 1; +} + +/* APIC IPIs are queued */ +static void numachip_apic_wait_icr_idle(void) +{ } -static const struct apic apic_numachip __refconst = { +/* APIC NMI IPIs are queued */ +static u32 numachip_safe_apic_wait_icr_idle(void) +{ + return 0; +} +static const struct apic apic_numachip1 __refconst = { .name = "NumaConnect system", - .probe = numachip_probe, - .acpi_madt_oem_check = numachip_acpi_madt_oem_check, + .probe = numachip1_probe, + .acpi_madt_oem_check = numachip1_acpi_madt_oem_check, + .apic_id_valid = numachip_apic_id_valid, + .apic_id_registered = numachip_apic_id_registered, + + .irq_delivery_mode = dest_Fixed, + .irq_dest_mode = 0, /* physical */ + + .target_cpus = online_target_cpus, + .disable_esr = 0, + .dest_logical = 0, + .check_apicid_used = NULL, + + .vector_allocation_domain = default_vector_allocation_domain, + .init_apic_ldr = flat_init_apic_ldr, + + .ioapic_phys_id_map = NULL, + .setup_apic_routing = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = NULL, + .check_phys_apicid_present = default_check_phys_apicid_present, + .phys_pkg_id = numachip_phys_pkg_id, + + .get_apic_id = numachip1_get_apic_id, + .set_apic_id = numachip1_set_apic_id, + .apic_id_mask = 0xffU << 24, + + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + + .send_IPI_mask = numachip_send_IPI_mask, + .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, + .send_IPI_allbutself = numachip_send_IPI_allbutself, + .send_IPI_all = numachip_send_IPI_all, + .send_IPI_self = numachip_send_IPI_self, + + .wakeup_secondary_cpu = numachip_wakeup_secondary, + .inquire_remote_apic = NULL, /* REMRD not supported */ + + .read = native_apic_mem_read, + .write = native_apic_mem_write, + .eoi_write = native_apic_mem_write, + .icr_read = native_apic_icr_read, + .icr_write = native_apic_icr_write, + .wait_icr_idle = numachip_apic_wait_icr_idle, + .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle, +}; + +apic_driver(apic_numachip1); + +static const struct apic apic_numachip2 __refconst = { + .name = "NumaConnect2 system", + .probe = numachip2_probe, + .acpi_madt_oem_check = numachip2_acpi_madt_oem_check, .apic_id_valid = numachip_apic_id_valid, .apic_id_registered = numachip_apic_id_registered, @@ -222,8 +318,8 @@ static const struct apic apic_numachip __refconst = { .check_phys_apicid_present = default_check_phys_apicid_present, .phys_pkg_id = numachip_phys_pkg_id, - .get_apic_id = get_apic_id, - .set_apic_id = set_apic_id, + .get_apic_id = numachip2_get_apic_id, + .set_apic_id = numachip2_set_apic_id, .apic_id_mask = 0xffU << 24, .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, @@ -235,7 +331,6 @@ static const struct apic apic_numachip __refconst = { .send_IPI_self = numachip_send_IPI_self, .wakeup_secondary_cpu = numachip_wakeup_secondary, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, /* REMRD not supported */ .read = native_apic_mem_read, @@ -243,8 +338,8 @@ static const struct apic apic_numachip __refconst = { .eoi_write = native_apic_mem_write, .icr_read = native_apic_icr_read, .icr_write = native_apic_icr_write, - .wait_icr_idle = native_apic_wait_icr_idle, - .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, + .wait_icr_idle = numachip_apic_wait_icr_idle, + .safe_wait_icr_idle = numachip_safe_apic_wait_icr_idle, }; -apic_driver(apic_numachip); +apic_driver(apic_numachip2); diff --git a/kernel/arch/x86/kernel/apic/bigsmp_32.c b/kernel/arch/x86/kernel/apic/bigsmp_32.c index c4a8d63f8..971cf8875 100644 --- a/kernel/arch/x86/kernel/apic/bigsmp_32.c +++ b/kernel/arch/x86/kernel/apic/bigsmp_32.c @@ -186,7 +186,6 @@ static struct apic apic_bigsmp = { .send_IPI_all = bigsmp_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wait_for_init_deassert = true, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/kernel/arch/x86/kernel/apic/htirq.c b/kernel/arch/x86/kernel/apic/htirq.c index 816f36e97..ae50d3454 100644 --- a/kernel/arch/x86/kernel/apic/htirq.c +++ b/kernel/arch/x86/kernel/apic/htirq.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Add support of hierarchical irqdomain * * 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 @@ -14,78 +16,112 @@ #include <linux/device.h> #include <linux/pci.h> #include <linux/htirq.h> +#include <asm/irqdomain.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/hypertransport.h> +static struct irq_domain *htirq_domain; + /* * Hypertransport interrupt support */ -static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector) -{ - struct ht_irq_msg msg; - - fetch_ht_irq_msg(irq, &msg); - - msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK); - msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); - - msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest); - msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest); - - write_ht_irq_msg(irq, &msg); -} - static int ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest; + struct irq_data *parent = data->parent_data; int ret; - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; - - target_ht_irq(data->irq, dest, cfg->vector); - return IRQ_SET_MASK_OK_NOCOPY; + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0) { + struct ht_irq_msg msg; + struct irq_cfg *cfg = irqd_cfg(data); + + fetch_ht_irq_msg(data->irq, &msg); + msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | + HT_IRQ_LOW_DEST_ID_MASK); + msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) | + HT_IRQ_LOW_DEST_ID(cfg->dest_apicid); + msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK); + msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); + write_ht_irq_msg(data->irq, &msg); + } + + return ret; } static struct irq_chip ht_irq_chip = { .name = "PCI-HT", .irq_mask = mask_ht_irq, .irq_unmask = unmask_ht_irq, - .irq_ack = apic_ack_edge, + .irq_ack = irq_chip_ack_parent, .irq_set_affinity = ht_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) +static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - struct irq_cfg *cfg; - struct ht_irq_msg msg; - unsigned dest; - int err; + struct ht_irq_cfg *ht_cfg; + struct irq_alloc_info *info = arg; + struct pci_dev *dev; + irq_hw_number_t hwirq; + int ret; - if (disable_apic) - return -ENXIO; + if (nr_irqs > 1 || !info) + return -EINVAL; - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + dev = info->ht_dev; + hwirq = (info->ht_idx & 0xFF) | + PCI_DEVID(dev->bus->number, dev->devfn) << 8 | + (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24; + if (irq_find_mapping(domain, hwirq) > 0) + return -EEXIST; - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; + ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL); + if (!ht_cfg) + return -ENOMEM; - msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest); + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); + if (ret < 0) { + kfree(ht_cfg); + return ret; + } + + /* Initialize msg to a value that will never match the first write. */ + ht_cfg->msg.address_lo = 0xffffffff; + ht_cfg->msg.address_hi = 0xffffffff; + ht_cfg->dev = info->ht_dev; + ht_cfg->update = info->ht_update; + ht_cfg->pos = info->ht_pos; + ht_cfg->idx = 0x10 + (info->ht_idx * 2); + irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg, + handle_edge_irq, ht_cfg, "edge"); + + return 0; +} + +static void htirq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + BUG_ON(nr_irqs != 1); + kfree(irq_data->chip_data); + irq_domain_free_irqs_top(domain, virq, nr_irqs); +} +static void htirq_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct ht_irq_msg msg; + struct irq_cfg *cfg = irqd_cfg(irq_data); + + msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid); msg.address_lo = HT_IRQ_LOW_BASE | - HT_IRQ_LOW_DEST_ID(dest) | + HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) | HT_IRQ_LOW_VECTOR(cfg->vector) | ((apic->irq_dest_mode == 0) ? HT_IRQ_LOW_DM_PHYSICAL : @@ -95,13 +131,56 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev) HT_IRQ_LOW_MT_FIXED : HT_IRQ_LOW_MT_ARBITRATED) | HT_IRQ_LOW_IRQ_MASKED; + write_ht_irq_msg(irq_data->irq, &msg); +} - write_ht_irq_msg(irq, &msg); +static void htirq_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct ht_irq_msg msg; - irq_set_chip_and_handler_name(irq, &ht_irq_chip, - handle_edge_irq, "edge"); + memset(&msg, 0, sizeof(msg)); + write_ht_irq_msg(irq_data->irq, &msg); +} - dev_dbg(&dev->dev, "irq %d for HT\n", irq); +static const struct irq_domain_ops htirq_domain_ops = { + .alloc = htirq_domain_alloc, + .free = htirq_domain_free, + .activate = htirq_domain_activate, + .deactivate = htirq_domain_deactivate, +}; - return 0; +void arch_init_htirq_domain(struct irq_domain *parent) +{ + if (disable_apic) + return; + + htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL); + if (!htirq_domain) + pr_warn("failed to initialize irqdomain for HTIRQ.\n"); + else + htirq_domain->parent = parent; +} + +int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, + ht_irq_update_t *update) +{ + struct irq_alloc_info info; + + if (!htirq_domain) + return -ENOSYS; + + init_irq_alloc_info(&info, NULL); + info.ht_idx = idx; + info.ht_pos = pos; + info.ht_dev = dev; + info.ht_update = update; + + return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev), + &info); +} + +void arch_teardown_ht_irq(unsigned int irq) +{ + irq_domain_free_irqs(irq, 1); } diff --git a/kernel/arch/x86/kernel/apic/hw_nmi.c b/kernel/arch/x86/kernel/apic/hw_nmi.c index 6873ab925..045e424fb 100644 --- a/kernel/arch/x86/kernel/apic/hw_nmi.c +++ b/kernel/arch/x86/kernel/apic/hw_nmi.c @@ -28,146 +28,21 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) #endif #ifdef arch_trigger_all_cpu_backtrace -/* For reliability, we're prepared to waste bits here. */ -static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; -static cpumask_t printtrace_mask; - -#define NMI_BUF_SIZE 4096 - -struct nmi_seq_buf { - unsigned char buffer[NMI_BUF_SIZE]; - struct seq_buf seq; -}; - -/* Safe printing in NMI context */ -static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq); - -/* "in progress" flag of arch_trigger_all_cpu_backtrace */ -static unsigned long backtrace_flag; - -static void print_seq_line(struct nmi_seq_buf *s, int start, int end) +static void nmi_raise_cpu_backtrace(cpumask_t *mask) { - const char *buf = s->buffer + start; - - printk("%.*s", (end - start) + 1, buf); + apic->send_IPI_mask(mask, NMI_VECTOR); } void arch_trigger_all_cpu_backtrace(bool include_self) { - struct nmi_seq_buf *s; - int len; - int cpu; - int i; - int this_cpu = get_cpu(); - - if (test_and_set_bit(0, &backtrace_flag)) { - /* - * If there is already a trigger_all_cpu_backtrace() in progress - * (backtrace_flag == 1), don't output double cpu dump infos. - */ - put_cpu(); - return; - } - - cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); - if (!include_self) - cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); - - cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask)); - /* - * Set up per_cpu seq_buf buffers that the NMIs running on the other - * CPUs will write to. - */ - for_each_cpu(cpu, to_cpumask(backtrace_mask)) { - s = &per_cpu(nmi_print_seq, cpu); - seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE); - } - - if (!cpumask_empty(to_cpumask(backtrace_mask))) { - pr_info("sending NMI to %s CPUs:\n", - (include_self ? "all" : "other")); - apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR); - } - - /* Wait for up to 10 seconds for all CPUs to do the backtrace */ - for (i = 0; i < 10 * 1000; i++) { - if (cpumask_empty(to_cpumask(backtrace_mask))) - break; - mdelay(1); - touch_softlockup_watchdog(); - } - - /* - * Now that all the NMIs have triggered, we can dump out their - * back traces safely to the console. - */ - for_each_cpu(cpu, &printtrace_mask) { - int last_i = 0; - - s = &per_cpu(nmi_print_seq, cpu); - len = seq_buf_used(&s->seq); - if (!len) - continue; - - /* Print line by line. */ - for (i = 0; i < len; i++) { - if (s->buffer[i] == '\n') { - print_seq_line(s, last_i, i); - last_i = i + 1; - } - } - /* Check if there was a partial line. */ - if (last_i < len) { - print_seq_line(s, last_i, len - 1); - pr_cont("\n"); - } - } - - clear_bit(0, &backtrace_flag); - smp_mb__after_atomic(); - put_cpu(); -} - -/* - * It is not safe to call printk() directly from NMI handlers. - * It may be fine if the NMI detected a lock up and we have no choice - * but to do so, but doing a NMI on all other CPUs to get a back trace - * can be done with a sysrq-l. We don't want that to lock up, which - * can happen if the NMI interrupts a printk in progress. - * - * Instead, we redirect the vprintk() to this nmi_vprintk() that writes - * the content into a per cpu seq_buf buffer. Then when the NMIs are - * all done, we can safely dump the contents of the seq_buf to a printk() - * from a non NMI context. - */ -static int nmi_vprintk(const char *fmt, va_list args) -{ - struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq); - unsigned int len = seq_buf_used(&s->seq); - - seq_buf_vprintf(&s->seq, fmt, args); - return seq_buf_used(&s->seq) - len; + nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace); } static int arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { - int cpu; - - cpu = smp_processor_id(); - - if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) { - printk_func_t printk_func_save = this_cpu_read(printk_func); - - /* Replace printk to write into the NMI seq */ - this_cpu_write(printk_func, nmi_vprintk); - printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); - show_regs(regs); - this_cpu_write(printk_func, printk_func_save); - - cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); + if (nmi_cpu_backtrace(regs)) return NMI_HANDLED; - } return NMI_DONE; } diff --git a/kernel/arch/x86/kernel/apic/io_apic.c b/kernel/arch/x86/kernel/apic/io_apic.c index 07c6aba75..678c711e2 100644 --- a/kernel/arch/x86/kernel/apic/io_apic.c +++ b/kernel/arch/x86/kernel/apic/io_apic.c @@ -18,6 +18,16 @@ * and Rolf G. Tews * for testing these extensively * Paul Diefenbaugh : Added full ACPI support + * + * Historical information which is worth to be preserved: + * + * - SiS APIC rmw bug: + * + * We used to have a workaround for a bug in SiS chips which + * required to rewrite the index register for a read-modify-write + * operation as the chip lost the index information which was + * setup for the read already. We cache the data now, so that + * workaround has been removed. */ #include <linux/mm.h> @@ -31,13 +41,13 @@ #include <linux/acpi.h> #include <linux/module.h> #include <linux/syscore_ops.h> -#include <linux/irqdomain.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/jiffies.h> /* time_after() */ #include <linux/slab.h> #include <linux/bootmem.h> +#include <asm/irqdomain.h> #include <asm/idle.h> #include <asm/io.h> #include <asm/smp.h> @@ -63,27 +73,31 @@ #define for_each_ioapic_pin(idx, pin) \ for_each_ioapic((idx)) \ for_each_pin((idx), (pin)) - #define for_each_irq_pin(entry, head) \ list_for_each_entry(entry, &head, list) -/* - * Is the SiS APIC rmw bug present ? - * -1 = don't know, 0 = no, 1 = yes - */ -int sis_apic_bug = -1; - static DEFINE_RAW_SPINLOCK(ioapic_lock); static DEFINE_MUTEX(ioapic_mutex); static unsigned int ioapic_dynirq_base; static int ioapic_initialized; -struct mp_pin_info { +struct irq_pin_list { + struct list_head list; + int apic, pin; +}; + +struct mp_chip_data { + struct list_head irq_2_pin; + struct IO_APIC_route_entry entry; int trigger; int polarity; - int node; - int set; u32 count; + bool isa_irq; +}; + +struct mp_ioapic_gsi { + u32 gsi_base; + u32 gsi_end; }; static struct ioapic { @@ -101,7 +115,6 @@ static struct ioapic { struct mp_ioapic_gsi gsi_config; struct ioapic_domain_cfg irqdomain_cfg; struct irq_domain *irqdomain; - struct mp_pin_info *pin_info; struct resource *iomem_res; } ioapics[MAX_IO_APICS]; @@ -117,7 +130,7 @@ unsigned int mpc_ioapic_addr(int ioapic_idx) return ioapics[ioapic_idx].mp_config.apicaddr; } -struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) +static inline struct mp_ioapic_gsi *mp_ioapic_gsi_routing(int ioapic_idx) { return &ioapics[ioapic_idx].gsi_config; } @@ -129,11 +142,16 @@ static inline int mp_ioapic_pin_count(int ioapic) return gsi_cfg->gsi_end - gsi_cfg->gsi_base + 1; } -u32 mp_pin_to_gsi(int ioapic, int pin) +static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return mp_ioapic_gsi_routing(ioapic)->gsi_base + pin; } +static inline bool mp_is_legacy_irq(int irq) +{ + return irq >= 0 && irq < nr_legacy_irqs(); +} + /* * Initialize all legacy IRQs and all pins on the first IOAPIC * if we have legacy interrupt controller. Kernel boot option "pirq=" @@ -144,12 +162,7 @@ static inline int mp_init_irq_at_boot(int ioapic, int irq) if (!nr_legacy_irqs()) return 0; - return ioapic == 0 || (irq >= 0 && irq < nr_legacy_irqs()); -} - -static inline struct mp_pin_info *mp_pin_info(int ioapic_idx, int pin) -{ - return ioapics[ioapic_idx].pin_info + pin; + return ioapic == 0 || mp_is_legacy_irq(irq); } static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic) @@ -216,16 +229,6 @@ void mp_save_irq(struct mpc_intsrc *m) panic("Max # of irq sources exceeded!!\n"); } -struct irq_pin_list { - struct list_head list; - int apic, pin; -}; - -static struct irq_pin_list *alloc_irq_pin_list(int node) -{ - return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node); -} - static void alloc_ioapic_saved_registers(int idx) { size_t size; @@ -247,8 +250,7 @@ static void free_ioapic_saved_registers(int idx) int __init arch_early_ioapic_init(void) { - struct irq_cfg *cfg; - int i, node = cpu_to_node(0); + int i; if (!nr_legacy_irqs()) io_apic_irqs = ~0UL; @@ -256,16 +258,6 @@ int __init arch_early_ioapic_init(void) for_each_ioapic(i) alloc_ioapic_saved_registers(i); - /* - * For legacy IRQ's, start with assigning irq0 to irq15 to - * IRQ0_VECTOR to IRQ15_VECTOR for all cpu's. - */ - for (i = 0; i < nr_legacy_irqs(); i++) { - cfg = alloc_irq_and_cfg_at(i, node); - cfg->vector = IRQ0_VECTOR + i; - cpumask_setall(cfg->domain); - } - return 0; } @@ -283,7 +275,7 @@ static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx) + (mpc_ioapic_addr(idx) & ~PAGE_MASK); } -void io_apic_eoi(unsigned int apic, unsigned int vector) +static inline void io_apic_eoi(unsigned int apic, unsigned int vector) { struct io_apic __iomem *io_apic = io_apic_base(apic); writel(vector, &io_apic->eoi); @@ -296,7 +288,8 @@ unsigned int native_io_apic_read(unsigned int apic, unsigned int reg) return readl(&io_apic->data); } -void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +static void io_apic_write(unsigned int apic, unsigned int reg, + unsigned int value) { struct io_apic __iomem *io_apic = io_apic_base(apic); @@ -304,21 +297,6 @@ void native_io_apic_write(unsigned int apic, unsigned int reg, unsigned int valu writel(value, &io_apic->data); } -/* - * Re-write a value: to be used for read-modify-write - * cycles where the read already set up the index register. - * - * Older SiS APIC requires we rewrite the index register - */ -void native_io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value) -{ - struct io_apic __iomem *io_apic = io_apic_base(apic); - - if (sis_apic_bug) - writel(reg, &io_apic->index); - writel(value, &io_apic->data); -} - union entry_union { struct { u32 w1, w2; }; struct IO_APIC_route_entry entry; @@ -378,7 +356,7 @@ static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e) static void ioapic_mask_entry(int apic, int pin) { unsigned long flags; - union entry_union eu = { .entry.mask = 1 }; + union entry_union eu = { .entry.mask = IOAPIC_MASKED }; raw_spin_lock_irqsave(&ioapic_lock, flags); io_apic_write(apic, 0x10 + 2*pin, eu.w1); @@ -391,16 +369,17 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static int __add_pin_to_irq_node(struct mp_chip_data *data, + int node, int apic, int pin) { struct irq_pin_list *entry; /* don't allow duplicates */ - for_each_irq_pin(entry, cfg->irq_2_pin) + for_each_irq_pin(entry, data->irq_2_pin) if (entry->apic == apic && entry->pin == pin) return 0; - entry = alloc_irq_pin_list(node); + entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node); if (!entry) { pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", node, apic, pin); @@ -408,16 +387,16 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi } entry->apic = apic; entry->pin = pin; + list_add_tail(&entry->list, &data->irq_2_pin); - list_add_tail(&entry->list, &cfg->irq_2_pin); return 0; } -static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) +static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) { struct irq_pin_list *tmp, *entry; - list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list) + list_for_each_entry_safe(entry, tmp, &data->irq_2_pin, list) if (entry->apic == apic && entry->pin == pin) { list_del(&entry->list); kfree(entry); @@ -425,22 +404,23 @@ static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin) } } -static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin) +static void add_pin_to_irq_node(struct mp_chip_data *data, + int node, int apic, int pin) { - if (__add_pin_to_irq_node(cfg, node, apic, pin)) + if (__add_pin_to_irq_node(data, node, apic, pin)) panic("IO-APIC: failed to add irq-pin. Can not proceed\n"); } /* * Reroute an IRQ to a different pin. */ -static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, +static void __init replace_pin_at_irq_node(struct mp_chip_data *data, int node, int oldapic, int oldpin, int newapic, int newpin) { struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, data->irq_2_pin) { if (entry->apic == oldapic && entry->pin == oldpin) { entry->apic = newapic; entry->pin = newpin; @@ -450,32 +430,26 @@ static void __init replace_pin_at_irq_node(struct irq_cfg *cfg, int node, } /* old apic/pin didn't exist, so just add new ones */ - add_pin_to_irq_node(cfg, node, newapic, newpin); + add_pin_to_irq_node(data, node, newapic, newpin); } -static void __io_apic_modify_irq(struct irq_pin_list *entry, - int mask_and, int mask_or, - void (*final)(struct irq_pin_list *entry)) -{ - unsigned int reg, pin; - - pin = entry->pin; - reg = io_apic_read(entry->apic, 0x10 + pin * 2); - reg &= mask_and; - reg |= mask_or; - io_apic_modify(entry->apic, 0x10 + pin * 2, reg); - if (final) - final(entry); -} - -static void io_apic_modify_irq(struct irq_cfg *cfg, +static void io_apic_modify_irq(struct mp_chip_data *data, int mask_and, int mask_or, void (*final)(struct irq_pin_list *entry)) { + union entry_union eu; struct irq_pin_list *entry; - for_each_irq_pin(entry, cfg->irq_2_pin) - __io_apic_modify_irq(entry, mask_and, mask_or, final); + eu.entry = data->entry; + eu.w1 &= mask_and; + eu.w1 |= mask_or; + data->entry = eu.entry; + + for_each_irq_pin(entry, data->irq_2_pin) { + io_apic_write(entry->apic, 0x10 + 2 * entry->pin, eu.w1); + if (final) + final(entry); + } } static void io_apic_sync(struct irq_pin_list *entry) @@ -490,39 +464,31 @@ static void io_apic_sync(struct irq_pin_list *entry) readl(&io_apic->data); } -static void mask_ioapic(struct irq_cfg *cfg) +static void mask_ioapic_irq(struct irq_data *irq_data) { + struct mp_chip_data *data = irq_data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); + io_apic_modify_irq(data, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } -static void mask_ioapic_irq(struct irq_data *data) +static void __unmask_ioapic(struct mp_chip_data *data) { - mask_ioapic(irqd_cfg(data)); + io_apic_modify_irq(data, ~IO_APIC_REDIR_MASKED, 0, NULL); } -static void __unmask_ioapic(struct irq_cfg *cfg) -{ - io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL); -} - -static void unmask_ioapic(struct irq_cfg *cfg) +static void unmask_ioapic_irq(struct irq_data *irq_data) { + struct mp_chip_data *data = irq_data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - __unmask_ioapic(cfg); + __unmask_ioapic(data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } -static void unmask_ioapic_irq(struct irq_data *data) -{ - unmask_ioapic(irqd_cfg(data)); -} - /* * IO-APIC versions below 0x20 don't support EOI register. * For the record, here is the information about various versions: @@ -539,7 +505,7 @@ static void unmask_ioapic_irq(struct irq_data *data) * Otherwise, we simulate the EOI message manually by changing the trigger * mode to edge and then back to level, with RTE being masked during this. */ -void native_eoi_ioapic_pin(int apic, int pin, int vector) +static void __eoi_ioapic_pin(int apic, int pin, int vector) { if (mpc_ioapic_ver(apic) >= 0x20) { io_apic_eoi(apic, vector); @@ -551,7 +517,7 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector) /* * Mask the entry and change the trigger mode to edge. */ - entry1.mask = 1; + entry1.mask = IOAPIC_MASKED; entry1.trigger = IOAPIC_EDGE; __ioapic_write_entry(apic, pin, entry1); @@ -563,15 +529,14 @@ void native_eoi_ioapic_pin(int apic, int pin, int vector) } } -void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) +static void eoi_ioapic_pin(int vector, struct mp_chip_data *data) { - struct irq_pin_list *entry; unsigned long flags; + struct irq_pin_list *entry; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) - x86_io_apic_ops.eoi_ioapic_pin(entry->apic, entry->pin, - cfg->vector); + for_each_irq_pin(entry, data->irq_2_pin) + __eoi_ioapic_pin(entry->apic, entry->pin, vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -588,8 +553,8 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * Make sure the entry is masked and re-read the contents to check * if it is a level triggered pin and if the remote-IRR is set. */ - if (!entry.mask) { - entry.mask = 1; + if (entry.mask == IOAPIC_UNMASKED) { + entry.mask = IOAPIC_MASKED; ioapic_write_entry(apic, pin, entry); entry = ioapic_read_entry(apic, pin); } @@ -602,13 +567,12 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) * doesn't clear the remote-IRR if the trigger mode is not * set to level. */ - if (!entry.trigger) { + if (entry.trigger == IOAPIC_EDGE) { entry.trigger = IOAPIC_LEVEL; ioapic_write_entry(apic, pin, entry); } - raw_spin_lock_irqsave(&ioapic_lock, flags); - x86_io_apic_ops.eoi_ioapic_pin(apic, pin, entry.vector); + __eoi_ioapic_pin(apic, pin, entry.vector); raw_spin_unlock_irqrestore(&ioapic_lock, flags); } @@ -706,8 +670,8 @@ void mask_ioapic_entries(void) struct IO_APIC_route_entry entry; entry = ioapics[apic].saved_registers[pin]; - if (!entry.mask) { - entry.mask = 1; + if (entry.mask == IOAPIC_UNMASKED) { + entry.mask = IOAPIC_MASKED; ioapic_write_entry(apic, pin, entry); } } @@ -809,11 +773,11 @@ static int EISA_ELCR(unsigned int irq) #endif -/* ISA interrupts are always polarity zero edge triggered, +/* ISA interrupts are always active high edge triggered, * when listed as conforming in the MP table. */ -#define default_ISA_trigger(idx) (0) -#define default_ISA_polarity(idx) (0) +#define default_ISA_trigger(idx) (IOAPIC_EDGE) +#define default_ISA_polarity(idx) (IOAPIC_POL_HIGH) /* EISA interrupts are always polarity zero and can be edge or level * trigger depending on the ELCR value. If an interrupt is listed as @@ -823,54 +787,56 @@ static int EISA_ELCR(unsigned int irq) #define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].srcbusirq)) #define default_EISA_polarity(idx) default_ISA_polarity(idx) -/* PCI interrupts are always polarity one level triggered, +/* PCI interrupts are always active low level triggered, * when listed as conforming in the MP table. */ -#define default_PCI_trigger(idx) (1) -#define default_PCI_polarity(idx) (1) +#define default_PCI_trigger(idx) (IOAPIC_LEVEL) +#define default_PCI_polarity(idx) (IOAPIC_POL_LOW) static int irq_polarity(int idx) { int bus = mp_irqs[idx].srcbus; - int polarity; /* * Determine IRQ line polarity (high active or low active): */ - switch (mp_irqs[idx].irqflag & 3) - { - case 0: /* conforms, ie. bus-type dependent polarity */ - if (test_bit(bus, mp_bus_not_pci)) - polarity = default_ISA_polarity(idx); - else - polarity = default_PCI_polarity(idx); - break; - case 1: /* high active */ - { - polarity = 0; - break; - } - case 2: /* reserved */ - { - pr_warn("broken BIOS!!\n"); - polarity = 1; - break; - } - case 3: /* low active */ - { - polarity = 1; - break; - } - default: /* invalid */ - { - pr_warn("broken BIOS!!\n"); - polarity = 1; - break; - } + switch (mp_irqs[idx].irqflag & 0x03) { + case 0: + /* conforms to spec, ie. bus-type dependent polarity */ + if (test_bit(bus, mp_bus_not_pci)) + return default_ISA_polarity(idx); + else + return default_PCI_polarity(idx); + case 1: + return IOAPIC_POL_HIGH; + case 2: + pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); + case 3: + default: /* Pointless default required due to do gcc stupidity */ + return IOAPIC_POL_LOW; } - return polarity; } +#ifdef CONFIG_EISA +static int eisa_irq_trigger(int idx, int bus, int trigger) +{ + switch (mp_bus_id_to_type[bus]) { + case MP_BUS_PCI: + case MP_BUS_ISA: + return trigger; + case MP_BUS_EISA: + return default_EISA_trigger(idx); + } + pr_warn("IOAPIC: Invalid srcbus: %d defaulting to level\n", bus); + return IOAPIC_LEVEL; +} +#else +static inline int eisa_irq_trigger(int idx, int bus, int trigger) +{ + return trigger; +} +#endif + static int irq_trigger(int idx) { int bus = mp_irqs[idx].srcbus; @@ -879,153 +845,227 @@ static int irq_trigger(int idx) /* * Determine IRQ trigger mode (edge or level sensitive): */ - switch ((mp_irqs[idx].irqflag>>2) & 3) - { - case 0: /* conforms, ie. bus-type dependent */ - if (test_bit(bus, mp_bus_not_pci)) - trigger = default_ISA_trigger(idx); - else - trigger = default_PCI_trigger(idx); -#ifdef CONFIG_EISA - switch (mp_bus_id_to_type[bus]) { - case MP_BUS_ISA: /* ISA pin */ - { - /* set before the switch */ - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* set before the switch */ - break; - } - default: - { - pr_warn("broken BIOS!!\n"); - trigger = 1; - break; - } - } + switch ((mp_irqs[idx].irqflag >> 2) & 0x03) { + case 0: + /* conforms to spec, ie. bus-type dependent trigger mode */ + if (test_bit(bus, mp_bus_not_pci)) + trigger = default_ISA_trigger(idx); + else + trigger = default_PCI_trigger(idx); + /* Take EISA into account */ + return eisa_irq_trigger(idx, bus, trigger); + case 1: + return IOAPIC_EDGE; + case 2: + pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); + case 3: + default: /* Pointless default required due to do gcc stupidity */ + return IOAPIC_LEVEL; + } +} + +void ioapic_set_alloc_attr(struct irq_alloc_info *info, int node, + int trigger, int polarity) +{ + init_irq_alloc_info(info, NULL); + info->type = X86_IRQ_ALLOC_TYPE_IOAPIC; + info->ioapic_node = node; + info->ioapic_trigger = trigger; + info->ioapic_polarity = polarity; + info->ioapic_valid = 1; +} + +#ifndef CONFIG_ACPI +int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #endif - break; - case 1: /* edge */ - { - trigger = 0; - break; - } - case 2: /* reserved */ - { - pr_warn("broken BIOS!!\n"); - trigger = 1; - break; - } - case 3: /* level */ - { - trigger = 1; - break; - } - default: /* invalid */ - { - pr_warn("broken BIOS!!\n"); - trigger = 0; - break; + +static void ioapic_copy_alloc_attr(struct irq_alloc_info *dst, + struct irq_alloc_info *src, + u32 gsi, int ioapic_idx, int pin) +{ + int trigger, polarity; + + copy_irq_alloc_info(dst, src); + dst->type = X86_IRQ_ALLOC_TYPE_IOAPIC; + dst->ioapic_id = mpc_ioapic_id(ioapic_idx); + dst->ioapic_pin = pin; + dst->ioapic_valid = 1; + if (src && src->ioapic_valid) { + dst->ioapic_node = src->ioapic_node; + dst->ioapic_trigger = src->ioapic_trigger; + dst->ioapic_polarity = src->ioapic_polarity; + } else { + dst->ioapic_node = NUMA_NO_NODE; + if (acpi_get_override_irq(gsi, &trigger, &polarity) >= 0) { + dst->ioapic_trigger = trigger; + dst->ioapic_polarity = polarity; + } else { + /* + * PCI interrupts are always active low level + * triggered. + */ + dst->ioapic_trigger = IOAPIC_LEVEL; + dst->ioapic_polarity = IOAPIC_POL_LOW; } } - return trigger; } -static int alloc_irq_from_domain(struct irq_domain *domain, u32 gsi, int pin) +static int ioapic_alloc_attr_node(struct irq_alloc_info *info) +{ + return (info && info->ioapic_valid) ? info->ioapic_node : NUMA_NO_NODE; +} + +static void mp_register_handler(unsigned int irq, unsigned long trigger) { + irq_flow_handler_t hdl; + bool fasteoi; + + if (trigger) { + irq_set_status_flags(irq, IRQ_LEVEL); + fasteoi = true; + } else { + irq_clear_status_flags(irq, IRQ_LEVEL); + fasteoi = false; + } + + hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; + __irq_set_handler(irq, hdl, 0, fasteoi ? "fasteoi" : "edge"); +} + +static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) +{ + struct mp_chip_data *data = irq_get_chip_data(irq); + + /* + * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger + * and polarity attirbutes. So allow the first user to reprogram the + * pin with real trigger and polarity attributes. + */ + if (irq < nr_legacy_irqs() && data->count == 1) { + if (info->ioapic_trigger != data->trigger) + mp_register_handler(irq, info->ioapic_trigger); + data->entry.trigger = data->trigger = info->ioapic_trigger; + data->entry.polarity = data->polarity = info->ioapic_polarity; + } + + return data->trigger == info->ioapic_trigger && + data->polarity == info->ioapic_polarity; +} + +static int alloc_irq_from_domain(struct irq_domain *domain, int ioapic, u32 gsi, + struct irq_alloc_info *info) +{ + bool legacy = false; int irq = -1; - int ioapic = (int)(long)domain->host_data; int type = ioapics[ioapic].irqdomain_cfg.type; switch (type) { case IOAPIC_DOMAIN_LEGACY: /* - * Dynamically allocate IRQ number for non-ISA IRQs in the first 16 - * GSIs on some weird platforms. + * Dynamically allocate IRQ number for non-ISA IRQs in the first + * 16 GSIs on some weird platforms. */ - if (gsi < nr_legacy_irqs()) - irq = irq_create_mapping(domain, pin); - else if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) + if (!ioapic_initialized || gsi >= nr_legacy_irqs()) irq = gsi; + legacy = mp_is_legacy_irq(irq); break; case IOAPIC_DOMAIN_STRICT: - if (irq_create_strict_mappings(domain, gsi, pin, 1) == 0) - irq = gsi; + irq = gsi; break; case IOAPIC_DOMAIN_DYNAMIC: - irq = irq_create_mapping(domain, pin); break; default: WARN(1, "ioapic: unknown irqdomain type %d\n", type); - break; + return -1; + } + + return __irq_domain_alloc_irqs(domain, irq, 1, + ioapic_alloc_attr_node(info), + info, legacy); +} + +/* + * Need special handling for ISA IRQs because there may be multiple IOAPIC pins + * sharing the same ISA IRQ number and irqdomain only supports 1:1 mapping + * between IOAPIC pin and IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are + * used for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). + * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are available, and + * some BIOSes may use MP Interrupt Source records to override IRQ numbers for + * PIRQs instead of reprogramming the interrupt routing logic. Thus there may be + * multiple pins sharing the same legacy IRQ number when ACPI is disabled. + */ +static int alloc_isa_irq_from_domain(struct irq_domain *domain, + int irq, int ioapic, int pin, + struct irq_alloc_info *info) +{ + struct mp_chip_data *data; + struct irq_data *irq_data = irq_get_irq_data(irq); + int node = ioapic_alloc_attr_node(info); + + /* + * Legacy ISA IRQ has already been allocated, just add pin to + * the pin list assoicated with this IRQ and program the IOAPIC + * entry. The IOAPIC entry + */ + if (irq_data && irq_data->parent_data) { + if (!mp_check_pin_attr(irq, info)) + return -EBUSY; + if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, + info->ioapic_pin)) + return -ENOMEM; + } else { + irq = __irq_domain_alloc_irqs(domain, irq, 1, node, info, true); + if (irq >= 0) { + irq_data = irq_domain_get_irq_data(domain, irq); + data = irq_data->chip_data; + data->isa_irq = true; + } } - return irq > 0 ? irq : -1; + return irq; } static int mp_map_pin_to_irq(u32 gsi, int idx, int ioapic, int pin, - unsigned int flags) + unsigned int flags, struct irq_alloc_info *info) { int irq; + bool legacy = false; + struct irq_alloc_info tmp; + struct mp_chip_data *data; struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); - struct mp_pin_info *info = mp_pin_info(ioapic, pin); if (!domain) - return -1; + return -ENOSYS; - mutex_lock(&ioapic_mutex); - - /* - * Don't use irqdomain to manage ISA IRQs because there may be - * multiple IOAPIC pins sharing the same ISA IRQ number and - * irqdomain only supports 1:1 mapping between IOAPIC pin and - * IRQ number. A typical IOAPIC has 24 pins, pin 0-15 are used - * for legacy IRQs and pin 16-23 are used for PCI IRQs (PIRQ A-H). - * When ACPI is disabled, only legacy IRQ numbers (IRQ0-15) are - * available, and some BIOSes may use MP Interrupt Source records - * to override IRQ numbers for PIRQs instead of reprogramming - * the interrupt routing logic. Thus there may be multiple pins - * sharing the same legacy IRQ number when ACPI is disabled. - */ if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) { irq = mp_irqs[idx].srcbusirq; - if (flags & IOAPIC_MAP_ALLOC) { - if (info->count == 0 && - mp_irqdomain_map(domain, irq, pin) != 0) - irq = -1; + legacy = mp_is_legacy_irq(irq); + } - /* special handling for timer IRQ0 */ + mutex_lock(&ioapic_mutex); + if (!(flags & IOAPIC_MAP_ALLOC)) { + if (!legacy) { + irq = irq_find_mapping(domain, pin); if (irq == 0) - info->count++; + irq = -ENOENT; } } else { - irq = irq_find_mapping(domain, pin); - if (irq <= 0 && (flags & IOAPIC_MAP_ALLOC)) - irq = alloc_irq_from_domain(domain, gsi, pin); - } - - if (flags & IOAPIC_MAP_ALLOC) { - /* special handling for legacy IRQs */ - if (irq < nr_legacy_irqs() && info->count == 1 && - mp_irqdomain_map(domain, irq, pin) != 0) - irq = -1; - - if (irq > 0) - info->count++; - else if (info->count == 0) - info->set = 0; + ioapic_copy_alloc_attr(&tmp, info, gsi, ioapic, pin); + if (legacy) + irq = alloc_isa_irq_from_domain(domain, irq, + ioapic, pin, &tmp); + else if ((irq = irq_find_mapping(domain, pin)) == 0) + irq = alloc_irq_from_domain(domain, ioapic, gsi, &tmp); + else if (!mp_check_pin_attr(irq, &tmp)) + irq = -EBUSY; + if (irq >= 0) { + data = irq_get_chip_data(irq); + data->count++; + } } - mutex_unlock(&ioapic_mutex); - return irq > 0 ? irq : -1; + return irq; } static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) @@ -1058,10 +1098,10 @@ static int pin_2_irq(int idx, int ioapic, int pin, unsigned int flags) } #endif - return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, NULL); } -int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) +int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info) { int ioapic, pin, idx; @@ -1074,31 +1114,24 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) if ((flags & IOAPIC_MAP_CHECK) && idx < 0) return -1; - return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags); + return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info); } void mp_unmap_irq(int irq) { - struct irq_data *data = irq_get_irq_data(irq); - struct mp_pin_info *info; - int ioapic, pin; + struct irq_data *irq_data = irq_get_irq_data(irq); + struct mp_chip_data *data; - if (!data || !data->domain) + if (!irq_data || !irq_data->domain) return; - ioapic = (int)(long)data->domain->host_data; - pin = (int)data->hwirq; - info = mp_pin_info(ioapic, pin); + data = irq_data->chip_data; + if (!data || data->isa_irq) + return; mutex_lock(&ioapic_mutex); - if (--info->count == 0) { - info->set = 0; - if (irq < nr_legacy_irqs() && - ioapics[ioapic].irqdomain_cfg.type == IOAPIC_DOMAIN_LEGACY) - mp_irqdomain_unmap(data->domain, irq); - else - irq_dispose_mapping(irq); - } + if (--data->count == 0) + irq_domain_free_irqs(irq, 1); mutex_unlock(&ioapic_mutex); } @@ -1165,7 +1198,7 @@ out: } EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); -static struct irq_chip ioapic_chip; +static struct irq_chip ioapic_chip, ioapic_ir_chip; #ifdef CONFIG_X86_32 static inline int IO_APIC_irq_trigger(int irq) @@ -1189,96 +1222,6 @@ static inline int IO_APIC_irq_trigger(int irq) } #endif -static void ioapic_register_intr(unsigned int irq, struct irq_cfg *cfg, - unsigned long trigger) -{ - struct irq_chip *chip = &ioapic_chip; - irq_flow_handler_t hdl; - bool fasteoi; - - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) { - irq_set_status_flags(irq, IRQ_LEVEL); - fasteoi = true; - } else { - irq_clear_status_flags(irq, IRQ_LEVEL); - fasteoi = false; - } - - if (setup_remapped_irq(irq, cfg, chip)) - fasteoi = trigger != 0; - - hdl = fasteoi ? handle_fasteoi_irq : handle_edge_irq; - irq_set_chip_and_handler_name(irq, chip, hdl, - fasteoi ? "fasteoi" : "edge"); -} - -int native_setup_ioapic_entry(int irq, struct IO_APIC_route_entry *entry, - unsigned int destination, int vector, - struct io_apic_irq_attr *attr) -{ - memset(entry, 0, sizeof(*entry)); - - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->dest = destination; - entry->vector = vector; - entry->mask = 0; /* enable IRQ */ - entry->trigger = attr->trigger; - entry->polarity = attr->polarity; - - /* - * Mask level triggered irqs. - * Use IRQ_DELAYED_DISABLE for edge triggered irqs. - */ - if (attr->trigger) - entry->mask = 1; - - return 0; -} - -static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg, - struct io_apic_irq_attr *attr) -{ - struct IO_APIC_route_entry entry; - unsigned int dest; - - if (!IO_APIC_IRQ(irq)) - return; - - if (assign_irq_vector(irq, cfg, apic->target_cpus())) - return; - - if (apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus(), - &dest)) { - pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n", - mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - clear_irq_vector(irq, cfg); - - return; - } - - apic_printk(APIC_VERBOSE,KERN_DEBUG - "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> " - "IRQ %d Mode:%i Active:%i Dest:%d)\n", - attr->ioapic, mpc_ioapic_id(attr->ioapic), attr->ioapic_pin, - cfg->vector, irq, attr->trigger, attr->polarity, dest); - - if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) { - pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n", - mpc_ioapic_id(attr->ioapic), attr->ioapic_pin); - clear_irq_vector(irq, cfg); - - return; - } - - ioapic_register_intr(irq, cfg, attr->trigger); - if (irq < nr_legacy_irqs()) - legacy_pic->mask(irq); - - ioapic_write_entry(attr->ioapic, attr->ioapic_pin, entry); -} - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; @@ -1298,106 +1241,41 @@ static void __init setup_IO_APIC_irqs(void) } } -/* - * Set up the timer pin, possibly with the 8259A-master behind. - */ -static void __init setup_timer_IRQ0_pin(unsigned int ioapic_idx, - unsigned int pin, int vector) -{ - struct IO_APIC_route_entry entry; - unsigned int dest; - - memset(&entry, 0, sizeof(entry)); - - /* - * We use logical delivery to get the timer IRQ - * to the first CPU. - */ - if (unlikely(apic->cpu_mask_to_apicid_and(apic->target_cpus(), - apic->target_cpus(), &dest))) - dest = BAD_APICID; - - entry.dest_mode = apic->irq_dest_mode; - entry.mask = 0; /* don't mask IRQ for edge */ - entry.dest = dest; - entry.delivery_mode = apic->irq_delivery_mode; - entry.polarity = 0; - entry.trigger = 0; - entry.vector = vector; - - /* - * The timer IRQ doesn't have to know that behind the - * scene we may have a 8259A-master in AEOI mode ... - */ - irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, - "edge"); - - /* - * Add it to the IO-APIC irq-routing table: - */ - ioapic_write_entry(ioapic_idx, pin, entry); -} - -void native_io_apic_print_entries(unsigned int apic, unsigned int nr_entries) +void ioapic_zap_locks(void) { - int i; - - pr_debug(" NR Dst Mask Trig IRR Pol Stat Dmod Deli Vect:\n"); - - for (i = 0; i <= nr_entries; i++) { - struct IO_APIC_route_entry entry; - - entry = ioapic_read_entry(apic, i); - - pr_debug(" %02x %02X ", i, entry.dest); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector); - } + raw_spin_lock_init(&ioapic_lock); } -void intel_ir_io_apic_print_entries(unsigned int apic, - unsigned int nr_entries) +static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) { int i; + char buf[256]; + struct IO_APIC_route_entry entry; + struct IR_IO_APIC_route_entry *ir_entry = (void *)&entry; - pr_debug(" NR Indx Fmt Mask Trig IRR Pol Stat Indx2 Zero Vect:\n"); - + printk(KERN_DEBUG "IOAPIC %d:\n", apic); for (i = 0; i <= nr_entries; i++) { - struct IR_IO_APIC_route_entry *ir_entry; - struct IO_APIC_route_entry entry; - entry = ioapic_read_entry(apic, i); - - ir_entry = (struct IR_IO_APIC_route_entry *)&entry; - - pr_debug(" %02x %04X ", i, ir_entry->index); - pr_cont("%1d %1d %1d %1d %1d " - "%1d %1d %X %02X\n", - ir_entry->format, - ir_entry->mask, - ir_entry->trigger, - ir_entry->irr, - ir_entry->polarity, - ir_entry->delivery_status, - ir_entry->index2, - ir_entry->zero, - ir_entry->vector); + snprintf(buf, sizeof(buf), + " pin%02x, %s, %s, %s, V(%02X), IRR(%1d), S(%1d)", + i, + entry.mask == IOAPIC_MASKED ? "disabled" : "enabled ", + entry.trigger == IOAPIC_LEVEL ? "level" : "edge ", + entry.polarity == IOAPIC_POL_LOW ? "low " : "high", + entry.vector, entry.irr, entry.delivery_status); + if (ir_entry->format) + printk(KERN_DEBUG "%s, remapped, I(%04X), Z(%X)\n", + buf, (ir_entry->index << 15) | ir_entry->index, + ir_entry->zero); + else + printk(KERN_DEBUG "%s, %s, D(%02X), M(%1d)\n", + buf, + entry.dest_mode == IOAPIC_DEST_MODE_LOGICAL ? + "logical " : "physical", + entry.dest, entry.delivery_mode); } } -void ioapic_zap_locks(void) -{ - raw_spin_lock_init(&ioapic_lock); -} - static void __init print_IO_APIC(int ioapic_idx) { union IO_APIC_reg_00 reg_00; @@ -1451,16 +1329,13 @@ static void __init print_IO_APIC(int ioapic_idx) } printk(KERN_DEBUG ".... IRQ redirection table:\n"); - - x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries); + io_apic_print_entries(ioapic_idx, reg_01.bits.entries); } void __init print_IO_APICs(void) { int ioapic_idx; - struct irq_cfg *cfg; unsigned int irq; - struct irq_chip *chip; printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); for_each_ioapic(ioapic_idx) @@ -1480,18 +1355,20 @@ void __init print_IO_APICs(void) printk(KERN_DEBUG "IRQ to pin mappings:\n"); for_each_active_irq(irq) { struct irq_pin_list *entry; + struct irq_chip *chip; + struct mp_chip_data *data; chip = irq_get_chip(irq); - if (chip != &ioapic_chip) + if (chip != &ioapic_chip && chip != &ioapic_ir_chip) continue; - - cfg = irq_cfg(irq); - if (!cfg) + data = irq_get_chip_data(irq); + if (!data) continue; - if (list_empty(&cfg->irq_2_pin)) + if (list_empty(&data->irq_2_pin)) continue; + printk(KERN_DEBUG "IRQ%d ", irq); - for_each_irq_pin(entry, cfg->irq_2_pin) + for_each_irq_pin(entry, data->irq_2_pin) pr_cont("-> %d:%d", entry->apic, entry->pin); pr_cont("\n"); } @@ -1564,15 +1441,12 @@ void native_disable_io_apic(void) struct IO_APIC_route_entry entry; memset(&entry, 0, sizeof(entry)); - entry.mask = 0; /* Enabled */ - entry.trigger = 0; /* Edge */ - entry.irr = 0; - entry.polarity = 0; /* High */ - entry.delivery_status = 0; - entry.dest_mode = 0; /* Physical */ - entry.delivery_mode = dest_ExtINT; /* ExtInt */ - entry.vector = 0; - entry.dest = read_apic_id(); + entry.mask = IOAPIC_UNMASKED; + entry.trigger = IOAPIC_EDGE; + entry.polarity = IOAPIC_POL_HIGH; + entry.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; + entry.delivery_mode = dest_ExtINT; + entry.dest = read_apic_id(); /* * Add it to the IO-APIC irq-routing table: @@ -1582,7 +1456,6 @@ void native_disable_io_apic(void) if (cpu_has_apic || apic_from_smp_config()) disconnect_bsp_APIC(ioapic_i8259.pin != -1); - } /* @@ -1792,7 +1665,6 @@ static int __init timer_irq_works(void) * This is not complete - we should be able to fake * an edge even if it isn't on the 8259A... */ - static unsigned int startup_ioapic_irq(struct irq_data *data) { int was_pending = 0, irq = data->irq; @@ -1804,74 +1676,22 @@ static unsigned int startup_ioapic_irq(struct irq_data *data) if (legacy_pic->irq_pending(irq)) was_pending = 1; } - __unmask_ioapic(irqd_cfg(data)); + __unmask_ioapic(data->chip_data); raw_spin_unlock_irqrestore(&ioapic_lock, flags); return was_pending; } -/* - * Level and edge triggered IO-APIC interrupts need different handling, - * so we use two separate IRQ descriptors. Edge triggered IRQs can be - * handled with the level-triggered descriptor, but that one has slightly - * more overhead. Level-triggered interrupts cannot be handled with the - * edge-triggered handler, without risking IRQ storms and other ugly - * races. - */ - -static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg) -{ - int apic, pin; - struct irq_pin_list *entry; - u8 vector = cfg->vector; - - for_each_irq_pin(entry, cfg->irq_2_pin) { - unsigned int reg; - - apic = entry->apic; - pin = entry->pin; - - io_apic_write(apic, 0x11 + pin*2, dest); - reg = io_apic_read(apic, 0x10 + pin*2); - reg &= ~IO_APIC_REDIR_VECTOR_MASK; - reg |= vector; - io_apic_modify(apic, 0x10 + pin*2, reg); - } -} - -int native_ioapic_set_affinity(struct irq_data *data, - const struct cpumask *mask, - bool force) -{ - unsigned int dest, irq = data->irq; - unsigned long flags; - int ret; - - if (!config_enabled(CONFIG_SMP)) - return -EPERM; - - raw_spin_lock_irqsave(&ioapic_lock, flags); - ret = apic_set_affinity(data, mask, &dest); - if (!ret) { - /* Only the high 8 bits are valid. */ - dest = SET_APIC_LOGICAL_ID(dest); - __target_IO_APIC_irq(irq, dest, irqd_cfg(data)); - ret = IRQ_SET_MASK_OK_NOCOPY; - } - raw_spin_unlock_irqrestore(&ioapic_lock, flags); - return ret; -} - atomic_t irq_mis_count; #ifdef CONFIG_GENERIC_PENDING_IRQ -static bool io_apic_level_ack_pending(struct irq_cfg *cfg) +static bool io_apic_level_ack_pending(struct mp_chip_data *data) { struct irq_pin_list *entry; unsigned long flags; raw_spin_lock_irqsave(&ioapic_lock, flags); - for_each_irq_pin(entry, cfg->irq_2_pin) { + for_each_irq_pin(entry, data->irq_2_pin) { unsigned int reg; int pin; @@ -1888,19 +1708,18 @@ static bool io_apic_level_ack_pending(struct irq_cfg *cfg) return false; } -static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +static inline bool ioapic_irqd_mask(struct irq_data *data) { /* If we are moving the irq we need to mask it */ if (unlikely(irqd_is_setaffinity_pending(data) && !irqd_irq_inprogress(data))) { - mask_ioapic(cfg); + mask_ioapic_irq(data); return true; } return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, - struct irq_cfg *cfg, bool masked) +static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) { if (unlikely(masked)) { /* Only migrate the irq if the ack has been received. @@ -1929,31 +1748,30 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, * accurate and is causing problems then it is a hardware bug * and you can go talk to the chipset vendor about it. */ - if (!io_apic_level_ack_pending(cfg)) + if (!io_apic_level_ack_pending(data->chip_data)) irq_move_masked_irq(data); - unmask_ioapic(cfg); + unmask_ioapic_irq(data); } } #else -static inline bool ioapic_irqd_mask(struct irq_data *data, struct irq_cfg *cfg) +static inline bool ioapic_irqd_mask(struct irq_data *data) { return false; } -static inline void ioapic_irqd_unmask(struct irq_data *data, - struct irq_cfg *cfg, bool masked) +static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) { } #endif -static void ack_ioapic_level(struct irq_data *data) +static void ioapic_ack_level(struct irq_data *irq_data) { - struct irq_cfg *cfg = irqd_cfg(data); - int i, irq = data->irq; + struct irq_cfg *cfg = irqd_cfg(irq_data); unsigned long v; bool masked; + int i; irq_complete_move(cfg); - masked = ioapic_irqd_mask(data, cfg); + masked = ioapic_irqd_mask(irq_data); /* * It appears there is an erratum which affects at least version 0x11 @@ -2005,11 +1823,49 @@ static void ack_ioapic_level(struct irq_data *data) */ if (!(v & (1 << (i & 0x1f)))) { atomic_inc(&irq_mis_count); + eoi_ioapic_pin(cfg->vector, irq_data->chip_data); + } + + ioapic_irqd_unmask(irq_data, masked); +} + +static void ioapic_ir_ack_level(struct irq_data *irq_data) +{ + struct mp_chip_data *data = irq_data->chip_data; + + /* + * Intr-remapping uses pin number as the virtual vector + * in the RTE. Actual vector is programmed in + * intr-remapping table entry. Hence for the io-apic + * EOI we use the pin number. + */ + ack_APIC_irq(); + eoi_ioapic_pin(data->entry.vector, data); +} + +static int ioapic_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = irq_data->parent_data; + struct mp_chip_data *data = irq_data->chip_data; + struct irq_pin_list *entry; + struct irq_cfg *cfg; + unsigned long flags; + int ret; - eoi_ioapic_irq(irq, cfg); + ret = parent->chip->irq_set_affinity(parent, mask, force); + raw_spin_lock_irqsave(&ioapic_lock, flags); + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { + cfg = irqd_cfg(irq_data); + data->entry.dest = cfg->dest_apicid; + data->entry.vector = cfg->vector; + for_each_irq_pin(entry, data->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, + data->entry); } + raw_spin_unlock_irqrestore(&ioapic_lock, flags); - ioapic_irqd_unmask(data, cfg, masked); + return ret; } static struct irq_chip ioapic_chip __read_mostly = { @@ -2017,10 +1873,20 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_startup = startup_ioapic_irq, .irq_mask = mask_ioapic_irq, .irq_unmask = unmask_ioapic_irq, - .irq_ack = apic_ack_edge, - .irq_eoi = ack_ioapic_level, - .irq_set_affinity = native_ioapic_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_ack = irq_chip_ack_parent, + .irq_eoi = ioapic_ack_level, + .irq_set_affinity = ioapic_set_affinity, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +static struct irq_chip ioapic_ir_chip __read_mostly = { + .name = "IR-IO-APIC", + .irq_startup = startup_ioapic_irq, + .irq_mask = mask_ioapic_irq, + .irq_unmask = unmask_ioapic_irq, + .irq_ack = irq_chip_ack_parent, + .irq_eoi = ioapic_ir_ack_level, + .irq_set_affinity = ioapic_set_affinity, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -2114,12 +1980,12 @@ static inline void __init unlock_ExtINT_logic(void) memset(&entry1, 0, sizeof(entry1)); - entry1.dest_mode = 0; /* physical delivery */ - entry1.mask = 0; /* unmask IRQ now */ + entry1.dest_mode = IOAPIC_DEST_MODE_PHYSICAL; + entry1.mask = IOAPIC_UNMASKED; entry1.dest = hard_smp_processor_id(); entry1.delivery_mode = dest_ExtINT; entry1.polarity = entry0.polarity; - entry1.trigger = 0; + entry1.trigger = IOAPIC_EDGE; entry1.vector = 0; ioapic_write_entry(apic, pin, entry1); @@ -2153,6 +2019,25 @@ static int __init disable_timer_pin_setup(char *arg) } early_param("disable_timer_pin_1", disable_timer_pin_setup); +static int mp_alloc_timer_irq(int ioapic, int pin) +{ + int irq = -1; + struct irq_domain *domain = mp_ioapic_irqdomain(ioapic); + + if (domain) { + struct irq_alloc_info info; + + ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 0, 0); + info.ioapic_id = mpc_ioapic_id(ioapic); + info.ioapic_pin = pin; + mutex_lock(&ioapic_mutex); + irq = alloc_isa_irq_from_domain(domain, 0, ioapic, pin, &info); + mutex_unlock(&ioapic_mutex); + } + + return irq; +} + /* * This code may look a bit paranoid, but it's supposed to cooperate with * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ @@ -2163,7 +2048,9 @@ early_param("disable_timer_pin_1", disable_timer_pin_setup); */ static inline void __init check_timer(void) { - struct irq_cfg *cfg = irq_cfg(0); + struct irq_data *irq_data = irq_get_irq_data(0); + struct mp_chip_data *data = irq_data->chip_data; + struct irq_cfg *cfg = irqd_cfg(irq_data); int node = cpu_to_node(0); int apic1, pin1, apic2, pin2; unsigned long flags; @@ -2175,7 +2062,6 @@ static inline void __init check_timer(void) * get/set the timer IRQ vector: */ legacy_pic->mask(0); - assign_irq_vector(0, cfg, apic->target_cpus()); /* * As IRQ0 is to be enabled in the 8259A, the virtual @@ -2216,23 +2102,21 @@ static inline void __init check_timer(void) } if (pin1 != -1) { - /* - * Ok, does IRQ0 through the IOAPIC work? - */ + /* Ok, does IRQ0 through the IOAPIC work? */ if (no_pin1) { - add_pin_to_irq_node(cfg, node, apic1, pin1); - setup_timer_IRQ0_pin(apic1, pin1, cfg->vector); + mp_alloc_timer_irq(apic1, pin1); } else { - /* for edge trigger, setup_ioapic_irq already - * leave it unmasked. + /* + * for edge trigger, it's already unmasked, * so only need to unmask if it is level-trigger * do we really have level trigger timer? */ int idx; idx = find_irq_entry(apic1, pin1, mp_INT); if (idx != -1 && irq_trigger(idx)) - unmask_ioapic(cfg); + unmask_ioapic_irq(irq_get_chip_data(0)); } + irq_domain_activate_irq(irq_data); if (timer_irq_works()) { if (disable_timer_pin_1 > 0) clear_IO_APIC_pin(0, pin1); @@ -2252,8 +2136,8 @@ static inline void __init check_timer(void) /* * legacy devices should be connected to IO APIC #0 */ - replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2); - setup_timer_IRQ0_pin(apic2, pin2, cfg->vector); + replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2); + irq_domain_activate_irq(irq_data); legacy_pic->unmask(0); if (timer_irq_works()) { apic_printk(APIC_QUIET, KERN_INFO "....... works.\n"); @@ -2330,36 +2214,35 @@ out: static int mp_irqdomain_create(int ioapic) { - size_t size; + struct irq_alloc_info info; + struct irq_domain *parent; int hwirqs = mp_ioapic_pin_count(ioapic); struct ioapic *ip = &ioapics[ioapic]; struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); - size = sizeof(struct mp_pin_info) * mp_ioapic_pin_count(ioapic); - ip->pin_info = kzalloc(size, GFP_KERNEL); - if (!ip->pin_info) - return -ENOMEM; - if (cfg->type == IOAPIC_DOMAIN_INVALID) return 0; + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_IOAPIC; + info.ioapic_id = mpc_ioapic_id(ioapic); + parent = irq_remapping_get_ir_irq_domain(&info); + if (!parent) + parent = x86_vector_domain; + ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops, (void *)(long)ioapic); - if(!ip->irqdomain) { - kfree(ip->pin_info); - ip->pin_info = NULL; + if (!ip->irqdomain) return -ENOMEM; - } + + ip->irqdomain->parent = parent; if (cfg->type == IOAPIC_DOMAIN_LEGACY || cfg->type == IOAPIC_DOMAIN_STRICT) ioapic_dynirq_base = max(ioapic_dynirq_base, gsi_cfg->gsi_end + 1); - if (gsi_cfg->gsi_base == 0) - irq_set_default_host(ip->irqdomain); - return 0; } @@ -2369,8 +2252,6 @@ static void ioapic_destroy_irqdomain(int idx) irq_domain_remove(ioapics[idx].irqdomain); ioapics[idx].irqdomain = NULL; } - kfree(ioapics[idx].pin_info); - ioapics[idx].pin_info = NULL; } void __init setup_IO_APIC(void) @@ -2400,20 +2281,6 @@ void __init setup_IO_APIC(void) ioapic_initialized = 1; } -/* - * Called after all the initialization is done. If we didn't find any - * APIC bugs then we can allow the modify fast path - */ - -static int __init io_apic_bug_finalize(void) -{ - if (sis_apic_bug == -1) - sis_apic_bug = 0; - return 0; -} - -late_initcall(io_apic_bug_finalize); - static void resume_ioapic_id(int ioapic_idx) { unsigned long flags; @@ -2452,20 +2319,6 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); -static int -io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr) -{ - struct irq_cfg *cfg = alloc_irq_and_cfg_at(irq, node); - int ret; - - if (!cfg) - return -EINVAL; - ret = __add_pin_to_irq_node(cfg, node, attr->ioapic, attr->ioapic_pin); - if (!ret) - setup_ioapic_irq(irq, cfg, attr); - return ret; -} - static int io_apic_get_redir_entries(int ioapic) { union IO_APIC_reg_01 reg_01; @@ -2669,7 +2522,9 @@ void __init setup_ioapic_dest(void) { int pin, ioapic, irq, irq_entry; const struct cpumask *mask; + struct irq_desc *desc; struct irq_data *idata; + struct irq_chip *chip; if (skip_ioapic_setup == 1) return; @@ -2683,19 +2538,24 @@ void __init setup_ioapic_dest(void) if (irq < 0 || !mp_init_irq_at_boot(ioapic, irq)) continue; - idata = irq_get_irq_data(irq); + desc = irq_to_desc(irq); + raw_spin_lock_irq(&desc->lock); + idata = irq_desc_get_irq_data(desc); /* * Honour affinities which have been set in early boot */ if (!irqd_can_balance(idata) || irqd_affinity_was_set(idata)) - mask = idata->affinity; + mask = irq_data_get_affinity_mask(idata); else mask = apic->target_cpus(); - x86_io_apic_ops.set_affinity(idata, mask, false); + chip = irq_data_get_irq_chip(idata); + /* Might be lapic_chip for irq 0 */ + if (chip->irq_set_affinity) + chip->irq_set_affinity(idata, mask, false); + raw_spin_unlock_irq(&desc->lock); } - } #endif @@ -2738,7 +2598,7 @@ static struct resource * __init ioapic_setup_resources(void) return res; } -void __init native_io_apic_init_mappings(void) +void __init io_apic_init_mappings(void) { unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0; struct resource *ioapic_res; @@ -2963,7 +2823,6 @@ int mp_unregister_ioapic(u32 gsi_base) { int ioapic, pin; int found = 0; - struct mp_pin_info *pin_info; for_each_ioapic(ioapic) if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) { @@ -2976,11 +2835,17 @@ int mp_unregister_ioapic(u32 gsi_base) } for_each_pin(ioapic, pin) { - pin_info = mp_pin_info(ioapic, pin); - if (pin_info->count) { - pr_warn("pin%d on IOAPIC%d is still in use.\n", - pin, ioapic); - return -EBUSY; + u32 gsi = mp_pin_to_gsi(ioapic, pin); + int irq = mp_map_gsi_to_irq(gsi, 0, NULL); + struct mp_chip_data *data; + + if (irq >= 0) { + data = irq_get_chip_data(irq); + if (data && data->count) { + pr_warn("pin%d on IOAPIC%d is still in use.\n", + pin, ioapic); + return -EBUSY; + } } } @@ -3007,108 +2872,145 @@ int mp_ioapic_registered(u32 gsi_base) return 0; } -static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr, - int ioapic, int ioapic_pin, - int trigger, int polarity) +static void mp_irqdomain_get_attr(u32 gsi, struct mp_chip_data *data, + struct irq_alloc_info *info) +{ + if (info && info->ioapic_valid) { + data->trigger = info->ioapic_trigger; + data->polarity = info->ioapic_polarity; + } else if (acpi_get_override_irq(gsi, &data->trigger, + &data->polarity) < 0) { + /* PCI interrupts are always active low level triggered. */ + data->trigger = IOAPIC_LEVEL; + data->polarity = IOAPIC_POL_LOW; + } +} + +static void mp_setup_entry(struct irq_cfg *cfg, struct mp_chip_data *data, + struct IO_APIC_route_entry *entry) { - irq_attr->ioapic = ioapic; - irq_attr->ioapic_pin = ioapic_pin; - irq_attr->trigger = trigger; - irq_attr->polarity = polarity; + memset(entry, 0, sizeof(*entry)); + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->dest = cfg->dest_apicid; + entry->vector = cfg->vector; + entry->trigger = data->trigger; + entry->polarity = data->polarity; + /* + * Mask level triggered irqs. Edge triggered irqs are masked + * by the irq core code in case they fire. + */ + if (data->trigger == IOAPIC_LEVEL) + entry->mask = IOAPIC_MASKED; + else + entry->mask = IOAPIC_UNMASKED; } -int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - int ioapic = (int)(long)domain->host_data; - struct mp_pin_info *info = mp_pin_info(ioapic, hwirq); - struct io_apic_irq_attr attr; + int ret, ioapic, pin; + struct irq_cfg *cfg; + struct irq_data *irq_data; + struct mp_chip_data *data; + struct irq_alloc_info *info = arg; + unsigned long flags; - /* Get default attribute if not set by caller yet */ - if (!info->set) { - u32 gsi = mp_pin_to_gsi(ioapic, hwirq); + if (!info || nr_irqs > 1) + return -EINVAL; + irq_data = irq_domain_get_irq_data(domain, virq); + if (!irq_data) + return -EINVAL; - if (acpi_get_override_irq(gsi, &info->trigger, - &info->polarity) < 0) { - /* - * PCI interrupts are always polarity one level - * triggered. - */ - info->trigger = 1; - info->polarity = 1; - } - info->node = NUMA_NO_NODE; + ioapic = mp_irqdomain_ioapic_idx(domain); + pin = info->ioapic_pin; + if (irq_find_mapping(domain, (irq_hw_number_t)pin) > 0) + return -EEXIST; - /* - * setup_IO_APIC_irqs() programs all legacy IRQs with default - * trigger and polarity attributes. Don't set the flag for that - * case so the first legacy IRQ user could reprogram the pin - * with real trigger and polarity attributes. - */ - if (virq >= nr_legacy_irqs() || info->count) - info->set = 1; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + info->ioapic_entry = &data->entry; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); + if (ret < 0) { + kfree(data); + return ret; } - set_io_apic_irq_attr(&attr, ioapic, hwirq, info->trigger, - info->polarity); - return io_apic_setup_irq_pin(virq, info->node, &attr); -} + INIT_LIST_HEAD(&data->irq_2_pin); + irq_data->hwirq = info->ioapic_pin; + irq_data->chip = (domain->parent == x86_vector_domain) ? + &ioapic_chip : &ioapic_ir_chip; + irq_data->chip_data = data; + mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); -void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq) -{ - struct irq_data *data = irq_get_irq_data(virq); - struct irq_cfg *cfg = irq_cfg(virq); - int ioapic = (int)(long)domain->host_data; - int pin = (int)data->hwirq; + cfg = irqd_cfg(irq_data); + add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); - ioapic_mask_entry(ioapic, pin); - __remove_pin_from_irq(cfg, ioapic, pin); - WARN_ON(!list_empty(&cfg->irq_2_pin)); - arch_teardown_hwirq(virq); -} + local_irq_save(flags); + if (info->ioapic_entry) + mp_setup_entry(cfg, data, info->ioapic_entry); + mp_register_handler(virq, data->trigger); + if (virq < nr_legacy_irqs()) + legacy_pic->mask(virq); + local_irq_restore(flags); -int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node) -{ - int ret = 0; - int ioapic, pin; - struct mp_pin_info *info; + apic_printk(APIC_VERBOSE, KERN_DEBUG + "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n", + ioapic, mpc_ioapic_id(ioapic), pin, cfg->vector, + virq, data->trigger, data->polarity, cfg->dest_apicid); - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return -ENODEV; + return 0; +} - pin = mp_find_ioapic_pin(ioapic, gsi); - info = mp_pin_info(ioapic, pin); - trigger = trigger ? 1 : 0; - polarity = polarity ? 1 : 0; +void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data; + struct mp_chip_data *data; - mutex_lock(&ioapic_mutex); - if (!info->set) { - info->trigger = trigger; - info->polarity = polarity; - info->node = node; - info->set = 1; - } else if (info->trigger != trigger || info->polarity != polarity) { - ret = -EBUSY; + BUG_ON(nr_irqs != 1); + irq_data = irq_domain_get_irq_data(domain, virq); + if (irq_data && irq_data->chip_data) { + data = irq_data->chip_data; + __remove_pin_from_irq(data, mp_irqdomain_ioapic_idx(domain), + (int)irq_data->hwirq); + WARN_ON(!list_empty(&data->irq_2_pin)); + kfree(irq_data->chip_data); } - mutex_unlock(&ioapic_mutex); - - return ret; + irq_domain_free_irqs_top(domain, virq, nr_irqs); } -/* Enable IOAPIC early just for system timer */ -void __init pre_init_apic_IRQ0(void) +void mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data) { - struct io_apic_irq_attr attr = { 0, 0, 0, 0 }; + unsigned long flags; + struct irq_pin_list *entry; + struct mp_chip_data *data = irq_data->chip_data; - printk(KERN_INFO "Early APIC setup for system timer0\n"); -#ifndef CONFIG_SMP - physid_set_mask_of_physid(boot_cpu_physical_apicid, - &phys_cpu_present_map); -#endif - setup_local_APIC(); + raw_spin_lock_irqsave(&ioapic_lock, flags); + for_each_irq_pin(entry, data->irq_2_pin) + __ioapic_write_entry(entry->apic, entry->pin, data->entry); + raw_spin_unlock_irqrestore(&ioapic_lock, flags); +} - io_apic_setup_irq_pin(0, 0, &attr); - irq_set_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, - "edge"); +void mp_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + /* It won't be called for IRQ with multiple IOAPIC pins associated */ + ioapic_mask_entry(mp_irqdomain_ioapic_idx(domain), + (int)irq_data->hwirq); +} + +int mp_irqdomain_ioapic_idx(struct irq_domain *domain) +{ + return (int)(long)domain->host_data; } + +const struct irq_domain_ops mp_ioapic_irqdomain_ops = { + .alloc = mp_irqdomain_alloc, + .free = mp_irqdomain_free, + .activate = mp_irqdomain_activate, + .deactivate = mp_irqdomain_deactivate, +}; diff --git a/kernel/arch/x86/kernel/apic/msi.c b/kernel/arch/x86/kernel/apic/msi.c index d6ba2d660..5f1feb685 100644 --- a/kernel/arch/x86/kernel/apic/msi.c +++ b/kernel/arch/x86/kernel/apic/msi.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Convert to hierarchical irqdomain * * 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 @@ -14,22 +16,23 @@ #include <linux/dmar.h> #include <linux/hpet.h> #include <linux/msi.h> +#include <asm/irqdomain.h> #include <asm/msidef.h> #include <asm/hpet.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/irq_remapping.h> -void native_compose_msi_msg(struct pci_dev *pdev, - unsigned int irq, unsigned int dest, - struct msi_msg *msg, u8 hpet_id) +static struct irq_domain *msi_default_domain; + +static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irq_cfg(irq); + struct irq_cfg *cfg = irqd_cfg(data); msg->address_hi = MSI_ADDR_BASE_HI; if (x2apic_enabled()) - msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest); + msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid); msg->address_lo = MSI_ADDR_BASE_LO | @@ -39,7 +42,7 @@ void native_compose_msi_msg(struct pci_dev *pdev, ((apic->irq_delivery_mode != dest_LowestPrio) ? MSI_ADDR_REDIRECTION_CPU : MSI_ADDR_REDIRECTION_LOWPRI) | - MSI_ADDR_DEST_ID(dest); + MSI_ADDR_DEST_ID(cfg->dest_apicid); msg->data = MSI_DATA_TRIGGER_EDGE | @@ -50,180 +53,201 @@ void native_compose_msi_msg(struct pci_dev *pdev, MSI_DATA_VECTOR(cfg->vector); } -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, - struct msi_msg *msg, u8 hpet_id) +/* + * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, + * which implement the MSI or MSI-X Capability Structure. + */ +static struct irq_chip pci_msi_controller = { + .name = "PCI-MSI", + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; + +int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - struct irq_cfg *cfg; - int err; - unsigned dest; + struct irq_domain *domain; + struct irq_alloc_info info; - if (disable_apic) - return -ENXIO; + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_MSI; + info.msi_dev = dev; - cfg = irq_cfg(irq); - err = assign_irq_vector(irq, cfg, apic->target_cpus()); - if (err) - return err; + domain = irq_remapping_get_irq_domain(&info); + if (domain == NULL) + domain = msi_default_domain; + if (domain == NULL) + return -ENOSYS; - err = apic->cpu_mask_to_apicid_and(cfg->domain, - apic->target_cpus(), &dest); - if (err) - return err; + return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); +} - x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id); +void native_teardown_msi_irq(unsigned int irq) +{ + irq_domain_free_irqs(irq, 1); +} - return 0; +static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->msi_hwirq; } -static int -msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) +static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) { - struct irq_cfg *cfg = irqd_cfg(data); - struct msi_msg msg; - unsigned int dest; - int ret; + struct pci_dev *pdev = to_pci_dev(dev); + struct msi_desc *desc = first_pci_msi_entry(pdev); + + init_irq_alloc_info(arg, NULL); + arg->msi_dev = pdev; + if (desc->msi_attrib.is_msix) { + arg->type = X86_IRQ_ALLOC_TYPE_MSIX; + } else { + arg->type = X86_IRQ_ALLOC_TYPE_MSI; + arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + } - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; + return 0; +} - __get_cached_msi_msg(data->msi_desc, &msg); +static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); +} + +static struct msi_domain_ops pci_msi_domain_ops = { + .get_hwirq = pci_msi_get_hwirq, + .msi_prepare = pci_msi_prepare, + .set_desc = pci_msi_set_desc, +}; - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); +static struct msi_domain_info pci_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &pci_msi_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; - __pci_write_msi_msg(data->msi_desc, &msg); +void arch_init_msi_domain(struct irq_domain *parent) +{ + if (disable_apic) + return; - return IRQ_SET_MASK_OK_NOCOPY; + msi_default_domain = pci_msi_create_irq_domain(NULL, + &pci_msi_domain_info, parent); + if (!msi_default_domain) + pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); } -/* - * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, - * which implement the MSI or MSI-X Capability Structure. - */ -static struct irq_chip msi_chip = { - .name = "PCI-MSI", +#ifdef CONFIG_IRQ_REMAP +static struct irq_chip pci_msi_ir_controller = { + .name = "IR-PCI-MSI", .irq_unmask = pci_msi_unmask_irq, .irq_mask = pci_msi_mask_irq, - .irq_ack = apic_ack_edge, - .irq_set_affinity = msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, + .irq_ack = irq_chip_ack_parent, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent, .flags = IRQCHIP_SKIP_SET_WAKE, }; -int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, - unsigned int irq_base, unsigned int irq_offset) -{ - struct irq_chip *chip = &msi_chip; - struct msi_msg msg; - unsigned int irq = irq_base + irq_offset; - int ret; - - ret = msi_compose_msg(dev, irq, &msg, -1); - if (ret < 0) - return ret; - - irq_set_msi_desc_off(irq_base, irq_offset, msidesc); - - /* - * MSI-X message is written per-IRQ, the offset is always 0. - * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. - */ - if (!irq_offset) - pci_write_msi_msg(irq, &msg); +static struct msi_domain_info pci_msi_ir_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, + .ops = &pci_msi_domain_ops, + .chip = &pci_msi_ir_controller, + .handler = handle_edge_irq, + .handler_name = "edge", +}; - setup_remapped_irq(irq, irq_cfg(irq), chip); +struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent) +{ + return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent); +} +#endif - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); +#ifdef CONFIG_DMAR_TABLE +static void dmar_msi_write_msg(struct irq_data *data, struct msi_msg *msg) +{ + dmar_msi_write(data->irq, msg); +} - dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq); +static struct irq_chip dmar_msi_controller = { + .name = "DMAR-MSI", + .irq_unmask = dmar_msi_unmask, + .irq_mask = dmar_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_write_msi_msg = dmar_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; - return 0; +static irq_hw_number_t dmar_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->dmar_id; } -int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +static int dmar_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - struct msi_desc *msidesc; - unsigned int irq; - int node, ret; + irq_domain_set_info(domain, virq, arg->dmar_id, info->chip, NULL, + handle_edge_irq, arg->dmar_data, "edge"); - /* Multiple MSI vectors only supported with interrupt remapping */ - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; + return 0; +} - node = dev_to_node(&dev->dev); +static struct msi_domain_ops dmar_msi_domain_ops = { + .get_hwirq = dmar_msi_get_hwirq, + .msi_init = dmar_msi_init, +}; - list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = irq_alloc_hwirq(node); - if (!irq) - return -ENOSPC; +static struct msi_domain_info dmar_msi_domain_info = { + .ops = &dmar_msi_domain_ops, + .chip = &dmar_msi_controller, +}; - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) { - irq_free_hwirq(irq); - return ret; - } +static struct irq_domain *dmar_get_irq_domain(void) +{ + static struct irq_domain *dmar_domain; + static DEFINE_MUTEX(dmar_lock); - } - return 0; -} + mutex_lock(&dmar_lock); + if (dmar_domain == NULL) + dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info, + x86_vector_domain); + mutex_unlock(&dmar_lock); -void native_teardown_msi_irq(unsigned int irq) -{ - irq_free_hwirq(irq); + return dmar_domain; } -#ifdef CONFIG_DMAR_TABLE -static int -dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) +int dmar_alloc_hwirq(int id, int node, void *arg) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest, irq = data->irq; - struct msi_msg msg; - int ret; - - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; + struct irq_domain *domain = dmar_get_irq_domain(); + struct irq_alloc_info info; - dmar_msi_read(irq, &msg); + if (!domain) + return -1; - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); - msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest); + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_DMAR; + info.dmar_id = id; + info.dmar_data = arg; - dmar_msi_write(irq, &msg); - - return IRQ_SET_MASK_OK_NOCOPY; + return irq_domain_alloc_irqs(domain, 1, node, &info); } -static struct irq_chip dmar_msi_type = { - .name = "DMAR_MSI", - .irq_unmask = dmar_msi_unmask, - .irq_mask = dmar_msi_mask, - .irq_ack = apic_ack_edge, - .irq_set_affinity = dmar_msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, - .flags = IRQCHIP_SKIP_SET_WAKE, -}; - -int arch_setup_dmar_msi(unsigned int irq) +void dmar_free_hwirq(int irq) { - int ret; - struct msi_msg msg; - - ret = msi_compose_msg(NULL, irq, &msg, -1); - if (ret < 0) - return ret; - dmar_msi_write(irq, &msg); - irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq, - "edge"); - return 0; + irq_domain_free_irqs(irq, 1); } #endif @@ -231,56 +255,103 @@ int arch_setup_dmar_msi(unsigned int irq) * MSI message composition */ #ifdef CONFIG_HPET_TIMER +static inline int hpet_dev_id(struct irq_domain *domain) +{ + struct msi_domain_info *info = msi_get_domain_info(domain); + + return (int)(long)info->data; +} -static int hpet_msi_set_affinity(struct irq_data *data, - const struct cpumask *mask, bool force) +static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); - struct msi_msg msg; - unsigned int dest; - int ret; + hpet_msi_write(irq_data_get_irq_handler_data(data), msg); +} - ret = apic_set_affinity(data, mask, &dest); - if (ret) - return ret; +static struct irq_chip hpet_msi_controller = { + .name = "HPET-MSI", + .irq_unmask = hpet_msi_unmask, + .irq_mask = hpet_msi_mask, + .irq_ack = irq_chip_ack_parent, + .irq_set_affinity = msi_domain_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, + .irq_compose_msi_msg = irq_msi_compose_msg, + .irq_write_msi_msg = hpet_msi_write_msg, + .flags = IRQCHIP_SKIP_SET_WAKE, +}; - hpet_msi_read(data->handler_data, &msg); +static irq_hw_number_t hpet_msi_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->hpet_index; +} - msg.data &= ~MSI_DATA_VECTOR_MASK; - msg.data |= MSI_DATA_VECTOR(cfg->vector); - msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; - msg.address_lo |= MSI_ADDR_DEST_ID(dest); +static int hpet_msi_init(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq, + irq_hw_number_t hwirq, msi_alloc_info_t *arg) +{ + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + irq_domain_set_info(domain, virq, arg->hpet_index, info->chip, NULL, + handle_edge_irq, arg->hpet_data, "edge"); - hpet_msi_write(data->handler_data, &msg); + return 0; +} - return IRQ_SET_MASK_OK_NOCOPY; +static void hpet_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); } -static struct irq_chip hpet_msi_type = { - .name = "HPET_MSI", - .irq_unmask = hpet_msi_unmask, - .irq_mask = hpet_msi_mask, - .irq_ack = apic_ack_edge, - .irq_set_affinity = hpet_msi_set_affinity, - .irq_retrigger = apic_retrigger_irq, - .flags = IRQCHIP_SKIP_SET_WAKE, +static struct msi_domain_ops hpet_msi_domain_ops = { + .get_hwirq = hpet_msi_get_hwirq, + .msi_init = hpet_msi_init, + .msi_free = hpet_msi_free, +}; + +static struct msi_domain_info hpet_msi_domain_info = { + .ops = &hpet_msi_domain_ops, + .chip = &hpet_msi_controller, }; -int default_setup_hpet_msi(unsigned int irq, unsigned int id) +struct irq_domain *hpet_create_irq_domain(int hpet_id) { - struct irq_chip *chip = &hpet_msi_type; - struct msi_msg msg; - int ret; + struct irq_domain *parent; + struct irq_alloc_info info; + struct msi_domain_info *domain_info; + + if (x86_vector_domain == NULL) + return NULL; + + domain_info = kzalloc(sizeof(*domain_info), GFP_KERNEL); + if (!domain_info) + return NULL; + + *domain_info = hpet_msi_domain_info; + domain_info->data = (void *)(long)hpet_id; + + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.hpet_id = hpet_id; + parent = irq_remapping_get_ir_irq_domain(&info); + if (parent == NULL) + parent = x86_vector_domain; + else + hpet_msi_controller.name = "IR-HPET-MSI"; + + return msi_create_irq_domain(NULL, domain_info, parent); +} - ret = msi_compose_msg(NULL, irq, &msg, id); - if (ret < 0) - return ret; +int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev, + int dev_num) +{ + struct irq_alloc_info info; - hpet_msi_write(irq_get_handler_data(irq), &msg); - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - setup_remapped_irq(irq, irq_cfg(irq), chip); + init_irq_alloc_info(&info, NULL); + info.type = X86_IRQ_ALLOC_TYPE_HPET; + info.hpet_data = dev; + info.hpet_id = hpet_dev_id(domain); + info.hpet_index = dev_num; - irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge"); - return 0; + return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, &info); } #endif diff --git a/kernel/arch/x86/kernel/apic/probe_32.c b/kernel/arch/x86/kernel/apic/probe_32.c index bda488680..7694ae6c1 100644 --- a/kernel/arch/x86/kernel/apic/probe_32.c +++ b/kernel/arch/x86/kernel/apic/probe_32.c @@ -111,7 +111,6 @@ static struct apic apic_default = { .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, - .wait_for_init_deassert = true, .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, diff --git a/kernel/arch/x86/kernel/apic/vector.c b/kernel/arch/x86/kernel/apic/vector.c index 6cedd7914..a35f6b547 100644 --- a/kernel/arch/x86/kernel/apic/vector.c +++ b/kernel/arch/x86/kernel/apic/vector.c @@ -3,6 +3,8 @@ * * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo * Moved from arch/x86/kernel/apic/io_apic.c. + * Jiang Liu <jiang.liu@linux.intel.com> + * Enable support of hierarchical irqdomains * * 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 @@ -11,15 +13,28 @@ #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compiler.h> -#include <linux/irqdomain.h> #include <linux/slab.h> +#include <asm/irqdomain.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/i8259.h> #include <asm/desc.h> #include <asm/irq_remapping.h> +struct apic_chip_data { + struct irq_cfg cfg; + cpumask_var_t domain; + cpumask_var_t old_domain; + u8 move_in_progress : 1; +}; + +struct irq_domain *x86_vector_domain; static DEFINE_RAW_SPINLOCK(vector_lock); +static cpumask_var_t vector_cpumask, vector_searchmask, searched_cpumask; +static struct irq_chip lapic_controller; +#ifdef CONFIG_X86_IO_APIC +static struct apic_chip_data *legacy_irq_data[NR_IRQS_LEGACY]; +#endif void lock_vector_lock(void) { @@ -34,71 +49,59 @@ void unlock_vector_lock(void) raw_spin_unlock(&vector_lock); } -struct irq_cfg *irq_cfg(unsigned int irq) +static struct apic_chip_data *apic_chip_data(struct irq_data *irq_data) { - return irq_get_chip_data(irq); + if (!irq_data) + return NULL; + + while (irq_data->parent_data) + irq_data = irq_data->parent_data; + + return irq_data->chip_data; } struct irq_cfg *irqd_cfg(struct irq_data *irq_data) { - return irq_data->chip_data; + struct apic_chip_data *data = apic_chip_data(irq_data); + + return data ? &data->cfg : NULL; } -static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node) +struct irq_cfg *irq_cfg(unsigned int irq) { - struct irq_cfg *cfg; + return irqd_cfg(irq_get_irq_data(irq)); +} - cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node); - if (!cfg) +static struct apic_chip_data *alloc_apic_chip_data(int node) +{ + struct apic_chip_data *data; + + data = kzalloc_node(sizeof(*data), GFP_KERNEL, node); + if (!data) return NULL; - if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node)) - goto out_cfg; - if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node)) + if (!zalloc_cpumask_var_node(&data->domain, GFP_KERNEL, node)) + goto out_data; + if (!zalloc_cpumask_var_node(&data->old_domain, GFP_KERNEL, node)) goto out_domain; -#ifdef CONFIG_X86_IO_APIC - INIT_LIST_HEAD(&cfg->irq_2_pin); -#endif - return cfg; + return data; out_domain: - free_cpumask_var(cfg->domain); -out_cfg: - kfree(cfg); + free_cpumask_var(data->domain); +out_data: + kfree(data); return NULL; } -struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) +static void free_apic_chip_data(struct apic_chip_data *data) { - int res = irq_alloc_desc_at(at, node); - struct irq_cfg *cfg; - - if (res < 0) { - if (res != -EEXIST) - return NULL; - cfg = irq_cfg(at); - if (cfg) - return cfg; + if (data) { + free_cpumask_var(data->domain); + free_cpumask_var(data->old_domain); + kfree(data); } - - cfg = alloc_irq_cfg(at, node); - if (cfg) - irq_set_chip_data(at, cfg); - else - irq_free_desc(at); - return cfg; -} - -static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) -{ - if (!cfg) - return; - irq_set_chip_data(at, NULL); - free_cpumask_var(cfg->domain); - free_cpumask_var(cfg->old_domain); - kfree(cfg); } -static int -__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +static int __assign_irq_vector(int irq, struct apic_chip_data *d, + const struct cpumask *mask) { /* * NOTE! The local APIC isn't very good at handling @@ -113,38 +116,47 @@ __assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) */ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START; static int current_offset = VECTOR_OFFSET_START % 16; - int cpu, err; - cpumask_var_t tmp_mask; + int cpu, vector; - if (cfg->move_in_progress) + /* + * If there is still a move in progress or the previous move has not + * been cleaned up completely, tell the caller to come back later. + */ + if (d->move_in_progress || + cpumask_intersects(d->old_domain, cpu_online_mask)) return -EBUSY; - if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC)) - return -ENOMEM; - /* Only try and allocate irqs on cpus that are present */ - err = -ENOSPC; - cpumask_clear(cfg->old_domain); + cpumask_clear(d->old_domain); + cpumask_clear(searched_cpumask); cpu = cpumask_first_and(mask, cpu_online_mask); while (cpu < nr_cpu_ids) { - int new_cpu, vector, offset; + int new_cpu, offset; + + /* Get the possible target cpus for @mask/@cpu from the apic */ + apic->vector_allocation_domain(cpu, vector_cpumask, mask); - apic->vector_allocation_domain(cpu, tmp_mask, mask); + /* + * Clear the offline cpus from @vector_cpumask for searching + * and verify whether the result overlaps with @mask. If true, + * then the call to apic->cpu_mask_to_apicid_and() will + * succeed as well. If not, no point in trying to find a + * vector in this mask. + */ + cpumask_and(vector_searchmask, vector_cpumask, cpu_online_mask); + if (!cpumask_intersects(vector_searchmask, mask)) + goto next_cpu; - if (cpumask_subset(tmp_mask, cfg->domain)) { - err = 0; - if (cpumask_equal(tmp_mask, cfg->domain)) - break; + if (cpumask_subset(vector_cpumask, d->domain)) { + if (cpumask_equal(vector_cpumask, d->domain)) + goto success; /* - * New cpumask using the vector is a proper subset of - * the current in use mask. So cleanup the vector - * allocation for the members that are not used anymore. + * Mark the cpus which are not longer in the mask for + * cleanup. */ - cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); - cpumask_and(cfg->domain, cfg->domain, tmp_mask); - break; + cpumask_andnot(d->old_domain, d->domain, vector_cpumask); + vector = d->cfg.vector; + goto update; } vector = current_vector; @@ -156,85 +168,211 @@ next: vector = FIRST_EXTERNAL_VECTOR + offset; } - if (unlikely(current_vector == vector)) { - cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask); - cpumask_andnot(tmp_mask, mask, cfg->old_domain); - cpu = cpumask_first_and(tmp_mask, cpu_online_mask); - continue; - } + /* If the search wrapped around, try the next cpu */ + if (unlikely(current_vector == vector)) + goto next_cpu; if (test_bit(vector, used_vectors)) goto next; - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) { - if (per_cpu(vector_irq, new_cpu)[vector] > - VECTOR_UNDEFINED) + for_each_cpu(new_cpu, vector_searchmask) { + if (!IS_ERR_OR_NULL(per_cpu(vector_irq, new_cpu)[vector])) goto next; } /* Found one! */ current_vector = vector; current_offset = offset; - if (cfg->vector) { - cpumask_copy(cfg->old_domain, cfg->domain); - cfg->move_in_progress = - cpumask_intersects(cfg->old_domain, cpu_online_mask); - } - for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) - per_cpu(vector_irq, new_cpu)[vector] = irq; - cfg->vector = vector; - cpumask_copy(cfg->domain, tmp_mask); - err = 0; - break; + /* Schedule the old vector for cleanup on all cpus */ + if (d->cfg.vector) + cpumask_copy(d->old_domain, d->domain); + for_each_cpu(new_cpu, vector_searchmask) + per_cpu(vector_irq, new_cpu)[vector] = irq_to_desc(irq); + goto update; + +next_cpu: + /* + * We exclude the current @vector_cpumask from the requested + * @mask and try again with the next online cpu in the + * result. We cannot modify @mask, so we use @vector_cpumask + * as a temporary buffer here as it will be reassigned when + * calling apic->vector_allocation_domain() above. + */ + cpumask_or(searched_cpumask, searched_cpumask, vector_cpumask); + cpumask_andnot(vector_cpumask, mask, searched_cpumask); + cpu = cpumask_first_and(vector_cpumask, cpu_online_mask); + continue; } - free_cpumask_var(tmp_mask); + return -ENOSPC; - return err; +update: + /* + * Exclude offline cpus from the cleanup mask and set the + * move_in_progress flag when the result is not empty. + */ + cpumask_and(d->old_domain, d->old_domain, cpu_online_mask); + d->move_in_progress = !cpumask_empty(d->old_domain); + d->cfg.vector = vector; + cpumask_copy(d->domain, vector_cpumask); +success: + /* + * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail + * as we already established, that mask & d->domain & cpu_online_mask + * is not empty. + */ + BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, + &d->cfg.dest_apicid)); + return 0; } -int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask) +static int assign_irq_vector(int irq, struct apic_chip_data *data, + const struct cpumask *mask) { int err; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, cfg, mask); + err = __assign_irq_vector(irq, data, mask); raw_spin_unlock_irqrestore(&vector_lock, flags); return err; } -void clear_irq_vector(int irq, struct irq_cfg *cfg) +static int assign_irq_vector_policy(int irq, int node, + struct apic_chip_data *data, + struct irq_alloc_info *info) +{ + if (info && info->mask) + return assign_irq_vector(irq, data, info->mask); + if (node != NUMA_NO_NODE && + assign_irq_vector(irq, data, cpumask_of_node(node)) == 0) + return 0; + return assign_irq_vector(irq, data, apic->target_cpus()); +} + +static void clear_irq_vector(int irq, struct apic_chip_data *data) { + struct irq_desc *desc; int cpu, vector; - unsigned long flags; - raw_spin_lock_irqsave(&vector_lock, flags); - BUG_ON(!cfg->vector); + BUG_ON(!data->cfg.vector); - vector = cfg->vector; - for_each_cpu_and(cpu, cfg->domain, cpu_online_mask) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + vector = data->cfg.vector; + for_each_cpu_and(cpu, data->domain, cpu_online_mask) + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; - cfg->vector = 0; - cpumask_clear(cfg->domain); + data->cfg.vector = 0; + cpumask_clear(data->domain); - if (likely(!cfg->move_in_progress)) { - raw_spin_unlock_irqrestore(&vector_lock, flags); + /* + * If move is in progress or the old_domain mask is not empty, + * i.e. the cleanup IPI has not been processed yet, we need to remove + * the old references to desc from all cpus vector tables. + */ + if (!data->move_in_progress && cpumask_empty(data->old_domain)) return; - } - for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) { + desc = irq_to_desc(irq); + for_each_cpu_and(cpu, data->old_domain, cpu_online_mask) { for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - if (per_cpu(vector_irq, cpu)[vector] != irq) + if (per_cpu(vector_irq, cpu)[vector] != desc) continue; - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; break; } } - cfg->move_in_progress = 0; - raw_spin_unlock_irqrestore(&vector_lock, flags); + data->move_in_progress = 0; +} + +void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask) +{ + memset(info, 0, sizeof(*info)); + info->mask = mask; +} + +void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src) +{ + if (src) + *dst = *src; + else + memset(dst, 0, sizeof(*dst)); +} + +static void x86_vector_free_irqs(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct apic_chip_data *apic_data; + struct irq_data *irq_data; + unsigned long flags; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(x86_vector_domain, virq + i); + if (irq_data && irq_data->chip_data) { + raw_spin_lock_irqsave(&vector_lock, flags); + clear_irq_vector(virq + i, irq_data->chip_data); + apic_data = irq_data->chip_data; + irq_domain_reset_irq_data(irq_data); + raw_spin_unlock_irqrestore(&vector_lock, flags); + free_apic_chip_data(apic_data); +#ifdef CONFIG_X86_IO_APIC + if (virq + i < nr_legacy_irqs()) + legacy_irq_data[virq + i] = NULL; +#endif + } + } } +static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct irq_alloc_info *info = arg; + struct apic_chip_data *data; + struct irq_data *irq_data; + int i, err, node; + + if (disable_apic) + return -ENXIO; + + /* Currently vector allocator can't guarantee contiguous allocations */ + if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1) + return -ENOSYS; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + BUG_ON(!irq_data); + node = irq_data_get_node(irq_data); +#ifdef CONFIG_X86_IO_APIC + if (virq + i < nr_legacy_irqs() && legacy_irq_data[virq + i]) + data = legacy_irq_data[virq + i]; + else +#endif + data = alloc_apic_chip_data(node); + if (!data) { + err = -ENOMEM; + goto error; + } + + irq_data->chip = &lapic_controller; + irq_data->chip_data = data; + irq_data->hwirq = virq + i; + err = assign_irq_vector_policy(virq + i, node, data, info); + if (err) + goto error; + } + + return 0; + +error: + x86_vector_free_irqs(domain, virq, i + 1); + return err; +} + +static const struct irq_domain_ops x86_vector_domain_ops = { + .alloc = x86_vector_alloc_irqs, + .free = x86_vector_free_irqs, +}; + int __init arch_probe_nr_irqs(void) { int nr; @@ -255,57 +393,92 @@ int __init arch_probe_nr_irqs(void) if (nr < nr_irqs) nr_irqs = nr; - return nr_legacy_irqs(); + /* + * We don't know if PIC is present at this point so we need to do + * probe() to get the right number of legacy IRQs. + */ + return legacy_pic->probe(); } +#ifdef CONFIG_X86_IO_APIC +static void init_legacy_irqs(void) +{ + int i, node = cpu_to_node(0); + struct apic_chip_data *data; + + /* + * For legacy IRQ's, start with assigning irq0 to irq15 to + * ISA_IRQ_VECTOR(i) for all cpu's. + */ + for (i = 0; i < nr_legacy_irqs(); i++) { + data = legacy_irq_data[i] = alloc_apic_chip_data(node); + BUG_ON(!data); + + data->cfg.vector = ISA_IRQ_VECTOR(i); + cpumask_setall(data->domain); + irq_set_chip_data(i, data); + } +} +#else +static void init_legacy_irqs(void) { } +#endif + int __init arch_early_irq_init(void) { + init_legacy_irqs(); + + x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops, + NULL); + BUG_ON(x86_vector_domain == NULL); + irq_set_default_host(x86_vector_domain); + + arch_init_msi_domain(x86_vector_domain); + arch_init_htirq_domain(x86_vector_domain); + + BUG_ON(!alloc_cpumask_var(&vector_cpumask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL)); + BUG_ON(!alloc_cpumask_var(&searched_cpumask, GFP_KERNEL)); + return arch_early_ioapic_init(); } +/* Initialize vector_irq on a new cpu */ static void __setup_vector_irq(int cpu) { - /* Initialize vector_irq on a new cpu */ + struct apic_chip_data *data; + struct irq_desc *desc; int irq, vector; - struct irq_cfg *cfg; - /* - * vector_lock will make sure that we don't run into irq vector - * assignments that might be happening on another cpu in parallel, - * while we setup our initial vector to irq mappings. - */ - raw_spin_lock(&vector_lock); /* Mark the inuse vectors */ - for_each_active_irq(irq) { - cfg = irq_cfg(irq); - if (!cfg) - continue; + for_each_irq_desc(irq, desc) { + struct irq_data *idata = irq_desc_get_irq_data(desc); - if (!cpumask_test_cpu(cpu, cfg->domain)) + data = apic_chip_data(idata); + if (!data || !cpumask_test_cpu(cpu, data->domain)) continue; - vector = cfg->vector; - per_cpu(vector_irq, cpu)[vector] = irq; + vector = data->cfg.vector; + per_cpu(vector_irq, cpu)[vector] = desc; } /* Mark the free vectors */ for (vector = 0; vector < NR_VECTORS; ++vector) { - irq = per_cpu(vector_irq, cpu)[vector]; - if (irq <= VECTOR_UNDEFINED) + desc = per_cpu(vector_irq, cpu)[vector]; + if (IS_ERR_OR_NULL(desc)) continue; - cfg = irq_cfg(irq); - if (!cpumask_test_cpu(cpu, cfg->domain)) - per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED; + data = apic_chip_data(irq_desc_get_irq_data(desc)); + if (!cpumask_test_cpu(cpu, data->domain)) + per_cpu(vector_irq, cpu)[vector] = VECTOR_UNUSED; } - raw_spin_unlock(&vector_lock); } /* - * Setup the vector to irq mappings. + * Setup the vector to irq mappings. Must be called with vector_lock held. */ void setup_vector_irq(int cpu) { int irq; + lockdep_assert_held(&vector_lock); /* * On most of the platforms, legacy PIC delivers the interrupts on the * boot cpu. But there are certain platforms where PIC interrupts are @@ -314,20 +487,20 @@ void setup_vector_irq(int cpu) * legacy vector to irq mapping: */ for (irq = 0; irq < nr_legacy_irqs(); irq++) - per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq; + per_cpu(vector_irq, cpu)[ISA_IRQ_VECTOR(irq)] = irq_to_desc(irq); __setup_vector_irq(cpu); } -int apic_retrigger_irq(struct irq_data *data) +static int apic_retrigger_irq(struct irq_data *irq_data) { - struct irq_cfg *cfg = irqd_cfg(data); + struct apic_chip_data *data = apic_chip_data(irq_data); unsigned long flags; int cpu; raw_spin_lock_irqsave(&vector_lock, flags); - cpu = cpumask_first_and(cfg->domain, cpu_online_mask); - apic->send_IPI_mask(cpumask_of(cpu), cfg->vector); + cpu = cpumask_first_and(data->domain, cpu_online_mask); + apic->send_IPI_mask(cpumask_of(cpu), data->cfg.vector); raw_spin_unlock_irqrestore(&vector_lock, flags); return 1; @@ -340,97 +513,101 @@ void apic_ack_edge(struct irq_data *data) ack_APIC_irq(); } -/* - * Either sets data->affinity to a valid value, and returns - * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and - * leaves data->affinity untouched. - */ -int apic_set_affinity(struct irq_data *data, const struct cpumask *mask, - unsigned int *dest_id) +static int apic_set_affinity(struct irq_data *irq_data, + const struct cpumask *dest, bool force) { - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int irq = data->irq; - int err; + struct apic_chip_data *data = irq_data->chip_data; + int err, irq = irq_data->irq; if (!config_enabled(CONFIG_SMP)) return -EPERM; - if (!cpumask_intersects(mask, cpu_online_mask)) + if (!cpumask_intersects(dest, cpu_online_mask)) return -EINVAL; - err = assign_irq_vector(irq, cfg, mask); - if (err) - return err; - - err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id); - if (err) { - if (assign_irq_vector(irq, cfg, data->affinity)) - pr_err("Failed to recover vector for irq %d\n", irq); - return err; - } + err = assign_irq_vector(irq, data, dest); + return err ? err : IRQ_SET_MASK_OK; +} - cpumask_copy(data->affinity, mask); +static struct irq_chip lapic_controller = { + .irq_ack = apic_ack_edge, + .irq_set_affinity = apic_set_affinity, + .irq_retrigger = apic_retrigger_irq, +}; - return 0; +#ifdef CONFIG_SMP +static void __send_cleanup_vector(struct apic_chip_data *data) +{ + raw_spin_lock(&vector_lock); + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); + data->move_in_progress = 0; + if (!cpumask_empty(data->old_domain)) + apic->send_IPI_mask(data->old_domain, IRQ_MOVE_CLEANUP_VECTOR); + raw_spin_unlock(&vector_lock); } -#ifdef CONFIG_SMP void send_cleanup_vector(struct irq_cfg *cfg) { - cpumask_var_t cleanup_mask; - - if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) { - unsigned int i; + struct apic_chip_data *data; - for_each_cpu_and(i, cfg->old_domain, cpu_online_mask) - apic->send_IPI_mask(cpumask_of(i), - IRQ_MOVE_CLEANUP_VECTOR); - } else { - cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask); - apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR); - free_cpumask_var(cleanup_mask); - } - cfg->move_in_progress = 0; + data = container_of(cfg, struct apic_chip_data, cfg); + if (data->move_in_progress) + __send_cleanup_vector(data); } asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) { unsigned vector, me; - ack_APIC_irq(); - irq_enter(); - exit_idle(); + entering_ack_irq(); + + /* Prevent vectors vanishing under us */ + raw_spin_lock(&vector_lock); me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - int irq; - unsigned int irr; + struct apic_chip_data *data; struct irq_desc *desc; - struct irq_cfg *cfg; - - irq = __this_cpu_read(vector_irq[vector]); - - if (irq <= VECTOR_UNDEFINED) - continue; + unsigned int irr; - desc = irq_to_desc(irq); - if (!desc) + retry: + desc = __this_cpu_read(vector_irq[vector]); + if (IS_ERR_OR_NULL(desc)) continue; - cfg = irq_cfg(irq); - if (!cfg) - continue; + if (!raw_spin_trylock(&desc->lock)) { + raw_spin_unlock(&vector_lock); + cpu_relax(); + raw_spin_lock(&vector_lock); + goto retry; + } - raw_spin_lock(&desc->lock); + data = apic_chip_data(irq_desc_get_irq_data(desc)); + if (!data) + goto unlock; /* - * Check if the irq migration is in progress. If so, we - * haven't received the cleanup request yet for this irq. + * Nothing to cleanup if irq migration is in progress + * or this cpu is not set in the cleanup mask. */ - if (cfg->move_in_progress) + if (data->move_in_progress || + !cpumask_test_cpu(me, data->old_domain)) goto unlock; - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) + /* + * We have two cases to handle here: + * 1) vector is unchanged but the target mask got reduced + * 2) vector and the target mask has changed + * + * #1 is obvious, but in #2 we have two vectors with the same + * irq descriptor: the old and the new vector. So we need to + * make sure that we only cleanup the old vector. The new + * vector has the current @vector number in the config and + * this cpu is part of the target mask. We better leave that + * one alone. + */ + if (vector == data->cfg.vector && + cpumask_test_cpu(me, data->domain)) goto unlock; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); @@ -445,25 +622,29 @@ asmlinkage __visible void smp_irq_move_cleanup_interrupt(void) apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR); goto unlock; } - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); + cpumask_clear_cpu(me, data->old_domain); unlock: raw_spin_unlock(&desc->lock); } - irq_exit(); + raw_spin_unlock(&vector_lock); + + exiting_irq(); } static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) { unsigned me; + struct apic_chip_data *data; - if (likely(!cfg->move_in_progress)) + data = container_of(cfg, struct apic_chip_data, cfg); + if (likely(!data->move_in_progress)) return; me = smp_processor_id(); - - if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) - send_cleanup_vector(cfg); + if (vector == data->cfg.vector && cpumask_test_cpu(me, data->domain)) + __send_cleanup_vector(data); } void irq_complete_move(struct irq_cfg *cfg) @@ -471,49 +652,50 @@ void irq_complete_move(struct irq_cfg *cfg) __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); } -void irq_force_complete_move(int irq) -{ - struct irq_cfg *cfg = irq_cfg(irq); - - if (!cfg) - return; - - __irq_complete_move(cfg, cfg->vector); -} -#endif - /* - * Dynamic irq allocate and deallocation. Should be replaced by irq domains! + * Called with @desc->lock held and interrupts disabled. */ -int arch_setup_hwirq(unsigned int irq, int node) +void irq_force_complete_move(struct irq_desc *desc) { - struct irq_cfg *cfg; - unsigned long flags; - int ret; + struct irq_data *irqdata = irq_desc_get_irq_data(desc); + struct apic_chip_data *data = apic_chip_data(irqdata); + struct irq_cfg *cfg = data ? &data->cfg : NULL; - cfg = alloc_irq_cfg(irq, node); if (!cfg) - return -ENOMEM; - - raw_spin_lock_irqsave(&vector_lock, flags); - ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); - raw_spin_unlock_irqrestore(&vector_lock, flags); - - if (!ret) - irq_set_chip_data(irq, cfg); - else - free_irq_cfg(irq, cfg); - return ret; -} + return; -void arch_teardown_hwirq(unsigned int irq) -{ - struct irq_cfg *cfg = irq_cfg(irq); + __irq_complete_move(cfg, cfg->vector); - free_remapped_irq(irq); - clear_irq_vector(irq, cfg); - free_irq_cfg(irq, cfg); + /* + * This is tricky. If the cleanup of @data->old_domain has not been + * done yet, then the following setaffinity call will fail with + * -EBUSY. This can leave the interrupt in a stale state. + * + * The cleanup cannot make progress because we hold @desc->lock. So in + * case @data->old_domain is not yet cleaned up, we need to drop the + * lock and acquire it again. @desc cannot go away, because the + * hotplug code holds the sparse irq lock. + */ + raw_spin_lock(&vector_lock); + /* Clean out all offline cpus (including ourself) first. */ + cpumask_and(data->old_domain, data->old_domain, cpu_online_mask); + while (!cpumask_empty(data->old_domain)) { + raw_spin_unlock(&vector_lock); + raw_spin_unlock(&desc->lock); + cpu_relax(); + raw_spin_lock(&desc->lock); + /* + * Reevaluate apic_chip_data. It might have been cleared after + * we dropped @desc->lock. + */ + data = apic_chip_data(irqdata); + if (!data) + return; + raw_spin_lock(&vector_lock); + } + raw_spin_unlock(&vector_lock); } +#endif static void __init print_APIC_field(int base) { diff --git a/kernel/arch/x86/kernel/apic/x2apic_cluster.c b/kernel/arch/x86/kernel/apic/x2apic_cluster.c index ab3219b3f..cc8311c4d 100644 --- a/kernel/arch/x86/kernel/apic/x2apic_cluster.c +++ b/kernel/arch/x86/kernel/apic/x2apic_cluster.c @@ -182,7 +182,7 @@ update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu) return notifier_from_errno(err); } -static struct notifier_block __refdata x2apic_cpu_notifier = { +static struct notifier_block x2apic_cpu_notifier = { .notifier_call = update_clusterinfo, }; @@ -272,7 +272,6 @@ static struct apic apic_x2apic_cluster = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/kernel/arch/x86/kernel/apic/x2apic_phys.c b/kernel/arch/x86/kernel/apic/x2apic_phys.c index 6fae733e9..662e9150e 100644 --- a/kernel/arch/x86/kernel/apic/x2apic_phys.c +++ b/kernel/arch/x86/kernel/apic/x2apic_phys.c @@ -21,11 +21,13 @@ early_param("x2apic_phys", set_x2apic_phys_mode); static bool x2apic_fadt_phys(void) { +#ifdef CONFIG_ACPI if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) && (acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL)) { printk(KERN_DEBUG "System requires x2apic physical mode\n"); return true; } +#endif return false; } @@ -126,7 +128,6 @@ static struct apic apic_x2apic_phys = { .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/kernel/arch/x86/kernel/apic/x2apic_uv_x.c b/kernel/arch/x86/kernel/apic/x2apic_uv_x.c index 3d2fbca33..ad2afff02 100644 --- a/kernel/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/kernel/arch/x86/kernel/apic/x2apic_uv_x.c @@ -248,7 +248,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) APIC_DM_STARTUP; uv_write_global_mmr64(pnode, UVH_IPI_INT, val); - atomic_set(&init_deasserted, 1); return 0; } @@ -414,7 +413,6 @@ static struct apic __refdata apic_x2apic_uv_x = { .send_IPI_self = uv_send_IPI_self, .wakeup_secondary_cpu = uv_wakeup_secondary, - .wait_for_init_deassert = false, .inquire_remote_apic = NULL, .read = native_apic_msr_read, diff --git a/kernel/arch/x86/kernel/apm_32.c b/kernel/arch/x86/kernel/apm_32.c index 927ec9235..052c9c302 100644 --- a/kernel/arch/x86/kernel/apm_32.c +++ b/kernel/arch/x86/kernel/apm_32.c @@ -919,7 +919,7 @@ recalc: } else if (jiffies_since_last_check > idle_period) { unsigned int idle_percentage; - idle_percentage = stime - last_stime; + idle_percentage = cputime_to_jiffies(stime - last_stime); idle_percentage *= 100; idle_percentage /= jiffies_since_last_check; use_apm_idle = (idle_percentage > idle_threshold); diff --git a/kernel/arch/x86/kernel/asm-offsets.c b/kernel/arch/x86/kernel/asm-offsets.c index 5701b5075..b7954ddd6 100644 --- a/kernel/arch/x86/kernel/asm-offsets.c +++ b/kernel/arch/x86/kernel/asm-offsets.c @@ -42,6 +42,22 @@ void common(void) { OFFSET(pbe_orig_address, pbe, orig_address); OFFSET(pbe_next, pbe, next); +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) + BLANK(); + OFFSET(IA32_SIGCONTEXT_ax, sigcontext_32, ax); + OFFSET(IA32_SIGCONTEXT_bx, sigcontext_32, bx); + OFFSET(IA32_SIGCONTEXT_cx, sigcontext_32, cx); + OFFSET(IA32_SIGCONTEXT_dx, sigcontext_32, dx); + OFFSET(IA32_SIGCONTEXT_si, sigcontext_32, si); + OFFSET(IA32_SIGCONTEXT_di, sigcontext_32, di); + OFFSET(IA32_SIGCONTEXT_bp, sigcontext_32, bp); + OFFSET(IA32_SIGCONTEXT_sp, sigcontext_32, sp); + OFFSET(IA32_SIGCONTEXT_ip, sigcontext_32, ip); + + BLANK(); + OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); +#endif + #ifdef CONFIG_PARAVIRT BLANK(); OFFSET(PARAVIRT_enabled, pv_info, paravirt_enabled); @@ -50,7 +66,9 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); +#ifdef CONFIG_X86_32 OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); +#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/kernel/arch/x86/kernel/asm-offsets_32.c b/kernel/arch/x86/kernel/asm-offsets_32.c index 47703aed7..6ce39025f 100644 --- a/kernel/arch/x86/kernel/asm-offsets_32.c +++ b/kernel/arch/x86/kernel/asm-offsets_32.c @@ -17,17 +17,6 @@ void foo(void); void foo(void) { - OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax); - OFFSET(IA32_SIGCONTEXT_bx, sigcontext, bx); - OFFSET(IA32_SIGCONTEXT_cx, sigcontext, cx); - OFFSET(IA32_SIGCONTEXT_dx, sigcontext, dx); - OFFSET(IA32_SIGCONTEXT_si, sigcontext, si); - OFFSET(IA32_SIGCONTEXT_di, sigcontext, di); - OFFSET(IA32_SIGCONTEXT_bp, sigcontext, bp); - OFFSET(IA32_SIGCONTEXT_sp, sigcontext, sp); - OFFSET(IA32_SIGCONTEXT_ip, sigcontext, ip); - BLANK(); - OFFSET(CPUINFO_x86, cpuinfo_x86, x86); OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor); OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model); @@ -37,10 +26,6 @@ void foo(void) OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); BLANK(); - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - OFFSET(TI_cpu, thread_info, cpu); - BLANK(); - OFFSET(PT_EBX, pt_regs, bx); OFFSET(PT_ECX, pt_regs, cx); OFFSET(PT_EDX, pt_regs, dx); @@ -60,9 +45,6 @@ void foo(void) OFFSET(PT_OLDSS, pt_regs, ss); BLANK(); - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext); - BLANK(); - OFFSET(saved_context_gdt_desc, saved_context, gdt_desc); BLANK(); diff --git a/kernel/arch/x86/kernel/asm-offsets_64.c b/kernel/arch/x86/kernel/asm-offsets_64.c index 5ce6f2da8..d8f42f902 100644 --- a/kernel/arch/x86/kernel/asm-offsets_64.c +++ b/kernel/arch/x86/kernel/asm-offsets_64.c @@ -29,27 +29,6 @@ int main(void) BLANK(); #endif -#ifdef CONFIG_IA32_EMULATION - OFFSET(TI_sysenter_return, thread_info, sysenter_return); - BLANK(); - -#define ENTRY(entry) OFFSET(IA32_SIGCONTEXT_ ## entry, sigcontext_ia32, entry) - ENTRY(ax); - ENTRY(bx); - ENTRY(cx); - ENTRY(dx); - ENTRY(si); - ENTRY(di); - ENTRY(bp); - ENTRY(sp); - ENTRY(ip); - BLANK(); -#undef ENTRY - - OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); - BLANK(); -#endif - #define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry) ENTRY(bx); ENTRY(cx); @@ -87,7 +66,7 @@ int main(void) DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); - DEFINE(__NR_ia32_syscall_max, sizeof(syscalls_ia32) - 1); + DEFINE(__NR_syscall_compat_max, sizeof(syscalls_ia32) - 1); DEFINE(IA32_NR_syscalls, sizeof(syscalls_ia32)); return 0; diff --git a/kernel/arch/x86/kernel/bootflag.c b/kernel/arch/x86/kernel/bootflag.c index 5de7f4c56..52c8e3c77 100644 --- a/kernel/arch/x86/kernel/bootflag.c +++ b/kernel/arch/x86/kernel/bootflag.c @@ -98,4 +98,4 @@ static int __init sbf_init(void) return 0; } -module_init(sbf_init); +arch_initcall(sbf_init); diff --git a/kernel/arch/x86/kernel/check.c b/kernel/arch/x86/kernel/check.c index 83a799562..145863d4d 100644 --- a/kernel/arch/x86/kernel/check.c +++ b/kernel/arch/x86/kernel/check.c @@ -1,4 +1,4 @@ -#include <linux/module.h> +#include <linux/init.h> #include <linux/sched.h> #include <linux/kthread.h> #include <linux/workqueue.h> @@ -91,7 +91,8 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) { start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), PAGE_SIZE, corruption_check_size); end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), @@ -162,6 +163,5 @@ static int start_periodic_check_for_corruption(void) schedule_delayed_work(&bios_check_work, 0); return 0; } - -module_init(start_periodic_check_for_corruption); +device_initcall(start_periodic_check_for_corruption); diff --git a/kernel/arch/x86/kernel/cpu/Makefile b/kernel/arch/x86/kernel/cpu/Makefile index 9bff68798..58031303e 100644 --- a/kernel/arch/x86/kernel/cpu/Makefile +++ b/kernel/arch/x86/kernel/cpu/Makefile @@ -41,11 +41,14 @@ obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_cstate.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ perf_event_intel_uncore_snb.o \ perf_event_intel_uncore_snbep.o \ perf_event_intel_uncore_nhmex.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_msr.o +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_msr.o endif diff --git a/kernel/arch/x86/kernel/cpu/amd.c b/kernel/arch/x86/kernel/cpu/amd.c index e4cf63301..a8816b325 100644 --- a/kernel/arch/x86/kernel/cpu/amd.c +++ b/kernel/arch/x86/kernel/cpu/amd.c @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/smp.h> #include <asm/pci-direct.h> +#include <asm/delay.h> #ifdef CONFIG_X86_64 # include <asm/mmconfig.h> @@ -19,6 +20,13 @@ #include "cpu.h" +/* + * nodes_per_socket: Stores the number of nodes per socket. + * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX + * Node Identifiers[10:8] + */ +static u32 nodes_per_socket = 1; + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -107,7 +115,7 @@ static void init_amd_k6(struct cpuinfo_x86 *c) const int K6_BUG_LOOP = 1000000; int n; void (*f_vide)(void); - unsigned long d, d2; + u64 d, d2; printk(KERN_INFO "AMD K6 stepping B detected - "); @@ -118,10 +126,10 @@ static void init_amd_k6(struct cpuinfo_x86 *c) n = K6_BUG_LOOP; f_vide = vide; - rdtscl(d); + d = rdtsc(); while (n--) f_vide(); - rdtscl(d2); + d2 = rdtsc(); d = d2-d; if (d > 20*K6_BUG_LOOP) @@ -288,10 +296,10 @@ static int nearby_node(int apicid) * Assumption: Number of cores in each internal node is the same. * (2) AMD processors supporting compute units */ -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP static void amd_get_topology(struct cpuinfo_x86 *c) { - u32 nodes, cores_per_cu = 1; + u32 cores_per_cu = 1; u8 node_id; int cpu = smp_processor_id(); @@ -300,7 +308,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - nodes = ((ecx >> 8) & 7) + 1; + nodes_per_socket = ((ecx >> 8) & 7) + 1; node_id = ecx & 7; /* get compute unit information */ @@ -311,18 +319,18 @@ static void amd_get_topology(struct cpuinfo_x86 *c) u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes = ((value >> 3) & 7) + 1; + nodes_per_socket = ((value >> 3) & 7) + 1; node_id = value & 7; } else return; /* fixup multi-node processor information */ - if (nodes > 1) { + if (nodes_per_socket > 1) { u32 cores_per_node; u32 cus_per_node; set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cores_per_node = c->x86_max_cores / nodes; + cores_per_node = c->x86_max_cores / nodes_per_socket; cus_per_node = cores_per_node / cores_per_cu; /* store NodeID, use llc_shared_map to store sibling info */ @@ -341,9 +349,10 @@ static void amd_get_topology(struct cpuinfo_x86 *c) */ static void amd_detect_cmp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); + unsigned int socket_id, core_complex_id; bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ @@ -353,6 +362,18 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; amd_get_topology(c); + + /* + * Fix percpu cpu_llc_id here as LLC topology is different + * for Fam17h systems. + */ + if (c->x86 != 0x17 || !cpuid_edx(0x80000006)) + return; + + socket_id = (c->apicid >> bits) - 1; + core_complex_id = (c->apicid & ((1 << bits) - 1)) >> 3; + + per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id; #endif } @@ -366,6 +387,12 @@ u16 amd_get_nb_id(int cpu) } EXPORT_SYMBOL_GPL(amd_get_nb_id); +u32 amd_get_nodes_per_socket(void) +{ + return nodes_per_socket; +} +EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); + static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -420,7 +447,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) static void early_init_amd_mc(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned bits, ecx; /* Multi core CPU? */ @@ -493,6 +520,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) /* A random value per boot for bit slice [12:upper_bit) */ va_align.bits = get_random_int() & va_align.mask; } + + if (cpu_has(c, X86_FEATURE_MWAITX)) + use_mwaitx_delay(); } static void early_init_amd(struct cpuinfo_x86 *c) @@ -520,8 +550,16 @@ static void early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K6_MTRR); #endif #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_PCI) - /* check CPU config space for extended APIC ID */ - if (cpu_has_apic && c->x86 >= 0xf) { + /* + * ApicID can always be treated as an 8-bit value for AMD APIC versions + * >= 0x10, but even old K8s came out of reset with version 0x10. So, we + * can safely set X86_FEATURE_EXTD_APICID unconditionally for families + * after 16h. + */ + if (cpu_has_apic && c->x86 > 0x16) { + set_cpu_cap(c, X86_FEATURE_EXTD_APICID); + } else if (cpu_has_apic && c->x86 >= 0xf) { + /* check CPU config space for extended APIC ID */ unsigned int val; val = read_pci_config(0, 24, 0, 0x68); if ((val & ((1 << 17) | (1 << 18))) == ((1 << 17) | (1 << 18))) diff --git a/kernel/arch/x86/kernel/cpu/bugs.c b/kernel/arch/x86/kernel/cpu/bugs.c index 03445346e..bd17db15a 100644 --- a/kernel/arch/x86/kernel/cpu/bugs.c +++ b/kernel/arch/x86/kernel/cpu/bugs.c @@ -12,57 +12,11 @@ #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include <asm/msr.h> #include <asm/paravirt.h> #include <asm/alternative.h> -static double __initdata x = 4195835.0; -static double __initdata y = 3145727.0; - -/* - * This used to check for exceptions.. - * However, it turns out that to support that, - * the XMM trap handlers basically had to - * be buggy. So let's have a correct XMM trap - * handler, and forget about printing out - * some status at boot. - * - * We should really only care about bugs here - * anyway. Not features. - */ -static void __init check_fpu(void) -{ - s32 fdiv_bug; - - kernel_fpu_begin(); - - /* - * trap_init() enabled FXSR and company _before_ testing for FP - * problems here. - * - * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug - */ - __asm__("fninit\n\t" - "fldl %1\n\t" - "fdivl %2\n\t" - "fmull %2\n\t" - "fldl %1\n\t" - "fsubp %%st,%%st(1)\n\t" - "fistpl %0\n\t" - "fwait\n\t" - "fninit" - : "=m" (*&fdiv_bug) - : "m" (*&x), "m" (*&y)); - - kernel_fpu_end(); - - if (fdiv_bug) { - set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); - pr_warn("Hmm, FPU with FDIV bug\n"); - } -} - void __init check_bugs(void) { identify_boot_cpu(); @@ -85,10 +39,5 @@ void __init check_bugs(void) '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); - /* - * kernel_fpu_begin/end() in check_fpu() relies on the patched - * alternative instructions. - */ - if (cpu_has_fpu) - check_fpu(); + fpu__init_check_bugs(); } diff --git a/kernel/arch/x86/kernel/cpu/common.c b/kernel/arch/x86/kernel/cpu/common.c index 205e0f3df..c2b7522cb 100644 --- a/kernel/arch/x86/kernel/cpu/common.c +++ b/kernel/arch/x86/kernel/cpu/common.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/percpu.h> #include <linux/string.h> +#include <linux/ctype.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/init.h> @@ -12,6 +13,7 @@ #include <linux/kgdb.h> #include <linux/smp.h> #include <linux/io.h> +#include <linux/syscore_ops.h> #include <asm/stackprotector.h> #include <asm/perf_event.h> @@ -31,8 +33,7 @@ #include <asm/setup.h> #include <asm/apic.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mtrr.h> #include <linux/numa.h> #include <asm/asm.h> @@ -145,32 +146,21 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); -static int __init x86_xsave_setup(char *s) +static int __init x86_mpx_setup(char *s) { + /* require an exact match without trailing characters */ if (strlen(s)) return 0; - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - setup_clear_cpu_cap(X86_FEATURE_XSAVES); - setup_clear_cpu_cap(X86_FEATURE_AVX); - setup_clear_cpu_cap(X86_FEATURE_AVX2); - return 1; -} -__setup("noxsave", x86_xsave_setup); -static int __init x86_xsaveopt_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - return 1; -} -__setup("noxsaveopt", x86_xsaveopt_setup); + /* do not emit a message if the feature is not present */ + if (!boot_cpu_has(X86_FEATURE_MPX)) + return 1; -static int __init x86_xsaves_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_MPX); + pr_info("nompx: Intel Memory Protection Extensions (MPX) disabled\n"); return 1; } -__setup("noxsaves", x86_xsaves_setup); +__setup("nompx", x86_mpx_setup); #ifdef CONFIG_X86_32 static int cachesize_override = -1; @@ -183,14 +173,6 @@ static int __init cachesize_setup(char *str) } __setup("cachesize=", cachesize_setup); -static int __init x86_fxsr_setup(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FXSR); - setup_clear_cpu_cap(X86_FEATURE_XMM); - return 1; -} -__setup("nofxsr", x86_fxsr_setup); - static int __init x86_sep_setup(char *s) { setup_clear_cpu_cap(X86_FEATURE_SEP); @@ -291,10 +273,9 @@ __setup("nosmap", setup_disable_smap); static __always_inline void setup_smap(struct cpuinfo_x86 *c) { - unsigned long eflags; + unsigned long eflags = native_save_fl(); /* This should have been cleared long ago */ - raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); if (cpu_has(c, X86_FEATURE_SMAP)) { @@ -419,7 +400,7 @@ static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; static void get_model_name(struct cpuinfo_x86 *c) { unsigned int *v; - char *p, *q; + char *p, *q, *s; if (c->extended_cpuid_level < 0x80000004) return; @@ -430,19 +411,21 @@ static void get_model_name(struct cpuinfo_x86 *c) cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); c->x86_model_id[48] = 0; - /* - * Intel chips right-justify this string for some dumb reason; - * undo that brain damage: - */ - p = q = &c->x86_model_id[0]; + /* Trim whitespace */ + p = q = s = &c->x86_model_id[0]; + while (*p == ' ') p++; - if (p != q) { - while (*p) - *q++ = *p++; - while (q <= &c->x86_model_id[48]) - *q++ = '\0'; /* Zero-pad the rest */ + + while (*p) { + /* Note the last non-whitespace index */ + if (!isspace(*p)) + s = q; + + *q++ = *p++; } + + *(s + 1) = '\0'; } void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) @@ -508,7 +491,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) void detect_ht(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP u32 eax, ebx, ecx, edx; int index_msb, core_bits; static bool printed; @@ -686,6 +669,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; + c->x86_capability[13] = cpuid_ebx(0x80000008); } #ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) @@ -759,7 +743,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); - fpu_detect(c); if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -771,6 +754,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); setup_force_cpu_cap(X86_FEATURE_ALWAYS); + fpu__init_system(c); } void __init early_cpu_init(void) @@ -844,7 +828,7 @@ static void generic_identify(struct cpuinfo_x86 *c) if (c->cpuid_level >= 0x00000001) { c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 -# ifdef CONFIG_X86_HT +# ifdef CONFIG_SMP c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); # else c->apicid = c->initial_apicid; @@ -1026,7 +1010,7 @@ void enable_sep_cpu(void) (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), 0); - wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0); + wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); out: put_cpu(); @@ -1122,14 +1106,14 @@ void print_cpu_info(struct cpuinfo_x86 *c) printk(KERN_CONT "%s ", vendor); if (c->x86_model_id[0]) - printk(KERN_CONT "%s", strim(c->x86_model_id)); + printk(KERN_CONT "%s", c->x86_model_id); else printk(KERN_CONT "%d86", c->x86); - printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model); + printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model); if (c->x86_mask || c->cpuid_level >= 0) - printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask); + printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask); else printk(KERN_CONT ")\n"); @@ -1155,10 +1139,6 @@ static __init int setup_disablecpuid(char *arg) } __setup("clearcpuid=", setup_disablecpuid); -DEFINE_PER_CPU(unsigned long, kernel_stack) = - (unsigned long)&init_thread_union + THREAD_SIZE; -EXPORT_PER_CPU_SYMBOL(kernel_stack); - #ifdef CONFIG_X86_64 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, @@ -1183,8 +1163,6 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); - /* * Special IST stacks which the CPU switches to when it calls * an IST-marked descriptor entry. Up to 7 stacks (hardware @@ -1208,10 +1186,10 @@ void syscall_init(void) * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); - wrmsrl(MSR_LSTAR, system_call); + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION - wrmsrl(MSR_CSTAR, ia32_cstar_target); + wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); /* * This only works on Intel CPUs. * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. @@ -1220,9 +1198,9 @@ void syscall_init(void) */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else - wrmsrl(MSR_CSTAR, ignore_sysret); + wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); @@ -1275,7 +1253,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); /* * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find @@ -1439,7 +1416,7 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); if (is_uv_system()) uv_cpu_init(); @@ -1495,7 +1472,7 @@ void cpu_init(void) clear_all_debug_regs(); dbg_restore_debug_regs(); - fpu_init(); + fpu__init_cpu(); } #endif @@ -1512,3 +1489,20 @@ inline bool __static_cpu_has_safe(u16 bit) return boot_cpu_has(bit); } EXPORT_SYMBOL_GPL(__static_cpu_has_safe); + +static void bsp_resume(void) +{ + if (this_cpu->c_bsp_resume) + this_cpu->c_bsp_resume(&boot_cpu_data); +} + +static struct syscore_ops cpu_syscore_ops = { + .resume = bsp_resume, +}; + +static int __init init_cpu_syscore(void) +{ + register_syscore_ops(&cpu_syscore_ops); + return 0; +} +core_initcall(init_cpu_syscore); diff --git a/kernel/arch/x86/kernel/cpu/cpu.h b/kernel/arch/x86/kernel/cpu/cpu.h index c37dc37e8..2584265d4 100644 --- a/kernel/arch/x86/kernel/cpu/cpu.h +++ b/kernel/arch/x86/kernel/cpu/cpu.h @@ -13,6 +13,7 @@ struct cpu_dev { void (*c_init)(struct cpuinfo_x86 *); void (*c_identify)(struct cpuinfo_x86 *); void (*c_detect_tlb)(struct cpuinfo_x86 *); + void (*c_bsp_resume)(struct cpuinfo_x86 *); int c_x86_vendor; #ifdef CONFIG_X86_32 /* Optional vendor specific routine to obtain the cache size. */ diff --git a/kernel/arch/x86/kernel/cpu/intel.c b/kernel/arch/x86/kernel/cpu/intel.c index 50163fa90..209ac1e7d 100644 --- a/kernel/arch/x86/kernel/cpu/intel.c +++ b/kernel/arch/x86/kernel/cpu/intel.c @@ -97,6 +97,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) switch (c->x86_model) { case 0x27: /* Penwell */ case 0x35: /* Cloverview */ + case 0x4a: /* Merrifield */ set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); break; default: @@ -371,6 +372,36 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c) } } +static void init_intel_energy_perf(struct cpuinfo_x86 *c) +{ + u64 epb; + + /* + * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized. + * (x86_energy_perf_policy(8) is available to change it at run-time.) + */ + if (!cpu_has(c, X86_FEATURE_EPB)) + return; + + rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); + if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE) + return; + + pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); + pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); + epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; + wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); +} + +static void intel_bsp_resume(struct cpuinfo_x86 *c) +{ + /* + * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume, + * so reinitialize it properly like during bootup: + */ + init_intel_energy_perf(c); +} + static void init_intel(struct cpuinfo_x86 *c) { unsigned int l2 = 0; @@ -478,21 +509,7 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_VMX)) detect_vmx_virtcap(c); - /* - * Initialize MSR_IA32_ENERGY_PERF_BIAS if BIOS did not. - * x86_energy_perf_policy(8) is available to change it at run-time - */ - if (cpu_has(c, X86_FEATURE_EPB)) { - u64 epb; - - rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); - if ((epb & 0xF) == ENERGY_PERF_BIAS_PERFORMANCE) { - pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); - pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); - epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; - wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); - } - } + init_intel_energy_perf(c); } #ifdef CONFIG_X86_32 @@ -747,6 +764,7 @@ static const struct cpu_dev intel_cpu_dev = { .c_detect_tlb = intel_detect_tlb, .c_early_init = early_init_intel, .c_init = init_intel, + .c_bsp_resume = intel_bsp_resume, .c_x86_vendor = X86_VENDOR_INTEL, }; diff --git a/kernel/arch/x86/kernel/cpu/intel_cacheinfo.c b/kernel/arch/x86/kernel/cpu/intel_cacheinfo.c index edcb0e28c..e38d338a6 100644 --- a/kernel/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/kernel/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -157,7 +157,7 @@ struct _cpuid4_info_regs { struct amd_northbridge *nb; }; -unsigned short num_cache_leaves; +static unsigned short num_cache_leaves; /* AMD doesn't have CPUID4. Emulate it here to report the same information to the user. This makes some assumptions about the machine: @@ -326,7 +326,7 @@ static void amd_calc_l3_indices(struct amd_northbridge *nb) * * @returns: the disabled index if used or negative value if slot free. */ -int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot) +static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot) { unsigned int reg = 0; @@ -403,8 +403,8 @@ static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu, * * @return: 0 on success, error status on failure */ -int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot, - unsigned long index) +static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, + unsigned slot, unsigned long index) { int ret = 0; @@ -654,7 +654,7 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP unsigned int cpu = c->cpu_index; #endif @@ -773,19 +773,19 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l2) { l2 = new_l2; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l2_id; #endif } if (new_l3) { l3 = new_l3; -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP per_cpu(cpu_llc_id, cpu) = l3_id; #endif } -#ifdef CONFIG_X86_HT +#ifdef CONFIG_SMP /* * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in * turns means that the only possibility is SMT (as indicated in diff --git a/kernel/arch/x86/kernel/cpu/intel_pt.h b/kernel/arch/x86/kernel/cpu/intel_pt.h index 1c338b0eb..336878a5d 100644 --- a/kernel/arch/x86/kernel/cpu/intel_pt.h +++ b/kernel/arch/x86/kernel/cpu/intel_pt.h @@ -25,32 +25,11 @@ */ #define TOPA_PMI_MARGIN 512 -/* - * Table of Physical Addresses bits - */ -enum topa_sz { - TOPA_4K = 0, - TOPA_8K, - TOPA_16K, - TOPA_32K, - TOPA_64K, - TOPA_128K, - TOPA_256K, - TOPA_512K, - TOPA_1MB, - TOPA_2MB, - TOPA_4MB, - TOPA_8MB, - TOPA_16MB, - TOPA_32MB, - TOPA_64MB, - TOPA_128MB, - TOPA_SZ_END, -}; +#define TOPA_SHIFT 12 -static inline unsigned int sizes(enum topa_sz tsz) +static inline unsigned int sizes(unsigned int tsz) { - return 1 << (tsz + 12); + return 1 << (tsz + TOPA_SHIFT); }; struct topa_entry { @@ -66,20 +45,26 @@ struct topa_entry { u64 rsvd4 : 16; }; -#define TOPA_SHIFT 12 -#define PT_CPUID_LEAVES 2 +#define PT_CPUID_LEAVES 2 +#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ enum pt_capabilities { PT_CAP_max_subleaf = 0, PT_CAP_cr3_filtering, + PT_CAP_psb_cyc, + PT_CAP_mtc, PT_CAP_topa_output, PT_CAP_topa_multiple_entries, + PT_CAP_single_range_output, PT_CAP_payloads_lip, + PT_CAP_mtc_periods, + PT_CAP_cycle_thresholds, + PT_CAP_psb_periods, }; struct pt_pmu { struct pmu pmu; - u32 caps[4 * PT_CPUID_LEAVES]; + u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; }; /** diff --git a/kernel/arch/x86/kernel/cpu/mcheck/Makefile b/kernel/arch/x86/kernel/cpu/mcheck/Makefile index bb34b03af..a3311c886 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/Makefile +++ b/kernel/arch/x86/kernel/cpu/mcheck/Makefile @@ -1,4 +1,4 @@ -obj-y = mce.o mce-severity.o +obj-y = mce.o mce-severity.o mce-genpool.o obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce-apei.c b/kernel/arch/x86/kernel/cpu/mcheck/mce-apei.c index a1aef9533..34c89a3e8 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -57,7 +57,6 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) m.addr = mem_err->physical_addr; mce_log(&m); - mce_notify_irq(); } EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c new file mode 100644 index 000000000..0a850100c --- /dev/null +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce-genpool.c @@ -0,0 +1,99 @@ +/* + * MCE event pool management in MCE context + * + * Copyright (C) 2015 Intel Corp. + * Author: Chen, Gong <gong.chen@linux.intel.com> + * + * This file is licensed under GPLv2. + */ +#include <linux/smp.h> +#include <linux/mm.h> +#include <linux/genalloc.h> +#include <linux/llist.h> +#include "mce-internal.h" + +/* + * printk() is not safe in MCE context. This is a lock-less memory allocator + * used to save error information organized in a lock-less list. + * + * This memory pool is only to be used to save MCE records in MCE context. + * MCE events are rare, so a fixed size memory pool should be enough. Use + * 2 pages to save MCE events for now (~80 MCE records at most). + */ +#define MCE_POOLSZ (2 * PAGE_SIZE) + +static struct gen_pool *mce_evt_pool; +static LLIST_HEAD(mce_event_llist); +static char gen_pool_buf[MCE_POOLSZ]; + +void mce_gen_pool_process(void) +{ + struct llist_node *head; + struct mce_evt_llist *node; + struct mce *mce; + + head = llist_del_all(&mce_event_llist); + if (!head) + return; + + head = llist_reverse_order(head); + llist_for_each_entry(node, head, llnode) { + mce = &node->mce; + atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); + } +} + +bool mce_gen_pool_empty(void) +{ + return llist_empty(&mce_event_llist); +} + +int mce_gen_pool_add(struct mce *mce) +{ + struct mce_evt_llist *node; + + if (!mce_evt_pool) + return -EINVAL; + + node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); + if (!node) { + pr_warn_ratelimited("MCE records pool full!\n"); + return -ENOMEM; + } + + memcpy(&node->mce, mce, sizeof(*mce)); + llist_add(&node->llnode, &mce_event_llist); + + return 0; +} + +static int mce_gen_pool_create(void) +{ + struct gen_pool *tmpp; + int ret = -ENOMEM; + + tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1); + if (!tmpp) + goto out; + + ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1); + if (ret) { + gen_pool_destroy(tmpp); + goto out; + } + + mce_evt_pool = tmpp; + +out: + return ret; +} + +int mce_gen_pool_init(void) +{ + /* Just init mce_gen_pool once. */ + if (mce_evt_pool) + return 0; + + return mce_gen_pool_create(); +} diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h b/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h index fe32074b8..547720efd 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -13,6 +13,8 @@ enum severity_level { MCE_PANIC_SEVERITY, }; +extern struct atomic_notifier_head x86_mce_decoder_chain; + #define ATTR_LEN 16 #define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ @@ -24,6 +26,16 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; +struct mce_evt_llist { + struct llist_node llnode; + struct mce mce; +}; + +void mce_gen_pool_process(void); +bool mce_gen_pool_empty(void); +int mce_gen_pool_add(struct mce *mce); +int mce_gen_pool_init(void); + extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); @@ -67,3 +79,5 @@ static inline int apei_clear_mce(u64 record_id) return -EINVAL; } #endif + +void mce_inject_log(struct mce *m); diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce.c b/kernel/arch/x86/kernel/cpu/mcheck/mce.c index 9d46f9a13..a080b4939 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce.c @@ -54,10 +54,13 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); -#define rcu_dereference_check_mce(p) \ - rcu_dereference_index_check((p), \ - rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex)) +#define mce_log_get_idx_check(p) \ +({ \ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious mce_log_get_idx_check() usage"); \ + smp_load_acquire(&(p)); \ +}) #define CREATE_TRACE_POINTS #include <trace/events/mce.h> @@ -109,22 +112,24 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { */ mce_banks_t mce_banks_ce_disabled; -static DEFINE_PER_CPU(struct work_struct, mce_work); +static struct work_struct mce_work; +static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); +static int mce_usable_address(struct mce *m); /* * CPU/chipset specific EDAC code can register a notifier call here to print * MCE errors in a human-readable form. */ -static ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); +ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); - rdtscll(m->tsc); + m->tsc = rdtsc(); /* We hope get_seconds stays lockless */ m->time = get_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; @@ -156,12 +161,13 @@ void mce_log(struct mce *mce) /* Emit the trace record: */ trace_mce_record(mce); - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + if (!mce_gen_pool_add(mce)) + irq_work_queue(&mce_irq_work); mce->finished = 0; wmb(); for (;;) { - entry = rcu_dereference_check_mce(mcelog.next); + entry = mce_log_get_idx_check(mcelog.next); for (;;) { /* @@ -195,48 +201,23 @@ void mce_log(struct mce *mce) set_bit(0, &mce_need_notify); } -static void drain_mcelog_buffer(void) +void mce_inject_log(struct mce *m) { - unsigned int next, i, prev = 0; - - next = ACCESS_ONCE(mcelog.next); - - do { - struct mce *m; - - /* drain what was logged during boot */ - for (i = prev; i < next; i++) { - unsigned long start = jiffies; - unsigned retries = 1; - - m = &mcelog.entry[i]; - - while (!m->finished) { - if (time_after_eq(jiffies, start + 2*retries)) - retries++; - - cpu_relax(); - - if (!m->finished && retries >= 4) { - pr_err("skipping error being logged currently!\n"); - break; - } - } - smp_rmb(); - atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m); - } - - memset(mcelog.entry + prev, 0, (next - prev) * sizeof(*m)); - prev = next; - next = cmpxchg(&mcelog.next, prev, 0); - } while (next != prev); + mutex_lock(&mce_chrdev_read_mutex); + mce_log(m); + mutex_unlock(&mce_chrdev_read_mutex); } +EXPORT_SYMBOL_GPL(mce_inject_log); +static struct notifier_block mce_srao_nb; void mce_register_decode_chain(struct notifier_block *nb) { + /* Ensure SRAO notifier has the highest priority in the decode chain. */ + if (nb != &mce_srao_nb && nb->priority == INT_MAX) + nb->priority -= 1; + atomic_notifier_chain_register(&x86_mce_decoder_chain, nb); - drain_mcelog_buffer(); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); @@ -460,61 +441,6 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs) } } -/* - * Simple lockless ring to communicate PFNs from the exception handler with the - * process context work function. This is vastly simplified because there's - * only a single reader and a single writer. - */ -#define MCE_RING_SIZE 16 /* we use one entry less */ - -struct mce_ring { - unsigned short start; - unsigned short end; - unsigned long ring[MCE_RING_SIZE]; -}; -static DEFINE_PER_CPU(struct mce_ring, mce_ring); - -/* Runs with CPU affinity in workqueue */ -static int mce_ring_empty(void) -{ - struct mce_ring *r = this_cpu_ptr(&mce_ring); - - return r->start == r->end; -} - -static int mce_ring_get(unsigned long *pfn) -{ - struct mce_ring *r; - int ret = 0; - - *pfn = 0; - get_cpu(); - r = this_cpu_ptr(&mce_ring); - if (r->start == r->end) - goto out; - *pfn = r->ring[r->start]; - r->start = (r->start + 1) % MCE_RING_SIZE; - ret = 1; -out: - put_cpu(); - return ret; -} - -/* Always runs in MCE context with preempt off */ -static int mce_ring_add(unsigned long pfn) -{ - struct mce_ring *r = this_cpu_ptr(&mce_ring); - unsigned next; - - next = (r->end + 1) % MCE_RING_SIZE; - if (next == r->start) - return -1; - r->ring[r->end] = pfn; - wmb(); - r->end = next; - return 0; -} - int mce_available(struct cpuinfo_x86 *c) { if (mca_cfg.disabled) @@ -524,12 +450,10 @@ int mce_available(struct cpuinfo_x86 *c) static void mce_schedule_work(void) { - if (!mce_ring_empty()) - schedule_work(this_cpu_ptr(&mce_work)); + if (!mce_gen_pool_empty() && keventd_up()) + schedule_work(&mce_work); } -static DEFINE_PER_CPU(struct irq_work, mce_irq_work); - static void mce_irq_work_cb(struct irq_work *entry) { mce_notify_irq(); @@ -550,9 +474,30 @@ static void mce_report_event(struct pt_regs *regs) return; } - irq_work_queue(this_cpu_ptr(&mce_irq_work)); + irq_work_queue(&mce_irq_work); } +static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + unsigned long pfn; + + if (!mce) + return NOTIFY_DONE; + + if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) { + pfn = mce->addr >> PAGE_SHIFT; + memory_failure(pfn, MCE_VECTOR, 0); + } + + return NOTIFY_OK; +} +static struct notifier_block mce_srao_nb = { + .notifier_call = srao_decode_notifier, + .priority = INT_MAX, +}; + /* * Read ADDR and MISC registers. */ @@ -671,8 +616,11 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) */ if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { if (m.status & MCI_STATUS_ADDRV) { - mce_ring_add(m.addr >> PAGE_SHIFT); - mce_schedule_work(); + m.severity = severity; + m.usable_addr = mce_usable_address(&m); + + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } } @@ -1028,7 +976,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) { struct mca_config *cfg = &mca_cfg; struct mce m, *final; - enum ctx_state prev_state; int i; int worst = 0; int severity; @@ -1052,8 +999,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) char *msg = "Unknown"; u64 recover_paddr = ~0ull; int flags = MF_ACTION_REQUIRED; + int lmce = 0; - prev_state = ist_enter(regs); + /* If this CPU is offline, just bail out. */ + if (cpu_is_offline(smp_processor_id())) { + u64 mcgstatus; + + mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (mcgstatus & MCG_STATUS_RIPV) { + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + return; + } + } + + ist_enter(regs); this_cpu_inc(mce_exception_count); @@ -1079,11 +1038,20 @@ void do_machine_check(struct pt_regs *regs, long error_code) kill_it = 1; /* - * Go through all the banks in exclusion of the other CPUs. - * This way we don't report duplicated events on shared banks - * because the first one to see it will clear it. + * Check if this MCE is signaled to only this logical processor */ - order = mce_start(&no_way_out); + if (m.mcgstatus & MCG_STATUS_LMCES) + lmce = 1; + else { + /* + * Go through all the banks in exclusion of the other CPUs. + * This way we don't report duplicated events on shared banks + * because the first one to see it will clear it. + * If this is a Local MCE, then no need to perform rendezvous. + */ + order = mce_start(&no_way_out); + } + for (i = 0; i < cfg->banks; i++) { __clear_bit(i, toclear); if (!test_bit(i, valid_banks)) @@ -1132,15 +1100,9 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_read_aux(&m, i); - /* - * Action optional error. Queue address for later processing. - * When the ring overflows we just ignore the AO error. - * RED-PEN add some logging mechanism when - * usable_address or mce_add_ring fails. - * RED-PEN don't ignore overflow for mca_cfg.tolerant == 0 - */ - if (severity == MCE_AO_SEVERITY && mce_usable_address(&m)) - mce_ring_add(m.addr >> PAGE_SHIFT); + /* assuming valid severity level != 0 */ + m.severity = severity; + m.usable_addr = mce_usable_address(&m); mce_log(&m); @@ -1160,8 +1122,18 @@ void do_machine_check(struct pt_regs *regs, long error_code) * Do most of the synchronization with other CPUs. * When there's any problem use only local no_way_out state. */ - if (mce_end(order) < 0) - no_way_out = worst >= MCE_PANIC_SEVERITY; + if (!lmce) { + if (mce_end(order) < 0) + no_way_out = worst >= MCE_PANIC_SEVERITY; + } else { + /* + * Local MCE skipped calling mce_reign() + * If we found a fatal error, we need to panic here. + */ + if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) + mce_panic("Machine check from unknown source", + NULL, NULL); + } /* * At insane "tolerant" levels we take no action. Otherwise @@ -1206,7 +1178,7 @@ out: local_irq_disable(); ist_end_non_atomic(); done: - ist_exit(regs, prev_state); + ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -1226,14 +1198,11 @@ int memory_failure(unsigned long pfn, int vector, int flags) /* * Action optional processing happens here (picking up * from the list of faulting pages that do_machine_check() - * placed into the "ring"). + * placed into the genpool). */ static void mce_process_work(struct work_struct *dummy) { - unsigned long pfn; - - while (mce_ring_get(&pfn)) - memory_failure(pfn, MCE_VECTOR, 0); + mce_gen_pool_process(); } #ifdef CONFIG_X86_MCE_INTEL @@ -1655,6 +1624,8 @@ static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) winchip_mcheck_init(c); return 1; break; + default: + return 0; } return 0; @@ -1667,9 +1638,28 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_intel_feature_init(c); mce_adjust_timer = cmci_intel_adjust_timer; break; - case X86_VENDOR_AMD: + + case X86_VENDOR_AMD: { + u32 ebx = cpuid_ebx(0x80000007); + mce_amd_feature_init(c); - mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1; + mce_flags.overflow_recov = !!(ebx & BIT(0)); + mce_flags.succor = !!(ebx & BIT(1)); + mce_flags.smca = !!(ebx & BIT(3)); + + break; + } + + default: + break; + } +} + +static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) +{ + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_feature_clear(c); break; default: break; @@ -1730,13 +1720,36 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) return; } + if (mce_gen_pool_init()) { + mca_cfg.disabled = true; + pr_emerg("Couldn't allocate MCE records pool!\n"); + return; + } + machine_check_vector = do_machine_check; __mcheck_cpu_init_generic(); __mcheck_cpu_init_vendor(c); __mcheck_cpu_init_timer(); - INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work); - init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb); +} + +/* + * Called for each booted CPU to clear some machine checks opt-ins + */ +void mcheck_cpu_clear(struct cpuinfo_x86 *c) +{ + if (mca_cfg.disabled) + return; + + if (!mce_available(c)) + return; + + /* + * Possibly to clear general settings generic to x86 + * __mcheck_cpu_clear_generic(c); + */ + __mcheck_cpu_clear_vendor(c); + } /* @@ -1783,7 +1796,7 @@ static void collect_tscs(void *data) { unsigned long *cpu_tsc = (unsigned long *)data; - rdtscll(cpu_tsc[smp_processor_id()]); + cpu_tsc[smp_processor_id()] = rdtsc(); } static int mce_apei_read_done; @@ -1849,7 +1862,7 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, goto out; } - next = rcu_dereference_check_mce(mcelog.next); + next = mce_log_get_idx_check(mcelog.next); /* Only supports full reads right now */ err = -EINVAL; @@ -1915,7 +1928,7 @@ out: static unsigned int mce_chrdev_poll(struct file *file, poll_table *wait) { poll_wait(file, &mce_chrdev_wait, wait); - if (rcu_access_index(mcelog.next)) + if (READ_ONCE(mcelog.next)) return POLLIN | POLLRDNORM; if (!mce_apei_read_done && apei_check_mce()) return POLLIN | POLLRDNORM; @@ -1960,8 +1973,8 @@ void register_mce_write_callback(ssize_t (*fn)(struct file *filp, } EXPORT_SYMBOL_GPL(register_mce_write_callback); -ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) { if (mce_write) return mce_write(filp, ubuf, usize, off); @@ -2007,6 +2020,7 @@ void mce_disable_bank(int bank) /* * mce=off Disables machine check * mce=no_cmci Disables CMCI + * mce=no_lmce Disables LMCE * mce=dont_log_ce Clears corrected events silently, no log created for CEs. * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared. * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) @@ -2030,6 +2044,8 @@ static int __init mcheck_enable(char *str) cfg->disabled = true; else if (!strcmp(str, "no_cmci")) cfg->cmci_disabled = true; + else if (!strcmp(str, "no_lmce")) + cfg->lmce_disabled = true; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; else if (!strcmp(str, "ignore_ce")) @@ -2039,11 +2055,8 @@ static int __init mcheck_enable(char *str) else if (!strcmp(str, "bios_cmci_threshold")) cfg->bios_cmci_threshold = true; else if (isdigit(str[0])) { - get_option(&str, &(cfg->tolerant)); - if (*str == ',') { - ++str; + if (get_option(&str, &cfg->tolerant) == 2) get_option(&str, &(cfg->monarch_timeout)); - } } else { pr_info("mce argument %s ignored. Please use /sys\n", str); return 0; @@ -2055,8 +2068,12 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); + mce_register_decode_chain(&mce_srao_nb); mcheck_vendor_init_severity(); + INIT_WORK(&mce_work, mce_process_work); + init_irq_work(&mce_irq_work, mce_irq_work_cb); + return 0; } @@ -2068,7 +2085,7 @@ int __init mcheck_init(void) * Disable machine checks on suspend and shutdown. We can't really handle * them later. */ -static int mce_disable_error_reporting(void) +static void mce_disable_error_reporting(void) { int i; @@ -2078,17 +2095,32 @@ static int mce_disable_error_reporting(void) if (b->init) wrmsrl(MSR_IA32_MCx_CTL(i), 0); } - return 0; + return; +} + +static void vendor_disable_error_reporting(void) +{ + /* + * Don't clear on Intel CPUs. Some of these MSRs are socket-wide. + * Disabling them for just a single offlined CPU is bad, since it will + * inhibit reporting for all shared resources on the socket like the + * last level cache (LLC), the integrated memory controller (iMC), etc. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return; + + mce_disable_error_reporting(); } static int mce_syscore_suspend(void) { - return mce_disable_error_reporting(); + vendor_disable_error_reporting(); + return 0; } static void mce_syscore_shutdown(void) { - mce_disable_error_reporting(); + vendor_disable_error_reporting(); } /* @@ -2368,7 +2400,6 @@ static void mce_device_remove(unsigned int cpu) static void mce_disable_cpu(void *h) { unsigned long action = *(unsigned long *)h; - int i; if (!mce_available(raw_cpu_ptr(&cpu_info))) return; @@ -2377,12 +2408,8 @@ static void mce_disable_cpu(void *h) if (!(action & CPU_TASKS_FROZEN)) cmci_clear(); - for (i = 0; i < mca_cfg.banks; i++) { - struct mce_bank *b = &mce_banks[i]; - if (b->init) - wrmsrl(MSR_IA32_MCx_CTL(i), 0); - } + vendor_disable_error_reporting(); } static void mce_reenable_cpu(void *h) @@ -2594,5 +2621,20 @@ static int __init mcheck_debugfs_init(void) return 0; } -late_initcall(mcheck_debugfs_init); +#else +static int __init mcheck_debugfs_init(void) { return -EINVAL; } #endif + +static int __init mcheck_late_init(void) +{ + mcheck_debugfs_init(); + + /* + * Flush out everything that has been logged during early boot, now that + * everything has been initialized (workqueues, decoders, ...). + */ + mce_schedule_work(); + + return 0; +} +late_initcall(mcheck_late_init); diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c b/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c index 55ad9b37c..e99b15077 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -1,19 +1,13 @@ /* - * (c) 2005-2012 Advanced Micro Devices, Inc. + * (c) 2005-2015 Advanced Micro Devices, Inc. * Your use of this code is subject to the terms and conditions of the * GNU general public license version 2. See "COPYING" or * http://www.gnu.org/licenses/gpl.html * * Written by Jacob Shin - AMD, Inc. - * * Maintained by: Borislav Petkov <bp@alien8.de> * - * April 2006 - * - added support for AMD Family 0x10 processors - * May 2012 - * - major scrubbing - * - * All MC4_MISCi registers are shared between multi-cores + * All MC4_MISCi registers are shared between cores on a node. */ #include <linux/interrupt.h> #include <linux/notifier.h> @@ -32,6 +26,7 @@ #include <asm/idle.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/trace/irq_vectors.h> #define NR_BLOCKS 9 #define THRESHOLD_MAX 0xFFF @@ -47,6 +42,13 @@ #define MASK_BLKPTR_LO 0xFF000000 #define MCG_XBLK_ADDR 0xC0000400 +/* Deferred error settings */ +#define MSR_CU_DEF_ERR 0xC0000410 +#define MASK_DEF_LVTOFF 0x000000F0 +#define MASK_DEF_INT_TYPE 0x00000006 +#define DEF_LVT_OFF 0x2 +#define DEF_INT_TYPE_APIC 0x2 + static const char * const th_names[] = { "load_store", "insn_fetch", @@ -60,6 +62,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ static void amd_threshold_interrupt(void); +static void amd_deferred_error_interrupt(void); + +static void default_deferred_error_interrupt(void) +{ + pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR); +} +void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; /* * CPU Initialization @@ -196,7 +205,7 @@ static void mce_threshold_block_init(struct threshold_block *b, int offset) threshold_restart_bank(&tr); }; -static int setup_APIC_mce(int reserved, int new) +static int setup_APIC_mce_threshold(int reserved, int new) { if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR, APIC_EILVT_MSG_FIX, 0)) @@ -205,6 +214,39 @@ static int setup_APIC_mce(int reserved, int new) return reserved; } +static int setup_APIC_deferred_error(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; +} + +static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) +{ + u32 low = 0, high = 0; + int def_offset = -1, def_new; + + if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high)) + return; + + def_new = (low & MASK_DEF_LVTOFF) >> 4; + if (!(low & MASK_DEF_LVTOFF)) { + pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n"); + def_new = DEF_LVT_OFF; + low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4); + } + + def_offset = setup_APIC_deferred_error(def_offset, def_new); + if ((def_offset == def_new) && + (deferred_error_int_vector != amd_deferred_error_interrupt)) + deferred_error_int_vector = amd_deferred_error_interrupt; + + low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC; + wrmsr(MSR_CU_DEF_ERR, low, high); +} + /* cpu init entry point, called from mce.c with preempt off */ void mce_amd_feature_init(struct cpuinfo_x86 *c) { @@ -252,7 +294,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) b.interrupt_enable = 1; new = (high & MASK_LVTOFF_HI) >> 20; - offset = setup_APIC_mce(offset, new); + offset = setup_APIC_mce_threshold(offset, new); if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) @@ -262,6 +304,73 @@ init: mce_threshold_block_init(&b, offset); } } + + if (mce_flags.succor) + deferred_error_interrupt_enable(c); +} + +static void __log_error(unsigned int bank, bool threshold_err, u64 misc) +{ + struct mce m; + u64 status; + + rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + if (!(status & MCI_STATUS_VAL)) + return; + + mce_setup(&m); + + m.status = status; + m.bank = bank; + + if (threshold_err) + m.misc = misc; + + if (m.status & MCI_STATUS_ADDRV) + rdmsrl(MSR_IA32_MCx_ADDR(bank), m.addr); + + mce_log(&m); + wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); +} + +static inline void __smp_deferred_error_interrupt(void) +{ + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); +} + +asmlinkage __visible void smp_deferred_error_interrupt(void) +{ + entering_irq(); + __smp_deferred_error_interrupt(); + exiting_ack_irq(); +} + +asmlinkage __visible void smp_trace_deferred_error_interrupt(void) +{ + entering_irq(); + trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); + __smp_deferred_error_interrupt(); + trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); + exiting_ack_irq(); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) +{ + u64 status; + unsigned int bank; + + for (bank = 0; bank < mca_cfg.banks; ++bank) { + rdmsrl(MSR_IA32_MCx_STATUS(bank), status); + + if (!(status & MCI_STATUS_VAL) || + !(status & MCI_STATUS_DEFERRED)) + continue; + + __log_error(bank, false, 0); + break; + } } /* @@ -273,12 +382,12 @@ init: * the interrupt goes off when error_count reaches threshold_limit. * the handler will simply log mcelog w/ software defined bank number. */ + static void amd_threshold_interrupt(void) { u32 low = 0, high = 0, address = 0; int cpu = smp_processor_id(); unsigned int bank, block; - struct mce m; /* assume first bank caused it */ for (bank = 0; bank < mca_cfg.banks; ++bank) { @@ -321,15 +430,7 @@ static void amd_threshold_interrupt(void) return; log: - mce_setup(&m); - rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); - if (!(m.status & MCI_STATUS_VAL)) - return; - m.misc = ((u64)high << 32) | low; - m.bank = bank; - mce_log(&m); - - wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); + __log_error(bank, true, ((u64)high << 32) | low); } /* diff --git a/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c b/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c index e166d833c..1e8bb6c94 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -91,6 +91,36 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } +static bool lmce_supported(void) +{ + u64 tmp; + + if (mca_cfg.lmce_disabled) + return false; + + rdmsrl(MSR_IA32_MCG_CAP, tmp); + + /* + * LMCE depends on recovery support in the processor. Hence both + * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP. + */ + if ((tmp & (MCG_SER_P | MCG_LMCE_P)) != + (MCG_SER_P | MCG_LMCE_P)) + return false; + + /* + * BIOS should indicate support for LMCE by setting bit 20 in + * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will + * generate a #GP fault. + */ + rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp); + if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) == + (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) + return true; + + return false; +} + bool mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) @@ -221,7 +251,6 @@ static void intel_threshold_interrupt(void) return; machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); - mce_notify_irq(); } /* @@ -410,8 +439,39 @@ static void intel_init_cmci(void) cmci_recheck(); } +static void intel_init_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + + if (!(val & MCG_EXT_CTL_LMCE_EN)) + wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); +} + +static void intel_clear_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + val &= ~MCG_EXT_CTL_LMCE_EN; + wrmsrl(MSR_IA32_MCG_EXT_CTL, val); +} + void mce_intel_feature_init(struct cpuinfo_x86 *c) { intel_init_thermal(c); intel_init_cmci(); + intel_init_lmce(); +} + +void mce_intel_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); } diff --git a/kernel/arch/x86/kernel/cpu/mcheck/p5.c b/kernel/arch/x86/kernel/cpu/mcheck/p5.c index 737b0ad4e..12402e10a 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/p5.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/p5.c @@ -19,10 +19,9 @@ int mce_p5_enabled __read_mostly; /* Machine check handler for Pentium class Intel CPUs: */ static void pentium_machine_check(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; u32 loaddr, hi, lotype; - prev_state = ist_enter(regs); + ist_enter(regs); rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); @@ -39,7 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs, prev_state); + ist_exit(regs); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c b/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c index 1af51b158..2c5aaf8c2 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -503,14 +503,6 @@ void intel_init_thermal(struct cpuinfo_x86 *c) return; } - /* Check whether a vector already exists */ - if (h & APIC_VECTOR_MASK) { - printk(KERN_DEBUG - "CPU%d: Thermal LVT vector (%#x) already installed\n", - cpu, (h & APIC_VECTOR_MASK)); - return; - } - /* early Pentium M models use different method for enabling TM2 */ if (cpu_has(c, X86_FEATURE_TM2)) { if (c->x86 == 6 && (c->x86_model == 9 || c->x86_model == 13)) { diff --git a/kernel/arch/x86/kernel/cpu/mcheck/winchip.c b/kernel/arch/x86/kernel/cpu/mcheck/winchip.c index 44f138296..01dd87028 100644 --- a/kernel/arch/x86/kernel/cpu/mcheck/winchip.c +++ b/kernel/arch/x86/kernel/cpu/mcheck/winchip.c @@ -15,12 +15,12 @@ /* Machine check handler for WinChip C6: */ static void winchip_machine_check(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state = ist_enter(regs); + ist_enter(regs); printk(KERN_EMERG "CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - ist_exit(regs, prev_state); + ist_exit(regs); } /* Set up machine check reporting on the Winchip C6 series */ diff --git a/kernel/arch/x86/kernel/cpu/microcode/Makefile b/kernel/arch/x86/kernel/cpu/microcode/Makefile index 285c85427..220b1a508 100644 --- a/kernel/arch/x86/kernel/cpu/microcode/Makefile +++ b/kernel/arch/x86/kernel/cpu/microcode/Makefile @@ -2,6 +2,3 @@ microcode-y := core.o obj-$(CONFIG_MICROCODE) += microcode.o microcode-$(CONFIG_MICROCODE_INTEL) += intel.o intel_lib.o microcode-$(CONFIG_MICROCODE_AMD) += amd.o -obj-$(CONFIG_MICROCODE_EARLY) += core_early.o -obj-$(CONFIG_MICROCODE_INTEL_EARLY) += intel_early.o -obj-$(CONFIG_MICROCODE_AMD_EARLY) += amd_early.o diff --git a/kernel/arch/x86/kernel/cpu/microcode/amd.c b/kernel/arch/x86/kernel/cpu/microcode/amd.c index 12829c3ce..2233f8a76 100644 --- a/kernel/arch/x86/kernel/cpu/microcode/amd.c +++ b/kernel/arch/x86/kernel/cpu/microcode/amd.c @@ -1,5 +1,9 @@ /* * AMD CPU Microcode Update Driver for Linux + * + * This driver allows to upgrade microcode on F10h AMD + * CPUs and later. + * * Copyright (C) 2008-2011 Advanced Micro Devices Inc. * * Author: Peter Oruba <peter.oruba@amd.com> @@ -7,34 +11,31 @@ * Based on work by: * Tigran Aivazian <tigran@aivazian.fsnet.co.uk> * - * Maintainers: - * Andreas Herrmann <herrmann.der.user@googlemail.com> - * Borislav Petkov <bp@alien8.de> + * early loader: + * Copyright (C) 2013 Advanced Micro Devices, Inc. * - * This driver allows to upgrade microcode on F10h AMD - * CPUs and later. + * Author: Jacob Shin <jacob.shin@amd.com> + * Fixes: Borislav Petkov <bp@suse.de> * * Licensed under the terms of the GNU General Public * License version 2. See file COPYING for details. */ +#define pr_fmt(fmt) "microcode: " fmt -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - +#include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> +#include <linux/initrd.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/pci.h> +#include <asm/microcode_amd.h> #include <asm/microcode.h> #include <asm/processor.h> +#include <asm/setup.h> +#include <asm/cpu.h> #include <asm/msr.h> -#include <asm/microcode_amd.h> - -MODULE_DESCRIPTION("AMD Microcode Update Driver"); -MODULE_AUTHOR("Peter Oruba"); -MODULE_LICENSE("GPL v2"); static struct equiv_cpu_entry *equiv_cpu_table; @@ -47,6 +48,432 @@ struct ucode_patch { static LIST_HEAD(pcache); +/* + * This points to the current valid container of microcode patches which we will + * save from the initrd before jettisoning its contents. + */ +static u8 *container; +static size_t container_size; + +static u32 ucode_new_rev; +u8 amd_ucode_patch[PATCH_MAX_SIZE]; +static u16 this_equiv_id; + +static struct cpio_data ucode_cpio; + +/* + * Microcode patch container file is prepended to the initrd in cpio format. + * See Documentation/x86/early-microcode.txt + */ +static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; + +static struct cpio_data __init find_ucode_in_initrd(void) +{ + long offset = 0; + char *path; + void *start; + size_t size; + +#ifdef CONFIG_X86_32 + struct boot_params *p; + + /* + * On 32-bit, early load occurs before paging is turned on so we need + * to use physical addresses. + */ + p = (struct boot_params *)__pa_nodebug(&boot_params); + path = (char *)__pa_nodebug(ucode_path); + start = (void *)p->hdr.ramdisk_image; + size = p->hdr.ramdisk_size; +#else + path = ucode_path; + start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); + size = boot_params.hdr.ramdisk_size; +#endif + + return find_cpio_data(path, start, size, &offset); +} + +static size_t compute_container_size(u8 *data, u32 total_size) +{ + size_t size = 0; + u32 *header = (u32 *)data; + + if (header[0] != UCODE_MAGIC || + header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + header[2] == 0) /* size */ + return size; + + size = header[2] + CONTAINER_HDR_SZ; + total_size -= size; + data += size; + + while (total_size) { + u16 patch_size; + + header = (u32 *)data; + + if (header[0] != UCODE_UCODE_TYPE) + break; + + /* + * Sanity-check patch size. + */ + patch_size = header[1]; + if (patch_size > PATCH_MAX_SIZE) + break; + + size += patch_size + SECTION_HDR_SIZE; + data += patch_size + SECTION_HDR_SIZE; + total_size -= patch_size + SECTION_HDR_SIZE; + } + + return size; +} + +/* + * Early load occurs before we can vmalloc(). So we look for the microcode + * patch container file in initrd, traverse equivalent cpu table, look for a + * matching microcode patch, and update, all in initrd memory in place. + * When vmalloc() is available for use later -- on 64-bit during first AP load, + * and on 32-bit during save_microcode_in_initrd_amd() -- we can call + * load_microcode_amd() to save equivalent cpu table and microcode patches in + * kernel heap memory. + */ +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) +{ + struct equiv_cpu_entry *eq; + size_t *cont_sz; + u32 *header; + u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; + u16 eq_id = 0; + int offset, left; + u32 rev, eax, ebx, ecx, edx; + u32 *new_rev; + +#ifdef CONFIG_X86_32 + new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); + cont_sz = (size_t *)__pa_nodebug(&container_size); + cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); +#else + new_rev = &ucode_new_rev; + cont_sz = &container_size; + cont = &container; + patch = &amd_ucode_patch; +#endif + + data = ucode; + left = size; + header = (u32 *)data; + + /* find equiv cpu table */ + if (header[0] != UCODE_MAGIC || + header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ + header[2] == 0) /* size */ + return; + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + + while (left > 0) { + eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); + + *cont = data; + + /* Advance past the container header */ + offset = header[2] + CONTAINER_HDR_SZ; + data += offset; + left -= offset; + + eq_id = find_equiv_id(eq, eax); + if (eq_id) { + this_equiv_id = eq_id; + *cont_sz = compute_container_size(*cont, left + offset); + + /* + * truncate how much we need to iterate over in the + * ucode update loop below + */ + left = *cont_sz - offset; + break; + } + + /* + * support multiple container files appended together. if this + * one does not have a matching equivalent cpu entry, we fast + * forward to the next container file. + */ + while (left > 0) { + header = (u32 *)data; + if (header[0] == UCODE_MAGIC && + header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) + break; + + offset = header[1] + SECTION_HDR_SIZE; + data += offset; + left -= offset; + } + + /* mark where the next microcode container file starts */ + offset = data - (u8 *)ucode; + ucode = data; + } + + if (!eq_id) { + *cont = NULL; + *cont_sz = 0; + return; + } + + if (check_current_patch_level(&rev, true)) + return; + + while (left > 0) { + struct microcode_amd *mc; + + header = (u32 *)data; + if (header[0] != UCODE_UCODE_TYPE || /* type */ + header[1] == 0) /* size */ + break; + + mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); + + if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { + + if (!__apply_microcode_amd(mc)) { + rev = mc->hdr.patch_id; + *new_rev = rev; + + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); + } + } + + offset = header[1] + SECTION_HDR_SIZE; + data += offset; + left -= offset; + } +} + +static bool __init load_builtin_amd_microcode(struct cpio_data *cp, + unsigned int family) +{ +#ifdef CONFIG_X86_64 + char fw_name[36] = "amd-ucode/microcode_amd.bin"; + + if (family >= 0x15) + snprintf(fw_name, sizeof(fw_name), + "amd-ucode/microcode_amd_fam%.2xh.bin", family); + + return get_builtin_firmware(cp, fw_name); +#else + return false; +#endif +} + +void __init load_ucode_amd_bsp(unsigned int family) +{ + struct cpio_data cp; + void **data; + size_t *size; + +#ifdef CONFIG_X86_32 + data = (void **)__pa_nodebug(&ucode_cpio.data); + size = (size_t *)__pa_nodebug(&ucode_cpio.size); +#else + data = &ucode_cpio.data; + size = &ucode_cpio.size; +#endif + + cp = find_ucode_in_initrd(); + if (!cp.data) { + if (!load_builtin_amd_microcode(&cp, family)) + return; + } + + *data = cp.data; + *size = cp.size; + + apply_ucode_in_initrd(cp.data, cp.size, true); +} + +#ifdef CONFIG_X86_32 +/* + * On 32-bit, since AP's early load occurs before paging is turned on, we + * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during + * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During + * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, + * which is used upon resume from suspend. + */ +void load_ucode_amd_ap(void) +{ + struct microcode_amd *mc; + size_t *usize; + void **ucode; + + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); + if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { + __apply_microcode_amd(mc); + return; + } + + ucode = (void *)__pa_nodebug(&container); + usize = (size_t *)__pa_nodebug(&container_size); + + if (!*ucode || !*usize) + return; + + apply_ucode_in_initrd(*ucode, *usize, false); +} + +static void __init collect_cpu_sig_on_bsp(void *arg) +{ + unsigned int cpu = smp_processor_id(); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + + uci->cpu_sig.sig = cpuid_eax(0x00000001); +} + +static void __init get_bsp_sig(void) +{ + unsigned int bsp = boot_cpu_data.cpu_index; + struct ucode_cpu_info *uci = ucode_cpu_info + bsp; + + if (!uci->cpu_sig.sig) + smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); +} +#else +void load_ucode_amd_ap(void) +{ + unsigned int cpu = smp_processor_id(); + struct equiv_cpu_entry *eq; + struct microcode_amd *mc; + u32 rev, eax; + u16 eq_id; + + /* Exit if called on the BSP. */ + if (!cpu) + return; + + if (!container) + return; + + /* + * 64-bit runs with paging enabled, thus early==false. + */ + if (check_current_patch_level(&rev, false)) + return; + + eax = cpuid_eax(0x00000001); + eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); + + eq_id = find_equiv_id(eq, eax); + if (!eq_id) + return; + + if (eq_id == this_equiv_id) { + mc = (struct microcode_amd *)amd_ucode_patch; + + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) + ucode_new_rev = mc->hdr.patch_id; + } + + } else { + if (!ucode_cpio.data) + return; + + /* + * AP has a different equivalence ID than BSP, looks like + * mixed-steppings silicon so go through the ucode blob anew. + */ + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); + } +} +#endif + +int __init save_microcode_in_initrd_amd(void) +{ + unsigned long cont; + int retval = 0; + enum ucode_state ret; + u8 *cont_va; + u32 eax; + + if (!container) + return -EINVAL; + +#ifdef CONFIG_X86_32 + get_bsp_sig(); + cont = (unsigned long)container; + cont_va = __va(container); +#else + /* + * We need the physical address of the container for both bitness since + * boot_params.hdr.ramdisk_image is a physical address. + */ + cont = __pa(container); + cont_va = container; +#endif + + /* + * Take into account the fact that the ramdisk might get relocated and + * therefore we need to recompute the container's position in virtual + * memory space. + */ + if (relocated_ramdisk) + container = (u8 *)(__va(relocated_ramdisk) + + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; + + if (ucode_new_rev) + pr_info("microcode: updated early to new patch_level=0x%08x\n", + ucode_new_rev); + + eax = cpuid_eax(0x00000001); + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + + ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); + if (ret != UCODE_OK) + retval = -EINVAL; + + /* + * This will be freed any msec now, stash patches for the current + * family and switch to patch cache for cpu hotplug, etc later. + */ + container = NULL; + container_size = 0; + + return retval; +} + +void reload_ucode_amd(void) +{ + struct microcode_amd *mc; + u32 rev; + + /* + * early==false because this is a syscore ->resume path and by + * that time paging is long enabled. + */ + if (check_current_patch_level(&rev, false)) + return; + + mc = (struct microcode_amd *)amd_ucode_patch; + + if (mc && rev < mc->hdr.patch_id) { + if (!__apply_microcode_amd(mc)) { + ucode_new_rev = mc->hdr.patch_id; + pr_info("microcode: reload patch_level=0x%08x\n", + ucode_new_rev); + } + } +} static u16 __find_equiv_id(unsigned int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; @@ -177,6 +604,53 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size, return patch_size; } +/* + * Those patch levels cannot be updated to newer ones and thus should be final. + */ +static u32 final_levels[] = { + 0x01000098, + 0x0100009f, + 0x010000af, + 0, /* T-101 terminator */ +}; + +/* + * Check the current patch level on this CPU. + * + * @rev: Use it to return the patch level. It is set to 0 in the case of + * error. + * + * Returns: + * - true: if update should stop + * - false: otherwise + */ +bool check_current_patch_level(u32 *rev, bool early) +{ + u32 lvl, dummy, i; + bool ret = false; + u32 *levels; + + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); + + if (IS_ENABLED(CONFIG_X86_32) && early) + levels = (u32 *)__pa_nodebug(&final_levels); + else + levels = final_levels; + + for (i = 0; levels[i]; i++) { + if (lvl == levels[i]) { + lvl = 0; + ret = true; + break; + } + } + + if (rev) + *rev = lvl; + + return ret; +} + int __apply_microcode_amd(struct microcode_amd *mc_amd) { u32 rev, dummy; @@ -197,7 +671,7 @@ int apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; - u32 rev, dummy; + u32 rev; BUG_ON(raw_smp_processor_id() != cpu); @@ -210,7 +684,8 @@ int apply_microcode_amd(int cpu) mc_amd = p->data; uci->mc = p->data; - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); + if (check_current_patch_level(&rev, false)) + return -1; /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { @@ -387,7 +862,7 @@ enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t s if (ret != UCODE_OK) cleanup(); -#if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) +#ifdef CONFIG_X86_32 /* save BSP's matching patch for early load */ if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { struct ucode_patch *p = find_patch(cpu); @@ -475,7 +950,7 @@ static struct microcode_ops microcode_amd_ops = { struct microcode_ops * __init init_amd_microcode(void) { - struct cpuinfo_x86 *c = &cpu_data(0); + struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { pr_warning("AMD CPU family 0x%x not supported\n", c->x86); diff --git a/kernel/arch/x86/kernel/cpu/microcode/amd_early.c b/kernel/arch/x86/kernel/cpu/microcode/amd_early.c deleted file mode 100644 index 737737edb..000000000 --- a/kernel/arch/x86/kernel/cpu/microcode/amd_early.c +++ /dev/null @@ -1,422 +0,0 @@ -/* - * Copyright (C) 2013 Advanced Micro Devices, Inc. - * - * Author: Jacob Shin <jacob.shin@amd.com> - * Fixes: Borislav Petkov <bp@suse.de> - * - * 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 <linux/earlycpio.h> -#include <linux/initrd.h> - -#include <asm/cpu.h> -#include <asm/setup.h> -#include <asm/microcode_amd.h> - -/* - * This points to the current valid container of microcode patches which we will - * save from the initrd before jettisoning its contents. - */ -static u8 *container; -static size_t container_size; - -static u32 ucode_new_rev; -u8 amd_ucode_patch[PATCH_MAX_SIZE]; -static u16 this_equiv_id; - -static struct cpio_data ucode_cpio; - -/* - * Microcode patch container file is prepended to the initrd in cpio format. - * See Documentation/x86/early-microcode.txt - */ -static __initdata char ucode_path[] = "kernel/x86/microcode/AuthenticAMD.bin"; - -static struct cpio_data __init find_ucode_in_initrd(void) -{ - long offset = 0; - char *path; - void *start; - size_t size; - -#ifdef CONFIG_X86_32 - struct boot_params *p; - - /* - * On 32-bit, early load occurs before paging is turned on so we need - * to use physical addresses. - */ - p = (struct boot_params *)__pa_nodebug(&boot_params); - path = (char *)__pa_nodebug(ucode_path); - start = (void *)p->hdr.ramdisk_image; - size = p->hdr.ramdisk_size; -#else - path = ucode_path; - start = (void *)(boot_params.hdr.ramdisk_image + PAGE_OFFSET); - size = boot_params.hdr.ramdisk_size; -#endif - - return find_cpio_data(path, start, size, &offset); -} - -static size_t compute_container_size(u8 *data, u32 total_size) -{ - size_t size = 0; - u32 *header = (u32 *)data; - - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return size; - - size = header[2] + CONTAINER_HDR_SZ; - total_size -= size; - data += size; - - while (total_size) { - u16 patch_size; - - header = (u32 *)data; - - if (header[0] != UCODE_UCODE_TYPE) - break; - - /* - * Sanity-check patch size. - */ - patch_size = header[1]; - if (patch_size > PATCH_MAX_SIZE) - break; - - size += patch_size + SECTION_HDR_SIZE; - data += patch_size + SECTION_HDR_SIZE; - total_size -= patch_size + SECTION_HDR_SIZE; - } - - return size; -} - -/* - * Early load occurs before we can vmalloc(). So we look for the microcode - * patch container file in initrd, traverse equivalent cpu table, look for a - * matching microcode patch, and update, all in initrd memory in place. - * When vmalloc() is available for use later -- on 64-bit during first AP load, - * and on 32-bit during save_microcode_in_initrd_amd() -- we can call - * load_microcode_amd() to save equivalent cpu table and microcode patches in - * kernel heap memory. - */ -static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) -{ - struct equiv_cpu_entry *eq; - size_t *cont_sz; - u32 *header; - u8 *data, **cont; - u8 (*patch)[PATCH_MAX_SIZE]; - u16 eq_id = 0; - int offset, left; - u32 rev, eax, ebx, ecx, edx; - u32 *new_rev; - -#ifdef CONFIG_X86_32 - new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); - cont_sz = (size_t *)__pa_nodebug(&container_size); - cont = (u8 **)__pa_nodebug(&container); - patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); -#else - new_rev = &ucode_new_rev; - cont_sz = &container_size; - cont = &container; - patch = &amd_ucode_patch; -#endif - - data = ucode; - left = size; - header = (u32 *)data; - - /* find equiv cpu table */ - if (header[0] != UCODE_MAGIC || - header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */ - header[2] == 0) /* size */ - return; - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - - while (left > 0) { - eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ); - - *cont = data; - - /* Advance past the container header */ - offset = header[2] + CONTAINER_HDR_SZ; - data += offset; - left -= offset; - - eq_id = find_equiv_id(eq, eax); - if (eq_id) { - this_equiv_id = eq_id; - *cont_sz = compute_container_size(*cont, left + offset); - - /* - * truncate how much we need to iterate over in the - * ucode update loop below - */ - left = *cont_sz - offset; - break; - } - - /* - * support multiple container files appended together. if this - * one does not have a matching equivalent cpu entry, we fast - * forward to the next container file. - */ - while (left > 0) { - header = (u32 *)data; - if (header[0] == UCODE_MAGIC && - header[1] == UCODE_EQUIV_CPU_TABLE_TYPE) - break; - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } - - /* mark where the next microcode container file starts */ - offset = data - (u8 *)ucode; - ucode = data; - } - - if (!eq_id) { - *cont = NULL; - *cont_sz = 0; - return; - } - - /* find ucode and update if needed */ - - native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - - while (left > 0) { - struct microcode_amd *mc; - - header = (u32 *)data; - if (header[0] != UCODE_UCODE_TYPE || /* type */ - header[1] == 0) /* size */ - break; - - mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE); - - if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) { - - if (!__apply_microcode_amd(mc)) { - rev = mc->hdr.patch_id; - *new_rev = rev; - - if (save_patch) - memcpy(patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); - } - } - - offset = header[1] + SECTION_HDR_SIZE; - data += offset; - left -= offset; - } -} - -void __init load_ucode_amd_bsp(void) -{ - struct cpio_data cp; - void **data; - size_t *size; - -#ifdef CONFIG_X86_32 - data = (void **)__pa_nodebug(&ucode_cpio.data); - size = (size_t *)__pa_nodebug(&ucode_cpio.size); -#else - data = &ucode_cpio.data; - size = &ucode_cpio.size; -#endif - - cp = find_ucode_in_initrd(); - if (!cp.data) - return; - - *data = cp.data; - *size = cp.size; - - apply_ucode_in_initrd(cp.data, cp.size, true); -} - -#ifdef CONFIG_X86_32 -/* - * On 32-bit, since AP's early load occurs before paging is turned on, we - * cannot traverse cpu_equiv_table and pcache in kernel heap memory. So during - * cold boot, AP will apply_ucode_in_initrd() just like the BSP. During - * save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch, - * which is used upon resume from suspend. - */ -void load_ucode_amd_ap(void) -{ - struct microcode_amd *mc; - size_t *usize; - void **ucode; - - mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); - if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { - __apply_microcode_amd(mc); - return; - } - - ucode = (void *)__pa_nodebug(&container); - usize = (size_t *)__pa_nodebug(&container_size); - - if (!*ucode || !*usize) - return; - - apply_ucode_in_initrd(*ucode, *usize, false); -} - -static void __init collect_cpu_sig_on_bsp(void *arg) -{ - unsigned int cpu = smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - uci->cpu_sig.sig = cpuid_eax(0x00000001); -} - -static void __init get_bsp_sig(void) -{ - unsigned int bsp = boot_cpu_data.cpu_index; - struct ucode_cpu_info *uci = ucode_cpu_info + bsp; - - if (!uci->cpu_sig.sig) - smp_call_function_single(bsp, collect_cpu_sig_on_bsp, NULL, 1); -} -#else -void load_ucode_amd_ap(void) -{ - unsigned int cpu = smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct equiv_cpu_entry *eq; - struct microcode_amd *mc; - u32 rev, eax; - u16 eq_id; - - /* Exit if called on the BSP. */ - if (!cpu) - return; - - if (!container) - return; - - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - - uci->cpu_sig.rev = rev; - uci->cpu_sig.sig = eax; - - eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); - - eq_id = find_equiv_id(eq, eax); - if (!eq_id) - return; - - if (eq_id == this_equiv_id) { - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) - ucode_new_rev = mc->hdr.patch_id; - } - - } else { - if (!ucode_cpio.data) - return; - - /* - * AP has a different equivalence ID than BSP, looks like - * mixed-steppings silicon so go through the ucode blob anew. - */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); - } -} -#endif - -int __init save_microcode_in_initrd_amd(void) -{ - unsigned long cont; - int retval = 0; - enum ucode_state ret; - u8 *cont_va; - u32 eax; - - if (!container) - return -EINVAL; - -#ifdef CONFIG_X86_32 - get_bsp_sig(); - cont = (unsigned long)container; - cont_va = __va(container); -#else - /* - * We need the physical address of the container for both bitness since - * boot_params.hdr.ramdisk_image is a physical address. - */ - cont = __pa(container); - cont_va = container; -#endif - - /* - * Take into account the fact that the ramdisk might get relocated and - * therefore we need to recompute the container's position in virtual - * memory space. - */ - if (relocated_ramdisk) - container = (u8 *)(__va(relocated_ramdisk) + - (cont - boot_params.hdr.ramdisk_image)); - else - container = cont_va; - - if (ucode_new_rev) - pr_info("microcode: updated early to new patch_level=0x%08x\n", - ucode_new_rev); - - eax = cpuid_eax(0x00000001); - eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); - - ret = load_microcode_amd(smp_processor_id(), eax, container, container_size); - if (ret != UCODE_OK) - retval = -EINVAL; - - /* - * This will be freed any msec now, stash patches for the current - * family and switch to patch cache for cpu hotplug, etc later. - */ - container = NULL; - container_size = 0; - - return retval; -} - -void reload_ucode_amd(void) -{ - struct microcode_amd *mc; - u32 rev, eax; - - rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); - - mc = (struct microcode_amd *)amd_ucode_patch; - - if (mc && rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc)) { - ucode_new_rev = mc->hdr.patch_id; - pr_info("microcode: reload patch_level=0x%08x\n", - ucode_new_rev); - } - } -} diff --git a/kernel/arch/x86/kernel/cpu/microcode/core.c b/kernel/arch/x86/kernel/cpu/microcode/core.c index 36a83617e..b3e94ef46 100644 --- a/kernel/arch/x86/kernel/cpu/microcode/core.c +++ b/kernel/arch/x86/kernel/cpu/microcode/core.c @@ -1,104 +1,57 @@ /* - * Intel CPU Microcode Update Driver for Linux + * CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> + * 2013-2015 Borislav Petkov <bp@alien8.de> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. + * X86 CPU microcode early update for Linux: * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: + * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> + * H Peter Anvin" <hpa@zytor.com> + * (C) 2015 Borislav Petkov <bp@alien8.de> * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf + * This driver allows to upgrade microcode on x86 processors. * - * For more information, go to http://www.urbanmyth.org/microcode - * - * 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. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * 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. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#define pr_fmt(fmt) "microcode: " fmt #include <linux/platform_device.h> +#include <linux/syscore_ops.h> #include <linux/miscdevice.h> #include <linux/capability.h> +#include <linux/firmware.h> #include <linux/kernel.h> -#include <linux/module.h> #include <linux/mutex.h> #include <linux/cpu.h> #include <linux/fs.h> #include <linux/mm.h> -#include <linux/syscore_ops.h> -#include <asm/microcode.h> -#include <asm/processor.h> +#include <asm/microcode_intel.h> #include <asm/cpu_device_id.h> +#include <asm/microcode_amd.h> #include <asm/perf_event.h> +#include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/cmdline.h> -MODULE_DESCRIPTION("Microcode Update Driver"); -MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); -MODULE_LICENSE("GPL"); - -#define MICROCODE_VERSION "2.00" +#define MICROCODE_VERSION "2.01" static struct microcode_ops *microcode_ops; -bool dis_ucode_ldr; -module_param(dis_ucode_ldr, bool, 0); +static bool dis_ucode_ldr; + +static int __init disable_loader(char *str) +{ + dis_ucode_ldr = true; + return 1; +} +__setup("dis_ucode_ldr", disable_loader); /* * Synchronization. @@ -126,6 +79,150 @@ struct cpu_info_ctx { int err; }; +static bool __init check_loader_disabled_bsp(void) +{ +#ifdef CONFIG_X86_32 + const char *cmdline = (const char *)__pa_nodebug(boot_command_line); + const char *opt = "dis_ucode_ldr"; + const char *option = (const char *)__pa_nodebug(opt); + bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); + +#else /* CONFIG_X86_64 */ + const char *cmdline = boot_command_line; + const char *option = "dis_ucode_ldr"; + bool *res = &dis_ucode_ldr; +#endif + + if (cmdline_find_option_bool(cmdline, option)) + *res = true; + + return *res; +} + +extern struct builtin_fw __start_builtin_fw[]; +extern struct builtin_fw __end_builtin_fw[]; + +bool get_builtin_firmware(struct cpio_data *cd, const char *name) +{ +#ifdef CONFIG_FW_LOADER + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { + if (!strcmp(name, b_fw->name)) { + cd->size = b_fw->size; + cd->data = b_fw->data; + return true; + } + } +#endif + return false; +} + +void __init load_ucode_bsp(void) +{ + int vendor; + unsigned int family; + + if (check_loader_disabled_bsp()) + return; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + family = x86_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (family >= 6) + load_ucode_intel_bsp(); + break; + case X86_VENDOR_AMD: + if (family >= 0x10) + load_ucode_amd_bsp(family); + break; + default: + break; + } +} + +static bool check_loader_disabled_ap(void) +{ +#ifdef CONFIG_X86_32 + return *((bool *)__pa_nodebug(&dis_ucode_ldr)); +#else + return dis_ucode_ldr; +#endif +} + +void load_ucode_ap(void) +{ + int vendor, family; + + if (check_loader_disabled_ap()) + return; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + family = x86_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (family >= 6) + load_ucode_intel_ap(); + break; + case X86_VENDOR_AMD: + if (family >= 0x10) + load_ucode_amd_ap(); + break; + default: + break; + } +} + +int __init save_microcode_in_initrd(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + if (c->x86 >= 6) + save_microcode_in_initrd_intel(); + break; + case X86_VENDOR_AMD: + if (c->x86 >= 0x10) + save_microcode_in_initrd_amd(); + break; + default: + break; + } + + return 0; +} + +void reload_early_microcode(void) +{ + int vendor, family; + + vendor = x86_vendor(); + family = x86_family(); + + switch (vendor) { + case X86_VENDOR_INTEL: + if (family >= 6) + reload_ucode_intel(); + break; + case X86_VENDOR_AMD: + if (family >= 0x10) + reload_ucode_amd(); + break; + default: + break; + } +} + static void collect_cpu_info_local(void *arg) { struct cpu_info_ctx *ctx = arg; @@ -268,9 +365,6 @@ static void __exit microcode_dev_exit(void) { misc_deregister(µcode_dev); } - -MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); -MODULE_ALIAS("devname:cpu/microcode"); #else #define microcode_dev_init() 0 #define microcode_dev_exit() do { } while (0) @@ -435,17 +529,16 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif) return err; } -static int mc_device_remove(struct device *dev, struct subsys_interface *sif) +static void mc_device_remove(struct device *dev, struct subsys_interface *sif) { int cpu = dev->id; if (!cpu_online(cpu)) - return 0; + return; pr_debug("CPU%d removed\n", cpu); microcode_fini_cpu(cpu); sysfs_remove_group(&dev->kobj, &mc_attr_group); - return 0; } static struct subsys_interface mc_cpu_interface = { @@ -518,24 +611,10 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) return NOTIFY_OK; } -static struct notifier_block __refdata mc_cpu_notifier = { +static struct notifier_block mc_cpu_notifier = { .notifier_call = mc_cpu_callback, }; -#ifdef MODULE -/* Autoload on Intel and AMD systems */ -static const struct x86_cpu_id __initconst microcode_id[] = { -#ifdef CONFIG_MICROCODE_INTEL - { X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, }, -#endif -#ifdef CONFIG_MICROCODE_AMD - { X86_VENDOR_AMD, X86_FAMILY_ANY, X86_MODEL_ANY, }, -#endif - {} -}; -MODULE_DEVICE_TABLE(x86cpu, microcode_id); -#endif - static struct attribute *cpu_root_microcode_attrs[] = { &dev_attr_reload.attr, NULL @@ -546,9 +625,9 @@ static struct attribute_group cpu_root_microcode_group = { .attrs = cpu_root_microcode_attrs, }; -static int __init microcode_init(void) +int __init microcode_init(void) { - struct cpuinfo_x86 *c = &cpu_data(0); + struct cpuinfo_x86 *c = &boot_cpu_data; int error; if (paravirt_enabled() || dis_ucode_ldr) @@ -619,35 +698,4 @@ static int __init microcode_init(void) return error; } -module_init(microcode_init); - -static void __exit microcode_exit(void) -{ - struct cpuinfo_x86 *c = &cpu_data(0); - - microcode_dev_exit(); - - unregister_hotcpu_notifier(&mc_cpu_notifier); - unregister_syscore_ops(&mc_syscore_ops); - - sysfs_remove_group(&cpu_subsys.dev_root->kobj, - &cpu_root_microcode_group); - - get_online_cpus(); - mutex_lock(µcode_mutex); - - subsys_interface_unregister(&mc_cpu_interface); - - mutex_unlock(µcode_mutex); - put_online_cpus(); - - platform_device_unregister(microcode_pdev); - - microcode_ops = NULL; - - if (c->x86_vendor == X86_VENDOR_AMD) - exit_amd_microcode(); - - pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n"); -} -module_exit(microcode_exit); +late_initcall(microcode_init); diff --git a/kernel/arch/x86/kernel/cpu/microcode/core_early.c b/kernel/arch/x86/kernel/cpu/microcode/core_early.c deleted file mode 100644 index a413a69cb..000000000 --- a/kernel/arch/x86/kernel/cpu/microcode/core_early.c +++ /dev/null @@ -1,148 +0,0 @@ -/* - * X86 CPU microcode early update for Linux - * - * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> - * H Peter Anvin" <hpa@zytor.com> - * - * This driver allows to early upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture - * Software Developer's Manual. - * - * 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. - */ -#include <linux/module.h> -#include <asm/microcode.h> -#include <asm/microcode_intel.h> -#include <asm/microcode_amd.h> -#include <asm/processor.h> -#include <asm/cmdline.h> - -static bool __init check_loader_disabled_bsp(void) -{ -#ifdef CONFIG_X86_32 - const char *cmdline = (const char *)__pa_nodebug(boot_command_line); - const char *opt = "dis_ucode_ldr"; - const char *option = (const char *)__pa_nodebug(opt); - bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); - -#else /* CONFIG_X86_64 */ - const char *cmdline = boot_command_line; - const char *option = "dis_ucode_ldr"; - bool *res = &dis_ucode_ldr; -#endif - - if (cmdline_find_option_bool(cmdline, option)) - *res = true; - - return *res; -} - -void __init load_ucode_bsp(void) -{ - int vendor, family; - - if (check_loader_disabled_bsp()) - return; - - if (!have_cpuid_p()) - return; - - vendor = x86_vendor(); - family = x86_family(); - - switch (vendor) { - case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_bsp(); - break; - case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_bsp(); - break; - default: - break; - } -} - -static bool check_loader_disabled_ap(void) -{ -#ifdef CONFIG_X86_32 - return *((bool *)__pa_nodebug(&dis_ucode_ldr)); -#else - return dis_ucode_ldr; -#endif -} - -void load_ucode_ap(void) -{ - int vendor, family; - - if (check_loader_disabled_ap()) - return; - - if (!have_cpuid_p()) - return; - - vendor = x86_vendor(); - family = x86_family(); - - switch (vendor) { - case X86_VENDOR_INTEL: - if (family >= 6) - load_ucode_intel_ap(); - break; - case X86_VENDOR_AMD: - if (family >= 0x10) - load_ucode_amd_ap(); - break; - default: - break; - } -} - -int __init save_microcode_in_initrd(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - if (c->x86 >= 6) - save_microcode_in_initrd_intel(); - break; - case X86_VENDOR_AMD: - if (c->x86 >= 0x10) - save_microcode_in_initrd_amd(); - break; - default: - break; - } - - return 0; -} - -void reload_early_microcode(void) -{ - int vendor, family; - - vendor = x86_vendor(); - family = x86_family(); - - switch (vendor) { - case X86_VENDOR_INTEL: - if (family >= 6) - reload_ucode_intel(); - break; - case X86_VENDOR_AMD: - if (family >= 0x10) - reload_ucode_amd(); - break; - default: - break; - } -} diff --git a/kernel/arch/x86/kernel/cpu/microcode/intel.c b/kernel/arch/x86/kernel/cpu/microcode/intel.c index a41beadb3..ce47402eb 100644 --- a/kernel/arch/x86/kernel/cpu/microcode/intel.c +++ b/kernel/arch/x86/kernel/cpu/microcode/intel.c @@ -1,91 +1,807 @@ /* - * Intel CPU Microcode Update Driver for Linux + * Intel CPU Microcode Update Driver for Linux * - * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> - * 2006 Shaohua Li <shaohua.li@intel.com> + * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk> + * 2006 Shaohua Li <shaohua.li@intel.com> * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. + * Intel CPU microcode early update for Linux * - * Reference: Section 8.11 of Volume 3a, IA-32 Intel? Architecture - * Software Developer's Manual - * Order Number 253668 or free download from: + * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> + * H Peter Anvin" <hpa@zytor.com> * - * http://developer.intel.com/Assets/PDF/manual/253668.pdf - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * 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. - * - * 1.0 16 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Initial release. - * 1.01 18 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added read() support + cleanups. - * 1.02 21 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Added 'device trimming' support. open(O_WRONLY) zeroes - * and frees the saved copy of applied microcode. - * 1.03 29 Feb 2000, Tigran Aivazian <tigran@sco.com> - * Made to use devfs (/dev/cpu/microcode) + cleanups. - * 1.04 06 Jun 2000, Simon Trimmer <simon@veritas.com> - * Added misc device support (now uses both devfs and misc). - * Added MICROCODE_IOCFREE ioctl to clear memory. - * 1.05 09 Jun 2000, Simon Trimmer <simon@veritas.com> - * Messages for error cases (non Intel & no suitable microcode). - * 1.06 03 Aug 2000, Tigran Aivazian <tigran@veritas.com> - * Removed ->release(). Removed exclusive open and status bitmap. - * Added microcode_rwsem to serialize read()/write()/ioctl(). - * Removed global kernel lock usage. - * 1.07 07 Sep 2000, Tigran Aivazian <tigran@veritas.com> - * Write 0 to 0x8B msr and then cpuid before reading revision, - * so that it works even if there were no update done by the - * BIOS. Otherwise, reading from 0x8B gives junk (which happened - * to be 0 on my machine which is why it worked even when I - * disabled update by the BIOS) - * Thanks to Eric W. Biederman <ebiederman@lnxi.com> for the fix. - * 1.08 11 Dec 2000, Richard Schaal <richard.schaal@intel.com> and - * Tigran Aivazian <tigran@veritas.com> - * Intel Pentium 4 processor support and bugfixes. - * 1.09 30 Oct 2001, Tigran Aivazian <tigran@veritas.com> - * Bugfix for HT (Hyper-Threading) enabled processors - * whereby processor resources are shared by all logical processors - * in a single CPU package. - * 1.10 28 Feb 2002 Asit K Mallick <asit.k.mallick@intel.com> and - * Tigran Aivazian <tigran@veritas.com>, - * Serialize updates as required on HT processors due to - * speculative nature of implementation. - * 1.11 22 Mar 2002 Tigran Aivazian <tigran@veritas.com> - * Fix the panic when writing zero-length microcode chunk. - * 1.12 29 Sep 2003 Nitin Kamble <nitin.a.kamble@intel.com>, - * Jun Nakajima <jun.nakajima@intel.com> - * Support for the microcode updates in the new format. - * 1.13 10 Oct 2003 Tigran Aivazian <tigran@veritas.com> - * Removed ->read() method and obsoleted MICROCODE_IOCFREE ioctl - * because we no longer hold a copy of applied microcode - * in kernel memory. - * 1.14 25 Jun 2004 Tigran Aivazian <tigran@veritas.com> - * Fix sigmatch() macro to handle old CPUs with pf == 0. - * Thanks to Stuart Swales for pointing out this bug. + * 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. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +/* + * This needs to be before all headers so that pr_debug in printk.h doesn't turn + * printk calls into no_printk(). + * + *#define DEBUG + */ +#define pr_fmt(fmt) "microcode: " fmt +#include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> -#include <linux/kernel.h> -#include <linux/module.h> #include <linux/vmalloc.h> +#include <linux/initrd.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <linux/mm.h> #include <asm/microcode_intel.h> #include <asm/processor.h> +#include <asm/tlbflush.h> +#include <asm/setup.h> #include <asm/msr.h> -MODULE_DESCRIPTION("Microcode Update Driver"); -MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); -MODULE_LICENSE("GPL"); +static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; +static struct mc_saved_data { + unsigned int mc_saved_count; + struct microcode_intel **mc_saved; +} mc_saved_data; + +static enum ucode_state +load_microcode_early(struct microcode_intel **saved, + unsigned int num_saved, struct ucode_cpu_info *uci) +{ + struct microcode_intel *ucode_ptr, *new_mc = NULL; + struct microcode_header_intel *mc_hdr; + int new_rev, ret, i; + + new_rev = uci->cpu_sig.rev; + + for (i = 0; i < num_saved; i++) { + ucode_ptr = saved[i]; + mc_hdr = (struct microcode_header_intel *)ucode_ptr; + + ret = has_newer_microcode(ucode_ptr, + uci->cpu_sig.sig, + uci->cpu_sig.pf, + new_rev); + if (!ret) + continue; + + new_rev = mc_hdr->rev; + new_mc = ucode_ptr; + } + + if (!new_mc) + return UCODE_NFOUND; + + uci->mc = (struct microcode_intel *)new_mc; + return UCODE_OK; +} + +static inline void +copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd, + unsigned long off, int num_saved) +{ + int i; + + for (i = 0; i < num_saved; i++) + mc_saved[i] = (struct microcode_intel *)(initrd[i] + off); +} + +#ifdef CONFIG_X86_32 +static void +microcode_phys(struct microcode_intel **mc_saved_tmp, + struct mc_saved_data *mc_saved_data) +{ + int i; + struct microcode_intel ***mc_saved; + + mc_saved = (struct microcode_intel ***) + __pa_nodebug(&mc_saved_data->mc_saved); + for (i = 0; i < mc_saved_data->mc_saved_count; i++) { + struct microcode_intel *p; + + p = *(struct microcode_intel **) + __pa_nodebug(mc_saved_data->mc_saved + i); + mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); + } +} +#endif + +static enum ucode_state +load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, + unsigned long initrd_start, struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int count = mc_saved_data->mc_saved_count; + + if (!mc_saved_data->mc_saved) { + copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count); + + return load_microcode_early(mc_saved_tmp, count, uci); + } else { +#ifdef CONFIG_X86_32 + microcode_phys(mc_saved_tmp, mc_saved_data); + return load_microcode_early(mc_saved_tmp, count, uci); +#else + return load_microcode_early(mc_saved_data->mc_saved, + count, uci); +#endif + } +} + +/* + * Given CPU signature and a microcode patch, this function finds if the + * microcode patch has matching family and model with the CPU. + */ +static enum ucode_state +matching_model_microcode(struct microcode_header_intel *mc_header, + unsigned long sig) +{ + unsigned int fam, model; + unsigned int fam_ucode, model_ucode; + struct extended_sigtable *ext_header; + unsigned long total_size = get_totalsize(mc_header); + unsigned long data_size = get_datasize(mc_header); + int ext_sigcount, i; + struct extended_signature *ext_sig; + + fam = __x86_family(sig); + model = x86_model(sig); + + fam_ucode = __x86_family(mc_header->sig); + model_ucode = x86_model(mc_header->sig); + + if (fam == fam_ucode && model == model_ucode) + return UCODE_OK; + + /* Look for ext. headers: */ + if (total_size <= data_size + MC_HEADER_SIZE) + return UCODE_NFOUND; + + ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + ext_sigcount = ext_header->count; + + for (i = 0; i < ext_sigcount; i++) { + fam_ucode = __x86_family(ext_sig->sig); + model_ucode = x86_model(ext_sig->sig); + + if (fam == fam_ucode && model == model_ucode) + return UCODE_OK; + + ext_sig++; + } + return UCODE_NFOUND; +} + +static int +save_microcode(struct mc_saved_data *mc_saved_data, + struct microcode_intel **mc_saved_src, + unsigned int mc_saved_count) +{ + int i, j; + struct microcode_intel **saved_ptr; + int ret; + + if (!mc_saved_count) + return -EINVAL; + + /* + * Copy new microcode data. + */ + saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL); + if (!saved_ptr) + return -ENOMEM; + + for (i = 0; i < mc_saved_count; i++) { + struct microcode_header_intel *mc_hdr; + struct microcode_intel *mc; + unsigned long size; + + if (!mc_saved_src[i]) { + ret = -EINVAL; + goto err; + } + + mc = mc_saved_src[i]; + mc_hdr = &mc->hdr; + size = get_totalsize(mc_hdr); + + saved_ptr[i] = kmalloc(size, GFP_KERNEL); + if (!saved_ptr[i]) { + ret = -ENOMEM; + goto err; + } + + memcpy(saved_ptr[i], mc, size); + } + + /* + * Point to newly saved microcode. + */ + mc_saved_data->mc_saved = saved_ptr; + mc_saved_data->mc_saved_count = mc_saved_count; + + return 0; + +err: + for (j = 0; j <= i; j++) + kfree(saved_ptr[j]); + kfree(saved_ptr); + + return ret; +} + +/* + * A microcode patch in ucode_ptr is saved into mc_saved + * - if it has matching signature and newer revision compared to an existing + * patch mc_saved. + * - or if it is a newly discovered microcode patch. + * + * The microcode patch should have matching model with CPU. + * + * Returns: The updated number @num_saved of saved microcode patches. + */ +static unsigned int _save_mc(struct microcode_intel **mc_saved, + u8 *ucode_ptr, unsigned int num_saved) +{ + struct microcode_header_intel *mc_hdr, *mc_saved_hdr; + unsigned int sig, pf; + int found = 0, i; + + mc_hdr = (struct microcode_header_intel *)ucode_ptr; + + for (i = 0; i < num_saved; i++) { + mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; + sig = mc_saved_hdr->sig; + pf = mc_saved_hdr->pf; + + if (!find_matching_signature(ucode_ptr, sig, pf)) + continue; + + found = 1; + + if (mc_hdr->rev <= mc_saved_hdr->rev) + continue; + + /* + * Found an older ucode saved earlier. Replace it with + * this newer one. + */ + mc_saved[i] = (struct microcode_intel *)ucode_ptr; + break; + } + + /* Newly detected microcode, save it to memory. */ + if (i >= num_saved && !found) + mc_saved[num_saved++] = (struct microcode_intel *)ucode_ptr; + + return num_saved; +} + +/* + * Get microcode matching with BSP's model. Only CPUs with the same model as + * BSP can stay in the platform. + */ +static enum ucode_state __init +get_matching_model_microcode(int cpu, unsigned long start, + void *data, size_t size, + struct mc_saved_data *mc_saved_data, + unsigned long *mc_saved_in_initrd, + struct ucode_cpu_info *uci) +{ + u8 *ucode_ptr = data; + unsigned int leftover = size; + enum ucode_state state = UCODE_OK; + unsigned int mc_size; + struct microcode_header_intel *mc_header; + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int mc_saved_count = mc_saved_data->mc_saved_count; + int i; + + while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { + + if (leftover < sizeof(mc_header)) + break; + + mc_header = (struct microcode_header_intel *)ucode_ptr; + + mc_size = get_totalsize(mc_header); + if (!mc_size || mc_size > leftover || + microcode_sanity_check(ucode_ptr, 0) < 0) + break; + + leftover -= mc_size; + + /* + * Since APs with same family and model as the BSP may boot in + * the platform, we need to find and save microcode patches + * with the same family and model as the BSP. + */ + if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != + UCODE_OK) { + ucode_ptr += mc_size; + continue; + } + + mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count); + + ucode_ptr += mc_size; + } + + if (leftover) { + state = UCODE_ERROR; + goto out; + } + + if (mc_saved_count == 0) { + state = UCODE_NFOUND; + goto out; + } + + for (i = 0; i < mc_saved_count; i++) + mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start; + + mc_saved_data->mc_saved_count = mc_saved_count; +out: + return state; +} + +static int collect_cpu_info_early(struct ucode_cpu_info *uci) +{ + unsigned int val[2]; + unsigned int family, model; + struct cpu_signature csig; + unsigned int eax, ebx, ecx, edx; + + csig.sig = 0; + csig.pf = 0; + csig.rev = 0; + + memset(uci, 0, sizeof(*uci)); + + eax = 0x00000001; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + csig.sig = eax; + + family = __x86_family(csig.sig); + model = x86_model(csig.sig); + + if ((model >= 5) || (family > 6)) { + /* get processor flags from MSR 0x17 */ + native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); + csig.pf = 1 << ((val[1] >> 18) & 7); + } + native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + sync_core(); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + + csig.rev = val[1]; + + uci->cpu_sig = csig; + uci->valid = 1; + + return 0; +} + +static void show_saved_mc(void) +{ +#ifdef DEBUG + int i, j; + unsigned int sig, pf, rev, total_size, data_size, date; + struct ucode_cpu_info uci; + + if (mc_saved_data.mc_saved_count == 0) { + pr_debug("no microcode data saved.\n"); + return; + } + pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); + + collect_cpu_info_early(&uci); + + sig = uci.cpu_sig.sig; + pf = uci.cpu_sig.pf; + rev = uci.cpu_sig.rev; + pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); + + for (i = 0; i < mc_saved_data.mc_saved_count; i++) { + struct microcode_header_intel *mc_saved_header; + struct extended_sigtable *ext_header; + int ext_sigcount; + struct extended_signature *ext_sig; + + mc_saved_header = (struct microcode_header_intel *) + mc_saved_data.mc_saved[i]; + sig = mc_saved_header->sig; + pf = mc_saved_header->pf; + rev = mc_saved_header->rev; + total_size = get_totalsize(mc_saved_header); + data_size = get_datasize(mc_saved_header); + date = mc_saved_header->date; + + pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n", + i, sig, pf, rev, total_size, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); + + /* Look for ext. headers: */ + if (total_size <= data_size + MC_HEADER_SIZE) + continue; + + ext_header = (void *) mc_saved_header + data_size + MC_HEADER_SIZE; + ext_sigcount = ext_header->count; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + + for (j = 0; j < ext_sigcount; j++) { + sig = ext_sig->sig; + pf = ext_sig->pf; + + pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n", + j, sig, pf); + + ext_sig++; + } + + } +#endif +} + +#ifdef CONFIG_HOTPLUG_CPU +static DEFINE_MUTEX(x86_cpu_microcode_mutex); +/* + * Save this mc into mc_saved_data. So it will be loaded early when a CPU is + * hot added or resumes. + * + * Please make sure this mc should be a valid microcode patch before calling + * this function. + */ +int save_mc_for_early(u8 *mc) +{ + struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; + unsigned int mc_saved_count_init; + unsigned int mc_saved_count; + struct microcode_intel **mc_saved; + int ret = 0; + int i; + + /* + * Hold hotplug lock so mc_saved_data is not accessed by a CPU in + * hotplug. + */ + mutex_lock(&x86_cpu_microcode_mutex); + + mc_saved_count_init = mc_saved_data.mc_saved_count; + mc_saved_count = mc_saved_data.mc_saved_count; + mc_saved = mc_saved_data.mc_saved; + + if (mc_saved && mc_saved_count) + memcpy(mc_saved_tmp, mc_saved, + mc_saved_count * sizeof(struct microcode_intel *)); + /* + * Save the microcode patch mc in mc_save_tmp structure if it's a newer + * version. + */ + mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count); + + /* + * Save the mc_save_tmp in global mc_saved_data. + */ + ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); + if (ret) { + pr_err("Cannot save microcode patch.\n"); + goto out; + } + + show_saved_mc(); + + /* + * Free old saved microcode data. + */ + if (mc_saved) { + for (i = 0; i < mc_saved_count_init; i++) + kfree(mc_saved[i]); + kfree(mc_saved); + } + +out: + mutex_unlock(&x86_cpu_microcode_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(save_mc_for_early); +#endif + +static bool __init load_builtin_intel_microcode(struct cpio_data *cp) +{ +#ifdef CONFIG_X86_64 + unsigned int eax = 0x00000001, ebx, ecx = 0, edx; + unsigned int family, model, stepping; + char name[30]; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + family = __x86_family(eax); + model = x86_model(eax); + stepping = eax & 0xf; + + sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping); + + return get_builtin_firmware(cp, name); +#else + return false; +#endif +} + +static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; +static __init enum ucode_state +scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, + unsigned long start, unsigned long size, + struct ucode_cpu_info *uci) +{ + struct cpio_data cd; + long offset = 0; +#ifdef CONFIG_X86_32 + char *p = (char *)__pa_nodebug(ucode_name); +#else + char *p = ucode_name; +#endif + + cd.data = NULL; + cd.size = 0; + + cd = find_cpio_data(p, (void *)start, size, &offset); + if (!cd.data) { + if (!load_builtin_intel_microcode(&cd)) + return UCODE_ERROR; + } + + return get_matching_model_microcode(0, start, cd.data, cd.size, + mc_saved_data, initrd, uci); +} + +/* + * Print ucode update info. + */ +static void +print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) +{ + int cpu = smp_processor_id(); + + pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", + cpu, + uci->cpu_sig.rev, + date & 0xffff, + date >> 24, + (date >> 16) & 0xff); +} + +#ifdef CONFIG_X86_32 + +static int delay_ucode_info; +static int current_mc_date; + +/* + * Print early updated ucode info after printk works. This is delayed info dump. + */ +void show_ucode_info_early(void) +{ + struct ucode_cpu_info uci; + + if (delay_ucode_info) { + collect_cpu_info_early(&uci); + print_ucode_info(&uci, current_mc_date); + delay_ucode_info = 0; + } +} + +/* + * At this point, we can not call printk() yet. Keep microcode patch number in + * mc_saved_data.mc_saved and delay printing microcode info in + * show_ucode_info_early() until printk() works. + */ +static void print_ucode(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + int *delay_ucode_info_p; + int *current_mc_date_p; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return; + + delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); + current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); + + *delay_ucode_info_p = 1; + *current_mc_date_p = mc_intel->hdr.date; +} +#else + +/* + * Flush global tlb. We only do this in x86_64 where paging has been enabled + * already and PGE should be enabled as well. + */ +static inline void flush_tlb_early(void) +{ + __native_flush_tlb_global_irq_disabled(); +} + +static inline void print_ucode(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc_intel; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return; + + print_ucode_info(uci, mc_intel->hdr.date); +} +#endif + +static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) +{ + struct microcode_intel *mc_intel; + unsigned int val[2]; + + mc_intel = uci->mc; + if (mc_intel == NULL) + return 0; + + /* write microcode via MSR 0x79 */ + native_wrmsr(MSR_IA32_UCODE_WRITE, + (unsigned long) mc_intel->bits, + (unsigned long) mc_intel->bits >> 16 >> 16); + native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + sync_core(); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); + if (val[1] != mc_intel->hdr.rev) + return -1; + +#ifdef CONFIG_X86_64 + /* Flush global tlb. This is precaution. */ + flush_tlb_early(); +#endif + uci->cpu_sig.rev = val[1]; + + if (early) + print_ucode(uci); + else + print_ucode_info(uci, mc_intel->hdr.date); + + return 0; +} + +/* + * This function converts microcode patch offsets previously stored in + * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. + */ +int __init save_microcode_in_initrd_intel(void) +{ + unsigned int count = mc_saved_data.mc_saved_count; + struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; + int ret = 0; + + if (count == 0) + return ret; + + copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); + ret = save_microcode(&mc_saved_data, mc_saved, count); + if (ret) + pr_err("Cannot save microcode patches from initrd.\n"); + + show_saved_mc(); + + return ret; +} + +static void __init +_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, + unsigned long *initrd, + unsigned long start, unsigned long size) +{ + struct ucode_cpu_info uci; + enum ucode_state ret; + + collect_cpu_info_early(&uci); + + ret = scan_microcode(mc_saved_data, initrd, start, size, &uci); + if (ret != UCODE_OK) + return; + + ret = load_microcode(mc_saved_data, initrd, start, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, true); +} + +void __init load_ucode_intel_bsp(void) +{ + u64 start, size; +#ifdef CONFIG_X86_32 + struct boot_params *p; + + p = (struct boot_params *)__pa_nodebug(&boot_params); + start = p->hdr.ramdisk_image; + size = p->hdr.ramdisk_size; + + _load_ucode_intel_bsp( + (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), + start, size); +#else + start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; + size = boot_params.hdr.ramdisk_size; + + _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); +#endif +} + +void load_ucode_intel_ap(void) +{ + struct mc_saved_data *mc_saved_data_p; + struct ucode_cpu_info uci; + unsigned long *mc_saved_in_initrd_p; + unsigned long initrd_start_addr; + enum ucode_state ret; +#ifdef CONFIG_X86_32 + unsigned long *initrd_start_p; + + mc_saved_in_initrd_p = + (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); + initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); +#else + mc_saved_data_p = &mc_saved_data; + mc_saved_in_initrd_p = mc_saved_in_initrd; + initrd_start_addr = initrd_start; +#endif + + /* + * If there is no valid ucode previously saved in memory, no need to + * update ucode on this AP. + */ + if (mc_saved_data_p->mc_saved_count == 0) + return; + + collect_cpu_info_early(&uci); + ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, + initrd_start_addr, &uci); + + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, true); +} + +void reload_ucode_intel(void) +{ + struct ucode_cpu_info uci; + enum ucode_state ret; + + if (!mc_saved_data.mc_saved_count) + return; + + collect_cpu_info_early(&uci); + + ret = load_microcode_early(mc_saved_data.mc_saved, + mc_saved_data.mc_saved_count, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, false); +} static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { @@ -124,7 +840,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) cpf = cpu_sig.pf; crev = cpu_sig.rev; - return get_matching_microcode(csig, cpf, crev, mc_intel); + return has_newer_microcode(mc_intel, csig, cpf, crev); } static int apply_microcode_intel(int cpu) @@ -226,7 +942,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, csig = uci->cpu_sig.sig; cpf = uci->cpu_sig.pf; - if (get_matching_microcode(csig, cpf, new_rev, mc)) { + if (has_newer_microcode(mc, csig, cpf, new_rev)) { vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; @@ -325,7 +1041,7 @@ static struct microcode_ops microcode_intel_ops = { struct microcode_ops * __init init_intel_microcode(void) { - struct cpuinfo_x86 *c = &cpu_data(0); + struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 || cpu_has(c, X86_FEATURE_IA64)) { diff --git a/kernel/arch/x86/kernel/cpu/microcode/intel_early.c b/kernel/arch/x86/kernel/cpu/microcode/intel_early.c deleted file mode 100644 index 2f49ab4ac..000000000 --- a/kernel/arch/x86/kernel/cpu/microcode/intel_early.c +++ /dev/null @@ -1,786 +0,0 @@ -/* - * Intel CPU microcode early update for Linux - * - * Copyright (C) 2012 Fenghua Yu <fenghua.yu@intel.com> - * H Peter Anvin" <hpa@zytor.com> - * - * This allows to early upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 9.11 of Volume 3, IA-32 Intel Architecture - * Software Developer's Manual. - * - * 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 needs to be before all headers so that pr_debug in printk.h doesn't turn - * printk calls into no_printk(). - * - *#define DEBUG - */ - -#include <linux/module.h> -#include <linux/mm.h> -#include <linux/slab.h> -#include <linux/earlycpio.h> -#include <linux/initrd.h> -#include <linux/cpu.h> -#include <asm/msr.h> -#include <asm/microcode_intel.h> -#include <asm/processor.h> -#include <asm/tlbflush.h> -#include <asm/setup.h> - -#undef pr_fmt -#define pr_fmt(fmt) "microcode: " fmt - -static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; -static struct mc_saved_data { - unsigned int mc_saved_count; - struct microcode_intel **mc_saved; -} mc_saved_data; - -static enum ucode_state -load_microcode_early(struct microcode_intel **saved, - unsigned int num_saved, struct ucode_cpu_info *uci) -{ - struct microcode_intel *ucode_ptr, *new_mc = NULL; - struct microcode_header_intel *mc_hdr; - int new_rev, ret, i; - - new_rev = uci->cpu_sig.rev; - - for (i = 0; i < num_saved; i++) { - ucode_ptr = saved[i]; - mc_hdr = (struct microcode_header_intel *)ucode_ptr; - - ret = get_matching_microcode(uci->cpu_sig.sig, - uci->cpu_sig.pf, - new_rev, - ucode_ptr); - if (!ret) - continue; - - new_rev = mc_hdr->rev; - new_mc = ucode_ptr; - } - - if (!new_mc) - return UCODE_NFOUND; - - uci->mc = (struct microcode_intel *)new_mc; - return UCODE_OK; -} - -static inline void -copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd, - unsigned long off, int num_saved) -{ - int i; - - for (i = 0; i < num_saved; i++) - mc_saved[i] = (struct microcode_intel *)(initrd[i] + off); -} - -#ifdef CONFIG_X86_32 -static void -microcode_phys(struct microcode_intel **mc_saved_tmp, - struct mc_saved_data *mc_saved_data) -{ - int i; - struct microcode_intel ***mc_saved; - - mc_saved = (struct microcode_intel ***) - __pa_nodebug(&mc_saved_data->mc_saved); - for (i = 0; i < mc_saved_data->mc_saved_count; i++) { - struct microcode_intel *p; - - p = *(struct microcode_intel **) - __pa_nodebug(mc_saved_data->mc_saved + i); - mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); - } -} -#endif - -static enum ucode_state -load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, - unsigned long initrd_start, struct ucode_cpu_info *uci) -{ - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int count = mc_saved_data->mc_saved_count; - - if (!mc_saved_data->mc_saved) { - copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count); - - return load_microcode_early(mc_saved_tmp, count, uci); - } else { -#ifdef CONFIG_X86_32 - microcode_phys(mc_saved_tmp, mc_saved_data); - return load_microcode_early(mc_saved_tmp, count, uci); -#else - return load_microcode_early(mc_saved_data->mc_saved, - count, uci); -#endif - } -} - -/* - * Given CPU signature and a microcode patch, this function finds if the - * microcode patch has matching family and model with the CPU. - */ -static enum ucode_state -matching_model_microcode(struct microcode_header_intel *mc_header, - unsigned long sig) -{ - unsigned int fam, model; - unsigned int fam_ucode, model_ucode; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - unsigned long data_size = get_datasize(mc_header); - int ext_sigcount, i; - struct extended_signature *ext_sig; - - fam = __x86_family(sig); - model = x86_model(sig); - - fam_ucode = __x86_family(mc_header->sig); - model_ucode = x86_model(mc_header->sig); - - if (fam == fam_ucode && model == model_ucode) - return UCODE_OK; - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - return UCODE_NFOUND; - - ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - ext_sigcount = ext_header->count; - - for (i = 0; i < ext_sigcount; i++) { - fam_ucode = __x86_family(ext_sig->sig); - model_ucode = x86_model(ext_sig->sig); - - if (fam == fam_ucode && model == model_ucode) - return UCODE_OK; - - ext_sig++; - } - return UCODE_NFOUND; -} - -static int -save_microcode(struct mc_saved_data *mc_saved_data, - struct microcode_intel **mc_saved_src, - unsigned int mc_saved_count) -{ - int i, j; - struct microcode_intel **saved_ptr; - int ret; - - if (!mc_saved_count) - return -EINVAL; - - /* - * Copy new microcode data. - */ - saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL); - if (!saved_ptr) - return -ENOMEM; - - for (i = 0; i < mc_saved_count; i++) { - struct microcode_header_intel *mc_hdr; - struct microcode_intel *mc; - unsigned long size; - - if (!mc_saved_src[i]) { - ret = -EINVAL; - goto err; - } - - mc = mc_saved_src[i]; - mc_hdr = &mc->hdr; - size = get_totalsize(mc_hdr); - - saved_ptr[i] = kmalloc(size, GFP_KERNEL); - if (!saved_ptr[i]) { - ret = -ENOMEM; - goto err; - } - - memcpy(saved_ptr[i], mc, size); - } - - /* - * Point to newly saved microcode. - */ - mc_saved_data->mc_saved = saved_ptr; - mc_saved_data->mc_saved_count = mc_saved_count; - - return 0; - -err: - for (j = 0; j <= i; j++) - kfree(saved_ptr[j]); - kfree(saved_ptr); - - return ret; -} - -/* - * A microcode patch in ucode_ptr is saved into mc_saved - * - if it has matching signature and newer revision compared to an existing - * patch mc_saved. - * - or if it is a newly discovered microcode patch. - * - * The microcode patch should have matching model with CPU. - * - * Returns: The updated number @num_saved of saved microcode patches. - */ -static unsigned int _save_mc(struct microcode_intel **mc_saved, - u8 *ucode_ptr, unsigned int num_saved) -{ - struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - unsigned int sig, pf, new_rev; - int found = 0, i; - - mc_hdr = (struct microcode_header_intel *)ucode_ptr; - - for (i = 0; i < num_saved; i++) { - mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; - sig = mc_saved_hdr->sig; - pf = mc_saved_hdr->pf; - new_rev = mc_hdr->rev; - - if (!get_matching_sig(sig, pf, new_rev, ucode_ptr)) - continue; - - found = 1; - - if (!revision_is_newer(mc_hdr, new_rev)) - continue; - - /* - * Found an older ucode saved earlier. Replace it with - * this newer one. - */ - mc_saved[i] = (struct microcode_intel *)ucode_ptr; - break; - } - - /* Newly detected microcode, save it to memory. */ - if (i >= num_saved && !found) - mc_saved[num_saved++] = (struct microcode_intel *)ucode_ptr; - - return num_saved; -} - -/* - * Get microcode matching with BSP's model. Only CPUs with the same model as - * BSP can stay in the platform. - */ -static enum ucode_state __init -get_matching_model_microcode(int cpu, unsigned long start, - void *data, size_t size, - struct mc_saved_data *mc_saved_data, - unsigned long *mc_saved_in_initrd, - struct ucode_cpu_info *uci) -{ - u8 *ucode_ptr = data; - unsigned int leftover = size; - enum ucode_state state = UCODE_OK; - unsigned int mc_size; - struct microcode_header_intel *mc_header; - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int mc_saved_count = mc_saved_data->mc_saved_count; - int i; - - while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) { - - if (leftover < sizeof(mc_header)) - break; - - mc_header = (struct microcode_header_intel *)ucode_ptr; - - mc_size = get_totalsize(mc_header); - if (!mc_size || mc_size > leftover || - microcode_sanity_check(ucode_ptr, 0) < 0) - break; - - leftover -= mc_size; - - /* - * Since APs with same family and model as the BSP may boot in - * the platform, we need to find and save microcode patches - * with the same family and model as the BSP. - */ - if (matching_model_microcode(mc_header, uci->cpu_sig.sig) != - UCODE_OK) { - ucode_ptr += mc_size; - continue; - } - - mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count); - - ucode_ptr += mc_size; - } - - if (leftover) { - state = UCODE_ERROR; - goto out; - } - - if (mc_saved_count == 0) { - state = UCODE_NFOUND; - goto out; - } - - for (i = 0; i < mc_saved_count; i++) - mc_saved_in_initrd[i] = (unsigned long)mc_saved_tmp[i] - start; - - mc_saved_data->mc_saved_count = mc_saved_count; -out: - return state; -} - -static int collect_cpu_info_early(struct ucode_cpu_info *uci) -{ - unsigned int val[2]; - unsigned int family, model; - struct cpu_signature csig; - unsigned int eax, ebx, ecx, edx; - - csig.sig = 0; - csig.pf = 0; - csig.rev = 0; - - memset(uci, 0, sizeof(*uci)); - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - csig.sig = eax; - - family = __x86_family(csig.sig); - model = x86_model(csig.sig); - - if ((model >= 5) || (family > 6)) { - /* get processor flags from MSR 0x17 */ - native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig.pf = 1 << ((val[1] >> 18) & 7); - } - native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - - csig.rev = val[1]; - - uci->cpu_sig = csig; - uci->valid = 1; - - return 0; -} - -#ifdef DEBUG -static void __ref show_saved_mc(void) -{ - int i, j; - unsigned int sig, pf, rev, total_size, data_size, date; - struct ucode_cpu_info uci; - - if (mc_saved_data.mc_saved_count == 0) { - pr_debug("no microcode data saved.\n"); - return; - } - pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count); - - collect_cpu_info_early(&uci); - - sig = uci.cpu_sig.sig; - pf = uci.cpu_sig.pf; - rev = uci.cpu_sig.rev; - pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); - - for (i = 0; i < mc_saved_data.mc_saved_count; i++) { - struct microcode_header_intel *mc_saved_header; - struct extended_sigtable *ext_header; - int ext_sigcount; - struct extended_signature *ext_sig; - - mc_saved_header = (struct microcode_header_intel *) - mc_saved_data.mc_saved[i]; - sig = mc_saved_header->sig; - pf = mc_saved_header->pf; - rev = mc_saved_header->rev; - total_size = get_totalsize(mc_saved_header); - data_size = get_datasize(mc_saved_header); - date = mc_saved_header->date; - - pr_debug("mc_saved[%d]: sig=0x%x, pf=0x%x, rev=0x%x, toal size=0x%x, date = %04x-%02x-%02x\n", - i, sig, pf, rev, total_size, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); - - /* Look for ext. headers: */ - if (total_size <= data_size + MC_HEADER_SIZE) - continue; - - ext_header = (void *) mc_saved_header + data_size + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; - - for (j = 0; j < ext_sigcount; j++) { - sig = ext_sig->sig; - pf = ext_sig->pf; - - pr_debug("\tExtended[%d]: sig=0x%x, pf=0x%x\n", - j, sig, pf); - - ext_sig++; - } - - } -} -#else -static inline void show_saved_mc(void) -{ -} -#endif - -#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU) -static DEFINE_MUTEX(x86_cpu_microcode_mutex); -/* - * Save this mc into mc_saved_data. So it will be loaded early when a CPU is - * hot added or resumes. - * - * Please make sure this mc should be a valid microcode patch before calling - * this function. - */ -int save_mc_for_early(u8 *mc) -{ - struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; - unsigned int mc_saved_count_init; - unsigned int mc_saved_count; - struct microcode_intel **mc_saved; - int ret = 0; - int i; - - /* - * Hold hotplug lock so mc_saved_data is not accessed by a CPU in - * hotplug. - */ - mutex_lock(&x86_cpu_microcode_mutex); - - mc_saved_count_init = mc_saved_data.mc_saved_count; - mc_saved_count = mc_saved_data.mc_saved_count; - mc_saved = mc_saved_data.mc_saved; - - if (mc_saved && mc_saved_count) - memcpy(mc_saved_tmp, mc_saved, - mc_saved_count * sizeof(struct microcode_intel *)); - /* - * Save the microcode patch mc in mc_save_tmp structure if it's a newer - * version. - */ - mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count); - - /* - * Save the mc_save_tmp in global mc_saved_data. - */ - ret = save_microcode(&mc_saved_data, mc_saved_tmp, mc_saved_count); - if (ret) { - pr_err("Cannot save microcode patch.\n"); - goto out; - } - - show_saved_mc(); - - /* - * Free old saved microcode data. - */ - if (mc_saved) { - for (i = 0; i < mc_saved_count_init; i++) - kfree(mc_saved[i]); - kfree(mc_saved); - } - -out: - mutex_unlock(&x86_cpu_microcode_mutex); - - return ret; -} -EXPORT_SYMBOL_GPL(save_mc_for_early); -#endif - -static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; -static __init enum ucode_state -scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, - unsigned long start, unsigned long size, - struct ucode_cpu_info *uci) -{ - struct cpio_data cd; - long offset = 0; -#ifdef CONFIG_X86_32 - char *p = (char *)__pa_nodebug(ucode_name); -#else - char *p = ucode_name; -#endif - - cd.data = NULL; - cd.size = 0; - - cd = find_cpio_data(p, (void *)start, size, &offset); - if (!cd.data) - return UCODE_ERROR; - - return get_matching_model_microcode(0, start, cd.data, cd.size, - mc_saved_data, initrd, uci); -} - -/* - * Print ucode update info. - */ -static void -print_ucode_info(struct ucode_cpu_info *uci, unsigned int date) -{ - int cpu = smp_processor_id(); - - pr_info("CPU%d microcode updated early to revision 0x%x, date = %04x-%02x-%02x\n", - cpu, - uci->cpu_sig.rev, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); -} - -#ifdef CONFIG_X86_32 - -static int delay_ucode_info; -static int current_mc_date; - -/* - * Print early updated ucode info after printk works. This is delayed info dump. - */ -void show_ucode_info_early(void) -{ - struct ucode_cpu_info uci; - - if (delay_ucode_info) { - collect_cpu_info_early(&uci); - print_ucode_info(&uci, current_mc_date); - delay_ucode_info = 0; - } -} - -/* - * At this point, we can not call printk() yet. Keep microcode patch number in - * mc_saved_data.mc_saved and delay printing microcode info in - * show_ucode_info_early() until printk() works. - */ -static void print_ucode(struct ucode_cpu_info *uci) -{ - struct microcode_intel *mc_intel; - int *delay_ucode_info_p; - int *current_mc_date_p; - - mc_intel = uci->mc; - if (mc_intel == NULL) - return; - - delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); - current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); - - *delay_ucode_info_p = 1; - *current_mc_date_p = mc_intel->hdr.date; -} -#else - -/* - * Flush global tlb. We only do this in x86_64 where paging has been enabled - * already and PGE should be enabled as well. - */ -static inline void flush_tlb_early(void) -{ - __native_flush_tlb_global_irq_disabled(); -} - -static inline void print_ucode(struct ucode_cpu_info *uci) -{ - struct microcode_intel *mc_intel; - - mc_intel = uci->mc; - if (mc_intel == NULL) - return; - - print_ucode_info(uci, mc_intel->hdr.date); -} -#endif - -static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) -{ - struct microcode_intel *mc_intel; - unsigned int val[2]; - - mc_intel = uci->mc; - if (mc_intel == NULL) - return 0; - - /* write microcode via MSR 0x79 */ - native_wrmsr(MSR_IA32_UCODE_WRITE, - (unsigned long) mc_intel->bits, - (unsigned long) mc_intel->bits >> 16 >> 16); - native_wrmsr(MSR_IA32_UCODE_REV, 0, 0); - - /* As documented in the SDM: Do a CPUID 1 here */ - sync_core(); - - /* get the current revision from MSR 0x8B */ - native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]); - if (val[1] != mc_intel->hdr.rev) - return -1; - -#ifdef CONFIG_X86_64 - /* Flush global tlb. This is precaution. */ - flush_tlb_early(); -#endif - uci->cpu_sig.rev = val[1]; - - if (early) - print_ucode(uci); - else - print_ucode_info(uci, mc_intel->hdr.date); - - return 0; -} - -/* - * This function converts microcode patch offsets previously stored in - * mc_saved_in_initrd to pointers and stores the pointers in mc_saved_data. - */ -int __init save_microcode_in_initrd_intel(void) -{ - unsigned int count = mc_saved_data.mc_saved_count; - struct microcode_intel *mc_saved[MAX_UCODE_COUNT]; - int ret = 0; - - if (count == 0) - return ret; - - copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); - ret = save_microcode(&mc_saved_data, mc_saved, count); - if (ret) - pr_err("Cannot save microcode patches from initrd.\n"); - - show_saved_mc(); - - return ret; -} - -static void __init -_load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, - unsigned long *initrd, - unsigned long start, unsigned long size) -{ - struct ucode_cpu_info uci; - enum ucode_state ret; - - collect_cpu_info_early(&uci); - - ret = scan_microcode(mc_saved_data, initrd, start, size, &uci); - if (ret != UCODE_OK) - return; - - ret = load_microcode(mc_saved_data, initrd, start, &uci); - if (ret != UCODE_OK) - return; - - apply_microcode_early(&uci, true); -} - -void __init load_ucode_intel_bsp(void) -{ - u64 start, size; -#ifdef CONFIG_X86_32 - struct boot_params *p; - - p = (struct boot_params *)__pa_nodebug(&boot_params); - start = p->hdr.ramdisk_image; - size = p->hdr.ramdisk_size; - - _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - start, size); -#else - start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; - size = boot_params.hdr.ramdisk_size; - - _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); -#endif -} - -void load_ucode_intel_ap(void) -{ - struct mc_saved_data *mc_saved_data_p; - struct ucode_cpu_info uci; - unsigned long *mc_saved_in_initrd_p; - unsigned long initrd_start_addr; - enum ucode_state ret; -#ifdef CONFIG_X86_32 - unsigned long *initrd_start_p; - - mc_saved_in_initrd_p = - (unsigned long *)__pa_nodebug(mc_saved_in_initrd); - mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); - initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); -#else - mc_saved_data_p = &mc_saved_data; - mc_saved_in_initrd_p = mc_saved_in_initrd; - initrd_start_addr = initrd_start; -#endif - - /* - * If there is no valid ucode previously saved in memory, no need to - * update ucode on this AP. - */ - if (mc_saved_data_p->mc_saved_count == 0) - return; - - collect_cpu_info_early(&uci); - ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); - - if (ret != UCODE_OK) - return; - - apply_microcode_early(&uci, true); -} - -void reload_ucode_intel(void) -{ - struct ucode_cpu_info uci; - enum ucode_state ret; - - if (!mc_saved_data.mc_saved_count) - return; - - collect_cpu_info_early(&uci); - - ret = load_microcode_early(mc_saved_data.mc_saved, - mc_saved_data.mc_saved_count, &uci); - if (ret != UCODE_OK) - return; - - apply_microcode_early(&uci, false); -} diff --git a/kernel/arch/x86/kernel/cpu/microcode/intel_lib.c b/kernel/arch/x86/kernel/cpu/microcode/intel_lib.c index cd47a510a..b96896bcb 100644 --- a/kernel/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/kernel/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -25,17 +25,23 @@ #include <linux/firmware.h> #include <linux/uaccess.h> #include <linux/kernel.h> -#include <linux/module.h> #include <asm/microcode_intel.h> #include <asm/processor.h> #include <asm/msr.h> -static inline int -update_match_cpu(unsigned int csig, unsigned int cpf, - unsigned int sig, unsigned int pf) +static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, + unsigned int s2, unsigned int p2) { - return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1; + if (s1 != s2) + return false; + + /* Processor flags are either both 0 ... */ + if (!p1 && !p2) + return true; + + /* ... or they intersect. */ + return p1 & p2; } int microcode_sanity_check(void *mc, int print_err) @@ -124,27 +130,25 @@ EXPORT_SYMBOL_GPL(microcode_sanity_check); /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) +int find_matching_signature(void *mc, unsigned int csig, int cpf) { - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header; - unsigned long total_size = get_totalsize(mc_header); - int ext_sigcount, i; + struct microcode_header_intel *mc_hdr = mc; + struct extended_sigtable *ext_hdr; struct extended_signature *ext_sig; + int i; - if (update_match_cpu(csig, cpf, mc_header->sig, mc_header->pf)) + if (cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) return 1; /* Look for ext. headers: */ - if (total_size <= get_datasize(mc_header) + MC_HEADER_SIZE) + if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) return 0; - ext_header = mc + get_datasize(mc_header) + MC_HEADER_SIZE; - ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; + ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; + ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; - for (i = 0; i < ext_sigcount; i++) { - if (update_match_cpu(csig, cpf, ext_sig->sig, ext_sig->pf)) + for (i = 0; i < ext_hdr->count; i++) { + if (cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) return 1; ext_sig++; } @@ -154,13 +158,13 @@ int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) /* * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc) +int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) { struct microcode_header_intel *mc_hdr = mc; - if (!revision_is_newer(mc_hdr, rev)) + if (mc_hdr->rev <= new_rev) return 0; - return get_matching_sig(csig, cpf, rev, mc); + return find_matching_signature(mc, csig, cpf); } -EXPORT_SYMBOL_GPL(get_matching_microcode); +EXPORT_SYMBOL_GPL(has_newer_microcode); diff --git a/kernel/arch/x86/kernel/cpu/mshyperv.c b/kernel/arch/x86/kernel/cpu/mshyperv.c index 939155ffd..20e242ea1 100644 --- a/kernel/arch/x86/kernel/cpu/mshyperv.c +++ b/kernel/arch/x86/kernel/cpu/mshyperv.c @@ -18,6 +18,7 @@ #include <linux/efi.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/kexec.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv.h> @@ -28,25 +29,26 @@ #include <asm/i8259.h> #include <asm/apic.h> #include <asm/timer.h> +#include <asm/reboot.h> struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); #if IS_ENABLED(CONFIG_HYPERV) static void (*vmbus_handler)(void); +static void (*hv_kexec_handler)(void); +static void (*hv_crash_handler)(struct pt_regs *regs); void hyperv_vector_handler(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - irq_enter(); - exit_idle(); - + entering_irq(); inc_irq_stat(irq_hv_callback_count); if (vmbus_handler) vmbus_handler(); - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); } @@ -69,7 +71,47 @@ void hv_remove_vmbus_irq(void) } EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq); EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq); -#endif + +void hv_setup_kexec_handler(void (*handler)(void)) +{ + hv_kexec_handler = handler; +} +EXPORT_SYMBOL_GPL(hv_setup_kexec_handler); + +void hv_remove_kexec_handler(void) +{ + hv_kexec_handler = NULL; +} +EXPORT_SYMBOL_GPL(hv_remove_kexec_handler); + +void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs)) +{ + hv_crash_handler = handler; +} +EXPORT_SYMBOL_GPL(hv_setup_crash_handler); + +void hv_remove_crash_handler(void) +{ + hv_crash_handler = NULL; +} +EXPORT_SYMBOL_GPL(hv_remove_crash_handler); + +#ifdef CONFIG_KEXEC_CORE +static void hv_machine_shutdown(void) +{ + if (kexec_in_progress && hv_kexec_handler) + hv_kexec_handler(); + native_machine_shutdown(); +} + +static void hv_machine_crash_shutdown(struct pt_regs *regs) +{ + if (hv_crash_handler) + hv_crash_handler(regs); + native_machine_crash_shutdown(regs); +} +#endif /* CONFIG_KEXEC_CORE */ +#endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) { @@ -116,6 +158,7 @@ static void __init ms_hyperv_init_platform(void) * Extract the features and hints */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); + ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n", @@ -143,6 +186,11 @@ static void __init ms_hyperv_init_platform(void) no_timer_check = 1; #endif +#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE) + machine_ops.shutdown = hv_machine_shutdown; + machine_ops.crash_shutdown = hv_machine_crash_shutdown; +#endif + mark_tsc_unstable("running on Hyper-V"); } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { diff --git a/kernel/arch/x86/kernel/cpu/mtrr/cleanup.c b/kernel/arch/x86/kernel/cpu/mtrr/cleanup.c index 5f90b85ff..70d7c93f4 100644 --- a/kernel/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/kernel/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -98,7 +98,8 @@ x86_get_mtrr_mem_range(struct range *range, int nr_range, continue; base = range_state[i].base_pfn; if (base < (1<<(20-PAGE_SHIFT)) && mtrr_state.have_fixed && - (mtrr_state.enabled & 1)) { + (mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { /* Var MTRR contains UC entry below 1M? Skip it: */ printk(BIOS_BUG_MSG, i); if (base + size <= (1<<(20-PAGE_SHIFT))) diff --git a/kernel/arch/x86/kernel/cpu/mtrr/generic.c b/kernel/arch/x86/kernel/cpu/mtrr/generic.c index 7d74f7b3c..3b533cf37 100644 --- a/kernel/arch/x86/kernel/cpu/mtrr/generic.c +++ b/kernel/arch/x86/kernel/cpu/mtrr/generic.c @@ -102,59 +102,76 @@ static int check_type_overlap(u8 *prev, u8 *curr) return 0; } -/* - * Error/Semi-error returns: - * 0xFF - when MTRR is not enabled - * *repeat == 1 implies [start:end] spanned across MTRR range and type returned - * corresponds only to [start:*partial_end]. - * Caller has to lookup again for [*partial_end:end]. +/** + * mtrr_type_lookup_fixed - look up memory type in MTRR fixed entries + * + * Return the MTRR fixed memory type of 'start'. + * + * MTRR fixed entries are divided into the following ways: + * 0x00000 - 0x7FFFF : This range is divided into eight 64KB sub-ranges + * 0x80000 - 0xBFFFF : This range is divided into sixteen 16KB sub-ranges + * 0xC0000 - 0xFFFFF : This range is divided into sixty-four 4KB sub-ranges + * + * Return Values: + * MTRR_TYPE_(type) - Matched memory type + * MTRR_TYPE_INVALID - Unmatched + */ +static u8 mtrr_type_lookup_fixed(u64 start, u64 end) +{ + int idx; + + if (start >= 0x100000) + return MTRR_TYPE_INVALID; + + /* 0x0 - 0x7FFFF */ + if (start < 0x80000) { + idx = 0; + idx += (start >> 16); + return mtrr_state.fixed_ranges[idx]; + /* 0x80000 - 0xBFFFF */ + } else if (start < 0xC0000) { + idx = 1 * 8; + idx += ((start - 0x80000) >> 14); + return mtrr_state.fixed_ranges[idx]; + } + + /* 0xC0000 - 0xFFFFF */ + idx = 3 * 8; + idx += ((start - 0xC0000) >> 12); + return mtrr_state.fixed_ranges[idx]; +} + +/** + * mtrr_type_lookup_variable - look up memory type in MTRR variable entries + * + * Return Value: + * MTRR_TYPE_(type) - Matched memory type or default memory type (unmatched) + * + * Output Arguments: + * repeat - Set to 1 when [start:end] spanned across MTRR range and type + * returned corresponds only to [start:*partial_end]. Caller has + * to lookup again for [*partial_end:end]. + * + * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the + * region is fully covered by a single MTRR entry or the default + * type. */ -static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) +static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, + int *repeat, u8 *uniform) { int i; u64 base, mask; u8 prev_match, curr_match; *repeat = 0; - if (!mtrr_state_set) - return 0xFF; - - if (!mtrr_state.enabled) - return 0xFF; + *uniform = 1; - /* Make end inclusive end, instead of exclusive */ + /* Make end inclusive instead of exclusive */ end--; - /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state.have_fixed && (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state.fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state.fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state.fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - if (!(mtrr_state.enabled & 2)) - return mtrr_state.def_type; - - prev_match = 0xFF; + prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; + unsigned short start_state, end_state, inclusive; if (!(mtrr_state.var_ranges[i].mask_lo & (1 << 11))) continue; @@ -166,20 +183,29 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) start_state = ((start & mask) == (base & mask)); end_state = ((end & mask) == (base & mask)); + inclusive = ((start < base) && (end > base)); - if (start_state != end_state) { + if ((start_state != end_state) || inclusive) { /* * We have start:end spanning across an MTRR. - * We split the region into - * either - * (start:mtrr_end) (mtrr_end:end) - * or - * (start:mtrr_start) (mtrr_start:end) + * We split the region into either + * + * - start_state:1 + * (start:mtrr_end)(mtrr_end:end) + * - end_state:1 + * (start:mtrr_start)(mtrr_start:end) + * - inclusive:1 + * (start:mtrr_start)(mtrr_start:mtrr_end)(mtrr_end:end) + * * depending on kind of overlap. - * Return the type for first region and a pointer to - * the start of second region so that caller will - * lookup again on the second region. - * Note: This way we handle multiple overlaps as well. + * + * Return the type of the first region and a pointer + * to the start of next region so that caller will be + * advised to lookup again after having adjusted start + * and end. + * + * Note: This way we handle overlaps with multiple + * entries and the default type properly. */ if (start_state) *partial_end = base + get_mtrr_size(mask); @@ -193,59 +219,94 @@ static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat) end = *partial_end - 1; /* end is inclusive */ *repeat = 1; + *uniform = 0; } if ((start & mask) != (base & mask)) continue; curr_match = mtrr_state.var_ranges[i].base_lo & 0xff; - if (prev_match == 0xFF) { + if (prev_match == MTRR_TYPE_INVALID) { prev_match = curr_match; continue; } + *uniform = 0; if (check_type_overlap(&prev_match, &curr_match)) return curr_match; } - if (mtrr_tom2) { - if (start >= (1ULL<<32) && (end < mtrr_tom2)) - return MTRR_TYPE_WRBACK; - } - - if (prev_match != 0xFF) + if (prev_match != MTRR_TYPE_INVALID) return prev_match; return mtrr_state.def_type; } -/* - * Returns the effective MTRR type for the region - * Error return: - * 0xFF - when MTRR is not enabled +/** + * mtrr_type_lookup - look up memory type in MTRR + * + * Return Values: + * MTRR_TYPE_(type) - The effective MTRR type for the region + * MTRR_TYPE_INVALID - MTRR is disabled + * + * Output Argument: + * uniform - Set to 1 when an MTRR covers the region uniformly, i.e. the + * region is fully covered by a single MTRR entry or the default + * type. */ -u8 mtrr_type_lookup(u64 start, u64 end) +u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { - u8 type, prev_type; + u8 type, prev_type, is_uniform = 1, dummy; int repeat; u64 partial_end; - type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + if (!mtrr_state_set) + return MTRR_TYPE_INVALID; + + if (!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED)) + return MTRR_TYPE_INVALID; + + /* + * Look up the fixed ranges first, which take priority over + * the variable ranges. + */ + if ((start < 0x100000) && + (mtrr_state.have_fixed) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) { + is_uniform = 0; + type = mtrr_type_lookup_fixed(start, end); + goto out; + } + + /* + * Look up the variable ranges. Look of multiple ranges matching + * this address and pick type as per MTRR precedence. + */ + type = mtrr_type_lookup_variable(start, end, &partial_end, + &repeat, &is_uniform); /* * Common path is with repeat = 0. * However, we can have cases where [start:end] spans across some - * MTRR range. Do repeated lookups for that case here. + * MTRR ranges and/or the default type. Do repeated lookups for + * that case here. */ while (repeat) { prev_type = type; start = partial_end; - type = __mtrr_type_lookup(start, end, &partial_end, &repeat); + is_uniform = 0; + type = mtrr_type_lookup_variable(start, end, &partial_end, + &repeat, &dummy); if (check_type_overlap(&prev_type, &type)) - return type; + goto out; } + if (mtrr_tom2 && (start >= (1ULL<<32)) && (end < mtrr_tom2)) + type = MTRR_TYPE_WRBACK; + +out: + *uniform = is_uniform; return type; } @@ -347,7 +408,9 @@ static void __init print_mtrr_state(void) mtrr_attrib_to_str(mtrr_state.def_type)); if (mtrr_state.have_fixed) { pr_debug("MTRR fixed ranges %sabled:\n", - mtrr_state.enabled & 1 ? "en" : "dis"); + ((mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED) && + (mtrr_state.enabled & MTRR_STATE_MTRR_FIXED_ENABLED)) ? + "en" : "dis"); print_fixed(0x00000, 0x10000, mtrr_state.fixed_ranges + 0); for (i = 0; i < 2; ++i) print_fixed(0x80000 + i * 0x20000, 0x04000, @@ -360,7 +423,7 @@ static void __init print_mtrr_state(void) print_fixed_last(); } pr_debug("MTRR variable ranges %sabled:\n", - mtrr_state.enabled & 2 ? "en" : "dis"); + mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED ? "en" : "dis"); high_width = (__ffs64(size_or_mask) - (32 - PAGE_SHIFT) + 3) / 4; for (i = 0; i < num_var_ranges; ++i) { @@ -382,7 +445,7 @@ static void __init print_mtrr_state(void) } /* Grab all of the MTRR state for this CPU into *state */ -void __init get_mtrr_state(void) +bool __init get_mtrr_state(void) { struct mtrr_var_range *vrs; unsigned long flags; @@ -426,6 +489,8 @@ void __init get_mtrr_state(void) post_set(); local_irq_restore(flags); + + return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED); } /* Some BIOS's are messed up and don't set all MTRRs the same! */ diff --git a/kernel/arch/x86/kernel/cpu/mtrr/main.c b/kernel/arch/x86/kernel/cpu/mtrr/main.c index ea5f363a1..f891b4750 100644 --- a/kernel/arch/x86/kernel/cpu/mtrr/main.c +++ b/kernel/arch/x86/kernel/cpu/mtrr/main.c @@ -59,6 +59,12 @@ #define MTRR_TO_PHYS_WC_OFFSET 1000 u32 num_var_ranges; +static bool __mtrr_enabled; + +static bool mtrr_enabled(void) +{ + return __mtrr_enabled; +} unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; static DEFINE_MUTEX(mtrr_mutex); @@ -286,7 +292,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, int i, replace, error; mtrr_type ltype; - if (!mtrr_if) + if (!mtrr_enabled()) return -ENXIO; error = mtrr_if->validate_add_page(base, size, type); @@ -435,12 +441,13 @@ static int mtrr_check(unsigned long base, unsigned long size) int mtrr_add(unsigned long base, unsigned long size, unsigned int type, bool increment) { + if (!mtrr_enabled()) + return -ENODEV; if (mtrr_check(base, size)) return -EINVAL; return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type, increment); } -EXPORT_SYMBOL(mtrr_add); /** * mtrr_del_page - delete a memory type region @@ -463,8 +470,8 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) unsigned long lbase, lsize; int error = -EINVAL; - if (!mtrr_if) - return -ENXIO; + if (!mtrr_enabled()) + return -ENODEV; max = num_var_ranges; /* No CPU hotplug when we change MTRR entries */ @@ -523,11 +530,12 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) */ int mtrr_del(int reg, unsigned long base, unsigned long size) { + if (!mtrr_enabled()) + return -ENODEV; if (mtrr_check(base, size)) return -EINVAL; return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT); } -EXPORT_SYMBOL(mtrr_del); /** * arch_phys_wc_add - add a WC MTRR and handle errors if PAT is unavailable @@ -538,6 +546,9 @@ EXPORT_SYMBOL(mtrr_del); * attempts to add a WC MTRR covering size bytes starting at base and * logs an error if this fails. * + * The called should provide a power of two size on an equivalent + * power of two boundary. + * * Drivers must store the return value to pass to mtrr_del_wc_if_needed, * but drivers should not try to interpret that return value. */ @@ -545,7 +556,7 @@ int arch_phys_wc_add(unsigned long base, unsigned long size) { int ret; - if (pat_enabled) + if (pat_enabled() || !mtrr_enabled()) return 0; /* Success! (We don't need to do anything.) */ ret = mtrr_add(base, size, MTRR_TYPE_WRCOMB, true); @@ -577,7 +588,7 @@ void arch_phys_wc_del(int handle) EXPORT_SYMBOL(arch_phys_wc_del); /* - * phys_wc_to_mtrr_index - translates arch_phys_wc_add's return value + * arch_phys_wc_index - translates arch_phys_wc_add's return value * @handle: Return value from arch_phys_wc_add * * This will turn the return value from arch_phys_wc_add into an mtrr @@ -587,14 +598,14 @@ EXPORT_SYMBOL(arch_phys_wc_del); * in printk line. Alas there is an illegitimate use in some ancient * drm ioctls. */ -int phys_wc_to_mtrr_index(int handle) +int arch_phys_wc_index(int handle) { if (handle < MTRR_TO_PHYS_WC_OFFSET) return -1; else return handle - MTRR_TO_PHYS_WC_OFFSET; } -EXPORT_SYMBOL_GPL(phys_wc_to_mtrr_index); +EXPORT_SYMBOL_GPL(arch_phys_wc_index); /* * HACK ALERT! @@ -734,10 +745,12 @@ void __init mtrr_bp_init(void) } if (mtrr_if) { + __mtrr_enabled = true; set_num_var_ranges(); init_table(); if (use_intel()) { - get_mtrr_state(); + /* BIOS may override */ + __mtrr_enabled = get_mtrr_state(); if (mtrr_cleanup(phys_addr)) { changed_by_mtrr_cleanup = 1; @@ -745,10 +758,16 @@ void __init mtrr_bp_init(void) } } } + + if (!mtrr_enabled()) + pr_info("MTRR: Disabled\n"); } void mtrr_ap_init(void) { + if (!mtrr_enabled()) + return; + if (!use_intel() || mtrr_aps_delayed_init) return; /* @@ -774,6 +793,9 @@ void mtrr_save_state(void) { int first_cpu; + if (!mtrr_enabled()) + return; + get_online_cpus(); first_cpu = cpumask_first(cpu_online_mask); smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); @@ -782,6 +804,8 @@ void mtrr_save_state(void) void set_mtrr_aps_delayed_init(void) { + if (!mtrr_enabled()) + return; if (!use_intel()) return; @@ -793,7 +817,7 @@ void set_mtrr_aps_delayed_init(void) */ void mtrr_aps_init(void) { - if (!use_intel()) + if (!use_intel() || !mtrr_enabled()) return; /* @@ -810,7 +834,7 @@ void mtrr_aps_init(void) void mtrr_bp_restore(void) { - if (!use_intel()) + if (!use_intel() || !mtrr_enabled()) return; mtrr_if->set_all(); @@ -818,7 +842,7 @@ void mtrr_bp_restore(void) static int __init mtrr_init_finialize(void) { - if (!mtrr_if) + if (!mtrr_enabled()) return 0; if (use_intel()) { diff --git a/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h b/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h index df5e41f31..951884dcc 100644 --- a/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/kernel/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -51,7 +51,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); -void get_mtrr_state(void); +bool get_mtrr_state(void); extern void set_mtrr_ops(const struct mtrr_ops *ops); diff --git a/kernel/arch/x86/kernel/cpu/perf_event.c b/kernel/arch/x86/kernel/cpu/perf_event.c index 4cc98a4e8..2bf79d7c9 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event.c +++ b/kernel/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -135,6 +135,7 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) } static atomic_t active_events; +static atomic_t pmc_refcount; static DEFINE_MUTEX(pmc_reserve_mutex); #ifdef CONFIG_X86_LOCAL_APIC @@ -271,6 +272,7 @@ msr_fail: static void hw_perf_event_destroy(struct perf_event *event) { x86_release_hardware(); + atomic_dec(&active_events); } void hw_perf_lbr_event_destroy(struct perf_event *event) @@ -324,16 +326,16 @@ int x86_reserve_hardware(void) { int err = 0; - if (!atomic_inc_not_zero(&active_events)) { + if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); - if (atomic_read(&active_events) == 0) { + if (atomic_read(&pmc_refcount) == 0) { if (!reserve_pmc_hardware()) err = -EBUSY; else reserve_ds_buffers(); } if (!err) - atomic_inc(&active_events); + atomic_inc(&pmc_refcount); mutex_unlock(&pmc_reserve_mutex); } @@ -342,7 +344,7 @@ int x86_reserve_hardware(void) void x86_release_hardware(void) { - if (atomic_dec_and_mutex_lock(&active_events, &pmc_reserve_mutex)) { + if (atomic_dec_and_mutex_lock(&pmc_refcount, &pmc_reserve_mutex)) { release_pmc_hardware(); release_ds_buffers(); mutex_unlock(&pmc_reserve_mutex); @@ -355,28 +357,30 @@ void x86_release_hardware(void) */ int x86_add_exclusive(unsigned int what) { - int ret = -EBUSY, i; - - if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) - return 0; + int i; - mutex_lock(&pmc_reserve_mutex); - for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { - if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) - goto out; + if (!atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) { + mutex_lock(&pmc_reserve_mutex); + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) { + if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) + goto fail_unlock; + } + atomic_inc(&x86_pmu.lbr_exclusive[what]); + mutex_unlock(&pmc_reserve_mutex); } - atomic_inc(&x86_pmu.lbr_exclusive[what]); - ret = 0; + atomic_inc(&active_events); + return 0; -out: +fail_unlock: mutex_unlock(&pmc_reserve_mutex); - return ret; + return -EBUSY; } void x86_del_exclusive(unsigned int what) { atomic_dec(&x86_pmu.lbr_exclusive[what]); + atomic_dec(&active_events); } int x86_setup_perfctr(struct perf_event *event) @@ -557,6 +561,7 @@ static int __x86_pmu_event_init(struct perf_event *event) if (err) return err; + atomic_inc(&active_events); event->destroy = hw_perf_event_destroy; event->hw.idx = -1; @@ -895,10 +900,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if (x86_pmu.commit_scheduling) x86_pmu.commit_scheduling(cpuc, i, assign[i]); } - } - - if (!assign || unsched) { - + } else { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -1111,13 +1113,16 @@ int x86_perf_event_set_period(struct perf_event *event) per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; - /* - * The hw event starts counting from this event offset, - * mark it to be able to extra future deltas: - */ - local64_set(&hwc->prev_count, (u64)-left); + if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) || + local64_read(&hwc->prev_count) != (u64)-left) { + /* + * The hw event starts counting from this event offset, + * mark it to be able to extra future deltas: + */ + local64_set(&hwc->prev_count, (u64)-left); - wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask); + } /* * Due to erratum on certan cpu we need @@ -1170,7 +1175,7 @@ static int x86_pmu_add(struct perf_event *event, int flags) * skip the schedulability test here, it will be performed * at commit time (->commit_txn) as a whole. */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) goto done_collect; ret = x86_pmu.schedule_events(cpuc, n, assign); @@ -1321,7 +1326,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) * XXX assumes any ->del() called during a TXN will only be on * an event added during that same TXN. */ - if (cpuc->group_flag & PERF_EVENT_TXN) + if (cpuc->txn_flags & PERF_PMU_TXN_ADD) return; /* @@ -1429,6 +1434,10 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) u64 finish_clock; int ret; + /* + * All PMUs/events that share this PMI handler should make sure to + * increment active_events for their events. + */ if (!atomic_read(&active_events)) return NMI_DONE; @@ -1542,7 +1551,7 @@ static void __init filter_events(struct attribute **attrs) } /* Merge two pointer arrays */ -static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b) +__init struct attribute **merge_attr(struct attribute **a, struct attribute **b) { struct attribute **new; int j, i; @@ -1739,11 +1748,22 @@ static inline void x86_pmu_read(struct perf_event *event) * Start group events scheduling transaction * Set the flag to make pmu::enable() not perform the * schedulability test, it will be performed at commit time + * + * We only support PERF_PMU_TXN_ADD transactions. Save the + * transaction flags but otherwise ignore non-PERF_PMU_TXN_ADD + * transactions. */ -static void x86_pmu_start_txn(struct pmu *pmu) +static void x86_pmu_start_txn(struct pmu *pmu, unsigned int txn_flags) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(cpuc->txn_flags); /* txn already in flight */ + + cpuc->txn_flags = txn_flags; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + perf_pmu_disable(pmu); - __this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN); __this_cpu_write(cpu_hw_events.n_txn, 0); } @@ -1754,7 +1774,16 @@ static void x86_pmu_start_txn(struct pmu *pmu) */ static void x86_pmu_cancel_txn(struct pmu *pmu) { - __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN); + unsigned int txn_flags; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + txn_flags = cpuc->txn_flags; + cpuc->txn_flags = 0; + if (txn_flags & ~PERF_PMU_TXN_ADD) + return; + /* * Truncate collected array by the number of events added in this * transaction. See x86_pmu_add() and x86_pmu_*_txn(). @@ -1777,6 +1806,13 @@ static int x86_pmu_commit_txn(struct pmu *pmu) int assign[X86_PMC_IDX_MAX]; int n, ret; + WARN_ON_ONCE(!cpuc->txn_flags); /* no txn in flight */ + + if (cpuc->txn_flags & ~PERF_PMU_TXN_ADD) { + cpuc->txn_flags = 0; + return 0; + } + n = cpuc->n_events; if (!x86_pmu_initialized()) @@ -1792,7 +1828,7 @@ static int x86_pmu_commit_txn(struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); - cpuc->group_flag &= ~PERF_EVENT_TXN; + cpuc->txn_flags = 0; perf_pmu_enable(pmu); return 0; } @@ -2170,6 +2206,7 @@ static unsigned long get_segment_base(unsigned int segment) int idx = segment >> 3; if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; if (idx > LDT_ENTRIES) @@ -2181,6 +2218,9 @@ static unsigned long get_segment_base(unsigned int segment) return 0; desc = &ldt->entries[idx]; +#else + return 0; +#endif } else { if (idx > GDT_ENTRIES) return 0; @@ -2191,7 +2231,7 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_IA32_EMULATION #include <asm/compat.h> diff --git a/kernel/arch/x86/kernel/cpu/perf_event.h b/kernel/arch/x86/kernel/cpu/perf_event.h index f068695ea..d0e35ebb2 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event.h +++ b/kernel/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com> * Copyright (C) 2009 Google, Inc., Stephane Eranian * @@ -47,6 +47,7 @@ enum extra_reg_type { EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ EXTRA_REG_LBR = 2, /* lbr_select */ EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ + EXTRA_REG_FE = 4, /* fe_* */ EXTRA_REG_MAX /* number of entries needed */ }; @@ -75,6 +76,8 @@ struct event_constraint { #define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ #define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ #define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_FREERUNNING 0x0800 /* use freerunning PEBS */ struct amd_nb { @@ -88,6 +91,18 @@ struct amd_nb { #define MAX_PEBS_EVENTS 8 /* + * Flags PEBS can handle without an PMI. + * + * TID can only be handled by flushing at context switch. + * + */ +#define PEBS_FREERUNNING_FLAGS \ + (PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \ + PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \ + PERF_SAMPLE_TRANSACTION) + +/* * A debug store configuration. * * We only support architectures that use 64bit fields. @@ -133,7 +148,6 @@ enum intel_excl_state_type { }; struct intel_excl_states { - enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; enum intel_excl_state_type state[X86_PMC_IDX_MAX]; bool sched_started; /* true if scheduling has started */ }; @@ -152,7 +166,7 @@ struct intel_excl_cntrs { unsigned core_id; /* per-core: core id */ }; -#define MAX_LBR_ENTRIES 16 +#define MAX_LBR_ENTRIES 32 enum { X86_PERF_KFREE_SHARED = 0, @@ -182,7 +196,7 @@ struct cpu_hw_events { int n_excl; /* the number of exclusive events */ - unsigned int group_flag; + unsigned int txn_flags; int is_fake; /* @@ -373,7 +387,7 @@ struct cpu_hw_events { /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ - INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW) @@ -527,10 +541,10 @@ struct x86_pmu { void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); - void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); - void (*start_scheduling)(struct cpu_hw_events *cpuc); + void (*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr); + void (*stop_scheduling)(struct cpu_hw_events *cpuc); struct event_constraint *event_constraints; @@ -581,6 +595,7 @@ struct x86_pmu { struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); int max_pebs_events; + unsigned long free_running_flags; /* * Intel LBR @@ -611,6 +626,8 @@ struct x86_pmu { struct x86_perf_task_context { u64 lbr_from[MAX_LBR_ENTRIES]; u64 lbr_to[MAX_LBR_ENTRIES]; + u64 lbr_info[MAX_LBR_ENTRIES]; + int tos; int lbr_callstack_users; int lbr_stack_state; }; @@ -780,6 +797,8 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip) ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event); ssize_t intel_event_sysfs_show(char *page, u64 config); +struct attribute **merge_attr(struct attribute **a, struct attribute **b); + #ifdef CONFIG_CPU_SUP_AMD int amd_pmu_init(void); @@ -795,20 +814,6 @@ static inline int amd_pmu_init(void) #ifdef CONFIG_CPU_SUP_INTEL -static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) -{ - /* user explicitly requested branch sampling */ - if (has_branch_stack(event)) - return true; - - /* implicit branch sampling to correct PEBS skid */ - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && - x86_pmu.intel_cap.pebs_format < 2) - return true; - - return false; -} - static inline bool intel_pmu_has_bts(struct perf_event *event) { if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && @@ -860,6 +865,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[]; extern struct event_constraint intel_hsw_pebs_event_constraints[]; +extern struct event_constraint intel_skl_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_enable(struct perf_event *event); @@ -870,6 +877,8 @@ void intel_pmu_pebs_enable_all(void); void intel_pmu_pebs_disable_all(void); +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); @@ -896,6 +905,8 @@ void intel_pmu_lbr_init_snb(void); void intel_pmu_lbr_init_hsw(void); +void intel_pmu_lbr_init_skl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); @@ -919,6 +930,7 @@ static inline int is_ht_workaround_enabled(void) { return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED); } + #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel.c b/kernel/arch/x86/kernel/cpu/perf_event_intel.c index 2813ea0f1..e2a430021 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel.c @@ -12,7 +12,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/export.h> -#include <linux/watchdog.h> +#include <linux/nmi.h> #include <asm/cpufeature.h> #include <asm/hardirq.h> @@ -177,6 +177,14 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +struct event_constraint intel_skl_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + EVENT_CONSTRAINT_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), @@ -193,6 +201,18 @@ static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; +static struct extra_reg intel_skl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + /* + * Note the low 8 bits eventsel code is not a continuous field, containing + * some #GPing bits. These are masked out. + */ + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + EVENT_EXTRA_END +}; + EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); @@ -212,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ - INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ @@ -235,7 +255,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ + INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -244,6 +264,200 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } +/* + * Notes on the events: + * - data reads do not include code reads (comparable to earlier tables) + * - data counts include speculative execution (except L1 write, dtlb, bpu) + * - remote node access includes remote memory, remote cache, remote mmio. + * - prefetches are not included in the counts. + * - icache miss does not include decoded icache + */ + +#define SKL_DEMAND_DATA_RD BIT_ULL(0) +#define SKL_DEMAND_RFO BIT_ULL(1) +#define SKL_ANY_RESPONSE BIT_ULL(16) +#define SKL_SUPPLIER_NONE BIT_ULL(17) +#define SKL_L3_MISS_LOCAL_DRAM BIT_ULL(26) +#define SKL_L3_MISS_REMOTE_HOP0_DRAM BIT_ULL(27) +#define SKL_L3_MISS_REMOTE_HOP1_DRAM BIT_ULL(28) +#define SKL_L3_MISS_REMOTE_HOP2P_DRAM BIT_ULL(29) +#define SKL_L3_MISS (SKL_L3_MISS_LOCAL_DRAM| \ + SKL_L3_MISS_REMOTE_HOP0_DRAM| \ + SKL_L3_MISS_REMOTE_HOP1_DRAM| \ + SKL_L3_MISS_REMOTE_HOP2P_DRAM) +#define SKL_SPL_HIT BIT_ULL(30) +#define SKL_SNOOP_NONE BIT_ULL(31) +#define SKL_SNOOP_NOT_NEEDED BIT_ULL(32) +#define SKL_SNOOP_MISS BIT_ULL(33) +#define SKL_SNOOP_HIT_NO_FWD BIT_ULL(34) +#define SKL_SNOOP_HIT_WITH_FWD BIT_ULL(35) +#define SKL_SNOOP_HITM BIT_ULL(36) +#define SKL_SNOOP_NON_DRAM BIT_ULL(37) +#define SKL_ANY_SNOOP (SKL_SPL_HIT|SKL_SNOOP_NONE| \ + SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \ + SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \ + SKL_SNOOP_HITM|SKL_SNOOP_NON_DRAM) +#define SKL_DEMAND_READ SKL_DEMAND_DATA_RD +#define SKL_SNOOP_DRAM (SKL_SNOOP_NONE| \ + SKL_SNOOP_NOT_NEEDED|SKL_SNOOP_MISS| \ + SKL_SNOOP_HIT_NO_FWD|SKL_SNOOP_HIT_WITH_FWD| \ + SKL_SNOOP_HITM|SKL_SPL_HIT) +#define SKL_DEMAND_WRITE SKL_DEMAND_RFO +#define SKL_LLC_ACCESS SKL_ANY_RESPONSE +#define SKL_L3_MISS_REMOTE (SKL_L3_MISS_REMOTE_HOP0_DRAM| \ + SKL_L3_MISS_REMOTE_HOP1_DRAM| \ + SKL_L3_MISS_REMOTE_HOP2P_DRAM) + +static __initconst const u64 skl_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x283, /* ICACHE_64B.MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x608, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x649, /* DTLB_STORE_MISSES.WALK_COMPLETED */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x2085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0xe85, /* ITLB_MISSES.WALK_COMPLETED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + +static __initconst const u64 skl_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_READ| + SKL_LLC_ACCESS|SKL_ANY_SNOOP, + [ C(RESULT_MISS) ] = SKL_DEMAND_READ| + SKL_L3_MISS|SKL_ANY_SNOOP| + SKL_SUPPLIER_NONE, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE| + SKL_LLC_ACCESS|SKL_ANY_SNOOP, + [ C(RESULT_MISS) ] = SKL_DEMAND_WRITE| + SKL_L3_MISS|SKL_ANY_SNOOP| + SKL_SUPPLIER_NONE, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_READ| + SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM, + [ C(RESULT_MISS) ] = SKL_DEMAND_READ| + SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SKL_DEMAND_WRITE| + SKL_L3_MISS_LOCAL_DRAM|SKL_SNOOP_DRAM, + [ C(RESULT_MISS) ] = SKL_DEMAND_WRITE| + SKL_L3_MISS_REMOTE|SKL_SNOOP_DRAM, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + #define SNB_DMND_DATA_RD (1ULL << 0) #define SNB_DMND_RFO (1ULL << 1) #define SNB_DMND_IFETCH (1ULL << 2) @@ -1114,7 +1328,7 @@ static struct extra_reg intel_slm_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0), - INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x368005ffffull, RSP_1), EVENT_EXTRA_END }; @@ -1594,6 +1808,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) loops = 0; again: + intel_pmu_lbr_read(); intel_pmu_ack_status(status); if (++loops > 100) { static bool warned = false; @@ -1608,16 +1823,16 @@ again: inc_irq_stat(apic_perf_irqs); - intel_pmu_lbr_read(); /* - * CondChgd bit 63 doesn't mean any overflow status. Ignore - * and clear the bit. + * Ignore a range of extra bits in status that do not indicate + * overflow by themselves. */ - if (__test_and_clear_bit(63, (unsigned long *)&status)) { - if (!status) - goto done; - } + status &= ~(GLOBAL_STATUS_COND_CHG | + GLOBAL_STATUS_ASIF | + GLOBAL_STATUS_LBRS_FROZEN); + if (!status) + goto done; /* * PEBS overflow sets bit 62 in the global status register @@ -1699,18 +1914,22 @@ intel_bts_constraints(struct perf_event *event) return NULL; } -static int intel_alt_er(int idx) +static int intel_alt_er(int idx, u64 config) { + int alt_idx; if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; if (idx == EXTRA_REG_RSP_0) - return EXTRA_REG_RSP_1; + alt_idx = EXTRA_REG_RSP_1; if (idx == EXTRA_REG_RSP_1) - return EXTRA_REG_RSP_0; + alt_idx = EXTRA_REG_RSP_0; + + if (config & ~x86_pmu.extra_regs[alt_idx].valid_mask) + return idx; - return idx; + return alt_idx; } static void intel_fixup_er(struct perf_event *event, int idx) @@ -1799,7 +2018,7 @@ again: */ c = NULL; } else { - idx = intel_alt_er(idx); + idx = intel_alt_er(idx, reg->config); if (idx != reg->idx) { raw_spin_unlock_irqrestore(&era->lock, flags); goto again; @@ -1903,9 +2122,8 @@ static void intel_start_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1916,10 +2134,9 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; xl->sched_started = true; @@ -1928,22 +2145,41 @@ intel_start_scheduling(struct cpu_hw_events *cpuc) * in stop_event_scheduling() * makes scheduling appear as a transaction */ - WARN_ON_ONCE(!irqs_disabled()); raw_spin_lock(&excl_cntrs->lock); +} - /* - * save initial state of sibling thread - */ - memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = cpuc->event_constraint[idx]; + struct intel_excl_states *xl; + int tid = cpuc->excl_thread_id; + + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + if (WARN_ON_ONCE(!excl_cntrs)) + return; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + xl = &excl_cntrs->states[tid]; + + lockdep_assert_held(&excl_cntrs->lock); + + if (c->flags & PERF_X86_EVENT_EXCL) + xl->state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xl->state[cntr] = INTEL_EXCL_SHARED; } static void intel_stop_scheduling(struct cpu_hw_events *cpuc) { struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; + struct intel_excl_states *xl; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* sibling thread */ /* * nothing needed if in group validation mode @@ -1953,17 +2189,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc) /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xlo = &excl_cntrs->states[o_tid]; xl = &excl_cntrs->states[tid]; - /* - * make new sibling thread state visible - */ - memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); - xl->sched_started = false; /* * release shared state lock (acquired in intel_start_scheduling()) @@ -1975,12 +2205,10 @@ static struct event_constraint * intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, int idx, struct event_constraint *c) { - struct event_constraint *cx; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xl, *xlo; - int is_excl, i; + struct intel_excl_states *xlo; int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; /* alternate */ + int is_excl, i; /* * validating a group does not require @@ -1992,27 +2220,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, /* * no exclusion needed */ - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return c; - /* - * event requires exclusive counter access - * across HT threads - */ - is_excl = c->flags & PERF_X86_EVENT_EXCL; - if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { - event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; - if (!cpuc->n_excl++) - WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); - } - - /* - * xl = state of current HT - * xlo = state of sibling HT - */ - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - cx = c; /* * because we modify the constraint, we need @@ -2023,10 +2232,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * been cloned (marked dynamic) */ if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { - - /* sanity check */ - if (idx < 0) - return &emptyconstraint; + struct event_constraint *cx; /* * grab pre-allocated constraint entry @@ -2037,13 +2243,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * initialize dynamic constraint * with static constraint */ - memcpy(cx, c, sizeof(*cx)); + *cx = *c; /* * mark constraint as dynamic, so we * can free it later on */ cx->flags |= PERF_X86_EVENT_DYNAMIC; + c = cx; } /* @@ -2054,6 +2261,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, */ /* + * state of sibling HT + */ + xlo = &excl_cntrs->states[tid ^ 1]; + + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) { + event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT; + if (!cpuc->n_excl++) + WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1); + } + + /* * Modify static constraint with current dynamic * state of thread * @@ -2061,46 +2284,49 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, * SHARED : sibling counter measuring non-exclusive event * UNUSED : sibling counter unused */ - for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) { /* * exclusive event in sibling counter * our corresponding counter cannot be used * regardless of our event */ - if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) - __clear_bit(i, cx->idxmsk); + if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, c->idxmsk); /* * if measuring an exclusive event, sibling * measuring non-exclusive, then counter cannot * be used */ - if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) - __clear_bit(i, cx->idxmsk); + if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, c->idxmsk); } /* * recompute actual bit weight for scheduling algorithm */ - cx->weight = hweight64(cx->idxmsk64); + c->weight = hweight64(c->idxmsk64); /* * if we return an empty mask, then switch * back to static empty constraint to avoid * the cost of freeing later on */ - if (cx->weight == 0) - cx = &emptyconstraint; + if (c->weight == 0) + c = &emptyconstraint; - return cx; + return c; } static struct event_constraint * intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { - struct event_constraint *c1 = cpuc->event_constraint[idx]; + struct event_constraint *c1 = NULL; struct event_constraint *c2; + if (idx >= 0) /* fake does < 0 */ + c1 = cpuc->event_constraint[idx]; + /* * first time only * - static constraint: no change across incremental scheduling calls @@ -2124,10 +2350,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, { struct hw_perf_event *hwc = &event->hw; struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct intel_excl_states *xlo, *xl; - unsigned long flags = 0; /* keep compiler happy */ int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; + struct intel_excl_states *xl; /* * nothing needed if in group validation mode @@ -2135,13 +2359,9 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, if (cpuc->is_fake) return; - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) + if (WARN_ON_ONCE(!excl_cntrs)) return; - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) { hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT; if (!--cpuc->n_excl) @@ -2149,22 +2369,25 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, } /* - * put_constraint may be called from x86_schedule_events() - * which already has the lock held so here make locking - * conditional + * If event was actually assigned, then mark the counter state as + * unused now. */ - if (!xl->sched_started) - raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + if (hwc->idx >= 0) { + xl = &excl_cntrs->states[tid]; - /* - * if event was actually assigned, then mark the - * counter state as unused now - */ - if (hwc->idx >= 0) - xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional. + */ + if (!xl->sched_started) + raw_spin_lock(&excl_cntrs->lock); + + xl->state[hwc->idx] = INTEL_EXCL_UNUSED; - if (!xl->sched_started) - raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); + if (!xl->sched_started) + raw_spin_unlock(&excl_cntrs->lock); + } } static void @@ -2196,41 +2419,6 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc, intel_put_excl_constraints(cpuc, event); } -static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr) -{ - struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; - struct event_constraint *c = cpuc->event_constraint[idx]; - struct intel_excl_states *xlo, *xl; - int tid = cpuc->excl_thread_id; - int o_tid = 1 - tid; - int is_excl; - - if (cpuc->is_fake || !c) - return; - - is_excl = c->flags & PERF_X86_EVENT_EXCL; - - if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) - return; - - WARN_ON_ONCE(!excl_cntrs); - - if (!excl_cntrs) - return; - - xl = &excl_cntrs->states[tid]; - xlo = &excl_cntrs->states[o_tid]; - - WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); - - if (cntr >= 0) { - if (is_excl) - xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; - else - xlo->init_state[cntr] = INTEL_EXCL_SHARED; - } -} - static void intel_pebs_aliases_core2(struct perf_event *event) { if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { @@ -2287,6 +2475,15 @@ static void intel_pebs_aliases_snb(struct perf_event *event) } } +static unsigned long intel_pmu_free_running_flags(struct perf_event *event) +{ + unsigned long flags = x86_pmu.free_running_flags; + + if (event->attr.use_clockid) + flags &= ~PERF_SAMPLE_TIME; + return flags; +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -2294,8 +2491,16 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; - if (event->attr.precise_ip && x86_pmu.pebs_aliases) - x86_pmu.pebs_aliases(event); + if (event->attr.precise_ip) { + if (!event->attr.freq) { + event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; + if (!(event->attr.sample_type & + ~intel_pmu_free_running_flags(event))) + event->hw.flags |= PERF_X86_EVENT_FREERUNNING; + } + if (x86_pmu.pebs_aliases) + x86_pmu.pebs_aliases(event); + } if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); @@ -2544,19 +2749,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) { struct intel_excl_cntrs *c; - int i; c = kzalloc_node(sizeof(struct intel_excl_cntrs), GFP_KERNEL, cpu_to_node(cpu)); if (c) { raw_spin_lock_init(&c->lock); - for (i = 0; i < X86_PMC_IDX_MAX; i++) { - c->states[0].state[i] = INTEL_EXCL_UNUSED; - c->states[0].init_state[i] = INTEL_EXCL_UNUSED; - - c->states[1].state[i] = INTEL_EXCL_UNUSED; - c->states[1].init_state[i] = INTEL_EXCL_UNUSED; - } c->core_id = -1; } return c; @@ -2569,7 +2766,7 @@ static int intel_pmu_cpu_prepare(int cpu) if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { cpuc->shared_regs = allocate_shared_regs(cpu); if (!cpuc->shared_regs) - return NOTIFY_BAD; + goto err; } if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { @@ -2577,18 +2774,27 @@ static int intel_pmu_cpu_prepare(int cpu) cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); if (!cpuc->constraint_list) - return NOTIFY_BAD; + goto err_shared_regs; cpuc->excl_cntrs = allocate_excl_cntrs(cpu); - if (!cpuc->excl_cntrs) { - kfree(cpuc->constraint_list); - kfree(cpuc->shared_regs); - return NOTIFY_BAD; - } + if (!cpuc->excl_cntrs) + goto err_constraint_list; + cpuc->excl_thread_id = 0; } return NOTIFY_OK; + +err_constraint_list: + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + +err_shared_regs: + kfree(cpuc->shared_regs); + cpuc->shared_regs = NULL; + +err: + return NOTIFY_BAD; } static void intel_pmu_cpu_starting(int cpu) @@ -2611,7 +2817,7 @@ static void intel_pmu_cpu_starting(int cpu) if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; @@ -2629,7 +2835,7 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { - for_each_cpu(i, topology_thread_cpumask(cpu)) { + for_each_cpu(i, topology_sibling_cpumask(cpu)) { struct intel_excl_cntrs *c; c = per_cpu(cpu_hw_events, i).excl_cntrs; @@ -2677,10 +2883,21 @@ static void intel_pmu_cpu_dying(int cpu) fini_debug_store_on_cpu(cpu); } +static void intel_pmu_sched_task(struct perf_event_context *ctx, + bool sched_in) +{ + if (x86_pmu.pebs_active) + intel_pmu_pebs_sched_task(ctx, sched_in); + if (x86_pmu.lbr_nr) + intel_pmu_lbr_sched_task(ctx, sched_in); +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); +PMU_FORMAT_ATTR(frontend, "config1:0-23"); + static struct attribute *intel_arch3_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -2697,6 +2914,11 @@ static struct attribute *intel_arch3_formats_attr[] = { NULL, }; +static struct attribute *skl_format_attr[] = { + &format_attr_frontend.attr, + NULL, +}; + static __initconst const struct x86_pmu core_pmu = { .name = "core", .handle_irq = x86_pmu_handle_irq, @@ -2711,6 +2933,8 @@ static __initconst const struct x86_pmu core_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, + .free_running_flags = PEBS_FREERUNNING_FLAGS, + /* * Intel PMCs cannot be accessed sanely above 32-bit width, * so we install an artificial 1<<31 period regardless of @@ -2749,6 +2973,7 @@ static __initconst const struct x86_pmu intel_pmu = { .event_map = intel_pmu_event_map, .max_events = ARRAY_SIZE(intel_perfmon_event_map), .apic = 1, + .free_running_flags = PEBS_FREERUNNING_FLAGS, /* * Intel PMCs cannot be accessed sanely above 32 bit width, * so we install an artificial 1<<31 period regardless of @@ -2766,7 +2991,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .sched_task = intel_pmu_lbr_sched_task, + .sched_task = intel_pmu_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2939,8 +3164,8 @@ static __init void intel_ht_bug(void) { x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; - x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.commit_scheduling = intel_commit_scheduling; x86_pmu.stop_scheduling = intel_stop_scheduling; } @@ -3286,6 +3511,30 @@ __init int intel_pmu_init(void) pr_cont("Broadwell events, "); break; + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_skl(); + + x86_pmu.event_constraints = intel_skl_event_constraints; + x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints; + x86_pmu.extra_regs = intel_skl_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr, + skl_format_attr); + WARN_ON(!x86_pmu.format_attrs); + x86_pmu.cpu_events = hsw_events_attrs; + pr_cont("Skylake events, "); + break; + default: switch (x86_pmu.version) { case 1: @@ -3355,7 +3604,7 @@ __init int intel_pmu_init(void) */ if (x86_pmu.extra_regs) { for (er = x86_pmu.extra_regs; er->msr; er++) { - er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + er->extra_msr_access = check_msr(er->msr, 0x11UL); /* Disable LBR select mapping */ if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) x86_pmu.lbr_sel_map = NULL; @@ -3388,21 +3637,24 @@ static __init int fixup_ht_bug(void) if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) return 0; - w = cpumask_weight(topology_thread_cpumask(cpu)); + w = cpumask_weight(topology_sibling_cpumask(cpu)); if (w > 1) { pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); return 0; } - watchdog_nmi_disable_all(); + if (lockup_detector_suspend() != 0) { + pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n"); + return 0; + } x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); - x86_pmu.commit_scheduling = NULL; x86_pmu.start_scheduling = NULL; + x86_pmu.commit_scheduling = NULL; x86_pmu.stop_scheduling = NULL; - watchdog_nmi_enable_all(); + lockup_detector_resume(); get_online_cpus(); diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_bts.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_bts.c index 7795f3f8b..2cad71d1b 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_bts.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -62,9 +62,6 @@ struct bts_buffer { struct pmu bts_pmu; -void intel_pmu_enable_bts(u64 config); -void intel_pmu_disable_bts(void); - static size_t buf_size(struct page *page) { return 1 << (PAGE_SHIFT + page_private(page)); @@ -225,6 +222,7 @@ static void __bts_event_start(struct perf_event *event) if (!buf || bts_buffer_is_full(buf, bts)) return; + event->hw.itrace_started = 1; event->hw.state = 0; if (!buf->snapshot) @@ -497,6 +495,19 @@ static int bts_event_init(struct perf_event *event) if (x86_add_exclusive(x86_lbr_exclusive_bts)) return -EBUSY; + /* + * BTS leaks kernel addresses even when CPL0 tracing is + * disabled, so disallow intel_bts driver for unprivileged + * users on paranoid systems since it provides trace data + * to the user in a zero-copy fashion. + * + * Note that the default paranoia setting permits unprivileged + * users to profile the kernel. + */ + if (event->attr.exclude_kernel && perf_paranoid_kernel() && + !capable(CAP_SYS_ADMIN)) + return -EACCES; + ret = x86_reserve_hardware(); if (ret) { x86_del_exclusive(x86_lbr_exclusive_bts); @@ -530,5 +541,4 @@ static __init int bts_init(void) return perf_pmu_register(&bts_pmu, "intel_bts", -1); } - -module_init(bts_init); +arch_initcall(bts_init); diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c index cb77b11bc..a316ca96f 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -13,16 +13,35 @@ #define MSR_IA32_QM_CTR 0x0c8e #define MSR_IA32_QM_EVTSEL 0x0c8d -static unsigned int cqm_max_rmid = -1; +static u32 cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -struct intel_cqm_state { - raw_spinlock_t lock; - int rmid; - int cnt; +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @rmid_usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { + u32 rmid; + u32 closid; + int rmid_usecnt; }; -static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); +/* + * The cached intel_pqr_state is strictly per CPU and can never be + * updated from a remote CPU. Both functions which modify the state + * (intel_cqm_event_start and intel_cqm_event_stop) are called with + * interrupts disabled, which is sufficient for the protection. + */ +static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. @@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask; * near-zero occupancy value, i.e. no cachelines are tagged with this * RMID, once __intel_cqm_rmid_rotate() returns. */ -static unsigned int intel_cqm_rotation_rmid; +static u32 intel_cqm_rotation_rmid; #define INVALID_RMID (-1) @@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid; * Likewise, an rmid value of -1 is used to indicate "no rmid currently * assigned" and is used as part of the rotation code. */ -static inline bool __rmid_valid(unsigned int rmid) +static inline bool __rmid_valid(u32 rmid) { if (!rmid || rmid == INVALID_RMID) return false; @@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid) return true; } -static u64 __rmid_read(unsigned int rmid) +static u64 __rmid_read(u32 rmid) { u64 val; @@ -102,7 +121,7 @@ enum rmid_recycle_state { }; struct cqm_rmid_entry { - unsigned int rmid; + u32 rmid; enum rmid_recycle_state state; struct list_head list; unsigned long queue_time; @@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru); */ static struct cqm_rmid_entry **cqm_rmid_ptrs; -static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid) { struct cqm_rmid_entry *entry; @@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid) * * We expect to be called with cache_mutex held. */ -static int __get_rmid(void) +static u32 __get_rmid(void) { struct cqm_rmid_entry *entry; @@ -177,7 +196,7 @@ static int __get_rmid(void) return entry->rmid; } -static void __put_rmid(unsigned int rmid) +static void __put_rmid(u32 rmid) { struct cqm_rmid_entry *entry; @@ -279,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } @@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b) } struct rmid_read { - unsigned int rmid; + u32 rmid; atomic64_t value; }; @@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info); /* * Exchange the RMID of a group of events. */ -static unsigned int -intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid) { struct perf_event *event; - unsigned int old_rmid = group->hw.cqm_rmid; struct list_head *head = &group->hw.cqm_group_entry; + u32 old_rmid = group->hw.cqm_rmid; lockdep_assert_held(&cache_mutex); @@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg) * If we have group events waiting for an RMID that don't conflict with * events already running, assign @rmid. */ -static bool intel_cqm_sched_in_event(unsigned int rmid) +static bool intel_cqm_sched_in_event(u32 rmid) { struct perf_event *leader, *event; @@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available) static void __intel_cqm_pick_and_rotate(struct perf_event *next) { struct perf_event *rotor; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next) static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) { struct perf_event *group, *g; - unsigned int rmid; + u32 rmid; lockdep_assert_held(&cache_mutex); @@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event, struct perf_event **group) { struct perf_event *iter; - unsigned int rmid; bool conflict = false; + u32 rmid; list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { rmid = iter->hw.cqm_rmid; @@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event, static void intel_cqm_event_read(struct perf_event *event) { unsigned long flags; - unsigned int rmid; + u32 rmid; u64 val; /* @@ -969,55 +987,48 @@ out: static void intel_cqm_event_start(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned int rmid = event->hw.cqm_rmid; - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 rmid = event->hw.cqm_rmid; if (!(event->hw.cqm_state & PERF_HES_STOPPED)) return; event->hw.cqm_state &= ~PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); - - if (state->cnt++) - WARN_ON_ONCE(state->rmid != rmid); - else + if (state->rmid_usecnt++) { + if (!WARN_ON_ONCE(state->rmid != rmid)) + return; + } else { WARN_ON_ONCE(state->rmid); + } state->rmid = rmid; - wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); - - raw_spin_unlock_irqrestore(&state->lock, flags); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); } static void intel_cqm_event_stop(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); - unsigned long flags; + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); if (event->hw.cqm_state & PERF_HES_STOPPED) return; event->hw.cqm_state |= PERF_HES_STOPPED; - raw_spin_lock_irqsave(&state->lock, flags); intel_cqm_event_read(event); - if (!--state->cnt) { + if (!--state->rmid_usecnt) { state->rmid = 0; - wrmsrl(MSR_IA32_PQR_ASSOC, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); } else { WARN_ON_ONCE(!state->rmid); } - - raw_spin_unlock_irqrestore(&state->lock, flags); } static int intel_cqm_event_add(struct perf_event *event, int mode) { unsigned long flags; - unsigned int rmid; + u32 rmid; raw_spin_lock_irqsave(&cache_lock, flags); @@ -1032,11 +1043,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode) return 0; } -static void intel_cqm_event_del(struct perf_event *event, int mode) -{ - intel_cqm_event_stop(event, mode); -} - static void intel_cqm_event_destroy(struct perf_event *event) { struct perf_event *group_other = NULL; @@ -1065,7 +1071,7 @@ static void intel_cqm_event_destroy(struct perf_event *event) list_replace(&event->hw.cqm_groups_entry, &group_other->hw.cqm_groups_entry); } else { - unsigned int rmid = event->hw.cqm_rmid; + u32 rmid = event->hw.cqm_rmid; if (__rmid_valid(rmid)) __put_rmid(rmid); @@ -1229,7 +1235,7 @@ static struct pmu intel_cqm_pmu = { .task_ctx_nr = perf_sw_context, .event_init = intel_cqm_event_init, .add = intel_cqm_event_add, - .del = intel_cqm_event_del, + .del = intel_cqm_event_stop, .start = intel_cqm_event_start, .stop = intel_cqm_event_stop, .read = intel_cqm_event_read, @@ -1249,14 +1255,14 @@ static inline void cqm_pick_event_reader(int cpu) cpumask_set_cpu(cpu, &cqm_cpumask); } -static void intel_cqm_cpu_prepare(unsigned int cpu) +static void intel_cqm_cpu_starting(unsigned int cpu) { - struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); - raw_spin_lock_init(&state->lock); state->rmid = 0; - state->cnt = 0; + state->closid = 0; + state->rmid_usecnt = 0; WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); @@ -1290,13 +1296,11 @@ static int intel_cqm_cpu_notifier(struct notifier_block *nb, unsigned int cpu = (unsigned long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { - case CPU_UP_PREPARE: - intel_cqm_cpu_prepare(cpu); - break; case CPU_DOWN_PREPARE: intel_cqm_cpu_exit(cpu); break; case CPU_STARTING: + intel_cqm_cpu_starting(cpu); cqm_pick_event_reader(cpu); break; } @@ -1367,7 +1371,7 @@ static int __init intel_cqm_init(void) goto out; for_each_online_cpu(i) { - intel_cqm_cpu_prepare(i); + intel_cqm_cpu_starting(i); cqm_pick_event_reader(i); } diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_cstate.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_cstate.c new file mode 100644 index 000000000..75a38b5a2 --- /dev/null +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_cstate.c @@ -0,0 +1,694 @@ +/* + * perf_event_intel_cstate.c: support cstate residency counters + * + * Copyright (C) 2015, Intel Corp. + * Author: Kan Liang (kan.liang@intel.com) + * + * This 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. + * + * This 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. + * + */ + +/* + * This file export cstate related free running (read-only) counters + * for perf. These counters may be use simultaneously by other tools, + * such as turbostat. However, it still make sense to implement them + * in perf. Because we can conveniently collect them together with + * other events, and allow to use them from tools without special MSR + * access code. + * + * The events only support system-wide mode counting. There is no + * sampling support because it is not supported by the hardware. + * + * According to counters' scope and category, two PMUs are registered + * with the perf_event core subsystem. + * - 'cstate_core': The counter is available for each physical core. + * The counters include CORE_C*_RESIDENCY. + * - 'cstate_pkg': The counter is available for each physical package. + * The counters include PKG_C*_RESIDENCY. + * + * All of these counters are specified in the Intel® 64 and IA-32 + * Architectures Software Developer.s Manual Vol3b. + * + * Model specific counters: + * MSR_CORE_C1_RES: CORE C1 Residency Counter + * perf code: 0x00 + * Available model: SLM,AMT + * Scope: Core (each processor core has a MSR) + * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter + * perf code: 0x01 + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Core + * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter + * perf code: 0x02 + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Core + * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter + * perf code: 0x03 + * Available model: SNB,IVB,HSW,BDW,SKL + * Scope: Core + * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. + * perf code: 0x00 + * Available model: SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. + * perf code: 0x01 + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. + * perf code: 0x02 + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. + * perf code: 0x03 + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Scope: Package (physical package) + * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. + * perf code: 0x04 + * Available model: HSW ULT only + * Scope: Package (physical package) + * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. + * perf code: 0x05 + * Available model: HSW ULT only + * Scope: Package (physical package) + * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. + * perf code: 0x06 + * Available model: HSW ULT only + * Scope: Package (physical package) + * + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/perf_event.h> +#include <asm/cpu_device_id.h> +#include "perf_event.h" + +#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format) \ +static ssize_t __cstate_##_var##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ +static struct kobj_attribute format_attr_##_var = \ + __ATTR(_name, 0444, __cstate_##_var##_show, NULL) + +static ssize_t cstate_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, + char *buf); + +struct perf_cstate_msr { + u64 msr; + struct perf_pmu_events_attr *attr; + bool (*test)(int idx); +}; + + +/* cstate_core PMU */ + +static struct pmu cstate_core_pmu; +static bool has_cstate_core; + +enum perf_cstate_core_id { + /* + * cstate_core events + */ + PERF_CSTATE_CORE_C1_RES = 0, + PERF_CSTATE_CORE_C3_RES, + PERF_CSTATE_CORE_C6_RES, + PERF_CSTATE_CORE_C7_RES, + + PERF_CSTATE_CORE_EVENT_MAX, +}; + +bool test_core(int idx) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return false; + + switch (boot_cpu_data.x86_model) { + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ + + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ + if (idx == PERF_CSTATE_CORE_C3_RES || + idx == PERF_CSTATE_CORE_C6_RES) + return true; + break; + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ + + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + if (idx == PERF_CSTATE_CORE_C3_RES || + idx == PERF_CSTATE_CORE_C6_RES || + idx == PERF_CSTATE_CORE_C7_RES) + return true; + break; + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ + case 76: /* 14nm Atom "Airmont" */ + if (idx == PERF_CSTATE_CORE_C1_RES || + idx == PERF_CSTATE_CORE_C6_RES) + return true; + break; + } + + return false; +} + +PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00"); +PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01"); +PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02"); +PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03"); + +static struct perf_cstate_msr core_msr[] = { + [PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES, &evattr_cstate_core_c1, test_core, }, + [PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY, &evattr_cstate_core_c3, test_core, }, + [PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY, &evattr_cstate_core_c6, test_core, }, + [PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY, &evattr_cstate_core_c7, test_core, }, +}; + +static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = { + NULL, +}; + +static struct attribute_group core_events_attr_group = { + .name = "events", + .attrs = core_events_attrs, +}; + +DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63"); +static struct attribute *core_format_attrs[] = { + &format_attr_core_event.attr, + NULL, +}; + +static struct attribute_group core_format_attr_group = { + .name = "format", + .attrs = core_format_attrs, +}; + +static cpumask_t cstate_core_cpu_mask; +static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL); + +static struct attribute *cstate_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cstate_cpumask_attrs, +}; + +static const struct attribute_group *core_attr_groups[] = { + &core_events_attr_group, + &core_format_attr_group, + &cpumask_attr_group, + NULL, +}; + +/* cstate_core PMU end */ + + +/* cstate_pkg PMU */ + +static struct pmu cstate_pkg_pmu; +static bool has_cstate_pkg; + +enum perf_cstate_pkg_id { + /* + * cstate_pkg events + */ + PERF_CSTATE_PKG_C2_RES = 0, + PERF_CSTATE_PKG_C3_RES, + PERF_CSTATE_PKG_C6_RES, + PERF_CSTATE_PKG_C7_RES, + PERF_CSTATE_PKG_C8_RES, + PERF_CSTATE_PKG_C9_RES, + PERF_CSTATE_PKG_C10_RES, + + PERF_CSTATE_PKG_EVENT_MAX, +}; + +bool test_pkg(int idx) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return false; + + switch (boot_cpu_data.x86_model) { + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ + + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ + if (idx == PERF_CSTATE_CORE_C3_RES || + idx == PERF_CSTATE_CORE_C6_RES || + idx == PERF_CSTATE_CORE_C7_RES) + return true; + break; + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ + + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + if (idx == PERF_CSTATE_PKG_C2_RES || + idx == PERF_CSTATE_PKG_C3_RES || + idx == PERF_CSTATE_PKG_C6_RES || + idx == PERF_CSTATE_PKG_C7_RES) + return true; + break; + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ + case 76: /* 14nm Atom "Airmont" */ + if (idx == PERF_CSTATE_CORE_C6_RES) + return true; + break; + case 69: /* 22nm Haswell ULT */ + if (idx == PERF_CSTATE_PKG_C2_RES || + idx == PERF_CSTATE_PKG_C3_RES || + idx == PERF_CSTATE_PKG_C6_RES || + idx == PERF_CSTATE_PKG_C7_RES || + idx == PERF_CSTATE_PKG_C8_RES || + idx == PERF_CSTATE_PKG_C9_RES || + idx == PERF_CSTATE_PKG_C10_RES) + return true; + break; + } + + return false; +} + +PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00"); +PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01"); +PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02"); +PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03"); +PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04"); +PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05"); +PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06"); + +static struct perf_cstate_msr pkg_msr[] = { + [PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY, &evattr_cstate_pkg_c2, test_pkg, }, + [PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY, &evattr_cstate_pkg_c3, test_pkg, }, + [PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY, &evattr_cstate_pkg_c6, test_pkg, }, + [PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY, &evattr_cstate_pkg_c7, test_pkg, }, + [PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY, &evattr_cstate_pkg_c8, test_pkg, }, + [PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY, &evattr_cstate_pkg_c9, test_pkg, }, + [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &evattr_cstate_pkg_c10, test_pkg, }, +}; + +static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = { + NULL, +}; + +static struct attribute_group pkg_events_attr_group = { + .name = "events", + .attrs = pkg_events_attrs, +}; + +DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63"); +static struct attribute *pkg_format_attrs[] = { + &format_attr_pkg_event.attr, + NULL, +}; +static struct attribute_group pkg_format_attr_group = { + .name = "format", + .attrs = pkg_format_attrs, +}; + +static cpumask_t cstate_pkg_cpu_mask; + +static const struct attribute_group *pkg_attr_groups[] = { + &pkg_events_attr_group, + &pkg_format_attr_group, + &cpumask_attr_group, + NULL, +}; + +/* cstate_pkg PMU end*/ + +static ssize_t cstate_get_attr_cpumask(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pmu *pmu = dev_get_drvdata(dev); + + if (pmu == &cstate_core_pmu) + return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask); + else if (pmu == &cstate_pkg_pmu) + return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask); + else + return 0; +} + +static int cstate_pmu_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config; + int ret = 0; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + if (event->pmu == &cstate_core_pmu) { + if (cfg >= PERF_CSTATE_CORE_EVENT_MAX) + return -EINVAL; + if (!core_msr[cfg].attr) + return -EINVAL; + event->hw.event_base = core_msr[cfg].msr; + } else if (event->pmu == &cstate_pkg_pmu) { + if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) + return -EINVAL; + if (!pkg_msr[cfg].attr) + return -EINVAL; + event->hw.event_base = pkg_msr[cfg].msr; + } else + return -ENOENT; + + /* must be done before validate_group */ + event->hw.config = cfg; + event->hw.idx = -1; + + return ret; +} + +static inline u64 cstate_pmu_read_counter(struct perf_event *event) +{ + u64 val; + + rdmsrl(event->hw.event_base, val); + return val; +} + +static void cstate_pmu_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev_raw_count, new_raw_count; + +again: + prev_raw_count = local64_read(&hwc->prev_count); + new_raw_count = cstate_pmu_read_counter(event); + + if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count) != prev_raw_count) + goto again; + + local64_add(new_raw_count - prev_raw_count, &event->count); +} + +static void cstate_pmu_event_start(struct perf_event *event, int mode) +{ + local64_set(&event->hw.prev_count, cstate_pmu_read_counter(event)); +} + +static void cstate_pmu_event_stop(struct perf_event *event, int mode) +{ + cstate_pmu_event_update(event); +} + +static void cstate_pmu_event_del(struct perf_event *event, int mode) +{ + cstate_pmu_event_stop(event, PERF_EF_UPDATE); +} + +static int cstate_pmu_event_add(struct perf_event *event, int mode) +{ + if (mode & PERF_EF_START) + cstate_pmu_event_start(event, mode); + + return 0; +} + +static void cstate_cpu_exit(int cpu) +{ + int i, id, target; + + /* cpu exit for cstate core */ + if (has_cstate_core) { + id = topology_core_id(cpu); + target = -1; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (id == topology_core_id(i)) { + target = i; + break; + } + } + if (cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &cstate_core_cpu_mask); + WARN_ON(cpumask_empty(&cstate_core_cpu_mask)); + if (target >= 0) + perf_pmu_migrate_context(&cstate_core_pmu, cpu, target); + } + + /* cpu exit for cstate pkg */ + if (has_cstate_pkg) { + id = topology_physical_package_id(cpu); + target = -1; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + if (id == topology_physical_package_id(i)) { + target = i; + break; + } + } + if (cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask) && target >= 0) + cpumask_set_cpu(target, &cstate_pkg_cpu_mask); + WARN_ON(cpumask_empty(&cstate_pkg_cpu_mask)); + if (target >= 0) + perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); + } +} + +static void cstate_cpu_init(int cpu) +{ + int i, id; + + /* cpu init for cstate core */ + if (has_cstate_core) { + id = topology_core_id(cpu); + for_each_cpu(i, &cstate_core_cpu_mask) { + if (id == topology_core_id(i)) + break; + } + if (i >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_core_cpu_mask); + } + + /* cpu init for cstate pkg */ + if (has_cstate_pkg) { + id = topology_physical_package_id(cpu); + for_each_cpu(i, &cstate_pkg_cpu_mask) { + if (id == topology_physical_package_id(i)) + break; + } + if (i >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); + } +} + +static int cstate_cpu_notifier(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + break; + case CPU_STARTING: + cstate_cpu_init(cpu); + break; + case CPU_UP_CANCELED: + case CPU_DYING: + break; + case CPU_ONLINE: + case CPU_DEAD: + break; + case CPU_DOWN_PREPARE: + cstate_cpu_exit(cpu); + break; + default: + break; + } + + return NOTIFY_OK; +} + +/* + * Probe the cstate events and insert the available one into sysfs attrs + * Return false if there is no available events. + */ +static bool cstate_probe_msr(struct perf_cstate_msr *msr, + struct attribute **events_attrs, + int max_event_nr) +{ + int i, j = 0; + u64 val; + + /* Probe the cstate events. */ + for (i = 0; i < max_event_nr; i++) { + if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) + msr[i].attr = NULL; + } + + /* List remaining events in the sysfs attrs. */ + for (i = 0; i < max_event_nr; i++) { + if (msr[i].attr) + events_attrs[j++] = &msr[i].attr->attr.attr; + } + events_attrs[j] = NULL; + + return (j > 0) ? true : false; +} + +static int __init cstate_init(void) +{ + /* SLM has different MSR for PKG C6 */ + switch (boot_cpu_data.x86_model) { + case 55: + case 76: + case 77: + pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + } + + if (cstate_probe_msr(core_msr, core_events_attrs, PERF_CSTATE_CORE_EVENT_MAX)) + has_cstate_core = true; + + if (cstate_probe_msr(pkg_msr, pkg_events_attrs, PERF_CSTATE_PKG_EVENT_MAX)) + has_cstate_pkg = true; + + return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; +} + +static void __init cstate_cpumask_init(void) +{ + int cpu; + + cpu_notifier_register_begin(); + + for_each_online_cpu(cpu) + cstate_cpu_init(cpu); + + __perf_cpu_notifier(cstate_cpu_notifier); + + cpu_notifier_register_done(); +} + +static struct pmu cstate_core_pmu = { + .attr_groups = core_attr_groups, + .name = "cstate_core", + .task_ctx_nr = perf_invalid_context, + .event_init = cstate_pmu_event_init, + .add = cstate_pmu_event_add, /* must have */ + .del = cstate_pmu_event_del, /* must have */ + .start = cstate_pmu_event_start, + .stop = cstate_pmu_event_stop, + .read = cstate_pmu_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, +}; + +static struct pmu cstate_pkg_pmu = { + .attr_groups = pkg_attr_groups, + .name = "cstate_pkg", + .task_ctx_nr = perf_invalid_context, + .event_init = cstate_pmu_event_init, + .add = cstate_pmu_event_add, /* must have */ + .del = cstate_pmu_event_del, /* must have */ + .start = cstate_pmu_event_start, + .stop = cstate_pmu_event_stop, + .read = cstate_pmu_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, +}; + +static void __init cstate_pmus_register(void) +{ + int err; + + if (has_cstate_core) { + err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1); + if (WARN_ON(err)) + pr_info("Failed to register PMU %s error %d\n", + cstate_core_pmu.name, err); + } + + if (has_cstate_pkg) { + err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1); + if (WARN_ON(err)) + pr_info("Failed to register PMU %s error %d\n", + cstate_pkg_pmu.name, err); + } +} + +static int __init cstate_pmu_init(void) +{ + int err; + + if (cpu_has_hypervisor) + return -ENODEV; + + err = cstate_init(); + if (err) + return err; + + cstate_cpumask_init(); + + cstate_pmus_register(); + + return 0; +} + +device_initcall(cstate_pmu_init); diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c index 7f73b3553..5db1c7755 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -11,7 +11,7 @@ #define BTS_RECORD_SIZE 24 #define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE PAGE_SIZE +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -224,6 +224,19 @@ union hsw_tsx_tuning { #define PEBS_HSW_TSX_FLAGS 0xff00000000ULL +/* Same as HSW, plus TSC */ + +struct pebs_record_skl { + u64 flags, ip; + u64 ax, bx, cx, dx; + u64 si, di, bp, sp; + u64 r8, r9, r10, r11; + u64 r12, r13, r14, r15; + u64 status, dla, dse, lat; + u64 real_ip, tsx_tuning; + u64 tsc; +}; + void init_debug_store_on_cpu(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; @@ -250,7 +263,7 @@ static int alloc_pebs_buffer(int cpu) { struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; int node = cpu_to_node(cpu); - int max, thresh = 1; /* always use a single PEBS record */ + int max; void *buffer, *ibuffer; if (!x86_pmu.pebs) @@ -280,9 +293,6 @@ static int alloc_pebs_buffer(int cpu) ds->pebs_absolute_maximum = ds->pebs_buffer_base + max * x86_pmu.pebs_record_size; - ds->pebs_interrupt_threshold = ds->pebs_buffer_base + - thresh * x86_pmu.pebs_record_size; - return 0; } @@ -500,10 +510,11 @@ int intel_pmu_drain_bts_buffer(void) u64 flags; }; struct perf_event *event = cpuc->events[INTEL_PMC_IDX_FIXED_BTS]; - struct bts_record *at, *top; + struct bts_record *at, *base, *top; struct perf_output_handle handle; struct perf_event_header header; struct perf_sample_data data; + unsigned long skip = 0; struct pt_regs regs; if (!event) @@ -512,10 +523,10 @@ int intel_pmu_drain_bts_buffer(void) if (!x86_pmu.bts_active) return 0; - at = (struct bts_record *)(unsigned long)ds->bts_buffer_base; - top = (struct bts_record *)(unsigned long)ds->bts_index; + base = (struct bts_record *)(unsigned long)ds->bts_buffer_base; + top = (struct bts_record *)(unsigned long)ds->bts_index; - if (top <= at) + if (top <= base) return 0; memset(®s, 0, sizeof(regs)); @@ -525,16 +536,43 @@ int intel_pmu_drain_bts_buffer(void) perf_sample_data_init(&data, 0, event->hw.last_period); /* + * BTS leaks kernel addresses in branches across the cpl boundary, + * such as traps or system calls, so unless the user is asking for + * kernel tracing (and right now it's not possible), we'd need to + * filter them out. But first we need to count how many of those we + * have in the current batch. This is an extra O(n) pass, however, + * it's much faster than the other one especially considering that + * n <= 2560 (BTS_BUFFER_SIZE / BTS_RECORD_SIZE * 15/16; see the + * alloc_bts_buffer()). + */ + for (at = base; at < top; at++) { + /* + * Note that right now *this* BTS code only works if + * attr::exclude_kernel is set, but let's keep this extra + * check here in case that changes. + */ + if (event->attr.exclude_kernel && + (kernel_ip(at->from) || kernel_ip(at->to))) + skip++; + } + + /* * Prepare a generic sample, i.e. fill in the invariant fields. * We will overwrite the from and to address before we output * the sample. */ perf_prepare_sample(&header, &data, event, ®s); - if (perf_output_begin(&handle, event, header.size * (top - at))) + if (perf_output_begin(&handle, event, header.size * + (top - base - skip))) return 1; - for (; at < top; at++) { + for (at = base; at < top; at++) { + /* Filter out any records that contain kernel addresses. */ + if (event->attr.exclude_kernel && + (kernel_ip(at->from) || kernel_ip(at->to))) + continue; + data.ip = at->from; data.addr = at->to; @@ -549,6 +587,19 @@ int intel_pmu_drain_bts_buffer(void) return 1; } +static inline void intel_pmu_drain_pebs_buffer(void) +{ + struct pt_regs regs; + + x86_pmu.drain_pebs(®s); +} + +void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + if (!sched_in) + intel_pmu_drain_pebs_buffer(); +} + /* * PEBS */ @@ -665,6 +716,28 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_skl_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ + /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x22d0, 0xf), /* MEM_INST_RETIRED.LOCK_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_L3_MISS_RETIRED.* */ + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), + EVENT_CONSTRAINT_END +}; + struct event_constraint *intel_pebs_constraints(struct perf_event *event) { struct event_constraint *c; @@ -684,25 +757,71 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) return &emptyconstraint; } +static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc) +{ + return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1)); +} + void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + bool first_pebs; + u64 threshold; hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + first_pebs = !pebs_is_enabled(cpuc); cpuc->pebs_enabled |= 1ULL << hwc->idx; if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled |= 1ULL << 63; + + /* + * When the event is constrained enough we can use a larger + * threshold and run the event with less frequent PMI. + */ + if (hwc->flags & PERF_X86_EVENT_FREERUNNING) { + threshold = ds->pebs_absolute_maximum - + x86_pmu.max_pebs_events * x86_pmu.pebs_record_size; + + if (first_pebs) + perf_sched_cb_inc(event->ctx->pmu); + } else { + threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + /* + * If not all events can use larger buffer, + * roll back to threshold = 1 + */ + if (!first_pebs && + (ds->pebs_interrupt_threshold > threshold)) + perf_sched_cb_dec(event->ctx->pmu); + } + + /* Use auto-reload if possible to save a MSR write in the PMI */ + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + ds->pebs_event_reset[hwc->idx] = + (u64)(-hwc->sample_period) & x86_pmu.cntval_mask; + } + + if (first_pebs || ds->pebs_interrupt_threshold > threshold) + ds->pebs_interrupt_threshold = threshold; } void intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; + struct debug_store *ds = cpuc->ds; + bool large_pebs = ds->pebs_interrupt_threshold > + ds->pebs_buffer_base + x86_pmu.pebs_record_size; + + if (large_pebs) + intel_pmu_drain_pebs_buffer(); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); @@ -711,6 +830,9 @@ void intel_pmu_pebs_disable(struct perf_event *event) else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) cpuc->pebs_enabled &= ~(1ULL << 63); + if (large_pebs && !pebs_is_enabled(cpuc)) + perf_sched_cb_dec(event->ctx->pmu); + if (cpuc->enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); @@ -827,7 +949,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) return 0; } -static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs) +static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs) { if (pebs->tsx_tuning) { union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning }; @@ -836,7 +958,7 @@ static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs) return 0; } -static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) +static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs) { u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32; @@ -846,8 +968,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs) return txn; } -static void __intel_pmu_pebs_event(struct perf_event *event, - struct pt_regs *iregs, void *__pebs) +static void setup_pebs_sample_data(struct perf_event *event, + struct pt_regs *iregs, void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) { #define PERF_X86_EVENT_PEBS_HSW_PREC \ (PERF_X86_EVENT_PEBS_ST_HSW | \ @@ -858,14 +982,12 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * unconditionally access the 'extra' entries. */ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct pebs_record_hsw *pebs = __pebs; - struct perf_sample_data data; - struct pt_regs regs; + struct pebs_record_skl *pebs = __pebs; u64 sample_type; int fll, fst, dsrc; int fl = event->hw.flags; - if (!intel_pmu_save_and_restart(event)) + if (pebs == NULL) return; sample_type = event->attr.sample_type; @@ -874,15 +996,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event, fll = fl & PERF_X86_EVENT_PEBS_LDLAT; fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); - perf_sample_data_init(&data, 0, event->hw.last_period); + perf_sample_data_init(data, 0, event->hw.last_period); - data.period = event->hw.last_period; + data->period = event->hw.last_period; /* * Use latency for weight (only avail with PEBS-LL) */ if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) - data.weight = pebs->lat; + data->weight = pebs->lat; /* * data.data_src encodes the data source @@ -895,7 +1017,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, val = precise_datala_hsw(event, pebs->dse); else if (fst) val = precise_store_data(pebs->dse); - data.data_src.val = val; + data->data_src.val = val; } /* @@ -908,61 +1030,133 @@ static void __intel_pmu_pebs_event(struct perf_event *event, * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly. * A possible PERF_SAMPLE_REGS will have to transfer all regs. */ - regs = *iregs; - regs.flags = pebs->flags; - set_linear_ip(®s, pebs->ip); - regs.bp = pebs->bp; - regs.sp = pebs->sp; + *regs = *iregs; + regs->flags = pebs->flags; + set_linear_ip(regs, pebs->ip); + regs->bp = pebs->bp; + regs->sp = pebs->sp; if (sample_type & PERF_SAMPLE_REGS_INTR) { - regs.ax = pebs->ax; - regs.bx = pebs->bx; - regs.cx = pebs->cx; - regs.dx = pebs->dx; - regs.si = pebs->si; - regs.di = pebs->di; - regs.bp = pebs->bp; - regs.sp = pebs->sp; - - regs.flags = pebs->flags; + regs->ax = pebs->ax; + regs->bx = pebs->bx; + regs->cx = pebs->cx; + regs->dx = pebs->dx; + regs->si = pebs->si; + regs->di = pebs->di; + regs->bp = pebs->bp; + regs->sp = pebs->sp; + + regs->flags = pebs->flags; #ifndef CONFIG_X86_32 - regs.r8 = pebs->r8; - regs.r9 = pebs->r9; - regs.r10 = pebs->r10; - regs.r11 = pebs->r11; - regs.r12 = pebs->r12; - regs.r13 = pebs->r13; - regs.r14 = pebs->r14; - regs.r15 = pebs->r15; + regs->r8 = pebs->r8; + regs->r9 = pebs->r9; + regs->r10 = pebs->r10; + regs->r11 = pebs->r11; + regs->r12 = pebs->r12; + regs->r13 = pebs->r13; + regs->r14 = pebs->r14; + regs->r15 = pebs->r15; #endif } if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) { - regs.ip = pebs->real_ip; - regs.flags |= PERF_EFLAGS_EXACT; - } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(®s)) - regs.flags |= PERF_EFLAGS_EXACT; + regs->ip = pebs->real_ip; + regs->flags |= PERF_EFLAGS_EXACT; + } else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs)) + regs->flags |= PERF_EFLAGS_EXACT; else - regs.flags &= ~PERF_EFLAGS_EXACT; + regs->flags &= ~PERF_EFLAGS_EXACT; if ((sample_type & PERF_SAMPLE_ADDR) && x86_pmu.intel_cap.pebs_format >= 1) - data.addr = pebs->dla; + data->addr = pebs->dla; if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll) - data.weight = intel_hsw_weight(pebs); + data->weight = intel_hsw_weight(pebs); if (sample_type & PERF_SAMPLE_TRANSACTION) - data.txn = intel_hsw_transaction(pebs); + data->txn = intel_hsw_transaction(pebs); } + /* + * v3 supplies an accurate time stamp, so we use that + * for the time stamp. + * + * We can only do this for the default trace clock. + */ + if (x86_pmu.intel_cap.pebs_format >= 3 && + event->attr.use_clockid == 0) + data->time = native_sched_clock_from_tsc(pebs->tsc); + if (has_branch_stack(event)) - data.br_stack = &cpuc->lbr_stack; + data->br_stack = &cpuc->lbr_stack; +} + +static inline void * +get_next_pebs_record_by_bit(void *base, void *top, int bit) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + void *at; + u64 pebs_status; + + if (base == NULL) + return NULL; + + for (at = base; at < top; at += x86_pmu.pebs_record_size) { + struct pebs_record_nhm *p = at; + + if (test_bit(bit, (unsigned long *)&p->status)) { + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) + return at; + + if (p->status == (1 << bit)) + return at; + + /* clear non-PEBS bit and re-check */ + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1; + if (pebs_status == (1 << bit)) + return at; + } + } + return NULL; +} + +static void __intel_pmu_pebs_event(struct perf_event *event, + struct pt_regs *iregs, + void *base, void *top, + int bit, int count) +{ + struct perf_sample_data data; + struct pt_regs regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + + if (!intel_pmu_save_and_restart(event) && + !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)) + return; + + while (count > 1) { + setup_pebs_sample_data(event, iregs, at, &data, ®s); + perf_event_output(event, &data, ®s); + at += x86_pmu.pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + count--; + } + + setup_pebs_sample_data(event, iregs, at, &data, ®s); - if (perf_event_overflow(event, &data, ®s)) + /* + * All but the last records are processed. + * The last one is left to be able to call the overflow handler. + */ + if (perf_event_overflow(event, &data, ®s)) { x86_pmu_stop(event, 0); + return; + } + } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) @@ -992,72 +1186,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = top - at; + n = (top - at) / x86_pmu.pebs_record_size; if (n <= 0) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(n > 1, "bad leftover pebs %d\n", n); - at += n - 1; - - __intel_pmu_pebs_event(event, iregs, at); + __intel_pmu_pebs_event(event, iregs, at, top, 0, n); } static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; - struct perf_event *event = NULL; - void *at, *top; - u64 status = 0; - int bit; + struct perf_event *event; + void *base, *at, *top; + short counts[MAX_PEBS_EVENTS] = {}; + short error[MAX_PEBS_EVENTS] = {}; + int bit, i; if (!x86_pmu.pebs_active) return; - at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; + base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base; top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index; ds->pebs_index = ds->pebs_buffer_base; - if (unlikely(at > top)) + if (unlikely(base >= top)) return; - /* - * Should not happen, we program the threshold at 1 and do not - * set a reset value. - */ - WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size, - "Unexpected number of pebs records %ld\n", - (long)(top - at) / x86_pmu.pebs_record_size); - - for (; at < top; at += x86_pmu.pebs_record_size) { + for (at = base; at < top; at += x86_pmu.pebs_record_size) { struct pebs_record_nhm *p = at; + u64 pebs_status; - for_each_set_bit(bit, (unsigned long *)&p->status, - x86_pmu.max_pebs_events) { - event = cpuc->events[bit]; - if (!test_bit(bit, cpuc->active_mask)) - continue; + /* PEBS v3 has accurate status bits */ + if (x86_pmu.intel_cap.pebs_format >= 3) { + for_each_set_bit(bit, (unsigned long *)&p->status, + MAX_PEBS_EVENTS) + counts[bit]++; - WARN_ON_ONCE(!event); + continue; + } - if (!event->attr.precise_ip) - continue; + pebs_status = p->status & cpuc->pebs_enabled; + pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; - if (__test_and_set_bit(bit, (unsigned long *)&status)) - continue; + bit = find_first_bit((unsigned long *)&pebs_status, + x86_pmu.max_pebs_events); + if (WARN(bit >= x86_pmu.max_pebs_events, + "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx", + (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled, + *(unsigned long long *)cpuc->active_mask)) + continue; - break; + /* + * The PEBS hardware does not deal well with the situation + * when events happen near to each other and multiple bits + * are set. But it should happen rarely. + * + * If these events include one PEBS and multiple non-PEBS + * events, it doesn't impact PEBS record. The record will + * be handled normally. (slow path) + * + * If these events include two or more PEBS events, the + * records for the events can be collapsed into a single + * one, and it's not possible to reconstruct all events + * that caused the PEBS record. It's called collision. + * If collision happened, the record will be dropped. + */ + if (p->status != (1ULL << bit)) { + for_each_set_bit(i, (unsigned long *)&pebs_status, + x86_pmu.max_pebs_events) + error[i]++; + continue; } - if (!event || bit >= x86_pmu.max_pebs_events) + counts[bit]++; + } + + for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) { + if ((counts[bit] == 0) && (error[bit] == 0)) continue; - __intel_pmu_pebs_event(event, iregs, at); + event = cpuc->events[bit]; + WARN_ON_ONCE(!event); + WARN_ON_ONCE(!event->attr.precise_ip); + + /* log dropped samples number */ + if (error[bit]) + perf_log_lost_samples(event, error[bit]); + + if (counts[bit]) { + __intel_pmu_pebs_event(event, iregs, base, + top, bit, counts[bit]); + } } } @@ -1098,6 +1319,14 @@ void __init intel_ds_init(void) x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; break; + case 3: + pr_cont("PEBS fmt3%c, ", pebs_type); + x86_pmu.pebs_record_size = + sizeof(struct pebs_record_skl); + x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm; + x86_pmu.free_running_flags |= PERF_SAMPLE_TIME; + break; + default: printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type); x86_pmu.pebs = 0; diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 94e5b506c..659f01e16 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -13,7 +13,8 @@ enum { LBR_FORMAT_EIP = 0x02, LBR_FORMAT_EIP_FLAGS = 0x03, LBR_FORMAT_EIP_FLAGS2 = 0x04, - LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_EIP_FLAGS2, + LBR_FORMAT_INFO = 0x05, + LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_INFO, }; static enum { @@ -96,6 +97,7 @@ enum { X86_BR_NO_TX = 1 << 14,/* not in transaction */ X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ X86_BR_CALL_STACK = 1 << 16,/* call stack */ + X86_BR_IND_JMP = 1 << 17,/* indirect jump */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -113,6 +115,7 @@ enum { X86_BR_IRQ |\ X86_BR_ABORT |\ X86_BR_IND_CALL |\ + X86_BR_IND_JMP |\ X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) @@ -138,13 +141,20 @@ static void __intel_pmu_lbr_enable(bool pmi) u64 debugctl, lbr_select = 0, orig_debugctl; /* + * No need to unfreeze manually, as v4 can do that as part + * of the GLOBAL_STATUS ack. + */ + if (pmi && x86_pmu.version >= 4) + return; + + /* * No need to reprogram LBR_SELECT in a PMI, as it * did not change. */ - if (cpuc->lbr_sel && !pmi) { + if (cpuc->lbr_sel) lbr_select = cpuc->lbr_sel->config; + if (!pmi) wrmsrl(MSR_LBR_SELECT, lbr_select); - } rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); orig_debugctl = debugctl; @@ -184,6 +194,8 @@ static void intel_pmu_lbr_reset_64(void) for (i = 0; i < x86_pmu.lbr_nr; i++) { wrmsrl(x86_pmu.lbr_from + i, 0); wrmsrl(x86_pmu.lbr_to + i, 0); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + i, 0); } } @@ -227,12 +239,15 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) } mask = x86_pmu.lbr_nr - 1; - tos = intel_pmu_lbr_tos(); - for (i = 0; i < x86_pmu.lbr_nr; i++) { + tos = task_ctx->tos; + for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + wrmsrl(x86_pmu.lbr_tos, tos); task_ctx->lbr_stack_state = LBR_NONE; } @@ -249,11 +264,14 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) mask = x86_pmu.lbr_nr - 1; tos = intel_pmu_lbr_tos(); - for (i = 0; i < x86_pmu.lbr_nr; i++) { + for (i = 0; i < tos; i++) { lbr_idx = (tos - i) & mask; rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO) + rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]); } + task_ctx->tos = tos; task_ctx->lbr_stack_state = LBR_VALID; } @@ -262,9 +280,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct x86_perf_task_context *task_ctx; - if (!x86_pmu.lbr_nr) - return; - /* * If LBR callstack feature is enabled and the stack was saved when * the task was scheduled out, restore the stack. Otherwise flush @@ -412,16 +427,31 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) u64 tos = intel_pmu_lbr_tos(); int i; int out = 0; + int num = x86_pmu.lbr_nr; - for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + + for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; u64 from, to, mis = 0, pred = 0, in_tx = 0, abort = 0; int skip = 0; + u16 cycles = 0; int lbr_flags = lbr_desc[lbr_format]; rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); + if (lbr_format == LBR_FORMAT_INFO) { + u64 info; + + rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info); + mis = !!(info & LBR_INFO_MISPRED); + pred = !mis; + in_tx = !!(info & LBR_INFO_IN_TX); + abort = !!(info & LBR_INFO_ABORT); + cycles = (info & LBR_INFO_CYCLES); + } if (lbr_flags & LBR_EIP_FLAGS) { mis = !!(from & LBR_FROM_FLAG_MISPRED); pred = !mis; @@ -451,6 +481,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) cpuc->lbr_entries[out].predicted = pred; cpuc->lbr_entries[out].in_tx = in_tx; cpuc->lbr_entries[out].abort = abort; + cpuc->lbr_entries[out].cycles = cycles; cpuc->lbr_entries[out].reserved = 0; out++; } @@ -523,6 +554,11 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) X86_BR_CALL_STACK; } + if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP) + mask |= X86_BR_IND_JMP; + + if (br_type & PERF_SAMPLE_BRANCH_CALL) + mask |= X86_BR_CALL | X86_BR_ZERO_CALL; /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -736,7 +772,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) break; case 4: case 5: - ret = X86_BR_JMP; + ret = X86_BR_IND_JMP; break; } break; @@ -844,6 +880,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { */ [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -856,6 +893,8 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL, }; static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { @@ -870,6 +909,8 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_RETURN | LBR_CALL_STACK, + [PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_CALL_SHIFT] = LBR_REL_CALL, }; /* core */ @@ -942,6 +983,26 @@ void intel_pmu_lbr_init_hsw(void) pr_cont("16-deep LBR, "); } +/* skylake */ +__init void intel_pmu_lbr_init_skl(void) +{ + x86_pmu.lbr_nr = 32; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = hsw_lbr_sel_map; + + /* + * SW branch filter usage: + * - support syscall, sysret capture. + * That requires LBR_FAR but that means far + * jmp need to be filtered out + */ + pr_cont("32-deep LBR, "); +} + /* atom */ void __init intel_pmu_lbr_init_atom(void) { diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c index 123ff1bb2..868e11943 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -65,15 +65,21 @@ static struct pt_cap_desc { } pt_caps[] = { PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), + PT_CAP(psb_cyc, 0, CR_EBX, BIT(1)), + PT_CAP(mtc, 0, CR_EBX, BIT(3)), PT_CAP(topa_output, 0, CR_ECX, BIT(0)), PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), + PT_CAP(single_range_output, 0, CR_ECX, BIT(2)), PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), + PT_CAP(mtc_periods, 1, CR_EAX, 0xffff0000), + PT_CAP(cycle_thresholds, 1, CR_EBX, 0xffff), + PT_CAP(psb_periods, 1, CR_EBX, 0xffff0000), }; static u32 pt_cap_get(enum pt_capabilities cap) { struct pt_cap_desc *cd = &pt_caps[cap]; - u32 c = pt_pmu.caps[cd->leaf * 4 + cd->reg]; + u32 c = pt_pmu.caps[cd->leaf * PT_CPUID_REGS_NUM + cd->reg]; unsigned int shift = __ffs(cd->mask); return (c & cd->mask) >> shift; @@ -94,12 +100,22 @@ static struct attribute_group pt_cap_group = { .name = "caps", }; +PMU_FORMAT_ATTR(cyc, "config:1" ); +PMU_FORMAT_ATTR(mtc, "config:9" ); PMU_FORMAT_ATTR(tsc, "config:10" ); PMU_FORMAT_ATTR(noretcomp, "config:11" ); +PMU_FORMAT_ATTR(mtc_period, "config:14-17" ); +PMU_FORMAT_ATTR(cyc_thresh, "config:19-22" ); +PMU_FORMAT_ATTR(psb_period, "config:24-27" ); static struct attribute *pt_formats_attr[] = { + &format_attr_cyc.attr, + &format_attr_mtc.attr, &format_attr_tsc.attr, &format_attr_noretcomp.attr, + &format_attr_mtc_period.attr, + &format_attr_cyc_thresh.attr, + &format_attr_psb_period.attr, NULL, }; @@ -123,16 +139,13 @@ static int __init pt_pmu_hw_init(void) long i; attrs = NULL; - ret = -ENODEV; - if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) - goto fail; for (i = 0; i < PT_CPUID_LEAVES; i++) { cpuid_count(20, i, - &pt_pmu.caps[CR_EAX + i*4], - &pt_pmu.caps[CR_EBX + i*4], - &pt_pmu.caps[CR_ECX + i*4], - &pt_pmu.caps[CR_EDX + i*4]); + &pt_pmu.caps[CR_EAX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CR_EBX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CR_ECX + i*PT_CPUID_REGS_NUM], + &pt_pmu.caps[CR_EDX + i*PT_CPUID_REGS_NUM]); } ret = -ENOMEM; @@ -170,15 +183,65 @@ fail: return ret; } -#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC) +#define RTIT_CTL_CYC_PSB (RTIT_CTL_CYCLEACC | \ + RTIT_CTL_CYC_THRESH | \ + RTIT_CTL_PSB_FREQ) + +#define RTIT_CTL_MTC (RTIT_CTL_MTC_EN | \ + RTIT_CTL_MTC_RANGE) + +#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | \ + RTIT_CTL_DISRETC | \ + RTIT_CTL_CYC_PSB | \ + RTIT_CTL_MTC) static bool pt_event_valid(struct perf_event *event) { u64 config = event->attr.config; + u64 allowed, requested; if ((config & PT_CONFIG_MASK) != config) return false; + if (config & RTIT_CTL_CYC_PSB) { + if (!pt_cap_get(PT_CAP_psb_cyc)) + return false; + + allowed = pt_cap_get(PT_CAP_psb_periods); + requested = (config & RTIT_CTL_PSB_FREQ) >> + RTIT_CTL_PSB_FREQ_OFFSET; + if (requested && (!(allowed & BIT(requested)))) + return false; + + allowed = pt_cap_get(PT_CAP_cycle_thresholds); + requested = (config & RTIT_CTL_CYC_THRESH) >> + RTIT_CTL_CYC_THRESH_OFFSET; + if (requested && (!(allowed & BIT(requested)))) + return false; + } + + if (config & RTIT_CTL_MTC) { + /* + * In the unlikely case that CPUID lists valid mtc periods, + * but not the mtc capability, drop out here. + * + * Spec says that setting mtc period bits while mtc bit in + * CPUID is 0 will #GP, so better safe than sorry. + */ + if (!pt_cap_get(PT_CAP_mtc)) + return false; + + allowed = pt_cap_get(PT_CAP_mtc_periods); + if (!allowed) + return false; + + requested = (config & RTIT_CTL_MTC_RANGE) >> + RTIT_CTL_MTC_RANGE_OFFSET; + + if (!(allowed & BIT(requested))) + return false; + } + return true; } @@ -187,19 +250,15 @@ static bool pt_event_valid(struct perf_event *event) * These all are cpu affine and operate on a local PT */ -static bool pt_is_running(void) -{ - u64 ctl; - - rdmsrl(MSR_IA32_RTIT_CTL, ctl); - - return !!(ctl & RTIT_CTL_TRACEEN); -} - static void pt_config(struct perf_event *event) { u64 reg; + if (!event->hw.itrace_started) { + event->hw.itrace_started = 1; + wrmsrl(MSR_IA32_RTIT_STATUS, 0); + } + reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; if (!event->attr.exclude_kernel) @@ -609,7 +668,12 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) * @handle: Current output handle. * * Place INT and STOP marks to prevent overwriting old data that the consumer - * hasn't yet collected. + * hasn't yet collected and waking up the consumer after a certain fraction of + * the buffer has filled up. Only needed and sensible for non-snapshot counters. + * + * This obviously relies on buf::head to figure out buffer markers, so it has + * to be called after pt_buffer_reset_offsets() and before the hardware tracing + * is enabled. */ static int pt_buffer_reset_markers(struct pt_buffer *buf, struct perf_output_handle *handle) @@ -618,9 +682,6 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf, unsigned long head = local64_read(&buf->head); unsigned long idx, npages, wakeup; - if (buf->snapshot) - return 0; - /* can't stop in the middle of an output region */ if (buf->output_off + handle->size + 1 < sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) @@ -674,7 +735,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) struct topa *cur = buf->first, *prev = buf->last; struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), *te_prev = TOPA_ENTRY(prev, prev->last - 1); - int pg = 0, idx = 0, ntopa = 0; + int pg = 0, idx = 0; while (pg < buf->nr_pages) { int tidx; @@ -689,9 +750,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) /* advance to next topa table */ idx = 0; cur = list_entry(cur->list.next, struct topa, list); - ntopa++; - } else + } else { idx++; + } te_cur = TOPA_ENTRY(cur, idx); } @@ -703,7 +764,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf) * @head: Write pointer (aux_head) from AUX buffer. * * Find the ToPA table and entry corresponding to given @head and set buffer's - * "current" pointers accordingly. + * "current" pointers accordingly. This is done after we have obtained the + * current aux_head position from a successful call to perf_aux_output_begin() + * to make sure the hardware is writing to the right place. + * + * This function modifies buf::{cur,cur_idx,output_off} that will be programmed + * into PT msrs when the tracing is enabled and buf::head and buf::data_size, + * which are used to determine INT and STOP markers' locations by a subsequent + * call to pt_buffer_reset_markers(). */ static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) { @@ -901,6 +969,7 @@ void intel_pt_interrupt(void) } pt_buffer_reset_offsets(buf, pt->handle.head); + /* snapshot counters don't use PMI, so it's safe */ ret = pt_buffer_reset_markers(buf, &pt->handle); if (ret) { perf_aux_output_end(&pt->handle, 0, true); @@ -909,7 +978,6 @@ void intel_pt_interrupt(void) pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); - wrmsrl(MSR_IA32_RTIT_STATUS, 0); pt_config(event); } } @@ -923,7 +991,7 @@ static void pt_event_start(struct perf_event *event, int mode) struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); - if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + if (!buf || pt_buffer_is_full(buf, pt)) { event->hw.state = PERF_HES_STOPPED; return; } @@ -933,7 +1001,6 @@ static void pt_event_start(struct perf_event *event, int mode) pt_config_buffer(buf->cur->table, buf->cur_idx, buf->output_off); - wrmsrl(MSR_IA32_RTIT_STATUS, 0); pt_config(event); } @@ -954,7 +1021,6 @@ static void pt_event_stop(struct perf_event *event, int mode) event->hw.state = PERF_HES_STOPPED; if (mode & PERF_EF_UPDATE) { - struct pt *pt = this_cpu_ptr(&pt_ctx); struct pt_buffer *buf = perf_get_aux(&pt->handle); if (!buf) @@ -1061,6 +1127,10 @@ static __init int pt_init(void) int ret, cpu, prior_warn = 0; BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); + + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + return -ENODEV; + get_online_cpus(); for_each_online_cpu(cpu) { u64 ctl; @@ -1106,5 +1176,4 @@ static __init int pt_init(void) return ret; } - -module_init(pt_init); +arch_initcall(pt_init); diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 358c54ad2..ed446bdcb 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -86,6 +86,10 @@ static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { 1<<RAPL_IDX_RAM_NRG_STAT|\ 1<<RAPL_IDX_PP1_NRG_STAT) +/* Knights Landing has PKG, RAM */ +#define RAPL_IDX_KNL (1<<RAPL_IDX_PKG_NRG_STAT|\ + 1<<RAPL_IDX_RAM_NRG_STAT) + /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved @@ -103,12 +107,6 @@ static ssize_t __rapl_##_var##_show(struct kobject *kobj, \ static struct kobj_attribute format_attr_##_var = \ __ATTR(_name, 0444, __rapl_##_var##_show, NULL) -#define RAPL_EVENT_DESC(_name, _config) \ -{ \ - .attr = __ATTR(_name, 0444, rapl_event_show, NULL), \ - .config = _config, \ -} - #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ #define RAPL_EVENT_ATTR_STR(_name, v, str) \ @@ -204,9 +202,8 @@ again: static void rapl_start_hrtimer(struct rapl_pmu *pmu) { - __hrtimer_start_range_ns(&pmu->hrtimer, - pmu->timer_interval, 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&pmu->hrtimer, pmu->timer_interval, + HRTIMER_MODE_REL_PINNED); } static void rapl_stop_hrtimer(struct rapl_pmu *pmu) @@ -487,6 +484,18 @@ static struct attribute *rapl_events_hsw_attr[] = { NULL, }; +static struct attribute *rapl_events_knl_attr[] = { + EVENT_PTR(rapl_pkg), + EVENT_PTR(rapl_ram), + + EVENT_PTR(rapl_pkg_unit), + EVENT_PTR(rapl_ram_unit), + + EVENT_PTR(rapl_pkg_scale), + EVENT_PTR(rapl_ram_scale), + NULL, +}; + static struct attribute_group rapl_pmu_events_group = { .name = "events", .attrs = NULL, /* patched at runtime */ @@ -731,6 +740,10 @@ static int __init rapl_pmu_init(void) rapl_cntr_mask = RAPL_IDX_SRV; rapl_pmu_events_group.attrs = rapl_events_srv_attr; break; + case 87: /* Knights Landing */ + rapl_add_quirk(rapl_hsw_server_quirk); + rapl_cntr_mask = RAPL_IDX_KNL; + rapl_pmu_events_group.attrs = rapl_events_knl_attr; default: /* unsupported */ diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 90b7c501c..61215a69b 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -7,7 +7,8 @@ struct intel_uncore_type **uncore_pci_uncores = empty_uncore; static bool pcidrv_registered; struct pci_driver *uncore_pci_driver; /* pci bus to socket mapping */ -int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, }; +DEFINE_RAW_SPINLOCK(pci2phy_map_lock); +struct list_head pci2phy_map_head = LIST_HEAD_INIT(pci2phy_map_head); struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; static DEFINE_RAW_SPINLOCK(uncore_box_lock); @@ -20,6 +21,59 @@ static struct event_constraint uncore_constraint_fixed = struct event_constraint uncore_constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +int uncore_pcibus_to_physid(struct pci_bus *bus) +{ + struct pci2phy_map *map; + int phys_id = -1; + + raw_spin_lock(&pci2phy_map_lock); + list_for_each_entry(map, &pci2phy_map_head, list) { + if (map->segment == pci_domain_nr(bus)) { + phys_id = map->pbus_to_physid[bus->number]; + break; + } + } + raw_spin_unlock(&pci2phy_map_lock); + + return phys_id; +} + +struct pci2phy_map *__find_pci2phy_map(int segment) +{ + struct pci2phy_map *map, *alloc = NULL; + int i; + + lockdep_assert_held(&pci2phy_map_lock); + +lookup: + list_for_each_entry(map, &pci2phy_map_head, list) { + if (map->segment == segment) + goto end; + } + + if (!alloc) { + raw_spin_unlock(&pci2phy_map_lock); + alloc = kmalloc(sizeof(struct pci2phy_map), GFP_KERNEL); + raw_spin_lock(&pci2phy_map_lock); + + if (!alloc) + return NULL; + + goto lookup; + } + + map = alloc; + alloc = NULL; + map->segment = segment; + for (i = 0; i < 256; i++) + map->pbus_to_physid[i] = -1; + list_add_tail(&map->list, &pci2phy_map_head); + +end: + kfree(alloc); + return map; +} + ssize_t uncore_event_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -233,9 +287,8 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer) void uncore_pmu_start_hrtimer(struct intel_uncore_box *box) { - __hrtimer_start_range_ns(&box->hrtimer, - ns_to_ktime(box->hrtimer_duration), 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration), + HRTIMER_MODE_REL_PINNED); } void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box) @@ -810,7 +863,7 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id int phys_id; bool first_box = false; - phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + phys_id = uncore_pcibus_to_physid(pdev->bus); if (phys_id < 0) return -ENODEV; @@ -857,9 +910,10 @@ static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); struct intel_uncore_pmu *pmu; - int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number]; + int i, cpu, phys_id; bool last_box = false; + phys_id = uncore_pcibus_to_physid(pdev->bus); box = pci_get_drvdata(pdev); if (!box) { for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { @@ -912,6 +966,9 @@ static int __init uncore_pci_init(void) case 63: /* Haswell-EP */ ret = hswep_uncore_pci_init(); break; + case 86: /* BDX-DE */ + ret = bdx_uncore_pci_init(); + break; case 42: /* Sandy Bridge */ ret = snb_uncore_pci_init(); break; @@ -922,6 +979,9 @@ static int __init uncore_pci_init(void) case 69: /* Haswell Celeron */ ret = hsw_uncore_pci_init(); break; + case 61: /* Broadwell */ + ret = bdw_uncore_pci_init(); + break; default: return 0; } @@ -1207,6 +1267,11 @@ static int __init uncore_cpu_init(void) break; case 42: /* Sandy Bridge */ case 58: /* Ivy Bridge */ + case 60: /* Haswell */ + case 69: /* Haswell */ + case 70: /* Haswell */ + case 61: /* Broadwell */ + case 71: /* Broadwell */ snb_uncore_cpu_init(); break; case 45: /* Sandy Bridge-EP */ @@ -1222,6 +1287,9 @@ static int __init uncore_cpu_init(void) case 63: /* Haswell-EP */ hswep_uncore_cpu_init(); break; + case 86: /* BDX-DE */ + bdx_uncore_cpu_init(); + break; default: return 0; } diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.h index ceac8f5dc..2f0a4a98e 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -117,6 +117,15 @@ struct uncore_event_desc { const char *config; }; +struct pci2phy_map { + struct list_head list; + int segment; + int pbus_to_physid[256]; +}; + +int uncore_pcibus_to_physid(struct pci_bus *bus); +struct pci2phy_map *__find_pci2phy_map(int segment); + ssize_t uncore_event_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf); @@ -317,7 +326,8 @@ u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx); extern struct intel_uncore_type **uncore_msr_uncores; extern struct intel_uncore_type **uncore_pci_uncores; extern struct pci_driver *uncore_pci_driver; -extern int uncore_pcibus_to_physid[256]; +extern raw_spinlock_t pci2phy_map_lock; +extern struct list_head pci2phy_map_head; extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; extern struct event_constraint uncore_constraint_empty; @@ -325,6 +335,7 @@ extern struct event_constraint uncore_constraint_empty; int snb_uncore_pci_init(void); int ivb_uncore_pci_init(void); int hsw_uncore_pci_init(void); +int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); @@ -335,6 +346,8 @@ int ivbep_uncore_pci_init(void); void ivbep_uncore_cpu_init(void); int hswep_uncore_pci_init(void); void hswep_uncore_cpu_init(void); +int bdx_uncore_pci_init(void); +void bdx_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 4562e9e22..845256158 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -7,6 +7,7 @@ #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 #define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 +#define PCI_DEVICE_ID_INTEL_BDW_IMC 0x1604 /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff @@ -44,6 +45,11 @@ #define SNB_UNC_CBO_0_PER_CTR0 0x706 #define SNB_UNC_CBO_MSR_OFFSET 0x10 +/* SNB ARB register */ +#define SNB_UNC_ARB_PER_CTR0 0x3b0 +#define SNB_UNC_ARB_PERFEVTSEL0 0x3b2 +#define SNB_UNC_ARB_MSR_OFFSET 0x10 + /* NHM global control register */ #define NHM_UNC_PERF_GLOBAL_CTL 0x391 #define NHM_UNC_FIXED_CTR 0x394 @@ -114,7 +120,7 @@ static struct intel_uncore_ops snb_uncore_msr_ops = { .read_counter = uncore_msr_read_counter, }; -static struct event_constraint snb_uncore_cbox_constraints[] = { +static struct event_constraint snb_uncore_arb_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x80, 0x1), UNCORE_EVENT_CONSTRAINT(0x83, 0x1), EVENT_CONSTRAINT_END @@ -133,14 +139,28 @@ static struct intel_uncore_type snb_uncore_cbox = { .single_fixed = 1, .event_mask = SNB_UNC_RAW_EVENT_MASK, .msr_offset = SNB_UNC_CBO_MSR_OFFSET, - .constraints = snb_uncore_cbox_constraints, .ops = &snb_uncore_msr_ops, .format_group = &snb_uncore_format_group, .event_descs = snb_uncore_events, }; +static struct intel_uncore_type snb_uncore_arb = { + .name = "arb", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .perf_ctr = SNB_UNC_ARB_PER_CTR0, + .event_ctl = SNB_UNC_ARB_PERFEVTSEL0, + .event_mask = SNB_UNC_RAW_EVENT_MASK, + .msr_offset = SNB_UNC_ARB_MSR_OFFSET, + .constraints = snb_uncore_arb_constraints, + .ops = &snb_uncore_msr_ops, + .format_group = &snb_uncore_format_group, +}; + static struct intel_uncore_type *snb_msr_uncores[] = { &snb_uncore_cbox, + &snb_uncore_arb, NULL, }; @@ -400,15 +420,25 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags) static int snb_pci2phy_map_init(int devid) { struct pci_dev *dev = NULL; - int bus; + struct pci2phy_map *map; + int bus, segment; dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev); if (!dev) return -ENOTTY; bus = dev->bus->number; - - uncore_pcibus_to_physid[bus] = 0; + segment = pci_domain_nr(dev->bus); + + raw_spin_lock(&pci2phy_map_lock); + map = __find_pci2phy_map(segment); + if (!map) { + raw_spin_unlock(&pci2phy_map_lock); + pci_dev_put(dev); + return -ENOMEM; + } + map->pbus_to_physid[bus] = 0; + raw_spin_unlock(&pci2phy_map_lock); pci_dev_put(dev); @@ -486,6 +516,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { { /* end: all zeroes */ }, }; +static const struct pci_device_id bdw_uncore_pci_ids[] = { + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, + { /* end: all zeroes */ }, +}; + static struct pci_driver snb_uncore_pci_driver = { .name = "snb_uncore", .id_table = snb_uncore_pci_ids, @@ -501,6 +539,11 @@ static struct pci_driver hsw_uncore_pci_driver = { .id_table = hsw_uncore_pci_ids, }; +static struct pci_driver bdw_uncore_pci_driver = { + .name = "bdw_uncore", + .id_table = bdw_uncore_pci_ids, +}; + struct imc_uncore_pci_dev { __u32 pci_id; struct pci_driver *driver; @@ -514,6 +557,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ + IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver), /* 5th Gen Core U */ { /* end marker */ } }; @@ -561,6 +605,11 @@ int hsw_uncore_pci_init(void) return imc_uncore_pci_init(); } +int bdw_uncore_pci_init(void) +{ + return imc_uncore_pci_init(); +} + /* end of Sandy Bridge uncore support */ /* Nehalem uncore support */ diff --git a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 6d6e85dd5..f0f4fcba2 100644 --- a/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/kernel/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -1087,7 +1087,8 @@ static struct pci_driver snbep_uncore_pci_driver = { static int snbep_pci2phy_map_init(int devid) { struct pci_dev *ubox_dev = NULL; - int i, bus, nodeid; + int i, bus, nodeid, segment; + struct pci2phy_map *map; int err = 0; u32 config = 0; @@ -1106,16 +1107,27 @@ static int snbep_pci2phy_map_init(int devid) err = pci_read_config_dword(ubox_dev, 0x54, &config); if (err) break; + + segment = pci_domain_nr(ubox_dev->bus); + raw_spin_lock(&pci2phy_map_lock); + map = __find_pci2phy_map(segment); + if (!map) { + raw_spin_unlock(&pci2phy_map_lock); + err = -ENOMEM; + break; + } + /* * every three bits in the Node ID mapping register maps * to a particular node. */ for (i = 0; i < 8; i++) { if (nodeid == ((config >> (3 * i)) & 0x7)) { - uncore_pcibus_to_physid[bus] = i; + map->pbus_to_physid[bus] = i; break; } } + raw_spin_unlock(&pci2phy_map_lock); } if (!err) { @@ -1123,13 +1135,17 @@ static int snbep_pci2phy_map_init(int devid) * For PCI bus with no UBOX device, find the next bus * that has UBOX device and use its mapping. */ - i = -1; - for (bus = 255; bus >= 0; bus--) { - if (uncore_pcibus_to_physid[bus] >= 0) - i = uncore_pcibus_to_physid[bus]; - else - uncore_pcibus_to_physid[bus] = i; + raw_spin_lock(&pci2phy_map_lock); + list_for_each_entry(map, &pci2phy_map_head, list) { + i = -1; + for (bus = 255; bus >= 0; bus--) { + if (map->pbus_to_physid[bus] >= 0) + i = map->pbus_to_physid[bus]; + else + map->pbus_to_physid[bus] = i; + } } + raw_spin_unlock(&pci2phy_map_lock); } pci_dev_put(ubox_dev); @@ -2215,7 +2231,7 @@ static struct intel_uncore_type *hswep_pci_uncores[] = { NULL, }; -static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = { +static const struct pci_device_id hswep_uncore_pci_ids[] = { { /* Home Agent 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30), .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0), @@ -2321,3 +2337,167 @@ int hswep_uncore_pci_init(void) return 0; } /* end of Haswell-EP uncore support */ + +/* BDX-DE uncore support */ + +static struct intel_uncore_type bdx_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .num_shared_regs = 1, + .ops = &ivbep_uncore_msr_ops, + .format_group = &ivbep_uncore_ubox_format_group, +}; + +static struct event_constraint bdx_uncore_cbox_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = bdx_uncore_cbox_constraints, + .ops = &hswep_uncore_cbox_ops, + .format_group = &hswep_uncore_cbox_format_group, +}; + +static struct intel_uncore_type *bdx_msr_uncores[] = { + &bdx_uncore_ubox, + &bdx_uncore_cbox, + &hswep_uncore_pcu, + NULL, +}; + +void bdx_uncore_cpu_init(void) +{ + if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) + bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + uncore_msr_uncores = bdx_msr_uncores; +} + +static struct intel_uncore_type bdx_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type bdx_uncore_imc = { + .name = "imc", + .num_counters = 5, + .num_boxes = 2, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + .event_descs = hswep_uncore_imc_events, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type bdx_uncore_irp = { + .name = "irp", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &hswep_uncore_irp_ops, + .format_group = &snbep_uncore_format_group, +}; + + +static struct event_constraint bdx_uncore_r2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x23, 0x1), + UNCORE_EVENT_CONSTRAINT(0x25, 0x1), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + BDX_PCI_UNCORE_HA, + BDX_PCI_UNCORE_IMC, + BDX_PCI_UNCORE_IRP, + BDX_PCI_UNCORE_R2PCIE, +}; + +static struct intel_uncore_type *bdx_pci_uncores[] = { + [BDX_PCI_UNCORE_HA] = &bdx_uncore_ha, + [BDX_PCI_UNCORE_IMC] = &bdx_uncore_imc, + [BDX_PCI_UNCORE_IRP] = &bdx_uncore_irp, + [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie, + NULL, +}; + +static const struct pci_device_id bdx_uncore_pci_ids[] = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0), + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0), + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0), + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver bdx_uncore_pci_driver = { + .name = "bdx_uncore", + .id_table = bdx_uncore_pci_ids, +}; + +int bdx_uncore_pci_init(void) +{ + int ret = snbep_pci2phy_map_init(0x6f1e); + + if (ret) + return ret; + uncore_pci_uncores = bdx_pci_uncores; + uncore_pci_driver = &bdx_uncore_pci_driver; + return 0; +} + +/* end of BDX-DE uncore support */ diff --git a/kernel/arch/x86/kernel/cpu/perf_event_msr.c b/kernel/arch/x86/kernel/cpu/perf_event_msr.c new file mode 100644 index 000000000..ec863b9a9 --- /dev/null +++ b/kernel/arch/x86/kernel/cpu/perf_event_msr.c @@ -0,0 +1,241 @@ +#include <linux/perf_event.h> + +enum perf_msr_id { + PERF_MSR_TSC = 0, + PERF_MSR_APERF = 1, + PERF_MSR_MPERF = 2, + PERF_MSR_PPERF = 3, + PERF_MSR_SMI = 4, + + PERF_MSR_EVENT_MAX, +}; + +static bool test_aperfmperf(int idx) +{ + return boot_cpu_has(X86_FEATURE_APERFMPERF); +} + +static bool test_intel(int idx) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL || + boot_cpu_data.x86 != 6) + return false; + + switch (boot_cpu_data.x86_model) { + case 30: /* 45nm Nehalem */ + case 26: /* 45nm Nehalem-EP */ + case 46: /* 45nm Nehalem-EX */ + + case 37: /* 32nm Westmere */ + case 44: /* 32nm Westmere-EP */ + case 47: /* 32nm Westmere-EX */ + + case 42: /* 32nm SandyBridge */ + case 45: /* 32nm SandyBridge-E/EN/EP */ + + case 58: /* 22nm IvyBridge */ + case 62: /* 22nm IvyBridge-EP/EX */ + + case 60: /* 22nm Haswell Core */ + case 63: /* 22nm Haswell Server */ + case 69: /* 22nm Haswell ULT */ + case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + case 71: /* 14nm Broadwell + GT3e (Intel Iris Pro graphics) */ + case 79: /* 14nm Broadwell Server */ + + case 55: /* 22nm Atom "Silvermont" */ + case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */ + case 76: /* 14nm Atom "Airmont" */ + if (idx == PERF_MSR_SMI) + return true; + break; + + case 78: /* 14nm Skylake Mobile */ + case 94: /* 14nm Skylake Desktop */ + if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) + return true; + break; + } + + return false; +} + +struct perf_msr { + u64 msr; + struct perf_pmu_events_attr *attr; + bool (*test)(int idx); +}; + +PMU_EVENT_ATTR_STRING(tsc, evattr_tsc, "event=0x00"); +PMU_EVENT_ATTR_STRING(aperf, evattr_aperf, "event=0x01"); +PMU_EVENT_ATTR_STRING(mperf, evattr_mperf, "event=0x02"); +PMU_EVENT_ATTR_STRING(pperf, evattr_pperf, "event=0x03"); +PMU_EVENT_ATTR_STRING(smi, evattr_smi, "event=0x04"); + +static struct perf_msr msr[] = { + [PERF_MSR_TSC] = { 0, &evattr_tsc, NULL, }, + [PERF_MSR_APERF] = { MSR_IA32_APERF, &evattr_aperf, test_aperfmperf, }, + [PERF_MSR_MPERF] = { MSR_IA32_MPERF, &evattr_mperf, test_aperfmperf, }, + [PERF_MSR_PPERF] = { MSR_PPERF, &evattr_pperf, test_intel, }, + [PERF_MSR_SMI] = { MSR_SMI_COUNT, &evattr_smi, test_intel, }, +}; + +static struct attribute *events_attrs[PERF_MSR_EVENT_MAX + 1] = { + NULL, +}; + +static struct attribute_group events_attr_group = { + .name = "events", + .attrs = events_attrs, +}; + +PMU_FORMAT_ATTR(event, "config:0-63"); +static struct attribute *format_attrs[] = { + &format_attr_event.attr, + NULL, +}; +static struct attribute_group format_attr_group = { + .name = "format", + .attrs = format_attrs, +}; + +static const struct attribute_group *attr_groups[] = { + &events_attr_group, + &format_attr_group, + NULL, +}; + +static int msr_event_init(struct perf_event *event) +{ + u64 cfg = event->attr.config; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + if (cfg >= PERF_MSR_EVENT_MAX) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + if (!msr[cfg].attr) + return -EINVAL; + + event->hw.idx = -1; + event->hw.event_base = msr[cfg].msr; + event->hw.config = cfg; + + return 0; +} + +static inline u64 msr_read_counter(struct perf_event *event) +{ + u64 now; + + if (event->hw.event_base) + rdmsrl(event->hw.event_base, now); + else + rdtscll(now); + + return now; +} +static void msr_event_update(struct perf_event *event) +{ + u64 prev, now; + s64 delta; + + /* Careful, an NMI might modify the previous event value. */ +again: + prev = local64_read(&event->hw.prev_count); + now = msr_read_counter(event); + + if (local64_cmpxchg(&event->hw.prev_count, prev, now) != prev) + goto again; + + delta = now - prev; + if (unlikely(event->hw.event_base == MSR_SMI_COUNT)) + delta = sign_extend64(delta, 31); + + local64_add(now - prev, &event->count); +} + +static void msr_event_start(struct perf_event *event, int flags) +{ + u64 now; + + now = msr_read_counter(event); + local64_set(&event->hw.prev_count, now); +} + +static void msr_event_stop(struct perf_event *event, int flags) +{ + msr_event_update(event); +} + +static void msr_event_del(struct perf_event *event, int flags) +{ + msr_event_stop(event, PERF_EF_UPDATE); +} + +static int msr_event_add(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_START) + msr_event_start(event, flags); + + return 0; +} + +static struct pmu pmu_msr = { + .task_ctx_nr = perf_sw_context, + .attr_groups = attr_groups, + .event_init = msr_event_init, + .add = msr_event_add, + .del = msr_event_del, + .start = msr_event_start, + .stop = msr_event_stop, + .read = msr_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT, +}; + +static int __init msr_init(void) +{ + int i, j = 0; + + if (!boot_cpu_has(X86_FEATURE_TSC)) { + pr_cont("no MSR PMU driver.\n"); + return 0; + } + + /* Probe the MSRs. */ + for (i = PERF_MSR_TSC + 1; i < PERF_MSR_EVENT_MAX; i++) { + u64 val; + + /* + * Virt sucks arse; you cannot tell if a R/O MSR is present :/ + */ + if (!msr[i].test(i) || rdmsrl_safe(msr[i].msr, &val)) + msr[i].attr = NULL; + } + + /* List remaining MSRs in the sysfs attrs. */ + for (i = 0; i < PERF_MSR_EVENT_MAX; i++) { + if (msr[i].attr) + events_attrs[j++] = &msr[i].attr->attr.attr; + } + events_attrs[j] = NULL; + + perf_pmu_register(&pmu_msr, "msr", -1); + + return 0; +} +device_initcall(msr_init); diff --git a/kernel/arch/x86/kernel/cpu/proc.c b/kernel/arch/x86/kernel/cpu/proc.c index e7d8c7608..18ca99f27 100644 --- a/kernel/arch/x86/kernel/cpu/proc.c +++ b/kernel/arch/x86/kernel/cpu/proc.c @@ -12,7 +12,8 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, { #ifdef CONFIG_SMP seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); - seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu))); + seq_printf(m, "siblings\t: %d\n", + cpumask_weight(topology_core_cpumask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); diff --git a/kernel/arch/x86/kernel/cpu/scattered.c b/kernel/arch/x86/kernel/cpu/scattered.c index 3d423a101..608fb26c7 100644 --- a/kernel/arch/x86/kernel/cpu/scattered.c +++ b/kernel/arch/x86/kernel/cpu/scattered.c @@ -37,7 +37,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 }, + { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 }, { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, diff --git a/kernel/arch/x86/kernel/cpuid.c b/kernel/arch/x86/kernel/cpuid.c index 83741a715..bd3507da3 100644 --- a/kernel/arch/x86/kernel/cpuid.c +++ b/kernel/arch/x86/kernel/cpuid.c @@ -170,7 +170,7 @@ static int cpuid_class_cpu_callback(struct notifier_block *nfb, return notifier_from_errno(err); } -static struct notifier_block __refdata cpuid_class_cpu_notifier = +static struct notifier_block cpuid_class_cpu_notifier = { .notifier_call = cpuid_class_cpu_callback, }; diff --git a/kernel/arch/x86/kernel/crash.c b/kernel/arch/x86/kernel/crash.c index c76d3e37c..2c1910f67 100644 --- a/kernel/arch/x86/kernel/crash.c +++ b/kernel/arch/x86/kernel/crash.c @@ -22,6 +22,7 @@ #include <linux/elfcore.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -74,8 +75,6 @@ struct crash_memmap_data { unsigned int type; }; -int in_crash_kexec; - /* * This is used to VMCLEAR all VMCSs loaded on the * processor. And when loading kvm_intel module, the @@ -131,7 +130,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) static void kdump_nmi_shootdown_cpus(void) { - in_crash_kexec = 1; nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); @@ -184,10 +182,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs) } #ifdef CONFIG_KEXEC_FILE -static int get_nr_ram_ranges_callback(unsigned long start_pfn, - unsigned long nr_pfn, void *arg) +static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg) { - int *nr_ranges = arg; + unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; @@ -213,7 +210,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced, ced->image = image; - walk_system_ram_range(0, -1, &nr_ranges, + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); ced->max_nr_ranges = nr_ranges; diff --git a/kernel/arch/x86/kernel/devicetree.c b/kernel/arch/x86/kernel/devicetree.c index 6367a780c..1f4acd68b 100644 --- a/kernel/arch/x86/kernel/devicetree.c +++ b/kernel/arch/x86/kernel/devicetree.c @@ -4,7 +4,6 @@ #include <linux/bootmem.h> #include <linux/export.h> #include <linux/io.h> -#include <linux/irqdomain.h> #include <linux/interrupt.h> #include <linux/list.h> #include <linux/of.h> @@ -17,6 +16,7 @@ #include <linux/of_pci.h> #include <linux/initrd.h> +#include <asm/irqdomain.h> #include <asm/hpet.h> #include <asm/apic.h> #include <asm/pci_x86.h> @@ -65,7 +65,7 @@ static int __init add_bus_probe(void) return of_platform_bus_probe(NULL, ce4100_ids, NULL); } -module_init(add_bus_probe); +device_initcall(add_bus_probe); #ifdef CONFIG_PCI struct device_node *pcibios_get_phb_of_node(struct pci_bus *bus) @@ -196,38 +196,31 @@ static struct of_ioapic_type of_ioapic_type[] = }, }; -static int ioapic_xlate(struct irq_domain *domain, - struct device_node *controller, - const u32 *intspec, u32 intsize, - irq_hw_number_t *out_hwirq, u32 *out_type) +static int dt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { + struct of_phandle_args *irq_data = (void *)arg; struct of_ioapic_type *it; - u32 line, idx, gsi; + struct irq_alloc_info tmp; - if (WARN_ON(intsize < 2)) + if (WARN_ON(irq_data->args_count < 2)) return -EINVAL; - - line = intspec[0]; - - if (intspec[1] >= ARRAY_SIZE(of_ioapic_type)) + if (irq_data->args[1] >= ARRAY_SIZE(of_ioapic_type)) return -EINVAL; - it = &of_ioapic_type[intspec[1]]; + it = &of_ioapic_type[irq_data->args[1]]; + ioapic_set_alloc_attr(&tmp, NUMA_NO_NODE, it->trigger, it->polarity); + tmp.ioapic_id = mpc_ioapic_id(mp_irqdomain_ioapic_idx(domain)); + tmp.ioapic_pin = irq_data->args[0]; - idx = (u32)(long)domain->host_data; - gsi = mp_pin_to_gsi(idx, line); - if (mp_set_gsi_attr(gsi, it->trigger, it->polarity, cpu_to_node(0))) - return -EBUSY; - - *out_hwirq = line; - *out_type = it->out_type; - return 0; + return mp_irqdomain_alloc(domain, virq, nr_irqs, &tmp); } -const struct irq_domain_ops ioapic_irq_domain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, - .xlate = ioapic_xlate, +static const struct irq_domain_ops ioapic_irq_domain_ops = { + .alloc = dt_irqdomain_alloc, + .free = mp_irqdomain_free, + .activate = mp_irqdomain_activate, + .deactivate = mp_irqdomain_deactivate, }; static void __init dtb_add_ioapic(struct device_node *dn) diff --git a/kernel/arch/x86/kernel/e820.c b/kernel/arch/x86/kernel/e820.c index e2ce85db2..569c1e4f9 100644 --- a/kernel/arch/x86/kernel/e820.c +++ b/kernel/arch/x86/kernel/e820.c @@ -149,6 +149,7 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PMEM: case E820_PRAM: printk(KERN_CONT "persistent (type %u)", type); break; @@ -910,7 +911,7 @@ void __init finish_e820_parsing(void) } } -static inline const char *e820_type_to_string(int e820_type) +static const char *e820_type_to_string(int e820_type) { switch (e820_type) { case E820_RESERVED_KERN: @@ -918,11 +919,32 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent RAM"; + case E820_PRAM: return "Persistent Memory (legacy)"; + case E820_PMEM: return "Persistent Memory"; default: return "reserved"; } } +static bool do_mark_busy(u32 type, struct resource *res) +{ + /* this is the legacy bios/dos rom-shadow + mmio region */ + if (res->start < (1ULL<<20)) + return true; + + /* + * Treat persistent memory like device memory, i.e. reserve it + * for exclusive use of a driver + */ + switch (type) { + case E820_RESERVED: + case E820_PRAM: + case E820_PMEM: + return false; + default: + return true; + } +} + /* * Mark e820 reserved areas as busy for the resource manager. */ @@ -952,9 +974,7 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (((e820.map[i].type != E820_RESERVED) && - (e820.map[i].type != E820_PRAM)) || - res->start < (1ULL<<20)) { + if (do_mark_busy(e820.map[i].type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } @@ -1123,7 +1143,8 @@ void __init memblock_find_dma_reserve(void) nr_pages += end_pfn - start_pfn; } - for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) { + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) { start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); if (start_pfn < end_pfn) diff --git a/kernel/arch/x86/kernel/early-quirks.c b/kernel/arch/x86/kernel/early-quirks.c index fe9f0b79a..db9a675e7 100644 --- a/kernel/arch/x86/kernel/early-quirks.c +++ b/kernel/arch/x86/kernel/early-quirks.c @@ -546,6 +546,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_BDW_D_IDS(&gen8_stolen_funcs), INTEL_CHV_IDS(&chv_stolen_funcs), INTEL_SKL_IDS(&gen9_stolen_funcs), + INTEL_BXT_IDS(&gen9_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) @@ -583,7 +584,7 @@ static void __init intel_graphics_stolen(int num, int slot, int func) static void __init force_disable_hpet(int num, int slot, int func) { #ifdef CONFIG_HPET_TIMER - boot_hpet_disable = 1; + boot_hpet_disable = true; pr_info("x86/hpet: Will disable the HPET for this platform because it's not reliable\n"); #endif } @@ -627,8 +628,12 @@ static struct chipset early_qrk[] __initdata = { { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID, QFLAG_APPLY_ONCE, intel_graphics_stolen }, /* - * HPET on current version of Baytrail platform has accuracy - * problems, disable it for now: + * HPET on the current version of the Baytrail platform has accuracy + * problems: it will halt in deep idle state - so we disable it. + * + * More details can be found in section 18.10.1.3 of the datasheet: + * + * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/atom-z8000-datasheet-vol-1.pdf */ { PCI_VENDOR_ID_INTEL, 0x0f00, PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet}, diff --git a/kernel/arch/x86/kernel/early_printk.c b/kernel/arch/x86/kernel/early_printk.c index 89427d8d4..21bf92490 100644 --- a/kernel/arch/x86/kernel/early_printk.c +++ b/kernel/arch/x86/kernel/early_printk.c @@ -175,7 +175,9 @@ static __init void early_serial_init(char *s) } if (*s) { - if (kstrtoul(s, 0, &baud) < 0 || baud == 0) + baud = simple_strtoull(s, &e, 0); + + if (baud == 0 || s == e) baud = DEFAULT_BAUD; } @@ -193,14 +195,14 @@ static __init void early_serial_init(char *s) #ifdef CONFIG_PCI static void mem32_serial_out(unsigned long addr, int offset, int value) { - u32 *vaddr = (u32 *)addr; + u32 __iomem *vaddr = (u32 __iomem *)addr; /* shift implied by pointer type */ writel(value, vaddr + offset); } static unsigned int mem32_serial_in(unsigned long addr, int offset) { - u32 *vaddr = (u32 *)addr; + u32 __iomem *vaddr = (u32 __iomem *)addr; /* shift implied by pointer type */ return readl(vaddr + offset); } @@ -314,7 +316,7 @@ static struct console early_serial_console = { .index = -1, }; -static inline void early_console_register(struct console *con, int keep_early) +static void early_console_register(struct console *con, int keep_early) { if (con->index != -1) { printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", diff --git a/kernel/arch/x86/kernel/entry_32.S b/kernel/arch/x86/kernel/entry_32.S deleted file mode 100644 index 8612b314a..000000000 --- a/kernel/arch/x86/kernel/entry_32.S +++ /dev/null @@ -1,1417 +0,0 @@ -/* - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -/* - * entry.S contains the system-call and fault low-level handling routines. - * This also contains the timer-interrupt handler, as well as all interrupts - * and faults that can result in a task-switch. - * - * NOTE: This code handles signal-recognition, which happens every time - * after a timer-interrupt and after each system call. - * - * I changed all the .align's to 4 (16 byte alignment), as that's faster - * on a 486. - * - * Stack layout in 'syscall_exit': - * ptrace needs to have all regs on the stack. - * if the order here is changed, it needs to be - * updated in fork.c:copy_process, signal.c:do_signal, - * ptrace.c and ptrace.h - * - * 0(%esp) - %ebx - * 4(%esp) - %ecx - * 8(%esp) - %edx - * C(%esp) - %esi - * 10(%esp) - %edi - * 14(%esp) - %ebp - * 18(%esp) - %eax - * 1C(%esp) - %ds - * 20(%esp) - %es - * 24(%esp) - %fs - * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS - * 2C(%esp) - orig_eax - * 30(%esp) - %eip - * 34(%esp) - %cs - * 38(%esp) - %eflags - * 3C(%esp) - %oldesp - * 40(%esp) - %oldss - * - * "current" is in register %ebx during any slow entries. - */ - -#include <linux/linkage.h> -#include <linux/err.h> -#include <asm/thread_info.h> -#include <asm/irqflags.h> -#include <asm/errno.h> -#include <asm/segment.h> -#include <asm/smp.h> -#include <asm/page_types.h> -#include <asm/percpu.h> -#include <asm/dwarf2.h> -#include <asm/processor-flags.h> -#include <asm/ftrace.h> -#include <asm/irq_vectors.h> -#include <asm/cpufeature.h> -#include <asm/alternative-asm.h> -#include <asm/asm.h> -#include <asm/smap.h> - -/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ -#include <linux/elf-em.h> -#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) -#define __AUDIT_ARCH_LE 0x40000000 - -#ifndef CONFIG_AUDITSYSCALL -#define sysenter_audit syscall_trace_entry -#define sysexit_audit syscall_exit_work -#endif - - .section .entry.text, "ax" - -/* - * We use macros for low-level operations which need to be overridden - * for paravirtualization. The following will never clobber any registers: - * INTERRUPT_RETURN (aka. "iret") - * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") - * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). - * - * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must - * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). - * Allowing a register to be clobbered can shrink the paravirt replacement - * enough to patch inline, increasing performance. - */ - -#ifdef CONFIG_PREEMPT -#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF -#else -#define preempt_stop(clobbers) -#define resume_kernel restore_all -#endif - -.macro TRACE_IRQS_IRET -#ifdef CONFIG_TRACE_IRQFLAGS - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off? - jz 1f - TRACE_IRQS_ON -1: -#endif -.endm - -/* - * User gs save/restore - * - * %gs is used for userland TLS and kernel only uses it for stack - * canary which is required to be at %gs:20 by gcc. Read the comment - * at the top of stackprotector.h for more info. - * - * Local labels 98 and 99 are used. - */ -#ifdef CONFIG_X86_32_LAZY_GS - - /* unfortunately push/pop can't be no-op */ -.macro PUSH_GS - pushl_cfi $0 -.endm -.macro POP_GS pop=0 - addl $(4 + \pop), %esp - CFI_ADJUST_CFA_OFFSET -(4 + \pop) -.endm -.macro POP_GS_EX -.endm - - /* all the rest are no-op */ -.macro PTGS_TO_GS -.endm -.macro PTGS_TO_GS_EX -.endm -.macro GS_TO_REG reg -.endm -.macro REG_TO_PTGS reg -.endm -.macro SET_KERNEL_GS reg -.endm - -#else /* CONFIG_X86_32_LAZY_GS */ - -.macro PUSH_GS - pushl_cfi %gs - /*CFI_REL_OFFSET gs, 0*/ -.endm - -.macro POP_GS pop=0 -98: popl_cfi %gs - /*CFI_RESTORE gs*/ - .if \pop <> 0 - add $\pop, %esp - CFI_ADJUST_CFA_OFFSET -\pop - .endif -.endm -.macro POP_GS_EX -.pushsection .fixup, "ax" -99: movl $0, (%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b,99b) -.endm - -.macro PTGS_TO_GS -98: mov PT_GS(%esp), %gs -.endm -.macro PTGS_TO_GS_EX -.pushsection .fixup, "ax" -99: movl $0, PT_GS(%esp) - jmp 98b -.popsection - _ASM_EXTABLE(98b,99b) -.endm - -.macro GS_TO_REG reg - movl %gs, \reg - /*CFI_REGISTER gs, \reg*/ -.endm -.macro REG_TO_PTGS reg - movl \reg, PT_GS(%esp) - /*CFI_REL_OFFSET gs, PT_GS*/ -.endm -.macro SET_KERNEL_GS reg - movl $(__KERNEL_STACK_CANARY), \reg - movl \reg, %gs -.endm - -#endif /* CONFIG_X86_32_LAZY_GS */ - -.macro SAVE_ALL - cld - PUSH_GS - pushl_cfi %fs - /*CFI_REL_OFFSET fs, 0;*/ - pushl_cfi %es - /*CFI_REL_OFFSET es, 0;*/ - pushl_cfi %ds - /*CFI_REL_OFFSET ds, 0;*/ - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ebp - CFI_REL_OFFSET ebp, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 - movl $(__USER_DS), %edx - movl %edx, %ds - movl %edx, %es - movl $(__KERNEL_PERCPU), %edx - movl %edx, %fs - SET_KERNEL_GS %edx -.endm - -.macro RESTORE_INT_REGS - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %ecx - CFI_RESTORE ecx - popl_cfi %edx - CFI_RESTORE edx - popl_cfi %esi - CFI_RESTORE esi - popl_cfi %edi - CFI_RESTORE edi - popl_cfi %ebp - CFI_RESTORE ebp - popl_cfi %eax - CFI_RESTORE eax -.endm - -.macro RESTORE_REGS pop=0 - RESTORE_INT_REGS -1: popl_cfi %ds - /*CFI_RESTORE ds;*/ -2: popl_cfi %es - /*CFI_RESTORE es;*/ -3: popl_cfi %fs - /*CFI_RESTORE fs;*/ - POP_GS \pop -.pushsection .fixup, "ax" -4: movl $0, (%esp) - jmp 1b -5: movl $0, (%esp) - jmp 2b -6: movl $0, (%esp) - jmp 3b -.popsection - _ASM_EXTABLE(1b,4b) - _ASM_EXTABLE(2b,5b) - _ASM_EXTABLE(3b,6b) - POP_GS_EX -.endm - -.macro RING0_INT_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 3*4 - /*CFI_OFFSET cs, -2*4;*/ - CFI_OFFSET eip, -3*4 -.endm - -.macro RING0_EC_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 4*4 - /*CFI_OFFSET cs, -2*4;*/ - CFI_OFFSET eip, -3*4 -.endm - -.macro RING0_PTREGS_FRAME - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, PT_OLDESP-PT_EBX - /*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/ - CFI_OFFSET eip, PT_EIP-PT_OLDESP - /*CFI_OFFSET es, PT_ES-PT_OLDESP;*/ - /*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/ - CFI_OFFSET eax, PT_EAX-PT_OLDESP - CFI_OFFSET ebp, PT_EBP-PT_OLDESP - CFI_OFFSET edi, PT_EDI-PT_OLDESP - CFI_OFFSET esi, PT_ESI-PT_OLDESP - CFI_OFFSET edx, PT_EDX-PT_OLDESP - CFI_OFFSET ecx, PT_ECX-PT_OLDESP - CFI_OFFSET ebx, PT_EBX-PT_OLDESP -.endm - -ENTRY(ret_from_fork) - CFI_STARTPROC - pushl_cfi %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl_cfi %eax - pushl_cfi $0x0202 # Reset kernel eflags - popfl_cfi - jmp syscall_exit - CFI_ENDPROC -END(ret_from_fork) - -ENTRY(ret_from_kernel_thread) - CFI_STARTPROC - pushl_cfi %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl_cfi %eax - pushl_cfi $0x0202 # Reset kernel eflags - popfl_cfi - movl PT_EBP(%esp),%eax - call *PT_EBX(%esp) - movl $0,PT_EAX(%esp) - jmp syscall_exit - CFI_ENDPROC -ENDPROC(ret_from_kernel_thread) - -/* - * Return to user mode is not as complex as all this looks, - * but we want the default path for a system call return to - * go as quickly as possible which is why some of this is - * less clear than it otherwise should be. - */ - - # userspace resumption stub bypassing syscall exit tracing - ALIGN - RING0_PTREGS_FRAME -ret_from_exception: - preempt_stop(CLBR_ANY) -ret_from_intr: - GET_THREAD_INFO(%ebp) -#ifdef CONFIG_VM86 - movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax -#else - /* - * We can be coming here from child spawned by kernel_thread(). - */ - movl PT_CS(%esp), %eax - andl $SEGMENT_RPL_MASK, %eax -#endif - cmpl $USER_RPL, %eax - jb resume_kernel # not returning to v8086 or userspace - -ENTRY(resume_userspace) - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done on - # int/exception return? - jne work_pending - jmp restore_all -END(ret_from_exception) - -#ifdef CONFIG_PREEMPT -ENTRY(resume_kernel) - DISABLE_INTERRUPTS(CLBR_ANY) -need_resched: - # preempt count == 0 + NEED_RS set? - cmpl $0,PER_CPU_VAR(__preempt_count) -#ifndef CONFIG_PREEMPT_LAZY - jnz restore_all -#else - jz test_int_off - - # atleast preempt count == 0 ? - cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) - jne restore_all - - cmpl $0,TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? - jnz restore_all - - testl $_TIF_NEED_RESCHED_LAZY, TI_flags(%ebp) - jz restore_all -test_int_off: -#endif - testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? - jz restore_all - call preempt_schedule_irq - jmp need_resched -END(resume_kernel) -#endif - CFI_ENDPROC - -/* SYSENTER_RETURN points to after the "sysenter" instruction in - the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ - - # sysenter call handler stub -ENTRY(ia32_sysenter_target) - CFI_STARTPROC simple - CFI_SIGNAL_FRAME - CFI_DEF_CFA esp, 0 - CFI_REGISTER esp, ebp - movl TSS_sysenter_sp0(%esp),%esp -sysenter_past_esp: - /* - * Interrupts are disabled here, but we can't trace it until - * enough kernel state to call TRACE_IRQS_OFF can be called - but - * we immediately enable interrupts at that point anyway. - */ - pushl_cfi $__USER_DS - /*CFI_REL_OFFSET ss, 0*/ - pushl_cfi %ebp - CFI_REL_OFFSET esp, 0 - pushfl_cfi - orl $X86_EFLAGS_IF, (%esp) - pushl_cfi $__USER_CS - /*CFI_REL_OFFSET cs, 0*/ - /* - * Push current_thread_info()->sysenter_return to the stack. - * A tiny bit of offset fixup is necessary: TI_sysenter_return - * is relative to thread_info, which is at the bottom of the - * kernel stack page. 4*4 means the 4 words pushed above; - * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; - * and THREAD_SIZE takes us to the bottom. - */ - pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) - CFI_REL_OFFSET eip, 0 - - pushl_cfi %eax - SAVE_ALL - ENABLE_INTERRUPTS(CLBR_NONE) - -/* - * Load the potential sixth argument from user stack. - * Careful about security. - */ - cmpl $__PAGE_OFFSET-3,%ebp - jae syscall_fault - ASM_STAC -1: movl (%ebp),%ebp - ASM_CLAC - movl %ebp,PT_EBP(%esp) - _ASM_EXTABLE(1b,syscall_fault) - - GET_THREAD_INFO(%ebp) - - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz sysenter_audit -sysenter_do_call: - cmpl $(NR_syscalls), %eax - jae sysenter_badsys - call *sys_call_table(,%eax,4) -sysenter_after_call: - movl %eax,PT_EAX(%esp) - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx - jnz sysexit_audit -sysenter_exit: -/* if something modifies registers it must also disable sysexit */ - movl PT_EIP(%esp), %edx - movl PT_OLDESP(%esp), %ecx - xorl %ebp,%ebp - TRACE_IRQS_ON -1: mov PT_FS(%esp), %fs - PTGS_TO_GS - ENABLE_INTERRUPTS_SYSEXIT - -#ifdef CONFIG_AUDITSYSCALL -sysenter_audit: - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) - jnz syscall_trace_entry - /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ - movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ - /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ - pushl_cfi PT_ESI(%esp) /* a3: 5th arg */ - pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */ - call __audit_syscall_entry - popl_cfi %ecx /* get that remapped edx off the stack */ - popl_cfi %ecx /* get that remapped esi off the stack */ - movl PT_EAX(%esp),%eax /* reload syscall number */ - jmp sysenter_do_call - -sysexit_audit: - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) - movl %eax,%edx /* second arg, syscall return value */ - cmpl $-MAX_ERRNO,%eax /* is it an error ? */ - setbe %al /* 1 if so, 0 if not */ - movzbl %al,%eax /* zero-extend that */ - call __audit_syscall_exit - DISABLE_INTERRUPTS(CLBR_ANY) - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jnz syscall_exit_work - movl PT_EAX(%esp),%eax /* reload syscall return value */ - jmp sysenter_exit -#endif - - CFI_ENDPROC -.pushsection .fixup,"ax" -2: movl $0,PT_FS(%esp) - jmp 1b -.popsection - _ASM_EXTABLE(1b,2b) - PTGS_TO_GS_EX -ENDPROC(ia32_sysenter_target) - - # system call handler stub -ENTRY(system_call) - RING0_INT_FRAME # can't unwind into user space anyway - ASM_CLAC - pushl_cfi %eax # save orig_eax - SAVE_ALL - GET_THREAD_INFO(%ebp) - # system call tracing in operation / emulation - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) - jnz syscall_trace_entry - cmpl $(NR_syscalls), %eax - jae syscall_badsys -syscall_call: - call *sys_call_table(,%eax,4) -syscall_after_call: - movl %eax,PT_EAX(%esp) # store the return value -syscall_exit: - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - testl $_TIF_ALLWORK_MASK, %ecx # current->work - jnz syscall_exit_work - -restore_all: - TRACE_IRQS_IRET -restore_all_notrace: -#ifdef CONFIG_X86_ESPFIX32 - movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS - # Warning: PT_OLDSS(%esp) contains the wrong/random values if we - # are returning to the kernel. - # See comments in process.c:copy_thread() for details. - movb PT_OLDSS(%esp), %ah - movb PT_CS(%esp), %al - andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax - cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax - CFI_REMEMBER_STATE - je ldt_ss # returning to user-space with LDT SS -#endif -restore_nocheck: - RESTORE_REGS 4 # skip orig_eax/error_code -irq_return: - INTERRUPT_RETURN -.section .fixup,"ax" -ENTRY(iret_exc) - pushl $0 # no error code - pushl $do_iret_error - jmp error_code -.previous - _ASM_EXTABLE(irq_return,iret_exc) - -#ifdef CONFIG_X86_ESPFIX32 - CFI_RESTORE_STATE -ldt_ss: -#ifdef CONFIG_PARAVIRT - /* - * The kernel can't run on a non-flat stack if paravirt mode - * is active. Rather than try to fixup the high bits of - * ESP, bypass this code entirely. This may break DOSemu - * and/or Wine support in a paravirt VM, although the option - * is still available to implement the setting of the high - * 16-bits in the INTERRUPT_RETURN paravirt-op. - */ - cmpl $0, pv_info+PARAVIRT_enabled - jne restore_nocheck -#endif - -/* - * Setup and switch to ESPFIX stack - * - * We're returning to userspace with a 16 bit stack. The CPU will not - * restore the high word of ESP for us on executing iret... This is an - * "official" bug of all the x86-compatible CPUs, which we can work - * around to make dosemu and wine happy. We do this by preloading the - * high word of ESP with the high word of the userspace ESP while - * compensating for the offset by changing to the ESPFIX segment with - * a base address that matches for the difference. - */ -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) - mov %esp, %edx /* load kernel esp */ - mov PT_OLDESP(%esp), %eax /* load userspace esp */ - mov %dx, %ax /* eax: new kernel esp */ - sub %eax, %edx /* offset (low word is 0) */ - shr $16, %edx - mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ - mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ - pushl_cfi $__ESPFIX_SS - pushl_cfi %eax /* new kernel esp */ - /* Disable interrupts, but do not irqtrace this section: we - * will soon execute iret and the tracer was already set to - * the irqstate after the iret */ - DISABLE_INTERRUPTS(CLBR_EAX) - lss (%esp), %esp /* switch to espfix segment */ - CFI_ADJUST_CFA_OFFSET -8 - jmp restore_nocheck -#endif - CFI_ENDPROC -ENDPROC(system_call) - - # perform work that needs to be done immediately before resumption - ALIGN - RING0_PTREGS_FRAME # can't unwind into user space anyway -work_pending: - testl $_TIF_NEED_RESCHED_MASK, %ecx - jz work_notifysig -work_resched: - call schedule - LOCKDEP_SYS_EXIT - DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - TRACE_IRQS_OFF - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done other - # than syscall tracing? - jz restore_all - testl $_TIF_NEED_RESCHED_MASK, %ecx - jnz work_resched - -work_notifysig: # deal with pending signals and - # notify-resume requests -#ifdef CONFIG_VM86 - testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) - movl %esp, %eax - jnz work_notifysig_v86 # returning to kernel-space or - # vm86-space -1: -#else - movl %esp, %eax -#endif - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_NONE) - movb PT_CS(%esp), %bl - andb $SEGMENT_RPL_MASK, %bl - cmpb $USER_RPL, %bl - jb resume_kernel - xorl %edx, %edx - call do_notify_resume - jmp resume_userspace - -#ifdef CONFIG_VM86 - ALIGN -work_notifysig_v86: - pushl_cfi %ecx # save ti_flags for do_notify_resume - call save_v86_state # %eax contains pt_regs pointer - popl_cfi %ecx - movl %eax, %esp - jmp 1b -#endif -END(work_pending) - - # perform syscall exit tracing - ALIGN -syscall_trace_entry: - movl $-ENOSYS,PT_EAX(%esp) - movl %esp, %eax - call syscall_trace_enter - /* What it returned is what we'll actually use. */ - cmpl $(NR_syscalls), %eax - jnae syscall_call - jmp syscall_exit -END(syscall_trace_entry) - - # perform syscall exit tracing - ALIGN -syscall_exit_work: - testl $_TIF_WORK_SYSCALL_EXIT, %ecx - jz work_pending - TRACE_IRQS_ON - ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call - # schedule() instead - movl %esp, %eax - call syscall_trace_leave - jmp resume_userspace -END(syscall_exit_work) - CFI_ENDPROC - - RING0_INT_FRAME # can't unwind into user space anyway -syscall_fault: - ASM_CLAC - GET_THREAD_INFO(%ebp) - movl $-EFAULT,PT_EAX(%esp) - jmp resume_userspace -END(syscall_fault) - -syscall_badsys: - movl $-ENOSYS,%eax - jmp syscall_after_call -END(syscall_badsys) - -sysenter_badsys: - movl $-ENOSYS,%eax - jmp sysenter_after_call -END(sysenter_badsys) - CFI_ENDPROC - -.macro FIXUP_ESPFIX_STACK -/* - * Switch back for ESPFIX stack to the normal zerobased stack - * - * We can't call C functions using the ESPFIX stack. This code reads - * the high word of the segment base from the GDT and swiches to the - * normal stack and adjusts ESP with the matching offset. - */ -#ifdef CONFIG_X86_ESPFIX32 - /* fixup the stack */ - mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ - mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ - shl $16, %eax - addl %esp, %eax /* the adjusted stack pointer */ - pushl_cfi $__KERNEL_DS - pushl_cfi %eax - lss (%esp), %esp /* switch to the normal stack segment */ - CFI_ADJUST_CFA_OFFSET -8 -#endif -.endm -.macro UNWIND_ESPFIX_STACK -#ifdef CONFIG_X86_ESPFIX32 - movl %ss, %eax - /* see if on espfix stack */ - cmpw $__ESPFIX_SS, %ax - jne 27f - movl $__KERNEL_DS, %eax - movl %eax, %ds - movl %eax, %es - /* switch to normal stack */ - FIXUP_ESPFIX_STACK -27: -#endif -.endm - -/* - * Build the entry stubs with some assembler magic. - * We pack 1 stub into every 8-byte block. - */ - .align 8 -ENTRY(irq_entries_start) - RING0_INT_FRAME - vector=FIRST_EXTERNAL_VECTOR - .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) - pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ - vector=vector+1 - jmp common_interrupt - CFI_ADJUST_CFA_OFFSET -4 - .align 8 - .endr -END(irq_entries_start) - -/* - * the CPU automatically disables interrupts when executing an IRQ vector, - * so IRQ-flags tracing has to follow that: - */ - .p2align CONFIG_X86_L1_CACHE_SHIFT -common_interrupt: - ASM_CLAC - addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ - SAVE_ALL - TRACE_IRQS_OFF - movl %esp,%eax - call do_IRQ - jmp ret_from_intr -ENDPROC(common_interrupt) - CFI_ENDPROC - -#define BUILD_INTERRUPT3(name, nr, fn) \ -ENTRY(name) \ - RING0_INT_FRAME; \ - ASM_CLAC; \ - pushl_cfi $~(nr); \ - SAVE_ALL; \ - TRACE_IRQS_OFF \ - movl %esp,%eax; \ - call fn; \ - jmp ret_from_intr; \ - CFI_ENDPROC; \ -ENDPROC(name) - - -#ifdef CONFIG_TRACING -#define TRACE_BUILD_INTERRUPT(name, nr) \ - BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) -#else -#define TRACE_BUILD_INTERRUPT(name, nr) -#endif - -#define BUILD_INTERRUPT(name, nr) \ - BUILD_INTERRUPT3(name, nr, smp_##name); \ - TRACE_BUILD_INTERRUPT(name, nr) - -/* The include is where all of the SMP etc. interrupts come from */ -#include <asm/entry_arch.h> - -ENTRY(coprocessor_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_coprocessor_error - jmp error_code - CFI_ENDPROC -END(coprocessor_error) - -ENTRY(simd_coprocessor_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 -#ifdef CONFIG_X86_INVD_BUG - /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ - ALTERNATIVE "pushl_cfi $do_general_protection", \ - "pushl $do_simd_coprocessor_error", \ - X86_FEATURE_XMM -#else - pushl_cfi $do_simd_coprocessor_error -#endif - jmp error_code - CFI_ENDPROC -END(simd_coprocessor_error) - -ENTRY(device_not_available) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $-1 # mark this as an int - pushl_cfi $do_device_not_available - jmp error_code - CFI_ENDPROC -END(device_not_available) - -#ifdef CONFIG_PARAVIRT -ENTRY(native_iret) - iret - _ASM_EXTABLE(native_iret, iret_exc) -END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) -#endif - -ENTRY(overflow) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_overflow - jmp error_code - CFI_ENDPROC -END(overflow) - -ENTRY(bounds) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_bounds - jmp error_code - CFI_ENDPROC -END(bounds) - -ENTRY(invalid_op) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_invalid_op - jmp error_code - CFI_ENDPROC -END(invalid_op) - -ENTRY(coprocessor_segment_overrun) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_coprocessor_segment_overrun - jmp error_code - CFI_ENDPROC -END(coprocessor_segment_overrun) - -ENTRY(invalid_TSS) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_invalid_TSS - jmp error_code - CFI_ENDPROC -END(invalid_TSS) - -ENTRY(segment_not_present) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_segment_not_present - jmp error_code - CFI_ENDPROC -END(segment_not_present) - -ENTRY(stack_segment) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_stack_segment - jmp error_code - CFI_ENDPROC -END(stack_segment) - -ENTRY(alignment_check) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_alignment_check - jmp error_code - CFI_ENDPROC -END(alignment_check) - -ENTRY(divide_error) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 # no error code - pushl_cfi $do_divide_error - jmp error_code - CFI_ENDPROC -END(divide_error) - -#ifdef CONFIG_X86_MCE -ENTRY(machine_check) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi machine_check_vector - jmp error_code - CFI_ENDPROC -END(machine_check) -#endif - -ENTRY(spurious_interrupt_bug) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $0 - pushl_cfi $do_spurious_interrupt_bug - jmp error_code - CFI_ENDPROC -END(spurious_interrupt_bug) - -#ifdef CONFIG_XEN -/* Xen doesn't set %esp to be precisely what the normal sysenter - entrypoint expects, so fix it up before using the normal path. */ -ENTRY(xen_sysenter_target) - RING0_INT_FRAME - addl $5*4, %esp /* remove xen-provided frame */ - CFI_ADJUST_CFA_OFFSET -5*4 - jmp sysenter_past_esp - CFI_ENDPROC - -ENTRY(xen_hypervisor_callback) - CFI_STARTPROC - pushl_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - TRACE_IRQS_OFF - - /* Check to see if we got the event in the critical - region in xen_iret_direct, after we've reenabled - events and checked for pending events. This simulates - iret instruction's behaviour where it delivers a - pending interrupt when enabling interrupts. */ - movl PT_EIP(%esp),%eax - cmpl $xen_iret_start_crit,%eax - jb 1f - cmpl $xen_iret_end_crit,%eax - jae 1f - - jmp xen_iret_crit_fixup - -ENTRY(xen_do_upcall) -1: mov %esp, %eax - call xen_evtchn_do_upcall -#ifndef CONFIG_PREEMPT - call xen_maybe_preempt_hcall -#endif - jmp ret_from_intr - CFI_ENDPROC -ENDPROC(xen_hypervisor_callback) - -# Hypervisor uses this for application faults while it executes. -# We get here for two reasons: -# 1. Fault while reloading DS, ES, FS or GS -# 2. Fault while executing IRET -# Category 1 we fix up by reattempting the load, and zeroing the segment -# register if the load fails. -# Category 2 we fix up by jumping to do_iret_error. We cannot use the -# normal Linux return path in this case because if we use the IRET hypercall -# to pop the stack frame we end up in an infinite loop of failsafe callbacks. -# We distinguish between categories by maintaining a status value in EAX. -ENTRY(xen_failsafe_callback) - CFI_STARTPROC - pushl_cfi %eax - movl $1,%eax -1: mov 4(%esp),%ds -2: mov 8(%esp),%es -3: mov 12(%esp),%fs -4: mov 16(%esp),%gs - /* EAX == 0 => Category 1 (Bad segment) - EAX != 0 => Category 2 (Bad IRET) */ - testl %eax,%eax - popl_cfi %eax - lea 16(%esp),%esp - CFI_ADJUST_CFA_OFFSET -16 - jz 5f - jmp iret_exc -5: pushl_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - jmp ret_from_exception - CFI_ENDPROC - -.section .fixup,"ax" -6: xorl %eax,%eax - movl %eax,4(%esp) - jmp 1b -7: xorl %eax,%eax - movl %eax,8(%esp) - jmp 2b -8: xorl %eax,%eax - movl %eax,12(%esp) - jmp 3b -9: xorl %eax,%eax - movl %eax,16(%esp) - jmp 4b -.previous - _ASM_EXTABLE(1b,6b) - _ASM_EXTABLE(2b,7b) - _ASM_EXTABLE(3b,8b) - _ASM_EXTABLE(4b,9b) -ENDPROC(xen_failsafe_callback) - -BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - xen_evtchn_do_upcall) - -#endif /* CONFIG_XEN */ - -#if IS_ENABLED(CONFIG_HYPERV) - -BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, - hyperv_vector_handler) - -#endif /* CONFIG_HYPERV */ - -#ifdef CONFIG_FUNCTION_TRACER -#ifdef CONFIG_DYNAMIC_FTRACE - -ENTRY(mcount) - ret -END(mcount) - -ENTRY(ftrace_caller) - pushl %eax - pushl %ecx - pushl %edx - pushl $0 /* Pass NULL as regs pointer */ - movl 4*4(%esp), %eax - movl 0x4(%ebp), %edx - movl function_trace_op, %ecx - subl $MCOUNT_INSN_SIZE, %eax - -.globl ftrace_call -ftrace_call: - call ftrace_stub - - addl $4,%esp /* skip NULL pointer */ - popl %edx - popl %ecx - popl %eax -ftrace_ret: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - jmp ftrace_stub -#endif - -.globl ftrace_stub -ftrace_stub: - ret -END(ftrace_caller) - -ENTRY(ftrace_regs_caller) - pushf /* push flags before compare (in cs location) */ - - /* - * i386 does not save SS and ESP when coming from kernel. - * Instead, to get sp, ®s->sp is used (see ptrace.h). - * Unfortunately, that means eflags must be at the same location - * as the current return ip is. We move the return ip into the - * ip location, and move flags into the return ip location. - */ - pushl 4(%esp) /* save return ip into ip slot */ - - pushl $0 /* Load 0 into orig_ax */ - pushl %gs - pushl %fs - pushl %es - pushl %ds - pushl %eax - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - pushl %ecx - pushl %ebx - - movl 13*4(%esp), %eax /* Get the saved flags */ - movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ - /* clobbering return ip */ - movl $__KERNEL_CS,13*4(%esp) - - movl 12*4(%esp), %eax /* Load ip (1st parameter) */ - subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ - movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ - pushl %esp /* Save pt_regs as 4th parameter */ - -GLOBAL(ftrace_regs_call) - call ftrace_stub - - addl $4, %esp /* Skip pt_regs */ - movl 14*4(%esp), %eax /* Move flags back into cs */ - movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ - movl 12*4(%esp), %eax /* Get return ip from regs->ip */ - movl %eax, 14*4(%esp) /* Put return ip back for ret */ - - popl %ebx - popl %ecx - popl %edx - popl %esi - popl %edi - popl %ebp - popl %eax - popl %ds - popl %es - popl %fs - popl %gs - addl $8, %esp /* Skip orig_ax and ip */ - popf /* Pop flags at end (no addl to corrupt flags) */ - jmp ftrace_ret - - popf - jmp ftrace_stub -#else /* ! CONFIG_DYNAMIC_FTRACE */ - -ENTRY(mcount) - cmpl $__PAGE_OFFSET, %esp - jb ftrace_stub /* Paging not enabled yet? */ - - cmpl $ftrace_stub, ftrace_trace_function - jnz trace -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpl $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpl $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif -.globl ftrace_stub -ftrace_stub: - ret - - /* taken from glibc */ -trace: - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - movl 0x4(%ebp), %edx - subl $MCOUNT_INSN_SIZE, %eax - - call *ftrace_trace_function - - popl %edx - popl %ecx - popl %eax - jmp ftrace_stub -END(mcount) -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FUNCTION_TRACER */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) - pushl %eax - pushl %ecx - pushl %edx - movl 0xc(%esp), %eax - lea 0x4(%ebp), %edx - movl (%ebp), %ecx - subl $MCOUNT_INSN_SIZE, %eax - call prepare_ftrace_return - popl %edx - popl %ecx - popl %eax - ret -END(ftrace_graph_caller) - -.globl return_to_handler -return_to_handler: - pushl %eax - pushl %edx - movl %ebp, %eax - call ftrace_return_to_handler - movl %eax, %ecx - popl %edx - popl %eax - jmp *%ecx -#endif - -#ifdef CONFIG_TRACING -ENTRY(trace_page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $trace_do_page_fault - jmp error_code - CFI_ENDPROC -END(trace_page_fault) -#endif - -ENTRY(page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_page_fault - ALIGN -error_code: - /* the function address is in %gs's slot on the stack */ - pushl_cfi %fs - /*CFI_REL_OFFSET fs, 0*/ - pushl_cfi %es - /*CFI_REL_OFFSET es, 0*/ - pushl_cfi %ds - /*CFI_REL_OFFSET ds, 0*/ - pushl_cfi_reg eax - pushl_cfi_reg ebp - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg edx - pushl_cfi_reg ecx - pushl_cfi_reg ebx - cld - movl $(__KERNEL_PERCPU), %ecx - movl %ecx, %fs - UNWIND_ESPFIX_STACK - GS_TO_REG %ecx - movl PT_GS(%esp), %edi # get the function address - movl PT_ORIG_EAX(%esp), %edx # get the error code - movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart - REG_TO_PTGS %ecx - SET_KERNEL_GS %ecx - movl $(__USER_DS), %ecx - movl %ecx, %ds - movl %ecx, %es - TRACE_IRQS_OFF - movl %esp,%eax # pt_regs pointer - call *%edi - jmp ret_from_exception - CFI_ENDPROC -END(page_fault) - -/* - * Debug traps and NMI can happen at the one SYSENTER instruction - * that sets up the real kernel stack. Check here, since we can't - * allow the wrong stack to be used. - * - * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have - * already pushed 3 words if it hits on the sysenter instruction: - * eflags, cs and eip. - * - * We just load the right stack, and push the three (known) values - * by hand onto the new stack - while updating the return eip past - * the instruction that would have done it for sysenter. - */ -.macro FIX_STACK offset ok label - cmpw $__KERNEL_CS, 4(%esp) - jne \ok -\label: - movl TSS_sysenter_sp0 + \offset(%esp), %esp - CFI_DEF_CFA esp, 0 - CFI_UNDEFINED eip - pushfl_cfi - pushl_cfi $__KERNEL_CS - pushl_cfi $sysenter_past_esp - CFI_REL_OFFSET eip, 0 -.endm - -ENTRY(debug) - RING0_INT_FRAME - ASM_CLAC - cmpl $ia32_sysenter_target,(%esp) - jne debug_stack_correct - FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn -debug_stack_correct: - pushl_cfi $-1 # mark this as an int - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # error code 0 - movl %esp,%eax # pt_regs pointer - call do_debug - jmp ret_from_exception - CFI_ENDPROC -END(debug) - -/* - * NMI is doubly nasty. It can happen _while_ we're handling - * a debug fault, and the debug fault hasn't yet been able to - * clear up the stack. So we first check whether we got an - * NMI on the sysenter entry path, but after that we need to - * check whether we got an NMI on the debug path where the debug - * fault happened on the sysenter path. - */ -ENTRY(nmi) - RING0_INT_FRAME - ASM_CLAC -#ifdef CONFIG_X86_ESPFIX32 - pushl_cfi %eax - movl %ss, %eax - cmpw $__ESPFIX_SS, %ax - popl_cfi %eax - je nmi_espfix_stack -#endif - cmpl $ia32_sysenter_target,(%esp) - je nmi_stack_fixup - pushl_cfi %eax - movl %esp,%eax - /* Do not access memory above the end of our stack page, - * it might not exist. - */ - andl $(THREAD_SIZE-1),%eax - cmpl $(THREAD_SIZE-20),%eax - popl_cfi %eax - jae nmi_stack_correct - cmpl $ia32_sysenter_target,12(%esp) - je nmi_debug_stack_check -nmi_stack_correct: - /* We have a RING0_INT_FRAME here */ - pushl_cfi %eax - SAVE_ALL - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_nmi - jmp restore_all_notrace - CFI_ENDPROC - -nmi_stack_fixup: - RING0_INT_FRAME - FIX_STACK 12, nmi_stack_correct, 1 - jmp nmi_stack_correct - -nmi_debug_stack_check: - /* We have a RING0_INT_FRAME here */ - cmpw $__KERNEL_CS,16(%esp) - jne nmi_stack_correct - cmpl $debug,(%esp) - jb nmi_stack_correct - cmpl $debug_esp_fix_insn,(%esp) - ja nmi_stack_correct - FIX_STACK 24, nmi_stack_correct, 1 - jmp nmi_stack_correct - -#ifdef CONFIG_X86_ESPFIX32 -nmi_espfix_stack: - /* We have a RING0_INT_FRAME here. - * - * create the pointer to lss back - */ - pushl_cfi %ss - pushl_cfi %esp - addl $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl_cfi 16(%esp) - .endr - pushl_cfi %eax - SAVE_ALL - FIXUP_ESPFIX_STACK # %eax == %esp - xorl %edx,%edx # zero error code - call do_nmi - RESTORE_REGS - lss 12+4(%esp), %esp # back to espfix stack - CFI_ADJUST_CFA_OFFSET -24 - jmp irq_return -#endif - CFI_ENDPROC -END(nmi) - -ENTRY(int3) - RING0_INT_FRAME - ASM_CLAC - pushl_cfi $-1 # mark this as an int - SAVE_ALL - TRACE_IRQS_OFF - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_int3 - jmp ret_from_exception - CFI_ENDPROC -END(int3) - -ENTRY(general_protection) - RING0_EC_FRAME - pushl_cfi $do_general_protection - jmp error_code - CFI_ENDPROC -END(general_protection) - -#ifdef CONFIG_KVM_GUEST -ENTRY(async_page_fault) - RING0_EC_FRAME - ASM_CLAC - pushl_cfi $do_async_page_fault - jmp error_code - CFI_ENDPROC -END(async_page_fault) -#endif - diff --git a/kernel/arch/x86/kernel/espfix_64.c b/kernel/arch/x86/kernel/espfix_64.c index f5d0730e7..4d38416e2 100644 --- a/kernel/arch/x86/kernel/espfix_64.c +++ b/kernel/arch/x86/kernel/espfix_64.c @@ -110,7 +110,7 @@ static void init_espfix_random(void) */ if (!arch_get_random_long(&rand)) { /* The constant is an arbitrary large prime */ - rdtscll(rand); + rand = rdtsc(); rand *= 0xc345c6b72fd16123UL; } @@ -131,25 +131,24 @@ void __init init_espfix_bsp(void) init_espfix_random(); /* The rest is the same as for any other processor */ - init_espfix_ap(); + init_espfix_ap(0); } -void init_espfix_ap(void) +void init_espfix_ap(int cpu) { - unsigned int cpu, page; + unsigned int page; unsigned long addr; pud_t pud, *pud_p; pmd_t pmd, *pmd_p; pte_t pte, *pte_p; - int n; + int n, node; void *stack_page; pteval_t ptemask; /* We only have to do this once... */ - if (likely(this_cpu_read(espfix_stack))) + if (likely(per_cpu(espfix_stack, cpu))) return; /* Already initialized */ - cpu = smp_processor_id(); addr = espfix_base_addr(cpu); page = cpu/ESPFIX_STACKS_PER_PAGE; @@ -165,12 +164,15 @@ void init_espfix_ap(void) if (stack_page) goto unlock_done; + node = cpu_to_node(cpu); ptemask = __supported_pte_mask; pud_p = &espfix_pud_page[pud_index(addr)]; pud = *pud_p; if (!pud_present(pud)) { - pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); + + pmd_p = (pmd_t *)page_address(page); pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PUD_CLONES; n++) @@ -180,7 +182,9 @@ void init_espfix_ap(void) pmd_p = pmd_offset(&pud, addr); pmd = *pmd_p; if (!pmd_present(pmd)) { - pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0); + + pte_p = (pte_t *)page_address(page); pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); for (n = 0; n < ESPFIX_PMD_CLONES; n++) @@ -188,7 +192,7 @@ void init_espfix_ap(void) } pte_p = pte_offset_kernel(&pmd, addr); - stack_page = (void *)__get_free_page(GFP_KERNEL); + stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0)); pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); for (n = 0; n < ESPFIX_PTE_CLONES; n++) set_pte(&pte_p[n*PTE_STRIDE], pte); @@ -199,7 +203,7 @@ void init_espfix_ap(void) unlock_done: mutex_unlock(&espfix_init_mutex); done: - this_cpu_write(espfix_stack, addr); - this_cpu_write(espfix_waddr, (unsigned long)stack_page - + (addr & ~PAGE_MASK)); + per_cpu(espfix_stack, cpu) = addr; + per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page + + (addr & ~PAGE_MASK); } diff --git a/kernel/arch/x86/kernel/fpu/Makefile b/kernel/arch/x86/kernel/fpu/Makefile new file mode 100644 index 000000000..68279efb8 --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/Makefile @@ -0,0 +1,5 @@ +# +# Build rules for the FPU support code: +# + +obj-y += init.o bugs.o core.o regset.o signal.o xstate.o diff --git a/kernel/arch/x86/kernel/fpu/bugs.c b/kernel/arch/x86/kernel/fpu/bugs.c new file mode 100644 index 000000000..dd9ca9b60 --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/bugs.c @@ -0,0 +1,71 @@ +/* + * x86 FPU bug checks: + */ +#include <asm/fpu/internal.h> + +/* + * Boot time CPU/FPU FDIV bug detection code: + */ + +static double __initdata x = 4195835.0; +static double __initdata y = 3145727.0; + +/* + * This used to check for exceptions.. + * However, it turns out that to support that, + * the XMM trap handlers basically had to + * be buggy. So let's have a correct XMM trap + * handler, and forget about printing out + * some status at boot. + * + * We should really only care about bugs here + * anyway. Not features. + */ +static void __init check_fpu(void) +{ + u32 cr0_saved; + s32 fdiv_bug; + + /* We might have CR0::TS set already, clear it: */ + cr0_saved = read_cr0(); + write_cr0(cr0_saved & ~X86_CR0_TS); + + kernel_fpu_begin(); + + /* + * trap_init() enabled FXSR and company _before_ testing for FP + * problems here. + * + * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug + */ + __asm__("fninit\n\t" + "fldl %1\n\t" + "fdivl %2\n\t" + "fmull %2\n\t" + "fldl %1\n\t" + "fsubp %%st,%%st(1)\n\t" + "fistpl %0\n\t" + "fwait\n\t" + "fninit" + : "=m" (*&fdiv_bug) + : "m" (*&x), "m" (*&y)); + + kernel_fpu_end(); + + write_cr0(cr0_saved); + + if (fdiv_bug) { + set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); + pr_warn("Hmm, FPU with FDIV bug\n"); + } +} + +void __init fpu__init_check_bugs(void) +{ + /* + * kernel_fpu_begin/end() in check_fpu() relies on the patched + * alternative instructions. + */ + if (cpu_has_fpu) + check_fpu(); +} diff --git a/kernel/arch/x86/kernel/fpu/core.c b/kernel/arch/x86/kernel/fpu/core.c new file mode 100644 index 000000000..d25097c3f --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/core.c @@ -0,0 +1,523 @@ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@valinux.com>, May 2000 + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/regset.h> +#include <asm/fpu/signal.h> +#include <asm/traps.h> + +#include <linux/hardirq.h> + +/* + * Represents the initial FPU state. It's mostly (but not completely) zeroes, + * depending on the FPU hardware format: + */ +union fpregs_state init_fpstate __read_mostly; + +/* + * Track whether the kernel is using the FPU state + * currently. + * + * This flag is used: + * + * - by IRQ context code to potentially use the FPU + * if it's unused. + * + * - to debug kernel_fpu_begin()/end() correctness + */ +static DEFINE_PER_CPU(bool, in_kernel_fpu); + +/* + * Track which context is using the FPU on the CPU: + */ +DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +static void kernel_fpu_disable(void) +{ + WARN_ON_FPU(this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, true); +} + +static void kernel_fpu_enable(void) +{ + WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); + this_cpu_write(in_kernel_fpu, false); +} + +static bool kernel_fpu_disabled(void) +{ + return this_cpu_read(in_kernel_fpu); +} + +/* + * Were we in an interrupt that interrupted kernel mode? + * + * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that + * pair does nothing at all: the thread must not have fpu (so + * that we don't try to save the FPU state), and TS must + * be set (so that the clts/stts pair does nothing that is + * visible in the interrupted kernel thread). + * + * Except for the eagerfpu case when we return true; in the likely case + * the thread has FPU but we are not going to set/clear TS. + */ +static bool interrupted_kernel_fpu_idle(void) +{ + if (kernel_fpu_disabled()) + return false; + + if (use_eager_fpu()) + return true; + + return !current->thread.fpu.fpregs_active && (read_cr0() & X86_CR0_TS); +} + +/* + * Were we in user mode (or vm86 mode) when we were + * interrupted? + * + * Doing kernel_fpu_begin/end() is ok if we are running + * in an interrupt context from user mode - we'll just + * save the FPU state as required. + */ +static bool interrupted_user_mode(void) +{ + struct pt_regs *regs = get_irq_regs(); + return regs && user_mode(regs); +} + +/* + * Can we use the FPU in kernel mode with the + * whole "kernel_fpu_begin/end()" sequence? + * + * It's always ok in process context (ie "not interrupt") + * but it is sometimes ok even from an irq. + */ +bool irq_fpu_usable(void) +{ + return !in_interrupt() || + interrupted_user_mode() || + interrupted_kernel_fpu_idle(); +} +EXPORT_SYMBOL(irq_fpu_usable); + +void __kernel_fpu_begin(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + WARN_ON_FPU(!irq_fpu_usable()); + + kernel_fpu_disable(); + + if (fpu->fpregs_active) { + copy_fpregs_to_fpstate(fpu); + } else { + this_cpu_write(fpu_fpregs_owner_ctx, NULL); + __fpregs_activate_hw(); + } +} +EXPORT_SYMBOL(__kernel_fpu_begin); + +void __kernel_fpu_end(void) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (fpu->fpregs_active) + copy_kernel_to_fpregs(&fpu->state); + else + __fpregs_deactivate_hw(); + + kernel_fpu_enable(); +} +EXPORT_SYMBOL(__kernel_fpu_end); + +void kernel_fpu_begin(void) +{ + preempt_disable(); + __kernel_fpu_begin(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + __kernel_fpu_end(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); + +/* + * CR0::TS save/restore functions: + */ +int irq_ts_save(void) +{ + /* + * If in process context and not atomic, we can take a spurious DNA fault. + * Otherwise, doing clts() in process context requires disabling preemption + * or some heavy lifting like kernel_fpu_begin() + */ + if (!in_atomic()) + return 0; + + if (read_cr0() & X86_CR0_TS) { + clts(); + return 1; + } + + return 0; +} +EXPORT_SYMBOL_GPL(irq_ts_save); + +void irq_ts_restore(int TS_state) +{ + if (TS_state) + stts(); +} +EXPORT_SYMBOL_GPL(irq_ts_restore); + +/* + * Save the FPU state (mark it for reload if necessary): + * + * This only ever gets called for the current task. + */ +void fpu__save(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + preempt_disable(); + if (fpu->fpregs_active) { + if (!copy_fpregs_to_fpstate(fpu)) + fpregs_deactivate(fpu); + } + preempt_enable(); +} +EXPORT_SYMBOL_GPL(fpu__save); + +/* + * Legacy x87 fpstate state init: + */ +static inline void fpstate_init_fstate(struct fregs_state *fp) +{ + fp->cwd = 0xffff037fu; + fp->swd = 0xffff0000u; + fp->twd = 0xffffffffu; + fp->fos = 0xffff0000u; +} + +void fpstate_init(union fpregs_state *state) +{ + if (!cpu_has_fpu) { + fpstate_init_soft(&state->soft); + return; + } + + memset(state, 0, xstate_size); + + if (cpu_has_fxsr) + fpstate_init_fxstate(&state->fxsave); + else + fpstate_init_fstate(&state->fsave); +} +EXPORT_SYMBOL_GPL(fpstate_init); + +/* + * Copy the current task's FPU state to a new task's FPU context. + * + * In both the 'eager' and the 'lazy' case we save hardware registers + * directly to the destination buffer. + */ +static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + WARN_ON_FPU(src_fpu != ¤t->thread.fpu); + + /* + * Don't let 'init optimized' areas of the XSAVE area + * leak into the child task: + */ + if (use_eager_fpu()) + memset(&dst_fpu->state.xsave, 0, xstate_size); + + /* + * Save current FPU registers directly into the child + * FPU context, without any memory-to-memory copying. + * + * If the FPU context got destroyed in the process (FNSAVE + * done on old CPUs) then copy it back into the source + * context and mark the current task for lazy restore. + * + * We have to do all this with preemption disabled, + * mostly because of the FNSAVE case, because in that + * case we must not allow preemption in the window + * between the FNSAVE and us marking the context lazy. + * + * It shouldn't be an issue as even FNSAVE is plenty + * fast in terms of critical section length. + */ + preempt_disable(); + if (!copy_fpregs_to_fpstate(dst_fpu)) { + memcpy(&src_fpu->state, &dst_fpu->state, xstate_size); + fpregs_deactivate(src_fpu); + } + preempt_enable(); +} + +int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) +{ + dst_fpu->counter = 0; + dst_fpu->fpregs_active = 0; + dst_fpu->last_cpu = -1; + + if (src_fpu->fpstate_active && cpu_has_fpu) + fpu_copy(dst_fpu, src_fpu); + + return 0; +} + +/* + * Activate the current task's in-memory FPU context, + * if it has not been used before: + */ +void fpu__activate_curr(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); + + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for the current task: */ + fpu->fpstate_active = 1; + } +} +EXPORT_SYMBOL_GPL(fpu__activate_curr); + +/* + * This function must be called before we read a task's fpstate. + * + * If the task has not used the FPU before then initialize its + * fpstate. + * + * If the task has used the FPU before then save it. + */ +void fpu__activate_fpstate_read(struct fpu *fpu) +{ + /* + * If fpregs are active (in the current CPU), then + * copy them to the fpstate: + */ + if (fpu->fpregs_active) { + fpu__save(fpu); + } else { + if (!fpu->fpstate_active) { + fpstate_init(&fpu->state); + + /* Safe to do for current and for stopped child tasks: */ + fpu->fpstate_active = 1; + } + } +} + +/* + * This function must be called before we write a task's fpstate. + * + * If the task has used the FPU before then unlazy it. + * If the task has not used the FPU before then initialize its fpstate. + * + * After this function call, after registers in the fpstate are + * modified and the child task has woken up, the child task will + * restore the modified FPU state from the modified context. If we + * didn't clear its lazy status here then the lazy in-registers + * state pending on its former CPU could be restored, corrupting + * the modifications. + */ +void fpu__activate_fpstate_write(struct fpu *fpu) +{ + /* + * Only stopped child tasks can be used to modify the FPU + * state in the fpstate buffer: + */ + WARN_ON_FPU(fpu == ¤t->thread.fpu); + + if (fpu->fpstate_active) { + /* Invalidate any lazy state: */ + fpu->last_cpu = -1; + } else { + fpstate_init(&fpu->state); + + /* Safe to do for stopped child tasks: */ + fpu->fpstate_active = 1; + } +} + +/* + * 'fpu__restore()' is called to copy FPU registers from + * the FPU fpstate to the live hw registers and to activate + * access to the hardware registers, so that FPU instructions + * can be used afterwards. + * + * Must be called with kernel preemption disabled (for example + * with local interrupts disabled, as it is in the case of + * do_device_not_available()). + */ +void fpu__restore(struct fpu *fpu) +{ + fpu__activate_curr(fpu); + + /* Avoid __kernel_fpu_begin() right after fpregs_activate() */ + kernel_fpu_disable(); + fpregs_activate(fpu); + copy_kernel_to_fpregs(&fpu->state); + fpu->counter++; + kernel_fpu_enable(); +} +EXPORT_SYMBOL_GPL(fpu__restore); + +/* + * Drops current FPU state: deactivates the fpregs and + * the fpstate. NOTE: it still leaves previous contents + * in the fpregs in the eager-FPU case. + * + * This function can be used in cases where we know that + * a state-restore is coming: either an explicit one, + * or a reschedule. + */ +void fpu__drop(struct fpu *fpu) +{ + preempt_disable(); + fpu->counter = 0; + + if (fpu->fpregs_active) { + /* Ignore delayed exceptions from user space */ + asm volatile("1: fwait\n" + "2:\n" + _ASM_EXTABLE(1b, 2b)); + fpregs_deactivate(fpu); + } + + fpu->fpstate_active = 0; + + preempt_enable(); +} + +/* + * Clear FPU registers by setting them up from + * the init fpstate: + */ +static inline void copy_init_fpstate_to_fpregs(void) +{ + if (use_xsave()) + copy_kernel_to_xregs(&init_fpstate.xsave, -1); + else + copy_kernel_to_fxregs(&init_fpstate.fxsave); +} + +/* + * Clear the FPU state back to init state. + * + * Called by sys_execve(), by the signal handler code and by various + * error paths. + */ +void fpu__clear(struct fpu *fpu) +{ + WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ + + if (!use_eager_fpu()) { + /* FPU state will be reallocated lazily at the first use. */ + fpu__drop(fpu); + } else { + if (!fpu->fpstate_active) { + fpu__activate_curr(fpu); + user_fpu_begin(); + } + copy_init_fpstate_to_fpregs(); + } +} + +/* + * x87 math exception handling: + */ + +static inline unsigned short get_fpu_cwd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.cwd; + } else { + return (unsigned short)fpu->state.fsave.cwd; + } +} + +static inline unsigned short get_fpu_swd(struct fpu *fpu) +{ + if (cpu_has_fxsr) { + return fpu->state.fxsave.swd; + } else { + return (unsigned short)fpu->state.fsave.swd; + } +} + +static inline unsigned short get_fpu_mxcsr(struct fpu *fpu) +{ + if (cpu_has_xmm) { + return fpu->state.fxsave.mxcsr; + } else { + return MXCSR_DEFAULT; + } +} + +int fpu__exception_code(struct fpu *fpu, int trap_nr) +{ + int err; + + if (trap_nr == X86_TRAP_MF) { + unsigned short cwd, swd; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't synchronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(fpu); + swd = get_fpu_swd(fpu); + + err = swd & ~cwd; + } else { + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + unsigned short mxcsr = get_fpu_mxcsr(fpu); + err = ~(mxcsr >> 7) & mxcsr; + } + + if (err & 0x001) { /* Invalid op */ + /* + * swd & 0x240 == 0x040: Stack Underflow + * swd & 0x240 == 0x240: Stack Overflow + * User must clear the SF bit (0x40) if set + */ + return FPE_FLTINV; + } else if (err & 0x004) { /* Divide by Zero */ + return FPE_FLTDIV; + } else if (err & 0x008) { /* Overflow */ + return FPE_FLTOVF; + } else if (err & 0x012) { /* Denormal, Underflow */ + return FPE_FLTUND; + } else if (err & 0x020) { /* Precision */ + return FPE_FLTRES; + } + + /* + * If we're using IRQ 13, or supposedly even some trap + * X86_TRAP_MF implementations, it's possible + * we get a spurious trap, which is not an error. + */ + return 0; +} diff --git a/kernel/arch/x86/kernel/fpu/init.c b/kernel/arch/x86/kernel/fpu/init.c new file mode 100644 index 000000000..be39b5fde --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/init.c @@ -0,0 +1,396 @@ +/* + * x86 FPU boot time init code: + */ +#include <asm/fpu/internal.h> +#include <asm/tlbflush.h> + +#include <linux/sched.h> + +/* + * Initialize the TS bit in CR0 according to the style of context-switches + * we are using: + */ +static void fpu__init_cpu_ctx_switch(void) +{ + if (!cpu_has_eager_fpu) + stts(); + else + clts(); +} + +/* + * Initialize the registers found in all CPUs, CR0 and CR4: + */ +static void fpu__init_cpu_generic(void) +{ + unsigned long cr0; + unsigned long cr4_mask = 0; + + if (cpu_has_fxsr) + cr4_mask |= X86_CR4_OSFXSR; + if (cpu_has_xmm) + cr4_mask |= X86_CR4_OSXMMEXCPT; + if (cr4_mask) + cr4_set_bits(cr4_mask); + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ + if (!cpu_has_fpu) + cr0 |= X86_CR0_EM; + write_cr0(cr0); + + /* Flush out any pending x87 state: */ +#ifdef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) + fpstate_init_soft(¤t->thread.fpu.state.soft); + else +#endif + asm volatile ("fninit"); +} + +/* + * Enable all supported FPU features. Called when a CPU is brought online: + */ +void fpu__init_cpu(void) +{ + fpu__init_cpu_generic(); + fpu__init_cpu_xstate(); + fpu__init_cpu_ctx_switch(); +} + +/* + * The earliest FPU detection code. + * + * Set the X86_FEATURE_FPU CPU-capability bit based on + * trying to execute an actual sequence of FPU instructions: + */ +static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) +{ + unsigned long cr0; + u16 fsw, fcw; + + fsw = fcw = 0xffff; + + cr0 = read_cr0(); + cr0 &= ~(X86_CR0_TS | X86_CR0_EM); + write_cr0(cr0); + + asm volatile("fninit ; fnstsw %0 ; fnstcw %1" + : "+m" (fsw), "+m" (fcw)); + + if (fsw == 0 && (fcw & 0x103f) == 0x003f) + set_cpu_cap(c, X86_FEATURE_FPU); + else + clear_cpu_cap(c, X86_FEATURE_FPU); + +#ifndef CONFIG_MATH_EMULATION + if (!cpu_has_fpu) { + pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n"); + for (;;) + asm volatile("hlt"); + } +#endif +} + +/* + * Boot time FPU feature detection code: + */ +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; + +static void __init fpu__init_system_mxcsr(void) +{ + unsigned int mask = 0; + + if (cpu_has_fxsr) { + /* Static because GCC does not get 16-byte stack alignment right: */ + static struct fxregs_state fxregs __initdata; + + asm volatile("fxsave %0" : "+m" (fxregs)); + + mask = fxregs.mxcsr_mask; + + /* + * If zero then use the default features mask, + * which has all features set, except the + * denormals-are-zero feature bit: + */ + if (mask == 0) + mask = 0x0000ffbf; + } + mxcsr_feature_mask &= mask; +} + +/* + * Once per bootup FPU initialization sequences that will run on most x86 CPUs: + */ +static void __init fpu__init_system_generic(void) +{ + /* + * Set up the legacy init FPU context. (xstate init might overwrite this + * with a more modern format, if the CPU supports it.) + */ + fpstate_init_fxstate(&init_fpstate.fxsave); + + fpu__init_system_mxcsr(); +} + +/* + * Size of the FPU context state. All tasks in the system use the + * same context size, regardless of what portion they use. + * This is inherent to the XSAVE architecture which puts all state + * components into a single, continuous memory block: + */ +unsigned int xstate_size; +EXPORT_SYMBOL_GPL(xstate_size); + +/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ + BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + +/* + * We append the 'struct fpu' to the task_struct: + */ +static void __init fpu__init_task_struct_size(void) +{ + int task_size = sizeof(struct task_struct); + + /* + * Subtract off the static size of the register state. + * It potentially has a bunch of padding. + */ + task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state); + + /* + * Add back the dynamically-calculated register state + * size. + */ + task_size += xstate_size; + + /* + * We dynamically size 'struct fpu', so we require that + * it be at the end of 'thread_struct' and that + * 'thread_struct' be at the end of 'task_struct'. If + * you hit a compile error here, check the structure to + * see if something got added to the end. + */ + CHECK_MEMBER_AT_END_OF(struct fpu, state); + CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu); + CHECK_MEMBER_AT_END_OF(struct task_struct, thread); + + arch_task_struct_size = task_size; +} + +/* + * Set up the xstate_size based on the legacy FPU context size. + * + * We set this up first, and later it will be overwritten by + * fpu__init_system_xstate() if the CPU knows about xstates. + */ +static void __init fpu__init_system_xstate_size_legacy(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + /* + * Note that xstate_size might be overwriten later during + * fpu__init_system_xstate(). + */ + + if (!cpu_has_fpu) { + /* + * Disable xsave as we do not support it if i387 + * emulation is enabled. + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + xstate_size = sizeof(struct swregs_state); + } else { + if (cpu_has_fxsr) + xstate_size = sizeof(struct fxregs_state); + else + xstate_size = sizeof(struct fregs_state); + } + /* + * Quirk: we don't yet handle the XSAVES* instructions + * correctly, as we don't correctly convert between + * standard and compacted format when interfacing + * with user-space - so disable it for now. + * + * The difference is small: with recent CPUs the + * compacted format is only marginally smaller than + * the standard FPU state format. + * + * ( This is easy to backport while we are fixing + * XSAVES* support. ) + */ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); +} + +/* + * FPU context switching strategies: + * + * Against popular belief, we don't do lazy FPU saves, due to the + * task migration complications it brings on SMP - we only do + * lazy FPU restores. + * + * 'lazy' is the traditional strategy, which is based on setting + * CR0::TS to 1 during context-switch (instead of doing a full + * restore of the FPU state), which causes the first FPU instruction + * after the context switch (whenever it is executed) to fault - at + * which point we lazily restore the FPU state into FPU registers. + * + * Tasks are of course under no obligation to execute FPU instructions, + * so it can easily happen that another context-switch occurs without + * a single FPU instruction being executed. If we eventually switch + * back to the original task (that still owns the FPU) then we have + * not only saved the restores along the way, but we also have the + * FPU ready to be used for the original task. + * + * 'eager' switching is used on modern CPUs, there we switch the FPU + * state during every context switch, regardless of whether the task + * has used FPU instructions in that time slice or not. This is done + * because modern FPU context saving instructions are able to optimize + * state saving and restoration in hardware: they can detect both + * unused and untouched FPU state and optimize accordingly. + * + * [ Note that even in 'lazy' mode we might optimize context switches + * to use 'eager' restores, if we detect that a task is using the FPU + * frequently. See the fpu->counter logic in fpu/internal.h for that. ] + */ +static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; + +static int __init eager_fpu_setup(char *s) +{ + if (!strcmp(s, "on")) + eagerfpu = ENABLE; + else if (!strcmp(s, "off")) + eagerfpu = DISABLE; + else if (!strcmp(s, "auto")) + eagerfpu = AUTO; + return 1; +} +__setup("eagerfpu=", eager_fpu_setup); + +/* + * Pick the FPU context switching strategy: + */ +static void __init fpu__init_system_ctx_switch(void) +{ + static bool on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + WARN_ON_FPU(current->thread.fpu.fpstate_active); + current_thread_info()->status = 0; + + /* Auto enable eagerfpu for xsaveopt */ + if (cpu_has_xsaveopt && eagerfpu != DISABLE) + eagerfpu = ENABLE; + + if (xfeatures_mask & XFEATURE_MASK_EAGER) { + if (eagerfpu == DISABLE) { + pr_err("x86/fpu: eagerfpu switching disabled, disabling the following xstate features: 0x%llx.\n", + xfeatures_mask & XFEATURE_MASK_EAGER); + xfeatures_mask &= ~XFEATURE_MASK_EAGER; + } else { + eagerfpu = ENABLE; + } + } + + if (eagerfpu == ENABLE) + setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); + + printk(KERN_INFO "x86/fpu: Using '%s' FPU context switches.\n", eagerfpu == ENABLE ? "eager" : "lazy"); +} + +/* + * Called on the boot CPU once per system bootup, to set up the initial + * FPU state that is later cloned into all processes: + */ +void __init fpu__init_system(struct cpuinfo_x86 *c) +{ + fpu__init_system_early_generic(c); + + /* + * The FPU has to be operational for some of the + * later FPU init activities: + */ + fpu__init_cpu(); + + /* + * But don't leave CR0::TS set yet, as some of the FPU setup + * methods depend on being able to execute FPU instructions + * that will fault on a set TS, such as the FXSAVE in + * fpu__init_system_mxcsr(). + */ + clts(); + + fpu__init_system_generic(); + fpu__init_system_xstate_size_legacy(); + fpu__init_system_xstate(); + fpu__init_task_struct_size(); + + fpu__init_system_ctx_switch(); +} + +/* + * Boot parameter to turn off FPU support and fall back to math-emu: + */ +static int __init no_387(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FPU); + return 1; +} +__setup("no387", no_387); + +/* + * Disable all xstate CPU features: + */ +static int __init x86_noxsave_setup(char *s) +{ + if (strlen(s)) + return 0; + + fpu__xstate_clear_all_cpu_caps(); + + return 1; +} +__setup("noxsave", x86_noxsave_setup); + +/* + * Disable the XSAVEOPT instruction specifically: + */ +static int __init x86_noxsaveopt_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + + return 1; +} +__setup("noxsaveopt", x86_noxsaveopt_setup); + +/* + * Disable the XSAVES instruction: + */ +static int __init x86_noxsaves_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + + return 1; +} +__setup("noxsaves", x86_noxsaves_setup); + +/* + * Disable FX save/restore and SSE support: + */ +static int __init x86_nofxsr_setup(char *s) +{ + setup_clear_cpu_cap(X86_FEATURE_FXSR); + setup_clear_cpu_cap(X86_FEATURE_FXSR_OPT); + setup_clear_cpu_cap(X86_FEATURE_XMM); + + return 1; +} +__setup("nofxsr", x86_nofxsr_setup); diff --git a/kernel/arch/x86/kernel/fpu/regset.c b/kernel/arch/x86/kernel/fpu/regset.c new file mode 100644 index 000000000..0bc349042 --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/regset.c @@ -0,0 +1,356 @@ +/* + * FPU register's regset abstraction, for ptrace, core dumps, etc. + */ +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +/* + * The xstateregs_active() routine is the same as the regset_fpregs_active() routine, + * as the "regset->n" for the xstate regset will be updated based on the feature + * capabilites supported by the xsave. + */ +int regset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return target_fpu->fpstate_active ? regset->n : 0; +} + +int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset) +{ + struct fpu *target_fpu = &target->thread.fpu; + + return (cpu_has_fxsr && target_fpu->fpstate_active) ? regset->n : 0; +} + +int xfpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + fpstate_sanitize_xstate(fpu); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); +} + +int xfpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + int ret; + + if (!cpu_has_fxsr) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fxsave, 0, -1); + + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; + + /* + * update the header bits in the xsave header, indicating the + * presence of FP and SSE state. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FPSSE; + + return ret; +} + +int xstateregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_read(fpu); + + xsave = &fpu->state.xsave; + + /* + * Copy the 48bytes defined by the software first into the xstate + * memory layout in the thread struct, so that we can copy the entire + * xstateregs to the user using one user_regset_copyout(). + */ + memcpy(&xsave->i387.sw_reserved, + xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); + /* + * Copy the xstate memory layout. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + return ret; +} + +int xstateregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct xregs_state *xsave; + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + fpu__activate_fpstate_write(fpu); + + xsave = &fpu->state.xsave; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + xsave->header.xfeatures &= xfeatures_mask; + /* + * These bits must be zero. + */ + memset(&xsave->header.reserved, 0, 48); + + return ret; +} + +#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION + +/* + * FPU tag word conversions. + */ + +static inline unsigned short twd_i387_to_fxsr(unsigned short twd) +{ + unsigned int tmp; /* to avoid 16 bit prefixes in the code */ + + /* Transform each pair of bits into 01 (valid) or 00 (empty) */ + tmp = ~twd; + tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ + /* and move the valid bits to the lower byte. */ + tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ + tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ + tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ + + return tmp; +} + +#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) +#define FP_EXP_TAG_VALID 0 +#define FP_EXP_TAG_ZERO 1 +#define FP_EXP_TAG_SPECIAL 2 +#define FP_EXP_TAG_EMPTY 3 + +static inline u32 twd_fxsr_to_i387(struct fxregs_state *fxsave) +{ + struct _fpxreg *st; + u32 tos = (fxsave->swd >> 11) & 7; + u32 twd = (unsigned long) fxsave->twd; + u32 tag; + u32 ret = 0xffff0000u; + int i; + + for (i = 0; i < 8; i++, twd >>= 1) { + if (twd & 0x1) { + st = FPREG_ADDR(fxsave, (i - tos) & 7); + + switch (st->exponent & 0x7fff) { + case 0x7fff: + tag = FP_EXP_TAG_SPECIAL; + break; + case 0x0000: + if (!st->significand[0] && + !st->significand[1] && + !st->significand[2] && + !st->significand[3]) + tag = FP_EXP_TAG_ZERO; + else + tag = FP_EXP_TAG_SPECIAL; + break; + default: + if (st->significand[3] & 0x8000) + tag = FP_EXP_TAG_VALID; + else + tag = FP_EXP_TAG_SPECIAL; + break; + } + } else { + tag = FP_EXP_TAG_EMPTY; + } + ret |= tag << (2 * i); + } + return ret; +} + +/* + * FXSR floating point environment conversions. + */ + +void +convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + env->cwd = fxsave->cwd | 0xffff0000u; + env->swd = fxsave->swd | 0xffff0000u; + env->twd = twd_fxsr_to_i387(fxsave); + +#ifdef CONFIG_X86_64 + env->fip = fxsave->rip; + env->foo = fxsave->rdp; + /* + * should be actually ds/cs at fpu exception time, but + * that information is not available in 64bit mode. + */ + env->fcs = task_pt_regs(tsk)->cs; + if (tsk == current) { + savesegment(ds, env->fos); + } else { + env->fos = tsk->thread.ds; + } + env->fos |= 0xffff0000; +#else + env->fip = fxsave->fip; + env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); + env->foo = fxsave->foo; + env->fos = fxsave->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(to[0])); +} + +void convert_to_fxsr(struct task_struct *tsk, + const struct user_i387_ia32_struct *env) + +{ + struct fxregs_state *fxsave = &tsk->thread.fpu.state.fxsave; + struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; + struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; + int i; + + fxsave->cwd = env->cwd; + fxsave->swd = env->swd; + fxsave->twd = twd_i387_to_fxsr(env->twd); + fxsave->fop = (u16) ((u32) env->fcs >> 16); +#ifdef CONFIG_X86_64 + fxsave->rip = env->fip; + fxsave->rdp = env->foo; + /* cs and ds ignored */ +#else + fxsave->fip = env->fip; + fxsave->fcs = (env->fcs & 0xffff); + fxsave->foo = env->foo; + fxsave->fos = env->fos; +#endif + + for (i = 0; i < 8; ++i) + memcpy(&to[i], &from[i], sizeof(from[0])); +} + +int fpregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + + fpu__activate_fpstate_read(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + fpstate_sanitize_xstate(fpu); + + if (kbuf && pos == 0 && count == sizeof(env)) { + convert_from_fxsr(kbuf, target); + return 0; + } + + convert_from_fxsr(&env, target); + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); +} + +int fpregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct fpu *fpu = &target->thread.fpu; + struct user_i387_ia32_struct env; + int ret; + + fpu__activate_fpstate_write(fpu); + fpstate_sanitize_xstate(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); + + if (!cpu_has_fxsr) + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &fpu->state.fsave, 0, + -1); + + if (pos > 0 || count < sizeof(env)) + convert_from_fxsr(&env, target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); + if (!ret) + convert_to_fxsr(target, &env); + + /* + * update the header bit in the xsave header, indicating the + * presence of FP. + */ + if (cpu_has_xsave) + fpu->state.xsave.header.xfeatures |= XFEATURE_MASK_FP; + return ret; +} + +/* + * FPU state for core dumps. + * This is only used for a.out dumps now. + * It is declared generically using elf_fpregset_t (which is + * struct user_i387_struct) but is in fact only used for 32-bit + * dumps, so on 64-bit it is really struct user_i387_ia32_struct. + */ +int dump_fpu(struct pt_regs *regs, struct user_i387_struct *ufpu) +{ + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int fpvalid; + + fpvalid = fpu->fpstate_active; + if (fpvalid) + fpvalid = !fpregs_get(tsk, NULL, + 0, sizeof(struct user_i387_ia32_struct), + ufpu, NULL); + + return fpvalid; +} +EXPORT_SYMBOL(dump_fpu); + +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ diff --git a/kernel/arch/x86/kernel/fpu/signal.c b/kernel/arch/x86/kernel/fpu/signal.c new file mode 100644 index 000000000..31c6a6050 --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/signal.c @@ -0,0 +1,403 @@ +/* + * FPU signal frame handling routines. + */ + +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/sigframe.h> + +static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; + +/* + * Check for the presence of extended state information in the + * user fpstate pointer in the sigcontext. + */ +static inline int check_for_xstate(struct fxregs_state __user *buf, + void __user *fpstate, + struct _fpx_sw_bytes *fx_sw) +{ + int min_xstate_size = sizeof(struct fxregs_state) + + sizeof(struct xstate_header); + unsigned int magic2; + + if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) + return -1; + + /* Check for the first magic field and other error scenarios. */ + if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || + fx_sw->xstate_size < min_xstate_size || + fx_sw->xstate_size > xstate_size || + fx_sw->xstate_size > fx_sw->extended_size) + return -1; + + /* + * Check for the presence of second magic word at the end of memory + * layout. This detects the case where the user just copied the legacy + * fpstate layout with out copying the extended state information + * in the memory layout. + */ + if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) + || magic2 != FP_XSTATE_MAGIC2) + return -1; + + return 0; +} + +/* + * Signal frame handlers. + */ +static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) +{ + if (use_fxsr()) { + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct user_i387_ia32_struct env; + struct _fpstate_32 __user *fp = buf; + + convert_from_fxsr(&env, tsk); + + if (__copy_to_user(buf, &env, sizeof(env)) || + __put_user(xsave->i387.swd, &fp->status) || + __put_user(X86_FXSR_MAGIC, &fp->magic)) + return -1; + } else { + struct fregs_state __user *fp = buf; + u32 swd; + if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) + return -1; + } + + return 0; +} + +static inline int save_xstate_epilog(void __user *buf, int ia32_frame) +{ + struct xregs_state __user *x = buf; + struct _fpx_sw_bytes *sw_bytes; + u32 xfeatures; + int err; + + /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ + sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; + err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); + + if (!use_xsave()) + return err; + + err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); + + /* + * Read the xfeatures which we copied (directly from the cpu or + * from the state in task struct) to the user buffers. + */ + err |= __get_user(xfeatures, (__u32 *)&x->header.xfeatures); + + /* + * For legacy compatible, we always set FP/SSE bits in the bit + * vector while saving the state to the user context. This will + * enable us capturing any changes(during sigreturn) to + * the FP/SSE bits by the legacy applications which don't touch + * xfeatures in the xsave header. + * + * xsave aware apps can change the xfeatures in the xsave + * header as well as change any contents in the memory layout. + * xrestore as part of sigreturn will capture all the changes. + */ + xfeatures |= XFEATURE_MASK_FPSSE; + + err |= __put_user(xfeatures, (__u32 *)&x->header.xfeatures); + + return err; +} + +static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf) +{ + int err; + + if (use_xsave()) + err = copy_xregs_to_user(buf); + else if (use_fxsr()) + err = copy_fxregs_to_user((struct fxregs_state __user *) buf); + else + err = copy_fregs_to_user((struct fregs_state __user *) buf); + + if (unlikely(err) && __clear_user(buf, xstate_size)) + err = -EFAULT; + return err; +} + +/* + * Save the fpu, extended register state to the user signal frame. + * + * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save + * state is copied. + * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. + * + * buf == buf_fx for 64-bit frames and 32-bit fsave frame. + * buf != buf_fx for 32-bit frames with fxstate. + * + * If the fpu, extended register state is live, save the state directly + * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, + * copy the thread's fpu state to the user frame starting at 'buf_fx'. + * + * If this is a 32-bit frame with fxstate, put a fsave header before + * the aligned state at 'buf_fx'. + * + * For [f]xsave state, update the SW reserved fields in the [f]xsave frame + * indicating the absence/presence of the extended state to the user. + */ +int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size) +{ + struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; + struct task_struct *tsk = current; + int ia32_fxstate = (buf != buf_fx); + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!access_ok(VERIFY_WRITE, buf, size)) + return -EACCES; + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_get(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), NULL, + (struct _fpstate_32 __user *) buf) ? -1 : 1; + + if (fpregs_active()) { + /* Save the live register state to the user directly. */ + if (copy_fpregs_to_sigframe(buf_fx)) + return -1; + /* Update the thread's fxstate to save the fsave header. */ + if (ia32_fxstate) + copy_fxregs_to_kernel(&tsk->thread.fpu); + } else { + fpstate_sanitize_xstate(&tsk->thread.fpu); + if (__copy_to_user(buf_fx, xsave, xstate_size)) + return -1; + } + + /* Save the fsave header for the 32-bit frames. */ + if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) + return -1; + + if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) + return -1; + + return 0; +} + +static inline void +sanitize_restored_xstate(struct task_struct *tsk, + struct user_i387_ia32_struct *ia32_env, + u64 xfeatures, int fx_only) +{ + struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; + struct xstate_header *header = &xsave->header; + + if (use_xsave()) { + /* These bits must be zero. */ + memset(header->reserved, 0, 48); + + /* + * Init the state that is not present in the memory + * layout and not enabled by the OS. + */ + if (fx_only) + header->xfeatures = XFEATURE_MASK_FPSSE; + else + header->xfeatures &= (xfeatures_mask & xfeatures); + } + + if (use_fxsr()) { + /* + * mscsr reserved bits must be masked to zero for security + * reasons. + */ + xsave->i387.mxcsr &= mxcsr_feature_mask; + + convert_to_fxsr(tsk, ia32_env); + } +} + +/* + * Restore the extended state if present. Otherwise, restore the FP/SSE state. + */ +static inline int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) +{ + if (use_xsave()) { + if ((unsigned long)buf % 64 || fx_only) { + u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE; + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_fxregs(buf); + } else { + u64 init_bv = xfeatures_mask & ~xbv; + if (unlikely(init_bv)) + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return copy_user_to_xregs(buf, xbv); + } + } else if (use_fxsr()) { + return copy_user_to_fxregs(buf); + } else + return copy_user_to_fregs(buf); +} + +static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) +{ + int ia32_fxstate = (buf != buf_fx); + struct task_struct *tsk = current; + struct fpu *fpu = &tsk->thread.fpu; + int state_size = xstate_size; + u64 xfeatures = 0; + int fx_only = 0; + + ia32_fxstate &= (config_enabled(CONFIG_X86_32) || + config_enabled(CONFIG_IA32_EMULATION)); + + if (!buf) { + fpu__clear(fpu); + return 0; + } + + if (!access_ok(VERIFY_READ, buf, size)) + return -EACCES; + + fpu__activate_curr(fpu); + + if (!static_cpu_has(X86_FEATURE_FPU)) + return fpregs_soft_set(current, NULL, + 0, sizeof(struct user_i387_ia32_struct), + NULL, buf) != 0; + + if (use_xsave()) { + struct _fpx_sw_bytes fx_sw_user; + if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { + /* + * Couldn't find the extended state information in the + * memory layout. Restore just the FP/SSE and init all + * the other extended state. + */ + state_size = sizeof(struct fxregs_state); + fx_only = 1; + } else { + state_size = fx_sw_user.xstate_size; + xfeatures = fx_sw_user.xfeatures; + } + } + + if (ia32_fxstate) { + /* + * For 32-bit frames with fxstate, copy the user state to the + * thread's fpu state, reconstruct fxstate from the fsave + * header. Sanitize the copied state etc. + */ + struct fpu *fpu = &tsk->thread.fpu; + struct user_i387_ia32_struct env; + int err = 0; + + /* + * Drop the current fpu which clears fpu->fpstate_active. This ensures + * that any context-switch during the copy of the new state, + * avoids the intermediate state from getting restored/saved. + * Thus avoiding the new restored state from getting corrupted. + * We will be ready to restore/save the state only after + * fpu->fpstate_active is again set. + */ + fpu__drop(fpu); + + if (__copy_from_user(&fpu->state.xsave, buf_fx, state_size) || + __copy_from_user(&env, buf, sizeof(env))) { + fpstate_init(&fpu->state); + err = -1; + } else { + sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); + } + + fpu->fpstate_active = 1; + if (use_eager_fpu()) { + preempt_disable(); + fpu__restore(fpu); + preempt_enable(); + } + + return err; + } else { + /* + * For 64-bit frames and 32-bit fsave frames, restore the user + * state to the registers directly (with exceptions handled). + */ + user_fpu_begin(); + if (copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only)) { + fpu__clear(fpu); + return -1; + } + } + + return 0; +} + +static inline int xstate_sigframe_size(void) +{ + return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size; +} + +/* + * Restore FPU state from a sigframe: + */ +int fpu__restore_sig(void __user *buf, int ia32_frame) +{ + void __user *buf_fx = buf; + int size = xstate_sigframe_size(); + + if (ia32_frame && use_fxsr()) { + buf_fx = buf + sizeof(struct fregs_state); + size += sizeof(struct fregs_state); + } + + return __fpu__restore_sig(buf, buf_fx, size); +} + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size) +{ + unsigned long frame_size = xstate_sigframe_size(); + + *buf_fx = sp = round_down(sp - frame_size, 64); + if (ia32_frame && use_fxsr()) { + frame_size += sizeof(struct fregs_state); + sp -= sizeof(struct fregs_state); + } + + *size = frame_size; + + return sp; +} +/* + * Prepare the SW reserved portion of the fxsave memory layout, indicating + * the presence of the extended state information in the memory layout + * pointed by the fpstate pointer in the sigcontext. + * This will be saved when ever the FP and extended state context is + * saved on the user stack during the signal handler delivery to the user. + */ +void fpu__init_prepare_fx_sw_frame(void) +{ + int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; + + fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; + fx_sw_reserved.extended_size = size; + fx_sw_reserved.xfeatures = xfeatures_mask; + fx_sw_reserved.xstate_size = xstate_size; + + if (config_enabled(CONFIG_IA32_EMULATION) || + config_enabled(CONFIG_X86_32)) { + int fsave_header_size = sizeof(struct fregs_state); + + fx_sw_reserved_ia32 = fx_sw_reserved; + fx_sw_reserved_ia32.extended_size = size + fsave_header_size; + } +} + diff --git a/kernel/arch/x86/kernel/fpu/xstate.c b/kernel/arch/x86/kernel/fpu/xstate.c new file mode 100644 index 000000000..70fc31222 --- /dev/null +++ b/kernel/arch/x86/kernel/fpu/xstate.c @@ -0,0 +1,752 @@ +/* + * xsave/xrstor support. + * + * Author: Suresh Siddha <suresh.b.siddha@intel.com> + */ +#include <linux/compat.h> +#include <linux/cpu.h> + +#include <asm/fpu/api.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> + +#include <asm/tlbflush.h> + +static const char *xfeature_names[] = +{ + "x87 floating point registers" , + "SSE registers" , + "AVX registers" , + "MPX bounds registers" , + "MPX CSR" , + "AVX-512 opmask" , + "AVX-512 Hi256" , + "AVX-512 ZMM_Hi256" , + "unknown xstate feature" , +}; + +/* + * Mask of xstate features supported by the CPU and the kernel: + */ +u64 xfeatures_mask __read_mostly; + +static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; +static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; +static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8]; + +/* + * Clear all of the X86_FEATURE_* bits that are unavailable + * when the CPU has no XSAVE support. + */ +void fpu__xstate_clear_all_cpu_caps(void) +{ + setup_clear_cpu_cap(X86_FEATURE_XSAVE); + setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); + setup_clear_cpu_cap(X86_FEATURE_XSAVEC); + setup_clear_cpu_cap(X86_FEATURE_XSAVES); + setup_clear_cpu_cap(X86_FEATURE_AVX); + setup_clear_cpu_cap(X86_FEATURE_AVX2); + setup_clear_cpu_cap(X86_FEATURE_AVX512F); + setup_clear_cpu_cap(X86_FEATURE_AVX512PF); + setup_clear_cpu_cap(X86_FEATURE_AVX512ER); + setup_clear_cpu_cap(X86_FEATURE_AVX512CD); + setup_clear_cpu_cap(X86_FEATURE_MPX); +} + +/* + * Return whether the system supports a given xfeature. + * + * Also return the name of the (most advanced) feature that the caller requested: + */ +int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) +{ + u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask; + + if (unlikely(feature_name)) { + long xfeature_idx, max_idx; + u64 xfeatures_print; + /* + * So we use FLS here to be able to print the most advanced + * feature that was requested but is missing. So if a driver + * asks about "XFEATURE_MASK_SSE | XFEATURE_MASK_YMM" we'll print the + * missing AVX feature - this is the most informative message + * to users: + */ + if (xfeatures_missing) + xfeatures_print = xfeatures_missing; + else + xfeatures_print = xfeatures_needed; + + xfeature_idx = fls64(xfeatures_print)-1; + max_idx = ARRAY_SIZE(xfeature_names)-1; + xfeature_idx = min(xfeature_idx, max_idx); + + *feature_name = xfeature_names[xfeature_idx]; + } + + if (xfeatures_missing) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(cpu_has_xfeatures); + +/* + * When executing XSAVEOPT (or other optimized XSAVE instructions), if + * a processor implementation detects that an FPU state component is still + * (or is again) in its initialized state, it may clear the corresponding + * bit in the header.xfeatures field, and can skip the writeout of registers + * to the corresponding memory layout. + * + * This means that when the bit is zero, the state component might still contain + * some previous - non-initialized register state. + * + * Before writing xstate information to user-space we sanitize those components, + * to always ensure that the memory layout of a feature will be in the init state + * if the corresponding header bit is zero. This is to ensure that user-space doesn't + * see some stale state in the memory layout during signal handling, debugging etc. + */ +void fpstate_sanitize_xstate(struct fpu *fpu) +{ + struct fxregs_state *fx = &fpu->state.fxsave; + int feature_bit; + u64 xfeatures; + + if (!use_xsaveopt()) + return; + + xfeatures = fpu->state.xsave.header.xfeatures; + + /* + * None of the feature bits are in init state. So nothing else + * to do for us, as the memory layout is up to date. + */ + if ((xfeatures & xfeatures_mask) == xfeatures_mask) + return; + + /* + * FP is in init state + */ + if (!(xfeatures & XFEATURE_MASK_FP)) { + fx->cwd = 0x37f; + fx->swd = 0; + fx->twd = 0; + fx->fop = 0; + fx->rip = 0; + fx->rdp = 0; + memset(&fx->st_space[0], 0, 128); + } + + /* + * SSE is in init state + */ + if (!(xfeatures & XFEATURE_MASK_SSE)) + memset(&fx->xmm_space[0], 0, 256); + + /* + * First two features are FPU and SSE, which above we handled + * in a special way already: + */ + feature_bit = 0x2; + xfeatures = (xfeatures_mask & ~xfeatures) >> 2; + + /* + * Update all the remaining memory layouts according to their + * standard xstate layout, if their header bit is in the init + * state: + */ + while (xfeatures) { + if (xfeatures & 0x1) { + int offset = xstate_offsets[feature_bit]; + int size = xstate_sizes[feature_bit]; + + memcpy((void *)fx + offset, + (void *)&init_fpstate.xsave + offset, + size); + } + + xfeatures >>= 1; + feature_bit++; + } +} + +/* + * Enable the extended processor state save/restore feature. + * Called once per CPU onlining. + */ +void fpu__init_cpu_xstate(void) +{ + if (!cpu_has_xsave || !xfeatures_mask) + return; + + cr4_set_bits(X86_CR4_OSXSAVE); + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Note that in the future we will likely need a pair of + * functions here: one for user xstates and the other for + * system xstates. For now, they are the same. + */ +static int xfeature_enabled(enum xfeature xfeature) +{ + return !!(xfeatures_mask & (1UL << xfeature)); +} + +/* + * Record the offsets and sizes of various xstates contained + * in the XSAVE state memory layout. + */ +static void __init setup_xstate_features(void) +{ + u32 eax, ebx, ecx, edx, i; + /* start at the beginnning of the "extended state" */ + unsigned int last_good_offset = offsetof(struct xregs_state, + extended_state_area); + + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (!xfeature_enabled(i)) + continue; + + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + xstate_offsets[i] = ebx; + xstate_sizes[i] = eax; + /* + * In our xstate size checks, we assume that the + * highest-numbered xstate feature has the + * highest offset in the buffer. Ensure it does. + */ + WARN_ONCE(last_good_offset > xstate_offsets[i], + "x86/fpu: misordered xstate at %d\n", last_good_offset); + last_good_offset = xstate_offsets[i]; + + printk(KERN_INFO "x86/fpu: xstate_offset[%d]: %4d, xstate_sizes[%d]: %4d\n", i, ebx, i, eax); + } +} + +static void __init print_xstate_feature(u64 xstate_mask) +{ + const char *feature_name; + + if (cpu_has_xfeatures(xstate_mask, &feature_name)) + pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name); +} + +/* + * Print out all the supported xstate features: + */ +static void __init print_xstate_features(void) +{ + print_xstate_feature(XFEATURE_MASK_FP); + print_xstate_feature(XFEATURE_MASK_SSE); + print_xstate_feature(XFEATURE_MASK_YMM); + print_xstate_feature(XFEATURE_MASK_BNDREGS); + print_xstate_feature(XFEATURE_MASK_BNDCSR); + print_xstate_feature(XFEATURE_MASK_OPMASK); + print_xstate_feature(XFEATURE_MASK_ZMM_Hi256); + print_xstate_feature(XFEATURE_MASK_Hi16_ZMM); +} + +/* + * This function sets up offsets and sizes of all extended states in + * xsave area. This supports both standard format and compacted format + * of the xsave aread. + */ +static void __init setup_xstate_comp(void) +{ + unsigned int xstate_comp_sizes[sizeof(xfeatures_mask)*8]; + int i; + + /* + * The FP xstates and SSE xstates are legacy states. They are always + * in the fixed offsets in the xsave area in either compacted form + * or standard form. + */ + xstate_comp_offsets[0] = 0; + xstate_comp_offsets[1] = offsetof(struct fxregs_state, xmm_space); + + if (!cpu_has_xsaves) { + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (xfeature_enabled(i)) { + xstate_comp_offsets[i] = xstate_offsets[i]; + xstate_comp_sizes[i] = xstate_sizes[i]; + } + } + return; + } + + xstate_comp_offsets[FIRST_EXTENDED_XFEATURE] = + FXSAVE_SIZE + XSAVE_HDR_SIZE; + + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (xfeature_enabled(i)) + xstate_comp_sizes[i] = xstate_sizes[i]; + else + xstate_comp_sizes[i] = 0; + + if (i > FIRST_EXTENDED_XFEATURE) + xstate_comp_offsets[i] = xstate_comp_offsets[i-1] + + xstate_comp_sizes[i-1]; + + } +} + +/* + * setup the xstate image representing the init state + */ +static void __init setup_init_fpu_buf(void) +{ + static int on_boot_cpu = 1; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) + return; + + setup_xstate_features(); + print_xstate_features(); + + if (cpu_has_xsaves) { + init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; + init_fpstate.xsave.header.xfeatures = xfeatures_mask; + } + + /* + * Init all the features state with header_bv being 0x0 + */ + copy_kernel_to_xregs_booting(&init_fpstate.xsave); + + /* + * Dump the init state again. This is to identify the init state + * of any feature which is not represented by all zero's. + */ + copy_xregs_to_kernel_booting(&init_fpstate.xsave); +} + +static int xfeature_is_supervisor(int xfeature_nr) +{ + /* + * We currently do not support supervisor states, but if + * we did, we could find out like this. + * + * SDM says: If state component i is a user state component, + * ECX[0] return 0; if state component i is a supervisor + * state component, ECX[0] returns 1. + u32 eax, ebx, ecx, edx; + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx; + return !!(ecx & 1); + */ + return 0; +} +/* +static int xfeature_is_user(int xfeature_nr) +{ + return !xfeature_is_supervisor(xfeature_nr); +} +*/ + +/* + * This check is important because it is easy to get XSTATE_* + * confused with XSTATE_BIT_*. + */ +#define CHECK_XFEATURE(nr) do { \ + WARN_ON(nr < FIRST_EXTENDED_XFEATURE); \ + WARN_ON(nr >= XFEATURE_MAX); \ +} while (0) + +/* + * We could cache this like xstate_size[], but we only use + * it here, so it would be a waste of space. + */ +static int xfeature_is_aligned(int xfeature_nr) +{ + u32 eax, ebx, ecx, edx; + + CHECK_XFEATURE(xfeature_nr); + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + /* + * The value returned by ECX[1] indicates the alignment + * of state component i when the compacted format + * of the extended region of an XSAVE area is used + */ + return !!(ecx & 2); +} + +static int xfeature_uncompacted_offset(int xfeature_nr) +{ + u32 eax, ebx, ecx, edx; + + CHECK_XFEATURE(xfeature_nr); + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + return ebx; +} + +static int xfeature_size(int xfeature_nr) +{ + u32 eax, ebx, ecx, edx; + + CHECK_XFEATURE(xfeature_nr); + cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + return eax; +} + +/* + * 'XSAVES' implies two different things: + * 1. saving of supervisor/system state + * 2. using the compacted format + * + * Use this function when dealing with the compacted format so + * that it is obvious which aspect of 'XSAVES' is being handled + * by the calling code. + */ +static int using_compacted_format(void) +{ + return cpu_has_xsaves; +} + +static void __xstate_dump_leaves(void) +{ + int i; + u32 eax, ebx, ecx, edx; + static int should_dump = 1; + + if (!should_dump) + return; + should_dump = 0; + /* + * Dump out a few leaves past the ones that we support + * just in case there are some goodies up there + */ + for (i = 0; i < XFEATURE_MAX + 10; i++) { + cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", + XSTATE_CPUID, i, eax, ebx, ecx, edx); + } +} + +#define XSTATE_WARN_ON(x) do { \ + if (WARN_ONCE(x, "XSAVE consistency problem, dumping leaves")) { \ + __xstate_dump_leaves(); \ + } \ +} while (0) + +#define XCHECK_SZ(sz, nr, nr_macro, __struct) do { \ + if ((nr == nr_macro) && \ + WARN_ONCE(sz != sizeof(__struct), \ + "%s: struct is %zu bytes, cpu state %d bytes\n", \ + __stringify(nr_macro), sizeof(__struct), sz)) { \ + __xstate_dump_leaves(); \ + } \ +} while (0) + +/* + * We have a C struct for each 'xstate'. We need to ensure + * that our software representation matches what the CPU + * tells us about the state's size. + */ +static void check_xstate_against_struct(int nr) +{ + /* + * Ask the CPU for the size of the state. + */ + int sz = xfeature_size(nr); + /* + * Match each CPU state with the corresponding software + * structure. + */ + XCHECK_SZ(sz, nr, XFEATURE_YMM, struct ymmh_struct); + XCHECK_SZ(sz, nr, XFEATURE_BNDREGS, struct mpx_bndreg_state); + XCHECK_SZ(sz, nr, XFEATURE_BNDCSR, struct mpx_bndcsr_state); + XCHECK_SZ(sz, nr, XFEATURE_OPMASK, struct avx_512_opmask_state); + XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state); + XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM, struct avx_512_hi16_state); + + /* + * Make *SURE* to add any feature numbers in below if + * there are "holes" in the xsave state component + * numbers. + */ + if ((nr < XFEATURE_YMM) || + (nr >= XFEATURE_MAX)) { + WARN_ONCE(1, "no structure for xstate: %d\n", nr); + XSTATE_WARN_ON(1); + } +} + +/* + * This essentially double-checks what the cpu told us about + * how large the XSAVE buffer needs to be. We are recalculating + * it to be safe. + */ +static void do_extra_xstate_size_checks(void) +{ + int paranoid_xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; + int i; + + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (!xfeature_enabled(i)) + continue; + + check_xstate_against_struct(i); + /* + * Supervisor state components can be managed only by + * XSAVES, which is compacted-format only. + */ + if (!using_compacted_format()) + XSTATE_WARN_ON(xfeature_is_supervisor(i)); + + /* Align from the end of the previous feature */ + if (xfeature_is_aligned(i)) + paranoid_xstate_size = ALIGN(paranoid_xstate_size, 64); + /* + * The offset of a given state in the non-compacted + * format is given to us in a CPUID leaf. We check + * them for being ordered (increasing offsets) in + * setup_xstate_features(). + */ + if (!using_compacted_format()) + paranoid_xstate_size = xfeature_uncompacted_offset(i); + /* + * The compacted-format offset always depends on where + * the previous state ended. + */ + paranoid_xstate_size += xfeature_size(i); + } + XSTATE_WARN_ON(paranoid_xstate_size != xstate_size); +} + +/* + * Calculate total size of enabled xstates in XCR0/xfeatures_mask. + * + * Note the SDM's wording here. "sub-function 0" only enumerates + * the size of the *user* states. If we use it to size a buffer + * that we use 'XSAVES' on, we could potentially overflow the + * buffer because 'XSAVES' saves system states too. + * + * Note that we do not currently set any bits on IA32_XSS so + * 'XCR0 | IA32_XSS == XCR0' for now. + */ +static unsigned int __init calculate_xstate_size(void) +{ + unsigned int eax, ebx, ecx, edx; + unsigned int calculated_xstate_size; + + if (!cpu_has_xsaves) { + /* + * - CPUID function 0DH, sub-function 0: + * EBX enumerates the size (in bytes) required by + * the XSAVE instruction for an XSAVE area + * containing all the *user* state components + * corresponding to bits currently set in XCR0. + */ + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + calculated_xstate_size = ebx; + } else { + /* + * - CPUID function 0DH, sub-function 1: + * EBX enumerates the size (in bytes) required by + * the XSAVES instruction for an XSAVE area + * containing all the state components + * corresponding to bits currently set in + * XCR0 | IA32_XSS. + */ + cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + calculated_xstate_size = ebx; + } + return calculated_xstate_size; +} + +/* + * Will the runtime-enumerated 'xstate_size' fit in the init + * task's statically-allocated buffer? + */ +static bool is_supported_xstate_size(unsigned int test_xstate_size) +{ + if (test_xstate_size <= sizeof(union fpregs_state)) + return true; + + pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n", + sizeof(union fpregs_state), test_xstate_size); + return false; +} + +static int init_xstate_size(void) +{ + /* Recompute the context size for enabled features: */ + unsigned int possible_xstate_size = calculate_xstate_size(); + + /* Ensure we have the space to store all enabled: */ + if (!is_supported_xstate_size(possible_xstate_size)) + return -EINVAL; + + /* + * The size is OK, we are definitely going to use xsave, + * make it known to the world that we need more space. + */ + xstate_size = possible_xstate_size; + do_extra_xstate_size_checks(); + return 0; +} + +/* + * We enabled the XSAVE hardware, but something went wrong and + * we can not use it. Disable it. + */ +static void fpu__init_disable_system_xstate(void) +{ + xfeatures_mask = 0; + cr4_clear_bits(X86_CR4_OSXSAVE); + fpu__xstate_clear_all_cpu_caps(); +} + +/* + * Enable and initialize the xsave feature. + * Called once per system bootup. + */ +void __init fpu__init_system_xstate(void) +{ + unsigned int eax, ebx, ecx, edx; + static int on_boot_cpu = 1; + int err; + + WARN_ON_FPU(!on_boot_cpu); + on_boot_cpu = 0; + + if (!cpu_has_xsave) { + pr_info("x86/fpu: Legacy x87 FPU detected.\n"); + return; + } + + if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { + WARN_ON_FPU(1); + return; + } + + cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + xfeatures_mask = eax + ((u64)edx << 32); + + if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { + pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask); + BUG(); + } + + /* Support only the state known to the OS: */ + xfeatures_mask = xfeatures_mask & XCNTXT_MASK; + + /* Enable xstate instructions to be able to continue with initialization: */ + fpu__init_cpu_xstate(); + err = init_xstate_size(); + if (err) { + /* something went wrong, boot without any XSAVE support */ + fpu__init_disable_system_xstate(); + return; + } + + update_regset_xstate_info(xstate_size, xfeatures_mask); + fpu__init_prepare_fx_sw_frame(); + setup_init_fpu_buf(); + setup_xstate_comp(); + + pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", + xfeatures_mask, + xstate_size, + cpu_has_xsaves ? "compacted" : "standard"); +} + +/* + * Restore minimal FPU state after suspend: + */ +void fpu__resume_cpu(void) +{ + /* + * Restore XCR0 on xsave capable CPUs: + */ + if (cpu_has_xsave) + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); +} + +/* + * Given the xsave area and a state inside, this function returns the + * address of the state. + * + * This is the API that is called to get xstate address in either + * standard format or compacted format of xsave area. + * + * Note that if there is no data for the field in the xsave buffer + * this will return NULL. + * + * Inputs: + * xstate: the thread's storage area for all FPU data + * xstate_feature: state which is defined in xsave.h (e.g. + * XFEATURE_MASK_FP, XFEATURE_MASK_SSE, etc...) + * Output: + * address of the state in the xsave area, or NULL if the + * field is not present in the xsave buffer. + */ +void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature) +{ + int feature_nr = fls64(xstate_feature) - 1; + /* + * Do we even *have* xsave state? + */ + if (!boot_cpu_has(X86_FEATURE_XSAVE)) + return NULL; + + /* + * We should not ever be requesting features that we + * have not enabled. Remember that pcntxt_mask is + * what we write to the XCR0 register. + */ + WARN_ONCE(!(xfeatures_mask & xstate_feature), + "get of unsupported state"); + /* + * This assumes the last 'xsave*' instruction to + * have requested that 'xstate_feature' be saved. + * If it did not, we might be seeing and old value + * of the field in the buffer. + * + * This can happen because the last 'xsave' did not + * request that this feature be saved (unlikely) + * or because the "init optimization" caused it + * to not be saved. + */ + if (!(xsave->header.xfeatures & xstate_feature)) + return NULL; + + return (void *)xsave + xstate_comp_offsets[feature_nr]; +} +EXPORT_SYMBOL_GPL(get_xsave_addr); + +/* + * This wraps up the common operations that need to occur when retrieving + * data from xsave state. It first ensures that the current task was + * using the FPU and retrieves the data in to a buffer. It then calculates + * the offset of the requested field in the buffer. + * + * This function is safe to call whether the FPU is in use or not. + * + * Note that this only works on the current task. + * + * Inputs: + * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, + * XFEATURE_MASK_SSE, etc...) + * Output: + * address of the state in the xsave area or NULL if the state + * is not present or is in its 'init state'. + */ +const void *get_xsave_field_ptr(int xsave_state) +{ + struct fpu *fpu = ¤t->thread.fpu; + + if (!fpu->fpstate_active) + return NULL; + /* + * fpu__save() takes the CPU's xstate registers + * and saves them off to the 'fpu memory buffer. + */ + fpu__save(fpu); + + return get_xsave_addr(&fpu->state.xsave, xsave_state); +} diff --git a/kernel/arch/x86/kernel/ftrace.c b/kernel/arch/x86/kernel/ftrace.c index 8b7b0a51e..311bcf338 100644 --- a/kernel/arch/x86/kernel/ftrace.c +++ b/kernel/arch/x86/kernel/ftrace.c @@ -556,6 +556,7 @@ void ftrace_replace_code(int enable) run_sync(); report = "updating code"; + count = 0; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); @@ -563,11 +564,13 @@ void ftrace_replace_code(int enable) ret = add_update(rec, enable); if (ret) goto remove_breakpoints; + count++; } run_sync(); report = "removing breakpoints"; + count = 0; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); @@ -575,6 +578,7 @@ void ftrace_replace_code(int enable) ret = finish_update(rec, enable); if (ret) goto remove_breakpoints; + count++; } run_sync(); diff --git a/kernel/arch/x86/kernel/head_32.S b/kernel/arch/x86/kernel/head_32.S index 7e429c99c..6bc9ae24b 100644 --- a/kernel/arch/x86/kernel/head_32.S +++ b/kernel/arch/x86/kernel/head_32.S @@ -152,7 +152,7 @@ ENTRY(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif -#ifdef CONFIG_MICROCODE_EARLY +#ifdef CONFIG_MICROCODE /* Early load ucode on BSP. */ call load_ucode_bsp #endif @@ -311,12 +311,11 @@ ENTRY(startup_32_smp) movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp -#ifdef CONFIG_MICROCODE_EARLY +#ifdef CONFIG_MICROCODE /* Early load ucode on AP. */ call load_ucode_ap #endif - default_entry: #define CR0_STATE (X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \ X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \ @@ -557,7 +556,7 @@ early_idt_handler_common: cld cmpl $2,(%esp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,%ss:early_recursion_flag je hlt_loop @@ -610,7 +609,7 @@ ex_entry: pop %ecx pop %eax decl %ss:early_recursion_flag -is_nmi: +.Lis_nmi: addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler_common) diff --git a/kernel/arch/x86/kernel/head_64.S b/kernel/arch/x86/kernel/head_64.S index 7e5da2cbe..ffdc0e860 100644 --- a/kernel/arch/x86/kernel/head_64.S +++ b/kernel/arch/x86/kernel/head_64.S @@ -65,6 +65,9 @@ startup_64: * tables and then reload them. */ + /* Sanitize CPU configuration */ + call verify_cpu + /* * Compute the delta between the address I am compiled to run at and the * address I am actually running at. @@ -174,6 +177,9 @@ ENTRY(secondary_startup_64) * after the boot processor executes this code. */ + /* Sanitize CPU configuration */ + call verify_cpu + movq $(init_level4_pgt - __START_KERNEL_map), %rax 1: @@ -288,6 +294,8 @@ ENTRY(secondary_startup_64) pushq %rax # target address in negative space lretq +#include "verify_cpu.S" + #ifdef CONFIG_HOTPLUG_CPU /* * Boot CPU0 entry point. It's called from play_dead(). Everything has been set @@ -346,7 +354,7 @@ early_idt_handler_common: cld cmpl $2,(%rsp) # X86_TRAP_NMI - je is_nmi # Ignore NMI + je .Lis_nmi # Ignore NMI cmpl $2,early_recursion_flag(%rip) jz 1f @@ -411,7 +419,7 @@ early_idt_handler_common: popq %rcx popq %rax decl early_recursion_flag(%rip) -is_nmi: +.Lis_nmi: addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler_common) diff --git a/kernel/arch/x86/kernel/hpet.c b/kernel/arch/x86/kernel/hpet.c index 3acbff471..b8e6ff5cd 100644 --- a/kernel/arch/x86/kernel/hpet.c +++ b/kernel/arch/x86/kernel/hpet.c @@ -12,6 +12,7 @@ #include <linux/pm.h> #include <linux/io.h> +#include <asm/irqdomain.h> #include <asm/fixmap.h> #include <asm/hpet.h> #include <asm/time.h> @@ -36,10 +37,10 @@ */ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ -u8 hpet_msi_disable; +bool hpet_msi_disable; #ifdef CONFIG_PCI_MSI -static unsigned long hpet_num_timers; +static unsigned int hpet_num_timers; #endif static void __iomem *hpet_virt_address; @@ -85,9 +86,9 @@ static inline void hpet_clear_mapping(void) /* * HPET command line enable / disable */ -int boot_hpet_disable; -int hpet_force_user; -static int hpet_verbose; +bool boot_hpet_disable; +bool hpet_force_user; +static bool hpet_verbose; static int __init hpet_setup(char *str) { @@ -97,11 +98,11 @@ static int __init hpet_setup(char *str) if (next) *next++ = 0; if (!strncmp("disable", str, 7)) - boot_hpet_disable = 1; + boot_hpet_disable = true; if (!strncmp("force", str, 5)) - hpet_force_user = 1; + hpet_force_user = true; if (!strncmp("verbose", str, 7)) - hpet_verbose = 1; + hpet_verbose = true; str = next; } return 1; @@ -110,7 +111,7 @@ __setup("hpet=", hpet_setup); static int __init disable_hpet(char *str) { - boot_hpet_disable = 1; + boot_hpet_disable = true; return 1; } __setup("nohpet", disable_hpet); @@ -123,7 +124,7 @@ static inline int is_hpet_capable(void) /* * HPET timer interrupt enable / disable */ -static int hpet_legacy_int_enabled; +static bool hpet_legacy_int_enabled; /** * is_hpet_enabled - check whether the hpet timer interrupt is enabled @@ -225,26 +226,11 @@ static void hpet_reserve_platform_timers(unsigned int id) { } */ static unsigned long hpet_freq; -static void hpet_legacy_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt); -static int hpet_legacy_next_event(unsigned long delta, - struct clock_event_device *evt); - -/* - * The hpet clock event device - */ -static struct clock_event_device hpet_clockevent = { - .name = "hpet", - .features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, - .set_mode = hpet_legacy_set_mode, - .set_next_event = hpet_legacy_next_event, - .irq = 0, - .rating = 50, -}; +static struct clock_event_device hpet_clockevent; static void hpet_stop_counter(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + u32 cfg = hpet_readl(HPET_CFG); cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } @@ -286,7 +272,7 @@ static void hpet_enable_legacy_int(void) cfg |= HPET_CFG_LEGACY; hpet_writel(cfg, HPET_CFG); - hpet_legacy_int_enabled = 1; + hpet_legacy_int_enabled = true; } static void hpet_legacy_clockevent_register(void) @@ -305,66 +291,74 @@ static void hpet_legacy_clockevent_register(void) printk(KERN_DEBUG "hpet clockevent registered\n"); } -static int hpet_setup_msi_irq(unsigned int irq); - -static void hpet_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt, int timer) +static int hpet_set_periodic(struct clock_event_device *evt, int timer) { unsigned int cfg, cmp, now; uint64_t delta; - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - hpet_stop_counter(); - delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; - delta >>= evt->shift; - now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned int) delta; - cfg = hpet_readl(HPET_Tn_CFG(timer)); - cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | - HPET_TN_SETVAL | HPET_TN_32BIT; - hpet_writel(cfg, HPET_Tn_CFG(timer)); - hpet_writel(cmp, HPET_Tn_CMP(timer)); - udelay(1); - /* - * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL - * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL - * bit is automatically cleared after the first write. - * (See AMD-8111 HyperTransport I/O Hub Data Sheet, - * Publication # 24674) - */ - hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer)); - hpet_start_counter(); - hpet_print_config(); - break; + hpet_stop_counter(); + delta = ((uint64_t)(NSEC_PER_SEC / HZ)) * evt->mult; + delta >>= evt->shift; + now = hpet_readl(HPET_COUNTER); + cmp = now + (unsigned int)delta; + cfg = hpet_readl(HPET_Tn_CFG(timer)); + cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | + HPET_TN_32BIT; + hpet_writel(cfg, HPET_Tn_CFG(timer)); + hpet_writel(cmp, HPET_Tn_CMP(timer)); + udelay(1); + /* + * HPET on AMD 81xx needs a second write (with HPET_TN_SETVAL + * cleared) to T0_CMP to set the period. The HPET_TN_SETVAL + * bit is automatically cleared after the first write. + * (See AMD-8111 HyperTransport I/O Hub Data Sheet, + * Publication # 24674) + */ + hpet_writel((unsigned int)delta, HPET_Tn_CMP(timer)); + hpet_start_counter(); + hpet_print_config(); - case CLOCK_EVT_MODE_ONESHOT: - cfg = hpet_readl(HPET_Tn_CFG(timer)); - cfg &= ~HPET_TN_PERIODIC; - cfg |= HPET_TN_ENABLE | HPET_TN_32BIT; - hpet_writel(cfg, HPET_Tn_CFG(timer)); - break; + return 0; +} - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - cfg = hpet_readl(HPET_Tn_CFG(timer)); - cfg &= ~HPET_TN_ENABLE; - hpet_writel(cfg, HPET_Tn_CFG(timer)); - break; +static int hpet_set_oneshot(struct clock_event_device *evt, int timer) +{ + unsigned int cfg; - case CLOCK_EVT_MODE_RESUME: - if (timer == 0) { - hpet_enable_legacy_int(); - } else { - struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - hpet_setup_msi_irq(hdev->irq); - disable_irq(hdev->irq); - irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); - enable_irq(hdev->irq); - } - hpet_print_config(); - break; + cfg = hpet_readl(HPET_Tn_CFG(timer)); + cfg &= ~HPET_TN_PERIODIC; + cfg |= HPET_TN_ENABLE | HPET_TN_32BIT; + hpet_writel(cfg, HPET_Tn_CFG(timer)); + + return 0; +} + +static int hpet_shutdown(struct clock_event_device *evt, int timer) +{ + unsigned int cfg; + + cfg = hpet_readl(HPET_Tn_CFG(timer)); + cfg &= ~HPET_TN_ENABLE; + hpet_writel(cfg, HPET_Tn_CFG(timer)); + + return 0; +} + +static int hpet_resume(struct clock_event_device *evt, int timer) +{ + if (!timer) { + hpet_enable_legacy_int(); + } else { + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + + irq_domain_activate_irq(irq_get_irq_data(hdev->irq)); + disable_irq(hdev->irq); + irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); + enable_irq(hdev->irq); } + hpet_print_config(); + + return 0; } static int hpet_next_event(unsigned long delta, @@ -404,10 +398,24 @@ static int hpet_next_event(unsigned long delta, return res < HPET_MIN_CYCLES ? -ETIME : 0; } -static void hpet_legacy_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int hpet_legacy_shutdown(struct clock_event_device *evt) +{ + return hpet_shutdown(evt, 0); +} + +static int hpet_legacy_set_oneshot(struct clock_event_device *evt) { - hpet_set_mode(mode, evt, 0); + return hpet_set_oneshot(evt, 0); +} + +static int hpet_legacy_set_periodic(struct clock_event_device *evt) +{ + return hpet_set_periodic(evt, 0); +} + +static int hpet_legacy_resume(struct clock_event_device *evt) +{ + return hpet_resume(evt, 0); } static int hpet_legacy_next_event(unsigned long delta, @@ -417,16 +425,33 @@ static int hpet_legacy_next_event(unsigned long delta, } /* + * The hpet clock event device + */ +static struct clock_event_device hpet_clockevent = { + .name = "hpet", + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + .set_state_periodic = hpet_legacy_set_periodic, + .set_state_oneshot = hpet_legacy_set_oneshot, + .set_state_shutdown = hpet_legacy_shutdown, + .tick_resume = hpet_legacy_resume, + .set_next_event = hpet_legacy_next_event, + .irq = 0, + .rating = 50, +}; + +/* * HPET MSI Support */ #ifdef CONFIG_PCI_MSI static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev); static struct hpet_dev *hpet_devs; +static struct irq_domain *hpet_domain; void hpet_msi_unmask(struct irq_data *data) { - struct hpet_dev *hdev = data->handler_data; + struct hpet_dev *hdev = irq_data_get_irq_handler_data(data); unsigned int cfg; /* unmask it */ @@ -437,7 +462,7 @@ void hpet_msi_unmask(struct irq_data *data) void hpet_msi_mask(struct irq_data *data) { - struct hpet_dev *hdev = data->handler_data; + struct hpet_dev *hdev = irq_data_get_irq_handler_data(data); unsigned int cfg; /* mask it */ @@ -459,43 +484,39 @@ void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg) msg->address_hi = 0; } -static void hpet_msi_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int hpet_msi_shutdown(struct clock_event_device *evt) { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - hpet_set_mode(mode, evt, hdev->num); + + return hpet_shutdown(evt, hdev->num); } -static int hpet_msi_next_event(unsigned long delta, - struct clock_event_device *evt) +static int hpet_msi_set_oneshot(struct clock_event_device *evt) { struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - return hpet_next_event(delta, evt, hdev->num); -} -static int hpet_setup_msi_irq(unsigned int irq) -{ - if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { - irq_free_hwirq(irq); - return -EINVAL; - } - return 0; + return hpet_set_oneshot(evt, hdev->num); } -static int hpet_assign_irq(struct hpet_dev *dev) +static int hpet_msi_set_periodic(struct clock_event_device *evt) { - unsigned int irq = irq_alloc_hwirq(-1); + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - if (!irq) - return -EINVAL; + return hpet_set_periodic(evt, hdev->num); +} - irq_set_handler_data(irq, dev); +static int hpet_msi_resume(struct clock_event_device *evt) +{ + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); - if (hpet_setup_msi_irq(irq)) - return -EINVAL; + return hpet_resume(evt, hdev->num); +} - dev->irq = irq; - return 0; +static int hpet_msi_next_event(unsigned long delta, + struct clock_event_device *evt) +{ + struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt); + return hpet_next_event(delta, evt, hdev->num); } static irqreturn_t hpet_interrupt_handler(int irq, void *data) @@ -540,9 +561,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) if (!(hdev->flags & HPET_DEV_VALID)) return; - if (hpet_setup_msi_irq(hdev->irq)) - return; - hdev->cpu = cpu; per_cpu(cpu_hpet_dev, cpu) = hdev; evt->name = hdev->name; @@ -551,10 +569,14 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu) evt->rating = 110; evt->features = CLOCK_EVT_FEAT_ONESHOT; - if (hdev->flags & HPET_DEV_PERI_CAP) + if (hdev->flags & HPET_DEV_PERI_CAP) { evt->features |= CLOCK_EVT_FEAT_PERIODIC; + evt->set_state_periodic = hpet_msi_set_periodic; + } - evt->set_mode = hpet_msi_set_mode; + evt->set_state_shutdown = hpet_msi_shutdown; + evt->set_state_oneshot = hpet_msi_set_oneshot; + evt->tick_resume = hpet_msi_resume; evt->set_next_event = hpet_msi_next_event; evt->cpumask = cpumask_of(hdev->cpu); @@ -574,7 +596,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int id; unsigned int num_timers; unsigned int num_timers_used = 0; - int i; + int i, irq; if (hpet_msi_disable) return; @@ -587,6 +609,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) num_timers++; /* Value read out starts from 0 */ hpet_print_config(); + hpet_domain = hpet_create_irq_domain(hpet_blockid); + if (!hpet_domain) + return; + hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL); if (!hpet_devs) return; @@ -604,12 +630,14 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) hdev->flags = 0; if (cfg & HPET_TN_PERIODIC_CAP) hdev->flags |= HPET_DEV_PERI_CAP; + sprintf(hdev->name, "hpet%d", i); hdev->num = i; - sprintf(hdev->name, "hpet%d", i); - if (hpet_assign_irq(hdev)) + irq = hpet_assign_irq(hpet_domain, hdev, hdev->num); + if (irq <= 0) continue; + hdev->irq = irq; hdev->flags |= HPET_DEV_FSB_CAP; hdev->flags |= HPET_DEV_VALID; num_timers_used++; @@ -709,10 +737,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n, } #else -static int hpet_setup_msi_irq(unsigned int irq) -{ - return 0; -} static void hpet_msi_capability_lookup(unsigned int start_timer) { return; @@ -761,7 +785,7 @@ static int hpet_clocksource_register(void) /* Verify whether hpet counter works */ t1 = hpet_readl(HPET_COUNTER); - rdtscll(start); + start = rdtsc(); /* * We don't know the TSC frequency yet, but waiting for @@ -771,7 +795,7 @@ static int hpet_clocksource_register(void) */ do { rep_nop(); - rdtscll(now); + now = rdtsc(); } while ((now - start) < 200000UL); if (t1 == hpet_readl(HPET_COUNTER)) { @@ -959,7 +983,7 @@ void hpet_disable(void) cfg = *hpet_boot_cfg; else if (hpet_legacy_int_enabled) { cfg &= ~HPET_CFG_LEGACY; - hpet_legacy_int_enabled = 0; + hpet_legacy_int_enabled = false; } cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); @@ -1097,8 +1121,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_timer_init); static void hpet_disable_rtc_channel(void) { - unsigned long cfg; - cfg = hpet_readl(HPET_T1_CFG); + u32 cfg = hpet_readl(HPET_T1_CFG); cfg &= ~HPET_TN_ENABLE; hpet_writel(cfg, HPET_T1_CFG); } diff --git a/kernel/arch/x86/kernel/hw_breakpoint.c b/kernel/arch/x86/kernel/hw_breakpoint.c index 7114ba220..50a3fad5b 100644 --- a/kernel/arch/x86/kernel/hw_breakpoint.c +++ b/kernel/arch/x86/kernel/hw_breakpoint.c @@ -32,6 +32,7 @@ #include <linux/irqflags.h> #include <linux/notifier.h> #include <linux/kallsyms.h> +#include <linux/kprobes.h> #include <linux/percpu.h> #include <linux/kdebug.h> #include <linux/kernel.h> @@ -179,7 +180,11 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp) va = info->address; len = bp->attr.bp_len; - return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); + /* + * We don't need to worry about va + len - 1 overflowing: + * we already require that va is aligned to a multiple of len. + */ + return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); } int arch_bp_generic_fields(int x86_len, int x86_type, @@ -243,6 +248,20 @@ static int arch_build_bp_info(struct perf_event *bp) info->type = X86_BREAKPOINT_RW; break; case HW_BREAKPOINT_X: + /* + * We don't allow kernel breakpoints in places that are not + * acceptable for kprobes. On non-kprobes kernels, we don't + * allow kernel breakpoints at all. + */ + if (bp->attr.bp_addr >= TASK_SIZE_MAX) { +#ifdef CONFIG_KPROBES + if (within_kprobe_blacklist(bp->attr.bp_addr)) + return -EINVAL; +#else + return -EINVAL; +#endif + } + info->type = X86_BREAKPOINT_EXECUTE; /* * x86 inst breakpoints need to have a specific undefined len. @@ -276,8 +295,18 @@ static int arch_build_bp_info(struct perf_event *bp) break; #endif default: + /* AMD range breakpoint */ if (!is_power_of_2(bp->attr.bp_len)) return -EINVAL; + if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) + return -EINVAL; + /* + * It's impossible to use a range breakpoint to fake out + * user vs kernel detection because bp_len - 1 can't + * have the high bit set. If we ever allow range instruction + * breakpoints, then we'll have to check for kprobe-blacklisted + * addresses anywhere in the range. + */ if (!cpu_has_bpext) return -EOPNOTSUPP; info->mask = bp->attr.bp_len - 1; diff --git a/kernel/arch/x86/kernel/i386_ksyms_32.c b/kernel/arch/x86/kernel/i386_ksyms_32.c index 05fd74f53..64341aa48 100644 --- a/kernel/arch/x86/kernel/i386_ksyms_32.c +++ b/kernel/arch/x86/kernel/i386_ksyms_32.c @@ -40,7 +40,5 @@ EXPORT_SYMBOL(empty_zero_page); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/kernel/arch/x86/kernel/i387.c b/kernel/arch/x86/kernel/i387.c deleted file mode 100644 index 6185d3141..000000000 --- a/kernel/arch/x86/kernel/i387.c +++ /dev/null @@ -1,671 +0,0 @@ -/* - * Copyright (C) 1994 Linus Torvalds - * - * Pentium III FXSR, SSE support - * General FPU state handling cleanups - * Gareth Hughes <gareth@valinux.com>, May 2000 - */ -#include <linux/module.h> -#include <linux/regset.h> -#include <linux/sched.h> -#include <linux/slab.h> - -#include <asm/sigcontext.h> -#include <asm/processor.h> -#include <asm/math_emu.h> -#include <asm/tlbflush.h> -#include <asm/uaccess.h> -#include <asm/ptrace.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/user.h> - -static DEFINE_PER_CPU(bool, in_kernel_fpu); - -void kernel_fpu_disable(void) -{ - WARN_ON(this_cpu_read(in_kernel_fpu)); - this_cpu_write(in_kernel_fpu, true); -} - -void kernel_fpu_enable(void) -{ - this_cpu_write(in_kernel_fpu, false); -} - -/* - * Were we in an interrupt that interrupted kernel mode? - * - * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that - * pair does nothing at all: the thread must not have fpu (so - * that we don't try to save the FPU state), and TS must - * be set (so that the clts/stts pair does nothing that is - * visible in the interrupted kernel thread). - * - * Except for the eagerfpu case when we return true; in the likely case - * the thread has FPU but we are not going to set/clear TS. - */ -static inline bool interrupted_kernel_fpu_idle(void) -{ - if (this_cpu_read(in_kernel_fpu)) - return false; - - if (use_eager_fpu()) - return true; - - return !__thread_has_fpu(current) && - (read_cr0() & X86_CR0_TS); -} - -/* - * Were we in user mode (or vm86 mode) when we were - * interrupted? - * - * Doing kernel_fpu_begin/end() is ok if we are running - * in an interrupt context from user mode - we'll just - * save the FPU state as required. - */ -static inline bool interrupted_user_mode(void) -{ - struct pt_regs *regs = get_irq_regs(); - return regs && user_mode(regs); -} - -/* - * Can we use the FPU in kernel mode with the - * whole "kernel_fpu_begin/end()" sequence? - * - * It's always ok in process context (ie "not interrupt") - * but it is sometimes ok even from an irq. - */ -bool irq_fpu_usable(void) -{ - return !in_interrupt() || - interrupted_user_mode() || - interrupted_kernel_fpu_idle(); -} -EXPORT_SYMBOL(irq_fpu_usable); - -void __kernel_fpu_begin(void) -{ - struct task_struct *me = current; - - this_cpu_write(in_kernel_fpu, true); - - if (__thread_has_fpu(me)) { - __save_init_fpu(me); - } else { - this_cpu_write(fpu_owner_task, NULL); - if (!use_eager_fpu()) - clts(); - } -} -EXPORT_SYMBOL(__kernel_fpu_begin); - -void __kernel_fpu_end(void) -{ - struct task_struct *me = current; - - if (__thread_has_fpu(me)) { - if (WARN_ON(restore_fpu_checking(me))) - fpu_reset_state(me); - } else if (!use_eager_fpu()) { - stts(); - } - - this_cpu_write(in_kernel_fpu, false); -} -EXPORT_SYMBOL(__kernel_fpu_end); - -void unlazy_fpu(struct task_struct *tsk) -{ - preempt_disable(); - if (__thread_has_fpu(tsk)) { - if (use_eager_fpu()) { - __save_fpu(tsk); - } else { - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - } - } - preempt_enable(); -} -EXPORT_SYMBOL(unlazy_fpu); - -unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; -unsigned int xstate_size; -EXPORT_SYMBOL_GPL(xstate_size); -static struct i387_fxsave_struct fx_scratch; - -static void mxcsr_feature_mask_init(void) -{ - unsigned long mask = 0; - - if (cpu_has_fxsr) { - memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : "+m" (fx_scratch)); - mask = fx_scratch.mxcsr_mask; - if (mask == 0) - mask = 0x0000ffbf; - } - mxcsr_feature_mask &= mask; -} - -static void init_thread_xstate(void) -{ - /* - * Note that xstate_size might be overwriten later during - * xsave_init(). - */ - - if (!cpu_has_fpu) { - /* - * Disable xsave as we do not support it if i387 - * emulation is enabled. - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVE); - setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); - xstate_size = sizeof(struct i387_soft_struct); - return; - } - - if (cpu_has_fxsr) - xstate_size = sizeof(struct i387_fxsave_struct); - else - xstate_size = sizeof(struct i387_fsave_struct); - - /* - * Quirk: we don't yet handle the XSAVES* instructions - * correctly, as we don't correctly convert between - * standard and compacted format when interfacing - * with user-space - so disable it for now. - * - * The difference is small: with recent CPUs the - * compacted format is only marginally smaller than - * the standard FPU state format. - * - * ( This is easy to backport while we are fixing - * XSAVES* support. ) - */ - setup_clear_cpu_cap(X86_FEATURE_XSAVES); -} - -/* - * Called at bootup to set up the initial FPU state that is later cloned - * into all processes. - */ - -void fpu_init(void) -{ - unsigned long cr0; - unsigned long cr4_mask = 0; - -#ifndef CONFIG_MATH_EMULATION - if (!cpu_has_fpu) { - pr_emerg("No FPU found and no math emulation present\n"); - pr_emerg("Giving up\n"); - for (;;) - asm volatile("hlt"); - } -#endif - if (cpu_has_fxsr) - cr4_mask |= X86_CR4_OSFXSR; - if (cpu_has_xmm) - cr4_mask |= X86_CR4_OSXMMEXCPT; - if (cr4_mask) - cr4_set_bits(cr4_mask); - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */ - if (!cpu_has_fpu) - cr0 |= X86_CR0_EM; - write_cr0(cr0); - - /* - * init_thread_xstate is only called once to avoid overriding - * xstate_size during boot time or during CPU hotplug. - */ - if (xstate_size == 0) - init_thread_xstate(); - - mxcsr_feature_mask_init(); - xsave_init(); - eager_fpu_init(); -} - -void fpu_finit(struct fpu *fpu) -{ - if (!cpu_has_fpu) { - finit_soft_fpu(&fpu->state->soft); - return; - } - - memset(fpu->state, 0, xstate_size); - - if (cpu_has_fxsr) { - fx_finit(&fpu->state->fxsave); - } else { - struct i387_fsave_struct *fp = &fpu->state->fsave; - fp->cwd = 0xffff037fu; - fp->swd = 0xffff0000u; - fp->twd = 0xffffffffu; - fp->fos = 0xffff0000u; - } -} -EXPORT_SYMBOL_GPL(fpu_finit); - -/* - * The _current_ task is using the FPU for the first time - * so initialize it and set the mxcsr to its default - * value at reset if we support XMM instructions and then - * remember the current task has used the FPU. - */ -int init_fpu(struct task_struct *tsk) -{ - int ret; - - if (tsk_used_math(tsk)) { - if (cpu_has_fpu && tsk == current) - unlazy_fpu(tsk); - task_disable_lazy_fpu_restore(tsk); - return 0; - } - - /* - * Memory allocation at the first usage of the FPU and other state. - */ - ret = fpu_alloc(&tsk->thread.fpu); - if (ret) - return ret; - - fpu_finit(&tsk->thread.fpu); - - set_stopped_child_used_math(tsk); - return 0; -} -EXPORT_SYMBOL_GPL(init_fpu); - -/* - * The xstateregs_active() routine is the same as the fpregs_active() routine, - * as the "regset->n" for the xstate regset will be updated based on the feature - * capabilites supported by the xsave. - */ -int fpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return tsk_used_math(target) ? regset->n : 0; -} - -int xfpregs_active(struct task_struct *target, const struct user_regset *regset) -{ - return (cpu_has_fxsr && tsk_used_math(target)) ? regset->n : 0; -} - -int xfpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); -} - -int xfpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret; - - if (!cpu_has_fxsr) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fxsave, 0, -1); - - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - - /* - * update the header bits in the xsave header, indicating the - * presence of FP and SSE state. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE; - - return ret; -} - -int xstateregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - /* - * Copy the 48bytes defined by the software first into the xstate - * memory layout in the thread struct, so that we can copy the entire - * xstateregs to the user using one user_regset_copyout(). - */ - memcpy(&xsave->i387.sw_reserved, - xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); - /* - * Copy the xstate memory layout. - */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - return ret; -} - -int xstateregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct xsave_struct *xsave; - int ret; - - if (!cpu_has_xsave) - return -ENODEV; - - ret = init_fpu(target); - if (ret) - return ret; - - xsave = &target->thread.fpu.state->xsave; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); - /* - * mxcsr reserved bits must be masked to zero for security reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - xsave->xsave_hdr.xstate_bv &= pcntxt_mask; - /* - * These bits must be zero. - */ - memset(&xsave->xsave_hdr.reserved, 0, 48); - return ret; -} - -#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION - -/* - * FPU tag word conversions. - */ - -static inline unsigned short twd_i387_to_fxsr(unsigned short twd) -{ - unsigned int tmp; /* to avoid 16 bit prefixes in the code */ - - /* Transform each pair of bits into 01 (valid) or 00 (empty) */ - tmp = ~twd; - tmp = (tmp | (tmp>>1)) & 0x5555; /* 0V0V0V0V0V0V0V0V */ - /* and move the valid bits to the lower byte. */ - tmp = (tmp | (tmp >> 1)) & 0x3333; /* 00VV00VV00VV00VV */ - tmp = (tmp | (tmp >> 2)) & 0x0f0f; /* 0000VVVV0000VVVV */ - tmp = (tmp | (tmp >> 4)) & 0x00ff; /* 00000000VVVVVVVV */ - - return tmp; -} - -#define FPREG_ADDR(f, n) ((void *)&(f)->st_space + (n) * 16) -#define FP_EXP_TAG_VALID 0 -#define FP_EXP_TAG_ZERO 1 -#define FP_EXP_TAG_SPECIAL 2 -#define FP_EXP_TAG_EMPTY 3 - -static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) -{ - struct _fpxreg *st; - u32 tos = (fxsave->swd >> 11) & 7; - u32 twd = (unsigned long) fxsave->twd; - u32 tag; - u32 ret = 0xffff0000u; - int i; - - for (i = 0; i < 8; i++, twd >>= 1) { - if (twd & 0x1) { - st = FPREG_ADDR(fxsave, (i - tos) & 7); - - switch (st->exponent & 0x7fff) { - case 0x7fff: - tag = FP_EXP_TAG_SPECIAL; - break; - case 0x0000: - if (!st->significand[0] && - !st->significand[1] && - !st->significand[2] && - !st->significand[3]) - tag = FP_EXP_TAG_ZERO; - else - tag = FP_EXP_TAG_SPECIAL; - break; - default: - if (st->significand[3] & 0x8000) - tag = FP_EXP_TAG_VALID; - else - tag = FP_EXP_TAG_SPECIAL; - break; - } - } else { - tag = FP_EXP_TAG_EMPTY; - } - ret |= tag << (2 * i); - } - return ret; -} - -/* - * FXSR floating point environment conversions. - */ - -void -convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - env->cwd = fxsave->cwd | 0xffff0000u; - env->swd = fxsave->swd | 0xffff0000u; - env->twd = twd_fxsr_to_i387(fxsave); - -#ifdef CONFIG_X86_64 - env->fip = fxsave->rip; - env->foo = fxsave->rdp; - /* - * should be actually ds/cs at fpu exception time, but - * that information is not available in 64bit mode. - */ - env->fcs = task_pt_regs(tsk)->cs; - if (tsk == current) { - savesegment(ds, env->fos); - } else { - env->fos = tsk->thread.ds; - } - env->fos |= 0xffff0000; -#else - env->fip = fxsave->fip; - env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16); - env->foo = fxsave->foo; - env->fos = fxsave->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(to[0])); -} - -void convert_to_fxsr(struct task_struct *tsk, - const struct user_i387_ia32_struct *env) - -{ - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; - struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; - struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; - int i; - - fxsave->cwd = env->cwd; - fxsave->swd = env->swd; - fxsave->twd = twd_i387_to_fxsr(env->twd); - fxsave->fop = (u16) ((u32) env->fcs >> 16); -#ifdef CONFIG_X86_64 - fxsave->rip = env->fip; - fxsave->rdp = env->foo; - /* cs and ds ignored */ -#else - fxsave->fip = env->fip; - fxsave->fcs = (env->fcs & 0xffff); - fxsave->foo = env->foo; - fxsave->fos = env->fos; -#endif - - for (i = 0; i < 8; ++i) - memcpy(&to[i], &from[i], sizeof(from[0])); -} - -int fpregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - sanitize_i387_state(target); - - if (kbuf && pos == 0 && count == sizeof(env)) { - convert_from_fxsr(kbuf, target); - return 0; - } - - convert_from_fxsr(&env, target); - - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &env, 0, -1); -} - -int fpregs_set(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - struct user_i387_ia32_struct env; - int ret; - - ret = init_fpu(target); - if (ret) - return ret; - - sanitize_i387_state(target); - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); - - if (!cpu_has_fxsr) - return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->fsave, 0, - -1); - - if (pos > 0 || count < sizeof(env)) - convert_from_fxsr(&env, target); - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &env, 0, -1); - if (!ret) - convert_to_fxsr(target, &env); - - /* - * update the header bit in the xsave header, indicating the - * presence of FP. - */ - if (cpu_has_xsave) - target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP; - return ret; -} - -/* - * FPU state for core dumps. - * This is only used for a.out dumps now. - * It is declared generically using elf_fpregset_t (which is - * struct user_i387_struct) but is in fact only used for 32-bit - * dumps, so on 64-bit it is really struct user_i387_ia32_struct. - */ -int dump_fpu(struct pt_regs *regs, struct user_i387_struct *fpu) -{ - struct task_struct *tsk = current; - int fpvalid; - - fpvalid = !!used_math(); - if (fpvalid) - fpvalid = !fpregs_get(tsk, NULL, - 0, sizeof(struct user_i387_ia32_struct), - fpu, NULL); - - return fpvalid; -} -EXPORT_SYMBOL(dump_fpu); - -#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ - -static int __init no_387(char *s) -{ - setup_clear_cpu_cap(X86_FEATURE_FPU); - return 1; -} - -__setup("no387", no_387); - -void fpu_detect(struct cpuinfo_x86 *c) -{ - unsigned long cr0; - u16 fsw, fcw; - - fsw = fcw = 0xffff; - - cr0 = read_cr0(); - cr0 &= ~(X86_CR0_TS | X86_CR0_EM); - write_cr0(cr0); - - asm volatile("fninit ; fnstsw %0 ; fnstcw %1" - : "+m" (fsw), "+m" (fcw)); - - if (fsw == 0 && (fcw & 0x103f) == 0x003f) - set_cpu_cap(c, X86_FEATURE_FPU); - else - clear_cpu_cap(c, X86_FEATURE_FPU); - - /* The final cr0 value is set in fpu_init() */ -} diff --git a/kernel/arch/x86/kernel/i8253.c b/kernel/arch/x86/kernel/i8253.c index f2b96de3c..efb82f07b 100644 --- a/kernel/arch/x86/kernel/i8253.c +++ b/kernel/arch/x86/kernel/i8253.c @@ -34,7 +34,7 @@ static int __init init_pit_clocksource(void) * - when local APIC timer is active (PIT is switched off) */ if (num_possible_cpus() > 1 || is_hpet_enabled() || - i8253_clockevent.mode != CLOCK_EVT_MODE_PERIODIC) + !clockevent_state_periodic(&i8253_clockevent)) return 0; return clocksource_i8253_init(); diff --git a/kernel/arch/x86/kernel/i8259.c b/kernel/arch/x86/kernel/i8259.c index e7cc5370c..be22f5a21 100644 --- a/kernel/arch/x86/kernel/i8259.c +++ b/kernel/arch/x86/kernel/i8259.c @@ -295,16 +295,11 @@ static void unmask_8259A(void) raw_spin_unlock_irqrestore(&i8259A_lock, flags); } -static void init_8259A(int auto_eoi) +static int probe_8259A(void) { unsigned long flags; unsigned char probe_val = ~(1 << PIC_CASCADE_IR); unsigned char new_val; - - i8259A_auto_eoi = auto_eoi; - - raw_spin_lock_irqsave(&i8259A_lock, flags); - /* * Check to see if we have a PIC. * Mask all except the cascade and read @@ -312,16 +307,28 @@ static void init_8259A(int auto_eoi) * have a PIC, we will read 0xff as opposed to the * value we wrote. */ + raw_spin_lock_irqsave(&i8259A_lock, flags); + outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ outb(probe_val, PIC_MASTER_IMR); new_val = inb(PIC_MASTER_IMR); if (new_val != probe_val) { printk(KERN_INFO "Using NULL legacy PIC\n"); legacy_pic = &null_legacy_pic; - raw_spin_unlock_irqrestore(&i8259A_lock, flags); - return; } + raw_spin_unlock_irqrestore(&i8259A_lock, flags); + return nr_legacy_irqs(); +} + +static void init_8259A(int auto_eoi) +{ + unsigned long flags; + + i8259A_auto_eoi = auto_eoi; + + raw_spin_lock_irqsave(&i8259A_lock, flags); + outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ /* @@ -329,8 +336,8 @@ static void init_8259A(int auto_eoi) */ outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */ - /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */ - outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR); + /* ICW2: 8259A-1 IR0-7 mapped to ISA_IRQ_VECTOR(0) */ + outb_pic(ISA_IRQ_VECTOR(0), PIC_MASTER_IMR); /* 8259A-1 (the master) has a slave on IR2 */ outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR); @@ -342,8 +349,8 @@ static void init_8259A(int auto_eoi) outb_pic(0x11, PIC_SLAVE_CMD); /* ICW1: select 8259A-2 init */ - /* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */ - outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR); + /* ICW2: 8259A-2 IR0-7 mapped to ISA_IRQ_VECTOR(8) */ + outb_pic(ISA_IRQ_VECTOR(8), PIC_SLAVE_IMR); /* 8259A-2 is a slave on master's IR2 */ outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */ @@ -379,6 +386,10 @@ static int legacy_pic_irq_pending_noop(unsigned int irq) { return 0; } +static int legacy_pic_probe(void) +{ + return 0; +} struct legacy_pic null_legacy_pic = { .nr_legacy_irqs = 0, @@ -388,6 +399,7 @@ struct legacy_pic null_legacy_pic = { .mask_all = legacy_pic_noop, .restore_mask = legacy_pic_noop, .init = legacy_pic_int_noop, + .probe = legacy_pic_probe, .irq_pending = legacy_pic_irq_pending_noop, .make_irq = legacy_pic_uint_noop, }; @@ -400,6 +412,7 @@ struct legacy_pic default_legacy_pic = { .mask_all = mask_8259A, .restore_mask = unmask_8259A, .init = init_8259A, + .probe = probe_8259A, .irq_pending = i8259A_irq_pending, .make_irq = make_8259A_irq, }; diff --git a/kernel/arch/x86/kernel/irq.c b/kernel/arch/x86/kernel/irq.c index e5952c225..61521dc19 100644 --- a/kernel/arch/x86/kernel/irq.c +++ b/kernel/arch/x86/kernel/irq.c @@ -22,6 +22,12 @@ #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> +DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); +EXPORT_PER_CPU_SYMBOL(irq_stat); + +DEFINE_PER_CPU(struct pt_regs *, irq_regs); +EXPORT_PER_CPU_SYMBOL(irq_regs); + atomic_t irq_err_count; /* Function pointer for generic interrupt vector handling */ @@ -116,6 +122,12 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count); seq_puts(p, " Threshold APIC interrupts\n"); #endif +#ifdef CONFIG_X86_MCE_AMD + seq_printf(p, "%*s: ", prec, "DFR"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_deferred_error_count); + seq_puts(p, " Deferred Error APIC interrupts\n"); +#endif #ifdef CONFIG_X86_MCE seq_printf(p, "%*s: ", prec, "MCE"); for_each_online_cpu(j) @@ -127,15 +139,30 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Machine check polls\n"); #endif #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN) - seq_printf(p, "%*s: ", prec, "HYP"); - for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count); - seq_puts(p, " Hypervisor callback interrupts\n"); + if (test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors)) { + seq_printf(p, "%*s: ", prec, "HYP"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->irq_hv_callback_count); + seq_puts(p, " Hypervisor callback interrupts\n"); + } #endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); #endif +#ifdef CONFIG_HAVE_KVM + seq_printf(p, "%*s: ", prec, "PIN"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); + seq_puts(p, " Posted-interrupt notification event\n"); + + seq_printf(p, "%*s: ", prec, "PIW"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", + irq_stats(j)->kvm_posted_intr_wakeup_ipis); + seq_puts(p, " Posted-interrupt wakeup event\n"); +#endif return 0; } @@ -187,29 +214,42 @@ u64 arch_irq_stat(void) __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - + struct irq_desc * desc; /* high bit used in ret_from_ code */ unsigned vector = ~regs->orig_ax; - unsigned irq; - irq_enter(); - exit_idle(); + /* + * NB: Unlike exception entries, IRQ entries do not reliably + * handle context tracking in the low-level entry code. This is + * because syscall entries execute briefly with IRQs on before + * updating context tracking state, so we can take an IRQ from + * kernel mode with CONTEXT_USER. The low-level entry code only + * updates the context if we came from user mode, so we won't + * switch to CONTEXT_KERNEL. We'll fix that once the syscall + * code is cleaned up enough that we can cleanly defer enabling + * IRQs. + */ - irq = __this_cpu_read(vector_irq[vector]); + entering_irq(); - if (!handle_irq(irq, regs)) { + /* entering_irq() tells RCU that we're not quiescent. Check it. */ + RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); + + desc = __this_cpu_read(vector_irq[vector]); + + if (!handle_irq(desc, regs)) { ack_APIC_irq(); - if (irq != VECTOR_RETRIGGERED) { - pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n", + if (desc != VECTOR_RETRIGGERED) { + pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n", __func__, smp_processor_id(), - vector, irq); + vector); } else { - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } - irq_exit(); + exiting_irq(); set_irq_regs(old_regs); return 1; @@ -237,6 +277,18 @@ __visible void smp_x86_platform_ipi(struct pt_regs *regs) } #ifdef CONFIG_HAVE_KVM +static void dummy_handler(void) {} +static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler; + +void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)) +{ + if (handler) + kvm_posted_intr_wakeup_handler = handler; + else + kvm_posted_intr_wakeup_handler = dummy_handler; +} +EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); + /* * Handler for POSTED_INTERRUPT_VECTOR. */ @@ -244,16 +296,23 @@ __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - ack_APIC_irq(); - - irq_enter(); - - exit_idle(); - + entering_ack_irq(); inc_irq_stat(kvm_posted_intr_ipis); + exiting_irq(); + set_irq_regs(old_regs); +} - irq_exit(); +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + entering_ack_irq(); + inc_irq_stat(kvm_posted_intr_wakeup_ipis); + kvm_posted_intr_wakeup_handler(); + exiting_irq(); set_irq_regs(old_regs); } #endif @@ -288,10 +347,10 @@ static struct cpumask affinity_new, online_new; */ int check_irq_vectors_for_cpu_disable(void) { - int irq, cpu; unsigned int this_cpu, vector, this_count, count; struct irq_desc *desc; struct irq_data *data; + int cpu; this_cpu = smp_processor_id(); cpumask_copy(&online_new, cpu_online_mask); @@ -299,39 +358,43 @@ int check_irq_vectors_for_cpu_disable(void) this_count = 0; for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - irq = __this_cpu_read(vector_irq[vector]); - if (irq >= 0) { - desc = irq_to_desc(irq); - if (!desc) - continue; + desc = __this_cpu_read(vector_irq[vector]); + if (IS_ERR_OR_NULL(desc)) + continue; + /* + * Protect against concurrent action removal, affinity + * changes etc. + */ + raw_spin_lock(&desc->lock); + data = irq_desc_get_irq_data(desc); + cpumask_copy(&affinity_new, + irq_data_get_affinity_mask(data)); + cpumask_clear_cpu(this_cpu, &affinity_new); - data = irq_desc_get_irq_data(desc); - cpumask_copy(&affinity_new, data->affinity); - cpumask_clear_cpu(this_cpu, &affinity_new); - - /* Do not count inactive or per-cpu irqs. */ - if (!irq_has_action(irq) || irqd_is_per_cpu(data)) - continue; - - /* - * A single irq may be mapped to multiple - * cpu's vector_irq[] (for example IOAPIC cluster - * mode). In this case we have two - * possibilities: - * - * 1) the resulting affinity mask is empty; that is - * this the down'd cpu is the last cpu in the irq's - * affinity mask, or - * - * 2) the resulting affinity mask is no longer - * a subset of the online cpus but the affinity - * mask is not zero; that is the down'd cpu is the - * last online cpu in a user set affinity mask. - */ - if (cpumask_empty(&affinity_new) || - !cpumask_subset(&affinity_new, &online_new)) - this_count++; + /* Do not count inactive or per-cpu irqs. */ + if (!irq_desc_has_action(desc) || irqd_is_per_cpu(data)) { + raw_spin_unlock(&desc->lock); + continue; } + + raw_spin_unlock(&desc->lock); + /* + * A single irq may be mapped to multiple cpu's + * vector_irq[] (for example IOAPIC cluster mode). In + * this case we have two possibilities: + * + * 1) the resulting affinity mask is empty; that is + * this the down'd cpu is the last cpu in the irq's + * affinity mask, or + * + * 2) the resulting affinity mask is no longer a + * subset of the online cpus but the affinity mask is + * not zero; that is the down'd cpu is the last online + * cpu in a user set affinity mask. + */ + if (cpumask_empty(&affinity_new) || + !cpumask_subset(&affinity_new, &online_new)) + this_count++; } count = 0; @@ -343,12 +406,15 @@ int check_irq_vectors_for_cpu_disable(void) * vector. If the vector is marked in the used vectors * bitmap or an irq is assigned to it, we don't count * it as available. + * + * As this is an inaccurate snapshot anyway, we can do + * this w/o holding vector_lock. */ for (vector = FIRST_EXTERNAL_VECTOR; vector < first_system_vector; vector++) { if (!test_bit(vector, used_vectors) && - per_cpu(vector_irq, cpu)[vector] < 0) - count++; + IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) + count++; } } @@ -384,7 +450,7 @@ void fixup_irqs(void) raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); - affinity = data->affinity; + affinity = irq_data_get_affinity_mask(data); if (!irq_has_action(irq) || irqd_is_per_cpu(data) || cpumask_subset(affinity, cpu_online_mask)) { raw_spin_unlock(&desc->lock); @@ -396,7 +462,7 @@ void fixup_irqs(void) * non intr-remapping case, we can't wait till this interrupt * arrives at this cpu before completing the irq move. */ - irq_force_complete_move(irq); + irq_force_complete_move(desc); if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; @@ -404,6 +470,15 @@ void fixup_irqs(void) } chip = irq_data_get_irq_chip(data); + /* + * The interrupt descriptor might have been cleaned up + * already, but it is not yet removed from the radix tree + */ + if (!chip) { + raw_spin_unlock(&desc->lock); + continue; + } + if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); @@ -444,20 +519,24 @@ void fixup_irqs(void) */ mdelay(1); + /* + * We can walk the vector array of this cpu without holding + * vector_lock because the cpu is already marked !online, so + * nothing else will touch it. + */ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { unsigned int irr; - if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED) + if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector]))) continue; irr = apic_read(APIC_IRR + (vector / 32 * 0x10)); if (irr & (1 << (vector % 32))) { - irq = __this_cpu_read(vector_irq[vector]); + desc = __this_cpu_read(vector_irq[vector]); - desc = irq_to_desc(irq); + raw_spin_lock(&desc->lock); data = irq_desc_get_irq_data(desc); chip = irq_data_get_irq_chip(data); - raw_spin_lock(&desc->lock); if (chip->irq_retrigger) { chip->irq_retrigger(data); __this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED); @@ -465,7 +544,7 @@ void fixup_irqs(void) raw_spin_unlock(&desc->lock); } if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED) - __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED); + __this_cpu_write(vector_irq[vector], VECTOR_UNUSED); } } #endif diff --git a/kernel/arch/x86/kernel/irq_32.c b/kernel/arch/x86/kernel/irq_32.c index 521ef3cc8..ce71f7098 100644 --- a/kernel/arch/x86/kernel/irq_32.c +++ b/kernel/arch/x86/kernel/irq_32.c @@ -21,12 +21,6 @@ #include <asm/apic.h> -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); - -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - #ifdef CONFIG_DEBUG_STACKOVERFLOW int sysctl_panic_on_stackoverflow __read_mostly; @@ -74,11 +68,10 @@ static inline void *current_stack(void) return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1)); } -static inline int -execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) +static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) { struct irq_stack *curstk, *irqstk; - u32 *isp, *prev_esp, arg1, arg2; + u32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *) current_stack(); irqstk = __this_cpu_read(hardirq_stack); @@ -104,8 +97,8 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) asm volatile("xchgl %%ebx,%%esp \n" "call *%%edi \n" "movl %%ebx,%%esp \n" - : "=a" (arg1), "=d" (arg2), "=b" (isp) - : "0" (irq), "1" (desc), "2" (isp), + : "=a" (arg1), "=b" (isp) + : "0" (desc), "1" (isp), "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; @@ -156,21 +149,17 @@ void do_softirq_own_stack(void) } #endif -bool handle_irq(unsigned irq, struct pt_regs *regs) +bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { - struct irq_desc *desc; - int overflow; - - overflow = check_stack_overflow(); + int overflow = check_stack_overflow(); - desc = irq_to_desc(irq); - if (unlikely(!desc)) + if (IS_ERR_OR_NULL(desc)) return false; - if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) { if (unlikely(overflow)) print_stack_overflow(); - desc->handle_irq(irq, desc); + generic_handle_irq_desc(desc); } return true; diff --git a/kernel/arch/x86/kernel/irq_64.c b/kernel/arch/x86/kernel/irq_64.c index 394e643d7..206d0b90a 100644 --- a/kernel/arch/x86/kernel/irq_64.c +++ b/kernel/arch/x86/kernel/irq_64.c @@ -20,12 +20,6 @@ #include <asm/idle.h> #include <asm/apic.h> -DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); -EXPORT_PER_CPU_SYMBOL(irq_stat); - -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - int sysctl_panic_on_stackoverflow; /* @@ -74,16 +68,13 @@ static inline void stack_overflow_check(struct pt_regs *regs) #endif } -bool handle_irq(unsigned irq, struct pt_regs *regs) +bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) { - struct irq_desc *desc; - stack_overflow_check(regs); - desc = irq_to_desc(irq); - if (unlikely(!desc)) + if (IS_ERR_OR_NULL(desc)) return false; - generic_handle_irq_desc(irq, desc); + generic_handle_irq_desc(desc); return true; } diff --git a/kernel/arch/x86/kernel/irq_work.c b/kernel/arch/x86/kernel/irq_work.c index 15d741ddf..3512ba607 100644 --- a/kernel/arch/x86/kernel/irq_work.c +++ b/kernel/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> @@ -10,12 +10,6 @@ #include <asm/apic.h> #include <asm/trace/irq_vectors.h> -static inline void irq_work_entering_irq(void) -{ - irq_enter(); - ack_APIC_irq(); -} - static inline void __smp_irq_work_interrupt(void) { inc_irq_stat(apic_irq_work_irqs); @@ -24,14 +18,14 @@ static inline void __smp_irq_work_interrupt(void) __visible void smp_irq_work_interrupt(struct pt_regs *regs) { - irq_work_entering_irq(); + ipi_entering_ack_irq(); __smp_irq_work_interrupt(); exiting_irq(); } __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) { - irq_work_entering_irq(); + ipi_entering_ack_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); __smp_irq_work_interrupt(); trace_irq_work_exit(IRQ_WORK_VECTOR); diff --git a/kernel/arch/x86/kernel/irqinit.c b/kernel/arch/x86/kernel/irqinit.c index cd10a6437..1423ab1b0 100644 --- a/kernel/arch/x86/kernel/irqinit.c +++ b/kernel/arch/x86/kernel/irqinit.c @@ -52,7 +52,7 @@ static struct irqaction irq2 = { }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { - [0 ... NR_VECTORS - 1] = VECTOR_UNDEFINED, + [0 ... NR_VECTORS - 1] = VECTOR_UNUSED, }; int vector_used_by_percpu_irq(unsigned int vector) @@ -60,7 +60,7 @@ int vector_used_by_percpu_irq(unsigned int vector) int cpu; for_each_online_cpu(cpu) { - if (per_cpu(vector_irq, cpu)[vector] > VECTOR_UNDEFINED) + if (!IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) return 1; } @@ -86,7 +86,7 @@ void __init init_IRQ(void) int i; /* - * On cpu 0, Assign IRQ0_VECTOR..IRQ15_VECTOR's to IRQ 0..15. + * On cpu 0, Assign ISA_IRQ_VECTOR(irq) to IRQ 0..15. * If these IRQ's are handled by legacy interrupt-controllers like PIC, * then this configuration will likely be static after the boot. If * these IRQ's are handled by more mordern controllers like IO-APIC, @@ -94,7 +94,7 @@ void __init init_IRQ(void) * irq's migrate etc. */ for (i = 0; i < nr_legacy_irqs(); i++) - per_cpu(vector_irq, 0)[IRQ0_VECTOR + i] = i; + per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i); x86_init.irqs.intr_init(); } @@ -135,6 +135,10 @@ static void __init apic_intr_init(void) alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt); #endif +#ifdef CONFIG_X86_MCE_AMD + alloc_intr_gate(DEFERRED_ERROR_VECTOR, deferred_error_interrupt); +#endif + #ifdef CONFIG_X86_LOCAL_APIC /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); @@ -144,6 +148,8 @@ static void __init apic_intr_init(void) #ifdef CONFIG_HAVE_KVM /* IPI for KVM to deliver posted interrupt */ alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi); + /* IPI for KVM to deliver interrupt to wake up tasks */ + alloc_intr_gate(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi); #endif /* IPI vectors for APIC spurious and error interrupts */ diff --git a/kernel/arch/x86/kernel/jump_label.c b/kernel/arch/x86/kernel/jump_label.c index 26d5a55a2..e565e0e4d 100644 --- a/kernel/arch/x86/kernel/jump_label.c +++ b/kernel/arch/x86/kernel/jump_label.c @@ -45,7 +45,7 @@ static void __jump_label_transform(struct jump_entry *entry, const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - if (type == JUMP_LABEL_ENABLE) { + if (type == JUMP_LABEL_JMP) { if (init) { /* * Jump label is enabled for the first time. diff --git a/kernel/arch/x86/kernel/kexec-bzimage64.c b/kernel/arch/x86/kernel/kexec-bzimage64.c index ca05f8648..0f8a6bbaa 100644 --- a/kernel/arch/x86/kernel/kexec-bzimage64.c +++ b/kernel/arch/x86/kernel/kexec-bzimage64.c @@ -72,15 +72,16 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, unsigned long cmdline_len) { char *cmdline_ptr = ((char *)params) + cmdline_offset; - unsigned long cmdline_ptr_phys, len; + unsigned long cmdline_ptr_phys, len = 0; uint32_t cmdline_low_32, cmdline_ext_32; - memcpy(cmdline_ptr, cmdline, cmdline_len); if (image->type == KEXEC_TYPE_CRASH) { - len = sprintf(cmdline_ptr + cmdline_len - 1, - " elfcorehdr=0x%lx", image->arch.elf_load_addr); - cmdline_len += len; + len = sprintf(cmdline_ptr, + "elfcorehdr=0x%lx ", image->arch.elf_load_addr); } + memcpy(cmdline_ptr + len, cmdline, cmdline_len); + cmdline_len += len; + cmdline_ptr[cmdline_len - 1] = '\0'; pr_debug("Final command line is: %s\n", cmdline_ptr); @@ -222,9 +223,6 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, memset(¶ms->hd0_info, 0, sizeof(params->hd0_info)); memset(¶ms->hd1_info, 0, sizeof(params->hd1_info)); - /* Default sysdesc table */ - params->sys_desc_table.length = 0; - if (image->type == KEXEC_TYPE_CRASH) { ret = crash_setup_memmap_entries(image, params); if (ret) @@ -535,7 +533,9 @@ static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len) int ret; ret = verify_pefile_signature(kernel, kernel_len, - system_trusted_keyring, &trusted); + system_trusted_keyring, + VERIFYING_KEXEC_PE_SIGNATURE, + &trusted); if (ret < 0) return ret; if (!trusted) diff --git a/kernel/arch/x86/kernel/kgdb.c b/kernel/arch/x86/kernel/kgdb.c index d6178d979..44256a627 100644 --- a/kernel/arch/x86/kernel/kgdb.c +++ b/kernel/arch/x86/kernel/kgdb.c @@ -511,26 +511,31 @@ single_step_cont(struct pt_regs *regs, struct die_args *args) return NOTIFY_STOP; } -static int was_in_debug_nmi[NR_CPUS]; +static DECLARE_BITMAP(was_in_debug_nmi, NR_CPUS); static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + int cpu; + switch (cmd) { case NMI_LOCAL: if (atomic_read(&kgdb_active) != -1) { /* KGDB CPU roundup */ - kgdb_nmicallback(raw_smp_processor_id(), regs); - was_in_debug_nmi[raw_smp_processor_id()] = 1; + cpu = raw_smp_processor_id(); + kgdb_nmicallback(cpu, regs); + set_bit(cpu, was_in_debug_nmi); touch_nmi_watchdog(); + return NMI_HANDLED; } break; case NMI_UNKNOWN: - if (was_in_debug_nmi[raw_smp_processor_id()]) { - was_in_debug_nmi[raw_smp_processor_id()] = 0; + cpu = raw_smp_processor_id(); + + if (__test_and_clear_bit(cpu, was_in_debug_nmi)) return NMI_HANDLED; - } + break; default: /* do nothing */ diff --git a/kernel/arch/x86/kernel/kvm.c b/kernel/arch/x86/kernel/kvm.c index 943562006..807950860 100644 --- a/kernel/arch/x86/kernel/kvm.c +++ b/kernel/arch/x86/kernel/kvm.c @@ -36,6 +36,7 @@ #include <linux/kprobes.h> #include <linux/debugfs.h> #include <linux/nmi.h> +#include <linux/swait.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -91,14 +92,14 @@ static void kvm_io_delay(void) struct kvm_task_sleep_node { struct hlist_node link; - wait_queue_head_t wq; + struct swait_queue_head wq; u32 token; int cpu; bool halted; }; static struct kvm_task_sleep_head { - spinlock_t lock; + raw_spinlock_t lock; struct hlist_head list; } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE]; @@ -122,17 +123,17 @@ void kvm_async_pf_task_wait(u32 token) u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; struct kvm_task_sleep_node n, *e; - DEFINE_WAIT(wait); + DECLARE_SWAITQUEUE(wait); rcu_irq_enter(); - spin_lock(&b->lock); + raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { /* dummy entry exist -> wake up was delivered ahead of PF */ hlist_del(&e->link); kfree(e); - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); rcu_irq_exit(); return; @@ -141,13 +142,13 @@ void kvm_async_pf_task_wait(u32 token) n.token = token; n.cpu = smp_processor_id(); n.halted = is_idle_task(current) || preempt_count() > 1; - init_waitqueue_head(&n.wq); + init_swait_queue_head(&n.wq); hlist_add_head(&n.link, &b->list); - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); for (;;) { if (!n.halted) - prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; @@ -166,7 +167,7 @@ void kvm_async_pf_task_wait(u32 token) } } if (!n.halted) - finish_wait(&n.wq, &wait); + finish_swait(&n.wq, &wait); rcu_irq_exit(); return; @@ -178,8 +179,8 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n) hlist_del_init(&n->link); if (n->halted) smp_send_reschedule(n->cpu); - else if (waitqueue_active(&n->wq)) - wake_up(&n->wq); + else if (swait_active(&n->wq)) + swake_up(&n->wq); } static void apf_task_wake_all(void) @@ -189,14 +190,14 @@ static void apf_task_wake_all(void) for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { struct hlist_node *p, *next; struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; - spin_lock(&b->lock); + raw_spin_lock(&b->lock); hlist_for_each_safe(p, next, &b->list) { struct kvm_task_sleep_node *n = hlist_entry(p, typeof(*n), link); if (n->cpu == smp_processor_id()) apf_task_wake_one(n); } - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); } } @@ -212,7 +213,7 @@ void kvm_async_pf_task_wake(u32 token) } again: - spin_lock(&b->lock); + raw_spin_lock(&b->lock); n = _find_apf_task(b, token); if (!n) { /* @@ -225,17 +226,17 @@ again: * Allocation failed! Busy wait while other cpu * handles async PF. */ - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); cpu_relax(); goto again; } n->token = token; n->cpu = smp_processor_id(); - init_waitqueue_head(&n->wq); + init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); } else apf_task_wake_one(n); - spin_unlock(&b->lock); + raw_spin_unlock(&b->lock); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); @@ -331,7 +332,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val) apic_write(APIC_EOI, APIC_EOI_ACK); } -void kvm_guest_cpu_init(void) +static void kvm_guest_cpu_init(void) { if (!kvm_para_available()) return; @@ -486,7 +487,7 @@ void __init kvm_guest_init(void) paravirt_ops_setup(); register_reboot_notifier(&kvm_pv_reboot_nb); for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) - spin_lock_init(&async_pf_sleepers[i].lock); + raw_spin_lock_init(&async_pf_sleepers[i].lock); if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) x86_init.irqs.trap_init = kvm_apf_trap_init; @@ -584,6 +585,39 @@ static void kvm_kick_cpu(int cpu) kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); } + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void kvm_wait(u8 *ptr, u8 val) +{ + unsigned long flags; + + if (in_nmi()) + return; + + local_irq_save(flags); + + if (READ_ONCE(*ptr) != val) + goto out; + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + local_irq_restore(flags); +} + +#else /* !CONFIG_QUEUED_SPINLOCKS */ + enum kvm_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -655,7 +689,7 @@ static inline void spin_time_accum_blocked(u64 start) static struct dentry *d_spin_debug; static struct dentry *d_kvm_debug; -struct dentry *kvm_init_debugfs(void) +static struct dentry *kvm_init_debugfs(void) { d_kvm_debug = debugfs_create_dir("kvm-guest", NULL); if (!d_kvm_debug) @@ -817,6 +851,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) } } +#endif /* !CONFIG_QUEUED_SPINLOCKS */ + /* * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. */ @@ -828,8 +864,16 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = kvm_wait; + pv_lock_ops.kick = kvm_kick_cpu; +#else /* !CONFIG_QUEUED_SPINLOCKS */ pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); pv_lock_ops.unlock_kick = kvm_unlock_kick; +#endif } static __init int kvm_spinlock_init_jump(void) diff --git a/kernel/arch/x86/kernel/kvmclock.c b/kernel/arch/x86/kernel/kvmclock.c index 42caaef89..2bd81e302 100644 --- a/kernel/arch/x86/kernel/kvmclock.c +++ b/kernel/arch/x86/kernel/kvmclock.c @@ -24,6 +24,7 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/memblock.h> +#include <linux/sched.h> #include <asm/x86_init.h> #include <asm/reboot.h> @@ -31,6 +32,7 @@ static int kvmclock = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; +static cycle_t kvm_sched_clock_offset; static int parse_no_kvmclock(char *arg) { @@ -91,6 +93,29 @@ static cycle_t kvm_clock_get_cycles(struct clocksource *cs) return kvm_clock_read(); } +static cycle_t kvm_sched_clock_read(void) +{ + return kvm_clock_read() - kvm_sched_clock_offset; +} + +static inline void kvm_sched_clock_init(bool stable) +{ + if (!stable) { + pv_time_ops.sched_clock = kvm_clock_read; + return; + } + + kvm_sched_clock_offset = kvm_clock_read(); + pv_time_ops.sched_clock = kvm_sched_clock_read; + set_sched_clock_stable(); + + printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n", + kvm_sched_clock_offset); + + BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) > + sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time)); +} + /* * If we don't do that, there is the possibility that the guest * will calibrate under heavy load - thus, getting a lower lpj - @@ -199,7 +224,7 @@ static void kvm_setup_secondary_clock(void) * kind of shutdown from our side, we unregister the clock by writting anything * that does not have the 'enable' bit set in the msr */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE static void kvm_crash_shutdown(struct pt_regs *regs) { native_write_msr(msr_kvm_system_time, 0, 0); @@ -217,8 +242,10 @@ static void kvm_shutdown(void) void __init kvmclock_init(void) { + struct pvclock_vcpu_time_info *vcpu_time; unsigned long mem; - int size; + int size, cpu; + u8 flags; size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS); @@ -245,7 +272,17 @@ void __init kvmclock_init(void) memblock_free(mem, size); return; } - pv_time_ops.sched_clock = kvm_clock_read; + + if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) + pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); + + cpu = get_cpu(); + vcpu_time = &hv_clock[cpu].pvti; + flags = pvclock_read_flags(vcpu_time); + + kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT); + put_cpu(); + x86_platform.calibrate_tsc = kvm_get_tsc_khz; x86_platform.get_wallclock = kvm_get_wallclock; x86_platform.set_wallclock = kvm_set_wallclock; @@ -256,15 +293,12 @@ void __init kvmclock_init(void) x86_platform.save_sched_clock_state = kvm_save_sched_clock_state; x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state; machine_ops.shutdown = kvm_shutdown; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE machine_ops.crash_shutdown = kvm_crash_shutdown; #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); pv_info.name = "KVM"; - - if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) - pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT); } int __init kvm_setup_vsyscall_timeinfo(void) diff --git a/kernel/arch/x86/kernel/ldt.c b/kernel/arch/x86/kernel/ldt.c index 2bcc0525f..6acc9dd91 100644 --- a/kernel/arch/x86/kernel/ldt.c +++ b/kernel/arch/x86/kernel/ldt.c @@ -58,7 +58,7 @@ static struct ldt_struct *alloc_ldt_struct(int size) if (alloc_size > PAGE_SIZE) new_ldt->entries = vzalloc(alloc_size); else - new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL); + new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL); if (!new_ldt->entries) { kfree(new_ldt); @@ -95,7 +95,7 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) vfree(ldt->entries); else - kfree(ldt->entries); + free_page((unsigned long)ldt->entries); kfree(ldt); } diff --git a/kernel/arch/x86/kernel/livepatch.c b/kernel/arch/x86/kernel/livepatch.c index ff3c3101d..d1d35ccff 100644 --- a/kernel/arch/x86/kernel/livepatch.c +++ b/kernel/arch/x86/kernel/livepatch.c @@ -42,7 +42,6 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, bool readonly; unsigned long val; unsigned long core = (unsigned long)mod->module_core; - unsigned long core_ro_size = mod->core_ro_size; unsigned long core_size = mod->core_size; switch (type) { @@ -70,10 +69,12 @@ int klp_write_module_reloc(struct module *mod, unsigned long type, /* loc does not point to any symbol inside the module */ return -EINVAL; - if (loc < core + core_ro_size) + readonly = false; + +#ifdef CONFIG_DEBUG_SET_MODULE_RONX + if (loc < core + mod->core_ro_size) readonly = true; - else - readonly = false; +#endif /* determine if the relocation spans a page boundary */ numpages = ((loc & PAGE_MASK) == ((loc + size) & PAGE_MASK)) ? 1 : 2; diff --git a/kernel/arch/x86/kernel/machine_kexec_64.c b/kernel/arch/x86/kernel/machine_kexec_64.c index 415480d3e..819ab3f9c 100644 --- a/kernel/arch/x86/kernel/machine_kexec_64.c +++ b/kernel/arch/x86/kernel/machine_kexec_64.c @@ -17,6 +17,7 @@ #include <linux/ftrace.h> #include <linux/io.h> #include <linux/suspend.h> +#include <linux/vmalloc.h> #include <asm/init.h> #include <asm/pgtable.h> @@ -25,6 +26,7 @@ #include <asm/io_apic.h> #include <asm/debugreg.h> #include <asm/kexec-bzimage64.h> +#include <asm/setup.h> #ifdef CONFIG_KEXEC_FILE static struct kexec_file_ops *kexec_file_loaders[] = { @@ -334,7 +336,7 @@ void arch_crash_save_vmcoreinfo(void) VMCOREINFO_LENGTH(node_data, MAX_NUMNODES); #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", - (unsigned long)&_text - __START_KERNEL); + kaslr_offset()); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/kernel/arch/x86/kernel/mcount_64.S b/kernel/arch/x86/kernel/mcount_64.S index 94ea120fa..87e1762e2 100644 --- a/kernel/arch/x86/kernel/mcount_64.S +++ b/kernel/arch/x86/kernel/mcount_64.S @@ -278,6 +278,12 @@ trace: /* save_mcount_regs fills in first two parameters */ save_mcount_regs + /* + * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not + * set (see include/asm/ftrace.h and include/linux/ftrace.h). Only the + * ip and parent ip are used and the list function is called when + * function tracing is enabled. + */ call *ftrace_trace_function restore_mcount_regs diff --git a/kernel/arch/x86/kernel/mpparse.c b/kernel/arch/x86/kernel/mpparse.c index 2d2a237f2..30ca7607c 100644 --- a/kernel/arch/x86/kernel/mpparse.c +++ b/kernel/arch/x86/kernel/mpparse.c @@ -19,8 +19,8 @@ #include <linux/module.h> #include <linux/smp.h> #include <linux/pci.h> -#include <linux/irqdomain.h> +#include <asm/irqdomain.h> #include <asm/mtrr.h> #include <asm/mpspec.h> #include <asm/pgalloc.h> @@ -113,11 +113,6 @@ static void __init MP_bus_info(struct mpc_bus *m) pr_warn("Unknown bustype %s - ignoring\n", str); } -static struct irq_domain_ops mp_ioapic_irqdomain_ops = { - .map = mp_irqdomain_map, - .unmap = mp_irqdomain_unmap, -}; - static void __init MP_ioapic_info(struct mpc_ioapic *m) { struct ioapic_domain_cfg cfg = { diff --git a/kernel/arch/x86/kernel/nmi.c b/kernel/arch/x86/kernel/nmi.c index d05bd2e2e..697f90db0 100644 --- a/kernel/arch/x86/kernel/nmi.c +++ b/kernel/arch/x86/kernel/nmi.c @@ -110,7 +110,7 @@ static void nmi_max_handler(struct irq_work *w) a->handler, whole_msecs, decimal_msecs); } -static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static int nmi_handle(unsigned int type, struct pt_regs *regs) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -213,7 +213,7 @@ static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { /* check to see if anyone registered against these types of errors */ - if (nmi_handle(NMI_SERR, regs, false)) + if (nmi_handle(NMI_SERR, regs)) return; pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n", @@ -247,7 +247,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs) unsigned long i; /* check to see if anyone registered against these types of errors */ - if (nmi_handle(NMI_IO_CHECK, regs, false)) + if (nmi_handle(NMI_IO_CHECK, regs)) return; pr_emerg( @@ -284,7 +284,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) * as only the first one is ever run (unless it can actually determine * if it caused the NMI) */ - handled = nmi_handle(NMI_UNKNOWN, regs, false); + handled = nmi_handle(NMI_UNKNOWN, regs); if (handled) { __this_cpu_add(nmi_stats.unknown, handled); return; @@ -332,7 +332,7 @@ static void default_do_nmi(struct pt_regs *regs) __this_cpu_write(last_nmi_rip, regs->ip); - handled = nmi_handle(NMI_LOCAL, regs, b2b); + handled = nmi_handle(NMI_LOCAL, regs); __this_cpu_add(nmi_stats.normal, handled); if (handled) { /* diff --git a/kernel/arch/x86/kernel/paravirt-spinlocks.c b/kernel/arch/x86/kernel/paravirt-spinlocks.c index bbb6c7316..33ee3e0ef 100644 --- a/kernel/arch/x86/kernel/paravirt-spinlocks.c +++ b/kernel/arch/x86/kernel/paravirt-spinlocks.c @@ -8,11 +8,33 @@ #include <asm/paravirt.h> +#ifdef CONFIG_QUEUED_SPINLOCKS +__visible void __native_queued_spin_unlock(struct qspinlock *lock) +{ + native_queued_spin_unlock(lock); +} + +PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock); + +bool pv_is_native_spin_unlock(void) +{ + return pv_lock_ops.queued_spin_unlock.func == + __raw_callee_save___native_queued_spin_unlock; +} +#endif + struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP +#ifdef CONFIG_QUEUED_SPINLOCKS + .queued_spin_lock_slowpath = native_queued_spin_lock_slowpath, + .queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock), + .wait = paravirt_nop, + .kick = paravirt_nop, +#else /* !CONFIG_QUEUED_SPINLOCKS */ .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), .unlock_kick = paravirt_nop, -#endif +#endif /* !CONFIG_QUEUED_SPINLOCKS */ +#endif /* SMP */ }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/kernel/arch/x86/kernel/paravirt.c b/kernel/arch/x86/kernel/paravirt.c index c614dd492..c2130aef3 100644 --- a/kernel/arch/x86/kernel/paravirt.c +++ b/kernel/arch/x86/kernel/paravirt.c @@ -41,10 +41,18 @@ #include <asm/timer.h> #include <asm/special_insns.h> -/* nop stub */ -void _paravirt_nop(void) -{ -} +/* + * nop stub, which must not clobber anything *including the stack* to + * avoid confusing the entry prologues. + */ +extern void _paravirt_nop(void); +asm (".pushsection .entry.text, \"ax\"\n" + ".global _paravirt_nop\n" + "_paravirt_nop:\n\t" + "ret\n\t" + ".size _paravirt_nop, . - _paravirt_nop\n\t" + ".type _paravirt_nop, @function\n\t" + ".popsection"); /* identity function, which can be inlined */ u32 _paravirt_ident_32(u32 x) @@ -154,7 +162,9 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || +#ifdef CONFIG_X86_32 type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || +#endif type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ @@ -349,9 +359,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, .write_msr = native_write_msr_safe, - .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, - .read_tscp = native_read_tscp, .load_tr_desc = native_load_tr_desc, .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, @@ -371,7 +379,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +#if defined(CONFIG_X86_32) .irq_enable_sysexit = native_irq_enable_sysexit, #endif #ifdef CONFIG_X86_64 diff --git a/kernel/arch/x86/kernel/paravirt_patch_32.c b/kernel/arch/x86/kernel/paravirt_patch_32.c index d9f32e6d6..c89f50a76 100644 --- a/kernel/arch/x86/kernel/paravirt_patch_32.c +++ b/kernel/arch/x86/kernel/paravirt_patch_32.c @@ -10,7 +10,10 @@ DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); -DEF_NATIVE(pv_cpu_ops, read_tsc, "rdtsc"); + +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)"); +#endif unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { @@ -24,6 +27,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) return 0; } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -46,15 +51,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); PATCH_SITE(pv_cpu_ops, clts); - PATCH_SITE(pv_cpu_ops, read_tsc); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/kernel/arch/x86/kernel/paravirt_patch_64.c b/kernel/arch/x86/kernel/paravirt_patch_64.c index a1da6737b..8aa05583b 100644 --- a/kernel/arch/x86/kernel/paravirt_patch_64.c +++ b/kernel/arch/x86/kernel/paravirt_patch_64.c @@ -21,6 +21,10 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); DEF_NATIVE(, mov64, "mov %rdi, %rax"); +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) +DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)"); +#endif + unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len) { return paravirt_patch_insns(insnbuf, len, @@ -33,6 +37,8 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len) start__mov64, end__mov64); } +extern bool pv_is_native_spin_unlock(void); + unsigned native_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { @@ -49,7 +55,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); @@ -59,14 +64,22 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_cpu_ops, clts); PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); - - patch_site: - ret = paravirt_patch_insns(ibuf, len, start, end); - break; +#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS) + case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): + if (pv_is_native_spin_unlock()) { + start = start_pv_lock_ops_queued_spin_unlock; + end = end_pv_lock_ops_queued_spin_unlock; + goto patch_site; + } +#endif default: ret = paravirt_patch_default(type, clobbers, ibuf, addr, len); break; + +patch_site: + ret = paravirt_patch_insns(ibuf, len, start, end); + break; } #undef PATCH_SITE return ret; diff --git a/kernel/arch/x86/kernel/pci-dma.c b/kernel/arch/x86/kernel/pci-dma.c index a25e202bb..6ba014c61 100644 --- a/kernel/arch/x86/kernel/pci-dma.c +++ b/kernel/arch/x86/kernel/pci-dma.c @@ -58,17 +58,6 @@ EXPORT_SYMBOL(x86_dma_fallback_dev); /* Number of entries preallocated for DMA-API debugging */ #define PREALLOC_DMA_DEBUG_ENTRIES 65536 -int dma_set_mask(struct device *dev, u64 mask) -{ - if (!dev->dma_mask || !dma_supported(dev, mask)) - return -EIO; - - *dev->dma_mask = mask; - - return 0; -} -EXPORT_SYMBOL(dma_set_mask); - void __init pci_iommu_alloc(void) { struct iommu_table_entry *p; @@ -101,7 +90,7 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) { + if (gfpflags_allow_blocking(flag)) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (page && page_to_phys(page) + size > dma_mask) { dma_release_from_contiguous(dev, page, count); @@ -140,6 +129,21 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } +bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp) +{ + if (!*dev) + *dev = &x86_dma_fallback_dev; + + *gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); + *gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp); + + if (!is_device_dma_capable(*dev)) + return false; + return true; + +} +EXPORT_SYMBOL(arch_dma_alloc_attrs); + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/kernel/arch/x86/kernel/pci-swiotlb.c b/kernel/arch/x86/kernel/pci-swiotlb.c index 77dd0ad58..adf0392d5 100644 --- a/kernel/arch/x86/kernel/pci-swiotlb.c +++ b/kernel/arch/x86/kernel/pci-swiotlb.c @@ -20,6 +20,13 @@ void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, { void *vaddr; + /* + * Don't print a warning when the first allocation attempt fails. + * swiotlb_alloc_coherent() will print a warning when the DMA + * memory allocation ultimately failed. + */ + flags |= __GFP_NOWARN; + vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags, attrs); if (vaddr) diff --git a/kernel/arch/x86/kernel/pmem.c b/kernel/arch/x86/kernel/pmem.c index 3420c874d..14415aff1 100644 --- a/kernel/arch/x86/kernel/pmem.c +++ b/kernel/arch/x86/kernel/pmem.c @@ -1,53 +1,31 @@ /* * Copyright (c) 2015, Christoph Hellwig. + * Copyright (c) 2015, Intel Corporation. */ -#include <linux/memblock.h> #include <linux/platform_device.h> -#include <linux/slab.h> -#include <asm/e820.h> -#include <asm/page_types.h> -#include <asm/setup.h> +#include <linux/module.h> +#include <linux/ioport.h> -static __init void register_pmem_device(struct resource *res) +static int found(u64 start, u64 end, void *data) { - struct platform_device *pdev; - int error; - - pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); - if (!pdev) - return; - - error = platform_device_add_resources(pdev, res, 1); - if (error) - goto out_put_pdev; - - error = platform_device_add(pdev); - if (error) - goto out_put_pdev; - return; - -out_put_pdev: - dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); - platform_device_put(pdev); + return 1; } -static __init int register_pmem_devices(void) +static __init int register_e820_pmem(void) { - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - - if (ei->type == E820_PRAM) { - struct resource res = { - .flags = IORESOURCE_MEM, - .start = ei->addr, - .end = ei->addr + ei->size - 1, - }; - register_pmem_device(&res); - } - } - - return 0; + char *pmem = "Persistent Memory (legacy)"; + struct platform_device *pdev; + int rc; + + rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found); + if (rc <= 0) + return 0; + + /* + * See drivers/nvdimm/e820.c for the implementation, this is + * simply here to trigger the module to load on demand. + */ + pdev = platform_device_alloc("e820_pmem", -1); + return platform_device_add(pdev); } -device_initcall(register_pmem_devices); +device_initcall(register_e820_pmem); diff --git a/kernel/arch/x86/kernel/process.c b/kernel/arch/x86/kernel/process.c index 971743774..9f7c21c22 100644 --- a/kernel/arch/x86/kernel/process.c +++ b/kernel/arch/x86/kernel/process.c @@ -25,11 +25,12 @@ #include <asm/idle.h> #include <asm/uaccess.h> #include <asm/mwait.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> #include <asm/nmi.h> #include <asm/tlbflush.h> +#include <asm/mce.h> +#include <asm/vm86.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -76,47 +77,18 @@ void idle_notifier_unregister(struct notifier_block *n) EXPORT_SYMBOL_GPL(idle_notifier_unregister); #endif -struct kmem_cache *task_xstate_cachep; -EXPORT_SYMBOL_GPL(task_xstate_cachep); - /* * this gets called so that we can store lazy state into memory and copy the * current task into the new thread. */ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - *dst = *src; - - dst->thread.fpu_counter = 0; - dst->thread.fpu.has_fpu = 0; - dst->thread.fpu.state = NULL; - task_disable_lazy_fpu_restore(dst); - if (tsk_used_math(src)) { - int err = fpu_alloc(&dst->thread.fpu); - if (err) - return err; - fpu_copy(dst, src); - } - return 0; -} - -void free_thread_xstate(struct task_struct *tsk) -{ - fpu_free(&tsk->thread.fpu); -} - -void arch_release_task_struct(struct task_struct *tsk) -{ - free_thread_xstate(tsk); -} + memcpy(dst, src, arch_task_struct_size); +#ifdef CONFIG_VM86 + dst->thread.vm86 = NULL; +#endif -void arch_task_cache_init(void) -{ - task_xstate_cachep = - kmem_cache_create("task_xstate", xstate_size, - __alignof__(union thread_xstate), - SLAB_PANIC | SLAB_NOTRACK, NULL); - setup_xstate_comp(); + return fpu__copy(&dst->thread.fpu, &src->thread.fpu); } /* @@ -127,6 +99,7 @@ void exit_thread(void) struct task_struct *me = current; struct thread_struct *t = &me->thread; unsigned long *bp = t->io_bitmap_ptr; + struct fpu *fpu = &t->fpu; if (bp) { struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); @@ -142,7 +115,9 @@ void exit_thread(void) kfree(bp); } - drop_fpu(me); + free_vm86(t); + + fpu__drop(fpu); } void flush_thread(void) @@ -152,19 +127,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - if (!use_eager_fpu()) { - /* FPU state will be reallocated lazily at the first use. */ - drop_fpu(tsk); - free_thread_xstate(tsk); - } else { - if (!tsk_used_math(tsk)) { - /* kthread execs. TODO: cleanup this horror. */ - if (WARN_ON(init_fpu(tsk))) - force_sig(SIGKILL, tsk); - user_fpu_begin(); - } - restore_init_xstate(); - } + fpu__clear(&tsk->thread.fpu); } static void hard_disable_TSC(void) @@ -363,6 +326,7 @@ void stop_this_cpu(void *dummy) */ set_cpu_online(smp_processor_id(), false); disable_local_APIC(); + mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); for (;;) halt(); @@ -445,11 +409,10 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) } /* - * MONITOR/MWAIT with no hints, used for default default C1 state. - * This invokes MWAIT with interrutps enabled and no flags, - * which is backwards compatible with the original MWAIT implementation. + * MONITOR/MWAIT with no hints, used for default C1 state. This invokes MWAIT + * with interrupts enabled and no flags, which is backwards compatible with the + * original MWAIT implementation. */ - static void mwait_idle(void) { if (!current_set_polling_and_test()) { @@ -546,3 +509,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) return randomize_range(mm->brk, range_end, 0) ? : mm->brk; } +/* + * Called from fs/proc with a reference on @p to find the function + * which called into schedule(). This needs to be done carefully + * because the task might wake up and we might look at a stack + * changing under us. + */ +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long start, bottom, top, sp, fp, ip; + int count = 0; + + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + + start = (unsigned long)task_stack_page(p); + if (!start) + return 0; + + /* + * Layout of the stack page: + * + * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long) + * PADDING + * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING + * stack + * ----------- bottom = start + sizeof(thread_info) + * thread_info + * ----------- start + * + * The tasks stack pointer points at the location where the + * framepointer is stored. The data on the stack is: + * ... IP FP ... IP FP + * + * We need to read FP and IP, so we need to adjust the upper + * bound by another unsigned long. + */ + top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; + top -= 2 * sizeof(unsigned long); + bottom = start + sizeof(struct thread_info); + + sp = READ_ONCE(p->thread.sp); + if (sp < bottom || sp > top) + return 0; + + fp = READ_ONCE_NOCHECK(*(unsigned long *)sp); + do { + if (fp < bottom || fp > top) + return 0; + ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); + if (!in_sched_functions(ip)) + return ip; + fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); + } while (count++ < 16 && p->state != TASK_RUNNING); + return 0; +} diff --git a/kernel/arch/x86/kernel/process_32.c b/kernel/arch/x86/kernel/process_32.c index 3a7071307..4dd4beae9 100644 --- a/kernel/arch/x86/kernel/process_32.c +++ b/kernel/arch/x86/kernel/process_32.c @@ -40,8 +40,7 @@ #include <asm/pgtable.h> #include <asm/ldt.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/desc.h> #ifdef CONFIG_MATH_EMULATION #include <asm/math_emu.h> @@ -55,6 +54,7 @@ #include <asm/syscalls.h> #include <asm/debugreg.h> #include <asm/switch_to.h> +#include <asm/vm86.h> asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); @@ -130,8 +130,8 @@ void release_thread(struct task_struct *dead_task) release_vm86_irqs(dead_task); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); struct task_struct *tsk; @@ -186,7 +186,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); if (err && p->thread.io_bitmap_ptr) { kfree(p->thread.io_bitmap_ptr); @@ -272,14 +272,16 @@ __visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, - *next = &next_p->thread; + *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); - fpu_switch_t fpu; + fpu_switch_t fpu_switch; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -308,14 +310,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) set_iopl_mask(next->iopl); /* - * If it were not for PREEMPT_ACTIVE we could guarantee that the - * preempt_count of all tasks was equal here and this would not be - * needed. - */ - task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); - this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); - - /* * Now maybe handle debug registers and/or IO bitmaps */ if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || @@ -328,19 +322,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up + * done before fpu__restore(), so the TS bit is up * to date. */ arch_end_context_switch(next_p); /* - * Reload esp0, kernel_stack, and current_top_of_stack. This changes + * Reload esp0 and cpu_current_top_of_stack. This changes * current_thread_info(). */ load_sp0(tss, next); - this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + - THREAD_SIZE); this_cpu_write(cpu_current_top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); @@ -351,37 +342,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) lazy_load_gs(next->gs); - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); this_cpu_write(current_task, next_p); return prev_p; } - -#define top_esp (THREAD_SIZE - sizeof(unsigned long)) -#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) - -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long bp, sp, ip; - unsigned long stack_page; - int count = 0; - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack_page = (unsigned long)task_stack_page(p); - sp = p->thread.sp; - if (!stack_page || sp < stack_page || sp > top_esp+stack_page) - return 0; - /* include/asm-i386/system.h:switch_to() pushes bp last. */ - bp = *(unsigned long *) sp; - do { - if (bp < stack_page || bp > top_ebp+stack_page) - return 0; - ip = *(unsigned long *) (bp+4); - if (!in_sched_functions(ip)) - return ip; - bp = *(unsigned long *) bp; - } while (count++ < 16); - return 0; -} - diff --git a/kernel/arch/x86/kernel/process_64.c b/kernel/arch/x86/kernel/process_64.c index 5e0bf57d9..e835d263a 100644 --- a/kernel/arch/x86/kernel/process_64.c +++ b/kernel/arch/x86/kernel/process_64.c @@ -38,8 +38,7 @@ #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mmu_context.h> #include <asm/prctl.h> #include <asm/desc.h> @@ -122,6 +121,7 @@ void __show_regs(struct pt_regs *regs, int all) void release_thread(struct task_struct *dead_task) { if (dead_task->mm) { +#ifdef CONFIG_MODIFY_LDT_SYSCALL if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, @@ -129,6 +129,7 @@ void release_thread(struct task_struct *dead_task) dead_task->mm->context.ldt->size); BUG(); } +#endif } } @@ -151,8 +152,8 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls) return get_desc_base(&t->thread.tls_array[tls]); } -int copy_thread(unsigned long clone_flags, unsigned long sp, - unsigned long arg, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long sp, + unsigned long arg, struct task_struct *p, unsigned long tls) { int err; struct pt_regs *childregs; @@ -208,10 +209,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, #ifdef CONFIG_IA32_EMULATION if (is_ia32_task()) err = do_set_thread_area(p, -1, - (struct user_desc __user *)childregs->si, 0); + (struct user_desc __user *)tls, 0); else #endif - err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); + err = do_arch_prctl(p, ARCH_SET_FS, tls); if (err) goto out; } @@ -249,8 +250,8 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) __USER_CS, __USER_DS, 0); } -#ifdef CONFIG_IA32_EMULATION -void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) +#ifdef CONFIG_COMPAT +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp) { start_thread_common(regs, new_ip, new_sp, test_thread_flag(TIF_X32) @@ -274,12 +275,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; + struct fpu *prev_fpu = &prev->fpu; + struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(cpu_tss, cpu); unsigned fsindex, gsindex; - fpu_switch_t fpu; + fpu_switch_t fpu_switch; - fpu = switch_fpu_prepare(prev_p, next_p, cpu); + fpu_switch = switch_fpu_prepare(prev_fpu, next_fpu, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -299,7 +302,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Leave lazy mode, flushing any hypercalls made here. This * must be done after loading TLS entries in the GDT but before * loading segments that might reference them, and and it must - * be done before math_state_restore, so the TS bit is up to + * be done before fpu__restore(), so the TS bit is up to * date. */ arch_end_context_switch(next_p); @@ -329,7 +332,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Switch FS and GS. * - * These are even more complicated than FS and GS: they have + * These are even more complicated than DS and ES: they have * 64-bit bases are that controlled by arch_prctl. Those bases * only differ from the values in the GDT or LDT if the selector * is 0. @@ -391,27 +394,16 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) wrmsrl(MSR_KERNEL_GS_BASE, next->gs); prev->gsindex = gsindex; - switch_fpu_finish(next_p, fpu); + switch_fpu_finish(next_fpu, fpu_switch); /* * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); - /* - * If it were not for PREEMPT_ACTIVE we could guarantee that the - * preempt_count of all tasks was equal here and this would not be - * needed. - */ - task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); - this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); - /* Reload esp0 and ss1. This changes current_thread_info(). */ load_sp0(tss, next); - this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + THREAD_SIZE); - /* * Now maybe reload the debug registers and handle I/O bitmaps */ @@ -499,30 +491,6 @@ void set_personality_ia32(bool x32) } EXPORT_SYMBOL_GPL(set_personality_ia32); -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long stack; - u64 fp, ip; - int count = 0; - - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack = (unsigned long)task_stack_page(p); - if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE) - return 0; - fp = *(u64 *)(p->thread.sp); - do { - if (fp < (unsigned long)stack || - fp >= (unsigned long)stack+THREAD_SIZE) - return 0; - ip = *(u64 *)(fp+8); - if (!in_sched_functions(ip)) - return ip; - fp = *(u64 *)fp; - } while (count++ < 16); - return 0; -} - long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) { int ret = 0; diff --git a/kernel/arch/x86/kernel/ptrace.c b/kernel/arch/x86/kernel/ptrace.c index a7bc79480..558f50ede 100644 --- a/kernel/arch/x86/kernel/ptrace.c +++ b/kernel/arch/x86/kernel/ptrace.c @@ -11,7 +11,6 @@ #include <linux/errno.h> #include <linux/slab.h> #include <linux/ptrace.h> -#include <linux/regset.h> #include <linux/tracehook.h> #include <linux/user.h> #include <linux/elf.h> @@ -28,8 +27,9 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/processor.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> +#include <asm/fpu/regset.h> #include <asm/debugreg.h> #include <asm/ldt.h> #include <asm/desc.h> @@ -37,12 +37,10 @@ #include <asm/proto.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> +#include <asm/syscall.h> #include "tls.h" -#define CREATE_TRACE_POINTS -#include <trace/events/syscalls.h> - enum x86_regset { REGSET_GENERAL, REGSET_FP, @@ -1123,6 +1121,73 @@ static int genregs32_set(struct task_struct *target, return ret; } +static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + unsigned long addr = caddr; + unsigned long data = cdata; + void __user *datap = compat_ptr(data); + int ret; + __u32 val; + + switch (request) { + case PTRACE_PEEKUSR: + ret = getreg32(child, addr, &val); + if (ret == 0) + ret = put_user(val, (__u32 __user *)datap); + break; + + case PTRACE_POKEUSR: + ret = putreg32(child, addr, data); + break; + + case PTRACE_GETREGS: /* Get all gp regs from the child. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_GENERAL, + 0, sizeof(struct user_regs_struct32), + datap); + + case PTRACE_SETREGS: /* Set all gp regs in the child. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_GENERAL, 0, + sizeof(struct user_regs_struct32), + datap); + + case PTRACE_GETFPREGS: /* Get the child FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_FP, 0, + sizeof(struct user_i387_ia32_struct), + datap); + + case PTRACE_SETFPREGS: /* Set the child FPU state. */ + return copy_regset_from_user( + child, &user_x86_32_view, REGSET_FP, + 0, sizeof(struct user_i387_ia32_struct), datap); + + case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ + return copy_regset_to_user(child, &user_x86_32_view, + REGSET_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ + return copy_regset_from_user(child, &user_x86_32_view, + REGSET_XFP, 0, + sizeof(struct user32_fxsr_struct), + datap); + + case PTRACE_GET_THREAD_AREA: + case PTRACE_SET_THREAD_AREA: + return arch_ptrace(child, request, addr, data); + + default: + return compat_ptrace_request(child, request, addr, data); + } + + return ret; +} +#endif /* CONFIG_IA32_EMULATION */ + #ifdef CONFIG_X86_X32_ABI static long x32_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, @@ -1211,78 +1276,21 @@ static long x32_arch_ptrace(struct task_struct *child, } #endif +#ifdef CONFIG_COMPAT long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { - unsigned long addr = caddr; - unsigned long data = cdata; - void __user *datap = compat_ptr(data); - int ret; - __u32 val; - #ifdef CONFIG_X86_X32_ABI if (!is_ia32_task()) return x32_arch_ptrace(child, request, caddr, cdata); #endif - - switch (request) { - case PTRACE_PEEKUSR: - ret = getreg32(child, addr, &val); - if (ret == 0) - ret = put_user(val, (__u32 __user *)datap); - break; - - case PTRACE_POKEUSR: - ret = putreg32(child, addr, data); - break; - - case PTRACE_GETREGS: /* Get all gp regs from the child. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_GENERAL, - 0, sizeof(struct user_regs_struct32), - datap); - - case PTRACE_SETREGS: /* Set all gp regs in the child. */ - return copy_regset_from_user(child, &user_x86_32_view, - REGSET_GENERAL, 0, - sizeof(struct user_regs_struct32), - datap); - - case PTRACE_GETFPREGS: /* Get the child FPU state. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_FP, 0, - sizeof(struct user_i387_ia32_struct), - datap); - - case PTRACE_SETFPREGS: /* Set the child FPU state. */ - return copy_regset_from_user( - child, &user_x86_32_view, REGSET_FP, - 0, sizeof(struct user_i387_ia32_struct), datap); - - case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ - return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, 0, - sizeof(struct user32_fxsr_struct), - datap); - - case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ - return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, 0, - sizeof(struct user32_fxsr_struct), - datap); - - case PTRACE_GET_THREAD_AREA: - case PTRACE_SET_THREAD_AREA: - return arch_ptrace(child, request, addr, data); - - default: - return compat_ptrace_request(child, request, addr, data); - } - - return ret; +#ifdef CONFIG_IA32_EMULATION + return ia32_arch_ptrace(child, request, caddr, cdata); +#else + return 0; +#endif } - -#endif /* CONFIG_IA32_EMULATION */ +#endif /* CONFIG_COMPAT */ #ifdef CONFIG_X86_64 @@ -1297,7 +1305,7 @@ static struct user_regset x86_64_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_struct) / sizeof(long), .size = sizeof(long), .align = sizeof(long), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, @@ -1338,13 +1346,13 @@ static struct user_regset x86_32_regsets[] __read_mostly = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = fpregs_active, .get = fpregs_get, .set = fpregs_set + .active = regset_fpregs_active, .get = fpregs_get, .set = fpregs_set }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), - .active = xfpregs_active, .get = xfpregs_get, .set = xfpregs_set + .active = regset_xregset_fpregs_active, .get = xfpregs_get, .set = xfpregs_set }, [REGSET_XSTATE] = { .core_note_type = NT_X86_XSTATE, @@ -1434,201 +1442,3 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, /* Send us the fake SIGTRAP */ force_sig_info(SIGTRAP, &info, tsk); } - -static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) -{ -#ifdef CONFIG_X86_64 - if (arch == AUDIT_ARCH_X86_64) { - audit_syscall_entry(regs->orig_ax, regs->di, - regs->si, regs->dx, regs->r10); - } else -#endif - { - audit_syscall_entry(regs->orig_ax, regs->bx, - regs->cx, regs->dx, regs->si); - } -} - -/* - * We can return 0 to resume the syscall or anything else to go to phase - * 2. If we resume the syscall, we need to put something appropriate in - * regs->orig_ax. - * - * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax - * are fully functional. - * - * For phase 2's benefit, our return value is: - * 0: resume the syscall - * 1: go to phase 2; no seccomp phase 2 needed - * anything else: go to phase 2; pass return value to seccomp - */ -unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch) -{ - unsigned long ret = 0; - u32 work; - - BUG_ON(regs != task_pt_regs(current)); - - work = ACCESS_ONCE(current_thread_info()->flags) & - _TIF_WORK_SYSCALL_ENTRY; - - /* - * If TIF_NOHZ is set, we are required to call user_exit() before - * doing anything that could touch RCU. - */ - if (work & _TIF_NOHZ) { - user_exit(); - work &= ~_TIF_NOHZ; - } - -#ifdef CONFIG_SECCOMP - /* - * Do seccomp first -- it should minimize exposure of other - * code, and keeping seccomp fast is probably more valuable - * than the rest of this. - */ - if (work & _TIF_SECCOMP) { - struct seccomp_data sd; - - sd.arch = arch; - sd.nr = regs->orig_ax; - sd.instruction_pointer = regs->ip; -#ifdef CONFIG_X86_64 - if (arch == AUDIT_ARCH_X86_64) { - sd.args[0] = regs->di; - sd.args[1] = regs->si; - sd.args[2] = regs->dx; - sd.args[3] = regs->r10; - sd.args[4] = regs->r8; - sd.args[5] = regs->r9; - } else -#endif - { - sd.args[0] = regs->bx; - sd.args[1] = regs->cx; - sd.args[2] = regs->dx; - sd.args[3] = regs->si; - sd.args[4] = regs->di; - sd.args[5] = regs->bp; - } - - BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0); - BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1); - - ret = seccomp_phase1(&sd); - if (ret == SECCOMP_PHASE1_SKIP) { - regs->orig_ax = -1; - ret = 0; - } else if (ret != SECCOMP_PHASE1_OK) { - return ret; /* Go directly to phase 2 */ - } - - work &= ~_TIF_SECCOMP; - } -#endif - - /* Do our best to finish without phase 2. */ - if (work == 0) - return ret; /* seccomp and/or nohz only (ret == 0 here) */ - -#ifdef CONFIG_AUDITSYSCALL - if (work == _TIF_SYSCALL_AUDIT) { - /* - * If there is no more work to be done except auditing, - * then audit in phase 1. Phase 2 always audits, so, if - * we audit here, then we can't go on to phase 2. - */ - do_audit_syscall_entry(regs, arch); - return 0; - } -#endif - - return 1; /* Something is enabled that we can't handle in phase 1 */ -} - -/* Returns the syscall nr to run (which should match regs->orig_ax). */ -long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch, - unsigned long phase1_result) -{ - long ret = 0; - u32 work = ACCESS_ONCE(current_thread_info()->flags) & - _TIF_WORK_SYSCALL_ENTRY; - - BUG_ON(regs != task_pt_regs(current)); - - /* - * If we stepped into a sysenter/syscall insn, it trapped in - * kernel mode; do_debug() cleared TF and set TIF_SINGLESTEP. - * If user-mode had set TF itself, then it's still clear from - * do_debug() and we need to set it again to restore the user - * state. If we entered on the slow path, TF was already set. - */ - if (work & _TIF_SINGLESTEP) - regs->flags |= X86_EFLAGS_TF; - -#ifdef CONFIG_SECCOMP - /* - * Call seccomp_phase2 before running the other hooks so that - * they can see any changes made by a seccomp tracer. - */ - if (phase1_result > 1 && seccomp_phase2(phase1_result)) { - /* seccomp failures shouldn't expose any additional code. */ - return -1; - } -#endif - - if (unlikely(work & _TIF_SYSCALL_EMU)) - ret = -1L; - - if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) && - tracehook_report_syscall_entry(regs)) - ret = -1L; - - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_enter(regs, regs->orig_ax); - - do_audit_syscall_entry(regs, arch); - - return ret ?: regs->orig_ax; -} - -long syscall_trace_enter(struct pt_regs *regs) -{ - u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; - unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch); - - if (phase1_result == 0) - return regs->orig_ax; - else - return syscall_trace_enter_phase2(regs, arch, phase1_result); -} - -void syscall_trace_leave(struct pt_regs *regs) -{ - bool step; - - /* - * We may come here right after calling schedule_user() - * or do_notify_resume(), in which case we can be in RCU - * user mode. - */ - user_exit(); - - audit_syscall_exit(regs); - - if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->ax); - - /* - * If TIF_SYSCALL_EMU is set, we only get here because of - * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP). - * We already reported this syscall instruction in - * syscall_trace_enter(). - */ - step = unlikely(test_thread_flag(TIF_SINGLESTEP)) && - !test_thread_flag(TIF_SYSCALL_EMU); - if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); - - user_enter(); -} diff --git a/kernel/arch/x86/kernel/quirks.c b/kernel/arch/x86/kernel/quirks.c index 176a0f99d..cc457ff81 100644 --- a/kernel/arch/x86/kernel/quirks.c +++ b/kernel/arch/x86/kernel/quirks.c @@ -524,7 +524,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU, */ static void force_disable_hpet_msi(struct pci_dev *unused) { - hpet_msi_disable = 1; + hpet_msi_disable = true; } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, diff --git a/kernel/arch/x86/kernel/reboot.c b/kernel/arch/x86/kernel/reboot.c index 86db4bcd7..f660d63f4 100644 --- a/kernel/arch/x86/kernel/reboot.c +++ b/kernel/arch/x86/kernel/reboot.c @@ -182,6 +182,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"), }, }, + { /* Handle problems with rebooting on the iMac10,1. */ + .callback = set_pci_reboot, + .ident = "Apple iMac10,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "iMac10,1"), + }, + }, /* ASRock */ { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ @@ -673,7 +681,7 @@ struct machine_ops machine_ops = { .emergency_restart = native_machine_emergency_restart, .restart = native_machine_restart, .halt = native_machine_halt, -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE .crash_shutdown = native_machine_crash_shutdown, #endif }; @@ -703,7 +711,7 @@ void machine_halt(void) machine_ops.halt(); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE void machine_crash_shutdown(struct pt_regs *regs) { machine_ops.crash_shutdown(regs); diff --git a/kernel/arch/x86/kernel/rtc.c b/kernel/arch/x86/kernel/rtc.c index cd9685235..4af8d063f 100644 --- a/kernel/arch/x86/kernel/rtc.c +++ b/kernel/arch/x86/kernel/rtc.c @@ -200,6 +200,9 @@ static __init int add_rtc_cmos(void) } #endif + if (paravirt_enabled() && !paravirt_has(RTC)) + return -ENODEV; + platform_device_register(&rtc_device); dev_info(&rtc_device.dev, "registered platform RTC device (no PNP device found)\n"); diff --git a/kernel/arch/x86/kernel/setup.c b/kernel/arch/x86/kernel/setup.c index d74ac3329..d2bbe343f 100644 --- a/kernel/arch/x86/kernel/setup.c +++ b/kernel/arch/x86/kernel/setup.c @@ -111,6 +111,7 @@ #include <asm/mce.h> #include <asm/alternative.h> #include <asm/prom.h> +#include <asm/microcode.h> /* * max_low_pfn_mapped: highest direct mapped pfn under 4GB @@ -317,15 +318,12 @@ static u64 __init get_ramdisk_size(void) return ramdisk_size; } -#define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) static void __init relocate_initrd(void) { /* Assume only end is not page aligned */ u64 ramdisk_image = get_ramdisk_image(); u64 ramdisk_size = get_ramdisk_size(); u64 area_size = PAGE_ALIGN(ramdisk_size); - unsigned long slop, clen, mapaddr; - char *p, *q; /* We need to move the initrd down into directly mapped mem */ relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), @@ -343,25 +341,8 @@ static void __init relocate_initrd(void) printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n", relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1); - q = (char *)initrd_start; - - /* Copy the initrd */ - while (ramdisk_size) { - slop = ramdisk_image & ~PAGE_MASK; - clen = ramdisk_size; - if (clen > MAX_MAP_CHUNK-slop) - clen = MAX_MAP_CHUNK-slop; - mapaddr = ramdisk_image & PAGE_MASK; - p = early_memremap(mapaddr, clen+slop); - memcpy(q, p+slop, clen); - early_memunmap(p, clen+slop); - q += clen; - ramdisk_image += clen; - ramdisk_size -= clen; - } + copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size); - ramdisk_image = get_ramdisk_image(); - ramdisk_size = get_ramdisk_size(); printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to" " [mem %#010llx-%#010llx]\n", ramdisk_image, ramdisk_image + ramdisk_size - 1, @@ -461,19 +442,18 @@ static void __init e820_reserve_setup_data(void) { struct setup_data *data; u64 pa_data; - int found = 0; pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return; + while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); e820_update_range(pa_data, sizeof(*data)+data->len, E820_RAM, E820_RESERVED_KERN); - found = 1; pa_data = data->next; early_memunmap(data, sizeof(*data)); } - if (!found) - return; sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); memcpy(&e820_saved, &e820, sizeof(struct e820map)); @@ -499,7 +479,10 @@ static void __init memblock_x86_reserve_range_setup_data(void) * --------- Crashkernel reservation ------------------------------ */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE + +/* 16M alignment for crash kernel regions */ +#define CRASH_ALIGN (16 << 20) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels @@ -507,81 +490,80 @@ static void __init memblock_x86_reserve_range_setup_data(void) * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) -# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) +# define CRASH_ADDR_LOW_MAX (512 << 20) +# define CRASH_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) -# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM +# define CRASH_ADDR_LOW_MAX (896UL << 20) +# define CRASH_ADDR_HIGH_MAX MAXMEM #endif -static void __init reserve_crashkernel_low(void) +static int __init reserve_crashkernel_low(void) { #ifdef CONFIG_X86_64 - const unsigned long long alignment = 16<<20; /* 16M */ - unsigned long long low_base = 0, low_size = 0; + unsigned long long base, low_base = 0, low_size = 0; unsigned long total_low_mem; - unsigned long long base; - bool auto_set = false; int ret; - total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT)); + /* crashkernel=Y,low */ - ret = parse_crashkernel_low(boot_command_line, total_low_mem, - &low_size, &base); - if (ret != 0) { + ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); + if (ret) { /* * two parts from lib/swiotlb.c: - * swiotlb size: user specified with swiotlb= or default. - * swiotlb overflow buffer: now is hardcoded to 32k. - * We round it to 8M for other buffers that - * may need to stay low too. + * -swiotlb size: user-specified with swiotlb= or default. + * + * -swiotlb overflow buffer: now hardcoded to 32k. We round it + * to 8M for other buffers that may need to stay low too. Also + * make sure we allocate enough extra low memory so that we + * don't run out of DMA buffers for 32-bit devices. */ - low_size = swiotlb_size_or_default() + (8UL<<20); - auto_set = true; + low_size = max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); } else { /* passed with crashkernel=0,low ? */ if (!low_size) - return; + return 0; } - low_base = memblock_find_in_range(low_size, (1ULL<<32), - low_size, alignment); - + low_base = memblock_find_in_range(low_size, 1ULL << 32, low_size, CRASH_ALIGN); if (!low_base) { - if (!auto_set) - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n", + (unsigned long)(low_size >> 20)); + return -ENOMEM; + } - return; + ret = memblock_reserve(low_base, low_size); + if (ret) { + pr_err("%s: Error reserving crashkernel low memblock.\n", __func__); + return ret; } - memblock_reserve(low_base, low_size); pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n", - (unsigned long)(low_size >> 20), - (unsigned long)(low_base >> 20), - (unsigned long)(total_low_mem >> 20)); + (unsigned long)(low_size >> 20), + (unsigned long)(low_base >> 20), + (unsigned long)(total_low_mem >> 20)); + crashk_low_res.start = low_base; crashk_low_res.end = low_base + low_size - 1; insert_resource(&iomem_resource, &crashk_low_res); #endif + return 0; } static void __init reserve_crashkernel(void) { - const unsigned long long alignment = 16<<20; /* 16M */ - unsigned long long total_mem; - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem; bool high = false; int ret; total_mem = memblock_phys_mem_size(); /* crashkernel=XM */ - ret = parse_crashkernel(boot_command_line, total_mem, - &crash_size, &crash_base); + ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); if (ret != 0 || crash_size <= 0) { /* crashkernel=X,high */ ret = parse_crashkernel_high(boot_command_line, total_mem, - &crash_size, &crash_base); + &crash_size, &crash_base); if (ret != 0 || crash_size <= 0) return; high = true; @@ -592,11 +574,10 @@ static void __init reserve_crashkernel(void) /* * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ - crash_base = memblock_find_in_range(alignment, - high ? CRASH_KERNEL_ADDR_HIGH_MAX : - CRASH_KERNEL_ADDR_LOW_MAX, - crash_size, alignment); - + crash_base = memblock_find_in_range(CRASH_ALIGN, + high ? CRASH_ADDR_HIGH_MAX + : CRASH_ADDR_LOW_MAX, + crash_size, CRASH_ALIGN); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; @@ -606,26 +587,32 @@ static void __init reserve_crashkernel(void) unsigned long long start; start = memblock_find_in_range(crash_base, - crash_base + crash_size, crash_size, 1<<20); + crash_base + crash_size, + crash_size, 1 << 20); if (start != crash_base) { pr_info("crashkernel reservation failed - memory is in use.\n"); return; } } - memblock_reserve(crash_base, crash_size); + ret = memblock_reserve(crash_base, crash_size); + if (ret) { + pr_err("%s: Error reserving crashkernel memblock.\n", __func__); + return; + } - printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " - "for crashkernel (System RAM: %ldMB)\n", - (unsigned long)(crash_size >> 20), - (unsigned long)(crash_base >> 20), - (unsigned long)(total_mem >> 20)); + if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) { + memblock_free(crash_base, crash_size); + return; + } + + pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crash_base >> 20), + (unsigned long)(total_mem >> 20)); crashk_res.start = crash_base; crashk_res.end = crash_base + crash_size - 1; insert_resource(&iomem_resource, &crashk_res); - - if (crash_base >= (1ULL<<32)) - reserve_crashkernel_low(); } #else static void __init reserve_crashkernel(void) @@ -834,7 +821,7 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { if (kaslr_enabled()) { pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n", - (unsigned long)&_text - __START_KERNEL, + kaslr_offset(), __START_KERNEL, __START_KERNEL_map, MODULES_VADDR-1); @@ -915,11 +902,6 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_X86_32 apm_info.bios = boot_params.apm_bios_info; ist_info = boot_params.ist_info; - if (boot_params.sys_desc_table.length != 0) { - machine_id = boot_params.sys_desc_table.table[0]; - machine_submodel_id = boot_params.sys_desc_table.table[1]; - BIOS_revision = boot_params.sys_desc_table.table[2]; - } #endif saved_video_mode = boot_params.hdr.vid_mode; bootloader_type = boot_params.hdr.type_of_loader; @@ -1103,6 +1085,11 @@ void __init setup_arch(char **cmdline_p) memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); + if (efi_enabled(EFI_BOOT)) { + efi_fake_memmap(); + efi_find_mirror(); + } + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1194,6 +1181,14 @@ void __init setup_arch(char **cmdline_p) clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); + + /* + * sync back low identity map too. It is used for example + * in the 32-bit EFI stub. + */ + clone_pgd_range(initial_page_table, + swapper_pg_dir + KERNEL_PGD_BOUNDARY, + min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY)); #endif tboot_probe(); @@ -1222,8 +1217,7 @@ void __init setup_arch(char **cmdline_p) init_cpu_to_node(); init_apic_mappings(); - if (x86_io_apic_ops.init) - x86_io_apic_ops.init(); + io_apic_init_mappings(); kvm_guest_init(); diff --git a/kernel/arch/x86/kernel/signal.c b/kernel/arch/x86/kernel/signal.c index 12c28f79e..cb6282c36 100644 --- a/kernel/arch/x86/kernel/signal.c +++ b/kernel/arch/x86/kernel/signal.c @@ -26,16 +26,16 @@ #include <asm/processor.h> #include <asm/ucontext.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> +#include <asm/fpu/signal.h> #include <asm/vdso.h> #include <asm/mce.h> #include <asm/sighandling.h> +#include <asm/vm86.h> #ifdef CONFIG_X86_64 #include <asm/proto.h> #include <asm/ia32_unistd.h> -#include <asm/sys_ia32.h> #endif /* CONFIG_X86_64 */ #include <asm/syscall.h> @@ -63,6 +63,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) { + unsigned long buf_val; void __user *buf; unsigned int tmpflags; unsigned int err = 0; @@ -107,10 +108,11 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ - get_user_ex(buf, &sc->fpstate); + get_user_ex(buf_val, &sc->fpstate); + buf = (void __user *)buf_val; } get_user_catch(err); - err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + err |= fpu__restore_sig(buf, config_enabled(CONFIG_X86_32)); force_iret(); @@ -196,7 +198,7 @@ static unsigned long align_sigframe(unsigned long sp) return sp; } -static inline void __user * +static void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { @@ -205,6 +207,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long sp = regs->sp; unsigned long buf_fx = 0; int onsigstack = on_sig_stack(sp); + struct fpu *fpu = ¤t->thread.fpu; /* redzone */ if (config_enabled(CONFIG_X86_64)) @@ -224,9 +227,9 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, } } - if (used_math()) { - sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32), - &buf_fx, &math_size); + if (fpu->fpstate_active) { + sp = fpu__alloc_mathframe(sp, config_enabled(CONFIG_X86_32), + &buf_fx, &math_size); *fpstate = (void __user *)sp; } @@ -240,8 +243,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)-1L; /* save i387 and extended state */ - if (used_math() && - save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0) + if (fpu->fpstate_active && + copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0) return (void __user *)-1L; return (void __user *)sp; @@ -298,7 +301,7 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, if (current->mm->context.vdso) restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_sigreturn; + vdso_image_32.sym___kernel_sigreturn; else restorer = &frame->retcode; if (ksig->ka.sa.sa_flags & SA_RESTORER) @@ -362,7 +365,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, /* Set up to return from userspace. */ restorer = current->mm->context.vdso + - selected_vdso32->sym___kernel_rt_sigreturn; + vdso_image_32.sym___kernel_rt_sigreturn; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; put_user_ex(restorer, &frame->pretcode); @@ -589,6 +592,22 @@ badframe: return 0; } +static inline int is_ia32_compat_frame(void) +{ + return config_enabled(CONFIG_IA32_EMULATION) && + test_thread_flag(TIF_IA32); +} + +static inline int is_ia32_frame(void) +{ + return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame(); +} + +static inline int is_x32_frame(void) +{ + return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32); +} + static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { @@ -613,6 +632,10 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { bool stepping, failed; + struct fpu *fpu = ¤t->thread.fpu; + + if (v8086_mode(regs)) + save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL); /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { @@ -661,25 +684,28 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - if (used_math()) - fpu_reset_state(current); + if (fpu->fpstate_active) + fpu__clear(fpu); } signal_setup_done(failed, ksig, stepping); } -#ifdef CONFIG_X86_32 -#define NR_restart_syscall __NR_restart_syscall -#else /* !CONFIG_X86_32 */ -#define NR_restart_syscall \ - test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall -#endif /* CONFIG_X86_32 */ +static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) +{ +#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64) + return __NR_restart_syscall; +#else /* !CONFIG_X86_32 && CONFIG_X86_64 */ + return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : + __NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT); +#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */ +} /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -static void do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { struct ksignal ksig; @@ -701,7 +727,7 @@ static void do_signal(struct pt_regs *regs) break; case -ERESTART_RESTARTBLOCK: - regs->ax = NR_restart_syscall; + regs->ax = get_nr_restart_syscall(regs); regs->ip -= 2; break; } @@ -714,40 +740,6 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -/* - * notification of userspace execution resumption - * - triggered by the TIF_WORK_MASK flags - */ -__visible void -do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) -{ - user_exit(); - -#ifdef ARCH_RT_DELAYS_SIGNAL_SEND - if (unlikely(current->forced_info.si_signo)) { - struct task_struct *t = current; - force_sig_info(t->forced_info.si_signo, &t->forced_info, t); - t->forced_info.si_signo = 0; - } -#endif - - if (thread_info_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - - /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs); - - if (thread_info_flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(regs); - } - if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) - fire_user_return_notifiers(); - - user_enter(); -} - void signal_fault(struct pt_regs *regs, void __user *frame, char *where) { struct task_struct *me = current; diff --git a/kernel/arch/x86/kernel/signal_compat.c b/kernel/arch/x86/kernel/signal_compat.c new file mode 100644 index 000000000..dc3c0b1c8 --- /dev/null +++ b/kernel/arch/x86/kernel/signal_compat.c @@ -0,0 +1,95 @@ +#include <linux/compat.h> +#include <linux/uaccess.h> + +int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from) +{ + int err = 0; + bool ia32 = test_thread_flag(TIF_IA32); + + if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t))) + return -EFAULT; + + put_user_try { + /* If you change siginfo_t structure, please make sure that + this code is fixed accordingly. + 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. */ + put_user_ex(from->si_signo, &to->si_signo); + put_user_ex(from->si_errno, &to->si_errno); + put_user_ex((short)from->si_code, &to->si_code); + + if (from->si_code < 0) { + put_user_ex(from->si_pid, &to->si_pid); + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(ptr_to_compat(from->si_ptr), &to->si_ptr); + } else { + /* + * First 32bits of unions are always present: + * si_pid === si_band === si_tid === si_addr(LS half) + */ + put_user_ex(from->_sifields._pad[0], + &to->_sifields._pad[0]); + switch (from->si_code >> 16) { + case __SI_FAULT >> 16: + break; + case __SI_SYS >> 16: + put_user_ex(from->si_syscall, &to->si_syscall); + put_user_ex(from->si_arch, &to->si_arch); + break; + case __SI_CHLD >> 16: + if (ia32) { + put_user_ex(from->si_utime, &to->si_utime); + put_user_ex(from->si_stime, &to->si_stime); + } else { + put_user_ex(from->si_utime, &to->_sifields._sigchld_x32._utime); + put_user_ex(from->si_stime, &to->_sifields._sigchld_x32._stime); + } + put_user_ex(from->si_status, &to->si_status); + /* FALL THROUGH */ + default: + case __SI_KILL >> 16: + put_user_ex(from->si_uid, &to->si_uid); + break; + case __SI_POLL >> 16: + put_user_ex(from->si_fd, &to->si_fd); + break; + case __SI_TIMER >> 16: + put_user_ex(from->si_overrun, &to->si_overrun); + put_user_ex(ptr_to_compat(from->si_ptr), + &to->si_ptr); + break; + /* This is not generated by the kernel as of now. */ + case __SI_RT >> 16: + case __SI_MESGQ >> 16: + put_user_ex(from->si_uid, &to->si_uid); + put_user_ex(from->si_int, &to->si_int); + break; + } + } + } put_user_catch(err); + + return err; +} + +int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) +{ + int err = 0; + u32 ptr32; + + if (!access_ok(VERIFY_READ, from, sizeof(compat_siginfo_t))) + return -EFAULT; + + get_user_try { + get_user_ex(to->si_signo, &from->si_signo); + get_user_ex(to->si_errno, &from->si_errno); + get_user_ex(to->si_code, &from->si_code); + + get_user_ex(to->si_pid, &from->si_pid); + get_user_ex(to->si_uid, &from->si_uid); + get_user_ex(ptr32, &from->si_ptr); + to->si_ptr = compat_ptr(ptr32); + } get_user_catch(err); + + return err; +} diff --git a/kernel/arch/x86/kernel/smp.c b/kernel/arch/x86/kernel/smp.c index be8e1bde0..12c828620 100644 --- a/kernel/arch/x86/kernel/smp.c +++ b/kernel/arch/x86/kernel/smp.c @@ -30,6 +30,7 @@ #include <asm/proto.h> #include <asm/apic.h> #include <asm/nmi.h> +#include <asm/mce.h> #include <asm/trace/irq_vectors.h> /* * Some notes on x86 processor bugs affecting SMP operation: @@ -170,8 +171,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) asmlinkage __visible void smp_reboot_interrupt(void) { - ack_APIC_irq(); - irq_enter(); + ipi_entering_ack_irq(); stop_this_cpu(NULL); irq_exit(); } @@ -244,6 +244,7 @@ static void native_stop_other_cpus(int wait) finish: local_irq_save(flags); disable_local_APIC(); + mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); local_irq_restore(flags); } @@ -265,12 +266,6 @@ __visible void smp_reschedule_interrupt(struct pt_regs *regs) */ } -static inline void smp_entering_irq(void) -{ - ack_APIC_irq(); - irq_enter(); -} - __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) { /* @@ -279,7 +274,7 @@ __visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) * scheduler_ipi(). This is OK, since those functions are allowed * to nest. */ - smp_entering_irq(); + ipi_entering_ack_irq(); trace_reschedule_entry(RESCHEDULE_VECTOR); __smp_reschedule_interrupt(); trace_reschedule_exit(RESCHEDULE_VECTOR); @@ -297,14 +292,14 @@ static inline void __smp_call_function_interrupt(void) __visible void smp_call_function_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); __smp_call_function_interrupt(); exiting_irq(); } __visible void smp_trace_call_function_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); __smp_call_function_interrupt(); trace_call_function_exit(CALL_FUNCTION_VECTOR); @@ -319,14 +314,14 @@ static inline void __smp_call_function_single_interrupt(void) __visible void smp_call_function_single_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); __smp_call_function_single_interrupt(); exiting_irq(); } __visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs) { - smp_entering_irq(); + ipi_entering_ack_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); __smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); diff --git a/kernel/arch/x86/kernel/smpboot.c b/kernel/arch/x86/kernel/smpboot.c index 50e547eac..fbabe4fcc 100644 --- a/kernel/arch/x86/kernel/smpboot.c +++ b/kernel/arch/x86/kernel/smpboot.c @@ -68,8 +68,7 @@ #include <asm/mwait.h> #include <asm/apic.h> #include <asm/io_apic.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/setup.h> #include <asm/uv/uv.h> #include <linux/mc146818rtc.h> @@ -98,8 +97,6 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); EXPORT_PER_CPU_SYMBOL(cpu_info); -atomic_t init_deasserted; - static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; @@ -147,16 +144,11 @@ static void smp_callin(void) /* * If waken up by an INIT in an 82489DX configuration - * we may get here before an INIT-deassert IPI reaches - * our local APIC. We have to wait for the IPI or we'll - * lock up on an APIC access. - * - * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI. + * cpu_callout_mask guarantees we don't get here before + * an INIT_deassert IPI reaches our local APIC, so it is + * now safe to touch our local APIC. */ cpuid = smp_processor_id(); - if (apic->wait_for_init_deassert && cpuid) - while (!atomic_read(&init_deasserted)) - cpu_relax(); /* * (This works even if the APIC is not enabled.) @@ -172,11 +164,6 @@ static void smp_callin(void) apic_ap_setup(); /* - * Need to setup vector mappings before we enable interrupts. - */ - setup_vector_irq(smp_processor_id()); - - /* * Save our processor parameters. Note: this information * is needed for clock calibration. */ @@ -240,18 +227,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* - * Enable the espfix hack for this CPU - */ -#ifdef CONFIG_X86_ESPFIX64 - init_espfix_ap(); -#endif - - /* - * We need to hold vector_lock so there the set of online cpus - * does not change while we are assigning vectors to cpus. Holding - * this lock ensures we don't half assign or remove an irq from a cpu. + * Lock vector_lock and initialize the vectors on this cpu + * before setting the cpu online. We must set it online with + * vector_lock held to prevent a concurrent setup/teardown + * from seeing a half valid vector space. */ lock_vector_lock(); + setup_vector_irq(smp_processor_id()); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); cpu_set_state_online(smp_processor_id()); @@ -314,10 +296,10 @@ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name) cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2)); } -#define link_mask(_m, c1, c2) \ +#define link_mask(mfunc, c1, c2) \ do { \ - cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \ - cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \ + cpumask_set_cpu((c1), mfunc(c2)); \ + cpumask_set_cpu((c2), mfunc(c1)); \ } while (0) static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -398,9 +380,9 @@ void set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_setup_mask); if (!has_mp) { - cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); + cpumask_set_cpu(cpu, topology_sibling_cpumask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); - cpumask_set_cpu(cpu, cpu_core_mask(cpu)); + cpumask_set_cpu(cpu, topology_core_cpumask(cpu)); c->booted_cores = 1; return; } @@ -409,32 +391,34 @@ void set_cpu_sibling_map(int cpu) o = &cpu_data(i); if ((i == cpu) || (has_smt && match_smt(c, o))) - link_mask(sibling, cpu, i); + link_mask(topology_sibling_cpumask, cpu, i); if ((i == cpu) || (has_mp && match_llc(c, o))) - link_mask(llc_shared, cpu, i); + link_mask(cpu_llc_shared_mask, cpu, i); } /* * This needs a separate iteration over the cpus because we rely on all - * cpu_sibling_mask links to be set-up. + * topology_sibling_cpumask links to be set-up. */ for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); if ((i == cpu) || (has_mp && match_die(c, o))) { - link_mask(core, cpu, i); + link_mask(topology_core_cpumask, cpu, i); /* * Does this new cpu bringup a new core? */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) { + if (cpumask_weight( + topology_sibling_cpumask(cpu)) == 1) { /* * for each core in package, increment * the booted_cores for this new cpu */ - if (cpumask_first(cpu_sibling_mask(i)) == i) + if (cpumask_first( + topology_sibling_cpumask(i)) == i) c->booted_cores++; /* * increment the core count for all @@ -514,6 +498,44 @@ void __inquire_remote_apic(int apicid) } /* + * The Multiprocessor Specification 1.4 (1997) example code suggests + * that there should be a 10ms delay between the BSP asserting INIT + * and de-asserting INIT, when starting a remote processor. + * But that slows boot and resume on modern processors, which include + * many cores and don't require that delay. + * + * Cmdline "init_cpu_udelay=" is available to over-ride this delay. + * Modern processor families are quirked to remove the delay entirely. + */ +#define UDELAY_10MS_DEFAULT 10000 + +static unsigned int init_udelay = UINT_MAX; + +static int __init cpu_init_udelay(char *str) +{ + get_option(&str, &init_udelay); + + return 0; +} +early_param("cpu_init_udelay", cpu_init_udelay); + +static void __init smp_quirk_init_udelay(void) +{ + /* if cmdline changed it from default, leave it alone */ + if (init_udelay != UINT_MAX) + return; + + /* if modern processor, use no delay */ + if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) || + ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) { + init_udelay = 0; + return; + } + /* else, use legacy delay */ + init_udelay = UDELAY_10MS_DEFAULT; +} + +/* * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this * won't ... remember to clear down the APIC, etc later. @@ -555,7 +577,7 @@ wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip) static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) { - unsigned long send_status, accept_status = 0; + unsigned long send_status = 0, accept_status = 0; int maxlvt, num_starts, j; maxlvt = lapic_get_maxlvt(); @@ -583,7 +605,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) pr_debug("Waiting for send to finish...\n"); send_status = safe_apic_wait_icr_idle(); - mdelay(10); + udelay(init_udelay); pr_debug("Deasserting INIT\n"); @@ -595,7 +617,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) send_status = safe_apic_wait_icr_idle(); mb(); - atomic_set(&init_deasserted, 1); /* * Should we send STARTUP IPIs ? @@ -640,7 +661,10 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - udelay(300); + if (init_udelay == 0) + udelay(10); + else + udelay(300); pr_debug("Startup point 1\n"); @@ -650,7 +674,11 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) /* * Give the other CPU some time to accept the IPI. */ - udelay(200); + if (init_udelay == 0) + udelay(10); + else + udelay(200); + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ apic_write(APIC_ESR, 0); accept_status = (apic_read(APIC_ESR) & 0xEF); @@ -792,8 +820,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); #endif - per_cpu(kernel_stack, cpu) = - (unsigned long)task_stack_page(idle) + THREAD_SIZE; } /* @@ -820,6 +846,13 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) initial_code = (unsigned long)start_secondary; stack_start = idle->thread.sp; + /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(cpu); +#endif + /* So we see what's up */ announce_cpu(cpu, apicid); @@ -828,8 +861,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) * the targeted processor. */ - atomic_set(&init_deasserted, 0); - if (get_uv_system_type() != UV_NON_UNIQUE_APIC) { pr_debug("Setting warm reset code and vector.\n"); @@ -867,7 +898,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) if (!boot_error) { /* - * Wait 10s total for a response from AP + * Wait 10s total for first sign of life from AP */ boot_error = -1; timeout = jiffies + 10*HZ; @@ -880,7 +911,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) boot_error = 0; break; } - udelay(100); schedule(); } } @@ -896,7 +926,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) * for the MTRR work(triggered by the AP coming online) * to be completed in the stop machine context. */ - udelay(100); schedule(); } } @@ -961,8 +990,17 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); + /* + * We have to walk the irq descriptors to setup the vector + * space for the cpu which comes online. Prevent irq + * alloc/free across the bringup. + */ + irq_lock_sparse(); + err = do_boot_cpu(apicid, cpu, tidle); + if (err) { + irq_unlock_sparse(); pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } @@ -980,6 +1018,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } + irq_unlock_sparse(); + return 0; } @@ -1009,8 +1049,8 @@ static __init void disable_smp(void) physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); else physid_set_mask_of_physid(0, &phys_cpu_present_map); - cpumask_set_cpu(0, cpu_sibling_mask(0)); - cpumask_set_cpu(0, cpu_core_mask(0)); + cpumask_set_cpu(0, topology_sibling_cpumask(0)); + cpumask_set_cpu(0, topology_core_cpumask(0)); } enum { @@ -1176,6 +1216,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) uv_system_init(); set_mtrr_aps_delayed_init(); + + smp_quirk_init_udelay(); } void arch_enable_nonboot_cpus_begin(void) @@ -1293,28 +1335,28 @@ static void remove_siblinginfo(int cpu) int sibling; struct cpuinfo_x86 *c = &cpu_data(cpu); - for_each_cpu(sibling, cpu_core_mask(cpu)) { - cpumask_clear_cpu(cpu, cpu_core_mask(sibling)); + for_each_cpu(sibling, topology_core_cpumask(cpu)) { + cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); /*/ * last thread sibling in this cpu core going down */ - if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) + if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1) cpu_data(sibling).booted_cores--; } - for_each_cpu(sibling, cpu_sibling_mask(cpu)) - cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, topology_sibling_cpumask(cpu)) + cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); cpumask_clear(cpu_llc_shared_mask(cpu)); - cpumask_clear(cpu_sibling_mask(cpu)); - cpumask_clear(cpu_core_mask(cpu)); + cpumask_clear(topology_sibling_cpumask(cpu)); + cpumask_clear(topology_core_cpumask(cpu)); c->phys_proc_id = 0; c->cpu_core_id = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); } -static void __ref remove_cpu_from_maps(int cpu) +static void remove_cpu_from_maps(int cpu) { set_cpu_online(cpu, false); cpumask_clear_cpu(cpu, cpu_callout_mask); diff --git a/kernel/arch/x86/kernel/step.c b/kernel/arch/x86/kernel/step.c index 0ccb53a9f..c9a073866 100644 --- a/kernel/arch/x86/kernel/step.c +++ b/kernel/arch/x86/kernel/step.c @@ -18,6 +18,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re return addr; } +#ifdef CONFIG_MODIFY_LDT_SYSCALL /* * We'll assume that the code segments in the GDT * are all zero-based. That is largely true: the @@ -45,6 +46,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re } mutex_unlock(&child->mm->context.lock); } +#endif return addr; } diff --git a/kernel/arch/x86/kernel/topology.c b/kernel/arch/x86/kernel/topology.c index 649b010da..12cbe2b88 100644 --- a/kernel/arch/x86/kernel/topology.c +++ b/kernel/arch/x86/kernel/topology.c @@ -57,7 +57,7 @@ __setup("cpu0_hotplug", enable_cpu0_hotplug); * * This is only called for debugging CPU offline/online feature. */ -int __ref _debug_hotplug_cpu(int cpu, int action) +int _debug_hotplug_cpu(int cpu, int action) { struct device *dev = get_cpu_device(cpu); int ret; @@ -104,7 +104,7 @@ static int __init debug_hotplug_cpu(void) late_initcall_sync(debug_hotplug_cpu); #endif /* CONFIG_DEBUG_HOTPLUG_CPU0 */ -int __ref arch_register_cpu(int num) +int arch_register_cpu(int num) { struct cpuinfo_x86 *c = &cpu_data(num); diff --git a/kernel/arch/x86/kernel/trace_clock.c b/kernel/arch/x86/kernel/trace_clock.c index 25b993729..80bb24d9b 100644 --- a/kernel/arch/x86/kernel/trace_clock.c +++ b/kernel/arch/x86/kernel/trace_clock.c @@ -12,10 +12,5 @@ */ u64 notrace trace_clock_x86_tsc(void) { - u64 ret; - - rdtsc_barrier(); - rdtscll(ret); - - return ret; + return rdtsc_ordered(); } diff --git a/kernel/arch/x86/kernel/traps.c b/kernel/arch/x86/kernel/traps.c index ebae11893..ade185a46 100644 --- a/kernel/arch/x86/kernel/traps.c +++ b/kernel/arch/x86/kernel/traps.c @@ -54,13 +54,15 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> #include <asm/alternative.h> +#include <asm/fpu/xstate.h> +#include <asm/trace/mpx.h> #include <asm/mpx.h> +#include <asm/vm86.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -72,8 +74,7 @@ gate_desc debug_idt_table[NR_VECTORS] __page_aligned_bss; #else #include <asm/processor-flags.h> #include <asm/setup.h> - -asmlinkage int system_call(void); +#include <asm/proto.h> #endif /* Must be page-aligned because the real IDT is used in a fixmap. */ @@ -88,21 +89,9 @@ static inline void conditional_sti(struct pt_regs *regs) local_irq_enable(); } -static inline void conditional_sti_ist(struct pt_regs *regs) +static inline void preempt_conditional_sti(struct pt_regs *regs) { -#ifdef CONFIG_X86_64 - /* - * X86_64 uses a per CPU stack on the IST for certain traps - * like int3. The task can not be preempted when using one - * of these stacks, thus preemption must be disabled, otherwise - * the stack can be corrupted if the task is scheduled out, - * and another task comes in and uses this stack. - * - * On x86_32 the task keeps its own stack and it is OK if the - * task schedules out. - */ preempt_count_inc(); -#endif if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); } @@ -113,22 +102,17 @@ static inline void conditional_cli(struct pt_regs *regs) local_irq_disable(); } -static inline void conditional_cli_ist(struct pt_regs *regs) +static inline void preempt_conditional_cli(struct pt_regs *regs) { if (regs->flags & X86_EFLAGS_IF) local_irq_disable(); -#ifdef CONFIG_X86_64 preempt_count_dec(); -#endif } -enum ctx_state ist_enter(struct pt_regs *regs) +void ist_enter(struct pt_regs *regs) { - enum ctx_state prev_state; - if (user_mode(regs)) { - /* Other than that, we're just an exception. */ - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); } else { /* * We might have interrupted pretty much anything. In @@ -137,32 +121,25 @@ enum ctx_state ist_enter(struct pt_regs *regs) * but we need to notify RCU. */ rcu_nmi_enter(); - prev_state = CONTEXT_KERNEL; /* the value is irrelevant. */ } /* - * We are atomic because we're on the IST stack (or we're on x86_32, - * in which case we still shouldn't schedule). - * - * This must be after exception_enter(), because exception_enter() - * won't do anything if in_interrupt() returns true. + * We are atomic because we're on the IST stack; or we're on + * x86_32, in which case we still shouldn't schedule; or we're + * on x86_64 and entered from user mode, in which case we're + * still atomic unless ist_begin_non_atomic is called. */ preempt_count_add(HARDIRQ_OFFSET); /* This code is a bit fragile. Test it. */ - rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work"); - - return prev_state; + RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); } -void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) +void ist_exit(struct pt_regs *regs) { - /* Must be before exception_exit. */ preempt_count_sub(HARDIRQ_OFFSET); - if (user_mode(regs)) - return exception_exit(prev_state); - else + if (!user_mode(regs)) rcu_nmi_exit(); } @@ -176,7 +153,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) * a double fault, it can be safe to schedule. ist_begin_non_atomic() * begins a non-atomic section within an ist_enter()/ist_exit() region. * Callers are responsible for enabling interrupts themselves inside - * the non-atomic section, and callers must call is_end_non_atomic() + * the non-atomic section, and callers must call ist_end_non_atomic() * before ist_exit(). */ void ist_begin_non_atomic(struct pt_regs *regs) @@ -303,17 +280,16 @@ NOKPROBE_SYMBOL(do_trap); static void do_error_trap(struct pt_regs *regs, long error_code, char *str, unsigned long trapnr, int signr) { - enum ctx_state prev_state = exception_enter(); siginfo_t info; + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { conditional_sti(regs); do_trap(trapnr, signr, str, regs, error_code, fill_trap_info(regs, signr, trapnr, &info)); } - - exception_exit(prev_state); } #define DO_ERROR(trapnr, signr, str, name) \ @@ -365,7 +341,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) } #endif - ist_enter(regs); /* Discard prev_state because we won't return. */ + ist_enter(regs); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; @@ -385,16 +361,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) { - struct task_struct *tsk = current; - struct xsave_struct *xsave_buf; - enum ctx_state prev_state; - struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; siginfo_t *info; - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); if (notify_die(DIE_TRAP, "bounds", regs, error_code, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) - goto exit; + return; conditional_sti(regs); if (!user_mode(regs)) @@ -407,15 +380,15 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) /* * We need to look at BNDSTATUS to resolve this exception. - * It is not directly accessible, though, so we need to - * do an xsave and then pull it out of the xsave buffer. + * A NULL here might mean that it is in its 'init state', + * which is all zeros which indicates MPX was not + * responsible for the exception. */ - fpu_save_init(&tsk->thread.fpu); - xsave_buf = &(tsk->thread.fpu.state->xsave); - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) goto exit_trap; + trace_bounds_exception_mpx(bndcsr); /* * The error code field of the BNDSTATUS register communicates status * information of a bound range exception #BR or operation involving @@ -423,11 +396,11 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) */ switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) { case 2: /* Bound directory has invalid entry. */ - if (mpx_handle_bd_fault(xsave_buf)) + if (mpx_handle_bd_fault()) goto exit_trap; break; /* Success, it was handled */ case 1: /* Bound violation. */ - info = mpx_generate_siginfo(regs, xsave_buf); + info = mpx_generate_siginfo(regs); if (IS_ERR(info)) { /* * We failed to decode the MPX instruction. Act as if @@ -451,9 +424,8 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) die("bounds", regs, error_code); } -exit: - exception_exit(prev_state); return; + exit_trap: /* * This path out is for all the cases where we could not @@ -463,35 +435,33 @@ exit_trap: * time.. */ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL); - exception_exit(prev_state); } dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; - enum ctx_state prev_state; - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); conditional_sti(regs); if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - goto exit; + return; } tsk = current; if (!user_mode(regs)) { if (fixup_exception(regs)) - goto exit; + return; tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; if (notify_die(DIE_GPF, "general protection fault", regs, error_code, X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) die("general protection fault", regs, error_code); - goto exit; + return; } tsk->thread.error_code = error_code; @@ -507,16 +477,12 @@ do_general_protection(struct pt_regs *regs, long error_code) } force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); -exit: - exception_exit(prev_state); } NOKPROBE_SYMBOL(do_general_protection); /* May run on IST stack. */ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - #ifdef CONFIG_DYNAMIC_FTRACE /* * ftrace must be first, everything else may cause a recursive crash. @@ -529,7 +495,8 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) if (poke_int3_handler(regs)) return; - prev_state = ist_enter(regs); + ist_enter(regs); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -550,12 +517,12 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) * as we may switch to the interrupt stack. */ debug_stack_usage_inc(); - conditional_sti_ist(regs); + preempt_conditional_sti(regs); do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL); - conditional_cli_ist(regs); + preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - ist_exit(regs, prev_state); + ist_exit(regs); } NOKPROBE_SYMBOL(do_int3); @@ -631,12 +598,11 @@ NOKPROBE_SYMBOL(fixup_bad_iret); dotraplinkage void do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; - enum ctx_state prev_state; int user_icebp = 0; unsigned long dr6; int si_code; - prev_state = ist_enter(regs); + ist_enter(regs); get_debugreg(dr6, 6); @@ -682,12 +648,12 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_inc(); /* It's safe to allow irq's after DR6 has been saved */ - conditional_sti_ist(regs); + preempt_conditional_sti(regs); if (v8086_mode(regs)) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); - conditional_cli_ist(regs); + preempt_conditional_cli(regs); debug_stack_usage_dec(); goto exit; } @@ -707,11 +673,11 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) si_code = get_si_code(tsk->thread.debugreg6); if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) send_sigtrap(tsk, regs, error_code, si_code); - conditional_cli_ist(regs); + preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - ist_exit(regs, prev_state); + ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -723,8 +689,8 @@ NOKPROBE_SYMBOL(do_debug); static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; + struct fpu *fpu = &task->thread.fpu; siginfo_t info; - unsigned short err; char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" : "simd exception"; @@ -732,8 +698,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) return; conditional_sti(regs); - if (!user_mode(regs)) - { + if (!user_mode(regs)) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; task->thread.trap_nr = trapnr; @@ -745,150 +710,46 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) /* * Save the info for the exception handler and clear the error. */ - unlazy_fpu(task); - task->thread.trap_nr = trapnr; + fpu__save(fpu); + + task->thread.trap_nr = trapnr; task->thread.error_code = error_code; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - if (trapnr == X86_TRAP_MF) { - unsigned short cwd, swd; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_addr = (void __user *)uprobe_get_trap_addr(regs); - err = swd & ~cwd; - } else { - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - unsigned short mxcsr = get_fpu_mxcsr(task); - err = ~(mxcsr >> 7) & mxcsr; - } + info.si_code = fpu__exception_code(fpu, trapnr); - if (err & 0x001) { /* Invalid op */ - /* - * swd & 0x240 == 0x040: Stack Underflow - * swd & 0x240 == 0x240: Stack Overflow - * User must clear the SF bit (0x40) if set - */ - info.si_code = FPE_FLTINV; - } else if (err & 0x004) { /* Divide by Zero */ - info.si_code = FPE_FLTDIV; - } else if (err & 0x008) { /* Overflow */ - info.si_code = FPE_FLTOVF; - } else if (err & 0x012) { /* Denormal, Underflow */ - info.si_code = FPE_FLTUND; - } else if (err & 0x020) { /* Precision */ - info.si_code = FPE_FLTRES; - } else { - /* - * If we're using IRQ 13, or supposedly even some trap - * X86_TRAP_MF implementations, it's possible - * we get a spurious trap, which is not an error. - */ + /* Retry when we get spurious exceptions: */ + if (!info.si_code) return; - } + force_sig_info(SIGFPE, &info, task); } dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); math_error(regs, error_code, X86_TRAP_MF); - exception_exit(prev_state); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); math_error(regs, error_code, X86_TRAP_XF); - exception_exit(prev_state); } dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) { conditional_sti(regs); -#if 0 - /* No need to warn about this any longer. */ - pr_info("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); -#endif -} - -asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void) -{ -} - -asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void) -{ -} - -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - * - * Must be called with kernel preemption disabled (eg with local - * local interrupts as in the case of do_device_not_available). - */ -void math_state_restore(void) -{ - struct task_struct *tsk = current; - - if (!tsk_used_math(tsk)) { - local_irq_enable(); - /* - * does a slab alloc which can sleep - */ - if (init_fpu(tsk)) { - /* - * ran out of memory! - */ - do_group_exit(SIGKILL); - return; - } - local_irq_disable(); - } - - /* Avoid __kernel_fpu_begin() right after __thread_fpu_begin() */ - kernel_fpu_disable(); - __thread_fpu_begin(tsk); - if (unlikely(restore_fpu_checking(tsk))) { - fpu_reset_state(tsk); - force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); - } else { - tsk->thread.fpu_counter++; - } - kernel_fpu_enable(); } -EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { - enum ctx_state prev_state; - - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION @@ -899,15 +760,13 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - exception_exit(prev_state); return; } #endif - math_state_restore(); /* interrupts still off */ + fpu__restore(¤t->thread.fpu); /* interrupts still off */ #ifdef CONFIG_X86_32 conditional_sti(regs); #endif - exception_exit(prev_state); } NOKPROBE_SYMBOL(do_device_not_available); @@ -915,9 +774,8 @@ NOKPROBE_SYMBOL(do_device_not_available); dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; - enum ctx_state prev_state; - prev_state = exception_enter(); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); local_irq_enable(); info.si_signo = SIGILL; @@ -929,7 +787,6 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, &info); } - exception_exit(prev_state); } #endif @@ -1006,13 +863,13 @@ void __init trap_init(void) set_bit(i, used_vectors); #ifdef CONFIG_IA32_EMULATION - set_system_intr_gate(IA32_SYSCALL_VECTOR, ia32_syscall); + set_system_intr_gate(IA32_SYSCALL_VECTOR, entry_INT80_compat); set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif #ifdef CONFIG_X86_32 - set_system_trap_gate(SYSCALL_VECTOR, &system_call); - set_bit(SYSCALL_VECTOR, used_vectors); + set_system_trap_gate(IA32_SYSCALL_VECTOR, entry_INT80_32); + set_bit(IA32_SYSCALL_VECTOR, used_vectors); #endif /* diff --git a/kernel/arch/x86/kernel/tsc.c b/kernel/arch/x86/kernel/tsc.c index 505449700..c7c4d9c51 100644 --- a/kernel/arch/x86/kernel/tsc.c +++ b/kernel/arch/x86/kernel/tsc.c @@ -21,6 +21,7 @@ #include <asm/hypervisor.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/geode.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -38,7 +39,7 @@ static int __read_mostly tsc_unstable; erroneous rdtsc usage on !cpu_has_tsc processors */ static int __read_mostly tsc_disabled = -1; -static struct static_key __use_tsc = STATIC_KEY_INIT; +static DEFINE_STATIC_KEY_FALSE(__use_tsc); int tsc_clocksource_reliable; @@ -167,21 +168,20 @@ static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) * ns = cycles * cyc2ns_scale / SC * * And since SC is a constant power of two, we can convert the div - * into a shift. + * into a shift. The larger SC is, the more accurate the conversion, but + * cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication + * (64-bit result) can be used. * - * We can use khz divisor instead of mhz to keep a better precision, since - * cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits. + * We can use khz divisor instead of mhz to keep a better precision. * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ -#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */ - static void cyc2ns_data_init(struct cyc2ns_data *data) { data->cyc2ns_mul = 0; - data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + data->cyc2ns_shift = 0; data->cyc2ns_offset = 0; data->__count = 0; } @@ -215,14 +215,14 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) if (likely(data == tail)) { ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); } else { data->__count++; barrier(); ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); barrier(); @@ -248,7 +248,7 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) data = cyc2ns_write_begin(cpu); - rdtscll(tsc_now); + tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -256,12 +256,22 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - data->cyc2ns_mul = - DIV_ROUND_CLOSEST(NSEC_PER_MSEC << CYC2NS_SCALE_FACTOR, - cpu_khz); - data->cyc2ns_shift = CYC2NS_SCALE_FACTOR; + clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz, + NSEC_PER_MSEC, 0); + + /* + * cyc2ns_shift is exported via arch_perf_update_userpage() where it is + * not expected to be greater than 31 due to the original published + * conversion algorithm shifting a 32-bit value (now specifies a 64-bit + * value) - refer perf_event_mmap_page documentation in perf_event.h. + */ + if (data->cyc2ns_shift == 32) { + data->cyc2ns_shift = 31; + data->cyc2ns_mul >>= 1; + } + data->cyc2ns_offset = ns_now - - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, CYC2NS_SCALE_FACTOR); + mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); cyc2ns_write_end(cpu, data); @@ -274,7 +284,12 @@ done: */ u64 native_sched_clock(void) { - u64 tsc_now; + if (static_branch_likely(&__use_tsc)) { + u64 tsc_now = rdtsc(); + + /* return the value in ns */ + return cycles_2_ns(tsc_now); + } /* * Fall back to jiffies if there's no TSC available: @@ -284,16 +299,17 @@ u64 native_sched_clock(void) * very important for it to be as fast as the platform * can achieve it. ) */ - if (!static_key_false(&__use_tsc)) { - /* No locking but a rare wrong value is not a big deal: */ - return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); - } - /* read the Time Stamp Counter: */ - rdtscll(tsc_now); + /* No locking but a rare wrong value is not a big deal: */ + return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); +} - /* return the value in ns */ - return cycles_2_ns(tsc_now); +/* + * Generate a sched_clock if you already have a TSC value. + */ +u64 native_sched_clock_from_tsc(u64 tsc) +{ + return cycles_2_ns(tsc); } /* We need to define a real function for sched_clock, to override the @@ -308,12 +324,6 @@ unsigned long long sched_clock(void) __attribute__((alias("native_sched_clock"))); #endif -unsigned long long native_read_tsc(void) -{ - return __native_read_tsc(); -} -EXPORT_SYMBOL(native_read_tsc); - int check_tsc_unstable(void) { return tsc_unstable; @@ -598,10 +608,19 @@ static unsigned long quick_pit_calibrate(void) if (!pit_expect_msb(0xff-i, &delta, &d2)) break; + delta -= tsc; + + /* + * Extrapolate the error and fail fast if the error will + * never be below 500 ppm. + */ + if (i == 1 && + d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) + return 0; + /* * Iterate until the error is less than 500 ppm */ - delta -= tsc; if (d1+d2 >= delta >> 11) continue; @@ -967,7 +986,7 @@ static struct clocksource clocksource_tsc; */ static cycle_t read_tsc(struct clocksource *cs) { - return (cycle_t)get_cycles(); + return (cycle_t)rdtsc_ordered(); } /* @@ -1004,15 +1023,17 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable); static void __init check_system_tsc_reliable(void) { -#ifdef CONFIG_MGEODE_LX - /* RTSC counts during suspend */ +#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) + if (is_geode_lx()) { + /* RTSC counts during suspend */ #define RTSC_SUSP 0x100 - unsigned long res_low, res_high; + unsigned long res_low, res_high; - rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); - /* Geode_LX - the OLPC CPU has a very reliable TSC */ - if (res_low & RTSC_SUSP) - tsc_clocksource_reliable = 1; + rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); + /* Geode_LX - the OLPC CPU has a very reliable TSC */ + if (res_low & RTSC_SUSP) + tsc_clocksource_reliable = 1; + } #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; @@ -1201,7 +1222,7 @@ void __init tsc_init(void) /* now allow native_sched_clock() to use rdtsc */ tsc_disabled = 0; - static_key_slow_inc(&__use_tsc); + static_branch_enable(&__use_tsc); if (!no_sched_irq_time) enable_sched_clock_irqtime(); diff --git a/kernel/arch/x86/kernel/tsc_sync.c b/kernel/arch/x86/kernel/tsc_sync.c index 26488487b..78083bf23 100644 --- a/kernel/arch/x86/kernel/tsc_sync.c +++ b/kernel/arch/x86/kernel/tsc_sync.c @@ -39,16 +39,15 @@ static cycles_t max_warp; static int nr_warps; /* - * TSC-warp measurement loop running on both CPUs: + * TSC-warp measurement loop running on both CPUs. This is not called + * if there is no TSC. */ static void check_tsc_warp(unsigned int timeout) { cycles_t start, now, prev, end; int i; - rdtsc_barrier(); - start = get_cycles(); - rdtsc_barrier(); + start = rdtsc_ordered(); /* * The measurement runs for 'timeout' msecs: */ @@ -63,9 +62,7 @@ static void check_tsc_warp(unsigned int timeout) */ arch_spin_lock(&sync_lock); prev = last_tsc; - rdtsc_barrier(); - now = get_cycles(); - rdtsc_barrier(); + now = rdtsc_ordered(); last_tsc = now; arch_spin_unlock(&sync_lock); @@ -113,7 +110,7 @@ static void check_tsc_warp(unsigned int timeout) */ static inline unsigned int loop_timeout(int cpu) { - return (cpumask_weight(cpu_core_mask(cpu)) > 1) ? 2 : 20; + return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20; } /* @@ -126,7 +123,7 @@ void check_tsc_sync_source(int cpu) /* * No need to check if we already know that the TSC is not - * synchronized: + * synchronized or if we have no TSC. */ if (unsynchronized_tsc()) return; @@ -190,6 +187,7 @@ void check_tsc_sync_target(void) { int cpus = 2; + /* Also aborts if there is no TSC. */ if (unsynchronized_tsc() || tsc_clocksource_reliable) return; diff --git a/kernel/arch/x86/kernel/uprobes.c b/kernel/arch/x86/kernel/uprobes.c index 0b81ad67d..bf4db6eae 100644 --- a/kernel/arch/x86/kernel/uprobes.c +++ b/kernel/arch/x86/kernel/uprobes.c @@ -29,6 +29,7 @@ #include <linux/kdebug.h> #include <asm/processor.h> #include <asm/insn.h> +#include <asm/mmu_context.h> /* Post-execution fixups. */ @@ -312,11 +313,6 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool } #ifdef CONFIG_X86_64 -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return !config_enabled(CONFIG_IA32_EMULATION) || - !(mm->context.ia32_compat == TIF_IA32); -} /* * If arch_uprobe->insn doesn't use rip-relative addressing, return * immediately. Otherwise, rewrite the instruction so that it accesses @@ -497,10 +493,6 @@ static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) } } #else /* 32-bit: */ -static inline bool is_64bit_mm(struct mm_struct *mm) -{ - return false; -} /* * No RIP-relative addressing on 32-bit */ @@ -993,3 +985,12 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs return -1; } + +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CALL) /* sp was just decremented by "call" insn */ + return regs->sp < ret->stack; + else + return regs->sp <= ret->stack; +} diff --git a/kernel/arch/x86/kernel/verify_cpu.S b/kernel/arch/x86/kernel/verify_cpu.S index b9242bacb..4cf401f58 100644 --- a/kernel/arch/x86/kernel/verify_cpu.S +++ b/kernel/arch/x86/kernel/verify_cpu.S @@ -34,10 +34,11 @@ #include <asm/msr-index.h> verify_cpu: - pushfl # Save caller passed flags - pushl $0 # Kill any dangerous flags - popfl + pushf # Save caller passed flags + push $0 # Kill any dangerous flags + popf +#ifndef __x86_64__ pushfl # standard way to check for cpuid popl %eax movl %eax,%ebx @@ -48,6 +49,7 @@ verify_cpu: popl %eax cmpl %eax,%ebx jz verify_cpu_no_longmode # cpu has no cpuid +#endif movl $0x0,%eax # See if cpuid 1 is implemented cpuid @@ -130,10 +132,10 @@ verify_cpu_sse_test: jmp verify_cpu_sse_test # try again verify_cpu_no_longmode: - popfl # Restore caller passed flags + popf # Restore caller passed flags movl $1,%eax ret verify_cpu_sse_ok: - popfl # Restore caller passed flags + popf # Restore caller passed flags xorl %eax, %eax ret diff --git a/kernel/arch/x86/kernel/vm86_32.c b/kernel/arch/x86/kernel/vm86_32.c index fc9db6ef2..524619351 100644 --- a/kernel/arch/x86/kernel/vm86_32.c +++ b/kernel/arch/x86/kernel/vm86_32.c @@ -44,11 +44,15 @@ #include <linux/ptrace.h> #include <linux/audit.h> #include <linux/stddef.h> +#include <linux/slab.h> +#include <linux/security.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/tlbflush.h> #include <asm/irq.h> +#include <asm/traps.h> +#include <asm/vm86.h> /* * Known problems: @@ -66,10 +70,6 @@ */ -#define KVM86 ((struct kernel_vm86_struct *)regs) -#define VMPI KVM86->vm86plus - - /* * 8- and 16-bit register defines.. */ @@ -81,8 +81,8 @@ /* * virtual flags (16 and 32-bit versions) */ -#define VFLAGS (*(unsigned short *)&(current->thread.v86flags)) -#define VEFLAGS (current->thread.v86flags) +#define VFLAGS (*(unsigned short *)&(current->thread.vm86->veflags)) +#define VEFLAGS (current->thread.vm86->veflags) #define set_flags(X, new, mask) \ ((X) = ((X) & ~(mask)) | ((new) & (mask))) @@ -90,46 +90,13 @@ #define SAFE_MASK (0xDD5) #define RETURN_MASK (0xDFF) -/* convert kernel_vm86_regs to vm86_regs */ -static int copy_vm86_regs_to_user(struct vm86_regs __user *user, - const struct kernel_vm86_regs *regs) -{ - int ret = 0; - - /* - * kernel_vm86_regs is missing gs, so copy everything up to - * (but not including) orig_eax, and then rest including orig_eax. - */ - ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_ax)); - ret += copy_to_user(&user->orig_eax, ®s->pt.orig_ax, - sizeof(struct kernel_vm86_regs) - - offsetof(struct kernel_vm86_regs, pt.orig_ax)); - - return ret; -} - -/* convert vm86_regs to kernel_vm86_regs */ -static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs, - const struct vm86_regs __user *user, - unsigned extra) -{ - int ret = 0; - - /* copy ax-fs inclusive */ - ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.orig_ax)); - /* copy orig_ax-__gsh+extra */ - ret += copy_from_user(®s->pt.orig_ax, &user->orig_eax, - sizeof(struct kernel_vm86_regs) - - offsetof(struct kernel_vm86_regs, pt.orig_ax) + - extra); - return ret; -} - -struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) +void save_v86_state(struct kernel_vm86_regs *regs, int retval) { struct tss_struct *tss; - struct pt_regs *ret; - unsigned long tmp; + struct task_struct *tsk = current; + struct vm86plus_struct __user *user; + struct vm86 *vm86 = current->thread.vm86; + long err = 0; /* * This gets called from entry.S with interrupts disabled, but @@ -138,31 +105,57 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) */ local_irq_enable(); - if (!current->thread.vm86_info) { - pr_alert("no vm86_info: BAD\n"); + if (!vm86 || !vm86->user_vm86) { + pr_alert("no user_vm86: BAD\n"); + do_exit(SIGSEGV); + } + set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | vm86->veflags_mask); + user = vm86->user_vm86; + + if (!access_ok(VERIFY_WRITE, user, vm86->vm86plus.is_vm86pus ? + sizeof(struct vm86plus_struct) : + sizeof(struct vm86_struct))) { + pr_alert("could not access userspace vm86 info\n"); do_exit(SIGSEGV); } - set_flags(regs->pt.flags, VEFLAGS, X86_EFLAGS_VIF | current->thread.v86mask); - tmp = copy_vm86_regs_to_user(¤t->thread.vm86_info->regs, regs); - tmp += put_user(current->thread.screen_bitmap, ¤t->thread.vm86_info->screen_bitmap); - if (tmp) { - pr_alert("could not access userspace vm86_info\n"); + + put_user_try { + put_user_ex(regs->pt.bx, &user->regs.ebx); + put_user_ex(regs->pt.cx, &user->regs.ecx); + put_user_ex(regs->pt.dx, &user->regs.edx); + put_user_ex(regs->pt.si, &user->regs.esi); + put_user_ex(regs->pt.di, &user->regs.edi); + put_user_ex(regs->pt.bp, &user->regs.ebp); + put_user_ex(regs->pt.ax, &user->regs.eax); + put_user_ex(regs->pt.ip, &user->regs.eip); + put_user_ex(regs->pt.cs, &user->regs.cs); + put_user_ex(regs->pt.flags, &user->regs.eflags); + put_user_ex(regs->pt.sp, &user->regs.esp); + put_user_ex(regs->pt.ss, &user->regs.ss); + put_user_ex(regs->es, &user->regs.es); + put_user_ex(regs->ds, &user->regs.ds); + put_user_ex(regs->fs, &user->regs.fs); + put_user_ex(regs->gs, &user->regs.gs); + + put_user_ex(vm86->screen_bitmap, &user->screen_bitmap); + } put_user_catch(err); + if (err) { + pr_alert("could not access userspace vm86 info\n"); do_exit(SIGSEGV); } tss = &per_cpu(cpu_tss, get_cpu()); - current->thread.sp0 = current->thread.saved_sp0; - current->thread.sysenter_cs = __KERNEL_CS; - load_sp0(tss, ¤t->thread); - current->thread.saved_sp0 = 0; + tsk->thread.sp0 = vm86->saved_sp0; + tsk->thread.sysenter_cs = __KERNEL_CS; + load_sp0(tss, &tsk->thread); + vm86->saved_sp0 = 0; put_cpu(); - ret = KVM86->regs32; + memcpy(®s->pt, &vm86->regs32, sizeof(struct pt_regs)); - ret->fs = current->thread.saved_fs; - set_user_gs(ret, current->thread.saved_gs); + lazy_load_gs(vm86->regs32.gs); - return ret; + regs->pt.ax = retval; } static void mark_screen_rdonly(struct mm_struct *mm) @@ -200,45 +193,16 @@ out: static int do_vm86_irq_handling(int subfunction, int irqnumber); -static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk); +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus); -SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, v86) +SYSCALL_DEFINE1(vm86old, struct vm86_struct __user *, user_vm86) { - struct kernel_vm86_struct info; /* declare this _on top_, - * this avoids wasting of stack space. - * This remains on the stack until we - * return to 32 bit user space. - */ - struct task_struct *tsk = current; - int tmp; - - if (tsk->thread.saved_sp0) - return -EPERM; - tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, - offsetof(struct kernel_vm86_struct, vm86plus) - - sizeof(info.regs)); - if (tmp) - return -EFAULT; - memset(&info.vm86plus, 0, (int)&info.regs32 - (int)&info.vm86plus); - info.regs32 = current_pt_regs(); - tsk->thread.vm86_info = v86; - do_sys_vm86(&info, tsk); - return 0; /* we never return here */ + return do_sys_vm86((struct vm86plus_struct __user *) user_vm86, false); } SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) { - struct kernel_vm86_struct info; /* declare this _on top_, - * this avoids wasting of stack space. - * This remains on the stack until we - * return to 32 bit user space. - */ - struct task_struct *tsk; - int tmp; - struct vm86plus_struct __user *v86; - - tsk = current; switch (cmd) { case VM86_REQUEST_IRQ: case VM86_FREE_IRQ: @@ -256,114 +220,159 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg) } /* we come here only for functions VM86_ENTER, VM86_ENTER_NO_BYPASS */ - if (tsk->thread.saved_sp0) - return -EPERM; - v86 = (struct vm86plus_struct __user *)arg; - tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs, - offsetof(struct kernel_vm86_struct, regs32) - - sizeof(info.regs)); - if (tmp) - return -EFAULT; - info.regs32 = current_pt_regs(); - info.vm86plus.is_vm86pus = 1; - tsk->thread.vm86_info = (struct vm86_struct __user *)v86; - do_sys_vm86(&info, tsk); - return 0; /* we never return here */ + return do_sys_vm86((struct vm86plus_struct __user *) arg, true); } -static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk) +static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) { struct tss_struct *tss; -/* - * make sure the vm86() system call doesn't try to do anything silly - */ - info->regs.pt.ds = 0; - info->regs.pt.es = 0; - info->regs.pt.fs = 0; -#ifndef CONFIG_X86_32_LAZY_GS - info->regs.pt.gs = 0; -#endif + struct task_struct *tsk = current; + struct vm86 *vm86 = tsk->thread.vm86; + struct kernel_vm86_regs vm86regs; + struct pt_regs *regs = current_pt_regs(); + unsigned long err = 0; + + err = security_mmap_addr(0); + if (err) { + /* + * vm86 cannot virtualize the address space, so vm86 users + * need to manage the low 1MB themselves using mmap. Given + * that BIOS places important data in the first page, vm86 + * is essentially useless if mmap_min_addr != 0. DOSEMU, + * for example, won't even bother trying to use vm86 if it + * can't map a page at virtual address 0. + * + * To reduce the available kernel attack surface, simply + * disallow vm86(old) for users who cannot mmap at va 0. + * + * The implementation of security_mmap_addr will allow + * suitably privileged users to map va 0 even if + * vm.mmap_min_addr is set above 0, and we want this + * behavior for vm86 as well, as it ensures that legacy + * tools like vbetool will not fail just because of + * vm.mmap_min_addr. + */ + pr_info_once("Denied a call to vm86(old) from %s[%d] (uid: %d). Set the vm.mmap_min_addr sysctl to 0 and/or adjust LSM mmap_min_addr policy to enable vm86 if you are using a vm86-based DOS emulator.\n", + current->comm, task_pid_nr(current), + from_kuid_munged(&init_user_ns, current_uid())); + return -EPERM; + } + + if (!vm86) { + if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL))) + return -ENOMEM; + tsk->thread.vm86 = vm86; + } + if (vm86->saved_sp0) + return -EPERM; + + if (!access_ok(VERIFY_READ, user_vm86, plus ? + sizeof(struct vm86_struct) : + sizeof(struct vm86plus_struct))) + return -EFAULT; + + memset(&vm86regs, 0, sizeof(vm86regs)); + get_user_try { + unsigned short seg; + get_user_ex(vm86regs.pt.bx, &user_vm86->regs.ebx); + get_user_ex(vm86regs.pt.cx, &user_vm86->regs.ecx); + get_user_ex(vm86regs.pt.dx, &user_vm86->regs.edx); + get_user_ex(vm86regs.pt.si, &user_vm86->regs.esi); + get_user_ex(vm86regs.pt.di, &user_vm86->regs.edi); + get_user_ex(vm86regs.pt.bp, &user_vm86->regs.ebp); + get_user_ex(vm86regs.pt.ax, &user_vm86->regs.eax); + get_user_ex(vm86regs.pt.ip, &user_vm86->regs.eip); + get_user_ex(seg, &user_vm86->regs.cs); + vm86regs.pt.cs = seg; + get_user_ex(vm86regs.pt.flags, &user_vm86->regs.eflags); + get_user_ex(vm86regs.pt.sp, &user_vm86->regs.esp); + get_user_ex(seg, &user_vm86->regs.ss); + vm86regs.pt.ss = seg; + get_user_ex(vm86regs.es, &user_vm86->regs.es); + get_user_ex(vm86regs.ds, &user_vm86->regs.ds); + get_user_ex(vm86regs.fs, &user_vm86->regs.fs); + get_user_ex(vm86regs.gs, &user_vm86->regs.gs); + + get_user_ex(vm86->flags, &user_vm86->flags); + get_user_ex(vm86->screen_bitmap, &user_vm86->screen_bitmap); + get_user_ex(vm86->cpu_type, &user_vm86->cpu_type); + } get_user_catch(err); + if (err) + return err; + + if (copy_from_user(&vm86->int_revectored, + &user_vm86->int_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (copy_from_user(&vm86->int21_revectored, + &user_vm86->int21_revectored, + sizeof(struct revectored_struct))) + return -EFAULT; + if (plus) { + if (copy_from_user(&vm86->vm86plus, &user_vm86->vm86plus, + sizeof(struct vm86plus_info_struct))) + return -EFAULT; + vm86->vm86plus.is_vm86pus = 1; + } else + memset(&vm86->vm86plus, 0, + sizeof(struct vm86plus_info_struct)); + + memcpy(&vm86->regs32, regs, sizeof(struct pt_regs)); + vm86->user_vm86 = user_vm86; /* * The flags register is also special: we cannot trust that the user * has set it up safely, so this makes sure interrupt etc flags are * inherited from protected mode. */ - VEFLAGS = info->regs.pt.flags; - info->regs.pt.flags &= SAFE_MASK; - info->regs.pt.flags |= info->regs32->flags & ~SAFE_MASK; - info->regs.pt.flags |= X86_VM_MASK; + VEFLAGS = vm86regs.pt.flags; + vm86regs.pt.flags &= SAFE_MASK; + vm86regs.pt.flags |= regs->flags & ~SAFE_MASK; + vm86regs.pt.flags |= X86_VM_MASK; + + vm86regs.pt.orig_ax = regs->orig_ax; - switch (info->cpu_type) { + switch (vm86->cpu_type) { case CPU_286: - tsk->thread.v86mask = 0; + vm86->veflags_mask = 0; break; case CPU_386: - tsk->thread.v86mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; case CPU_486: - tsk->thread.v86mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; default: - tsk->thread.v86mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; + vm86->veflags_mask = X86_EFLAGS_ID | X86_EFLAGS_AC | X86_EFLAGS_NT | X86_EFLAGS_IOPL; break; } /* - * Save old state, set default return value (%ax) to 0 (VM86_SIGNAL) + * Save old state */ - info->regs32->ax = VM86_SIGNAL; - tsk->thread.saved_sp0 = tsk->thread.sp0; - tsk->thread.saved_fs = info->regs32->fs; - tsk->thread.saved_gs = get_user_gs(info->regs32); + vm86->saved_sp0 = tsk->thread.sp0; + lazy_save_gs(vm86->regs32.gs); tss = &per_cpu(cpu_tss, get_cpu()); - tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0; + /* make room for real-mode segments */ + tsk->thread.sp0 += 16; if (cpu_has_sep) tsk->thread.sysenter_cs = 0; load_sp0(tss, &tsk->thread); put_cpu(); - tsk->thread.screen_bitmap = info->screen_bitmap; - if (info->flags & VM86_SCREEN_BITMAP) + if (vm86->flags & VM86_SCREEN_BITMAP) mark_screen_rdonly(tsk->mm); - /*call __audit_syscall_exit since we do not exit via the normal paths */ -#ifdef CONFIG_AUDITSYSCALL - if (unlikely(current->audit_context)) - __audit_syscall_exit(1, 0); -#endif - - __asm__ __volatile__( - "movl %0,%%esp\n\t" - "movl %1,%%ebp\n\t" -#ifdef CONFIG_X86_32_LAZY_GS - "mov %2, %%gs\n\t" -#endif - "jmp resume_userspace" - : /* no outputs */ - :"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0)); - /* we never return here */ -} - -static inline void return_to_32bit(struct kernel_vm86_regs *regs16, int retval) -{ - struct pt_regs *regs32; - - regs32 = save_v86_state(regs16); - regs32->ax = retval; - __asm__ __volatile__("movl %0,%%esp\n\t" - "movl %1,%%ebp\n\t" - "jmp resume_userspace" - : : "r" (regs32), "r" (current_thread_info())); + memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); + force_iret(); + return regs->ax; } static inline void set_IF(struct kernel_vm86_regs *regs) { VEFLAGS |= X86_EFLAGS_VIF; - if (VEFLAGS & X86_EFLAGS_VIP) - return_to_32bit(regs, VM86_STI); } static inline void clear_IF(struct kernel_vm86_regs *regs) @@ -395,7 +404,7 @@ static inline void clear_AC(struct kernel_vm86_regs *regs) static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs *regs) { - set_flags(VEFLAGS, flags, current->thread.v86mask); + set_flags(VEFLAGS, flags, current->thread.vm86->veflags_mask); set_flags(regs->pt.flags, flags, SAFE_MASK); if (flags & X86_EFLAGS_IF) set_IF(regs); @@ -405,7 +414,7 @@ static inline void set_vflags_long(unsigned long flags, struct kernel_vm86_regs static inline void set_vflags_short(unsigned short flags, struct kernel_vm86_regs *regs) { - set_flags(VFLAGS, flags, current->thread.v86mask); + set_flags(VFLAGS, flags, current->thread.vm86->veflags_mask); set_flags(regs->pt.flags, flags, SAFE_MASK); if (flags & X86_EFLAGS_IF) set_IF(regs); @@ -420,7 +429,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs) if (VEFLAGS & X86_EFLAGS_VIF) flags |= X86_EFLAGS_IF; flags |= X86_EFLAGS_IOPL; - return flags | (VEFLAGS & current->thread.v86mask); + return flags | (VEFLAGS & current->thread.vm86->veflags_mask); } static inline int is_revectored(int nr, struct revectored_struct *bitmap) @@ -518,12 +527,13 @@ static void do_int(struct kernel_vm86_regs *regs, int i, { unsigned long __user *intr_ptr; unsigned long segoffs; + struct vm86 *vm86 = current->thread.vm86; if (regs->pt.cs == BIOSSEG) goto cannot_handle; - if (is_revectored(i, &KVM86->int_revectored)) + if (is_revectored(i, &vm86->int_revectored)) goto cannot_handle; - if (i == 0x21 && is_revectored(AH(regs), &KVM86->int21_revectored)) + if (i == 0x21 && is_revectored(AH(regs), &vm86->int21_revectored)) goto cannot_handle; intr_ptr = (unsigned long __user *) (i << 2); if (get_user(segoffs, intr_ptr)) @@ -542,18 +552,16 @@ static void do_int(struct kernel_vm86_regs *regs, int i, return; cannot_handle: - return_to_32bit(regs, VM86_INTx + (i << 8)); + save_v86_state(regs, VM86_INTx + (i << 8)); } int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno) { - if (VMPI.is_vm86pus) { + struct vm86 *vm86 = current->thread.vm86; + + if (vm86->vm86plus.is_vm86pus) { if ((trapno == 3) || (trapno == 1)) { - KVM86->regs32->ax = VM86_TRAP + (trapno << 8); - /* setting this flag forces the code in entry_32.S to - the path where we call save_v86_state() and change - the stack pointer to KVM86->regs32 */ - set_thread_flag(TIF_NOTIFY_RESUME); + save_v86_state(regs, VM86_TRAP + (trapno << 8)); return 0; } do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs)); @@ -574,16 +582,11 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) unsigned char __user *ssp; unsigned short ip, sp, orig_flags; int data32, pref_done; + struct vm86plus_info_struct *vmpi = ¤t->thread.vm86->vm86plus; #define CHECK_IF_IN_TRAP \ - if (VMPI.vm86dbg_active && VMPI.vm86dbg_TFpendig) \ + if (vmpi->vm86dbg_active && vmpi->vm86dbg_TFpendig) \ newflags |= X86_EFLAGS_TF -#define VM86_FAULT_RETURN do { \ - if (VMPI.force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) \ - return_to_32bit(regs, VM86_PICRETURN); \ - if (orig_flags & X86_EFLAGS_TF) \ - handle_vm86_trap(regs, 0, 1); \ - return; } while (0) orig_flags = *(unsigned short *)®s->pt.flags; @@ -622,7 +625,7 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) SP(regs) -= 2; } IP(regs) = ip; - VM86_FAULT_RETURN; + goto vm86_fault_return; /* popf */ case 0x9d: @@ -642,16 +645,18 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) else set_vflags_short(newflags, regs); - VM86_FAULT_RETURN; + goto check_vip; } /* int xx */ case 0xcd: { int intno = popb(csp, ip, simulate_sigsegv); IP(regs) = ip; - if (VMPI.vm86dbg_active) { - if ((1 << (intno & 7)) & VMPI.vm86dbg_intxxtab[intno >> 3]) - return_to_32bit(regs, VM86_INTx + (intno << 8)); + if (vmpi->vm86dbg_active) { + if ((1 << (intno & 7)) & vmpi->vm86dbg_intxxtab[intno >> 3]) { + save_v86_state(regs, VM86_INTx + (intno << 8)); + return; + } } do_int(regs, intno, ssp, sp); return; @@ -682,14 +687,14 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) } else { set_vflags_short(newflags, regs); } - VM86_FAULT_RETURN; + goto check_vip; } /* cli */ case 0xfa: IP(regs) = ip; clear_IF(regs); - VM86_FAULT_RETURN; + goto vm86_fault_return; /* sti */ /* @@ -701,14 +706,29 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code) case 0xfb: IP(regs) = ip; set_IF(regs); - VM86_FAULT_RETURN; + goto check_vip; default: - return_to_32bit(regs, VM86_UNKNOWN); + save_v86_state(regs, VM86_UNKNOWN); } return; +check_vip: + if (VEFLAGS & X86_EFLAGS_VIP) { + save_v86_state(regs, VM86_STI); + return; + } + +vm86_fault_return: + if (vmpi->force_return_for_pic && (VEFLAGS & (X86_EFLAGS_IF | X86_EFLAGS_VIF))) { + save_v86_state(regs, VM86_PICRETURN); + return; + } + if (orig_flags & X86_EFLAGS_TF) + handle_vm86_trap(regs, 0, X86_TRAP_DB); + return; + simulate_sigsegv: /* FIXME: After a long discussion with Stas we finally * agreed, that this is wrong. Here we should @@ -720,7 +740,7 @@ simulate_sigsegv: * should be a mixture of the two, but how do we * get the information? [KD] */ - return_to_32bit(regs, VM86_UNKNOWN); + save_v86_state(regs, VM86_UNKNOWN); } /* ---------------- vm86 special IRQ passing stuff ----------------- */ diff --git a/kernel/arch/x86/kernel/vmlinux.lds.S b/kernel/arch/x86/kernel/vmlinux.lds.S index 00bf300fd..74e4bf11f 100644 --- a/kernel/arch/x86/kernel/vmlinux.lds.S +++ b/kernel/arch/x86/kernel/vmlinux.lds.S @@ -364,7 +364,7 @@ INIT_PER_CPU(irq_stack_union); #endif /* CONFIG_X86_32 */ -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include <asm/kexec.h> . = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, diff --git a/kernel/arch/x86/kernel/vsmp_64.c b/kernel/arch/x86/kernel/vsmp_64.c index ee22c1d93..b034b1b14 100644 --- a/kernel/arch/x86/kernel/vsmp_64.c +++ b/kernel/arch/x86/kernel/vsmp_64.c @@ -72,7 +72,7 @@ asmlinkage __visible void vsmp_irq_enable(void) } PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); -static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf, +static unsigned __init vsmp_patch(u8 type, u16 clobbers, void *ibuf, unsigned long addr, unsigned len) { switch (type) { diff --git a/kernel/arch/x86/kernel/x8664_ksyms_64.c b/kernel/arch/x86/kernel/x8664_ksyms_64.c index 37d8fa443..a0695be19 100644 --- a/kernel/arch/x86/kernel/x8664_ksyms_64.c +++ b/kernel/arch/x86/kernel/x8664_ksyms_64.c @@ -75,7 +75,5 @@ EXPORT_SYMBOL(native_load_gs_index); #ifdef CONFIG_PREEMPT EXPORT_SYMBOL(___preempt_schedule); -#ifdef CONFIG_CONTEXT_TRACKING -EXPORT_SYMBOL(___preempt_schedule_context); -#endif +EXPORT_SYMBOL(___preempt_schedule_notrace); #endif diff --git a/kernel/arch/x86/kernel/x86_init.c b/kernel/arch/x86/kernel/x86_init.c index 234b0722d..3839628d9 100644 --- a/kernel/arch/x86/kernel/x86_init.c +++ b/kernel/arch/x86/kernel/x86_init.c @@ -11,7 +11,6 @@ #include <asm/bios_ebda.h> #include <asm/paravirt.h> #include <asm/pci_x86.h> -#include <asm/pci.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> @@ -111,11 +110,9 @@ EXPORT_SYMBOL_GPL(x86_platform); #if defined(CONFIG_PCI_MSI) struct x86_msi_ops x86_msi = { .setup_msi_irqs = native_setup_msi_irqs, - .compose_msi_msg = native_compose_msi_msg, .teardown_msi_irq = native_teardown_msi_irq, .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, - .setup_hpet_msi = default_setup_hpet_msi, }; /* MSI arch specific hooks */ @@ -141,13 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev) #endif struct x86_io_apic_ops x86_io_apic_ops = { - .init = native_io_apic_init_mappings, .read = native_io_apic_read, - .write = native_io_apic_write, - .modify = native_io_apic_modify, .disable = native_disable_io_apic, - .print_entries = native_io_apic_print_entries, - .set_affinity = native_ioapic_set_affinity, - .setup_entry = native_setup_ioapic_entry, - .eoi_ioapic_pin = native_eoi_ioapic_pin, }; diff --git a/kernel/arch/x86/kernel/xsave.c b/kernel/arch/x86/kernel/xsave.c deleted file mode 100644 index 87a815b85..000000000 --- a/kernel/arch/x86/kernel/xsave.c +++ /dev/null @@ -1,724 +0,0 @@ -/* - * xsave/xrstor support. - * - * Author: Suresh Siddha <suresh.b.siddha@intel.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/bootmem.h> -#include <linux/compat.h> -#include <linux/cpu.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> -#include <asm/sigframe.h> -#include <asm/tlbflush.h> -#include <asm/xcr.h> - -/* - * Supported feature mask by the CPU and the kernel. - */ -u64 pcntxt_mask; - -/* - * Represents init state for the supported extended state. - */ -struct xsave_struct *init_xstate_buf; - -static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32; -static unsigned int *xstate_offsets, *xstate_sizes; -static unsigned int xstate_comp_offsets[sizeof(pcntxt_mask)*8]; -static unsigned int xstate_features; - -/* - * If a processor implementation discern that a processor state component is - * in its initialized state it may modify the corresponding bit in the - * xsave_hdr.xstate_bv as '0', with out modifying the corresponding memory - * layout in the case of xsaveopt. While presenting the xstate information to - * the user, we always ensure that the memory layout of a feature will be in - * the init state if the corresponding header bit is zero. This is to ensure - * that the user doesn't see some stale state in the memory layout during - * signal handling, debugging etc. - */ -void __sanitize_i387_state(struct task_struct *tsk) -{ - struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave; - int feature_bit = 0x2; - u64 xstate_bv; - - if (!fx) - return; - - xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv; - - /* - * None of the feature bits are in init state. So nothing else - * to do for us, as the memory layout is up to date. - */ - if ((xstate_bv & pcntxt_mask) == pcntxt_mask) - return; - - /* - * FP is in init state - */ - if (!(xstate_bv & XSTATE_FP)) { - fx->cwd = 0x37f; - fx->swd = 0; - fx->twd = 0; - fx->fop = 0; - fx->rip = 0; - fx->rdp = 0; - memset(&fx->st_space[0], 0, 128); - } - - /* - * SSE is in init state - */ - if (!(xstate_bv & XSTATE_SSE)) - memset(&fx->xmm_space[0], 0, 256); - - xstate_bv = (pcntxt_mask & ~xstate_bv) >> 2; - - /* - * Update all the other memory layouts for which the corresponding - * header bit is in the init state. - */ - while (xstate_bv) { - if (xstate_bv & 0x1) { - int offset = xstate_offsets[feature_bit]; - int size = xstate_sizes[feature_bit]; - - memcpy(((void *) fx) + offset, - ((void *) init_xstate_buf) + offset, - size); - } - - xstate_bv >>= 1; - feature_bit++; - } -} - -/* - * Check for the presence of extended state information in the - * user fpstate pointer in the sigcontext. - */ -static inline int check_for_xstate(struct i387_fxsave_struct __user *buf, - void __user *fpstate, - struct _fpx_sw_bytes *fx_sw) -{ - int min_xstate_size = sizeof(struct i387_fxsave_struct) + - sizeof(struct xsave_hdr_struct); - unsigned int magic2; - - if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw))) - return -1; - - /* Check for the first magic field and other error scenarios. */ - if (fx_sw->magic1 != FP_XSTATE_MAGIC1 || - fx_sw->xstate_size < min_xstate_size || - fx_sw->xstate_size > xstate_size || - fx_sw->xstate_size > fx_sw->extended_size) - return -1; - - /* - * Check for the presence of second magic word at the end of memory - * layout. This detects the case where the user just copied the legacy - * fpstate layout with out copying the extended state information - * in the memory layout. - */ - if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size)) - || magic2 != FP_XSTATE_MAGIC2) - return -1; - - return 0; -} - -/* - * Signal frame handlers. - */ -static inline int save_fsave_header(struct task_struct *tsk, void __user *buf) -{ - if (use_fxsr()) { - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct user_i387_ia32_struct env; - struct _fpstate_ia32 __user *fp = buf; - - convert_from_fxsr(&env, tsk); - - if (__copy_to_user(buf, &env, sizeof(env)) || - __put_user(xsave->i387.swd, &fp->status) || - __put_user(X86_FXSR_MAGIC, &fp->magic)) - return -1; - } else { - struct i387_fsave_struct __user *fp = buf; - u32 swd; - if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status)) - return -1; - } - - return 0; -} - -static inline int save_xstate_epilog(void __user *buf, int ia32_frame) -{ - struct xsave_struct __user *x = buf; - struct _fpx_sw_bytes *sw_bytes; - u32 xstate_bv; - int err; - - /* Setup the bytes not touched by the [f]xsave and reserved for SW. */ - sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved; - err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes)); - - if (!use_xsave()) - return err; - - err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size)); - - /* - * Read the xstate_bv which we copied (directly from the cpu or - * from the state in task struct) to the user buffers. - */ - err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - /* - * For legacy compatible, we always set FP/SSE bits in the bit - * vector while saving the state to the user context. This will - * enable us capturing any changes(during sigreturn) to - * the FP/SSE bits by the legacy applications which don't touch - * xstate_bv in the xsave header. - * - * xsave aware apps can change the xstate_bv in the xsave - * header as well as change any contents in the memory layout. - * xrestore as part of sigreturn will capture all the changes. - */ - xstate_bv |= XSTATE_FPSSE; - - err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv); - - return err; -} - -static inline int save_user_xstate(struct xsave_struct __user *buf) -{ - int err; - - if (use_xsave()) - err = xsave_user(buf); - else if (use_fxsr()) - err = fxsave_user((struct i387_fxsave_struct __user *) buf); - else - err = fsave_user((struct i387_fsave_struct __user *) buf); - - if (unlikely(err) && __clear_user(buf, xstate_size)) - err = -EFAULT; - return err; -} - -/* - * Save the fpu, extended register state to the user signal frame. - * - * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save - * state is copied. - * 'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'. - * - * buf == buf_fx for 64-bit frames and 32-bit fsave frame. - * buf != buf_fx for 32-bit frames with fxstate. - * - * If the fpu, extended register state is live, save the state directly - * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise, - * copy the thread's fpu state to the user frame starting at 'buf_fx'. - * - * If this is a 32-bit frame with fxstate, put a fsave header before - * the aligned state at 'buf_fx'. - * - * For [f]xsave state, update the SW reserved fields in the [f]xsave frame - * indicating the absence/presence of the extended state to the user. - */ -int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - struct xsave_struct *xsave = ¤t->thread.fpu.state->xsave; - struct task_struct *tsk = current; - int ia32_fxstate = (buf != buf_fx); - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!access_ok(VERIFY_WRITE, buf, size)) - return -EACCES; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_get(current, NULL, 0, - sizeof(struct user_i387_ia32_struct), NULL, - (struct _fpstate_ia32 __user *) buf) ? -1 : 1; - - if (user_has_fpu()) { - /* Save the live register state to the user directly. */ - if (save_user_xstate(buf_fx)) - return -1; - /* Update the thread's fxstate to save the fsave header. */ - if (ia32_fxstate) - fpu_fxsave(&tsk->thread.fpu); - } else { - sanitize_i387_state(tsk); - if (__copy_to_user(buf_fx, xsave, xstate_size)) - return -1; - } - - /* Save the fsave header for the 32-bit frames. */ - if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf)) - return -1; - - if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) - return -1; - - return 0; -} - -static inline void -sanitize_restored_xstate(struct task_struct *tsk, - struct user_i387_ia32_struct *ia32_env, - u64 xstate_bv, int fx_only) -{ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; - struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr; - - if (use_xsave()) { - /* These bits must be zero. */ - memset(xsave_hdr->reserved, 0, 48); - - /* - * Init the state that is not present in the memory - * layout and not enabled by the OS. - */ - if (fx_only) - xsave_hdr->xstate_bv = XSTATE_FPSSE; - else - xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv); - } - - if (use_fxsr()) { - /* - * mscsr reserved bits must be masked to zero for security - * reasons. - */ - xsave->i387.mxcsr &= mxcsr_feature_mask; - - convert_to_fxsr(tsk, ia32_env); - } -} - -/* - * Restore the extended state if present. Otherwise, restore the FP/SSE state. - */ -static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only) -{ - if (use_xsave()) { - if ((unsigned long)buf % 64 || fx_only) { - u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE; - xrstor_state(init_xstate_buf, init_bv); - return fxrstor_user(buf); - } else { - u64 init_bv = pcntxt_mask & ~xbv; - if (unlikely(init_bv)) - xrstor_state(init_xstate_buf, init_bv); - return xrestore_user(buf, xbv); - } - } else if (use_fxsr()) { - return fxrstor_user(buf); - } else - return frstor_user(buf); -} - -int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) -{ - int ia32_fxstate = (buf != buf_fx); - struct task_struct *tsk = current; - int state_size = xstate_size; - u64 xstate_bv = 0; - int fx_only = 0; - - ia32_fxstate &= (config_enabled(CONFIG_X86_32) || - config_enabled(CONFIG_IA32_EMULATION)); - - if (!buf) { - fpu_reset_state(tsk); - return 0; - } - - if (!access_ok(VERIFY_READ, buf, size)) - return -EACCES; - - if (!used_math() && init_fpu(tsk)) - return -1; - - if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; - - if (use_xsave()) { - struct _fpx_sw_bytes fx_sw_user; - if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) { - /* - * Couldn't find the extended state information in the - * memory layout. Restore just the FP/SSE and init all - * the other extended state. - */ - state_size = sizeof(struct i387_fxsave_struct); - fx_only = 1; - } else { - state_size = fx_sw_user.xstate_size; - xstate_bv = fx_sw_user.xstate_bv; - } - } - - if (ia32_fxstate) { - /* - * For 32-bit frames with fxstate, copy the user state to the - * thread's fpu state, reconstruct fxstate from the fsave - * header. Sanitize the copied state etc. - */ - struct fpu *fpu = &tsk->thread.fpu; - struct user_i387_ia32_struct env; - int err = 0; - - /* - * Drop the current fpu which clears used_math(). This ensures - * that any context-switch during the copy of the new state, - * avoids the intermediate state from getting restored/saved. - * Thus avoiding the new restored state from getting corrupted. - * We will be ready to restore/save the state only after - * set_used_math() is again set. - */ - drop_fpu(tsk); - - if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || - __copy_from_user(&env, buf, sizeof(env))) { - fpu_finit(fpu); - err = -1; - } else { - sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - } - - set_used_math(); - if (use_eager_fpu()) { - preempt_disable(); - math_state_restore(); - preempt_enable(); - } - - return err; - } else { - /* - * For 64-bit frames and 32-bit fsave frames, restore the user - * state to the registers directly (with exceptions handled). - */ - user_fpu_begin(); - if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { - fpu_reset_state(tsk); - return -1; - } - } - - return 0; -} - -/* - * Prepare the SW reserved portion of the fxsave memory layout, indicating - * the presence of the extended state information in the memory layout - * pointed by the fpstate pointer in the sigcontext. - * This will be saved when ever the FP and extended state context is - * saved on the user stack during the signal handler delivery to the user. - */ -static void prepare_fx_sw_frame(void) -{ - int fsave_header_size = sizeof(struct i387_fsave_struct); - int size = xstate_size + FP_XSTATE_MAGIC2_SIZE; - - if (config_enabled(CONFIG_X86_32)) - size += fsave_header_size; - - fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; - fx_sw_reserved.extended_size = size; - fx_sw_reserved.xstate_bv = pcntxt_mask; - fx_sw_reserved.xstate_size = xstate_size; - - if (config_enabled(CONFIG_IA32_EMULATION)) { - fx_sw_reserved_ia32 = fx_sw_reserved; - fx_sw_reserved_ia32.extended_size += fsave_header_size; - } -} - -/* - * Enable the extended processor state save/restore feature - */ -static inline void xstate_enable(void) -{ - cr4_set_bits(X86_CR4_OSXSAVE); - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); -} - -/* - * Record the offsets and sizes of different state managed by the xsave - * memory layout. - */ -static void __init setup_xstate_features(void) -{ - int eax, ebx, ecx, edx, leaf = 0x2; - - xstate_features = fls64(pcntxt_mask); - xstate_offsets = alloc_bootmem(xstate_features * sizeof(int)); - xstate_sizes = alloc_bootmem(xstate_features * sizeof(int)); - - do { - cpuid_count(XSTATE_CPUID, leaf, &eax, &ebx, &ecx, &edx); - - if (eax == 0) - break; - - xstate_offsets[leaf] = ebx; - xstate_sizes[leaf] = eax; - - leaf++; - } while (1); -} - -/* - * This function sets up offsets and sizes of all extended states in - * xsave area. This supports both standard format and compacted format - * of the xsave aread. - * - * Input: void - * Output: void - */ -void setup_xstate_comp(void) -{ - unsigned int xstate_comp_sizes[sizeof(pcntxt_mask)*8]; - int i; - - /* - * The FP xstates and SSE xstates are legacy states. They are always - * in the fixed offsets in the xsave area in either compacted form - * or standard form. - */ - xstate_comp_offsets[0] = 0; - xstate_comp_offsets[1] = offsetof(struct i387_fxsave_struct, xmm_space); - - if (!cpu_has_xsaves) { - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - xstate_comp_offsets[i] = xstate_offsets[i]; - xstate_comp_sizes[i] = xstate_sizes[i]; - } - } - return; - } - - xstate_comp_offsets[2] = FXSAVE_SIZE + XSAVE_HDR_SIZE; - - for (i = 2; i < xstate_features; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) - xstate_comp_sizes[i] = xstate_sizes[i]; - else - xstate_comp_sizes[i] = 0; - - if (i > 2) - xstate_comp_offsets[i] = xstate_comp_offsets[i-1] - + xstate_comp_sizes[i-1]; - - } -} - -/* - * setup the xstate image representing the init state - */ -static void __init setup_init_fpu_buf(void) -{ - /* - * Setup init_xstate_buf to represent the init state of - * all the features managed by the xsave - */ - init_xstate_buf = alloc_bootmem_align(xstate_size, - __alignof__(struct xsave_struct)); - fx_finit(&init_xstate_buf->i387); - - if (!cpu_has_xsave) - return; - - setup_xstate_features(); - - if (cpu_has_xsaves) { - init_xstate_buf->xsave_hdr.xcomp_bv = - (u64)1 << 63 | pcntxt_mask; - init_xstate_buf->xsave_hdr.xstate_bv = pcntxt_mask; - } - - /* - * Init all the features state with header_bv being 0x0 - */ - xrstor_state_booting(init_xstate_buf, -1); - /* - * Dump the init state again. This is to identify the init state - * of any feature which is not represented by all zero's. - */ - xsave_state_booting(init_xstate_buf, -1); -} - -static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO; -static int __init eager_fpu_setup(char *s) -{ - if (!strcmp(s, "on")) - eagerfpu = ENABLE; - else if (!strcmp(s, "off")) - eagerfpu = DISABLE; - else if (!strcmp(s, "auto")) - eagerfpu = AUTO; - return 1; -} -__setup("eagerfpu=", eager_fpu_setup); - - -/* - * Calculate total size of enabled xstates in XCR0/pcntxt_mask. - */ -static void __init init_xstate_size(void) -{ - unsigned int eax, ebx, ecx, edx; - int i; - - if (!cpu_has_xsaves) { - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xstate_size = ebx; - return; - } - - xstate_size = FXSAVE_SIZE + XSAVE_HDR_SIZE; - for (i = 2; i < 64; i++) { - if (test_bit(i, (unsigned long *)&pcntxt_mask)) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); - xstate_size += eax; - } - } -} - -/* - * Enable and initialize the xsave feature. - */ -static void __init xstate_enable_boot_cpu(void) -{ - unsigned int eax, ebx, ecx, edx; - - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN(1, KERN_ERR "XSTATE_CPUID missing\n"); - return; - } - - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - pcntxt_mask = eax + ((u64)edx << 32); - - if ((pcntxt_mask & XSTATE_FPSSE) != XSTATE_FPSSE) { - pr_err("FP/SSE not shown under xsave features 0x%llx\n", - pcntxt_mask); - BUG(); - } - - /* - * Support only the state known to OS. - */ - pcntxt_mask = pcntxt_mask & XCNTXT_MASK; - - xstate_enable(); - - /* - * Recompute the context size for enabled features - */ - init_xstate_size(); - - update_regset_xstate_info(xstate_size, pcntxt_mask); - prepare_fx_sw_frame(); - setup_init_fpu_buf(); - - /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) - eagerfpu = ENABLE; - - if (pcntxt_mask & XSTATE_EAGER) { - if (eagerfpu == DISABLE) { - pr_err("eagerfpu not present, disabling some xstate features: 0x%llx\n", - pcntxt_mask & XSTATE_EAGER); - pcntxt_mask &= ~XSTATE_EAGER; - } else { - eagerfpu = ENABLE; - } - } - - pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x using %s\n", - pcntxt_mask, xstate_size, - cpu_has_xsaves ? "compacted form" : "standard form"); -} - -/* - * For the very first instance, this calls xstate_enable_boot_cpu(); - * for all subsequent instances, this calls xstate_enable(). - * - * This is somewhat obfuscated due to the lack of powerful enough - * overrides for the section checks. - */ -void xsave_init(void) -{ - static __refdata void (*next_func)(void) = xstate_enable_boot_cpu; - void (*this_func)(void); - - if (!cpu_has_xsave) - return; - - this_func = next_func; - next_func = xstate_enable; - this_func(); -} - -/* - * setup_init_fpu_buf() is __init and it is OK to call it here because - * init_xstate_buf will be unset only once during boot. - */ -void __init_refok eager_fpu_init(void) -{ - WARN_ON(used_math()); - current_thread_info()->status = 0; - - if (eagerfpu == ENABLE) - setup_force_cpu_cap(X86_FEATURE_EAGER_FPU); - - if (!cpu_has_eager_fpu) { - stts(); - return; - } - - if (!init_xstate_buf) - setup_init_fpu_buf(); -} - -/* - * Given the xsave area and a state inside, this function returns the - * address of the state. - * - * This is the API that is called to get xstate address in either - * standard format or compacted format of xsave area. - * - * Inputs: - * xsave: base address of the xsave area; - * xstate: state which is defined in xsave.h (e.g. XSTATE_FP, XSTATE_SSE, - * etc.) - * Output: - * address of the state in the xsave area. - */ -void *get_xsave_addr(struct xsave_struct *xsave, int xstate) -{ - int feature = fls64(xstate) - 1; - if (!test_bit(feature, (unsigned long *)&pcntxt_mask)) - return NULL; - - return (void *)xsave + xstate_comp_offsets[feature]; -} -EXPORT_SYMBOL_GPL(get_xsave_addr); diff --git a/kernel/arch/x86/kvm/Kconfig b/kernel/arch/x86/kvm/Kconfig index 413a7bf9e..639a6e345 100644 --- a/kernel/arch/x86/kvm/Kconfig +++ b/kernel/arch/x86/kvm/Kconfig @@ -28,6 +28,8 @@ config KVM select ANON_INODES select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + select IRQ_BYPASS_MANAGER + select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE @@ -86,15 +88,16 @@ config KVM_MMU_AUDIT auditing of KVM MMU events at runtime. config KVM_DEVICE_ASSIGNMENT - bool "KVM legacy PCI device assignment support" + bool "KVM legacy PCI device assignment support (DEPRECATED)" depends on KVM && PCI && IOMMU_API - default y + default n ---help--- Provide support for legacy PCI device assignment through KVM. The kernel now also supports a full featured userspace device driver - framework through VFIO, which supersedes much of this support. + framework through VFIO, which supersedes this support and provides + better security. - If unsure, say Y. + If unsure, say N. # OK, it's a little counter-intuitive to do this, but it puts it neatly under # the virtualization menu. diff --git a/kernel/arch/x86/kvm/Makefile b/kernel/arch/x86/kvm/Makefile index 16e8f962e..a1ff508bb 100644 --- a/kernel/arch/x86/kvm/Makefile +++ b/kernel/arch/x86/kvm/Makefile @@ -12,10 +12,12 @@ kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o ioapic.o irq_comm.o cpuid.o pmu.o + i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ + hyperv.o + kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o -kvm-intel-y += vmx.o -kvm-amd-y += svm.o +kvm-intel-y += vmx.o pmu_intel.o +kvm-amd-y += svm.o pmu_amd.o obj-$(CONFIG_KVM) += kvm.o obj-$(CONFIG_KVM_INTEL) += kvm-intel.o diff --git a/kernel/arch/x86/kvm/assigned-dev.c b/kernel/arch/x86/kvm/assigned-dev.c index d090ecf08..9dc091acd 100644 --- a/kernel/arch/x86/kvm/assigned-dev.c +++ b/kernel/arch/x86/kvm/assigned-dev.c @@ -21,6 +21,7 @@ #include <linux/fs.h> #include "irq.h" #include "assigned-dev.h" +#include "trace/events/kvm.h" struct kvm_assigned_dev_kernel { struct kvm_irq_ack_notifier ack_notifier; @@ -131,7 +132,42 @@ static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id) return IRQ_HANDLED; } -#ifdef __KVM_HAVE_MSI +/* + * Deliver an IRQ in an atomic context if we can, or return a failure, + * user can retry in a process context. + * Return value: + * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context. + * Other values - No need to retry. + */ +static int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, + int level) +{ + struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; + struct kvm_kernel_irq_routing_entry *e; + int ret = -EINVAL; + int idx; + + trace_kvm_set_irq(irq, level, irq_source_id); + + /* + * Injection into either PIC or IOAPIC might need to scan all CPUs, + * which would need to be retried from thread context; when same GSI + * is connected to both PIC and IOAPIC, we'd have to report a + * partial failure here. + * Since there's no easy way to do this, we only support injecting MSI + * which is limited to 1:1 GSI mapping. + */ + idx = srcu_read_lock(&kvm->irq_srcu); + if (kvm_irq_map_gsi(kvm, entries, irq) > 0) { + e = &entries[0]; + ret = kvm_arch_set_irq_inatomic(e, kvm, irq_source_id, + irq, level); + } + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + + static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id) { struct kvm_assigned_dev_kernel *assigned_dev = dev_id; @@ -150,9 +186,7 @@ static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id) return IRQ_HANDLED; } -#endif -#ifdef __KVM_HAVE_MSIX static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id) { struct kvm_assigned_dev_kernel *assigned_dev = dev_id; @@ -183,7 +217,6 @@ static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id) return IRQ_HANDLED; } -#endif /* Ack the irq line for an assigned device */ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian) @@ -386,7 +419,6 @@ static int assigned_device_enable_host_intx(struct kvm *kvm, return 0; } -#ifdef __KVM_HAVE_MSI static int assigned_device_enable_host_msi(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { @@ -408,9 +440,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm, return 0; } -#endif -#ifdef __KVM_HAVE_MSIX static int assigned_device_enable_host_msix(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev) { @@ -443,8 +473,6 @@ err: return r; } -#endif - static int assigned_device_enable_guest_intx(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, struct kvm_assigned_irq *irq) @@ -454,7 +482,6 @@ static int assigned_device_enable_guest_intx(struct kvm *kvm, return 0; } -#ifdef __KVM_HAVE_MSI static int assigned_device_enable_guest_msi(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, struct kvm_assigned_irq *irq) @@ -463,9 +490,7 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm, dev->ack_notifier.gsi = -1; return 0; } -#endif -#ifdef __KVM_HAVE_MSIX static int assigned_device_enable_guest_msix(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, struct kvm_assigned_irq *irq) @@ -474,7 +499,6 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm, dev->ack_notifier.gsi = -1; return 0; } -#endif static int assign_host_irq(struct kvm *kvm, struct kvm_assigned_dev_kernel *dev, @@ -492,16 +516,12 @@ static int assign_host_irq(struct kvm *kvm, case KVM_DEV_IRQ_HOST_INTX: r = assigned_device_enable_host_intx(kvm, dev); break; -#ifdef __KVM_HAVE_MSI case KVM_DEV_IRQ_HOST_MSI: r = assigned_device_enable_host_msi(kvm, dev); break; -#endif -#ifdef __KVM_HAVE_MSIX case KVM_DEV_IRQ_HOST_MSIX: r = assigned_device_enable_host_msix(kvm, dev); break; -#endif default: r = -EINVAL; } @@ -534,16 +554,12 @@ static int assign_guest_irq(struct kvm *kvm, case KVM_DEV_IRQ_GUEST_INTX: r = assigned_device_enable_guest_intx(kvm, dev, irq); break; -#ifdef __KVM_HAVE_MSI case KVM_DEV_IRQ_GUEST_MSI: r = assigned_device_enable_guest_msi(kvm, dev, irq); break; -#endif -#ifdef __KVM_HAVE_MSIX case KVM_DEV_IRQ_GUEST_MSIX: r = assigned_device_enable_guest_msix(kvm, dev, irq); break; -#endif default: r = -EINVAL; } @@ -826,7 +842,6 @@ out: } -#ifdef __KVM_HAVE_MSIX static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm, struct kvm_assigned_msix_nr *entry_nr) { @@ -906,7 +921,6 @@ msix_entry_out: return r; } -#endif static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm, struct kvm_assigned_pci_dev *assigned_dev) @@ -1012,7 +1026,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#ifdef __KVM_HAVE_MSIX case KVM_ASSIGN_SET_MSIX_NR: { struct kvm_assigned_msix_nr entry_nr; r = -EFAULT; @@ -1033,7 +1046,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl, goto out; break; } -#endif case KVM_ASSIGN_SET_INTX_MASK: { struct kvm_assigned_pci_dev assigned_dev; diff --git a/kernel/arch/x86/kvm/cpuid.c b/kernel/arch/x86/kvm/cpuid.c index 1d08ad358..6525e926f 100644 --- a/kernel/arch/x86/kvm/cpuid.c +++ b/kernel/arch/x86/kvm/cpuid.c @@ -16,21 +16,21 @@ #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> -#include <asm/i387.h> /* For use_eager_fpu. Ugh! */ -#include <asm/fpu-internal.h> /* For use_eager_fpu. Ugh! */ +#include <asm/fpu/internal.h> /* For use_eager_fpu. Ugh! */ #include <asm/user.h> -#include <asm/xsave.h> +#include <asm/fpu/xstate.h> #include "cpuid.h" #include "lapic.h" #include "mmu.h" #include "trace.h" +#include "pmu.h" static u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; - xstate_bv &= XSTATE_EXTEND_MASK; + xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { u32 eax, ebx, ecx, edx, offset; @@ -51,7 +51,7 @@ u64 kvm_supported_xcr0(void) u64 xcr0 = KVM_SUPPORTED_XCR0 & host_xcr0; if (!kvm_x86_ops->mpx_supported()) - xcr0 &= ~(XSTATE_BNDREGS | XSTATE_BNDCSR); + xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); return xcr0; } @@ -97,7 +97,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) if (best && (best->eax & (F(XSAVES) | F(XSAVEC)))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - vcpu->arch.eager_fpu = guest_cpuid_has_mpx(vcpu); + vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu); + if (vcpu->arch.eager_fpu) + kvm_x86_ops->fpu_activate(vcpu); /* * The existing code assumes virtual address is 48-bit in the canonical @@ -111,7 +113,7 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) /* Update physical-address width */ vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - kvm_pmu_cpuid_update(vcpu); + kvm_pmu_refresh(vcpu); return 0; } @@ -346,7 +348,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) | - F(AVX512CD); + F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(PCOMMIT); /* cpuid 0xD.1.eax */ const u32 kvm_supported_word10_x86_features = @@ -415,6 +417,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } + case 6: /* Thermal management */ + entry->eax = 0x4; /* allow ARAT */ + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; case 7: { entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; /* Mask ebx against host capability word 9 */ @@ -591,7 +599,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, break; case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ - case 6: /* Thermal management */ case 0xC0000002: case 0xC0000003: case 0xC0000004: diff --git a/kernel/arch/x86/kvm/cpuid.h b/kernel/arch/x86/kvm/cpuid.h index 496b3695d..3f5c48ddb 100644 --- a/kernel/arch/x86/kvm/cpuid.h +++ b/kernel/arch/x86/kvm/cpuid.h @@ -38,6 +38,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_XSAVE)); } +static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->edx & bit(X86_FEATURE_MTRR)); +} + static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -70,6 +78,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); } +static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_LM)); +} + static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -125,4 +141,41 @@ static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) best = kvm_find_cpuid_entry(vcpu, 7, 0); return best && (best->ebx & bit(X86_FEATURE_MPX)); } + +static inline bool guest_cpuid_has_pcommit(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_PCOMMIT)); +} + +static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_RDTSCP)); +} + +/* + * NRIPS is provided through cpuidfn 0x8000000a.edx bit 3 + */ +#define BIT_NRIPS 3 + +static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x8000000a, 0); + + /* + * NRIPS is a scattered cpuid feature, so we can't use + * X86_FEATURE_NRIPS here (X86_FEATURE_NRIPS would be bit + * position 8, not 3). + */ + return best && (best->edx & bit(BIT_NRIPS)); +} +#undef BIT_NRIPS + #endif diff --git a/kernel/arch/x86/kvm/emulate.c b/kernel/arch/x86/kvm/emulate.c index 630bcb0d7..b9b09fec1 100644 --- a/kernel/arch/x86/kvm/emulate.c +++ b/kernel/arch/x86/kvm/emulate.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <asm/kvm_emulate.h> #include <linux/stringify.h> +#include <asm/debugreg.h> #include "x86.h" #include "tss.h" @@ -523,13 +524,9 @@ static void masked_increment(ulong *reg, ulong mask, int inc) static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc) { - ulong mask; + ulong *preg = reg_rmw(ctxt, reg); - if (ctxt->ad_bytes == sizeof(unsigned long)) - mask = ~0UL; - else - mask = ad_mask(ctxt); - masked_increment(reg_rmw(ctxt, reg), mask, inc); + assign_register(preg, *preg + inc, ctxt->ad_bytes); } static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) @@ -656,6 +653,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -664,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -691,12 +690,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) return emulate_gp(ctxt, 0); - *linear = la; return X86EMUL_CONTINUE; bad: if (addr.seg == VCPU_SREG_SS) @@ -2262,6 +2259,283 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) return rc; } +static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) +{ + u32 eax, ebx, ecx, edx; + + eax = 0x80000001; + ecx = 0; + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + return edx & bit(X86_FEATURE_LM); +} + +#define GET_SMSTATE(type, smbase, offset) \ + ({ \ + type __val; \ + int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \ + sizeof(__val)); \ + if (r != X86EMUL_CONTINUE) \ + return X86EMUL_UNHANDLEABLE; \ + __val; \ + }) + +static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) +{ + desc->g = (flags >> 23) & 1; + desc->d = (flags >> 22) & 1; + desc->l = (flags >> 21) & 1; + desc->avl = (flags >> 20) & 1; + desc->p = (flags >> 15) & 1; + desc->dpl = (flags >> 13) & 3; + desc->s = (flags >> 12) & 1; + desc->type = (flags >> 8) & 15; +} + +static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +{ + struct desc_struct desc; + int offset; + u16 selector; + + selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4); + + if (n < 3) + offset = 0x7f84 + n * 12; + else + offset = 0x7f2c + (n - 3) * 12; + + set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); + return X86EMUL_CONTINUE; +} + +static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) +{ + struct desc_struct desc; + int offset; + u16 selector; + u32 base3; + + offset = 0x7e00 + n * 16; + + selector = GET_SMSTATE(u16, smbase, offset); + rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); + base3 = GET_SMSTATE(u32, smbase, offset + 12); + + ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); + return X86EMUL_CONTINUE; +} + +static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, + u64 cr0, u64 cr4) +{ + int bad; + + /* + * First enable PAE, long mode needs it before CR0.PG = 1 is set. + * Then enable protected mode. However, PCID cannot be enabled + * if EFER.LMA=0, so set it separately. + */ + bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); + if (bad) + return X86EMUL_UNHANDLEABLE; + + bad = ctxt->ops->set_cr(ctxt, 0, cr0); + if (bad) + return X86EMUL_UNHANDLEABLE; + + if (cr4 & X86_CR4_PCIDE) { + bad = ctxt->ops->set_cr(ctxt, 4, cr4); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + + return X86EMUL_CONTINUE; +} + +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct desc_struct desc; + struct desc_ptr dt; + u16 selector; + u32 val, cr0, cr4; + int i; + + cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); + ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8)); + ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; + ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); + + for (i = 0; i < 8; i++) + *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4); + + val = GET_SMSTATE(u32, smbase, 0x7fcc); + ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + val = GET_SMSTATE(u32, smbase, 0x7fc8); + ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + selector = GET_SMSTATE(u32, smbase, 0x7fc4); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); + + selector = GET_SMSTATE(u32, smbase, 0x7fc0); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80)); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c)); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78)); + ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); + + dt.address = GET_SMSTATE(u32, smbase, 0x7f74); + dt.size = GET_SMSTATE(u32, smbase, 0x7f70); + ctxt->ops->set_gdt(ctxt, &dt); + + dt.address = GET_SMSTATE(u32, smbase, 0x7f58); + dt.size = GET_SMSTATE(u32, smbase, 0x7f54); + ctxt->ops->set_idt(ctxt, &dt); + + for (i = 0; i < 6; i++) { + int r = rsm_load_seg_32(ctxt, smbase, i); + if (r != X86EMUL_CONTINUE) + return r; + } + + cr4 = GET_SMSTATE(u32, smbase, 0x7f14); + + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); + + return rsm_enter_protected_mode(ctxt, cr0, cr4); +} + +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct desc_struct desc; + struct desc_ptr dt; + u64 val, cr0, cr4; + u32 base3; + u16 selector; + int i, r; + + for (i = 0; i < 16; i++) + *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); + + ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78); + ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED; + + val = GET_SMSTATE(u32, smbase, 0x7f68); + ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + val = GET_SMSTATE(u32, smbase, 0x7f60); + ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + cr0 = GET_SMSTATE(u64, smbase, 0x7f58); + ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50)); + cr4 = GET_SMSTATE(u64, smbase, 0x7f48); + ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); + val = GET_SMSTATE(u64, smbase, 0x7ed0); + ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); + + selector = GET_SMSTATE(u32, smbase, 0x7e90); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98)); + base3 = GET_SMSTATE(u32, smbase, 0x7e9c); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); + + dt.size = GET_SMSTATE(u32, smbase, 0x7e84); + dt.address = GET_SMSTATE(u64, smbase, 0x7e88); + ctxt->ops->set_idt(ctxt, &dt); + + selector = GET_SMSTATE(u32, smbase, 0x7e70); + rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8); + set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74)); + set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78)); + base3 = GET_SMSTATE(u32, smbase, 0x7e7c); + ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); + + dt.size = GET_SMSTATE(u32, smbase, 0x7e64); + dt.address = GET_SMSTATE(u64, smbase, 0x7e68); + ctxt->ops->set_gdt(ctxt, &dt); + + r = rsm_enter_protected_mode(ctxt, cr0, cr4); + if (r != X86EMUL_CONTINUE) + return r; + + for (i = 0; i < 6; i++) { + r = rsm_load_seg_64(ctxt, smbase, i); + if (r != X86EMUL_CONTINUE) + return r; + } + + return X86EMUL_CONTINUE; +} + +static int em_rsm(struct x86_emulate_ctxt *ctxt) +{ + unsigned long cr0, cr4, efer; + u64 smbase; + int ret; + + if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0) + return emulate_ud(ctxt); + + /* + * Get back to real mode, to prepare a safe state in which to load + * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU + * supports long mode. + */ + cr4 = ctxt->ops->get_cr(ctxt, 4); + if (emulator_has_longmode(ctxt)) { + struct desc_struct cs_desc; + + /* Zero CR4.PCIDE before CR0.PG. */ + if (cr4 & X86_CR4_PCIDE) { + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); + cr4 &= ~X86_CR4_PCIDE; + } + + /* A 32-bit code segment is required to clear EFER.LMA. */ + memset(&cs_desc, 0, sizeof(cs_desc)); + cs_desc.type = 0xb; + cs_desc.s = cs_desc.g = cs_desc.p = 1; + ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS); + } + + /* For the 64-bit case, this will clear EFER.LMA. */ + cr0 = ctxt->ops->get_cr(ctxt, 0); + if (cr0 & X86_CR0_PE) + ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); + + /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */ + if (cr4 & X86_CR4_PAE) + ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); + + /* And finally go back to 32-bit mode. */ + efer = 0; + ctxt->ops->set_msr(ctxt, MSR_EFER, efer); + + smbase = ctxt->ops->get_smbase(ctxt); + if (emulator_has_longmode(ctxt)) + ret = rsm_load_state_64(ctxt, smbase + 0x8000); + else + ret = rsm_load_state_32(ctxt, smbase + 0x8000); + + if (ret != X86EMUL_CONTINUE) { + /* FIXME: should triple fault */ + return X86EMUL_UNHANDLEABLE; + } + + if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) + ctxt->ops->set_nmi_mask(ctxt, false); + + ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK; + ctxt->emul_flags &= ~X86EMUL_SMM_MASK; + return X86EMUL_CONTINUE; +} + static void setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, struct desc_struct *cs, struct desc_struct *ss) @@ -2573,6 +2847,30 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, return true; } +static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) +{ + /* + * Intel CPUs mask the counter and pointers in quite strange + * manner when ECX is zero due to REP-string optimizations. + */ +#ifdef CONFIG_X86_64 + if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt)) + return; + + *reg_write(ctxt, VCPU_REGS_RCX) = 0; + + switch (ctxt->b) { + case 0xa4: /* movsb */ + case 0xa5: /* movsd/w */ + *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; + /* fall through */ + case 0xaa: /* stosb */ + case 0xab: /* stosd/w */ + *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; + } +#endif +} + static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { @@ -2849,7 +3147,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ulong old_tss_base = ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; - ulong desc_addr; + ulong desc_addr, dr7; /* FIXME: old_tss_base == ~0 ? */ @@ -2934,6 +3232,9 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ret = em_push(ctxt); } + ops->get_dr(ctxt, 7, &dr7); + ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN)); + return ret; } @@ -3840,7 +4141,7 @@ static const struct opcode group5[] = { F(DstMem | SrcNone | Lock, em_inc), F(DstMem | SrcNone | Lock, em_dec), I(SrcMem | NearBranch, em_call_near_abs), - I(SrcMemFAddr | ImplicitOps | Stack, em_call_far), + I(SrcMemFAddr | ImplicitOps, em_call_far), I(SrcMem | NearBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps, em_jmp_far), I(SrcMem | Stack, em_push), D(Undefined), @@ -4173,7 +4474,7 @@ static const struct opcode twobyte_table[256] = { F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), - DI(ImplicitOps, rsm), + II(EmulateOnUD | ImplicitOps, em_rsm, rsm), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), F(DstMem | SrcReg | Src2CL | ModRM, em_shrd), @@ -4871,7 +5172,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(ctxt, &ctxt->dst); } - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -4900,7 +5201,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -4910,6 +5211,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (ctxt->rep_prefix && (ctxt->d & String)) { /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { + string_registers_quirk(ctxt); ctxt->eip = ctxt->_eip; ctxt->eflags &= ~X86_EFLAGS_RF; goto done; @@ -4953,7 +5255,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(ctxt->guest_mode) && (ctxt->d & Intercept)) { + if (unlikely(ctxt->emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/kernel/arch/x86/kvm/hyperv.c b/kernel/arch/x86/kvm/hyperv.c new file mode 100644 index 000000000..62cf8c915 --- /dev/null +++ b/kernel/arch/x86/kvm/hyperv.c @@ -0,0 +1,404 @@ +/* + * KVM Microsoft Hyper-V emulation + * + * derived from arch/x86/kvm/x86.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> + * Andrey Smetanin <asmetanin@virtuozzo.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include "x86.h" +#include "lapic.h" +#include "hyperv.h" + +#include <linux/kvm_host.h> +#include <trace/events/kvm.h> + +#include "trace.h" + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + case HV_X64_MSR_REFERENCE_TSC: + case HV_X64_MSR_TIME_REF_COUNT: + case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_RESET: + r = true; + break; + } + + return r; +} + +static int kvm_hv_msr_get_crash_data(struct kvm_vcpu *vcpu, + u32 index, u64 *pdata) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + return -EINVAL; + + *pdata = hv->hv_crash_param[index]; + return 0; +} + +static int kvm_hv_msr_get_crash_ctl(struct kvm_vcpu *vcpu, u64 *pdata) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + *pdata = hv->hv_crash_ctl; + return 0; +} + +static int kvm_hv_msr_set_crash_ctl(struct kvm_vcpu *vcpu, u64 data, bool host) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (host) + hv->hv_crash_ctl = data & HV_X64_MSR_CRASH_CTL_NOTIFY; + + if (!host && (data & HV_X64_MSR_CRASH_CTL_NOTIFY)) { + + vcpu_debug(vcpu, "hv crash (0x%llx 0x%llx 0x%llx 0x%llx 0x%llx)\n", + hv->hv_crash_param[0], + hv->hv_crash_param[1], + hv->hv_crash_param[2], + hv->hv_crash_param[3], + hv->hv_crash_param[4]); + + /* Send notification about crash to user space */ + kvm_make_request(KVM_REQ_HV_CRASH, vcpu); + } + + return 0; +} + +static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu, + u32 index, u64 data) +{ + struct kvm_hv *hv = &vcpu->kvm->arch.hyperv; + + if (WARN_ON_ONCE(index >= ARRAY_SIZE(hv->hv_crash_param))) + return -EINVAL; + + hv->hv_crash_param[index] = data; + return 0; +} + +static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, + bool host) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + hv->hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!hv->hv_guest_os_id) + hv->hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!hv->hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + hv->hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (__copy_to_user((void __user *)addr, instructions, 4)) + return 1; + hv->hv_hypercall = data; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_REFERENCE_TSC: { + u64 gfn; + HV_REFERENCE_TSC_PAGE tsc_ref; + + memset(&tsc_ref, 0, sizeof(tsc_ref)); + hv->hv_tsc_page = data; + if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) + break; + gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; + if (kvm_write_guest( + kvm, + gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, + &tsc_ref, sizeof(tsc_ref))) + return 1; + mark_page_dirty(kvm, gfn); + break; + } + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + return kvm_hv_msr_set_crash_data(vcpu, + msr - HV_X64_MSR_CRASH_P0, + data); + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_msr_set_crash_ctl(vcpu, data, host); + case HV_X64_MSR_RESET: + if (data == 1) { + vcpu_debug(vcpu, "hyper-v reset requested\n"); + kvm_make_request(KVM_REQ_HV_RESET, vcpu); + } + break; + default: + vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + msr, data); + return 1; + } + return 0; +} + +/* Calculate cpu time spent by current task in 100ns units */ +static u64 current_task_runtime_100ns(void) +{ + cputime_t utime, stime; + + task_cputime_adjusted(current, &utime, &stime); + return div_u64(cputime_to_nsecs(utime + stime), 100); +} + +static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + u64 gfn; + unsigned long addr; + + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + hv->hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; + break; + } + gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; + addr = kvm_vcpu_gfn_to_hva(vcpu, gfn); + if (kvm_is_error_hva(addr)) + return 1; + if (__clear_user((void __user *)addr, PAGE_SIZE)) + return 1; + hv->hv_vapic = data; + kvm_vcpu_mark_page_dirty(vcpu, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, + gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + case HV_X64_MSR_VP_RUNTIME: + if (!host) + return 1; + hv->runtime_offset = data - current_task_runtime_100ns(); + break; + default: + vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", + msr, data); + return 1; + } + + return 0; +} + +static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = &kvm->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = hv->hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = hv->hv_hypercall; + break; + case HV_X64_MSR_TIME_REF_COUNT: { + data = + div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + break; + } + case HV_X64_MSR_REFERENCE_TSC: + data = hv->hv_tsc_page; + break; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + return kvm_hv_msr_get_crash_data(vcpu, + msr - HV_X64_MSR_CRASH_P0, + pdata); + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_msr_get_crash_ctl(vcpu, pdata); + case HV_X64_MSR_RESET: + data = 0; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + + kvm_for_each_vcpu(r, v, vcpu->kvm) { + if (v == vcpu) { + data = r; + break; + } + } + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + case HV_X64_MSR_APIC_ASSIST_PAGE: + data = hv->hv_vapic; + break; + case HV_X64_MSR_VP_RUNTIME: + data = current_task_runtime_100ns() + hv->runtime_offset; + break; + default: + vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + +int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) +{ + if (kvm_hv_msr_partition_wide(msr)) { + int r; + + mutex_lock(&vcpu->kvm->lock); + r = kvm_hv_set_msr_pw(vcpu, msr, data, host); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return kvm_hv_set_msr(vcpu, msr, data, host); +} + +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + if (kvm_hv_msr_partition_wide(msr)) { + int r; + + mutex_lock(&vcpu->kvm->lock); + r = kvm_hv_get_msr_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return kvm_hv_get_msr(vcpu, msr, pdata); +} + +bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hyperv.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + longmode = is_64_bit_mode(vcpu); + + if (!longmode) { + param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); + ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); + outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} diff --git a/kernel/arch/x86/kvm/hyperv.h b/kernel/arch/x86/kvm/hyperv.h new file mode 100644 index 000000000..c7bce559f --- /dev/null +++ b/kernel/arch/x86/kvm/hyperv.h @@ -0,0 +1,32 @@ +/* + * KVM Microsoft Hyper-V emulation + * + * derived from arch/x86/kvm/x86.c + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright (C) 2008 Qumranet, Inc. + * Copyright IBM Corporation, 2008 + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright (C) 2015 Andrey Smetanin <asmetanin@virtuozzo.com> + * + * Authors: + * Avi Kivity <avi@qumranet.com> + * Yaniv Kamay <yaniv@qumranet.com> + * Amit Shah <amit.shah@qumranet.com> + * Ben-Ami Yassour <benami@il.ibm.com> + * Andrey Smetanin <asmetanin@virtuozzo.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#ifndef __ARCH_X86_KVM_HYPERV_H__ +#define __ARCH_X86_KVM_HYPERV_H__ + +int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); +int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +bool kvm_hv_hypercall_enabled(struct kvm *kvm); +int kvm_hv_hypercall(struct kvm_vcpu *vcpu); + +#endif diff --git a/kernel/arch/x86/kvm/i8254.c b/kernel/arch/x86/kvm/i8254.c index f90952f64..b0ea42b78 100644 --- a/kernel/arch/x86/kvm/i8254.c +++ b/kernel/arch/x86/kvm/i8254.c @@ -35,6 +35,7 @@ #include <linux/kvm_host.h> #include <linux/slab.h> +#include "ioapic.h" #include "irq.h" #include "i8254.h" #include "x86.h" @@ -333,7 +334,8 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; s64 interval; - if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) + if (!ioapic_in_kernel(kvm) || + ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) return; interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); @@ -418,6 +420,7 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_s u8 saved_mode; if (hpet_legacy_start) { /* save existing mode for later reenablement */ + WARN_ON(channel != 0); saved_mode = kvm->arch.vpit->pit_state.channels[0].mode; kvm->arch.vpit->pit_state.channels[0].mode = 0xff; /* disable timer */ pit_load_count(kvm, channel, val); diff --git a/kernel/arch/x86/kvm/i8259.c b/kernel/arch/x86/kvm/i8259.c index fef922ff2..7cc2360f1 100644 --- a/kernel/arch/x86/kvm/i8259.c +++ b/kernel/arch/x86/kvm/i8259.c @@ -651,15 +651,10 @@ fail_unlock: return NULL; } -void kvm_destroy_pic(struct kvm *kvm) +void kvm_destroy_pic(struct kvm_pic *vpic) { - struct kvm_pic *vpic = kvm->arch.vpic; - - if (vpic) { - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_master); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_slave); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &vpic->dev_eclr); - kvm->arch.vpic = NULL; - kfree(vpic); - } + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave); + kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr); + kfree(vpic); } diff --git a/kernel/arch/x86/kvm/ioapic.c b/kernel/arch/x86/kvm/ioapic.c index 28146f03c..88d0a92d3 100644 --- a/kernel/arch/x86/kvm/ioapic.c +++ b/kernel/arch/x86/kvm/ioapic.c @@ -233,21 +233,7 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr) } -static void update_handled_vectors(struct kvm_ioapic *ioapic) -{ - DECLARE_BITMAP(handled_vectors, 256); - int i; - - memset(handled_vectors, 0, sizeof(handled_vectors)); - for (i = 0; i < IOAPIC_NUM_PINS; ++i) - __set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors); - memcpy(ioapic->handled_vectors, handled_vectors, - sizeof(handled_vectors)); - smp_wmb(); -} - -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, - u32 *tmr) +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; union kvm_ioapic_redirect_entry *e; @@ -260,13 +246,11 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) || index == RTC_GSI) { if (kvm_apic_match_dest(vcpu, NULL, 0, - e->fields.dest_id, e->fields.dest_mode)) { + e->fields.dest_id, e->fields.dest_mode) || + (e->fields.trig_mode == IOAPIC_EDGE_TRIG && + kvm_apic_pending_eoi(vcpu, e->fields.vector))) __set_bit(e->fields.vector, (unsigned long *)eoi_exit_bitmap); - if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG) - __set_bit(e->fields.vector, - (unsigned long *)tmr); - } } } spin_unlock(&ioapic->lock); @@ -315,7 +299,6 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val) e->bits |= (u32) val; e->fields.remote_irr = 0; } - update_handled_vectors(ioapic); mask_after = e->fields.mask; if (mask_before != mask_after) kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after); @@ -349,6 +332,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.delivery_mode = entry->fields.delivery_mode << 8; irqe.level = 1; irqe.shorthand = 0; + irqe.msi_redir_hint = false; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) ioapic->irr_delivered |= 1 << irq; @@ -598,7 +582,6 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->id = 0; memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); rtc_irq_eoi_tracking_reset(ioapic); - update_handled_vectors(ioapic); } static const struct kvm_io_device_ops ioapic_mmio_ops = { @@ -627,8 +610,10 @@ int kvm_ioapic_init(struct kvm *kvm) if (ret < 0) { kvm->arch.vioapic = NULL; kfree(ioapic); + return ret; } + kvm_vcpu_request_scan_ioapic(kvm); return ret; } @@ -637,11 +622,9 @@ void kvm_ioapic_destroy(struct kvm *kvm) struct kvm_ioapic *ioapic = kvm->arch.vioapic; cancel_delayed_work_sync(&ioapic->eoi_inject); - if (ioapic) { - kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); - kvm->arch.vioapic = NULL; - kfree(ioapic); - } + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev); + kvm->arch.vioapic = NULL; + kfree(ioapic); } int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) @@ -667,7 +650,6 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; ioapic->irr_delivered = 0; - update_handled_vectors(ioapic); kvm_vcpu_request_scan_ioapic(kvm); kvm_ioapic_inject_all(ioapic, state->irr); spin_unlock(&ioapic->lock); diff --git a/kernel/arch/x86/kvm/ioapic.h b/kernel/arch/x86/kvm/ioapic.h index ca0b0b4e6..084617d37 100644 --- a/kernel/arch/x86/kvm/ioapic.h +++ b/kernel/arch/x86/kvm/ioapic.h @@ -9,6 +9,7 @@ struct kvm; struct kvm_vcpu; #define IOAPIC_NUM_PINS KVM_IOAPIC_NUM_PINS +#define MAX_NR_RESERVED_IOAPIC_PINS KVM_MAX_IRQ_ROUTES #define IOAPIC_VERSION_ID 0x11 /* IOAPIC version */ #define IOAPIC_EDGE_TRIG 0 #define IOAPIC_LEVEL_TRIG 1 @@ -73,7 +74,6 @@ struct kvm_ioapic { struct kvm *kvm; void (*ack_notifier)(void *opaque, int irq); spinlock_t lock; - DECLARE_BITMAP(handled_vectors, 256); struct rtc_status rtc_status; struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; @@ -98,11 +98,12 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } -static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) +static inline int ioapic_in_kernel(struct kvm *kvm) { - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); + int ret; + + ret = (ioapic_irqchip(kvm) != NULL); + return ret; } void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); @@ -120,7 +121,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap, - u32 *tmr); +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); #endif diff --git a/kernel/arch/x86/kvm/iommu.c b/kernel/arch/x86/kvm/iommu.c index 7dbced309..5c520ebf6 100644 --- a/kernel/arch/x86/kvm/iommu.c +++ b/kernel/arch/x86/kvm/iommu.c @@ -200,6 +200,7 @@ int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev) goto out_unmap; } + kvm_arch_start_assignment(kvm); pci_set_dev_assigned(pdev); dev_info(&pdev->dev, "kvm assign device\n"); @@ -224,6 +225,7 @@ int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev) iommu_detach_device(domain, &pdev->dev); pci_clear_dev_assigned(pdev); + kvm_arch_end_assignment(kvm); dev_info(&pdev->dev, "kvm deassign device\n"); diff --git a/kernel/arch/x86/kvm/irq.c b/kernel/arch/x86/kvm/irq.c index a1ec6a50a..097060e33 100644 --- a/kernel/arch/x86/kvm/irq.c +++ b/kernel/arch/x86/kvm/irq.c @@ -38,14 +38,27 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) EXPORT_SYMBOL(kvm_cpu_has_pending_timer); /* + * check if there is a pending userspace external interrupt + */ +static int pending_userspace_extint(struct kvm_vcpu *v) +{ + return v->arch.pending_external_vector != -1; +} + +/* * check if there is pending interrupt from * non-APIC source without intack. */ static int kvm_cpu_has_extint(struct kvm_vcpu *v) { - if (kvm_apic_accept_pic_intr(v)) - return pic_irqchip(v->kvm)->output; /* PIC */ - else + u8 accept = kvm_apic_accept_pic_intr(v); + + if (accept) { + if (irqchip_split(v->kvm)) + return pending_userspace_extint(v); + else + return pic_irqchip(v->kvm)->output; + } else return 0; } @@ -57,13 +70,13 @@ static int kvm_cpu_has_extint(struct kvm_vcpu *v) */ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) { - if (!irqchip_in_kernel(v->kvm)) + if (!lapic_in_kernel(v)) return v->arch.interrupt.pending; if (kvm_cpu_has_extint(v)) return 1; - if (kvm_apic_vid_enabled(v->kvm)) + if (kvm_vcpu_apic_vid_enabled(v)) return 0; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ @@ -75,7 +88,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) */ int kvm_cpu_has_interrupt(struct kvm_vcpu *v) { - if (!irqchip_in_kernel(v->kvm)) + if (!lapic_in_kernel(v)) return v->arch.interrupt.pending; if (kvm_cpu_has_extint(v)) @@ -91,9 +104,16 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt); */ static int kvm_cpu_get_extint(struct kvm_vcpu *v) { - if (kvm_cpu_has_extint(v)) - return kvm_pic_read_irq(v->kvm); /* PIC */ - return -1; + if (kvm_cpu_has_extint(v)) { + if (irqchip_split(v->kvm)) { + int vector = v->arch.pending_external_vector; + + v->arch.pending_external_vector = -1; + return vector; + } else + return kvm_pic_read_irq(v->kvm); /* PIC */ + } else + return -1; } /* @@ -103,7 +123,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) { int vector; - if (!irqchip_in_kernel(v->kvm)) + if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; vector = kvm_cpu_get_extint(v); diff --git a/kernel/arch/x86/kvm/irq.h b/kernel/arch/x86/kvm/irq.h index ad68c7300..ae5c78f23 100644 --- a/kernel/arch/x86/kvm/irq.h +++ b/kernel/arch/x86/kvm/irq.h @@ -74,7 +74,7 @@ struct kvm_pic { }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); -void kvm_destroy_pic(struct kvm *kvm); +void kvm_destroy_pic(struct kvm_pic *vpic); int kvm_pic_read_irq(struct kvm *kvm); void kvm_pic_update_irq(struct kvm_pic *s); @@ -83,15 +83,40 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) return kvm->arch.vpic; } -static inline int irqchip_in_kernel(struct kvm *kvm) +static inline int pic_in_kernel(struct kvm *kvm) { int ret; ret = (pic_irqchip(kvm) != NULL); + return ret; +} + +static inline int irqchip_split(struct kvm *kvm) +{ + return kvm->arch.irqchip_split; +} + +static inline int irqchip_in_kernel(struct kvm *kvm) +{ + struct kvm_pic *vpic = pic_irqchip(kvm); + bool ret; + + ret = (vpic != NULL); + ret |= irqchip_split(kvm); + + /* Read vpic before kvm->irq_routing. */ smp_rmb(); return ret; } +static inline int lapic_in_kernel(struct kvm_vcpu *vcpu) +{ + /* Same as irqchip_in_kernel(vcpu->kvm), but with less + * pointer chasing and no unnecessary memory barriers. + */ + return vcpu->arch.apic != NULL; +} + void kvm_pic_reset(struct kvm_kpic_state *s); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu); diff --git a/kernel/arch/x86/kvm/irq_comm.c b/kernel/arch/x86/kvm/irq_comm.c index 72298b3ac..84b96d319 100644 --- a/kernel/arch/x86/kvm/irq_comm.c +++ b/kernel/arch/x86/kvm/irq_comm.c @@ -31,6 +31,8 @@ #include "ioapic.h" +#include "lapic.h" + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -48,11 +50,6 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, line_status); } -inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq) -{ - return irq->delivery_mode == APIC_DM_LOWEST; -} - int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map) { @@ -60,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_vcpu *vcpu, *lowest = NULL; if (irq->dest_mode == 0 && irq->dest_id == 0xff && - kvm_is_dm_lowest_prio(irq)) { + kvm_lowest_prio_delivery(irq)) { printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } @@ -76,7 +73,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, irq->dest_id, irq->dest_mode)) continue; - if (!kvm_is_dm_lowest_prio(irq)) { + if (!kvm_lowest_prio_delivery(irq)) { if (r < 0) r = 0; r += kvm_apic_set_irq(vcpu, irq, dest_map); @@ -94,8 +91,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, return r; } -static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, - struct kvm_lapic_irq *irq) +void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm_lapic_irq *irq) { trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data); @@ -106,10 +103,12 @@ static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e, irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo; irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data; irq->delivery_mode = e->msi.data & 0x700; + irq->msi_redir_hint = ((e->msi.address_lo + & MSI_ADDR_REDIRECTION_LOWPRI) > 0); irq->level = 1; irq->shorthand = 0; - /* TODO Deal with RH bit of MSI message address */ } +EXPORT_SYMBOL_GPL(kvm_set_msi_irq); int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -125,12 +124,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, } -static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, - struct kvm *kvm) +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) { struct kvm_lapic_irq irq; int r; + if (unlikely(e->type != KVM_IRQ_ROUTING_MSI)) + return -EWOULDBLOCK; + kvm_set_msi_irq(e, &irq); if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL)) @@ -139,42 +142,6 @@ static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e, return -EWOULDBLOCK; } -/* - * Deliver an IRQ in an atomic context if we can, or return a failure, - * user can retry in a process context. - * Return value: - * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context. - * Other values - No need to retry. - */ -int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level) -{ - struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS]; - struct kvm_kernel_irq_routing_entry *e; - int ret = -EINVAL; - int idx; - - trace_kvm_set_irq(irq, level, irq_source_id); - - /* - * Injection into either PIC or IOAPIC might need to scan all CPUs, - * which would need to be retried from thread context; when same GSI - * is connected to both PIC and IOAPIC, we'd have to report a - * partial failure here. - * Since there's no easy way to do this, we only support injecting MSI - * which is limited to 1:1 GSI mapping. - */ - idx = srcu_read_lock(&kvm->irq_srcu); - if (kvm_irq_map_gsi(kvm, entries, irq) > 0) { - e = &entries[0]; - if (likely(e->type == KVM_IRQ_ROUTING_MSI)) - ret = kvm_set_msi_inatomic(e, kvm); - else - ret = -EWOULDBLOCK; - } - srcu_read_unlock(&kvm->irq_srcu, idx); - return ret; -} - int kvm_request_irq_source_id(struct kvm *kvm) { unsigned long *bitmap = &kvm->arch.irq_sources_bitmap; @@ -210,7 +177,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); - if (!irqchip_in_kernel(kvm)) + if (!ioapic_in_kernel(kvm)) goto unlock; kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id); @@ -299,6 +266,33 @@ out: return r; } +bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu) +{ + int i, r = 0; + struct kvm_vcpu *vcpu; + + if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) + return true; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!kvm_apic_present(vcpu)) + continue; + + if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand, + irq->dest_id, irq->dest_mode)) + continue; + + if (++r == 2) + return false; + + *dest_vcpu = vcpu; + } + + return r == 1; +} +EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu); + #define IOAPIC_ROUTING_ENTRY(irq) \ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } } @@ -330,3 +324,54 @@ int kvm_setup_default_irq_routing(struct kvm *kvm) return kvm_set_irq_routing(kvm, default_routing, ARRAY_SIZE(default_routing), 0); } + +static const struct kvm_irq_routing_entry empty_routing[] = {}; + +int kvm_setup_empty_irq_routing(struct kvm *kvm) +{ + return kvm_set_irq_routing(kvm, empty_routing, 0, 0); +} + +void kvm_arch_irq_routing_update(struct kvm *kvm) +{ + if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm)) + return; + kvm_make_scan_ioapic_request(kvm); +} + +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_kernel_irq_routing_entry *entry; + struct kvm_irq_routing_table *table; + u32 i, nr_ioapic_pins; + int idx; + + /* kvm->irq_routing must be read after clearing + * KVM_SCAN_IOAPIC. */ + smp_mb(); + idx = srcu_read_lock(&kvm->irq_srcu); + table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + nr_ioapic_pins = min_t(u32, table->nr_rt_entries, + kvm->arch.nr_reserved_ioapic_pins); + for (i = 0; i < nr_ioapic_pins; ++i) { + hlist_for_each_entry(entry, &table->map[i], link) { + u32 dest_id, dest_mode; + bool level; + + if (entry->type != KVM_IRQ_ROUTING_MSI) + continue; + dest_id = (entry->msi.address_lo >> 12) & 0xff; + dest_mode = (entry->msi.address_lo >> 2) & 0x1; + level = entry->msi.data & MSI_DATA_TRIGGER_LEVEL; + if (level && kvm_apic_match_dest(vcpu, NULL, 0, + dest_id, dest_mode)) { + u32 vector = entry->msi.data & 0xff; + + __set_bit(vector, + (unsigned long *) eoi_exit_bitmap); + } + } + } + srcu_read_unlock(&kvm->irq_srcu, idx); +} diff --git a/kernel/arch/x86/kvm/kvm_cache_regs.h b/kernel/arch/x86/kvm/kvm_cache_regs.h index 544076c4f..e1e89ee4a 100644 --- a/kernel/arch/x86/kvm/kvm_cache_regs.h +++ b/kernel/arch/x86/kvm/kvm_cache_regs.h @@ -99,4 +99,9 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu) return vcpu->arch.hflags & HF_GUEST_MASK; } +static inline bool is_smm(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hflags & HF_SMM_MASK; +} + #endif diff --git a/kernel/arch/x86/kvm/lapic.c b/kernel/arch/x86/kvm/lapic.c index 525db8be0..20d9e9fb3 100644 --- a/kernel/arch/x86/kvm/lapic.c +++ b/kernel/arch/x86/kvm/lapic.c @@ -209,7 +209,7 @@ out: if (old) kfree_rcu(old, rcu); - kvm_vcpu_request_scan_ioapic(kvm); + kvm_make_scan_ioapic_request(kvm); } static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) @@ -240,6 +240,15 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) recalculate_apic_map(apic->vcpu->kvm); } +static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u8 id) +{ + u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); + + apic_set_reg(apic, APIC_ID, id << 24); + apic_set_reg(apic, APIC_LDR, ldr); + recalculate_apic_map(apic->vcpu->kvm); +} + static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) { return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED); @@ -339,6 +348,8 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) struct kvm_lapic *apic = vcpu->arch.apic; __kvm_apic_update_irr(pir, apic->regs); + + kvm_make_request(KVM_REQ_EVENT, vcpu); } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); @@ -381,7 +392,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) vcpu = apic->vcpu; - if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) { + if (unlikely(kvm_vcpu_apic_vid_enabled(vcpu))) { /* try to update RVI */ apic_clear_vector(vec, apic->regs + APIC_IRR); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -542,15 +553,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - int i; - - for (i = 0; i < 8; i++) - apic_set_reg(apic, APIC_TMR + 0x10 * i, tmr[i]); -} - static void apic_update_ppr(struct kvm_lapic *apic) { u32 tpr, isrv, ppr, old_ppr; @@ -728,7 +730,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = map->logical_map[cid]; - if (irq->delivery_mode == APIC_DM_LOWEST) { + if (kvm_lowest_prio_delivery(irq)) { int l = -1; for_each_set_bit(i, &bitmap, 16) { if (!dst[i]) @@ -755,6 +757,65 @@ out: return ret; } +bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu) +{ + struct kvm_apic_map *map; + bool ret = false; + struct kvm_lapic *dst = NULL; + + if (irq->shorthand) + return false; + + rcu_read_lock(); + map = rcu_dereference(kvm->arch.apic_map); + + if (!map) + goto out; + + if (irq->dest_mode == APIC_DEST_PHYSICAL) { + if (irq->dest_id == 0xFF) + goto out; + + if (irq->dest_id >= ARRAY_SIZE(map->phys_map)) + goto out; + + dst = map->phys_map[irq->dest_id]; + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } else { + u16 cid; + unsigned long bitmap = 1; + int i, r = 0; + + if (!kvm_apic_logical_map_valid(map)) + goto out; + + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); + + if (cid >= ARRAY_SIZE(map->logical_map)) + goto out; + + for_each_set_bit(i, &bitmap, 16) { + dst = map->logical_map[cid][i]; + if (++r == 2) + goto out; + } + + if (dst && kvm_apic_present(dst->vcpu)) + *dest_vcpu = dst->vcpu; + else + goto out; + } + + ret = true; +out: + rcu_read_unlock(); + return ret; +} + /* * Add a pending IRQ into lapic. * Return 1 if successfully added and 0 if discarded. @@ -772,6 +833,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; case APIC_DM_FIXED: + if (unlikely(trig_mode && !level)) + break; + /* FIXME add logic for vcpu on reset */ if (unlikely(!apic_enabled(apic))) break; @@ -781,6 +845,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (dest_map) __set_bit(vcpu->vcpu_id, dest_map); + if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) { + if (trig_mode) + apic_set_vector(vector, apic->regs + APIC_TMR); + else + apic_clear_vector(vector, apic->regs + APIC_TMR); + } + if (kvm_x86_ops->deliver_posted_interrupt) kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); else { @@ -799,7 +870,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_SMI: - apic_debug("Ignoring guest SMI\n"); + result = 1; + kvm_make_request(KVM_REQ_SMI, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_NMI: @@ -857,16 +930,32 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio; } +static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) +{ + return test_bit(vector, (ulong *)apic->vcpu->arch.eoi_exit_bitmap); +} + static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) { - int trigger_mode; - if (apic_test_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; - kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); + int trigger_mode; + + /* Eoi the ioapic only if the ioapic doesn't own the vector. */ + if (!kvm_ioapic_handles_vector(apic, vector)) + return; + + /* Request a KVM exit to inform the userspace IOAPIC. */ + if (irqchip_split(apic->vcpu->kvm)) { + apic->vcpu->arch.pending_ioapic_eoi = vector; + kvm_make_request(KVM_REQ_IOAPIC_EOI_EXIT, apic->vcpu); + return; } + + if (apic_test_vector(vector, apic->regs + APIC_TMR)) + trigger_mode = IOAPIC_LEVEL_TRIG; + else + trigger_mode = IOAPIC_EDGE_TRIG; + + kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); } static int apic_set_eoi(struct kvm_lapic *apic) @@ -914,9 +1003,10 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.vector = icr_low & APIC_VECTOR_MASK; irq.delivery_mode = icr_low & APIC_MODE_MASK; irq.dest_mode = icr_low & APIC_DEST_MASK; - irq.level = icr_low & APIC_INT_ASSERT; + irq.level = (icr_low & APIC_INT_ASSERT) != 0; irq.trig_mode = icr_low & APIC_INT_LEVELTRIG; irq.shorthand = icr_low & APIC_SHORT_MASK; + irq.msi_redir_hint = false; if (apic_x2apic_mode(apic)) irq.dest_id = icr_high; else @@ -926,10 +1016,11 @@ static void apic_send_ipi(struct kvm_lapic *apic) apic_debug("icr_high 0x%x, icr_low 0x%x, " "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, " - "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n", + "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x, " + "msi_redir_hint 0x%x\n", icr_high, icr_low, irq.shorthand, irq.dest_id, irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, - irq.vector); + irq.vector, irq.msi_redir_hint); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq, NULL); } @@ -1104,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic) static void apic_timer_expired(struct kvm_lapic *apic) { struct kvm_vcpu *vcpu = apic->vcpu; - struct swait_head *q = &vcpu->wq; + struct swait_queue_head *q = &vcpu->wq; struct kvm_timer *ktimer = &apic->lapic_timer; if (atomic_read(&apic->lapic_timer.pending)) @@ -1113,8 +1204,8 @@ static void apic_timer_expired(struct kvm_lapic *apic) atomic_inc(&apic->lapic_timer.pending); kvm_set_pending_timer(vcpu); - if (swaitqueue_active(q)) - swait_wake_interruptible(q); + if (swait_active(q)) + swake_up(q); if (apic_lvtt_tscdeadline(apic)) ktimer->expired_tscdeadline = ktimer->tscdeadline; @@ -1159,7 +1250,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) tsc_deadline = apic->lapic_timer.expired_tscdeadline; apic->lapic_timer.expired_tscdeadline = 0; - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline); /* __delay is delay_tsc whenever the hardware has TSC, thus always. */ @@ -1167,36 +1258,8 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu) __delay(tsc_deadline - guest_tsc); } -static enum hrtimer_restart apic_timer_fn(struct hrtimer *data); - -static void __apic_timer_expired(struct hrtimer *data) -{ - int ret, i = 0; - enum hrtimer_restart r; - struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); - - r = apic_timer_fn(data); - - if (r == HRTIMER_RESTART) { - do { - ret = hrtimer_start_expires(data, HRTIMER_MODE_ABS); - if (ret == -ETIME) - hrtimer_add_expires_ns(&ktimer->timer, - ktimer->period); - i++; - } while (ret == -ETIME && i < 10); - - if (ret == -ETIME) { - printk_once(KERN_ERR "%s: failed to reprogram timer\n", - __func__); - WARN_ON_ONCE(1); - } - } -} - static void start_apic_timer(struct kvm_lapic *apic) { - int ret; ktime_t now; atomic_set(&apic->lapic_timer.pending, 0); @@ -1227,11 +1290,9 @@ static void start_apic_timer(struct kvm_lapic *apic) } } - ret = hrtimer_start(&apic->lapic_timer.timer, + hrtimer_start(&apic->lapic_timer.timer, ktime_add_ns(now, apic->lapic_timer.period), HRTIMER_MODE_ABS); - if (ret == -ETIME) - __apic_timer_expired(&apic->lapic_timer.timer); apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " @@ -1257,16 +1318,14 @@ static void start_apic_timer(struct kvm_lapic *apic) local_irq_save(flags); now = apic->lapic_timer.timer.base->get_time(); - guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, native_read_tsc()); + guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); if (likely(tscdeadline > guest_tsc)) { ns = (tscdeadline - guest_tsc) * 1000000ULL; do_div(ns, this_tsc_khz); expire = ktime_add_ns(now, ns); expire = ktime_sub_ns(expire, lapic_timer_advance_ns); - ret = hrtimer_start(&apic->lapic_timer.timer, + hrtimer_start(&apic->lapic_timer.timer, expire, HRTIMER_MODE_ABS); - if (ret == -ETIME) - __apic_timer_expired(&apic->lapic_timer.timer); } else apic_timer_expired(apic); @@ -1276,16 +1335,17 @@ static void start_apic_timer(struct kvm_lapic *apic) static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) { - int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0)); + bool lvt0_in_nmi_mode = apic_lvt_nmi_mode(lvt0_val); - if (apic_lvt_nmi_mode(lvt0_val)) { - if (!nmi_wd_enabled) { + if (apic->lvt0_in_nmi_mode != lvt0_in_nmi_mode) { + apic->lvt0_in_nmi_mode = lvt0_in_nmi_mode; + if (lvt0_in_nmi_mode) { apic_debug("Receive NMI setting on APIC_LVT0 " "for cpu %d\n", apic->vcpu->vcpu_id); atomic_inc(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); - } - } else if (nmi_wd_enabled) - atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); + } else + atomic_dec(&apic->vcpu->kvm->arch.vapics_in_nmi_mode); + } } static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) @@ -1573,9 +1633,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) { - u32 id = kvm_apic_id(apic); - u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf)); - kvm_apic_set_ldr(apic, ldr); + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); } else kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); @@ -1594,7 +1652,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } -void kvm_lapic_reset(struct kvm_vcpu *vcpu) +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { struct kvm_lapic *apic; int i; @@ -1608,19 +1666,23 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); - kvm_apic_set_id(apic, vcpu->vcpu_id); + if (!init_event) + kvm_apic_set_id(apic, vcpu->vcpu_id); kvm_apic_set_version(apic->vcpu); for (i = 0; i < APIC_LVT_NUM; i++) apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); - apic_set_reg(apic, APIC_LVT0, - SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) + apic_set_reg(apic, APIC_LVT0, + SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); + apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0)); apic_set_reg(apic, APIC_DFR, 0xffffffffU); apic_set_spiv(apic, 0xff); apic_set_reg(apic, APIC_TASKPRI, 0); - kvm_apic_set_ldr(apic, 0); + if (!apic_x2apic_mode(apic)) + kvm_apic_set_ldr(apic, 0); apic_set_reg(apic, APIC_ESR, 0); apic_set_reg(apic, APIC_ICR, 0); apic_set_reg(apic, APIC_ICR2, 0); @@ -1631,7 +1693,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm); + apic->irr_pending = kvm_vcpu_apic_vid_enabled(vcpu); apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0; apic->highest_isr_cache = -1; update_divide_count(apic); @@ -1750,7 +1812,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE); static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */ - kvm_lapic_reset(vcpu); + kvm_lapic_reset(vcpu, false); kvm_iodevice_init(&apic->dev, &apic_mmio_ops); return 0; @@ -1855,7 +1917,10 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_rtc_eoi_tracking_restore_one(vcpu); + if (ioapic_in_kernel(vcpu->kvm)) + kvm_rtc_eoi_tracking_restore_one(vcpu); + + vcpu->arch.apic_arb_prio = 0; } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) @@ -1867,8 +1932,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) timer = &vcpu->arch.apic->lapic_timer.timer; if (hrtimer_cancel(timer)) - if (hrtimer_start_expires(timer, HRTIMER_MODE_ABS) == -ETIME) - __apic_timer_expired(timer); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* @@ -1918,8 +1982,9 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, - sizeof(u32)); + if (kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32))) + return; apic_set_tpr(vcpu->arch.apic, data & 0xff); } @@ -1939,7 +2004,7 @@ static void apic_sync_pv_eoi_to_guest(struct kvm_vcpu *vcpu, /* Cache not set: could be safe but we don't bother. */ apic->highest_isr_cache == -1 || /* Need EOI to update ioapic. */ - kvm_ioapic_handles_vector(vcpu->kvm, apic->highest_isr_cache)) { + kvm_ioapic_handles_vector(apic, apic->highest_isr_cache)) { /* * PV EOI was disabled by apic_sync_pv_eoi_from_guest * so we need not do anything here. @@ -1995,7 +2060,7 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4; - if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; if (reg == APIC_ICR2) @@ -2012,7 +2077,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data) struct kvm_lapic *apic = vcpu->arch.apic; u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0; - if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic)) + if (!lapic_in_kernel(vcpu) || !apic_x2apic_mode(apic)) return 1; if (reg == APIC_DFR || reg == APIC_ICR2) { @@ -2084,11 +2149,22 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events) return; - pe = xchg(&apic->pending_events, 0); + /* + * INITs are latched while in SMM. Because an SMM CPU cannot + * be in KVM_MP_STATE_INIT_RECEIVED state, just eat SIPIs + * and delay processing of INIT until the next RSM. + */ + if (is_smm(vcpu)) { + WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED); + if (test_bit(KVM_APIC_SIPI, &apic->pending_events)) + clear_bit(KVM_APIC_SIPI, &apic->pending_events); + return; + } + pe = xchg(&apic->pending_events, 0); if (test_bit(KVM_APIC_INIT, &pe)) { - kvm_lapic_reset(vcpu); - kvm_vcpu_reset(vcpu); + kvm_lapic_reset(vcpu, true); + kvm_vcpu_reset(vcpu, true); if (kvm_vcpu_is_bsp(apic->vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else diff --git a/kernel/arch/x86/kvm/lapic.h b/kernel/arch/x86/kvm/lapic.h index c4ea87eed..fde8e35d5 100644 --- a/kernel/arch/x86/kvm/lapic.h +++ b/kernel/arch/x86/kvm/lapic.h @@ -26,6 +26,7 @@ struct kvm_lapic { struct kvm_vcpu *vcpu; bool sw_enabled; bool irr_pending; + bool lvt0_in_nmi_mode; /* Number of bits set in ISR. */ s16 isr_count; /* The highest vector set in ISR; if -1 - invalid, must scan ISR. */ @@ -48,7 +49,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu); int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu); void kvm_apic_accept_events(struct kvm_vcpu *vcpu); -void kvm_lapic_reset(struct kvm_vcpu *vcpu); +void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event); u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu); void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8); void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu); @@ -56,7 +57,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value); u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu); void kvm_apic_set_version(struct kvm_vcpu *vcpu); -void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr); void __kvm_apic_update_irr(u32 *pir, void *regs); void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, @@ -90,7 +90,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data); static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) { - return vcpu->arch.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; + return vcpu->arch.hyperv.hv_vapic & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE; } int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); @@ -143,9 +143,9 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) return apic->vcpu->arch.apic_base & X2APIC_ENABLE; } -static inline bool kvm_apic_vid_enabled(struct kvm *kvm) +static inline bool kvm_vcpu_apic_vid_enabled(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->vm_has_apicv(kvm); + return kvm_x86_ops->cpu_uses_apicv(vcpu); } static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) @@ -153,8 +153,21 @@ static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) return kvm_vcpu_has_lapic(vcpu) && vcpu->arch.apic->pending_events; } +static inline bool kvm_lowest_prio_delivery(struct kvm_lapic_irq *irq) +{ + return (irq->delivery_mode == APIC_DM_LOWEST || + irq->msi_redir_hint); +} + +static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); +bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq, + struct kvm_vcpu **dest_vcpu); #endif diff --git a/kernel/arch/x86/kvm/mmu.c b/kernel/arch/x86/kvm/mmu.c index 554e877e0..8eb8a934b 100644 --- a/kernel/arch/x86/kvm/mmu.c +++ b/kernel/arch/x86/kvm/mmu.c @@ -223,15 +223,15 @@ static unsigned int get_mmio_spte_generation(u64 spte) return gen; } -static unsigned int kvm_current_mmio_generation(struct kvm *kvm) +static unsigned int kvm_current_mmio_generation(struct kvm_vcpu *vcpu) { - return kvm_memslots(kvm)->generation & MMIO_GEN_MASK; + return kvm_vcpu_memslots(vcpu)->generation & MMIO_GEN_MASK; } -static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn, +static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned access) { - unsigned int gen = kvm_current_mmio_generation(kvm); + unsigned int gen = kvm_current_mmio_generation(vcpu); u64 mask = generation_mmio_spte_mask(gen); access &= ACC_WRITE_MASK | ACC_USER_MASK; @@ -258,22 +258,22 @@ static unsigned get_mmio_spte_access(u64 spte) return (spte & ~mask) & ~PAGE_MASK; } -static bool set_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, +static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, pfn_t pfn, unsigned access) { if (unlikely(is_noslot_pfn(pfn))) { - mark_mmio_spte(kvm, sptep, gfn, access); + mark_mmio_spte(vcpu, sptep, gfn, access); return true; } return false; } -static bool check_mmio_spte(struct kvm *kvm, u64 spte) +static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) { unsigned int kvm_gen, spte_gen; - kvm_gen = kvm_current_mmio_generation(kvm); + kvm_gen = kvm_current_mmio_generation(vcpu); spte_gen = get_mmio_spte_generation(spte); trace_check_mmio_spte(spte, kvm_gen, spte_gen); @@ -781,30 +781,36 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } -static void account_shadowed(struct kvm *kvm, gfn_t gfn) +static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; + gfn_t gfn; int i; - slot = gfn_to_memslot(kvm, gfn); - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + gfn = sp->gfn; + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count += 1; } kvm->arch.indirect_shadow_pages++; } -static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) +static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; + gfn_t gfn; int i; - slot = gfn_to_memslot(kvm, gfn); - for (i = PT_DIRECTORY_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + gfn = sp->gfn; + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); + for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); linfo->write_count -= 1; WARN_ON(linfo->write_count < 0); @@ -812,14 +818,11 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn) kvm->arch.indirect_shadow_pages--; } -static int has_wrprotected_page(struct kvm *kvm, - gfn_t gfn, - int level) +static int __has_wrprotected_page(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *slot; struct kvm_lpage_info *linfo; - slot = gfn_to_memslot(kvm, gfn); if (slot) { linfo = lpage_info_slot(gfn, slot, level); return linfo->write_count; @@ -828,6 +831,14 @@ static int has_wrprotected_page(struct kvm *kvm, return 1; } +static int has_wrprotected_page(struct kvm_vcpu *vcpu, gfn_t gfn, int level) +{ + struct kvm_memory_slot *slot; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + return __has_wrprotected_page(gfn, level, slot); +} + static int host_mapping_level(struct kvm *kvm, gfn_t gfn) { unsigned long page_size; @@ -835,8 +846,7 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) page_size = kvm_host_page_size(kvm, gfn); - for (i = PT_PAGE_TABLE_LEVEL; - i < (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES); ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { if (page_size >= KVM_HPAGE_SIZE(i)) ret = i; else @@ -846,28 +856,43 @@ static int host_mapping_level(struct kvm *kvm, gfn_t gfn) return ret; } +static inline bool memslot_valid_for_gpte(struct kvm_memory_slot *slot, + bool no_dirty_log) +{ + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return false; + if (no_dirty_log && slot->dirty_bitmap) + return false; + + return true; +} + static struct kvm_memory_slot * gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { struct kvm_memory_slot *slot; - slot = gfn_to_memslot(vcpu->kvm, gfn); - if (!slot || slot->flags & KVM_MEMSLOT_INVALID || - (no_dirty_log && slot->dirty_bitmap)) + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + if (!memslot_valid_for_gpte(slot, no_dirty_log)) slot = NULL; return slot; } -static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn) -{ - return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true); -} - -static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) +static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, + bool *force_pt_level) { int host_level, level, max_level; + struct kvm_memory_slot *slot; + + if (unlikely(*force_pt_level)) + return PT_PAGE_TABLE_LEVEL; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, large_gfn); + *force_pt_level = !memslot_valid_for_gpte(slot, true); + if (unlikely(*force_pt_level)) + return PT_PAGE_TABLE_LEVEL; host_level = host_mapping_level(vcpu->kvm, large_gfn); @@ -877,7 +902,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn) max_level = min(kvm_x86_ops->get_lpage_level(), host_level); for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level) - if (has_wrprotected_page(vcpu->kvm, large_gfn, level)) + if (__has_wrprotected_page(large_gfn, level, slot)) break; return level - 1; @@ -1019,12 +1044,14 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, /* * Take gfn and return the reverse mapping to it. */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) +static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) { + struct kvm_memslots *slots; struct kvm_memory_slot *slot; - slot = gfn_to_memslot(kvm, gfn); - return __gfn_to_rmap(gfn, level, slot); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, gfn); + return __gfn_to_rmap(gfn, sp->role.level, slot); } static bool rmap_can_add(struct kvm_vcpu *vcpu) @@ -1042,7 +1069,7 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); return pte_list_add(vcpu, spte, rmapp); } @@ -1054,7 +1081,7 @@ static void rmap_remove(struct kvm *kvm, u64 *spte) sp = page_header(__pa(spte)); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmapp = gfn_to_rmap(kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(kvm, gfn, sp); pte_list_remove(spte, rmapp); } @@ -1119,6 +1146,11 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) return NULL; } +#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \ + for (_spte_ = rmap_get_first(*_rmap_, _iter_); \ + _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \ + _spte_ = rmap_get_next(_iter_)) + static void drop_spte(struct kvm *kvm, u64 *sptep) { if (mmu_spte_clear_track_bits(sptep)) @@ -1182,12 +1214,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_write_protect(kvm, sptep, pt_protect); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1209,12 +1237,8 @@ static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp) struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_clear_dirty(kvm, sptep); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1236,12 +1260,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp) struct rmap_iterator iter; bool flush = false; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - + for_each_rmap_spte(rmapp, &iter, sptep) flush |= spte_set_dirty(kvm, sptep); - sptep = rmap_get_next(&iter); - } return flush; } @@ -1319,42 +1339,45 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } -static bool rmap_write_protect(struct kvm *kvm, u64 gfn) +static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; unsigned long *rmapp; int i; bool write_protected = false; - slot = gfn_to_memslot(kvm, gfn); + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { + for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(kvm, rmapp, true); + write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true); } return write_protected; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, - struct kvm_memory_slot *slot, gfn_t gfn, int level, - unsigned long data) +static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) { u64 *sptep; struct rmap_iterator iter; - int need_tlb_flush = 0; + bool flush = false; while ((sptep = rmap_get_first(*rmapp, &iter))) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n", - sptep, *sptep, gfn, level); + rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); drop_spte(kvm, sptep); - need_tlb_flush = 1; + flush = true; } - return need_tlb_flush; + return flush; +} + +static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, + struct kvm_memory_slot *slot, gfn_t gfn, int level, + unsigned long data) +{ + return kvm_zap_rmapp(kvm, rmapp); } static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, @@ -1371,8 +1394,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, WARN_ON(pte_huge(*ptep)); new_pfn = pte_pfn(*ptep); - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!is_shadow_present_pte(*sptep)); +restart: + for_each_rmap_spte(rmapp, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); @@ -1380,7 +1403,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, if (pte_write(*ptep)) { drop_spte(kvm, sptep); - sptep = rmap_get_first(*rmapp, &iter); + goto restart; } else { new_spte = *sptep & ~PT64_BASE_ADDR_MASK; new_spte |= (u64)new_pfn << PAGE_SHIFT; @@ -1391,7 +1414,6 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, mmu_spte_clear_track_bits(sptep); mmu_spte_set(sptep, new_spte); - sptep = rmap_get_next(&iter); } } @@ -1401,6 +1423,74 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, return 0; } +struct slot_rmap_walk_iterator { + /* input fields. */ + struct kvm_memory_slot *slot; + gfn_t start_gfn; + gfn_t end_gfn; + int start_level; + int end_level; + + /* output fields. */ + gfn_t gfn; + unsigned long *rmap; + int level; + + /* private field. */ + unsigned long *end_rmap; +}; + +static void +rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) +{ + iterator->level = level; + iterator->gfn = iterator->start_gfn; + iterator->rmap = __gfn_to_rmap(iterator->gfn, level, iterator->slot); + iterator->end_rmap = __gfn_to_rmap(iterator->end_gfn, level, + iterator->slot); +} + +static void +slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, + struct kvm_memory_slot *slot, int start_level, + int end_level, gfn_t start_gfn, gfn_t end_gfn) +{ + iterator->slot = slot; + iterator->start_level = start_level; + iterator->end_level = end_level; + iterator->start_gfn = start_gfn; + iterator->end_gfn = end_gfn; + + rmap_walk_init_level(iterator, iterator->start_level); +} + +static bool slot_rmap_walk_okay(struct slot_rmap_walk_iterator *iterator) +{ + return !!iterator->rmap; +} + +static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) +{ + if (++iterator->rmap <= iterator->end_rmap) { + iterator->gfn += (1UL << KVM_HPAGE_GFN_SHIFT(iterator->level)); + return; + } + + if (++iterator->level > iterator->end_level) { + iterator->rmap = NULL; + return; + } + + rmap_walk_init_level(iterator, iterator->level); +} + +#define for_each_slot_rmap_range(_slot_, _start_level_, _end_level_, \ + _start_gfn, _end_gfn, _iter_) \ + for (slot_rmap_walk_init(_iter_, _slot_, _start_level_, \ + _end_level_, _start_gfn, _end_gfn); \ + slot_rmap_walk_okay(_iter_); \ + slot_rmap_walk_next(_iter_)) + static int kvm_handle_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, @@ -1412,48 +1502,36 @@ static int kvm_handle_hva_range(struct kvm *kvm, int level, unsigned long data)) { - int j; - int ret = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + struct slot_rmap_walk_iterator iterator; + int ret = 0; + int i; - slots = kvm_memslots(kvm); - - kvm_for_each_memslot(memslot, slots) { - unsigned long hva_start, hva_end; - gfn_t gfn_start, gfn_end; - - hva_start = max(start, memslot->userspace_addr); - hva_end = min(end, memslot->userspace_addr + - (memslot->npages << PAGE_SHIFT)); - if (hva_start >= hva_end) - continue; - /* - * {gfn(page) | page intersects with [hva_start, hva_end)} = - * {gfn_start, gfn_start+1, ..., gfn_end-1}. - */ - gfn_start = hva_to_gfn_memslot(hva_start, memslot); - gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); - - for (j = PT_PAGE_TABLE_LEVEL; - j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) { - unsigned long idx, idx_end; - unsigned long *rmapp; - gfn_t gfn = gfn_start; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + unsigned long hva_start, hva_end; + gfn_t gfn_start, gfn_end; + hva_start = max(start, memslot->userspace_addr); + hva_end = min(end, memslot->userspace_addr + + (memslot->npages << PAGE_SHIFT)); + if (hva_start >= hva_end) + continue; /* - * {idx(page_j) | page_j intersects with - * [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}. + * {gfn(page) | page intersects with [hva_start, hva_end)} = + * {gfn_start, gfn_start+1, ..., gfn_end-1}. */ - idx = gfn_to_index(gfn_start, memslot->base_gfn, j); - idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j); - - rmapp = __gfn_to_rmap(gfn_start, j, memslot); - - for (; idx <= idx_end; - ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j))) - ret |= handler(kvm, rmapp++, memslot, - gfn, j, data); + gfn_start = hva_to_gfn_memslot(hva_start, memslot); + gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot); + + for_each_slot_rmap_range(memslot, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, + gfn_start, gfn_end - 1, + &iterator) + ret |= handler(kvm, iterator.rmap, memslot, + iterator.gfn, iterator.level, data); } } @@ -1495,16 +1573,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, BUG_ON(!shadow_accessed_mask); - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { - BUG_ON(!is_shadow_present_pte(*sptep)); - + for_each_rmap_spte(rmapp, &iter, sptep) if (*sptep & shadow_accessed_mask) { young = 1; clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } - } + trace_kvm_age_page(gfn, level, slot, young); return young; } @@ -1525,15 +1600,11 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { - BUG_ON(!is_shadow_present_pte(*sptep)); - + for_each_rmap_spte(rmapp, &iter, sptep) if (*sptep & shadow_accessed_mask) { young = 1; break; } - } out: return young; } @@ -1547,7 +1618,7 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) sp = page_header(__pa(spte)); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level); + rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0); kvm_flush_remote_tlbs(vcpu->kvm); @@ -1967,7 +2038,7 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, bool protected = false; for_each_sp(pages, sp, parents, i) - protected |= rmap_write_protect(vcpu->kvm, sp->gfn); + protected |= rmap_write_protect(vcpu, sp->gfn); if (protected) kvm_flush_remote_tlbs(vcpu->kvm); @@ -2065,12 +2136,12 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, hlist_add_head(&sp->hash_link, &vcpu->kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)]); if (!direct) { - if (rmap_write_protect(vcpu->kvm, gfn)) + if (rmap_write_protect(vcpu, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); if (level > PT_PAGE_TABLE_LEVEL && need_sync) kvm_sync_pages(vcpu, gfn); - account_shadowed(vcpu->kvm, gfn); + account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; init_shadow_page_table(sp); @@ -2251,7 +2322,7 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, kvm_mmu_unlink_parents(kvm, sp); if (!sp->role.invalid && !sp->role.direct) - unaccount_shadowed(kvm, sp->gfn); + unaccount_shadowed(kvm, sp); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); @@ -2363,111 +2434,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); -/* - * The function is based on mtrr_type_lookup() in - * arch/x86/kernel/cpu/mtrr/generic.c - */ -static int get_mtrr_type(struct mtrr_state_type *mtrr_state, - u64 start, u64 end) -{ - int i; - u64 base, mask; - u8 prev_match, curr_match; - int num_var_ranges = KVM_NR_VAR_MTRR; - - if (!mtrr_state->enabled) - return 0xFF; - - /* Make end inclusive end, instead of exclusive */ - end--; - - /* Look in fixed ranges. Just return the type as per start */ - if (mtrr_state->have_fixed && (start < 0x100000)) { - int idx; - - if (start < 0x80000) { - idx = 0; - idx += (start >> 16); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0xC0000) { - idx = 1 * 8; - idx += ((start - 0x80000) >> 14); - return mtrr_state->fixed_ranges[idx]; - } else if (start < 0x1000000) { - idx = 3 * 8; - idx += ((start - 0xC0000) >> 12); - return mtrr_state->fixed_ranges[idx]; - } - } - - /* - * Look in variable ranges - * Look of multiple ranges matching this address and pick type - * as per MTRR precedence - */ - if (!(mtrr_state->enabled & 2)) - return mtrr_state->def_type; - - prev_match = 0xFF; - for (i = 0; i < num_var_ranges; ++i) { - unsigned short start_state, end_state; - - if (!(mtrr_state->var_ranges[i].mask_lo & (1 << 11))) - continue; - - base = (((u64)mtrr_state->var_ranges[i].base_hi) << 32) + - (mtrr_state->var_ranges[i].base_lo & PAGE_MASK); - mask = (((u64)mtrr_state->var_ranges[i].mask_hi) << 32) + - (mtrr_state->var_ranges[i].mask_lo & PAGE_MASK); - - start_state = ((start & mask) == (base & mask)); - end_state = ((end & mask) == (base & mask)); - if (start_state != end_state) - return 0xFE; - - if ((start & mask) != (base & mask)) - continue; - - curr_match = mtrr_state->var_ranges[i].base_lo & 0xff; - if (prev_match == 0xFF) { - prev_match = curr_match; - continue; - } - - if (prev_match == MTRR_TYPE_UNCACHABLE || - curr_match == MTRR_TYPE_UNCACHABLE) - return MTRR_TYPE_UNCACHABLE; - - if ((prev_match == MTRR_TYPE_WRBACK && - curr_match == MTRR_TYPE_WRTHROUGH) || - (prev_match == MTRR_TYPE_WRTHROUGH && - curr_match == MTRR_TYPE_WRBACK)) { - prev_match = MTRR_TYPE_WRTHROUGH; - curr_match = MTRR_TYPE_WRTHROUGH; - } - - if (prev_match != curr_match) - return MTRR_TYPE_UNCACHABLE; - } - - if (prev_match != 0xFF) - return prev_match; - - return mtrr_state->def_type; -} - -u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) -{ - u8 mtrr; - - mtrr = get_mtrr_type(&vcpu->arch.mtrr_state, gfn << PAGE_SHIFT, - (gfn << PAGE_SHIFT) + PAGE_SIZE); - if (mtrr == 0xfe || mtrr == 0xff) - mtrr = MTRR_TYPE_WRBACK; - return mtrr; -} -EXPORT_SYMBOL_GPL(kvm_get_guest_memory_type); - static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { trace_kvm_mmu_unsync_page(sp); @@ -2510,6 +2476,14 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 0; } +static bool kvm_is_mmio_pfn(pfn_t pfn) +{ + if (pfn_valid(pfn)) + return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)); + + return true; +} + static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, int level, gfn_t gfn, pfn_t pfn, bool speculative, @@ -2518,7 +2492,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte; int ret = 0; - if (set_mmio_spte(vcpu->kvm, sptep, gfn, pfn, pte_access)) + if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access)) return 0; spte = PT_PRESENT_MASK; @@ -2537,7 +2511,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= PT_PAGE_SIZE_MASK; if (tdp_enabled) spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn, - kvm_is_reserved_pfn(pfn)); + kvm_is_mmio_pfn(pfn)); if (host_writable) spte |= SPTE_HOST_WRITEABLE; @@ -2555,7 +2529,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, * be fixed if guest refault. */ if (level > PT_PAGE_TABLE_LEVEL && - has_wrprotected_page(vcpu->kvm, gfn, level)) + has_wrprotected_page(vcpu, gfn, level)) goto done; spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE; @@ -2579,7 +2553,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } if (pte_access & ACC_WRITE_MASK) { - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); spte |= shadow_dirty_mask; } @@ -2669,15 +2643,17 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, u64 *start, u64 *end) { struct page *pages[PTE_PREFETCH_NUM]; + struct kvm_memory_slot *slot; unsigned access = sp->role.access; int i, ret; gfn_t gfn; gfn = kvm_mmu_page_get_gfn(sp, start - sp->spt); - if (!gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK)) + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, access & ACC_WRITE_MASK); + if (!slot) return -1; - ret = gfn_to_page_many_atomic(vcpu->kvm, gfn, pages, end - start); + ret = gfn_to_page_many_atomic(slot, gfn, pages, end - start); if (ret <= 0) return -1; @@ -2795,7 +2771,7 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn) return 1; if (pfn == KVM_PFN_ERR_HWPOISON) { - kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current); + kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); return 0; } @@ -2818,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu, if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL && PageTransCompound(pfn_to_page(pfn)) && - !has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) { + !has_wrprotected_page(vcpu, gfn, PT_DIRECTORY_LEVEL)) { unsigned long mask; /* * mmu_notifier_retry was successful and we hold the @@ -2910,7 +2886,7 @@ fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * Compare with set_spte where instead shadow_dirty_mask is set. */ if (cmpxchg64(sptep, spte, spte | PT_WRITABLE_MASK) == spte) - mark_page_dirty(vcpu->kvm, gfn); + kvm_vcpu_mark_page_dirty(vcpu, gfn); return true; } @@ -3006,14 +2982,13 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, { int r; int level; - int force_pt_level; + bool force_pt_level = false; pfn_t pfn; unsigned long mmu_seq; bool map_writable, write = error_code & PFERR_WRITE_MASK; - force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { - level = mapping_level(vcpu, gfn); /* * This path builds a PAE pagetable - so we can map * 2mb pages at maximum. Therefore check if the level @@ -3023,8 +2998,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, level = PT_DIRECTORY_LEVEL; gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); - } else - level = PT_PAGE_TABLE_LEVEL; + } if (fast_page_fault(vcpu, v, level, error_code)) return 0; @@ -3312,6 +3286,25 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr, return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception); } +static bool +__is_rsvd_bits_set(struct rsvd_bits_validate *rsvd_check, u64 pte, int level) +{ + int bit7 = (pte >> 7) & 1, low6 = pte & 0x3f; + + return (pte & rsvd_check->rsvd_bits_mask[bit7][level-1]) | + ((rsvd_check->bad_mt_xwr & (1ull << low6)) != 0); +} + +static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) +{ + return __is_rsvd_bits_set(&mmu->guest_rsvd_check, gpte, level); +} + +static bool is_shadow_zero_bits_set(struct kvm_mmu *mmu, u64 spte, int level) +{ + return __is_rsvd_bits_set(&mmu->shadow_zero_check, spte, level); +} + static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) { if (direct) @@ -3320,37 +3313,69 @@ static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct) return vcpu_match_mmio_gva(vcpu, addr); } -static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) +/* return true if reserved bit is detected on spte. */ +static bool +walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { struct kvm_shadow_walk_iterator iterator; - u64 spte = 0ull; + u64 sptes[PT64_ROOT_LEVEL], spte = 0ull; + int root, leaf; + bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return spte; + goto exit; walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) + + for (shadow_walk_init(&iterator, vcpu, addr), + leaf = root = iterator.level; + shadow_walk_okay(&iterator); + __shadow_walk_next(&iterator, spte)) { + spte = mmu_spte_get_lockless(iterator.sptep); + + sptes[leaf - 1] = spte; + leaf--; + if (!is_shadow_present_pte(spte)) break; + + reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte, + iterator.level); + } + walk_shadow_page_lockless_end(vcpu); - return spte; + if (reserved) { + pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", + __func__, addr); + while (root > leaf) { + pr_err("------ spte 0x%llx level %d.\n", + sptes[root - 1], root); + root--; + } + } +exit: + *sptep = spte; + return reserved; } -int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) +int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) { u64 spte; + bool reserved; if (quickly_check_mmio_pf(vcpu, addr, direct)) return RET_MMIO_PF_EMULATE; - spte = walk_shadow_page_get_mmio_spte(vcpu, addr); + reserved = walk_shadow_page_get_mmio_spte(vcpu, addr, &spte); + if (WARN_ON(reserved)) + return RET_MMIO_PF_BUG; if (is_mmio_spte(spte)) { gfn_t gfn = get_mmio_spte_gfn(spte); unsigned access = get_mmio_spte_access(spte); - if (!check_mmio_spte(vcpu->kvm, spte)) + if (!check_mmio_spte(vcpu, spte)) return RET_MMIO_PF_INVALID; if (direct) @@ -3367,17 +3392,7 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct) */ return RET_MMIO_PF_RETRY; } -EXPORT_SYMBOL_GPL(handle_mmio_page_fault_common); - -static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, - u32 error_code, bool direct) -{ - int ret; - - ret = handle_mmio_page_fault_common(vcpu, addr, direct); - WARN_ON(ret == RET_MMIO_PF_BUG); - return ret; -} +EXPORT_SYMBOL_GPL(handle_mmio_page_fault); static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, bool prefault) @@ -3388,7 +3403,7 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva, pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gva, error_code, true); + r = handle_mmio_page_fault(vcpu, gva, true); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -3415,12 +3430,12 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu.direct_map; arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch); + return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } static bool can_do_async_pf(struct kvm_vcpu *vcpu) { - if (unlikely(!irqchip_in_kernel(vcpu->kvm) || + if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu))) return false; @@ -3430,10 +3445,12 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu) static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, gva_t gva, pfn_t *pfn, bool write, bool *writable) { + struct kvm_memory_slot *slot; bool async; - *pfn = gfn_to_pfn_async(vcpu->kvm, gfn, &async, write, writable); - + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + async = false; + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); if (!async) return false; /* *pfn has correct page already */ @@ -3447,18 +3464,27 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write, writable); - + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); return false; } +static bool +check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level) +{ + int page_num = KVM_PAGES_PER_HPAGE(level); + + gfn &= ~(page_num - 1); + + return kvm_mtrr_check_gfn_range_consistency(vcpu, gfn, page_num); +} + static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, bool prefault) { pfn_t pfn; int r; int level; - int force_pt_level; + bool force_pt_level; gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; int write = error_code & PFERR_WRITE_MASK; @@ -3467,7 +3493,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, gpa, error_code, true); + r = handle_mmio_page_fault(vcpu, gpa, true); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -3477,12 +3503,15 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, if (r) return r; - force_pt_level = mapping_level_dirty_bitmap(vcpu, gfn); + force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn, + PT_DIRECTORY_LEVEL); + level = mapping_level(vcpu, gfn, &force_pt_level); if (likely(!force_pt_level)) { - level = mapping_level(vcpu, gfn); + if (level > PT_DIRECTORY_LEVEL && + !check_hugepage_cache_consistency(vcpu, gfn, level)) + level = PT_DIRECTORY_LEVEL; gfn &= ~(KVM_PAGES_PER_HPAGE(level) - 1); - } else - level = PT_PAGE_TABLE_LEVEL; + } if (fast_page_fault(vcpu, gpa, level, error_code)) return 0; @@ -3545,7 +3574,7 @@ static void inject_page_fault(struct kvm_vcpu *vcpu, vcpu->arch.mmu.inject_page_fault(vcpu, fault); } -static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, +static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned access, int *nr_present) { if (unlikely(is_mmio_spte(*sptep))) { @@ -3555,7 +3584,7 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, } (*nr_present)++; - mark_mmio_spte(kvm, sptep, gfn, access); + mark_mmio_spte(vcpu, sptep, gfn, access); return true; } @@ -3584,111 +3613,197 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp #include "paging_tmpl.h" #undef PTTYPE -static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, - struct kvm_mmu *context) +static void +__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct rsvd_bits_validate *rsvd_check, + int maxphyaddr, int level, bool nx, bool gbpages, + bool pse, bool amd) { - int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; - context->bad_mt_xwr = 0; + rsvd_check->bad_mt_xwr = 0; - if (!context->nx) + if (!nx) exb_bit_rsvd = rsvd_bits(63, 63); - if (!guest_cpuid_has_gbpages(vcpu)) + if (!gbpages) gbpages_bit_rsvd = rsvd_bits(7, 7); /* * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for * leaf entries) on AMD CPUs only. */ - if (guest_cpuid_is_amd(vcpu)) + if (amd) nonleaf_bit8_rsvd = rsvd_bits(8, 8); - switch (context->root_level) { + switch (level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ - context->rsvd_bits_mask[0][1] = 0; - context->rsvd_bits_mask[0][0] = 0; - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[0][1] = 0; + rsvd_check->rsvd_bits_mask[0][0] = 0; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; - if (!is_pse(vcpu)) { - context->rsvd_bits_mask[1][1] = 0; + if (!pse) { + rsvd_check->rsvd_bits_mask[1][1] = 0; break; } if (is_cpuid_PSE36()) /* 36bits PSE 4MB page */ - context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(17, 21); else /* 32 bits PSE 4MB page */ - context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); break; case PT32E_ROOT_LEVEL: - context->rsvd_bits_mask[0][2] = + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 63) | rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ - context->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PDE */ - context->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PTE */ - context->rsvd_bits_mask[1][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; break; case PT64_ROOT_LEVEL: - context->rsvd_bits_mask[0][3] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | + nonleaf_bit8_rsvd | rsvd_bits(7, 7) | + rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | + nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); - context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | + rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[1][3] = + rsvd_check->rsvd_bits_mask[0][3]; + rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 29); - context->rsvd_bits_mask[1][1] = exb_bit_rsvd | + rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 20); /* large page */ - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + rsvd_check->rsvd_bits_mask[1][0] = + rsvd_check->rsvd_bits_mask[0][0]; break; } } -static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, - struct kvm_mmu *context, bool execonly) +static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) { - int maxphyaddr = cpuid_maxphyaddr(vcpu); - int pte; + __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, + cpuid_maxphyaddr(vcpu), context->root_level, + context->nx, guest_cpuid_has_gbpages(vcpu), + is_pse(vcpu), guest_cpuid_is_amd(vcpu)); +} + +static void +__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, + int maxphyaddr, bool execonly) +{ + u64 bad_mt_xwr; - context->rsvd_bits_mask[0][3] = + rsvd_check->rsvd_bits_mask[0][3] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - context->rsvd_bits_mask[0][2] = + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - context->rsvd_bits_mask[0][1] = + rsvd_check->rsvd_bits_mask[0][1] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); /* large page */ - context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; - context->rsvd_bits_mask[1][2] = + rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; + rsvd_check->rsvd_bits_mask[1][2] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); - context->rsvd_bits_mask[1][1] = + rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); - context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; - - for (pte = 0; pte < 64; pte++) { - int rwx_bits = pte & 7; - int mt = pte >> 3; - if (mt == 0x2 || mt == 0x3 || mt == 0x7 || - rwx_bits == 0x2 || rwx_bits == 0x6 || - (rwx_bits == 0x4 && !execonly)) - context->bad_mt_xwr |= (1ull << pte); + rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; + + bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ + bad_mt_xwr |= 0xFFull << (3 * 8); /* bits 3..5 must not be 3 */ + bad_mt_xwr |= 0xFFull << (7 * 8); /* bits 3..5 must not be 7 */ + bad_mt_xwr |= REPEAT_BYTE(1ull << 2); /* bits 0..2 must not be 010 */ + bad_mt_xwr |= REPEAT_BYTE(1ull << 6); /* bits 0..2 must not be 110 */ + if (!execonly) { + /* bits 0..2 must not be 100 unless VMX capabilities allow it */ + bad_mt_xwr |= REPEAT_BYTE(1ull << 4); } + rsvd_check->bad_mt_xwr = bad_mt_xwr; +} + +static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, + cpuid_maxphyaddr(vcpu), execonly); +} + +/* + * the page table on host is the shadow page table for the page + * table in guest or amd nested guest, its mmu features completely + * follow the features in guest. + */ +void +reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) +{ + bool uses_nx = context->nx || context->base_role.smep_andnot_wp; + + /* + * Passing "true" to the last argument is okay; it adds a check + * on bit 8 of the SPTEs which KVM doesn't use anyway. + */ + __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + context->shadow_root_level, uses_nx, + guest_cpuid_has_gbpages(vcpu), is_pse(vcpu), + true); +} +EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask); + +static inline bool boot_cpu_is_amd(void) +{ + WARN_ON_ONCE(!tdp_enabled); + return shadow_x_mask == 0; +} + +/* + * the direct page table on host, use as much mmu features as + * possible, however, kvm currently does not do execution-protection. + */ +static void +reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context) +{ + if (boot_cpu_is_amd()) + __reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + context->shadow_root_level, false, + cpu_has_gbpages, true, true); + else + __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, + false); + +} + +/* + * as the comments in reset_shadow_zero_bits_mask() except it + * is the shadow page table for intel nested guest. + */ +static void +reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, + boot_cpu_data.x86_phys_bits, execonly); } static void update_permission_bitmask(struct kvm_vcpu *vcpu, @@ -3833,6 +3948,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = &vcpu->arch.mmu; context->base_role.word = 0; + context->base_role.smm = is_smm(vcpu); context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; @@ -3868,6 +3984,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); + reset_tdp_shadow_zero_bits_mask(vcpu, context); } void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) @@ -3894,6 +4011,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) = smep && !is_write_protection(vcpu); context->base_role.smap_andnot_wp = smap && !is_write_protection(vcpu); + context->base_role.smm = is_smm(vcpu); + reset_shadow_zero_bits_mask(vcpu, context); } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); @@ -3917,6 +4036,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly) update_permission_bitmask(vcpu, context, true); reset_rsvds_bits_mask_ept(vcpu, context, execonly); + reset_ept_shadow_zero_bits_mask(vcpu, context, execonly); } EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); @@ -4065,7 +4185,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; - r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8); + r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8); if (r) gentry = 0; new = (const u8 *)&gentry; @@ -4177,6 +4297,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.nxe = 1; mask.smep_andnot_wp = 1; mask.smap_andnot_wp = 1; + mask.smm = 1; /* * If we don't have indirect shadow pages, it means no page is @@ -4375,36 +4496,115 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) init_kvm_mmu(vcpu); } -void kvm_mmu_slot_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) +/* The return value indicates if tlb flush on all vcpus is needed. */ +typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap); + +/* The caller should hold mmu-lock before calling this function. */ +static bool +slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, bool lock_flush_tlb) { - gfn_t last_gfn; - int i; + struct slot_rmap_walk_iterator iterator; bool flush = false; - last_gfn = memslot->base_gfn + memslot->npages - 1; + for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + end_gfn, &iterator) { + if (iterator.rmap) + flush |= fn(kvm, iterator.rmap); - spin_lock(&kvm->mmu_lock); + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush && lock_flush_tlb) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; + return flush; +} + +static bool +slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, int start_level, int end_level, + bool lock_flush_tlb) +{ + return slot_handle_level_range(kvm, memslot, fn, start_level, + end_level, memslot->base_gfn, + memslot->base_gfn + memslot->npages - 1, + lock_flush_tlb); +} + +static bool +slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static bool +slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL + 1, + PT_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); +} + +static bool +slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, + slot_level_handler fn, bool lock_flush_tlb) +{ + return slot_handle_level(kvm, memslot, fn, PT_PAGE_TABLE_LEVEL, + PT_PAGE_TABLE_LEVEL, lock_flush_tlb); +} - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int i; - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_write_protect(kvm, rmapp, - false); + spin_lock(&kvm->mmu_lock); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(memslot, slots) { + gfn_t start, end; + + start = max(gfn_start, memslot->base_gfn); + end = min(gfn_end, memslot->base_gfn + memslot->npages); + if (start >= end) + continue; - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); + slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, + PT_PAGE_TABLE_LEVEL, PT_MAX_HUGEPAGE_LEVEL, + start, end - 1, true); } } spin_unlock(&kvm->mmu_lock); +} + +static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) +{ + return __rmap_write_protect(kvm, rmapp, false); +} + +void kvm_mmu_slot_remove_write_access(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + bool flush; + + spin_lock(&kvm->mmu_lock); + flush = slot_handle_all_level(kvm, memslot, slot_rmap_write_protect, + false); + spin_unlock(&kvm->mmu_lock); /* * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() @@ -4437,9 +4637,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, pfn_t pfn; struct kvm_mmu_page *sp; - for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); - +restart: + for_each_rmap_spte(rmapp, &iter, sptep) { sp = page_header(__pa(sptep)); pfn = spte_to_pfn(*sptep); @@ -4454,71 +4653,31 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, !kvm_is_reserved_pfn(pfn) && PageTransCompound(pfn_to_page(pfn))) { drop_spte(kvm, sptep); - sptep = rmap_get_first(*rmapp, &iter); need_tlb_flush = 1; - } else - sptep = rmap_get_next(&iter); + goto restart; + } } return need_tlb_flush; } void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, - struct kvm_memory_slot *memslot) + const struct kvm_memory_slot *memslot) { - bool flush = false; - unsigned long *rmapp; - unsigned long last_index, index; - + /* FIXME: const-ify all uses of struct kvm_memory_slot. */ spin_lock(&kvm->mmu_lock); - - rmapp = memslot->arch.rmap[0]; - last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1, - memslot->base_gfn, PT_PAGE_TABLE_LEVEL); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - if (flush) { - kvm_flush_remote_tlbs(kvm); - flush = false; - } - cond_resched_lock(&kvm->mmu_lock); - } - } - - if (flush) - kvm_flush_remote_tlbs(kvm); - + slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot, + kvm_mmu_zap_collapsible_spte, true); spin_unlock(&kvm->mmu_lock); } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - unsigned long *rmapp; - unsigned long last_index, index; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - rmapp = memslot->arch.rmap[PT_PAGE_TABLE_LEVEL - 1]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, - PT_PAGE_TABLE_LEVEL); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_clear_dirty(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - + flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); spin_unlock(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); @@ -4537,31 +4696,11 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - for (i = PT_PAGE_TABLE_LEVEL + 1; /* skip rmap for 4K page */ - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_write_protect(kvm, rmapp, - false); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } + flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, + false); spin_unlock(&kvm->mmu_lock); /* see kvm_mmu_slot_remove_write_access */ @@ -4575,31 +4714,10 @@ EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); void kvm_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { - gfn_t last_gfn; - int i; - bool flush = false; - - last_gfn = memslot->base_gfn + memslot->npages - 1; + bool flush; spin_lock(&kvm->mmu_lock); - - for (i = PT_PAGE_TABLE_LEVEL; - i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - unsigned long *rmapp; - unsigned long last_index, index; - - rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL]; - last_index = gfn_to_index(last_gfn, memslot->base_gfn, i); - - for (index = 0; index <= last_index; ++index, ++rmapp) { - if (*rmapp) - flush |= __rmap_set_dirty(kvm, rmapp); - - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) - cond_resched_lock(&kvm->mmu_lock); - } - } - + flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); spin_unlock(&kvm->mmu_lock); lockdep_assert_held(&kvm->slots_lock); @@ -4696,13 +4814,13 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages)); } -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots) { /* * The very rare case: if the generation-number is round, * zap all shadow pages. */ - if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { + if (unlikely((slots->generation & MMIO_GEN_MASK) == 0)) { printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } @@ -4824,41 +4942,22 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) unsigned int nr_pages = 0; struct kvm_memslots *slots; struct kvm_memory_slot *memslot; + int i; - slots = kvm_memslots(kvm); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) - nr_pages += memslot->npages; + kvm_for_each_memslot(memslot, slots) + nr_pages += memslot->npages; + } nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, - (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); + (unsigned int) KVM_MIN_ALLOC_MMU_PAGES); return nr_mmu_pages; } -int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) -{ - struct kvm_shadow_walk_iterator iterator; - u64 spte; - int nr_sptes = 0; - - if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) - return nr_sptes; - - walk_shadow_page_lockless_begin(vcpu); - for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { - sptes[iterator.level-1] = spte; - nr_sptes++; - if (!is_shadow_present_pte(spte)) - break; - } - walk_shadow_page_lockless_end(vcpu); - - return nr_sptes; -} -EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy); - void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); diff --git a/kernel/arch/x86/kvm/mmu.h b/kernel/arch/x86/kvm/mmu.h index 0ada65ecd..55ffb7b0f 100644 --- a/kernel/arch/x86/kvm/mmu.h +++ b/kernel/arch/x86/kvm/mmu.h @@ -43,23 +43,26 @@ #define PT_PDPE_LEVEL 3 #define PT_DIRECTORY_LEVEL 2 #define PT_PAGE_TABLE_LEVEL 1 +#define PT_MAX_HUGEPAGE_LEVEL (PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES - 1) static inline u64 rsvd_bits(int s, int e) { return ((1ULL << (e - s + 1)) - 1) << s; } -int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); +void +reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); + /* - * Return values of handle_mmio_page_fault_common: + * Return values of handle_mmio_page_fault: * RET_MMIO_PF_EMULATE: it is a real mmio page fault, emulate the instruction * directly. * RET_MMIO_PF_INVALID: invalid spte is detected then let the real page * fault path update the mmio spte. * RET_MMIO_PF_RETRY: let CPU fault again on the address. - * RET_MMIO_PF_BUG: bug is detected. + * RET_MMIO_PF_BUG: a bug was detected (and a WARN was printed). */ enum { RET_MMIO_PF_EMULATE = 1, @@ -68,7 +71,7 @@ enum { RET_MMIO_PF_BUG = -1 }; -int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); +int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly); @@ -170,4 +173,5 @@ static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm); +void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); #endif diff --git a/kernel/arch/x86/kvm/mmu_audit.c b/kernel/arch/x86/kvm/mmu_audit.c index 9ade5cfb5..03d518e49 100644 --- a/kernel/arch/x86/kvm/mmu_audit.c +++ b/kernel/arch/x86/kvm/mmu_audit.c @@ -114,7 +114,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) return; gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt); - pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn); + pfn = kvm_vcpu_gfn_to_pfn_atomic(vcpu, gfn); if (is_error_pfn(pfn)) return; @@ -131,12 +131,16 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); unsigned long *rmapp; struct kvm_mmu_page *rev_sp; + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; gfn_t gfn; rev_sp = page_header(__pa(sptep)); gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt); - if (!gfn_to_memslot(kvm, gfn)) { + slots = kvm_memslots_for_spte_role(kvm, rev_sp->role); + slot = __gfn_to_memslot(slots, gfn); + if (!slot) { if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no memslot for gfn %llx\n", gfn); @@ -146,7 +150,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level); + rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot); if (!*rmapp) { if (!__ratelimit(&ratelimit_state)) return; @@ -191,19 +195,21 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) unsigned long *rmapp; u64 *sptep; struct rmap_iterator iter; + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; if (sp->role.direct || sp->unsync || sp->role.invalid) return; - rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL); + slots = kvm_memslots_for_spte_role(kvm, sp->role); + slot = __gfn_to_memslot(slots, sp->gfn); + rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); - for (sptep = rmap_get_first(*rmapp, &iter); sptep; - sptep = rmap_get_next(&iter)) { + for_each_rmap_spte(rmapp, &iter, sptep) if (is_writable_pte(*sptep)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); - } } static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -291,7 +297,7 @@ static int mmu_audit_set(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops audit_param_ops = { +static const struct kernel_param_ops audit_param_ops = { .set = mmu_audit_set, .get = param_get_bool, }; diff --git a/kernel/arch/x86/kvm/mmutrace.h b/kernel/arch/x86/kvm/mmutrace.h index ce463a9cc..5a24b846a 100644 --- a/kernel/arch/x86/kvm/mmutrace.h +++ b/kernel/arch/x86/kvm/mmutrace.h @@ -2,7 +2,7 @@ #define _TRACE_KVMMMU_H #include <linux/tracepoint.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvmmmu diff --git a/kernel/arch/x86/kvm/mtrr.c b/kernel/arch/x86/kvm/mtrr.c new file mode 100644 index 000000000..3f8c73211 --- /dev/null +++ b/kernel/arch/x86/kvm/mtrr.c @@ -0,0 +1,732 @@ +/* + * vMTRR implementation + * + * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. + * Copyright(C) 2015 Intel Corporation. + * + * Authors: + * Yaniv Kamay <yaniv@qumranet.com> + * Avi Kivity <avi@qumranet.com> + * Marcelo Tosatti <mtosatti@redhat.com> + * Paolo Bonzini <pbonzini@redhat.com> + * Xiao Guangrong <guangrong.xiao@linux.intel.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include <linux/kvm_host.h> +#include <asm/mtrr.h> + +#include "cpuid.h" +#include "mmu.h" + +#define IA32_MTRR_DEF_TYPE_E (1ULL << 11) +#define IA32_MTRR_DEF_TYPE_FE (1ULL << 10) +#define IA32_MTRR_DEF_TYPE_TYPE_MASK (0xff) + +static bool msr_mtrr_valid(unsigned msr) +{ + switch (msr) { + case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: + case MSR_MTRRfix64K_00000: + case MSR_MTRRfix16K_80000: + case MSR_MTRRfix16K_A0000: + case MSR_MTRRfix4K_C0000: + case MSR_MTRRfix4K_C8000: + case MSR_MTRRfix4K_D0000: + case MSR_MTRRfix4K_D8000: + case MSR_MTRRfix4K_E0000: + case MSR_MTRRfix4K_E8000: + case MSR_MTRRfix4K_F0000: + case MSR_MTRRfix4K_F8000: + case MSR_MTRRdefType: + case MSR_IA32_CR_PAT: + return true; + case 0x2f8: + return true; + } + return false; +} + +static bool valid_pat_type(unsigned t) +{ + return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ +} + +static bool valid_mtrr_type(unsigned t) +{ + return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ +} + +bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int i; + u64 mask; + + if (!msr_mtrr_valid(msr)) + return false; + + if (msr == MSR_IA32_CR_PAT) { + for (i = 0; i < 8; i++) + if (!valid_pat_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } else if (msr == MSR_MTRRdefType) { + if (data & ~0xcff) + return false; + return valid_mtrr_type(data & 0xff); + } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { + for (i = 0; i < 8 ; i++) + if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) + return false; + return true; + } + + /* variable MTRRs */ + WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); + + mask = (~0ULL) << cpuid_maxphyaddr(vcpu); + if ((msr & 1) == 0) { + /* MTRR base */ + if (!valid_mtrr_type(data & 0xff)) + return false; + mask |= 0xf00; + } else + /* MTRR mask */ + mask |= 0x7ff; + if (data & mask) { + kvm_inject_gp(vcpu, 0); + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_valid); + +static bool mtrr_is_enabled(struct kvm_mtrr *mtrr_state) +{ + return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_E); +} + +static bool fixed_mtrr_is_enabled(struct kvm_mtrr *mtrr_state) +{ + return !!(mtrr_state->deftype & IA32_MTRR_DEF_TYPE_FE); +} + +static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state) +{ + return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK; +} + +static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu) +{ + /* + * Intel SDM 11.11.2.2: all MTRRs are disabled when + * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC + * memory type is applied to all of physical memory. + * + * However, virtual machines can be run with CPUID such that + * there are no MTRRs. In that case, the firmware will never + * enable MTRRs and it is obviously undesirable to run the + * guest entirely with UC memory and we use WB. + */ + if (guest_cpuid_has_mtrr(vcpu)) + return MTRR_TYPE_UNCACHABLE; + else + return MTRR_TYPE_WRBACK; +} + +/* +* Three terms are used in the following code: +* - segment, it indicates the address segments covered by fixed MTRRs. +* - unit, it corresponds to the MSR entry in the segment. +* - range, a range is covered in one memory cache type. +*/ +struct fixed_mtrr_segment { + u64 start; + u64 end; + + int range_shift; + + /* the start position in kvm_mtrr.fixed_ranges[]. */ + int range_start; +}; + +static struct fixed_mtrr_segment fixed_seg_table[] = { + /* MSR_MTRRfix64K_00000, 1 unit. 64K fixed mtrr. */ + { + .start = 0x0, + .end = 0x80000, + .range_shift = 16, /* 64K */ + .range_start = 0, + }, + + /* + * MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000, 2 units, + * 16K fixed mtrr. + */ + { + .start = 0x80000, + .end = 0xc0000, + .range_shift = 14, /* 16K */ + .range_start = 8, + }, + + /* + * MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000, 8 units, + * 4K fixed mtrr. + */ + { + .start = 0xc0000, + .end = 0x100000, + .range_shift = 12, /* 12K */ + .range_start = 24, + } +}; + +/* + * The size of unit is covered in one MSR, one MSR entry contains + * 8 ranges so that unit size is always 8 * 2^range_shift. + */ +static u64 fixed_mtrr_seg_unit_size(int seg) +{ + return 8 << fixed_seg_table[seg].range_shift; +} + +static bool fixed_msr_to_seg_unit(u32 msr, int *seg, int *unit) +{ + switch (msr) { + case MSR_MTRRfix64K_00000: + *seg = 0; + *unit = 0; + break; + case MSR_MTRRfix16K_80000 ... MSR_MTRRfix16K_A0000: + *seg = 1; + *unit = msr - MSR_MTRRfix16K_80000; + break; + case MSR_MTRRfix4K_C0000 ... MSR_MTRRfix4K_F8000: + *seg = 2; + *unit = msr - MSR_MTRRfix4K_C0000; + break; + default: + return false; + } + + return true; +} + +static void fixed_mtrr_seg_unit_range(int seg, int unit, u64 *start, u64 *end) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + u64 unit_size = fixed_mtrr_seg_unit_size(seg); + + *start = mtrr_seg->start + unit * unit_size; + *end = *start + unit_size; + WARN_ON(*end > mtrr_seg->end); +} + +static int fixed_mtrr_seg_unit_range_index(int seg, int unit) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + + WARN_ON(mtrr_seg->start + unit * fixed_mtrr_seg_unit_size(seg) + > mtrr_seg->end); + + /* each unit has 8 ranges. */ + return mtrr_seg->range_start + 8 * unit; +} + +static int fixed_mtrr_seg_end_range_index(int seg) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + int n; + + n = (mtrr_seg->end - mtrr_seg->start) >> mtrr_seg->range_shift; + return mtrr_seg->range_start + n - 1; +} + +static bool fixed_msr_to_range(u32 msr, u64 *start, u64 *end) +{ + int seg, unit; + + if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) + return false; + + fixed_mtrr_seg_unit_range(seg, unit, start, end); + return true; +} + +static int fixed_msr_to_range_index(u32 msr) +{ + int seg, unit; + + if (!fixed_msr_to_seg_unit(msr, &seg, &unit)) + return -1; + + return fixed_mtrr_seg_unit_range_index(seg, unit); +} + +static int fixed_mtrr_addr_to_seg(u64 addr) +{ + struct fixed_mtrr_segment *mtrr_seg; + int seg, seg_num = ARRAY_SIZE(fixed_seg_table); + + for (seg = 0; seg < seg_num; seg++) { + mtrr_seg = &fixed_seg_table[seg]; + if (mtrr_seg->start <= addr && addr < mtrr_seg->end) + return seg; + } + + return -1; +} + +static int fixed_mtrr_addr_seg_to_range_index(u64 addr, int seg) +{ + struct fixed_mtrr_segment *mtrr_seg; + int index; + + mtrr_seg = &fixed_seg_table[seg]; + index = mtrr_seg->range_start; + index += (addr - mtrr_seg->start) >> mtrr_seg->range_shift; + return index; +} + +static u64 fixed_mtrr_range_end_addr(int seg, int index) +{ + struct fixed_mtrr_segment *mtrr_seg = &fixed_seg_table[seg]; + int pos = index - mtrr_seg->range_start; + + return mtrr_seg->start + ((pos + 1) << mtrr_seg->range_shift); +} + +static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end) +{ + u64 mask; + + *start = range->base & PAGE_MASK; + + mask = range->mask & PAGE_MASK; + + /* This cannot overflow because writing to the reserved bits of + * variable MTRRs causes a #GP. + */ + *end = (*start | ~mask) + 1; +} + +static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + gfn_t start, end; + int index; + + if (msr == MSR_IA32_CR_PAT || !tdp_enabled || + !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + return; + + if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) + return; + + /* fixed MTRRs. */ + if (fixed_msr_to_range(msr, &start, &end)) { + if (!fixed_mtrr_is_enabled(mtrr_state)) + return; + } else if (msr == MSR_MTRRdefType) { + start = 0x0; + end = ~0ULL; + } else { + /* variable range MTRRs. */ + index = (msr - 0x200) / 2; + var_mtrr_range(&mtrr_state->var_ranges[index], &start, &end); + } + + kvm_zap_gfn_range(vcpu->kvm, gpa_to_gfn(start), gpa_to_gfn(end)); +} + +static bool var_mtrr_range_is_valid(struct kvm_mtrr_range *range) +{ + return (range->mask & (1 << 11)) != 0; +} + +static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct kvm_mtrr_range *tmp, *cur; + int index, is_mtrr_mask; + + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; + cur = &mtrr_state->var_ranges[index]; + + /* remove the entry if it's in the list. */ + if (var_mtrr_range_is_valid(cur)) + list_del(&mtrr_state->var_ranges[index].node); + + /* Extend the mask with all 1 bits to the left, since those + * bits must implicitly be 0. The bits are then cleared + * when reading them. + */ + if (!is_mtrr_mask) + cur->base = data; + else + cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu)); + + /* add it to the list if it's enabled. */ + if (var_mtrr_range_is_valid(cur)) { + list_for_each_entry(tmp, &mtrr_state->head, node) + if (cur->base >= tmp->base) + break; + list_add_tail(&cur->node, &tmp->node); + } +} + +int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + int index; + + if (!kvm_mtrr_valid(vcpu, msr, data)) + return 1; + + index = fixed_msr_to_range_index(msr); + if (index >= 0) + *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index] = data; + else if (msr == MSR_MTRRdefType) + vcpu->arch.mtrr_state.deftype = data; + else if (msr == MSR_IA32_CR_PAT) + vcpu->arch.pat = data; + else + set_var_mtrr_msr(vcpu, msr, data); + + update_mtrr(vcpu, msr); + return 0; +} + +int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + int index; + + /* MSR_MTRRcap is a readonly MSR. */ + if (msr == MSR_MTRRcap) { + /* + * SMRR = 0 + * WC = 1 + * FIX = 1 + * VCNT = KVM_NR_VAR_MTRR + */ + *pdata = 0x500 | KVM_NR_VAR_MTRR; + return 0; + } + + if (!msr_mtrr_valid(msr)) + return 1; + + index = fixed_msr_to_range_index(msr); + if (index >= 0) + *pdata = *(u64 *)&vcpu->arch.mtrr_state.fixed_ranges[index]; + else if (msr == MSR_MTRRdefType) + *pdata = vcpu->arch.mtrr_state.deftype; + else if (msr == MSR_IA32_CR_PAT) + *pdata = vcpu->arch.pat; + else { /* Variable MTRRs */ + int is_mtrr_mask; + + index = (msr - 0x200) / 2; + is_mtrr_mask = msr - 0x200 - 2 * index; + if (!is_mtrr_mask) + *pdata = vcpu->arch.mtrr_state.var_ranges[index].base; + else + *pdata = vcpu->arch.mtrr_state.var_ranges[index].mask; + + *pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1; + } + + return 0; +} + +void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu) +{ + INIT_LIST_HEAD(&vcpu->arch.mtrr_state.head); +} + +struct mtrr_iter { + /* input fields. */ + struct kvm_mtrr *mtrr_state; + u64 start; + u64 end; + + /* output fields. */ + int mem_type; + /* mtrr is completely disabled? */ + bool mtrr_disabled; + /* [start, end) is not fully covered in MTRRs? */ + bool partial_map; + + /* private fields. */ + union { + /* used for fixed MTRRs. */ + struct { + int index; + int seg; + }; + + /* used for var MTRRs. */ + struct { + struct kvm_mtrr_range *range; + /* max address has been covered in var MTRRs. */ + u64 start_max; + }; + }; + + bool fixed; +}; + +static bool mtrr_lookup_fixed_start(struct mtrr_iter *iter) +{ + int seg, index; + + if (!fixed_mtrr_is_enabled(iter->mtrr_state)) + return false; + + seg = fixed_mtrr_addr_to_seg(iter->start); + if (seg < 0) + return false; + + iter->fixed = true; + index = fixed_mtrr_addr_seg_to_range_index(iter->start, seg); + iter->index = index; + iter->seg = seg; + return true; +} + +static bool match_var_range(struct mtrr_iter *iter, + struct kvm_mtrr_range *range) +{ + u64 start, end; + + var_mtrr_range(range, &start, &end); + if (!(start >= iter->end || end <= iter->start)) { + iter->range = range; + + /* + * the function is called when we do kvm_mtrr.head walking. + * Range has the minimum base address which interleaves + * [looker->start_max, looker->end). + */ + iter->partial_map |= iter->start_max < start; + + /* update the max address has been covered. */ + iter->start_max = max(iter->start_max, end); + return true; + } + + return false; +} + +static void __mtrr_lookup_var_next(struct mtrr_iter *iter) +{ + struct kvm_mtrr *mtrr_state = iter->mtrr_state; + + list_for_each_entry_continue(iter->range, &mtrr_state->head, node) + if (match_var_range(iter, iter->range)) + return; + + iter->range = NULL; + iter->partial_map |= iter->start_max < iter->end; +} + +static void mtrr_lookup_var_start(struct mtrr_iter *iter) +{ + struct kvm_mtrr *mtrr_state = iter->mtrr_state; + + iter->fixed = false; + iter->start_max = iter->start; + iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node); + + __mtrr_lookup_var_next(iter); +} + +static void mtrr_lookup_fixed_next(struct mtrr_iter *iter) +{ + /* terminate the lookup. */ + if (fixed_mtrr_range_end_addr(iter->seg, iter->index) >= iter->end) { + iter->fixed = false; + iter->range = NULL; + return; + } + + iter->index++; + + /* have looked up for all fixed MTRRs. */ + if (iter->index >= ARRAY_SIZE(iter->mtrr_state->fixed_ranges)) + return mtrr_lookup_var_start(iter); + + /* switch to next segment. */ + if (iter->index > fixed_mtrr_seg_end_range_index(iter->seg)) + iter->seg++; +} + +static void mtrr_lookup_var_next(struct mtrr_iter *iter) +{ + __mtrr_lookup_var_next(iter); +} + +static void mtrr_lookup_start(struct mtrr_iter *iter) +{ + if (!mtrr_is_enabled(iter->mtrr_state)) { + iter->mtrr_disabled = true; + return; + } + + if (!mtrr_lookup_fixed_start(iter)) + mtrr_lookup_var_start(iter); +} + +static void mtrr_lookup_init(struct mtrr_iter *iter, + struct kvm_mtrr *mtrr_state, u64 start, u64 end) +{ + iter->mtrr_state = mtrr_state; + iter->start = start; + iter->end = end; + iter->mtrr_disabled = false; + iter->partial_map = false; + iter->fixed = false; + iter->range = NULL; + + mtrr_lookup_start(iter); +} + +static bool mtrr_lookup_okay(struct mtrr_iter *iter) +{ + if (iter->fixed) { + iter->mem_type = iter->mtrr_state->fixed_ranges[iter->index]; + return true; + } + + if (iter->range) { + iter->mem_type = iter->range->base & 0xff; + return true; + } + + return false; +} + +static void mtrr_lookup_next(struct mtrr_iter *iter) +{ + if (iter->fixed) + mtrr_lookup_fixed_next(iter); + else + mtrr_lookup_var_next(iter); +} + +#define mtrr_for_each_mem_type(_iter_, _mtrr_, _gpa_start_, _gpa_end_) \ + for (mtrr_lookup_init(_iter_, _mtrr_, _gpa_start_, _gpa_end_); \ + mtrr_lookup_okay(_iter_); mtrr_lookup_next(_iter_)) + +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct mtrr_iter iter; + u64 start, end; + int type = -1; + const int wt_wb_mask = (1 << MTRR_TYPE_WRBACK) + | (1 << MTRR_TYPE_WRTHROUGH); + + start = gfn_to_gpa(gfn); + end = start + PAGE_SIZE; + + mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { + int curr_type = iter.mem_type; + + /* + * Please refer to Intel SDM Volume 3: 11.11.4.1 MTRR + * Precedences. + */ + + if (type == -1) { + type = curr_type; + continue; + } + + /* + * If two or more variable memory ranges match and the + * memory types are identical, then that memory type is + * used. + */ + if (type == curr_type) + continue; + + /* + * If two or more variable memory ranges match and one of + * the memory types is UC, the UC memory type used. + */ + if (curr_type == MTRR_TYPE_UNCACHABLE) + return MTRR_TYPE_UNCACHABLE; + + /* + * If two or more variable memory ranges match and the + * memory types are WT and WB, the WT memory type is used. + */ + if (((1 << type) & wt_wb_mask) && + ((1 << curr_type) & wt_wb_mask)) { + type = MTRR_TYPE_WRTHROUGH; + continue; + } + + /* + * For overlaps not defined by the above rules, processor + * behavior is undefined. + */ + + /* We use WB for this undefined behavior. :( */ + return MTRR_TYPE_WRBACK; + } + + if (iter.mtrr_disabled) + return mtrr_disabled_type(vcpu); + + /* not contained in any MTRRs. */ + if (type == -1) + return mtrr_default_type(mtrr_state); + + /* + * We just check one page, partially covered by MTRRs is + * impossible. + */ + WARN_ON(iter.partial_map); + + return type; +} +EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type); + +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, + int page_num) +{ + struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; + struct mtrr_iter iter; + u64 start, end; + int type = -1; + + start = gfn_to_gpa(gfn); + end = gfn_to_gpa(gfn + page_num); + mtrr_for_each_mem_type(&iter, mtrr_state, start, end) { + if (type == -1) { + type = iter.mem_type; + continue; + } + + if (type != iter.mem_type) + return false; + } + + if (iter.mtrr_disabled) + return true; + + if (!iter.partial_map) + return true; + + if (type == -1) + return true; + + return type == mtrr_default_type(mtrr_state); +} diff --git a/kernel/arch/x86/kvm/paging_tmpl.h b/kernel/arch/x86/kvm/paging_tmpl.h index 6e6d115fe..7be8a2513 100644 --- a/kernel/arch/x86/kvm/paging_tmpl.h +++ b/kernel/arch/x86/kvm/paging_tmpl.h @@ -128,14 +128,6 @@ static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte) *access &= mask; } -static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) -{ - int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f; - - return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) | - ((mmu->bad_mt_xwr & (1ull << low6)) != 0); -} - static inline int FNAME(is_present_gpte)(unsigned long pte) { #if PTTYPE != PTTYPE_EPT @@ -172,7 +164,7 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) { - if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) goto no_present; if (!FNAME(is_present_gpte)(gpte)) @@ -256,8 +248,8 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (ret) return ret; - mark_page_dirty(vcpu->kvm, table_gfn); - walker->ptes[level] = pte; + kvm_vcpu_mark_page_dirty(vcpu, table_gfn); + walker->ptes[level - 1] = pte; } return 0; } @@ -338,7 +330,7 @@ retry_walk: real_gfn = gpa_to_gfn(real_gfn); - host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -353,8 +345,7 @@ retry_walk: if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, - walker->level))) { + if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) { errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } @@ -511,11 +502,11 @@ static bool FNAME(gpte_changed)(struct kvm_vcpu *vcpu, base_gpa = pte_gpa & ~mask; index = (pte_gpa - base_gpa) / sizeof(pt_element_t); - r = kvm_read_guest_atomic(vcpu->kvm, base_gpa, + r = kvm_vcpu_read_guest_atomic(vcpu, base_gpa, gw->prefetch_ptes, sizeof(gw->prefetch_ptes)); curr_pte = gw->prefetch_ptes[index]; } else - r = kvm_read_guest_atomic(vcpu->kvm, pte_gpa, + r = kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &curr_pte, sizeof(curr_pte)); return r || curr_pte != gw->ptes[level - 1]; @@ -707,15 +698,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, int r; pfn_t pfn; int level = PT_PAGE_TABLE_LEVEL; - int force_pt_level; + bool force_pt_level = false; unsigned long mmu_seq; bool map_writable, is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code); if (unlikely(error_code & PFERR_RSVD_MASK)) { - r = handle_mmio_page_fault(vcpu, addr, error_code, - mmu_is_nested(vcpu)); + r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu)); if (likely(r != RET_MMIO_PF_INVALID)) return r; @@ -752,15 +742,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable); - if (walker.level >= PT_DIRECTORY_LEVEL) - force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn) - || is_self_change_mapping; - else - force_pt_level = 1; - if (!force_pt_level) { - level = min(walker.level, mapping_level(vcpu, walker.gfn)); - walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); - } + if (walker.level >= PT_DIRECTORY_LEVEL && !is_self_change_mapping) { + level = mapping_level(vcpu, walker.gfn, &force_pt_level); + if (likely(!force_pt_level)) { + level = min(walker.level, level); + walker.gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE(level) - 1); + } + } else + force_pt_level = true; mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); @@ -869,8 +858,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) if (!rmap_can_add(vcpu)) break; - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) break; FNAME(update_pte)(vcpu, sp, sptep, &gpte); @@ -956,8 +945,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); - if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, - sizeof(pt_element_t))) + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) return -EINVAL; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { @@ -970,7 +959,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) pte_access &= FNAME(gpte_access)(vcpu, gpte); FNAME(protect_clean_gpte)(&pte_access, gpte); - if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access, + if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access, &nr_present)) continue; diff --git a/kernel/arch/x86/kvm/pmu.c b/kernel/arch/x86/kvm/pmu.c index 29fbf9dfd..31aa2c85d 100644 --- a/kernel/arch/x86/kvm/pmu.c +++ b/kernel/arch/x86/kvm/pmu.c @@ -1,11 +1,12 @@ /* * Kernel-based Virtual Machine -- Performance Monitoring Unit support * - * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * Copyright 2015 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@redhat.com> * Gleb Natapov <gleb@redhat.com> + * Wei Huang <wei@redhat.com> * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. @@ -19,88 +20,39 @@ #include "x86.h" #include "cpuid.h" #include "lapic.h" +#include "pmu.h" + +/* NOTE: + * - Each perf counter is defined as "struct kvm_pmc"; + * - There are two types of perf counters: general purpose (gp) and fixed. + * gp counters are stored in gp_counters[] and fixed counters are stored + * in fixed_counters[] respectively. Both of them are part of "struct + * kvm_pmu"; + * - pmu.c understands the difference between gp counters and fixed counters. + * However AMD doesn't support fixed-counters; + * - There are three types of index to access perf counters (PMC): + * 1. MSR (named msr): For example Intel has MSR_IA32_PERFCTRn and AMD + * has MSR_K7_PERFCTRn. + * 2. MSR Index (named idx): This normally is used by RDPMC instruction. + * For instance AMD RDPMC instruction uses 0000_0003h in ECX to access + * C001_0007h (MSR_K7_PERCTR3). Intel has a similar mechanism, except + * that it also supports fixed counters. idx can be used to as index to + * gp and fixed counters. + * 3. Global PMC Index (named pmc): pmc is an index specific to PMU + * code. Each pmc, stored in kvm_pmc.idx field, is unique across + * all perf counters (both gp and fixed). The mapping relationship + * between pmc and perf counters is as the following: + * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters + * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed + * * AMD: [0 .. AMD64_NUM_COUNTERS-1] <=> gp counters + */ -static struct kvm_arch_event_perf_mapping { - u8 eventsel; - u8 unit_mask; - unsigned event_type; - bool inexact; -} arch_events[] = { - /* Index must match CPUID 0x0A.EBX bit vector */ - [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, - [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, - [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, - [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, - [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, -}; - -/* mapping between fixed pmc index and arch_events array */ -static int fixed_pmc_events[] = {1, 0, 7}; - -static bool pmc_is_gp(struct kvm_pmc *pmc) -{ - return pmc->type == KVM_PMC_GP; -} - -static inline u64 pmc_bitmask(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - - return pmu->counter_bitmask[pmc->type]; -} - -static inline bool pmc_enabled(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); -} - -static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, - u32 base) -{ - if (msr >= base && msr < base + pmu->nr_arch_gp_counters) - return &pmu->gp_counters[msr - base]; - return NULL; -} - -static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) -{ - int base = MSR_CORE_PERF_FIXED_CTR0; - if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) - return &pmu->fixed_counters[msr - base]; - return NULL; -} - -static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) -{ - return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx); -} - -static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) -{ - if (idx < INTEL_PMC_IDX_FIXED) - return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); - else - return get_fixed_pmc_idx(pmu, idx - INTEL_PMC_IDX_FIXED); -} - -void kvm_deliver_pmi(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.apic) - kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); -} - -static void trigger_pmi(struct irq_work *irq_work) +static void kvm_pmi_trigger_fn(struct irq_work *irq_work) { - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, - irq_work); - struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu, - arch.pmu); + struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); + struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - kvm_deliver_pmi(vcpu); + kvm_pmu_deliver_pmi(vcpu); } static void kvm_perf_overflow(struct perf_event *perf_event, @@ -108,63 +60,46 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (!test_and_set_bit(pmc->idx, + (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } } static void kvm_perf_overflow_intr(struct perf_event *perf_event, - struct perf_sample_data *data, struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { struct kvm_pmc *pmc = perf_event->overflow_handler_context; - struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + if (!test_and_set_bit(pmc->idx, + (unsigned long *)&pmu->reprogram_pmi)) { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + /* * Inject PMI. If vcpu was in a guest mode during NMI PMI * can be ejected on a guest mode re-entry. Otherwise we can't * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until, + * time of vmexit and is not going to re-enter guest mode until * woken up. So we should wake it, but this is impossible from * NMI context. Do it from irq work instead. */ if (!kvm_is_in_guest()) - irq_work_queue(&pmc->vcpu->arch.pmu.irq_work); + irq_work_queue(&pmc_to_pmu(pmc)->irq_work); else kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } } -static u64 read_pmc(struct kvm_pmc *pmc) -{ - u64 counter, enabled, running; - - counter = pmc->counter; - - if (pmc->perf_event) - counter += perf_event_read_value(pmc->perf_event, - &enabled, &running); - - /* FIXME: Scaling needed? */ - - return counter & pmc_bitmask(pmc); -} - -static void stop_counter(struct kvm_pmc *pmc) -{ - if (pmc->perf_event) { - pmc->counter = read_pmc(pmc); - perf_event_release_kernel(pmc->perf_event); - pmc->perf_event = NULL; - } -} - -static void reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, bool exclude_kernel, - bool intr, bool in_tx, bool in_tx_cp) +static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, + unsigned config, bool exclude_user, + bool exclude_kernel, bool intr, + bool in_tx, bool in_tx_cp) { struct perf_event *event; struct perf_event_attr attr = { @@ -177,6 +112,7 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type, .exclude_kernel = exclude_kernel, .config = config, }; + if (in_tx) attr.config |= HSW_IN_TX; if (in_tx_cp) @@ -188,33 +124,16 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type, intr ? kvm_perf_overflow_intr : kvm_perf_overflow, pmc); if (IS_ERR(event)) { - printk_once("kvm: pmu event creation failed %ld\n", - PTR_ERR(event)); + printk_once("kvm_pmu: event creation failed %ld\n", + PTR_ERR(event)); return; } pmc->perf_event = event; - clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi); -} - -static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select, - u8 unit_mask) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(arch_events); i++) - if (arch_events[i].eventsel == event_select - && arch_events[i].unit_mask == unit_mask - && (pmu->available_event_types & (1 << i))) - break; - - if (i == ARRAY_SIZE(arch_events)) - return PERF_COUNT_HW_MAX; - - return arch_events[i].event_type; + clear_bit(pmc->idx, (unsigned long*)&pmc_to_pmu(pmc)->reprogram_pmi); } -static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) +void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { unsigned config, type = PERF_TYPE_RAW; u8 event_select, unit_mask; @@ -224,21 +143,22 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc->eventsel = eventsel; - stop_counter(pmc); + pmc_stop_counter(pmc); - if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc)) + if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc)) return; event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | - ARCH_PERFMON_EVENTSEL_INV | - ARCH_PERFMON_EVENTSEL_CMASK | - HSW_IN_TX | - HSW_IN_TX_CHECKPOINTED))) { - config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, - unit_mask); + ARCH_PERFMON_EVENTSEL_INV | + ARCH_PERFMON_EVENTSEL_CMASK | + HSW_IN_TX | + HSW_IN_TX_CHECKPOINTED))) { + config = kvm_x86_ops->pmu_ops->find_arch_event(pmc_to_pmu(pmc), + event_select, + unit_mask); if (config != PERF_COUNT_HW_MAX) type = PERF_TYPE_HARDWARE; } @@ -246,56 +166,36 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (type == PERF_TYPE_RAW) config = eventsel & X86_RAW_EVENT_MASK; - reprogram_counter(pmc, type, config, - !(eventsel & ARCH_PERFMON_EVENTSEL_USR), - !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT, - (eventsel & HSW_IN_TX), - (eventsel & HSW_IN_TX_CHECKPOINTED)); + pmc_reprogram_counter(pmc, type, config, + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT, + (eventsel & HSW_IN_TX), + (eventsel & HSW_IN_TX_CHECKPOINTED)); } +EXPORT_SYMBOL_GPL(reprogram_gp_counter); -static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) +void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) { - unsigned en = en_pmi & 0x3; - bool pmi = en_pmi & 0x8; + unsigned en_field = ctrl & 0x3; + bool pmi = ctrl & 0x8; - stop_counter(pmc); + pmc_stop_counter(pmc); - if (!en || !pmc_enabled(pmc)) + if (!en_field || !pmc_is_enabled(pmc)) return; - reprogram_counter(pmc, PERF_TYPE_HARDWARE, - arch_events[fixed_pmc_events[idx]].event_type, - !(en & 0x2), /* exclude user */ - !(en & 0x1), /* exclude kernel */ - pmi, false, false); + pmc_reprogram_counter(pmc, PERF_TYPE_HARDWARE, + kvm_x86_ops->pmu_ops->find_fixed_event(idx), + !(en_field & 0x2), /* exclude user */ + !(en_field & 0x1), /* exclude kernel */ + pmi, false, false); } +EXPORT_SYMBOL_GPL(reprogram_fixed_counter); -static inline u8 fixed_en_pmi(u64 ctrl, int idx) +void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx) { - return (ctrl >> (idx * 4)) & 0xf; -} - -static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) -{ - int i; - - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - u8 en_pmi = fixed_en_pmi(data, i); - struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); - - if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi) - continue; - - reprogram_fixed_counter(pmc, en_pmi, i); - } - - pmu->fixed_ctr_ctrl = data; -} - -static void reprogram_idx(struct kvm_pmu *pmu, int idx) -{ - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx); + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, pmc_idx); if (!pmc) return; @@ -303,274 +203,107 @@ static void reprogram_idx(struct kvm_pmu *pmu, int idx) if (pmc_is_gp(pmc)) reprogram_gp_counter(pmc, pmc->eventsel); else { - int fidx = idx - INTEL_PMC_IDX_FIXED; - reprogram_fixed_counter(pmc, - fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); + int idx = pmc_idx - INTEL_PMC_IDX_FIXED; + u8 ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, idx); + + reprogram_fixed_counter(pmc, ctrl, idx); } } +EXPORT_SYMBOL_GPL(reprogram_counter); -static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + u64 bitmask; int bit; - u64 diff = pmu->global_ctrl ^ data; - - pmu->global_ctrl = data; - - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) - reprogram_idx(pmu, bit); -} -bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - int ret; - - switch (msr) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - case MSR_CORE_PERF_GLOBAL_STATUS: - case MSR_CORE_PERF_GLOBAL_CTRL: - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - ret = pmu->version > 1; - break; - default: - ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) - || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) - || get_fixed_pmc(pmu, msr); - break; - } - return ret; -} + bitmask = pmu->reprogram_pmi; -int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; + for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + struct kvm_pmc *pmc = kvm_x86_ops->pmu_ops->pmc_idx_to_pmc(pmu, bit); - switch (index) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - *data = pmu->fixed_ctr_ctrl; - return 0; - case MSR_CORE_PERF_GLOBAL_STATUS: - *data = pmu->global_status; - return 0; - case MSR_CORE_PERF_GLOBAL_CTRL: - *data = pmu->global_ctrl; - return 0; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - *data = pmu->global_ovf_ctrl; - return 0; - default: - if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, index))) { - *data = read_pmc(pmc); - return 0; - } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { - *data = pmc->eventsel; - return 0; + if (unlikely(!pmc || !pmc->perf_event)) { + clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + continue; } - } - return 1; -} -int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_pmc *pmc; - u32 index = msr_info->index; - u64 data = msr_info->data; - - switch (index) { - case MSR_CORE_PERF_FIXED_CTR_CTRL: - if (pmu->fixed_ctr_ctrl == data) - return 0; - if (!(data & 0xfffffffffffff444ull)) { - reprogram_fixed_counters(pmu, data); - return 0; - } - break; - case MSR_CORE_PERF_GLOBAL_STATUS: - if (msr_info->host_initiated) { - pmu->global_status = data; - return 0; - } - break; /* RO MSR */ - case MSR_CORE_PERF_GLOBAL_CTRL: - if (pmu->global_ctrl == data) - return 0; - if (!(data & pmu->global_ctrl_mask)) { - global_ctrl_changed(pmu, data); - return 0; - } - break; - case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { - if (!msr_info->host_initiated) - pmu->global_status &= ~data; - pmu->global_ovf_ctrl = data; - return 0; - } - break; - default: - if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, index))) { - if (!msr_info->host_initiated) - data = (s64)(s32)data; - pmc->counter += data - read_pmc(pmc); - return 0; - } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { - reprogram_gp_counter(pmc, data); - return 0; - } - } + reprogram_counter(pmu, bit); } - return 1; } -int kvm_pmu_check_pmc(struct kvm_vcpu *vcpu, unsigned pmc) +/* check if idx is a valid index to access PMU */ +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - bool fixed = pmc & (1u << 30); - pmc &= ~(3u << 30); - return (!fixed && pmc >= pmu->nr_arch_gp_counters) || - (fixed && pmc >= pmu->nr_arch_fixed_counters); + return kvm_x86_ops->pmu_ops->is_valid_msr_idx(vcpu, idx); } -int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - bool fast_mode = pmc & (1u << 31); - bool fixed = pmc & (1u << 30); - struct kvm_pmc *counters; - u64 ctr; - - pmc &= ~(3u << 30); - if (!fixed && pmc >= pmu->nr_arch_gp_counters) - return 1; - if (fixed && pmc >= pmu->nr_arch_fixed_counters) + bool fast_mode = idx & (1u << 31); + struct kvm_pmc *pmc; + u64 ctr_val; + + pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx); + if (!pmc) return 1; - counters = fixed ? pmu->fixed_counters : pmu->gp_counters; - ctr = read_pmc(&counters[pmc]); + + ctr_val = pmc_read_counter(pmc); if (fast_mode) - ctr = (u32)ctr; - *data = ctr; + ctr_val = (u32)ctr_val; + *data = ctr_val; return 0; } -void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - struct kvm_cpuid_entry2 *entry; - union cpuid10_eax eax; - union cpuid10_edx edx; - - pmu->nr_arch_gp_counters = 0; - pmu->nr_arch_fixed_counters = 0; - pmu->counter_bitmask[KVM_PMC_GP] = 0; - pmu->counter_bitmask[KVM_PMC_FIXED] = 0; - pmu->version = 0; - pmu->reserved_bits = 0xffffffff00200000ull; - - entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); - if (!entry) - return; - eax.full = entry->eax; - edx.full = entry->edx; - - pmu->version = eax.split.version_id; - if (!pmu->version) - return; - - pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, - INTEL_PMC_MAX_GENERIC); - pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; - pmu->available_event_types = ~entry->ebx & - ((1ull << eax.split.mask_length) - 1); - - if (pmu->version == 1) { - pmu->nr_arch_fixed_counters = 0; - } else { - pmu->nr_arch_fixed_counters = - min_t(int, edx.split.num_counters_fixed, - INTEL_PMC_MAX_FIXED); - pmu->counter_bitmask[KVM_PMC_FIXED] = - ((u64)1 << edx.split.bit_width_fixed) - 1; - } + if (vcpu->arch.apic) + kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); +} - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); - pmu->global_ctrl_mask = ~pmu->global_ctrl; +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + return kvm_x86_ops->pmu_ops->is_valid_msr(vcpu, msr); +} - entry = kvm_find_cpuid_entry(vcpu, 7, 0); - if (entry && - (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && - (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) - pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + return kvm_x86_ops->pmu_ops->get_msr(vcpu, msr, data); } -void kvm_pmu_init(struct kvm_vcpu *vcpu) +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - int i; - struct kvm_pmu *pmu = &vcpu->arch.pmu; + return kvm_x86_ops->pmu_ops->set_msr(vcpu, msr_info); +} - memset(pmu, 0, sizeof(*pmu)); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - pmu->gp_counters[i].type = KVM_PMC_GP; - pmu->gp_counters[i].vcpu = vcpu; - pmu->gp_counters[i].idx = i; - } - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { - pmu->fixed_counters[i].type = KVM_PMC_FIXED; - pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; - } - init_irq_work(&pmu->irq_work, trigger_pmi); - kvm_pmu_cpuid_update(vcpu); +/* refresh PMU settings. This function generally is called when underlying + * settings are changed (such as changes of PMU CPUID by guest VMs), which + * should rarely happen. + */ +void kvm_pmu_refresh(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->pmu_ops->refresh(vcpu); } void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = &vcpu->arch.pmu; - int i; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); irq_work_sync(&pmu->irq_work); - for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { - struct kvm_pmc *pmc = &pmu->gp_counters[i]; - stop_counter(pmc); - pmc->counter = pmc->eventsel = 0; - } + kvm_x86_ops->pmu_ops->reset(vcpu); +} - for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) - stop_counter(&pmu->fixed_counters[i]); +void kvm_pmu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = - pmu->global_ovf_ctrl = 0; + memset(pmu, 0, sizeof(*pmu)); + kvm_x86_ops->pmu_ops->init(vcpu); + init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); + kvm_pmu_refresh(vcpu); } void kvm_pmu_destroy(struct kvm_vcpu *vcpu) { kvm_pmu_reset(vcpu); } - -void kvm_handle_pmu_event(struct kvm_vcpu *vcpu) -{ - struct kvm_pmu *pmu = &vcpu->arch.pmu; - u64 bitmask; - int bit; - - bitmask = pmu->reprogram_pmi; - - for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { - struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); - - if (unlikely(!pmc || !pmc->perf_event)) { - clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); - continue; - } - - reprogram_idx(pmu, bit); - } -} diff --git a/kernel/arch/x86/kvm/pmu.h b/kernel/arch/x86/kvm/pmu.h new file mode 100644 index 000000000..f96e1f962 --- /dev/null +++ b/kernel/arch/x86/kvm/pmu.h @@ -0,0 +1,118 @@ +#ifndef __KVM_X86_PMU_H +#define __KVM_X86_PMU_H + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) +#define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) + +/* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */ +#define fixed_ctrl_field(ctrl_reg, idx) (((ctrl_reg) >> ((idx)*4)) & 0xf) + +struct kvm_event_hw_type_mapping { + u8 eventsel; + u8 unit_mask; + unsigned event_type; +}; + +struct kvm_pmu_ops { + unsigned (*find_arch_event)(struct kvm_pmu *pmu, u8 event_select, + u8 unit_mask); + unsigned (*find_fixed_event)(int idx); + bool (*pmc_is_enabled)(struct kvm_pmc *pmc); + struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx); + int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); + bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); + int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); + int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); + void (*refresh)(struct kvm_vcpu *vcpu); + void (*init)(struct kvm_vcpu *vcpu); + void (*reset)(struct kvm_vcpu *vcpu); +}; + +static inline u64 pmc_bitmask(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + return pmu->counter_bitmask[pmc->type]; +} + +static inline u64 pmc_read_counter(struct kvm_pmc *pmc) +{ + u64 counter, enabled, running; + + counter = pmc->counter; + if (pmc->perf_event) + counter += perf_event_read_value(pmc->perf_event, + &enabled, &running); + /* FIXME: Scaling needed? */ + return counter & pmc_bitmask(pmc); +} + +static inline void pmc_stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = pmc_read_counter(pmc); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static inline bool pmc_is_gp(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_GP; +} + +static inline bool pmc_is_fixed(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_FIXED; +} + +static inline bool pmc_is_enabled(struct kvm_pmc *pmc) +{ + return kvm_x86_ops->pmu_ops->pmc_is_enabled(pmc); +} + +/* returns general purpose PMC with the specified MSR. Note that it can be + * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a + * paramenter to tell them apart. + */ +static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, + u32 base) +{ + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) + return &pmu->gp_counters[msr - base]; + + return NULL; +} + +/* returns fixed PMC with the specified MSR */ +static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) +{ + int base = MSR_CORE_PERF_FIXED_CTR0; + + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[msr - base]; + + return NULL; +} + +void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel); +void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int fixed_idx); +void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx); + +void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); +void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); +int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); +int kvm_pmu_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx); +bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data); +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); +void kvm_pmu_refresh(struct kvm_vcpu *vcpu); +void kvm_pmu_reset(struct kvm_vcpu *vcpu); +void kvm_pmu_init(struct kvm_vcpu *vcpu); +void kvm_pmu_destroy(struct kvm_vcpu *vcpu); + +extern struct kvm_pmu_ops intel_pmu_ops; +extern struct kvm_pmu_ops amd_pmu_ops; +#endif /* __KVM_X86_PMU_H */ diff --git a/kernel/arch/x86/kvm/pmu_amd.c b/kernel/arch/x86/kvm/pmu_amd.c new file mode 100644 index 000000000..39b91127e --- /dev/null +++ b/kernel/arch/x86/kvm/pmu_amd.c @@ -0,0 +1,205 @@ +/* + * KVM PMU support for AMD + * + * Copyright 2015, Red Hat, Inc. and/or its affiliates. + * + * Author: + * Wei Huang <wei@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Implementation is based on pmu_intel.c file + */ +#include <linux/types.h> +#include <linux/kvm_host.h> +#include <linux/perf_event.h> +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" +#include "pmu.h" + +/* duplicated from amd_perfmon_event_map, K7 and above should work. */ +static struct kvm_event_hw_type_mapping amd_event_mapping[] = { + [0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES }, + [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES }, + [4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }, + [7] = { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }, +}; + +static unsigned amd_find_arch_event(struct kvm_pmu *pmu, + u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(amd_event_mapping); i++) + if (amd_event_mapping[i].eventsel == event_select + && amd_event_mapping[i].unit_mask == unit_mask) + break; + + if (i == ARRAY_SIZE(amd_event_mapping)) + return PERF_COUNT_HW_MAX; + + return amd_event_mapping[i].event_type; +} + +/* return PERF_COUNT_HW_MAX as AMD doesn't have fixed events */ +static unsigned amd_find_fixed_event(int idx) +{ + return PERF_COUNT_HW_MAX; +} + +/* check if a PMC is enabled by comparing it against global_ctrl bits. Because + * AMD CPU doesn't have global_ctrl MSR, all PMCs are enabled (return TRUE). + */ +static bool amd_pmc_is_enabled(struct kvm_pmc *pmc) +{ + return true; +} + +static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +{ + return get_gp_pmc(pmu, MSR_K7_EVNTSEL0 + pmc_idx, MSR_K7_EVNTSEL0); +} + +/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ +static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + idx &= ~(3u << 30); + + return (idx >= pmu->nr_arch_gp_counters); +} + +/* idx is the ECX register of RDPMC instruction */ +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *counters; + + idx &= ~(3u << 30); + if (idx >= pmu->nr_arch_gp_counters) + return NULL; + counters = pmu->gp_counters; + + return &counters[idx]; +} + +static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int ret = false; + + ret = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0) || + get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + + return ret; +} + +static int amd_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* MSR_K7_PERFCTRn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); + if (pmc) { + *data = pmc_read_counter(pmc); + return 0; + } + /* MSR_K7_EVNTSELn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + if (pmc) { + *data = pmc->eventsel; + return 0; + } + + return 1; +} + +static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + /* MSR_K7_PERFCTRn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_PERFCTR0); + if (pmc) { + pmc->counter += data - pmc_read_counter(pmc); + return 0; + } + /* MSR_K7_EVNTSELn */ + pmc = get_gp_pmc(pmu, msr, MSR_K7_EVNTSEL0); + if (pmc) { + if (data == pmc->eventsel) + return 0; + if (!(data & pmu->reserved_bits)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + + return 1; +} + +static void amd_pmu_refresh(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; + pmu->reserved_bits = 0xffffffff00200000ull; + /* not applicable to AMD; but clean them to prevent any fall out */ + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->version = 0; + pmu->global_status = 0; +} + +static void amd_pmu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < AMD64_NUM_COUNTERS ; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } +} + +static void amd_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < AMD64_NUM_COUNTERS; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + + pmc_stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } +} + +struct kvm_pmu_ops amd_pmu_ops = { + .find_arch_event = amd_find_arch_event, + .find_fixed_event = amd_find_fixed_event, + .pmc_is_enabled = amd_pmc_is_enabled, + .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, + .msr_idx_to_pmc = amd_msr_idx_to_pmc, + .is_valid_msr_idx = amd_is_valid_msr_idx, + .is_valid_msr = amd_is_valid_msr, + .get_msr = amd_pmu_get_msr, + .set_msr = amd_pmu_set_msr, + .refresh = amd_pmu_refresh, + .init = amd_pmu_init, + .reset = amd_pmu_reset, +}; diff --git a/kernel/arch/x86/kvm/pmu_intel.c b/kernel/arch/x86/kvm/pmu_intel.c new file mode 100644 index 000000000..ab38af4f4 --- /dev/null +++ b/kernel/arch/x86/kvm/pmu_intel.c @@ -0,0 +1,358 @@ +/* + * KVM PMU support for Intel CPUs + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Avi Kivity <avi@redhat.com> + * Gleb Natapov <gleb@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ +#include <linux/types.h> +#include <linux/kvm_host.h> +#include <linux/perf_event.h> +#include <asm/perf_event.h> +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" +#include "pmu.h" + +static struct kvm_event_hw_type_mapping intel_arch_events[] = { + /* Index must match CPUID 0x0A.EBX bit vector */ + [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, + [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, + [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, + [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, + [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, +}; + +/* mapping between fixed pmc index and intel_arch_events array */ +static int fixed_pmc_events[] = {1, 0, 7}; + +static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) +{ + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { + u8 new_ctrl = fixed_ctrl_field(data, i); + u8 old_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, i); + struct kvm_pmc *pmc; + + pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); + + if (old_ctrl == new_ctrl) + continue; + + reprogram_fixed_counter(pmc, new_ctrl, i); + } + + pmu->fixed_ctr_ctrl = data; +} + +/* function is called when global control register has been updated. */ +static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +{ + int bit; + u64 diff = pmu->global_ctrl ^ data; + + pmu->global_ctrl = data; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + reprogram_counter(pmu, bit); +} + +static unsigned intel_find_arch_event(struct kvm_pmu *pmu, + u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(intel_arch_events); i++) + if (intel_arch_events[i].eventsel == event_select + && intel_arch_events[i].unit_mask == unit_mask + && (pmu->available_event_types & (1 << i))) + break; + + if (i == ARRAY_SIZE(intel_arch_events)) + return PERF_COUNT_HW_MAX; + + return intel_arch_events[i].event_type; +} + +static unsigned intel_find_fixed_event(int idx) +{ + if (idx >= ARRAY_SIZE(fixed_pmc_events)) + return PERF_COUNT_HW_MAX; + + return intel_arch_events[fixed_pmc_events[idx]].event_type; +} + +/* check if a PMC is enabled by comparising it with globl_ctrl bits. */ +static bool intel_pmc_is_enabled(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = pmc_to_pmu(pmc); + + return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); +} + +static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +{ + if (pmc_idx < INTEL_PMC_IDX_FIXED) + return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx, + MSR_P6_EVNTSEL0); + else { + u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED; + + return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0); + } +} + +/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */ +static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + + idx &= ~(3u << 30); + + return (!fixed && idx >= pmu->nr_arch_gp_counters) || + (fixed && idx >= pmu->nr_arch_fixed_counters); +} + +static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, + unsigned idx) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + bool fixed = idx & (1u << 30); + struct kvm_pmc *counters; + + idx &= ~(3u << 30); + if (!fixed && idx >= pmu->nr_arch_gp_counters) + return NULL; + if (fixed && idx >= pmu->nr_arch_fixed_counters) + return NULL; + counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + + return &counters[idx]; +} + +static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int ret; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + ret = pmu->version > 1; + break; + default: + ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) || + get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) || + get_fixed_pmc(pmu, msr); + break; + } + + return ret; +} + +static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + *data = pmu->fixed_ctr_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_STATUS: + *data = pmu->global_status; + return 0; + case MSR_CORE_PERF_GLOBAL_CTRL: + *data = pmu->global_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *data = pmu->global_ovf_ctrl; + return 0; + default: + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, msr))) { + *data = pmc_read_counter(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { + *data = pmc->eventsel; + return 0; + } + } + + return 1; +} + +static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u32 msr = msr_info->index; + u64 data = msr_info->data; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + if (pmu->fixed_ctr_ctrl == data) + return 0; + if (!(data & 0xfffffffffffff444ull)) { + reprogram_fixed_counters(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + if (msr_info->host_initiated) { + pmu->global_status = data; + return 0; + } + break; /* RO MSR */ + case MSR_CORE_PERF_GLOBAL_CTRL: + if (pmu->global_ctrl == data) + return 0; + if (!(data & pmu->global_ctrl_mask)) { + global_ctrl_changed(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { + if (!msr_info->host_initiated) + pmu->global_status &= ~data; + pmu->global_ovf_ctrl = data; + return 0; + } + break; + default: + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, msr))) { + if (!msr_info->host_initiated) + data = (s64)(s32)data; + pmc->counter += data - pmc_read_counter(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { + if (data == pmc->eventsel) + return 0; + if (!(data & pmu->reserved_bits)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + } + + return 1; +} + +static void intel_pmu_refresh(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_cpuid_entry2 *entry; + union cpuid10_eax eax; + union cpuid10_edx edx; + + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->version = 0; + pmu->reserved_bits = 0xffffffff00200000ull; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return; + eax.full = entry->eax; + edx.full = entry->edx; + + pmu->version = eax.split.version_id; + if (!pmu->version) + return; + + pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, + INTEL_PMC_MAX_GENERIC); + pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; + pmu->available_event_types = ~entry->ebx & + ((1ull << eax.split.mask_length) - 1); + + if (pmu->version == 1) { + pmu->nr_arch_fixed_counters = 0; + } else { + pmu->nr_arch_fixed_counters = + min_t(int, edx.split.num_counters_fixed, + INTEL_PMC_MAX_FIXED); + pmu->counter_bitmask[KVM_PMC_FIXED] = + ((u64)1 << edx.split.bit_width_fixed) - 1; + } + + pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); + pmu->global_ctrl_mask = ~pmu->global_ctrl; + + entry = kvm_find_cpuid_entry(vcpu, 7, 0); + if (entry && + (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && + (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) + pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; +} + +static void intel_pmu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } + + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) { + pmu->fixed_counters[i].type = KVM_PMC_FIXED; + pmu->fixed_counters[i].vcpu = vcpu; + pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + } +} + +static void intel_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + int i; + + for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + + pmc_stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } + + for (i = 0; i < INTEL_PMC_MAX_FIXED; i++) + pmc_stop_counter(&pmu->fixed_counters[i]); + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = + pmu->global_ovf_ctrl = 0; +} + +struct kvm_pmu_ops intel_pmu_ops = { + .find_arch_event = intel_find_arch_event, + .find_fixed_event = intel_find_fixed_event, + .pmc_is_enabled = intel_pmc_is_enabled, + .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, + .msr_idx_to_pmc = intel_msr_idx_to_pmc, + .is_valid_msr_idx = intel_is_valid_msr_idx, + .is_valid_msr = intel_is_valid_msr, + .get_msr = intel_pmu_get_msr, + .set_msr = intel_pmu_set_msr, + .refresh = intel_pmu_refresh, + .init = intel_pmu_init, + .reset = intel_pmu_reset, +}; diff --git a/kernel/arch/x86/kvm/svm.c b/kernel/arch/x86/kvm/svm.c index 4911bf191..899c40f82 100644 --- a/kernel/arch/x86/kvm/svm.c +++ b/kernel/arch/x86/kvm/svm.c @@ -21,6 +21,7 @@ #include "kvm_cache_regs.h" #include "x86.h" #include "cpuid.h" +#include "pmu.h" #include <linux/module.h> #include <linux/mod_devicetable.h> @@ -28,7 +29,7 @@ #include <linux/vmalloc.h> #include <linux/highmem.h> #include <linux/sched.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #include <linux/slab.h> #include <asm/perf_event.h> @@ -157,7 +158,8 @@ struct vcpu_svm { unsigned long int3_rip; u32 apf_reason; - u64 tsc_ratio; + /* cached guest cpuid flags for faster access */ + bool nrips_enabled : 1; }; static DEFINE_PER_CPU(u64, current_tsc_ratio); @@ -201,6 +203,7 @@ module_param(npt, int, S_IRUGO); static int nested = true; module_param(nested, int, S_IRUGO); +static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); static void svm_flush_tlb(struct kvm_vcpu *vcpu); static void svm_complete_interrupts(struct vcpu_svm *svm); @@ -209,7 +212,6 @@ static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); -static u64 __scale_tsc(u64 ratio, u64 tsc); enum { VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, @@ -512,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (svm->vmcb->control.next_rip != 0) { - WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); + WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; } @@ -889,20 +891,9 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_FFXSR); if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - u64 max; - kvm_has_tsc_control = true; - - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated needed because it will always - * be 1 on all machines and a value of 0 is used to disable - * tsc-scaling for the vcpu. - */ - max = min(0x7fffffffULL, __scale_tsc(tsc_khz, TSC_RATIO_MAX)); - - kvm_max_guest_tsc_khz = max; + kvm_max_tsc_scaling_ratio = TSC_RATIO_MAX; + kvm_tsc_scaling_ratio_frac_bits = 32; } if (nested) { @@ -966,68 +957,6 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } -static u64 __scale_tsc(u64 ratio, u64 tsc) -{ - u64 mult, frac, _tsc; - - mult = ratio >> 32; - frac = ratio & ((1ULL << 32) - 1); - - _tsc = tsc; - _tsc *= mult; - _tsc += (tsc >> 32) * frac; - _tsc += ((tsc & ((1ULL << 32) - 1)) * frac) >> 32; - - return _tsc; -} - -static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 _tsc = tsc; - - if (svm->tsc_ratio != TSC_RATIO_DEFAULT) - _tsc = __scale_tsc(svm->tsc_ratio, tsc); - - return _tsc; -} - -static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - struct vcpu_svm *svm = to_svm(vcpu); - u64 ratio; - u64 khz; - - /* Guest TSC same frequency as host TSC? */ - if (!scale) { - svm->tsc_ratio = TSC_RATIO_DEFAULT; - return; - } - - /* TSC scaling supported? */ - if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); - return; - } - - khz = user_tsc_khz; - - /* TSC scaling required - calculate ratio */ - ratio = khz << 32; - do_div(ratio, tsc_khz); - - if (ratio == 0 || ratio & TSC_RATIO_RSVD) { - WARN_ONCE(1, "Invalid TSC ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); - return; - } - svm->tsc_ratio = ratio; -} - static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1054,16 +983,10 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { struct vcpu_svm *svm = to_svm(vcpu); - if (host) { - if (svm->tsc_ratio != TSC_RATIO_DEFAULT) - WARN_ON(adjustment < 0); - adjustment = svm_scale_tsc(vcpu, (u64)adjustment); - } - svm->vmcb->control.tsc_offset += adjustment; if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; @@ -1075,15 +998,6 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - u64 tsc; - - tsc = svm_scale_tsc(vcpu, native_read_tsc()); - - return target_tsc - tsc; -} - static void init_vmcb(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1105,6 +1019,8 @@ static void init_vmcb(struct vcpu_svm *svm) set_exception_intercept(svm, PF_VECTOR); set_exception_intercept(svm, UD_VECTOR); set_exception_intercept(svm, MC_VECTOR); + set_exception_intercept(svm, AC_VECTOR); + set_exception_intercept(svm, DB_VECTOR); set_intercept(svm, INTERCEPT_INTR); set_intercept(svm, INTERCEPT_NMI); @@ -1162,11 +1078,11 @@ static void init_vmcb(struct vcpu_svm *svm) svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; /* - * This is the guest-visible cr0 value. * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. + * It also updates the guest-visible cr0 value. */ - svm->vcpu.arch.cr0 = 0; - (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); + svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET); + kvm_mmu_reset_context(&svm->vcpu); save->cr4 = X86_CR4_PAE; /* rdx = ?? */ @@ -1178,7 +1094,7 @@ static void init_vmcb(struct vcpu_svm *svm) clr_exception_intercept(svm, PF_VECTOR); clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); - save->g_pat = 0x0007040600070406ULL; + save->g_pat = svm->vcpu.arch.pat; save->cr3 = 0; save->cr4 = 0; } @@ -1197,12 +1113,18 @@ static void init_vmcb(struct vcpu_svm *svm) enable_gif(svm); } -static void svm_vcpu_reset(struct kvm_vcpu *vcpu) +static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_svm *svm = to_svm(vcpu); u32 dummy; u32 eax = 1; + if (!init_event) { + svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) + svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + } init_vmcb(svm); kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); @@ -1224,8 +1146,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } - svm->tsc_ratio = TSC_RATIO_DEFAULT; - err = kvm_vcpu_init(&svm->vcpu, kvm, id); if (err) goto free_svm; @@ -1261,11 +1181,6 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->asid_generation = 0; init_vmcb(svm); - svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | - MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) - svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; - svm_init_osvw(&svm->vcpu); return &svm->vcpu; @@ -1316,10 +1231,12 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - if (static_cpu_has(X86_FEATURE_TSCRATEMSR) && - svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) { - __this_cpu_write(current_tsc_ratio, svm->tsc_ratio); - wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio); + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + u64 tsc_ratio = vcpu->arch.tsc_scaling_ratio; + if (tsc_ratio != __this_cpu_read(current_tsc_ratio)) { + __this_cpu_write(current_tsc_ratio, tsc_ratio); + wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); + } } } @@ -1577,7 +1494,8 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) * does not do it - this results in some delay at * reboot */ - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); @@ -1637,20 +1555,13 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_db_bp_intercept(struct kvm_vcpu *vcpu) +static void update_bp_intercept(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - clr_exception_intercept(svm, DB_VECTOR); clr_exception_intercept(svm, BP_VECTOR); - if (svm->nmi_singlestep) - set_exception_intercept(svm, DB_VECTOR); - if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { - if (vcpu->guest_debug & - (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) set_exception_intercept(svm, BP_VECTOR); } else @@ -1756,7 +1667,6 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(&svm->vcpu); } if (svm->vcpu.guest_debug & @@ -1791,6 +1701,12 @@ static int ud_interception(struct vcpu_svm *svm) return 1; } +static int ac_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception_e(&svm->vcpu, AC_VECTOR, 0); + return 1; +} + static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1955,8 +1871,8 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; - ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, - offset_in_page(cr3) + index * 8, 8); + ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); if (ret) return 0; return pdpte; @@ -2010,6 +1926,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); + reset_shadow_zero_bits_mask(vcpu, &vcpu->arch.mmu); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; } @@ -2114,7 +2031,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) might_sleep(); - page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); + page = kvm_vcpu_gfn_to_page(&svm->vcpu, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto error; @@ -2153,7 +2070,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm) mask = (0xf >> (4 - size)) << start_bit; val = 0; - if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, iopm_len)) + if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len)) return NESTED_EXIT_DONE; return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; @@ -2178,7 +2095,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) /* Offset is in 32 bit units but need in 8 bit units */ offset *= 4; - if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4)) return NESTED_EXIT_DONE; return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; @@ -2359,7 +2276,9 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; - nested_vmcb->control.next_rip = vmcb->control.next_rip; + + if (svm->nrips_enabled) + nested_vmcb->control.next_rip = vmcb->control.next_rip; /* * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have @@ -2449,7 +2368,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) p = msrpm_offsets[i]; offset = svm->nested.vmcb_msrpm + (p * 4); - if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4)) + if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4)) return false; svm->nested.msrpm[p] = svm->msrpm[p] | value; @@ -3054,7 +2973,7 @@ static int cr8_write_interception(struct vcpu_svm *svm) u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(svm); - if (irqchip_in_kernel(svm->vcpu.kvm)) + if (lapic_in_kernel(&svm->vcpu)) return r; if (cr8_prev <= kvm_get_cr8(&svm->vcpu)) return r; @@ -3065,46 +2984,45 @@ static int cr8_write_interception(struct vcpu_svm *svm) static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); - return vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, host_tsc); + return vmcb->control.tsc_offset + host_tsc; } -static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) +static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); - switch (ecx) { + switch (msr_info->index) { case MSR_IA32_TSC: { - *data = svm->vmcb->control.tsc_offset + - svm_scale_tsc(vcpu, native_read_tsc()); + msr_info->data = svm->vmcb->control.tsc_offset + + kvm_scale_tsc(vcpu, rdtsc()); break; } case MSR_STAR: - *data = svm->vmcb->save.star; + msr_info->data = svm->vmcb->save.star; break; #ifdef CONFIG_X86_64 case MSR_LSTAR: - *data = svm->vmcb->save.lstar; + msr_info->data = svm->vmcb->save.lstar; break; case MSR_CSTAR: - *data = svm->vmcb->save.cstar; + msr_info->data = svm->vmcb->save.cstar; break; case MSR_KERNEL_GS_BASE: - *data = svm->vmcb->save.kernel_gs_base; + msr_info->data = svm->vmcb->save.kernel_gs_base; break; case MSR_SYSCALL_MASK: - *data = svm->vmcb->save.sfmask; + msr_info->data = svm->vmcb->save.sfmask; break; #endif case MSR_IA32_SYSENTER_CS: - *data = svm->vmcb->save.sysenter_cs; + msr_info->data = svm->vmcb->save.sysenter_cs; break; case MSR_IA32_SYSENTER_EIP: - *data = svm->sysenter_eip; + msr_info->data = svm->sysenter_eip; break; case MSR_IA32_SYSENTER_ESP: - *data = svm->sysenter_esp; + msr_info->data = svm->sysenter_esp; break; /* * Nobody will change the following 5 values in the VMCB so we can @@ -3112,31 +3030,31 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) * implemented. */ case MSR_IA32_DEBUGCTLMSR: - *data = svm->vmcb->save.dbgctl; + msr_info->data = svm->vmcb->save.dbgctl; break; case MSR_IA32_LASTBRANCHFROMIP: - *data = svm->vmcb->save.br_from; + msr_info->data = svm->vmcb->save.br_from; break; case MSR_IA32_LASTBRANCHTOIP: - *data = svm->vmcb->save.br_to; + msr_info->data = svm->vmcb->save.br_to; break; case MSR_IA32_LASTINTFROMIP: - *data = svm->vmcb->save.last_excp_from; + msr_info->data = svm->vmcb->save.last_excp_from; break; case MSR_IA32_LASTINTTOIP: - *data = svm->vmcb->save.last_excp_to; + msr_info->data = svm->vmcb->save.last_excp_to; break; case MSR_VM_HSAVE_PA: - *data = svm->nested.hsave_msr; + msr_info->data = svm->nested.hsave_msr; break; case MSR_VM_CR: - *data = svm->nested.vm_cr_msr; + msr_info->data = svm->nested.vm_cr_msr; break; case MSR_IA32_UCODE_REV: - *data = 0x01000065; + msr_info->data = 0x01000065; break; default: - return kvm_get_msr_common(vcpu, ecx, data); + return kvm_get_msr_common(vcpu, msr_info); } return 0; } @@ -3144,16 +3062,20 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); - u64 data; + struct msr_data msr_info; - if (svm_get_msr(&svm->vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (svm_get_msr(&svm->vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(&svm->vcpu, 0); } else { - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); - kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); - kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, + msr_info.data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, + msr_info.data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } @@ -3284,24 +3206,11 @@ static int msr_interception(struct vcpu_svm *svm) static int interrupt_window_interception(struct vcpu_svm *svm) { - struct kvm_run *kvm_run = svm->vcpu.run; - kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; mark_dirty(svm->vmcb, VMCB_INTR); ++svm->vcpu.stat.irq_window_exits; - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (!irqchip_in_kernel(svm->vcpu.kvm) && - kvm_run->request_interrupt_window && - !kvm_cpu_has_interrupt(&svm->vcpu)) { - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - return 0; - } - return 1; } @@ -3361,6 +3270,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception, + [SVM_EXIT_EXCP_BASE + AC_VECTOR] = ac_interception, [SVM_EXIT_INTR] = intr_interception, [SVM_EXIT_NMI] = nmi_interception, [SVM_EXIT_SMI] = nop_on_interception, @@ -3390,6 +3300,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = pf_interception, + [SVM_EXIT_RSM] = emulate_on_interception, }; static void dump_vmcb(struct kvm_vcpu *vcpu) @@ -3511,6 +3422,8 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; + trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM); + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) @@ -3648,12 +3561,12 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } -static int svm_vm_has_apicv(struct kvm *kvm) +static int svm_cpu_uses_apicv(struct kvm_vcpu *vcpu) { return 0; } -static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu) { return; } @@ -3743,7 +3656,6 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_bp_intercept(vcpu); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -3982,8 +3894,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); - if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_before_handle_nmi(&svm->vcpu); @@ -4075,6 +3985,11 @@ static bool svm_cpu_has_accelerated_tpr(void) return false; } +static bool svm_has_high_real_mode_segbase(void) +{ + return true; +} + static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { return 0; @@ -4082,6 +3997,10 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) static void svm_cpuid_update(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + /* Update nrips enabled cache */ + svm->nrips_enabled = !!guest_cpuid_has_nrips(&svm->vcpu); } static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -4350,6 +4269,7 @@ static struct kvm_x86_ops svm_x86_ops = { .hardware_enable = svm_hardware_enable, .hardware_disable = svm_hardware_disable, .cpu_has_accelerated_tpr = svm_cpu_has_accelerated_tpr, + .cpu_has_high_real_mode_segbase = svm_has_high_real_mode_segbase, .vcpu_create = svm_create_vcpu, .vcpu_free = svm_free_vcpu, @@ -4359,7 +4279,7 @@ static struct kvm_x86_ops svm_x86_ops = { .vcpu_load = svm_vcpu_load, .vcpu_put = svm_vcpu_put, - .update_db_bp_intercept = update_db_bp_intercept, + .update_bp_intercept = update_bp_intercept, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -4408,7 +4328,7 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, - .vm_has_apicv = svm_vm_has_apicv, + .cpu_uses_apicv = svm_cpu_uses_apicv, .load_eoi_exitmap = svm_load_eoi_exitmap, .sync_pir_to_irr = svm_sync_pir_to_irr, @@ -4431,11 +4351,9 @@ static struct kvm_x86_ops svm_x86_ops = { .has_wbinvd_exit = svm_has_wbinvd_exit, - .set_tsc_khz = svm_set_tsc_khz, .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, - .adjust_tsc_offset = svm_adjust_tsc_offset, - .compute_tsc_offset = svm_compute_tsc_offset, + .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest, .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, @@ -4444,6 +4362,8 @@ static struct kvm_x86_ops svm_x86_ops = { .handle_external_intr = svm_handle_external_intr, .sched_in = svm_sched_in, + + .pmu_ops = &amd_pmu_ops, }; static int __init svm_init(void) diff --git a/kernel/arch/x86/kvm/trace.h b/kernel/arch/x86/kvm/trace.h index 7c7bc8bef..ab9ae67a8 100644 --- a/kernel/arch/x86/kvm/trace.h +++ b/kernel/arch/x86/kvm/trace.h @@ -129,6 +129,24 @@ TRACE_EVENT(kvm_pio, ); /* + * Tracepoint for fast mmio. + */ +TRACE_EVENT(kvm_fast_mmio, + TP_PROTO(u64 gpa), + TP_ARGS(gpa), + + TP_STRUCT__entry( + __field(u64, gpa) + ), + + TP_fast_assign( + __entry->gpa = gpa; + ), + + TP_printk("fast mmio at gpa 0x%llx", __entry->gpa) +); + +/* * Tracepoint for cpuid. */ TRACE_EVENT(kvm_cpuid, @@ -250,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: @@ -952,6 +970,61 @@ TRACE_EVENT(kvm_wait_lapic_expire, __entry->delta < 0 ? "early" : "late") ); +TRACE_EVENT(kvm_enter_smm, + TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering), + TP_ARGS(vcpu_id, smbase, entering), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( u64, smbase ) + __field( bool, entering ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->smbase = smbase; + __entry->entering = entering; + ), + + TP_printk("vcpu %u: %s SMM, smbase 0x%llx", + __entry->vcpu_id, + __entry->entering ? "entering" : "leaving", + __entry->smbase) +); + +/* + * Tracepoint for VT-d posted-interrupts. + */ +TRACE_EVENT(kvm_pi_irte_update, + TP_PROTO(unsigned int vcpu_id, unsigned int gsi, + unsigned int gvec, u64 pi_desc_addr, bool set), + TP_ARGS(vcpu_id, gsi, gvec, pi_desc_addr, set), + + TP_STRUCT__entry( + __field( unsigned int, vcpu_id ) + __field( unsigned int, gsi ) + __field( unsigned int, gvec ) + __field( u64, pi_desc_addr ) + __field( bool, set ) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->gsi = gsi; + __entry->gvec = gvec; + __entry->pi_desc_addr = pi_desc_addr; + __entry->set = set; + ), + + TP_printk("VT-d PI is %s for this irq, vcpu %u, gsi: 0x%x, " + "gvec: 0x%x, pi_desc_addr: 0x%llx", + __entry->set ? "enabled and being updated" : "disabled", + __entry->vcpu_id, + __entry->gsi, + __entry->gvec, + __entry->pi_desc_addr) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/kernel/arch/x86/kvm/vmx.c b/kernel/arch/x86/kvm/vmx.c index 2d73807f0..0958fa2b7 100644 --- a/kernel/arch/x86/kvm/vmx.c +++ b/kernel/arch/x86/kvm/vmx.c @@ -28,26 +28,28 @@ #include <linux/sched.h> #include <linux/moduleparam.h> #include <linux/mod_devicetable.h> -#include <linux/ftrace_event.h> +#include <linux/trace_events.h> #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> #include "kvm_cache_regs.h" #include "x86.h" +#include <asm/cpu.h> #include <asm/io.h> #include <asm/desc.h> #include <asm/vmx.h> #include <asm/virtext.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/xcr.h> +#include <asm/fpu/internal.h> #include <asm/perf_event.h> #include <asm/debugreg.h> #include <asm/kexec.h> #include <asm/apic.h> +#include <asm/irq_remapping.h> #include "trace.h" +#include "pmu.h" #define __ex(x) __kvm_handle_fault_on_reboot(x) #define __ex_clear(x, reg) \ @@ -105,6 +107,8 @@ static u64 __read_mostly host_xss; static bool __read_mostly enable_pml = 1; module_param_named(pml, enable_pml, bool, S_IRUGO); +#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL + #define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE) #define KVM_VM_CR0_ALWAYS_ON \ @@ -424,6 +428,9 @@ struct nested_vmx { /* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */ u64 vmcs01_debugctl; + u16 vpid02; + u16 last_vpid; + u32 nested_vmx_procbased_ctls_low; u32 nested_vmx_procbased_ctls_high; u32 nested_vmx_true_procbased_ctls_low; @@ -440,14 +447,33 @@ struct nested_vmx { u32 nested_vmx_misc_low; u32 nested_vmx_misc_high; u32 nested_vmx_ept_caps; + u32 nested_vmx_vpid_caps; }; #define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + /* Posted-Interrupt Descriptor */ struct pi_desc { u32 pir[8]; /* Posted interrupt requested */ - u32 control; /* bit 0 of control is outstanding notification bit */ - u32 rsvd[7]; + union { + struct { + /* bit 256 - Outstanding Notification */ + u16 on : 1, + /* bit 257 - Suppress Notification */ + sn : 1, + /* bit 271:258 - Reserved */ + rsvd_1 : 14; + /* bit 279:272 - Notification Vector */ + u8 nv; + /* bit 287:280 - Reserved */ + u8 rsvd_2; + /* bit 319:288 - Notification Destination */ + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; } __aligned(64); static bool pi_test_and_set_on(struct pi_desc *pi_desc) @@ -467,6 +493,30 @@ static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + return clear_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + return set_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); +} + +static inline int pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, + (unsigned long *)&pi_desc->control); +} + struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; @@ -532,8 +582,6 @@ struct vcpu_vmx { s64 vnmi_blocked_time; u32 exit_reason; - bool rdtscp_enabled; - /* Posted interrupt descriptor */ struct pi_desc pi_desc; @@ -547,6 +595,8 @@ struct vcpu_vmx { /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; + + u64 current_tsc_ratio; }; enum segment_cache_field { @@ -563,6 +613,11 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) return container_of(vcpu, struct vcpu_vmx, vcpu); } +static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) +{ + return &(to_vmx(vcpu)->pi_desc); +} + #define VMCS12_OFFSET(x) offsetof(struct vmcs12, x) #define FIELD(number, name) [number] = VMCS12_OFFSET(name) #define FIELD64(number, name) [number] = VMCS12_OFFSET(name), \ @@ -786,7 +841,7 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu) static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr) { - struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT); + struct page *page = kvm_vcpu_gfn_to_page(vcpu, addr >> PAGE_SHIFT); if (is_error_page(page)) return NULL; @@ -809,7 +864,7 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static bool vmx_mpx_supported(void); static bool vmx_xsaves_supported(void); -static int vmx_vm_has_apicv(struct kvm *kvm); +static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -831,6 +886,13 @@ static DEFINE_PER_CPU(struct vmcs *, current_vmcs); static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DEFINE_PER_CPU(struct desc_ptr, host_gdt); +/* + * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we + * can find which vCPU should be waken up. + */ +static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock); + static unsigned long *vmx_io_bitmap_a; static unsigned long *vmx_io_bitmap_b; static unsigned long *vmx_msr_bitmap_legacy; @@ -946,9 +1008,9 @@ static inline bool cpu_has_vmx_tpr_shadow(void) return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW; } -static inline bool vm_need_tpr_shadow(struct kvm *kvm) +static inline bool cpu_need_tpr_shadow(struct kvm_vcpu *vcpu) { - return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm)); + return cpu_has_vmx_tpr_shadow() && lapic_in_kernel(vcpu); } static inline bool cpu_has_secondary_exec_ctrls(void) @@ -983,7 +1045,8 @@ static inline bool cpu_has_vmx_virtual_intr_delivery(void) static inline bool cpu_has_vmx_posted_intr(void) { - return vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; + return IS_ENABLED(CONFIG_X86_LOCAL_APIC) && + vmcs_config.pin_based_exec_ctrl & PIN_BASED_POSTED_INTR; } static inline bool cpu_has_vmx_apicv(void) @@ -1062,9 +1125,9 @@ static inline bool cpu_has_vmx_ple(void) SECONDARY_EXEC_PAUSE_LOOP_EXITING; } -static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm) +static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) { - return flexpriority_enabled && irqchip_in_kernel(kvm); + return flexpriority_enabled && lapic_in_kernel(vcpu); } static inline bool cpu_has_vmx_vpid(void) @@ -1113,6 +1176,12 @@ static inline bool cpu_has_vmx_pml(void) return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML; } +static inline bool cpu_has_vmx_tsc_scaling(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_TSC_SCALING; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -1157,6 +1226,11 @@ static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); } +static inline bool nested_cpu_has_vpid(struct vmcs12 *vmcs12) +{ + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_VPID); +} + static inline bool nested_cpu_has_apic_reg_virt(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_APIC_REGISTER_VIRT); @@ -1264,7 +1338,7 @@ static void vmcs_load(struct vmcs *vmcs) vmcs, phys_addr); } -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE /* * This bitmap is used to indicate whether the vmclear * operation is enabled on all cpus. All disabled by @@ -1302,7 +1376,7 @@ static void crash_vmclear_local_loaded_vmcss(void) #else static inline void crash_enable_local_vmclear(int cpu) { } static inline void crash_disable_local_vmclear(int cpu) { } -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ static void __loaded_vmcs_clear(void *arg) { @@ -1337,13 +1411,13 @@ static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs) __loaded_vmcs_clear, loaded_vmcs, 1); } -static inline void vpid_sync_vcpu_single(struct vcpu_vmx *vmx) +static inline void vpid_sync_vcpu_single(int vpid) { - if (vmx->vpid == 0) + if (vpid == 0) return; if (cpu_has_vmx_invvpid_single()) - __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vmx->vpid, 0); + __invvpid(VMX_VPID_EXTENT_SINGLE_CONTEXT, vpid, 0); } static inline void vpid_sync_vcpu_global(void) @@ -1352,10 +1426,10 @@ static inline void vpid_sync_vcpu_global(void) __invvpid(VMX_VPID_EXTENT_ALL_CONTEXT, 0, 0); } -static inline void vpid_sync_context(struct vcpu_vmx *vmx) +static inline void vpid_sync_context(int vpid) { if (cpu_has_vmx_invvpid_single()) - vpid_sync_vcpu_single(vmx); + vpid_sync_vcpu_single(vpid); else vpid_sync_vcpu_global(); } @@ -1567,7 +1641,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) u32 eb; eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | - (1u << NM_VECTOR) | (1u << DB_VECTOR); + (1u << NM_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) @@ -1674,6 +1748,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, return; } break; + case MSR_IA32_PEBS_ENABLE: + /* PEBS needs a quiescent period after being disabled (to write + * a record). Disabling PEBS through VMX MSR swapping doesn't + * provide that period, so a CPU could write host's record into + * guest's memory. + */ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); } for (i = 0; i < m->nr; ++i) @@ -1711,26 +1792,31 @@ static void reload_tss(void) static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - u64 guest_efer; - u64 ignore_bits; + u64 guest_efer = vmx->vcpu.arch.efer; + u64 ignore_bits = 0; - guest_efer = vmx->vcpu.arch.efer; + if (!enable_ept) { + /* + * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing + * host CPUID is more efficient than testing guest CPUID + * or CR4. Host SMEP is anyway a requirement for guest SMEP. + */ + if (boot_cpu_has(X86_FEATURE_SMEP)) + guest_efer |= EFER_NX; + else if (!(guest_efer & EFER_NX)) + ignore_bits |= EFER_NX; + } /* - * NX is emulated; LMA and LME handled by hardware; SCE meaningless - * outside long mode + * LMA and LME handled by hardware; SCE meaningless outside long mode. */ - ignore_bits = EFER_NX | EFER_SCE; + ignore_bits |= EFER_SCE; #ifdef CONFIG_X86_64 ignore_bits |= EFER_LMA | EFER_LME; /* SCE is meaningful only in long mode on Intel */ if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - guest_efer &= ~ignore_bits; - guest_efer |= host_efer & ignore_bits; - vmx->guest_msrs[efer_offset].data = guest_efer; - vmx->guest_msrs[efer_offset].mask = ~ignore_bits; clear_atomic_switch_msr(vmx, MSR_EFER); @@ -1741,16 +1827,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) */ if (cpu_has_load_ia32_efer || (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) { - guest_efer = vmx->vcpu.arch.efer; if (!(guest_efer & EFER_LMA)) guest_efer &= ~EFER_LME; if (guest_efer != host_efer) add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer); return false; - } + } else { + guest_efer &= ~ignore_bits; + guest_efer |= host_efer & ignore_bits; - return true; + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + + return true; + } } static unsigned long segment_base(u16 selector) @@ -1883,7 +1974,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) * If the FPU is not active (through the host task or * the guest vcpu), then restore the cr0.TS bit. */ - if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded) + if (!fpregs_active() && !vmx->vcpu.guest_fpu_loaded) stts(); load_gdt(this_cpu_ptr(&host_gdt)); } @@ -1895,6 +1986,52 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx) preempt_enable(); } +static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + do { + old.control = new.control = pi_desc->control; + + /* + * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there + * are two possible cases: + * 1. After running 'pre_block', context switch + * happened. For this case, 'sn' was set in + * vmx_vcpu_put(), so we need to clear it here. + * 2. After running 'pre_block', we were blocked, + * and woken up by some other guy. For this case, + * we don't need to do anything, 'pi_post_block' + * will do everything for us. However, we cannot + * check whether it is case #1 or case #2 here + * (maybe, not needed), so we also clear sn here, + * I think it is not a big deal. + */ + if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) { + if (vcpu->cpu != cpu) { + dest = cpu_physical_id(cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + } + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); +} /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -1943,12 +2080,37 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp); vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */ + vmx->loaded_vmcs->cpu = cpu; } + + /* Setup TSC multiplier */ + if (kvm_has_tsc_control && + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { + vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); + } + + vmx_vcpu_pi_load(vcpu, cpu); +} + +static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + /* Set SN when the vCPU is preempted */ + if (vcpu->preempted) + pi_set_sn(pi_desc); } static void vmx_vcpu_put(struct kvm_vcpu *vcpu) { + vmx_vcpu_pi_put(vcpu); + __vmx_load_host_state(to_vmx(vcpu)); if (!vmm_exclusive) { __loaded_vmcs_clear(to_vmx(vcpu)->loaded_vmcs); @@ -2170,8 +2332,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_nested; - else if (irqchip_in_kernel(vcpu->kvm) && - apic_x2apic_mode(vcpu->arch.apic)) { + else if (vcpu->arch.apic_base & X2APIC_ENABLE) { if (is_long_mode(vcpu)) msr_bitmap = vmx_msr_bitmap_longmode_x2apic; else @@ -2208,7 +2369,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); index = __find_msr_index(vmx, MSR_TSC_AUX); - if (index >= 0 && vmx->rdtscp_enabled) + if (index >= 0 && guest_cpuid_has_rdtscp(&vmx->vcpu)) move_msr_up(vmx, index, save_nmsrs++); /* * MSR_STAR is only needed on long mode guests, and only @@ -2231,15 +2392,16 @@ static void setup_msrs(struct vcpu_vmx *vmx) /* * reads and returns guest's timestamp counter "register" - * guest_tsc = host_tsc + tsc_offset -- 21.3 + * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset + * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3 */ -static u64 guest_read_tsc(void) +static u64 guest_read_tsc(struct kvm_vcpu *vcpu) { u64 host_tsc, tsc_offset; - rdtscll(host_tsc); + host_tsc = rdtsc(); tsc_offset = vmcs_read64(TSC_OFFSET); - return host_tsc + tsc_offset; + return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset; } /* @@ -2256,22 +2418,6 @@ static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) return host_tsc + tsc_offset; } -/* - * Engage any workarounds for mis-matched TSC rates. Currently limited to - * software catchup for faster rates on slower CPUs. - */ -static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) -{ - if (!scale) - return; - - if (user_tsc_khz > tsc_khz) { - vcpu->arch.tsc_catchup = 1; - vcpu->arch.tsc_always_catchup = 1; - } else - WARN(1, "user requested TSC rate below hardware speed\n"); -} - static u64 vmx_read_tsc_offset(struct kvm_vcpu *vcpu) { return vmcs_read64(TSC_OFFSET); @@ -2303,7 +2449,7 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) +static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { u64 offset = vmcs_read64(TSC_OFFSET); @@ -2316,11 +2462,6 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho offset + adjustment); } -static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) -{ - return target_tsc - native_read_tsc(); -} - static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0); @@ -2378,7 +2519,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - if (vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (vmx_cpu_uses_apicv(&vmx->vcpu)) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_POSTED_INTR; @@ -2444,10 +2585,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) CPU_BASED_CR8_LOAD_EXITING | CPU_BASED_CR8_STORE_EXITING | #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | - CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | - CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING | - CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW | - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; + CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_TRAP_FLAG | + CPU_BASED_MONITOR_EXITING | CPU_BASED_RDPMC_EXITING | + CPU_BASED_RDTSC_EXITING | CPU_BASED_PAUSE_EXITING | + CPU_BASED_TPR_SHADOW | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the * hardware. For example, L1 can specify an MSR bitmap - and we @@ -2472,10 +2613,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_WBINVD_EXITING | - SECONDARY_EXEC_XSAVES; + SECONDARY_EXEC_XSAVES | + SECONDARY_EXEC_PCOMMIT; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ @@ -2494,6 +2637,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + if (enable_vpid) + vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; + else + vmx->nested.nested_vmx_vpid_caps = 0; + if (enable_unrestricted_guest) vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_UNRESTRICTED_GUEST; @@ -2609,7 +2758,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) break; case MSR_IA32_VMX_EPT_VPID_CAP: /* Currently, no nested vpid support */ - *pdata = vmx->nested.nested_vmx_ept_caps; + *pdata = vmx->nested.nested_vmx_ept_caps | + ((u64)vmx->nested.nested_vmx_vpid_caps << 32); break; default: return 1; @@ -2623,76 +2773,69 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 data; struct shared_msr_entry *msr; - if (!pdata) { - printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); - return -EINVAL; - } - - switch (msr_index) { + switch (msr_info->index) { #ifdef CONFIG_X86_64 case MSR_FS_BASE: - data = vmcs_readl(GUEST_FS_BASE); + msr_info->data = vmcs_readl(GUEST_FS_BASE); break; case MSR_GS_BASE: - data = vmcs_readl(GUEST_GS_BASE); + msr_info->data = vmcs_readl(GUEST_GS_BASE); break; case MSR_KERNEL_GS_BASE: vmx_load_host_state(to_vmx(vcpu)); - data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + msr_info->data = to_vmx(vcpu)->msr_guest_kernel_gs_base; break; #endif case MSR_EFER: - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); case MSR_IA32_TSC: - data = guest_read_tsc(); + msr_info->data = guest_read_tsc(vcpu); break; case MSR_IA32_SYSENTER_CS: - data = vmcs_read32(GUEST_SYSENTER_CS); + msr_info->data = vmcs_read32(GUEST_SYSENTER_CS); break; case MSR_IA32_SYSENTER_EIP: - data = vmcs_readl(GUEST_SYSENTER_EIP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_EIP); break; case MSR_IA32_SYSENTER_ESP: - data = vmcs_readl(GUEST_SYSENTER_ESP); + msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: if (!vmx_mpx_supported()) return 1; - data = vmcs_read64(GUEST_BNDCFGS); + msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; case MSR_IA32_FEATURE_CONTROL: if (!nested_vmx_allowed(vcpu)) return 1; - data = to_vmx(vcpu)->nested.msr_ia32_feature_control; + msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control; break; case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: if (!nested_vmx_allowed(vcpu)) return 1; - return vmx_get_vmx_msr(vcpu, msr_index, pdata); + return vmx_get_vmx_msr(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_XSS: if (!vmx_xsaves_supported()) return 1; - data = vcpu->arch.ia32_xss; + msr_info->data = vcpu->arch.ia32_xss; break; case MSR_TSC_AUX: - if (!to_vmx(vcpu)->rdtscp_enabled) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Otherwise falls through */ default: - msr = find_msr_entry(to_vmx(vcpu), msr_index); + msr = find_msr_entry(to_vmx(vcpu), msr_info->index); if (msr) { - data = msr->data; + msr_info->data = msr->data; break; } - return kvm_get_msr_common(vcpu, msr_index, pdata); + return kvm_get_msr_common(vcpu, msr_info); } - *pdata = data; return 0; } @@ -2787,7 +2930,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) clear_atomic_switch_msr(vmx, MSR_IA32_XSS); break; case MSR_TSC_AUX: - if (!vmx->rdtscp_enabled) + if (!guest_cpuid_has_rdtscp(vcpu) && !msr_info->host_initiated) return 1; /* Check reserved bit, higher 32 bits should be zero */ if ((data >> 32) != 0) @@ -2882,6 +3025,8 @@ static int hardware_enable(void) return -EBUSY; INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu)); + INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); + spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); /* * Now we can enable the vmclear operation in kdump @@ -3023,7 +3168,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_SHADOW_VMCS | SECONDARY_EXEC_XSAVES | - SECONDARY_EXEC_ENABLE_PML; + SECONDARY_EXEC_ENABLE_PML | + SECONDARY_EXEC_PCOMMIT | + SECONDARY_EXEC_TSC_SCALING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -3158,7 +3305,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) struct page *pages; struct vmcs *vmcs; - pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order); + pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); @@ -3431,12 +3578,12 @@ static void enter_lmode(struct kvm_vcpu *vcpu) vmx_segment_cache_clear(to_vmx(vcpu)); guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES); - if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) { + if ((guest_tr_ar & VMX_AR_TYPE_MASK) != VMX_AR_TYPE_BUSY_64_TSS) { pr_debug_ratelimited("%s: tss fixup for long mode. \n", __func__); vmcs_write32(GUEST_TR_AR_BYTES, - (guest_tr_ar & ~AR_TYPE_MASK) - | AR_TYPE_BUSY_64_TSS); + (guest_tr_ar & ~VMX_AR_TYPE_MASK) + | VMX_AR_TYPE_BUSY_64_TSS); } vmx_set_efer(vcpu, vcpu->arch.efer | EFER_LMA); } @@ -3449,9 +3596,9 @@ static void exit_lmode(struct kvm_vcpu *vcpu) #endif -static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) { - vpid_sync_context(to_vmx(vcpu)); + vpid_sync_context(vpid); if (enable_ept) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; @@ -3459,6 +3606,11 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu) } } +static void vmx_flush_tlb(struct kvm_vcpu *vcpu) +{ + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid); +} + static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -3652,20 +3804,21 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (!is_paging(vcpu)) { hw_cr4 &= ~X86_CR4_PAE; hw_cr4 |= X86_CR4_PSE; - /* - * SMEP/SMAP is disabled if CPU is in non-paging mode - * in hardware. However KVM always uses paging mode to - * emulate guest non-paging mode with TDP. - * To emulate this behavior, SMEP/SMAP needs to be - * manually disabled when guest switches to non-paging - * mode. - */ - hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); } else if (!(cr4 & X86_CR4_PAE)) { hw_cr4 &= ~X86_CR4_PAE; } } + if (!enable_unrestricted_guest && !is_paging(vcpu)) + /* + * SMEP/SMAP is disabled if CPU is in non-paging mode in + * hardware. However KVM always uses paging mode without + * unrestricted guest. + * To emulate this behavior, SMEP/SMAP needs to be manually + * disabled when guest switches to non-paging mode. + */ + hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP); + vmcs_writel(CR4_READ_SHADOW, cr4); vmcs_writel(GUEST_CR4, hw_cr4); return 0; @@ -3727,7 +3880,7 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) return 0; else { int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); - return AR_DPL(ar); + return VMX_AR_DPL(ar); } } @@ -3855,11 +4008,11 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) if (cs.unusable) return false; - if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK)) + if (~cs.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; - if (cs.type & AR_TYPE_WRITEABLE_MASK) { + if (cs.type & VMX_AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; } else { @@ -3909,7 +4062,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) return false; if (!var.present) return false; - if (~var.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK)) { + if (~var.type & (VMX_AR_TYPE_CODE_MASK|VMX_AR_TYPE_WRITEABLE_MASK)) { if (var.dpl < rpl) /* DPL < RPL */ return false; } @@ -4113,17 +4266,13 @@ static void seg_setup(int seg) static int alloc_apic_access_page(struct kvm *kvm) { struct page *page; - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) goto out; - kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); if (r) goto out; @@ -4148,44 +4297,38 @@ static int alloc_identity_pagetable(struct kvm *kvm) { /* Called with kvm->slots_lock held. */ - struct kvm_userspace_memory_region kvm_userspace_mem; int r = 0; BUG_ON(kvm->arch.ept_identity_pagetable_done); - kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_userspace_mem.flags = 0; - kvm_userspace_mem.guest_phys_addr = - kvm->arch.ept_identity_map_addr; - kvm_userspace_mem.memory_size = PAGE_SIZE; - r = __kvm_set_memory_region(kvm, &kvm_userspace_mem); + r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, + kvm->arch.ept_identity_map_addr, PAGE_SIZE); return r; } -static void allocate_vpid(struct vcpu_vmx *vmx) +static int allocate_vpid(void) { int vpid; - vmx->vpid = 0; if (!enable_vpid) - return; + return 0; spin_lock(&vmx_vpid_lock); vpid = find_first_zero_bit(vmx_vpid_bitmap, VMX_NR_VPIDS); - if (vpid < VMX_NR_VPIDS) { - vmx->vpid = vpid; + if (vpid < VMX_NR_VPIDS) __set_bit(vpid, vmx_vpid_bitmap); - } + else + vpid = 0; spin_unlock(&vmx_vpid_lock); + return vpid; } -static void free_vpid(struct vcpu_vmx *vmx) +static void free_vpid(int vpid) { - if (!enable_vpid) + if (!enable_vpid || vpid == 0) return; spin_lock(&vmx_vpid_lock); - if (vmx->vpid != 0) - __clear_bit(vmx->vpid, vmx_vpid_bitmap); + __clear_bit(vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); } @@ -4340,9 +4483,9 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } -static int vmx_vm_has_apicv(struct kvm *kvm) +static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu) { - return enable_apicv && irqchip_in_kernel(kvm); + return enable_apicv && lapic_in_kernel(vcpu); } static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4386,6 +4529,22 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu) { #ifdef CONFIG_SMP if (vcpu->mode == IN_GUEST_MODE) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + + /* + * Currently, we don't support urgent interrupt, + * all interrupts are recognized as non-urgent + * interrupt, so we cannot post interrupts when + * 'SN' is set. + * + * If the vcpu is in guest mode, it means it is + * running instead of being scheduled out and + * waiting in the run queue, and that's the only + * case when 'SN' is set currently, warning if + * 'SN' is set. + */ + WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc)); + apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), POSTED_INTR_VECTOR); return true; @@ -4522,7 +4681,7 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (!vmx_cpu_uses_apicv(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; return pin_based_exec_ctrl; } @@ -4534,7 +4693,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) if (vmx->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT) exec_control &= ~CPU_BASED_MOV_DR_EXITING; - if (!vm_need_tpr_shadow(vmx->vcpu.kvm)) { + if (!cpu_need_tpr_shadow(&vmx->vcpu)) { exec_control &= ~CPU_BASED_TPR_SHADOW; #ifdef CONFIG_X86_64 exec_control |= CPU_BASED_CR8_STORE_EXITING | @@ -4551,7 +4710,7 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx) static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl; - if (!vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) + if (!cpu_need_virtualize_apic_accesses(&vmx->vcpu)) exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; @@ -4565,7 +4724,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!vmx_vm_has_apicv(vmx->vcpu.kvm)) + if (!vmx_cpu_uses_apicv(&vmx->vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; @@ -4575,8 +4734,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) a current VMCS12 */ exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - /* PML is enabled/disabled in creating/destorying vcpu */ - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; + + if (!enable_pml) + exec_control &= ~SECONDARY_EXEC_ENABLE_PML; + + /* Currently, we allow L1 guest to directly run pcommit instruction. */ + exec_control &= ~SECONDARY_EXEC_PCOMMIT; return exec_control; } @@ -4621,12 +4784,11 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx)); - if (cpu_has_secondary_exec_ctrls()) { + if (cpu_has_secondary_exec_ctrls()) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, vmx_secondary_exec_control(vmx)); - } - if (vmx_vm_has_apicv(vmx->vcpu.kvm)) { + if (vmx_cpu_uses_apicv(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); @@ -4667,16 +4829,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0); vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest)); - if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) { - u32 msr_low, msr_high; - u64 host_pat; - rdmsr(MSR_IA32_CR_PAT, msr_low, msr_high); - host_pat = msr_low | ((u64) msr_high << 32); - /* Write the default value follow host pat */ - vmcs_write64(GUEST_IA32_PAT, host_pat); - /* Keep arch.pat sync with GUEST_IA32_PAT */ - vmx->vcpu.arch.pat = host_pat; - } + if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) { u32 index = vmx_msr_index[i]; @@ -4708,22 +4862,27 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) return 0; } -static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) +static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct msr_data apic_base_msr; + u64 cr0; vmx->rmode.vm86_active = 0; vmx->soft_vnmi_blocked = 0; vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); - kvm_set_cr8(&vmx->vcpu, 0); - apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) - apic_base_msr.data |= MSR_IA32_APICBASE_BSP; - apic_base_msr.host_initiated = true; - kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); + kvm_set_cr8(vcpu, 0); + + if (!init_event) { + apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | + MSR_IA32_APICBASE_ENABLE; + if (kvm_vcpu_is_reset_bsp(vcpu)) + apic_base_msr.data |= MSR_IA32_APICBASE_BSP; + apic_base_msr.host_initiated = true; + kvm_set_apic_base(vcpu, &apic_base_msr); + } vmx_segment_cache_clear(vmx); @@ -4747,9 +4906,12 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_LDTR_LIMIT, 0xffff); vmcs_write32(GUEST_LDTR_AR_BYTES, 0x00082); - vmcs_write32(GUEST_SYSENTER_CS, 0); - vmcs_writel(GUEST_SYSENTER_ESP, 0); - vmcs_writel(GUEST_SYSENTER_EIP, 0); + if (!init_event) { + vmcs_write32(GUEST_SYSENTER_CS, 0); + vmcs_writel(GUEST_SYSENTER_ESP, 0); + vmcs_writel(GUEST_SYSENTER_EIP, 0); + vmcs_write64(GUEST_IA32_DEBUGCTL, 0); + } vmcs_writel(GUEST_RFLAGS, 0x02); kvm_rip_write(vcpu, 0xfff0); @@ -4764,37 +4926,35 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - /* Special registers */ - vmcs_write64(GUEST_IA32_DEBUGCTL, 0); - setup_msrs(vmx); vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */ - if (cpu_has_vmx_tpr_shadow()) { + if (cpu_has_vmx_tpr_shadow() && !init_event) { vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0); - if (vm_need_tpr_shadow(vmx->vcpu.kvm)) + if (cpu_need_tpr_shadow(vcpu)) vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, - __pa(vmx->vcpu.arch.apic->regs)); + __pa(vcpu->arch.apic->regs)); vmcs_write32(TPR_THRESHOLD, 0); } kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx_vm_has_apicv(vcpu->kvm)) + if (vmx_cpu_uses_apicv(vcpu)) memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */ - vmx_set_cr4(&vmx->vcpu, 0); - vmx_set_efer(&vmx->vcpu, 0); - vmx_fpu_activate(&vmx->vcpu); - update_exception_bitmap(&vmx->vcpu); + cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ + vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr4(vcpu, 0); + vmx_set_efer(vcpu, 0); + vmx_fpu_activate(vcpu); + update_exception_bitmap(vcpu); - vpid_sync_context(vmx); + vpid_sync_context(vmx->vpid); } /* @@ -4958,14 +5118,9 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) { int ret; - struct kvm_userspace_memory_region tss_mem = { - .slot = TSS_PRIVATE_MEMSLOT, - .guest_phys_addr = addr, - .memory_size = PAGE_SIZE * 3, - .flags = 0, - }; - ret = kvm_set_memory_region(kvm, &tss_mem); + ret = x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, addr, + PAGE_SIZE * 3); if (ret) return ret; kvm->arch.tss_addr = addr; @@ -5127,6 +5282,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) return handle_rmode_exception(vcpu, ex_no, error_code); switch (ex_no) { + case AC_VECTOR: + kvm_queue_exception_e(vcpu, AC_VECTOR, error_code); + return 1; case DB_VECTOR: dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & @@ -5319,7 +5477,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) u8 cr8 = (u8)val; err = kvm_set_cr8(vcpu, cr8); kvm_complete_insn_gp(vcpu, err); - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) return 1; if (cr8_prev <= cr8) return 1; @@ -5475,19 +5633,21 @@ static int handle_cpuid(struct kvm_vcpu *vcpu) static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; - u64 data; + struct msr_data msr_info; - if (vmx_get_msr(vcpu, ecx, &data)) { + msr_info.index = ecx; + msr_info.host_initiated = false; + if (vmx_get_msr(vcpu, &msr_info)) { trace_kvm_msr_read_ex(ecx); kvm_inject_gp(vcpu, 0); return 1; } - trace_kvm_msr_read(ecx, data); + trace_kvm_msr_read(ecx, msr_info.data); /* FIXME: handling of bits 32:63 of rax, rdx */ - vcpu->arch.regs[VCPU_REGS_RAX] = data & -1u; - vcpu->arch.regs[VCPU_REGS_RDX] = (data >> 32) & -1u; + vcpu->arch.regs[VCPU_REGS_RAX] = msr_info.data & -1u; + vcpu->arch.regs[VCPU_REGS_RDX] = (msr_info.data >> 32) & -1u; skip_emulated_instruction(vcpu); return 1; } @@ -5531,17 +5691,6 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); ++vcpu->stat.irq_window_exits; - - /* - * If the user space waits to inject interrupts, exit as soon as - * possible - */ - if (!irqchip_in_kernel(vcpu->kvm) && - vcpu->run->request_interrupt_window && - !kvm_cpu_has_interrupt(vcpu)) { - vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; - return 0; - } return 1; } @@ -5710,9 +5859,6 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) return 0; } - /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155); - /* * TODO: What about debug traps on tss switch? * Are we supposed to inject them and update dr6? @@ -5769,82 +5915,19 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } -static u64 ept_rsvd_mask(u64 spte, int level) -{ - int i; - u64 mask = 0; - - for (i = 51; i > boot_cpu_data.x86_phys_bits; i--) - mask |= (1ULL << i); - - if (level == 4) - /* bits 7:3 reserved */ - mask |= 0xf8; - else if (spte & (1ULL << 7)) - /* - * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively, - * level == 1 if the hypervisor is using the ignored bit 7. - */ - mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE; - else if (level > 1) - /* bits 6:3 reserved */ - mask |= 0x78; - - return mask; -} - -static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, - int level) -{ - printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level); - - /* 010b (write-only) */ - WARN_ON((spte & 0x7) == 0x2); - - /* 110b (write/execute) */ - WARN_ON((spte & 0x7) == 0x6); - - /* 100b (execute-only) and value not supported by logical processor */ - if (!cpu_has_vmx_ept_execute_only()) - WARN_ON((spte & 0x7) == 0x4); - - /* not 000b */ - if ((spte & 0x7)) { - u64 rsvd_bits = spte & ept_rsvd_mask(spte, level); - - if (rsvd_bits != 0) { - printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n", - __func__, rsvd_bits); - WARN_ON(1); - } - - /* bits 5:3 are _not_ reserved for large page or leaf page */ - if ((rsvd_bits & 0x38) == 0) { - u64 ept_mem_type = (spte & 0x38) >> 3; - - if (ept_mem_type == 2 || ept_mem_type == 3 || - ept_mem_type == 7) { - printk(KERN_ERR "%s: ept_mem_type=0x%llx\n", - __func__, ept_mem_type); - WARN_ON(1); - } - } - } -} - static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { - u64 sptes[4]; - int nr_sptes, i, ret; + int ret; gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); + trace_kvm_fast_mmio(gpa); return 1; } - ret = handle_mmio_page_fault_common(vcpu, gpa, true); + ret = handle_mmio_page_fault(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) return x86_emulate_instruction(vcpu, gpa, 0, NULL, 0) == EMULATE_DONE; @@ -5856,13 +5939,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) return 1; /* It is the real ept misconfig */ - printk(KERN_ERR "EPT: Misconfiguration.\n"); - printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa); - - nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes); - - for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) - ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); + WARN_ON(1); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; @@ -6004,6 +6081,25 @@ static void update_ple_window_actual_max(void) ple_window_grow, INT_MIN); } +/* + * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. + */ +static void wakeup_handler(void) +{ + struct kvm_vcpu *vcpu; + int cpu = smp_processor_id(); + + spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu), + blocked_vcpu_list) { + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (pi_test_on(pi_desc) == 1) + kvm_vcpu_kick(vcpu); + } + spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); +} + static __init int hardware_setup(void) { int r = -ENOMEM, i, msr; @@ -6122,6 +6218,12 @@ static __init int hardware_setup(void) if (!cpu_has_vmx_apicv()) enable_apicv = 0; + if (cpu_has_vmx_tsc_scaling()) { + kvm_has_tsc_control = true; + kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_tsc_scaling_ratio_frac_bits = 48; + } + if (enable_apicv) kvm_x86_ops->update_cr8_intercept = NULL; else { @@ -6144,6 +6246,8 @@ static __init int hardware_setup(void) memcpy(vmx_msr_bitmap_longmode_x2apic, vmx_msr_bitmap_longmode, PAGE_SIZE); + set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ + if (enable_apicv) { for (msr = 0x800; msr <= 0x8ff; msr++) vmx_disable_intercept_msr_read_x2apic(msr); @@ -6188,6 +6292,8 @@ static __init int hardware_setup(void) kvm_x86_ops->enable_log_dirty_pt_masked = NULL; } + kvm_set_posted_intr_wakeup_handler(wakeup_handler); + return alloc_kvm_area(); out8: @@ -6256,6 +6362,11 @@ static int handle_mwait(struct kvm_vcpu *vcpu) return handle_nop(vcpu); } +static int handle_monitor_trap(struct kvm_vcpu *vcpu) +{ + return 1; +} + static int handle_monitor(struct kvm_vcpu *vcpu) { printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); @@ -6418,8 +6529,12 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) */ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) + u32 vmx_instruction_info, bool wr, gva_t *ret) { + gva_t off; + bool exn; + struct kvm_segment s; + /* * According to Vol. 3B, "Information for VM Exits Due to Instruction * Execution", on an exit, vmx_instruction_info holds most of the @@ -6444,22 +6559,63 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Addr = segment_base + offset */ /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); + off = exit_qualification; /* holds the displacement */ if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); + off += kvm_register_read(vcpu, base_reg); if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ + off += kvm_register_read(vcpu, index_reg)<<scaling; + vmx_get_segment(vcpu, &s, seg_reg); + *ret = s.base + off; if (addr_size == 1) /* 32 bit */ *ret &= 0xffffffff; - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ + /* Checks for #GP/#SS exceptions. */ + exn = false; + if (is_protmode(vcpu)) { + /* Protected mode: apply checks for segment validity in the + * following order: + * - segment type check (#GP(0) may be thrown) + * - usability check (#GP(0)/#SS(0)) + * - limit check (#GP(0)/#SS(0)) + */ + if (wr) + /* #GP(0) if the destination operand is located in a + * read-only data segment or any code segment. + */ + exn = ((s.type & 0xa) == 0 || (s.type & 8)); + else + /* #GP(0) if the source operand is located in an + * execute-only code segment + */ + exn = ((s.type & 0xa) == 8); + } + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is an only check for long mode. + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { + /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. + */ + exn = (s.unusable != 0); + /* Protected mode: #GP(0)/#SS(0) if the memory + * operand is outside the segment limit. + */ + exn = exn || (off + sizeof(u64) > s.limit); + } + if (exn) { + kvm_queue_exception_e(vcpu, + seg_reg == VCPU_SREG_SS ? + SS_VECTOR : GP_VECTOR, + 0); + return 1; + } + return 0; } @@ -6481,7 +6637,7 @@ static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, @@ -6669,7 +6825,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) { - u32 exec_control; if (vmx->nested.current_vmptr == -1ull) return; @@ -6682,9 +6837,8 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx) they were modified */ copy_shadow_to_vmcs12(vmx); vmx->nested.sync_shadow_vmcs = false; - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_SHADOW_VMCS; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, -1ull); } vmx->nested.posted_intr_nv = -1; @@ -6704,6 +6858,7 @@ static void free_nested(struct vcpu_vmx *vmx) return; vmx->nested.vmxon = false; + free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); @@ -7009,7 +7164,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) field_value); } else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, true, &gva)) return 1; /* _system ok, as nested_vmx_check_permission verified cpl=0 */ kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva, @@ -7046,7 +7201,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) (((vmx_instruction_info) >> 3) & 0xf)); else { if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &field_value, (is_64_bit_mode(vcpu) ? 8 : 4), &e)) { @@ -7080,7 +7235,6 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); gpa_t vmptr; - u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; @@ -7112,9 +7266,8 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) vmx->nested.current_vmcs12 = new_vmcs12; vmx->nested.current_vmcs12_page = page; if (enable_shadow_vmcs) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_SHADOW_VMCS; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, __pa(vmx->nested.current_shadow_vmcs)); vmx->nested.sync_shadow_vmcs = true; @@ -7138,7 +7291,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return 1; if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, &vmcs_gva)) + vmx_instruction_info, true, &vmcs_gva)) return 1; /* ok to use *_system, as nested_vmx_check_permission verified cpl=0 */ if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva, @@ -7194,7 +7347,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) * operand is read even if it isn't needed (e.g., for type==global) */ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmx_instruction_info, &gva)) + vmx_instruction_info, false, &gva)) return 1; if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, sizeof(operand), &e)) { @@ -7220,7 +7373,58 @@ static int handle_invept(struct kvm_vcpu *vcpu) static int handle_invvpid(struct kvm_vcpu *vcpu) { - kvm_queue_exception(vcpu, UD_VECTOR); + struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 vmx_instruction_info; + unsigned long type, types; + gva_t gva; + struct x86_exception e; + int vpid; + + if (!(vmx->nested.nested_vmx_secondary_ctls_high & + SECONDARY_EXEC_ENABLE_VPID) || + !(vmx->nested.nested_vmx_vpid_caps & VMX_VPID_INVVPID_BIT)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + type = kvm_register_readl(vcpu, (vmx_instruction_info >> 28) & 0xf); + + types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7; + + if (!(types & (1UL << type))) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return 1; + } + + /* according to the intel vmx instruction reference, the memory + * operand is read even if it isn't needed (e.g., for type==global) + */ + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmx_instruction_info, false, &gva)) + return 1; + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid, + sizeof(u32), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (type) { + case VMX_VPID_EXTENT_ALL_CONTEXT: + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + nested_vmx_succeed(vcpu); + break; + default: + /* Trap single context invalidation invvpid calls */ + BUG_ON(1); + break; + } + + skip_emulated_instruction(vcpu); return 1; } @@ -7249,6 +7453,13 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } +static int handle_pcommit(struct kvm_vcpu *vcpu) +{ + /* we never catch pcommit instruct for L1 guest. */ + WARN_ON(1); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -7292,12 +7503,14 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_TRAP_FLAG] = handle_monitor_trap, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, [EXIT_REASON_INVVPID] = handle_invvpid, [EXIT_REASON_XSAVES] = handle_xsaves, [EXIT_REASON_XRSTORS] = handle_xrstors, [EXIT_REASON_PML_FULL] = handle_pml_full, + [EXIT_REASON_PCOMMIT] = handle_pcommit, }; static const int kvm_vmx_max_exit_handlers = @@ -7333,7 +7546,7 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) - if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap, &b, 1)) return true; if (b & (1 << (port & 7))) return true; @@ -7377,7 +7590,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, /* Then read the msr_index'th bit from this bitmap: */ if (msr_index < 1024*8) { unsigned char b; - if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) + if (kvm_vcpu_read_guest(vcpu, bitmap + msr_index/8, &b, 1)) return true; return 1 & (b >> (msr_index & 7)); } else @@ -7552,6 +7765,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); + case EXIT_REASON_MONITOR_TRAP_FLAG: + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); case EXIT_REASON_MONITOR_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING); case EXIT_REASON_PAUSE_INSTRUCTION: @@ -7597,6 +7812,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * the XSS exit bitmap in vmcs12. */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); + case EXIT_REASON_PCOMMIT: + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_PCOMMIT); default: return true; } @@ -7608,10 +7825,9 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) *info2 = vmcs_read32(VM_EXIT_INTR_INFO); } -static int vmx_enable_pml(struct vcpu_vmx *vmx) +static int vmx_create_pml_buffer(struct vcpu_vmx *vmx) { struct page *pml_pg; - u32 exec_control; pml_pg = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!pml_pg) @@ -7622,29 +7838,20 @@ static int vmx_enable_pml(struct vcpu_vmx *vmx) vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_ENABLE_PML; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); - return 0; } -static void vmx_disable_pml(struct vcpu_vmx *vmx) +static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { - u32 exec_control; - - ASSERT(vmx->pml_pg); - __free_page(vmx->pml_pg); - vmx->pml_pg = NULL; - - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_ENABLE_PML; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); + if (vmx->pml_pg) { + __free_page(vmx->pml_pg); + vmx->pml_pg = NULL; + } } -static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) +static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vmx->vcpu.kvm; + struct vcpu_vmx *vmx = to_vmx(vcpu); u64 *pml_buf; u16 pml_idx; @@ -7666,7 +7873,7 @@ static void vmx_flush_pml_buffer(struct vcpu_vmx *vmx) gpa = pml_buf[pml_idx]; WARN_ON(gpa & (PAGE_SIZE - 1)); - mark_page_dirty(kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ @@ -7691,6 +7898,161 @@ static void kvm_flush_pml_buffers(struct kvm *kvm) kvm_vcpu_kick(vcpu); } +static void vmx_dump_sel(char *name, uint32_t sel) +{ + pr_err("%s sel=0x%04x, attr=0x%05x, limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(sel), + vmcs_read32(sel + GUEST_ES_AR_BYTES - GUEST_ES_SELECTOR), + vmcs_read32(sel + GUEST_ES_LIMIT - GUEST_ES_SELECTOR), + vmcs_readl(sel + GUEST_ES_BASE - GUEST_ES_SELECTOR)); +} + +static void vmx_dump_dtsel(char *name, uint32_t limit) +{ + pr_err("%s limit=0x%08x, base=0x%016lx\n", + name, vmcs_read32(limit), + vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT)); +} + +static void dump_vmcs(void) +{ + u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS); + u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS); + u32 cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); + u32 secondary_exec_control = 0; + unsigned long cr4 = vmcs_readl(GUEST_CR4); + u64 efer = vmcs_readl(GUEST_IA32_EFER); + int i, n; + + if (cpu_has_secondary_exec_ctrls()) + secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + pr_err("*** Guest State ***\n"); + pr_err("CR0: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + vmcs_readl(GUEST_CR0), vmcs_readl(CR0_READ_SHADOW), + vmcs_readl(CR0_GUEST_HOST_MASK)); + pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n", + cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK)); + pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && + (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) + { + pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n", + vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3)); + } + pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", + vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); + pr_err("RFLAGS=0x%08lx DR7 = 0x%016lx\n", + vmcs_readl(GUEST_RFLAGS), vmcs_readl(GUEST_DR7)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(GUEST_SYSENTER_ESP), + vmcs_read32(GUEST_SYSENTER_CS), vmcs_readl(GUEST_SYSENTER_EIP)); + vmx_dump_sel("CS: ", GUEST_CS_SELECTOR); + vmx_dump_sel("DS: ", GUEST_DS_SELECTOR); + vmx_dump_sel("SS: ", GUEST_SS_SELECTOR); + vmx_dump_sel("ES: ", GUEST_ES_SELECTOR); + vmx_dump_sel("FS: ", GUEST_FS_SELECTOR); + vmx_dump_sel("GS: ", GUEST_GS_SELECTOR); + vmx_dump_dtsel("GDTR:", GUEST_GDTR_LIMIT); + vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR); + vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT); + vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); + if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || + (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) + pr_err("EFER = 0x%016llx PAT = 0x%016lx\n", + efer, vmcs_readl(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n", + vmcs_readl(GUEST_IA32_DEBUGCTL), + vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); + if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL)); + if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) + pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("Interruptibility = %08x ActivityState = %08x\n", + vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), + vmcs_read32(GUEST_ACTIVITY_STATE)); + if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) + pr_err("InterruptStatus = %04x\n", + vmcs_read16(GUEST_INTR_STATUS)); + + pr_err("*** Host State ***\n"); + pr_err("RIP = 0x%016lx RSP = 0x%016lx\n", + vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP)); + pr_err("CS=%04x SS=%04x DS=%04x ES=%04x FS=%04x GS=%04x TR=%04x\n", + vmcs_read16(HOST_CS_SELECTOR), vmcs_read16(HOST_SS_SELECTOR), + vmcs_read16(HOST_DS_SELECTOR), vmcs_read16(HOST_ES_SELECTOR), + vmcs_read16(HOST_FS_SELECTOR), vmcs_read16(HOST_GS_SELECTOR), + vmcs_read16(HOST_TR_SELECTOR)); + pr_err("FSBase=%016lx GSBase=%016lx TRBase=%016lx\n", + vmcs_readl(HOST_FS_BASE), vmcs_readl(HOST_GS_BASE), + vmcs_readl(HOST_TR_BASE)); + pr_err("GDTBase=%016lx IDTBase=%016lx\n", + vmcs_readl(HOST_GDTR_BASE), vmcs_readl(HOST_IDTR_BASE)); + pr_err("CR0=%016lx CR3=%016lx CR4=%016lx\n", + vmcs_readl(HOST_CR0), vmcs_readl(HOST_CR3), + vmcs_readl(HOST_CR4)); + pr_err("Sysenter RSP=%016lx CS:RIP=%04x:%016lx\n", + vmcs_readl(HOST_IA32_SYSENTER_ESP), + vmcs_read32(HOST_IA32_SYSENTER_CS), + vmcs_readl(HOST_IA32_SYSENTER_EIP)); + if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) + pr_err("EFER = 0x%016lx PAT = 0x%016lx\n", + vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT)); + if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) + pr_err("PerfGlobCtl = 0x%016lx\n", + vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL)); + + pr_err("*** Control State ***\n"); + pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", + pin_based_exec_ctrl, cpu_based_exec_ctrl, secondary_exec_control); + pr_err("EntryControls=%08x ExitControls=%08x\n", vmentry_ctl, vmexit_ctl); + pr_err("ExceptionBitmap=%08x PFECmask=%08x PFECmatch=%08x\n", + vmcs_read32(EXCEPTION_BITMAP), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MASK), + vmcs_read32(PAGE_FAULT_ERROR_CODE_MATCH)); + pr_err("VMEntry: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_ENTRY_INTR_INFO_FIELD), + vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE), + vmcs_read32(VM_ENTRY_INSTRUCTION_LEN)); + pr_err("VMExit: intr_info=%08x errcode=%08x ilen=%08x\n", + vmcs_read32(VM_EXIT_INTR_INFO), + vmcs_read32(VM_EXIT_INTR_ERROR_CODE), + vmcs_read32(VM_EXIT_INSTRUCTION_LEN)); + pr_err(" reason=%08x qualification=%016lx\n", + vmcs_read32(VM_EXIT_REASON), vmcs_readl(EXIT_QUALIFICATION)); + pr_err("IDTVectoring: info=%08x errcode=%08x\n", + vmcs_read32(IDT_VECTORING_INFO_FIELD), + vmcs_read32(IDT_VECTORING_ERROR_CODE)); + pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) + pr_err("TSC Multiplier = 0x%016lx\n", + vmcs_readl(TSC_MULTIPLIER)); + if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) + pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); + if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) + pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); + if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) + pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER)); + n = vmcs_read32(CR3_TARGET_COUNT); + for (i = 0; i + 1 < n; i += 4) + pr_err("CR3 target%u=%016lx target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2), + i + 1, vmcs_readl(CR3_TARGET_VALUE0 + i * 2 + 2)); + if (i < n) + pr_err("CR3 target%u=%016lx\n", + i, vmcs_readl(CR3_TARGET_VALUE0 + i * 2)); + if (secondary_exec_control & SECONDARY_EXEC_PAUSE_LOOP_EXITING) + pr_err("PLE Gap=%08x Window=%08x\n", + vmcs_read32(PLE_GAP), vmcs_read32(PLE_WINDOW)); + if (secondary_exec_control & SECONDARY_EXEC_ENABLE_VPID) + pr_err("Virtual processor ID = 0x%04x\n", + vmcs_read16(VIRTUAL_PROCESSOR_ID)); +} + /* * The guest has exited. See if we can fix it or if we need userspace * assistance. @@ -7701,6 +8063,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) u32 exit_reason = vmx->exit_reason; u32 vectoring_info = vmx->idt_vectoring_info; + trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX); + /* * Flush logged GPAs PML buffer, this will make dirty_bitmap more * updated. Another good is, in kvm_vm_ioctl_get_dirty_log, before @@ -7709,7 +8073,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) * flushed already. */ if (enable_pml) - vmx_flush_pml_buffer(vmx); + vmx_flush_pml_buffer(vcpu); /* If guest state is invalid, start emulating */ if (vmx->emulation_required) @@ -7723,6 +8087,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) } if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) { + dump_vmcs(); vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason; @@ -7810,10 +8175,10 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) * apicv */ if (!cpu_has_vmx_virtualize_x2apic_mode() || - !vmx_vm_has_apicv(vcpu->kvm)) + !vmx_cpu_uses_apicv(vcpu)) return; - if (!vm_need_tpr_shadow(vcpu->kvm)) + if (!cpu_need_tpr_shadow(vcpu)) return; sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); @@ -7915,9 +8280,10 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - if (!vmx_vm_has_apicv(vcpu->kvm)) + u64 *eoi_exit_bitmap = vcpu->arch.eoi_exit_bitmap; + if (!vmx_cpu_uses_apicv(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); @@ -7996,6 +8362,11 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) local_irq_enable(); } +static bool vmx_has_high_real_mode_segbase(void) +{ + return enable_unrestricted_guest || emulate_invalid_guest_state; +} + static bool vmx_mpx_supported(void) { return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_BNDCFGS) && @@ -8320,7 +8691,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->loaded_vmcs->launched = 1; vmx->exit_reason = vmcs_read32(VM_EXIT_REASON); - trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX); /* * the KVM_REQ_EVENT optimization bit is only on for one entry, and if @@ -8358,8 +8728,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); if (enable_pml) - vmx_disable_pml(vmx); - free_vpid(vmx); + vmx_destroy_pml_buffer(vmx); + free_vpid(vmx->vpid); leave_guest_mode(vcpu); vmx_load_vmcs01(vcpu); free_nested(vmx); @@ -8378,7 +8748,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) if (!vmx) return ERR_PTR(-ENOMEM); - allocate_vpid(vmx); + vmx->vpid = allocate_vpid(); err = kvm_vcpu_init(&vmx->vcpu, kvm, id); if (err) @@ -8411,7 +8781,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) put_cpu(); if (err) goto free_vmcs; - if (vm_need_virtualize_apic_accesses(kvm)) { + if (cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { err = alloc_apic_access_page(kvm); if (err) goto free_vmcs; @@ -8426,8 +8796,10 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) + if (nested) { nested_vmx_setup_ctls_msrs(vmx); + vmx->nested.vpid02 = allocate_vpid(); + } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -8440,7 +8812,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) * for the guest, etc. */ if (enable_pml) { - err = vmx_enable_pml(vmx); + err = vmx_create_pml_buffer(vmx); if (err) goto free_vmcs; } @@ -8448,13 +8820,14 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: + free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); free_vcpu: - free_vpid(vmx); + free_vpid(vmx->vpid); kmem_cache_free(kvm_vcpu_cache, vmx); return ERR_PTR(err); } @@ -8480,7 +8853,8 @@ static int get_ept_level(void) static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u64 ret; + u8 cache; + u64 ipat = 0; /* For VT-d and EPT combination * 1. MMIO: always map as UC @@ -8493,16 +8867,30 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (is_mmio) - ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT; - else if (kvm_arch_has_noncoherent_dma(vcpu->kvm)) - ret = kvm_get_guest_memory_type(vcpu, gfn) << - VMX_EPT_MT_EPTE_SHIFT; - else - ret = (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) - | VMX_EPT_IPAT_BIT; + if (is_mmio) { + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } - return ret; + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + ipat = VMX_EPT_IPAT_BIT; + cache = MTRR_TYPE_WRBACK; + goto exit; + } + + if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + ipat = VMX_EPT_IPAT_BIT; + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cache = MTRR_TYPE_WRBACK; + else + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn); + +exit: + return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat; } static int vmx_get_lpage_level(void) @@ -8514,49 +8902,68 @@ static int vmx_get_lpage_level(void) return PT_PDPE_LEVEL; } +static void vmcs_set_secondary_exec_control(u32 new_ctl) +{ + /* + * These bits in the secondary execution controls field + * are dynamic, the others are mostly based on the hypervisor + * architecture and the guest's CPUID. Do not touch the + * dynamic bits. + */ + u32 mask = + SECONDARY_EXEC_SHADOW_VMCS | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + + u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + + vmcs_write32(SECONDARY_VM_EXEC_CONTROL, + (new_ctl & ~mask) | (cur_ctl & mask)); +} + static void vmx_cpuid_update(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 exec_control; + u32 secondary_exec_ctl = vmx_secondary_exec_control(vmx); - vmx->rdtscp_enabled = false; if (vmx_rdtscp_supported()) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - if (exec_control & SECONDARY_EXEC_RDTSCP) { - best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (best && (best->edx & bit(X86_FEATURE_RDTSCP))) - vmx->rdtscp_enabled = true; - else { - exec_control &= ~SECONDARY_EXEC_RDTSCP; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } + bool rdtscp_enabled = guest_cpuid_has_rdtscp(vcpu); + if (!rdtscp_enabled) + secondary_exec_ctl &= ~SECONDARY_EXEC_RDTSCP; + + if (nested) { + if (rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_RDTSCP; + else + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } - if (nested && !vmx->rdtscp_enabled) - vmx->nested.nested_vmx_secondary_ctls_high &= - ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ best = kvm_find_cpuid_entry(vcpu, 0x7, 0); if (vmx_invpcid_supported() && - best && (best->ebx & bit(X86_FEATURE_INVPCID)) && - guest_cpuid_has_pcid(vcpu)) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control |= SECONDARY_EXEC_ENABLE_INVPCID; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } else { - if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); - exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID; - vmcs_write32(SECONDARY_VM_EXEC_CONTROL, - exec_control); - } + (!best || !(best->ebx & bit(X86_FEATURE_INVPCID)) || + !guest_cpuid_has_pcid(vcpu))) { + secondary_exec_ctl &= ~SECONDARY_EXEC_ENABLE_INVPCID; + if (best) best->ebx &= ~bit(X86_FEATURE_INVPCID); } + + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); + + if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { + if (guest_cpuid_has_pcommit(vcpu)) + vmx->nested.nested_vmx_secondary_ctls_high |= + SECONDARY_EXEC_PCOMMIT; + else + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_PCOMMIT; + } } static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) @@ -8924,7 +9331,7 @@ static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu, struct vmx_msr_entry *e) { /* x2APIC MSR accesses are not allowed */ - if (apic_x2apic_mode(vcpu->arch.apic) && e->index >> 8 == 0x8) + if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8) return -EINVAL; if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */ e->index == MSR_IA32_UCODE_REV) @@ -8966,8 +9373,8 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) msr.host_initiated = false; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, gpa + i * sizeof(e), - &e, sizeof(e))) { + if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e), + &e, sizeof(e))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -8999,9 +9406,10 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) struct vmx_msr_entry e; for (i = 0; i < count; i++) { - if (kvm_read_guest(vcpu->kvm, - gpa + i * sizeof(e), - &e, 2 * sizeof(u32))) { + struct msr_data msr_info; + if (kvm_vcpu_read_guest(vcpu, + gpa + i * sizeof(e), + &e, 2 * sizeof(u32))) { pr_warn_ratelimited( "%s cannot read MSR entry (%u, 0x%08llx)\n", __func__, i, gpa + i * sizeof(e)); @@ -9013,19 +9421,21 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count) __func__, i, e.index, e.reserved); return -EINVAL; } - if (kvm_get_msr(vcpu, e.index, &e.value)) { + msr_info.host_initiated = false; + msr_info.index = e.index; + if (kvm_get_msr(vcpu, &msr_info)) { pr_warn_ratelimited( "%s cannot read MSR (%u, 0x%x)\n", __func__, i, e.index); return -EINVAL; } - if (kvm_write_guest(vcpu->kvm, - gpa + i * sizeof(e) + - offsetof(struct vmx_msr_entry, value), - &e.value, sizeof(e.value))) { + if (kvm_vcpu_write_guest(vcpu, + gpa + i * sizeof(e) + + offsetof(struct vmx_msr_entry, value), + &msr_info.data, sizeof(msr_info.data))) { pr_warn_ratelimited( "%s cannot write MSR (%u, 0x%x, 0x%llx)\n", - __func__, i, e.index, e.value); + __func__, i, e.index, msr_info.data); return -EINVAL; } } @@ -9161,13 +9571,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (cpu_has_secondary_exec_ctrls()) { exec_control = vmx_secondary_exec_control(vmx); - if (!vmx->rdtscp_enabled) - exec_control &= ~SECONDARY_EXEC_RDTSCP; + /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT | + SECONDARY_EXEC_PCOMMIT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9186,7 +9596,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(vmx->nested.apic_access_page)); } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))) { + cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; kvm_vcpu_reload_apic_access_page(vcpu); @@ -9296,12 +9706,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (enable_vpid) { /* - * Trivially support vpid by letting L2s share their parent - * L1's vpid. TODO: move to a more elaborate solution, giving - * each L2 its own vpid and exposing the vpid feature to L1. + * There is no direct mapping between vpid02 and vpid12, the + * vpid02 is per-vCPU for L0 and reused while the value of + * vpid12 is changed w/ one invvpid during nested vmentry. + * The vpid12 is allocated by L1 for L2, so it will not + * influence global bitmap(for vpid01 and vpid02 allocation) + * even if spawn a lot of nested vCPUs. */ - vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx_flush_tlb(vcpu); + if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) { + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02); + if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { + vmx->nested.last_vpid = vmcs12->virtual_processor_id; + __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); + } + } else { + vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); + vmx_flush_tlb(vcpu); + } + } if (nested_cpu_has_ept(vmcs12)) { @@ -10141,6 +10563,201 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm, kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask); } +/* + * This routine does the following things for vCPU which is going + * to be blocked if VT-d PI is enabled. + * - Store the vCPU to the wakeup list, so when interrupts happen + * we can find the right vCPU to wake up. + * - Change the Posted-interrupt descriptor as below: + * 'NDST' <-- vcpu->pre_pcpu + * 'NV' <-- POSTED_INTR_WAKEUP_VECTOR + * - If 'ON' is set during this process, which means at least one + * interrupt is posted for this vCPU, we cannot block it, in + * this case, return 1, otherwise, return 0. + * + */ +static int vmx_pre_block(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + unsigned int dest; + struct pi_desc old, new; + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + vcpu->pre_pcpu = vcpu->cpu; + spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_add_tail(&vcpu->blocked_vcpu_list, + &per_cpu(blocked_vcpu_on_cpu, + vcpu->pre_pcpu)); + spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + + do { + old.control = new.control = pi_desc->control; + + /* + * We should not block the vCPU if + * an interrupt is posted for it. + */ + if (pi_test_on(pi_desc) == 1) { + spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + + return 1; + } + + WARN((pi_desc->sn == 1), + "Warning: SN field of posted-interrupts " + "is set before blocking\n"); + + /* + * Since vCPU can be preempted during this process, + * vcpu->cpu could be different with pre_pcpu, we + * need to set pre_pcpu as the destination of wakeup + * notification event, then we can find the right vCPU + * to wakeup in wakeup handler if interrupts happen + * when the vCPU is in blocked state. + */ + dest = cpu_physical_id(vcpu->pre_pcpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* set 'NV' to 'wakeup vector' */ + new.nv = POSTED_INTR_WAKEUP_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + return 0; +} + +static void vmx_post_block(struct kvm_vcpu *vcpu) +{ + struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct pi_desc old, new; + unsigned int dest; + unsigned long flags; + + if (!kvm_arch_has_assigned_device(vcpu->kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return; + + do { + old.control = new.control = pi_desc->control; + + dest = cpu_physical_id(vcpu->cpu); + + if (x2apic_enabled()) + new.ndst = dest; + else + new.ndst = (dest << 8) & 0xFF00; + + /* Allow posting non-urgent interrupts */ + new.sn = 0; + + /* set 'NV' to 'notification vector' */ + new.nv = POSTED_INTR_VECTOR; + } while (cmpxchg(&pi_desc->control, old.control, + new.control) != old.control); + + if(vcpu->pre_pcpu != -1) { + spin_lock_irqsave( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + list_del(&vcpu->blocked_vcpu_list); + spin_unlock_irqrestore( + &per_cpu(blocked_vcpu_on_cpu_lock, + vcpu->pre_pcpu), flags); + vcpu->pre_pcpu = -1; + } +} + +/* + * vmx_update_pi_irte - set IRTE for Posted-Interrupts + * + * @kvm: kvm + * @host_irq: host irq of the interrupt + * @guest_irq: gsi of the interrupt + * @set: set or unset PI + * returns 0 on success, < 0 on failure + */ +static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + struct kvm_kernel_irq_routing_entry *e; + struct kvm_irq_routing_table *irq_rt; + struct kvm_lapic_irq irq; + struct kvm_vcpu *vcpu; + struct vcpu_data vcpu_info; + int idx, ret = -EINVAL; + + if (!kvm_arch_has_assigned_device(kvm) || + !irq_remapping_cap(IRQ_POSTING_CAP)) + return 0; + + idx = srcu_read_lock(&kvm->irq_srcu); + irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); + BUG_ON(guest_irq >= irq_rt->nr_rt_entries); + + hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { + if (e->type != KVM_IRQ_ROUTING_MSI) + continue; + /* + * VT-d PI cannot support posting multicast/broadcast + * interrupts to a vCPU, we still use interrupt remapping + * for these kind of interrupts. + * + * For lowest-priority interrupts, we only support + * those with single CPU as the destination, e.g. user + * configures the interrupts via /proc/irq or uses + * irqbalance to make the interrupts single-CPU. + * + * We will support full lowest-priority interrupt later. + */ + + kvm_set_msi_irq(e, &irq); + if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) + continue; + + vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); + vcpu_info.vector = irq.vector; + + trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi, + vcpu_info.vector, vcpu_info.pi_desc_addr, set); + + if (set) + ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); + else { + /* suppress notification event before unposting */ + pi_set_sn(vcpu_to_pi_desc(vcpu)); + ret = irq_set_vcpu_affinity(host_irq, NULL); + pi_clear_sn(vcpu_to_pi_desc(vcpu)); + } + + if (ret < 0) { + printk(KERN_INFO "%s: failed to update PI IRTE\n", + __func__); + goto out; + } + } + + ret = 0; +out: + srcu_read_unlock(&kvm->irq_srcu, idx); + return ret; +} + static struct kvm_x86_ops vmx_x86_ops = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, @@ -10150,6 +10767,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .hardware_enable = hardware_enable, .hardware_disable = hardware_disable, .cpu_has_accelerated_tpr = report_flexpriority, + .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase, .vcpu_create = vmx_create_vcpu, .vcpu_free = vmx_free_vcpu, @@ -10159,7 +10777,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_load = vmx_vcpu_load, .vcpu_put = vmx_vcpu_put, - .update_db_bp_intercept = update_exception_bitmap, + .update_bp_intercept = update_exception_bitmap, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, @@ -10209,7 +10827,7 @@ static struct kvm_x86_ops vmx_x86_ops = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .vm_has_apicv = vmx_vm_has_apicv, + .cpu_uses_apicv = vmx_cpu_uses_apicv, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, @@ -10233,11 +10851,9 @@ static struct kvm_x86_ops vmx_x86_ops = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, - .set_tsc_khz = vmx_set_tsc_khz, .read_tsc_offset = vmx_read_tsc_offset, .write_tsc_offset = vmx_write_tsc_offset, - .adjust_tsc_offset = vmx_adjust_tsc_offset, - .compute_tsc_offset = vmx_compute_tsc_offset, + .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, @@ -10255,6 +10871,13 @@ static struct kvm_x86_ops vmx_x86_ops = { .slot_disable_log_dirty = vmx_slot_disable_log_dirty, .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, + + .pre_block = vmx_pre_block, + .post_block = vmx_post_block, + + .pmu_ops = &intel_pmu_ops, + + .update_pi_irte = vmx_update_pi_irte, }; static int __init vmx_init(void) @@ -10264,7 +10887,7 @@ static int __init vmx_init(void) if (r) return r; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); #endif @@ -10274,7 +10897,7 @@ static int __init vmx_init(void) static void __exit vmx_exit(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif diff --git a/kernel/arch/x86/kvm/x86.c b/kernel/arch/x86/kvm/x86.c index 37d79a026..27419ba5a 100644 --- a/kernel/arch/x86/kvm/x86.c +++ b/kernel/arch/x86/kvm/x86.c @@ -28,6 +28,8 @@ #include "x86.h" #include "cpuid.h" #include "assigned-dev.h" +#include "pmu.h" +#include "hyperv.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -49,6 +51,8 @@ #include <linux/pci.h> #include <linux/timekeeper_internal.h> #include <linux/pvclock_gtod.h> +#include <linux/kvm_irqfd.h> +#include <linux/irqbypass.h> #include <trace/events/kvm.h> #define CREATE_TRACE_POINTS @@ -57,13 +61,12 @@ #include <asm/debugreg.h> #include <asm/msr.h> #include <asm/desc.h> -#include <asm/mtrr.h> #include <asm/mce.h> -#include <asm/i387.h> -#include <asm/fpu-internal.h> /* Ugh! */ -#include <asm/xcr.h> +#include <linux/kernel_stat.h> +#include <asm/fpu/internal.h> /* Ugh! */ #include <asm/pvclock.h> #include <asm/div64.h> +#include <asm/irq_remapping.h> #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 @@ -90,29 +93,37 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); -struct kvm_x86_ops *kvm_x86_ops; +struct kvm_x86_ops *kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); -static bool ignore_msrs = 0; +static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); unsigned int min_timer_period_us = 500; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); -bool kvm_has_tsc_control; +static bool __read_mostly kvmclock_periodic_sync = true; +module_param(kvmclock_periodic_sync, bool, S_IRUGO); + +bool __read_mostly kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); -u32 kvm_max_guest_tsc_khz; +u32 __read_mostly kvm_max_guest_tsc_khz; EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); +u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits; +EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits); +u64 __read_mostly kvm_max_tsc_scaling_ratio; +EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); +static u64 __read_mostly kvm_default_tsc_scaling_ratio; /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ -static u32 tsc_tolerance_ppm = 250; +static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); /* lapic timer advance (tscdeadline mode only) in nanoseconds */ -unsigned int lapic_timer_advance_ns = 0; +unsigned int __read_mostly lapic_timer_advance_ns = 0; module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR); -static bool backwards_tsc_observed = false; +static bool __read_mostly backwards_tsc_observed = false; #define KVM_NR_SHARED_MSRS 16 @@ -146,6 +157,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { "nmi_window", VCPU_STAT(nmi_window_exits) }, { "halt_exits", VCPU_STAT(halt_exits) }, { "halt_successful_poll", VCPU_STAT(halt_successful_poll) }, + { "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) }, { "halt_wakeup", VCPU_STAT(halt_wakeup) }, { "hypercalls", VCPU_STAT(hypercalls) }, { "request_irq", VCPU_STAT(request_irq_exits) }, @@ -219,11 +231,9 @@ static void shared_msr_update(unsigned slot, u32 msr) void kvm_define_shared_msr(unsigned slot, u32 msr) { BUG_ON(slot >= KVM_NR_SHARED_MSRS); + shared_msrs_global.msrs[slot] = msr; if (slot >= shared_msrs_global.nr) shared_msrs_global.nr = slot + 1; - shared_msrs_global.msrs[slot] = msr; - /* we need ensured the shared_msr_global have been updated */ - smp_wmb(); } EXPORT_SYMBOL_GPL(kvm_define_shared_msr); @@ -475,7 +485,7 @@ EXPORT_SYMBOL_GPL(kvm_require_dr); /* * This function will be used to read from the physical memory of the currently - * running guest. The difference to kvm_read_guest_page is that this function + * running guest. The difference to kvm_vcpu_read_guest_page is that this function * can read from guest physical or from the guest's guest physical memory. */ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, @@ -493,7 +503,7 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, real_gfn = gpa_to_gfn(real_gfn); - return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len); + return kvm_vcpu_read_guest_page(vcpu, real_gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu); @@ -524,7 +534,8 @@ int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3) } for (i = 0; i < ARRAY_SIZE(pdpte); ++i) { if (is_present_gpte(pdpte[i]) && - (pdpte[i] & vcpu->arch.mmu.rsvd_bits_mask[0][2])) { + (pdpte[i] & + vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) { ret = 0; goto out; } @@ -572,8 +583,7 @@ out: int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { unsigned long old_cr0 = kvm_read_cr0(vcpu); - unsigned long update_bits = X86_CR0_PG | X86_CR0_WP | - X86_CR0_CD | X86_CR0_NW; + unsigned long update_bits = X86_CR0_PG | X86_CR0_WP; cr0 |= X86_CR0_ET; @@ -619,6 +629,12 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if ((cr0 ^ old_cr0) & update_bits) kvm_mmu_reset_context(vcpu); + + if (((cr0 ^ old_cr0) & X86_CR0_CD) && + kvm_arch_has_noncoherent_dma(vcpu->kvm) && + !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); + return 0; } EXPORT_SYMBOL_GPL(kvm_set_cr0); @@ -657,9 +673,9 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */ if (index != XCR_XFEATURE_ENABLED_MASK) return 1; - if (!(xcr0 & XSTATE_FP)) + if (!(xcr0 & XFEATURE_MASK_FP)) return 1; - if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE)) + if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE)) return 1; /* @@ -667,23 +683,24 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see fx_init). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP; + valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; - if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR))) + if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) != + (!(xcr0 & XFEATURE_MASK_BNDCSR))) return 1; - if (xcr0 & XSTATE_AVX512) { - if (!(xcr0 & XSTATE_YMM)) + if (xcr0 & XFEATURE_MASK_AVX512) { + if (!(xcr0 & XFEATURE_MASK_YMM)) return 1; - if ((xcr0 & XSTATE_AVX512) != XSTATE_AVX512) + if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; - if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK) + if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) kvm_update_cpuid(vcpu); return 0; } @@ -782,7 +799,7 @@ int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) return 1; - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) kvm_lapic_set_tpr(vcpu, cr8); else vcpu->arch.cr8 = cr8; @@ -792,7 +809,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr8); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) { - if (irqchip_in_kernel(vcpu->kvm)) + if (lapic_in_kernel(vcpu)) return kvm_lapic_get_cr8(vcpu); else return vcpu->arch.cr8; @@ -908,7 +925,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu) u64 data; int err; - err = kvm_pmu_read_pmc(vcpu, ecx, &data); + err = kvm_pmu_rdpmc(vcpu, ecx, &data); if (err) return err; kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); @@ -923,36 +940,45 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * * This list is modified at module load time to reflect the * capabilities of the host cpu. This capabilities test skips MSRs that are - * kvm-specific. Those are put in the beginning of the list. + * kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs + * may depend on host virtualization features rather than host cpu features. */ -#define KVM_SAVE_MSRS_BEGIN 12 static u32 msrs_to_save[] = { - MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, - HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, - HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, - HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, - MSR_KVM_PV_EOI_EN, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, - MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; -static const u32 emulated_msrs[] = { +static u32 emulated_msrs[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, + HV_X64_MSR_CRASH_P0, HV_X64_MSR_CRASH_P1, HV_X64_MSR_CRASH_P2, + HV_X64_MSR_CRASH_P3, HV_X64_MSR_CRASH_P4, HV_X64_MSR_CRASH_CTL, + HV_X64_MSR_RESET, + HV_X64_MSR_VP_INDEX, + HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, + MSR_KVM_PV_EOI_EN, + MSR_IA32_TSC_ADJUST, MSR_IA32_TSCDEADLINE, MSR_IA32_MISC_ENABLE, MSR_IA32_MCG_STATUS, MSR_IA32_MCG_CTL, + MSR_IA32_SMBASE, }; +static unsigned num_emulated_msrs; + bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { if (efer & efer_reserved_bits) @@ -1046,6 +1072,21 @@ EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention */ +static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) +{ + struct msr_data msr; + int r; + + msr.index = index; + msr.host_initiated = true; + r = kvm_get_msr(vcpu, &msr); + if (r) + return r; + + *data = msr.data; + return 0; +} + static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { struct msr_data msr; @@ -1193,11 +1234,6 @@ static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz, __func__, base_khz, scaled_khz, shift, *pmultiplier); } -static inline u64 get_kernel_ns(void) -{ - return ktime_get_boot_ns(); -} - #ifdef CONFIG_X86_64 static atomic_t kvm_guest_has_master_clock = ATOMIC_INIT(0); #endif @@ -1218,14 +1254,53 @@ static u32 adjust_tsc_khz(u32 khz, s32 ppm) return v; } -static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) +static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) +{ + u64 ratio; + + /* Guest TSC same frequency as host TSC? */ + if (!scale) { + vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + return 0; + } + + /* TSC scaling supported? */ + if (!kvm_has_tsc_control) { + if (user_tsc_khz > tsc_khz) { + vcpu->arch.tsc_catchup = 1; + vcpu->arch.tsc_always_catchup = 1; + return 0; + } else { + WARN(1, "user requested TSC rate below hardware speed\n"); + return -1; + } + } + + /* TSC scaling required - calculate ratio */ + ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits, + user_tsc_khz, tsc_khz); + + if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { + WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); + return -1; + } + + vcpu->arch.tsc_scaling_ratio = ratio; + return 0; +} + +static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) { u32 thresh_lo, thresh_hi; int use_scaling = 0; /* tsc_khz can be zero if TSC calibration fails */ - if (this_tsc_khz == 0) - return; + if (this_tsc_khz == 0) { + /* set tsc_scaling_ratio to a safe value */ + vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio; + return -1; + } /* Compute a scale to convert nanoseconds in TSC cycles */ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000, @@ -1245,7 +1320,7 @@ static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz) pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } - kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling); + return set_tsc_khz(vcpu, this_tsc_khz, use_scaling); } static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) @@ -1291,6 +1366,48 @@ static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset) vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset; } +/* + * Multiply tsc by a fixed point number represented by ratio. + * + * The most significant 64-N bits (mult) of ratio represent the + * integral part of the fixed point number; the remaining N bits + * (frac) represent the fractional part, ie. ratio represents a fixed + * point number (mult + frac * 2^(-N)). + * + * N equals to kvm_tsc_scaling_ratio_frac_bits. + */ +static inline u64 __scale_tsc(u64 ratio, u64 tsc) +{ + return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); +} + +u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +{ + u64 _tsc = tsc; + u64 ratio = vcpu->arch.tsc_scaling_ratio; + + if (ratio != kvm_default_tsc_scaling_ratio) + _tsc = __scale_tsc(ratio, tsc); + + return _tsc; +} +EXPORT_SYMBOL_GPL(kvm_scale_tsc); + +static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +{ + u64 tsc; + + tsc = kvm_scale_tsc(vcpu, rdtsc()); + + return target_tsc - tsc; +} + +u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) +{ + return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc)); +} +EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); + void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct kvm *kvm = vcpu->kvm; @@ -1302,7 +1419,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags); - offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + offset = kvm_compute_tsc_offset(vcpu, data); ns = get_kernel_ns(); elapsed = ns - kvm->arch.last_tsc_nsec; @@ -1359,7 +1476,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) } else { u64 delta = nsec_to_cycles(vcpu, elapsed); data += delta; - offset = kvm_x86_ops->compute_tsc_offset(vcpu, data); + offset = kvm_compute_tsc_offset(vcpu, data); pr_debug("kvm: adjusted tsc offset by %llu\n", delta); } matched = true; @@ -1416,24 +1533,26 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) EXPORT_SYMBOL_GPL(kvm_write_tsc); -#ifdef CONFIG_X86_64 +static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, + s64 adjustment) +{ + kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); +} -static cycle_t read_tsc(void) +static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - cycle_t ret; - u64 last; + if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + WARN_ON(adjustment < 0); + adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); + kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); +} - /* - * Empirically, a fence (of type that depends on the CPU) - * before rdtsc is enough to ensure that rdtsc is ordered - * with respect to loads. The various CPU manuals are unclear - * as to whether rdtsc can be reordered with later loads, - * but no one has ever seen it happen. - */ - rdtsc_barrier(); - ret = (cycle_t)vget_cycles(); +#ifdef CONFIG_X86_64 - last = pvclock_gtod_data.clock.cycle_last; +static cycle_t read_tsc(void) +{ + cycle_t ret = (cycle_t)rdtsc_ordered(); + u64 last = pvclock_gtod_data.clock.cycle_last; if (likely(ret >= last)) return ret; @@ -1589,7 +1708,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) static int kvm_guest_time_update(struct kvm_vcpu *v) { - unsigned long flags, this_tsc_khz; + unsigned long flags, this_tsc_khz, tgt_tsc_khz; struct kvm_vcpu_arch *vcpu = &v->arch; struct kvm_arch *ka = &v->kvm->arch; s64 kernel_ns; @@ -1622,11 +1741,11 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 1; } if (!use_master_clock) { - host_tsc = native_read_tsc(); + host_tsc = rdtsc(); kernel_ns = get_kernel_ns(); } - tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc); + tsc_timestamp = kvm_read_l1_tsc(v, host_tsc); /* * We may have to catch up the TSC to match elapsed wall clock @@ -1652,7 +1771,9 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) return 0; if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) { - kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz, + tgt_tsc_khz = kvm_has_tsc_control ? + vcpu->virtual_tsc_khz : this_tsc_khz; + kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz, &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = this_tsc_khz; @@ -1768,127 +1889,14 @@ static void kvmclock_sync_fn(struct work_struct *work) kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); + if (!kvmclock_periodic_sync) + return; + schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } -static bool msr_mtrr_valid(unsigned msr) -{ - switch (msr) { - case 0x200 ... 0x200 + 2 * KVM_NR_VAR_MTRR - 1: - case MSR_MTRRfix64K_00000: - case MSR_MTRRfix16K_80000: - case MSR_MTRRfix16K_A0000: - case MSR_MTRRfix4K_C0000: - case MSR_MTRRfix4K_C8000: - case MSR_MTRRfix4K_D0000: - case MSR_MTRRfix4K_D8000: - case MSR_MTRRfix4K_E0000: - case MSR_MTRRfix4K_E8000: - case MSR_MTRRfix4K_F0000: - case MSR_MTRRfix4K_F8000: - case MSR_MTRRdefType: - case MSR_IA32_CR_PAT: - return true; - case 0x2f8: - return true; - } - return false; -} - -static bool valid_pat_type(unsigned t) -{ - return t < 8 && (1 << t) & 0xf3; /* 0, 1, 4, 5, 6, 7 */ -} - -static bool valid_mtrr_type(unsigned t) -{ - return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */ -} - -bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - int i; - u64 mask; - - if (!msr_mtrr_valid(msr)) - return false; - - if (msr == MSR_IA32_CR_PAT) { - for (i = 0; i < 8; i++) - if (!valid_pat_type((data >> (i * 8)) & 0xff)) - return false; - return true; - } else if (msr == MSR_MTRRdefType) { - if (data & ~0xcff) - return false; - return valid_mtrr_type(data & 0xff); - } else if (msr >= MSR_MTRRfix64K_00000 && msr <= MSR_MTRRfix4K_F8000) { - for (i = 0; i < 8 ; i++) - if (!valid_mtrr_type((data >> (i * 8)) & 0xff)) - return false; - return true; - } - - /* variable MTRRs */ - WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR)); - - mask = (~0ULL) << cpuid_maxphyaddr(vcpu); - if ((msr & 1) == 0) { - /* MTRR base */ - if (!valid_mtrr_type(data & 0xff)) - return false; - mask |= 0xf00; - } else - /* MTRR mask */ - mask |= 0x7ff; - if (data & mask) { - kvm_inject_gp(vcpu, 0); - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(kvm_mtrr_valid); - -static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - - if (!kvm_mtrr_valid(vcpu, msr, data)) - return 1; - - if (msr == MSR_MTRRdefType) { - vcpu->arch.mtrr_state.def_type = data; - vcpu->arch.mtrr_state.enabled = (data & 0xc00) >> 10; - } else if (msr == MSR_MTRRfix64K_00000) - p[0] = data; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - p[1 + msr - MSR_MTRRfix16K_80000] = data; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - p[3 + msr - MSR_MTRRfix4K_C0000] = data; - else if (msr == MSR_IA32_CR_PAT) - vcpu->arch.pat = data; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pt = data; - } - - kvm_mmu_reset_context(vcpu); - return 0; -} - static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) { u64 mcg_cap = vcpu->arch.mcg_cap; @@ -1947,7 +1955,7 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) r = PTR_ERR(page); goto out; } - if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) goto out_free; r = 0; out_free: @@ -1956,123 +1964,6 @@ out: return r; } -static bool kvm_hv_hypercall_enabled(struct kvm *kvm) -{ - return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; -} - -static bool kvm_hv_msr_partition_wide(u32 msr) -{ - bool r = false; - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - case HV_X64_MSR_HYPERCALL: - case HV_X64_MSR_REFERENCE_TSC: - case HV_X64_MSR_TIME_REF_COUNT: - r = true; - break; - } - - return r; -} - -static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - kvm->arch.hv_guest_os_id = data; - /* setting guest os id to zero disables hypercall page */ - if (!kvm->arch.hv_guest_os_id) - kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; - break; - case HV_X64_MSR_HYPERCALL: { - u64 gfn; - unsigned long addr; - u8 instructions[4]; - - /* if guest os id is not set hypercall should remain disabled */ - if (!kvm->arch.hv_guest_os_id) - break; - if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { - kvm->arch.hv_hypercall = data; - break; - } - gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) - return 1; - kvm_x86_ops->patch_hypercall(vcpu, instructions); - ((unsigned char *)instructions)[3] = 0xc3; /* ret */ - if (__copy_to_user((void __user *)addr, instructions, 4)) - return 1; - kvm->arch.hv_hypercall = data; - mark_page_dirty(kvm, gfn); - break; - } - case HV_X64_MSR_REFERENCE_TSC: { - u64 gfn; - HV_REFERENCE_TSC_PAGE tsc_ref; - memset(&tsc_ref, 0, sizeof(tsc_ref)); - kvm->arch.hv_tsc_page = data; - if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE)) - break; - gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT; - if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT, - &tsc_ref, sizeof(tsc_ref))) - return 1; - mark_page_dirty(kvm, gfn); - break; - } - default: - vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); - return 1; - } - return 0; -} - -static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) -{ - switch (msr) { - case HV_X64_MSR_APIC_ASSIST_PAGE: { - u64 gfn; - unsigned long addr; - - if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { - vcpu->arch.hv_vapic = data; - if (kvm_lapic_enable_pv_eoi(vcpu, 0)) - return 1; - break; - } - gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; - addr = gfn_to_hva(vcpu->kvm, gfn); - if (kvm_is_error_hva(addr)) - return 1; - if (__clear_user((void __user *)addr, PAGE_SIZE)) - return 1; - vcpu->arch.hv_vapic = data; - mark_page_dirty(vcpu->kvm, gfn); - if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) - return 1; - break; - } - case HV_X64_MSR_EOI: - return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); - case HV_X64_MSR_ICR: - return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); - case HV_X64_MSR_TPR: - return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); - default: - vcpu_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " - "data 0x%llx\n", msr, data); - return 1; - } - - return 0; -} - static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) { gpa_t gpa = data & ~0x3f; @@ -2117,6 +2008,8 @@ static void accumulate_steal_time(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { + accumulate_steal_time(vcpu); + if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -2180,7 +2073,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) __func__, data); break; case 0x200 ... 0x2ff: - return set_msr_mtrr(vcpu, msr, data); + return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: @@ -2200,6 +2093,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_IA32_SMBASE: + if (!msr_info->host_initiated) + return 1; + vcpu->arch.smbase = data; + break; case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; @@ -2262,12 +2160,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!(data & KVM_MSR_ENABLED)) break; - vcpu->arch.st.last_steal = current->sched_info.run_delay; - - preempt_disable(); - accumulate_steal_time(vcpu); - preempt_enable(); - kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); break; @@ -2281,37 +2173,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: return set_msr_mce(vcpu, msr, data); - /* Performance counters are not protected by a CPUID bit, - * so we should check all of them in the generic path for the sake of - * cross vendor migration. - * Writing a zero into the event select MSRs disables them, - * which we perfectly emulate ;-). Any other value should be at least - * reported, some guests depend on them. - */ - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - if (data != 0) - vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); - break; - /* at least RHEL 4 unconditionally writes to the perfctr registers, - * so we ignore writes to make it happy. - */ - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: - vcpu_unimpl(vcpu, "unimplemented perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); - break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - pr = true; - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr)) + case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: + case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: + pr = true; /* fall through */ + case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: + case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: + if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (pr || data != 0) @@ -2329,15 +2196,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr)) { - int r; - mutex_lock(&vcpu->kvm->lock); - r = set_msr_hyperv_pw(vcpu, msr, data); - mutex_unlock(&vcpu->kvm->lock); - return r; - } else - return set_msr_hyperv(vcpu, msr, data); - break; + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_set_msr_common(vcpu, msr, data, + msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -2357,7 +2219,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); - if (kvm_pmu_msr(vcpu, msr)) + if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (!ignore_msrs) { vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", @@ -2379,48 +2241,12 @@ EXPORT_SYMBOL_GPL(kvm_set_msr_common); * Returns 0 on success, non-0 otherwise. * Assumes vcpu_load() was already called. */ -int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) +int kvm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { - return kvm_x86_ops->get_msr(vcpu, msr_index, pdata); + return kvm_x86_ops->get_msr(vcpu, msr); } EXPORT_SYMBOL_GPL(kvm_get_msr); -static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges; - - if (!msr_mtrr_valid(msr)) - return 1; - - if (msr == MSR_MTRRdefType) - *pdata = vcpu->arch.mtrr_state.def_type + - (vcpu->arch.mtrr_state.enabled << 10); - else if (msr == MSR_MTRRfix64K_00000) - *pdata = p[0]; - else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000) - *pdata = p[1 + msr - MSR_MTRRfix16K_80000]; - else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000) - *pdata = p[3 + msr - MSR_MTRRfix4K_C0000]; - else if (msr == MSR_IA32_CR_PAT) - *pdata = vcpu->arch.pat; - else { /* Variable MTRRs */ - int idx, is_mtrr_mask; - u64 *pt; - - idx = (msr - 0x200) / 2; - is_mtrr_mask = msr - 0x200 - 2 * idx; - if (!is_mtrr_mask) - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo; - else - pt = - (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo; - *pdata = *pt; - } - - return 0; -} - static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; @@ -2456,73 +2282,9 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } -static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data = 0; - struct kvm *kvm = vcpu->kvm; - - switch (msr) { - case HV_X64_MSR_GUEST_OS_ID: - data = kvm->arch.hv_guest_os_id; - break; - case HV_X64_MSR_HYPERCALL: - data = kvm->arch.hv_hypercall; - break; - case HV_X64_MSR_TIME_REF_COUNT: { - data = - div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); - break; - } - case HV_X64_MSR_REFERENCE_TSC: - data = kvm->arch.hv_tsc_page; - break; - default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); - return 1; - } - - *pdata = data; - return 0; -} - -static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) -{ - u64 data = 0; - - switch (msr) { - case HV_X64_MSR_VP_INDEX: { - int r; - struct kvm_vcpu *v; - kvm_for_each_vcpu(r, v, vcpu->kvm) { - if (v == vcpu) { - data = r; - break; - } - } - break; - } - case HV_X64_MSR_EOI: - return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); - case HV_X64_MSR_ICR: - return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); - case HV_X64_MSR_TPR: - return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); - case HV_X64_MSR_APIC_ASSIST_PAGE: - data = vcpu->arch.hv_vapic; - break; - default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); - return 1; - } - *pdata = data; - return 0; -} - -int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 data; - - switch (msr) { + switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: case MSR_IA32_DEBUGCTLMSR: @@ -2531,40 +2293,32 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: case MSR_K8_SYSCFG: + case MSR_K8_TSEG_ADDR: + case MSR_K8_TSEG_MASK: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: - case MSR_K7_EVNTSEL0: - case MSR_K7_EVNTSEL1: - case MSR_K7_EVNTSEL2: - case MSR_K7_EVNTSEL3: - case MSR_K7_PERFCTR0: - case MSR_K7_PERFCTR1: - case MSR_K7_PERFCTR2: - case MSR_K7_PERFCTR3: case MSR_K8_INT_PENDING_MSG: case MSR_AMD64_NB_CFG: case MSR_FAM10H_MMIO_CONF_BASE: case MSR_AMD64_BU_CFG2: - data = 0; + msr_info->data = 0; break; - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: - if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_get_msr(vcpu, msr, pdata); - data = 0; + case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: + case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: + case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: + case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); + msr_info->data = 0; break; case MSR_IA32_UCODE_REV: - data = 0x100000000ULL; + msr_info->data = 0x100000000ULL; break; case MSR_MTRRcap: - data = 0x500 | KVM_NR_VAR_MTRR; - break; case 0x200 ... 0x2ff: - return get_msr_mtrr(vcpu, msr, pdata); + return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); case 0xcd: /* fsb frequency */ - data = 3; + msr_info->data = 3; break; /* * MSR_EBC_FREQUENCY_ID @@ -2578,48 +2332,53 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * multiplying by zero otherwise. */ case MSR_EBC_FREQUENCY_ID: - data = 1 << 24; + msr_info->data = 1 << 24; break; case MSR_IA32_APICBASE: - data = kvm_get_apic_base(vcpu); + msr_info->data = kvm_get_apic_base(vcpu); break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: - return kvm_x2apic_msr_read(vcpu, msr, pdata); + return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); break; case MSR_IA32_TSCDEADLINE: - data = kvm_get_lapic_tscdeadline_msr(vcpu); + msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: - data = (u64)vcpu->arch.ia32_tsc_adjust_msr; + msr_info->data = (u64)vcpu->arch.ia32_tsc_adjust_msr; break; case MSR_IA32_MISC_ENABLE: - data = vcpu->arch.ia32_misc_enable_msr; + msr_info->data = vcpu->arch.ia32_misc_enable_msr; + break; + case MSR_IA32_SMBASE: + if (!msr_info->host_initiated) + return 1; + msr_info->data = vcpu->arch.smbase; break; case MSR_IA32_PERF_STATUS: /* TSC increment by tick */ - data = 1000ULL; + msr_info->data = 1000ULL; /* CPU multiplier */ - data |= (((uint64_t)4ULL) << 40); + msr_info->data |= (((uint64_t)4ULL) << 40); break; case MSR_EFER: - data = vcpu->arch.efer; + msr_info->data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: case MSR_KVM_WALL_CLOCK_NEW: - data = vcpu->kvm->arch.wall_clock; + msr_info->data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: case MSR_KVM_SYSTEM_TIME_NEW: - data = vcpu->arch.time; + msr_info->data = vcpu->arch.time; break; case MSR_KVM_ASYNC_PF_EN: - data = vcpu->arch.apf.msr_val; + msr_info->data = vcpu->arch.apf.msr_val; break; case MSR_KVM_STEAL_TIME: - data = vcpu->arch.st.msr_val; + msr_info->data = vcpu->arch.st.msr_val; break; case MSR_KVM_PV_EOI_EN: - data = vcpu->arch.pv_eoi.msr_val; + msr_info->data = vcpu->arch.pv_eoi.msr_val; break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: @@ -2627,7 +2386,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MCG_CTL: case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1: - return get_msr_mce(vcpu, msr, pdata); + return get_msr_mce(vcpu, msr_info->index, &msr_info->data); case MSR_K7_CLK_CTL: /* * Provide expected ramp-up count for K7. All other @@ -2638,17 +2397,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * type 6, model 8 and higher from exploding due to * the rdmsr failing. */ - data = 0x20000000; + msr_info->data = 0x20000000; break; case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: - if (kvm_hv_msr_partition_wide(msr)) { - int r; - mutex_lock(&vcpu->kvm->lock); - r = get_msr_hyperv_pw(vcpu, msr, pdata); - mutex_unlock(&vcpu->kvm->lock); - return r; - } else - return get_msr_hyperv(vcpu, msr, pdata); + case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: + case HV_X64_MSR_CRASH_CTL: + return kvm_hv_get_msr_common(vcpu, + msr_info->index, &msr_info->data); break; case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current @@ -2661,31 +2416,30 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) * L2 cache control register 3: 64GB range, 256KB size, * enabled, latency 0x1, configured */ - data = 0xbe702111; + msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has_osvw(vcpu)) return 1; - data = vcpu->arch.osvw.length; + msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: if (!guest_cpuid_has_osvw(vcpu)) return 1; - data = vcpu->arch.osvw.status; + msr_info->data = vcpu->arch.osvw.status; break; default: - if (kvm_pmu_msr(vcpu, msr)) - return kvm_pmu_get_msr(vcpu, msr, pdata); + if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) + return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data); if (!ignore_msrs) { - vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); + vcpu_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr_info->index); return 1; } else { - vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr); - data = 0; + vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index); + msr_info->data = 0; } break; } - *pdata = data; return 0; } EXPORT_SYMBOL_GPL(kvm_get_msr_common); @@ -2798,12 +2552,27 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: + case KVM_CAP_ENABLE_CAP_VM: + case KVM_CAP_DISABLE_QUIRKS: + case KVM_CAP_SET_BOOT_CPU_ID: + case KVM_CAP_SPLIT_IRQCHIP: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: #endif r = 1; break; + case KVM_CAP_X86_SMM: + /* SMBASE is usually relocated above 1M on modern chipsets, + * and SMM handlers might indeed rely on 4G segment limits, + * so do not report SMM to be available if real mode is + * emulated via vm86 mode. Still, do not go to great lengths + * to avoid userspace's usage of the feature, because it is a + * fringe case that is not enabled except via specific settings + * of the module parameters. + */ + r = kvm_x86_ops->cpu_has_high_real_mode_segbase(); + break; case KVM_CAP_COALESCED_MMIO: r = KVM_COALESCED_MMIO_PAGE_OFFSET; break; @@ -2860,7 +2629,7 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list)) goto out; n = msr_list.nmsrs; - msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs); + msr_list.nmsrs = num_msrs_to_save + num_emulated_msrs; if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list)) goto out; r = -E2BIG; @@ -2872,7 +2641,7 @@ long kvm_arch_dev_ioctl(struct file *filp, goto out; if (copy_to_user(user_msr_list->indices + num_msrs_to_save, &emulated_msrs, - ARRAY_SIZE(emulated_msrs) * sizeof(u32))) + num_emulated_msrs * sizeof(u32))) goto out; r = 0; break; @@ -2946,11 +2715,11 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) { s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 : - native_read_tsc() - vcpu->arch.last_host_tsc; + rdtsc() - vcpu->arch.last_host_tsc; if (tsc_delta < 0) mark_tsc_unstable("KVM discovered backwards TSC"); if (check_tsc_unstable()) { - u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu, + u64 offset = kvm_compute_tsc_offset(vcpu, vcpu->arch.last_guest_tsc); kvm_x86_ops->write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; @@ -2966,7 +2735,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; } - accumulate_steal_time(vcpu); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); } @@ -2974,7 +2742,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); - vcpu->arch.last_host_tsc = native_read_tsc(); + vcpu->arch.last_host_tsc = rdtsc(); } static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, @@ -2995,17 +2763,50 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu, return 0; } +static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu) +{ + return (!lapic_in_kernel(vcpu) || + kvm_apic_accept_pic_intr(vcpu)); +} + +/* + * if userspace requested an interrupt window, check that the + * interrupt window is open. + * + * No need to exit to userspace if we already have an interrupt queued. + */ +static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu) +{ + return kvm_arch_interrupt_allowed(vcpu) && + !kvm_cpu_has_interrupt(vcpu) && + !kvm_event_needs_reinjection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); +} + static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq) { if (irq->irq >= KVM_NR_INTERRUPTS) return -EINVAL; - if (irqchip_in_kernel(vcpu->kvm)) + + if (!irqchip_in_kernel(vcpu->kvm)) { + kvm_queue_interrupt(vcpu, irq->irq, false); + kvm_make_request(KVM_REQ_EVENT, vcpu); + return 0; + } + + /* + * With in-kernel LAPIC, we only use this to inject EXTINT, so + * fail for in-kernel 8259. + */ + if (pic_in_kernel(vcpu->kvm)) return -ENXIO; - kvm_queue_interrupt(vcpu, irq->irq, false); - kvm_make_request(KVM_REQ_EVENT, vcpu); + if (vcpu->arch.pending_external_vector != -1) + return -EEXIST; + vcpu->arch.pending_external_vector = irq->irq; + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; } @@ -3016,6 +2817,13 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) return 0; } +static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) +{ + kvm_make_request(KVM_REQ_SMI, vcpu); + + return 0; +} + static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -3121,8 +2929,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = 0; /* never valid when reporting to user space */ + events->smi.smm = is_smm(vcpu); + events->smi.pending = vcpu->arch.smi_pending; + events->smi.smm_inside_nmi = + !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); + events->smi.latched_init = kvm_lapic_latched_init(vcpu); + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SHADOW); + | KVM_VCPUEVENT_VALID_SHADOW + | KVM_VCPUEVENT_VALID_SMM); memset(&events->reserved, 0, sizeof(events->reserved)); } @@ -3131,7 +2946,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, { if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING | KVM_VCPUEVENT_VALID_SIPI_VECTOR - | KVM_VCPUEVENT_VALID_SHADOW)) + | KVM_VCPUEVENT_VALID_SHADOW + | KVM_VCPUEVENT_VALID_SMM)) return -EINVAL; process_nmi(vcpu); @@ -3156,6 +2972,24 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, kvm_vcpu_has_lapic(vcpu)) vcpu->arch.apic->sipi_vector = events->sipi_vector; + if (events->flags & KVM_VCPUEVENT_VALID_SMM) { + if (events->smi.smm) + vcpu->arch.hflags |= HF_SMM_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_MASK; + vcpu->arch.smi_pending = events->smi.pending; + if (events->smi.smm_inside_nmi) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; + if (kvm_vcpu_has_lapic(vcpu)) { + if (events->smi.latched_init) + set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + else + clear_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); + } + } + kvm_make_request(KVM_REQ_EVENT, vcpu); return 0; @@ -3194,8 +3028,8 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) { - struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; - u64 xstate_bv = xsave->xsave_hdr.xstate_bv; + struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave; + u64 xstate_bv = xsave->header.xfeatures; u64 valid; /* @@ -3211,7 +3045,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) * Copy each region from the possibly compacted offset to the * non-compacted offset. */ - valid = xstate_bv & ~XSTATE_FPSSE; + valid = xstate_bv & ~XFEATURE_MASK_FPSSE; while (valid) { u64 feature = valid & -valid; int index = fls64(feature) - 1; @@ -3230,7 +3064,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) { - struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave; + struct xregs_state *xsave = &vcpu->arch.guest_fpu.state.xsave; u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET); u64 valid; @@ -3241,15 +3075,15 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) memcpy(xsave, src, XSAVE_HDR_OFFSET); /* Set XSTATE_BV and possibly XCOMP_BV. */ - xsave->xsave_hdr.xstate_bv = xstate_bv; + xsave->header.xfeatures = xstate_bv; if (cpu_has_xsaves) - xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; + xsave->header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* * Copy each region from the non-compacted offset to the * possibly compacted offset. */ - valid = xstate_bv & ~XSTATE_FPSSE; + valid = xstate_bv & ~XFEATURE_MASK_FPSSE; while (valid) { u64 feature = valid & -valid; int index = fls64(feature) - 1; @@ -3260,8 +3094,7 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); memcpy(dest, src + offset, size); - } else - WARN_ON_ONCE(1); + } valid -= feature; } @@ -3275,10 +3108,10 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, fill_xsave((u8 *) guest_xsave->region, vcpu); } else { memcpy(guest_xsave->region, - &vcpu->arch.guest_fpu.state->fxsave, - sizeof(struct i387_fxsave_struct)); + &vcpu->arch.guest_fpu.state.fxsave, + sizeof(struct fxregs_state)); *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] = - XSTATE_FPSSE; + XFEATURE_MASK_FPSSE; } } @@ -3298,10 +3131,10 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { - if (xstate_bv & ~XSTATE_FPSSE) + if (xstate_bv & ~XFEATURE_MASK_FPSSE) return -EINVAL; - memcpy(&vcpu->arch.guest_fpu.state->fxsave, - guest_xsave->region, sizeof(struct i387_fxsave_struct)); + memcpy(&vcpu->arch.guest_fpu.state.fxsave, + guest_xsave->region, sizeof(struct fxregs_state)); } return 0; } @@ -3415,6 +3248,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_nmi(vcpu); break; } + case KVM_SMI: { + r = kvm_vcpu_ioctl_smi(vcpu); + break; + } case KVM_SET_CPUID: { struct kvm_cpuid __user *cpuid_arg = argp; struct kvm_cpuid cpuid; @@ -3454,7 +3291,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_GET_MSRS: - r = msr_io(vcpu, argp, kvm_get_msr, 1); + r = msr_io(vcpu, argp, do_get_msr, 1); break; case KVM_SET_MSRS: r = msr_io(vcpu, argp, do_set_msr, 0); @@ -3478,7 +3315,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_vapic_addr va; r = -EINVAL; - if (!irqchip_in_kernel(vcpu->kvm)) + if (!lapic_in_kernel(vcpu)) goto out; r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) @@ -3605,9 +3442,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (user_tsc_khz == 0) user_tsc_khz = tsc_khz; - kvm_set_tsc_khz(vcpu, user_tsc_khz); + if (!kvm_set_tsc_khz(vcpu, user_tsc_khz)) + r = 0; - r = 0; goto out; } case KVM_GET_TSC_KHZ: { @@ -3727,41 +3564,38 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps) { - int r = 0; - mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state)); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) { - int r = 0; - + int i; mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state)); - kvm_pit_load_count(kvm, 0, ps->channels[0].count, 0); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, ps->channels[i].count, 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { - int r = 0; - mutex_lock(&kvm->arch.vpit->pit_state.lock); memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels, sizeof(ps->channels)); ps->flags = kvm->arch.vpit->pit_state.flags; mutex_unlock(&kvm->arch.vpit->pit_state.lock); memset(&ps->reserved, 0, sizeof(ps->reserved)); - return r; + return 0; } static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) { - int r = 0, start = 0; + int start = 0; + int i; u32 prev_legacy, cur_legacy; mutex_lock(&kvm->arch.vpit->pit_state.lock); prev_legacy = kvm->arch.vpit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY; @@ -3771,9 +3605,11 @@ static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps) memcpy(&kvm->arch.vpit->pit_state.channels, &ps->channels, sizeof(kvm->arch.vpit->pit_state.channels)); kvm->arch.vpit->pit_state.flags = ps->flags; - kvm_pit_load_count(kvm, 0, kvm->arch.vpit->pit_state.channels[0].count, start); + for (i = 0; i < 3; i++) + kvm_pit_load_count(kvm, i, kvm->arch.vpit->pit_state.channels[i].count, + start && i == 0); mutex_unlock(&kvm->arch.vpit->pit_state.lock); - return r; + return 0; } static int kvm_vm_ioctl_reinject(struct kvm *kvm, @@ -3845,6 +3681,48 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, return 0; } +static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, + struct kvm_enable_cap *cap) +{ + int r; + + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_DISABLE_QUIRKS: + kvm->arch.disabled_quirks = cap->args[0]; + r = 0; + break; + case KVM_CAP_SPLIT_IRQCHIP: { + mutex_lock(&kvm->lock); + r = -EINVAL; + if (cap->args[0] > MAX_NR_RESERVED_IOAPIC_PINS) + goto split_irqchip_unlock; + r = -EEXIST; + if (irqchip_in_kernel(kvm)) + goto split_irqchip_unlock; + if (atomic_read(&kvm->online_vcpus)) + goto split_irqchip_unlock; + r = kvm_setup_empty_irq_routing(kvm); + if (r) + goto split_irqchip_unlock; + /* Pairs with irqchip_in_kernel. */ + smp_wmb(); + kvm->arch.irqchip_split = true; + kvm->arch.nr_reserved_ioapic_pins = cap->args[0]; + r = 0; +split_irqchip_unlock: + mutex_unlock(&kvm->lock); + break; + } + default: + r = -EINVAL; + break; + } + return r; +} + long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3897,30 +3775,25 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_ioapic_init(kvm); if (r) { mutex_lock(&kvm->slots_lock); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_master); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_slave); - kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, - &vpic->dev_eclr); + kvm_destroy_pic(vpic); mutex_unlock(&kvm->slots_lock); - kfree(vpic); goto create_irqchip_unlock; } } else goto create_irqchip_unlock; - smp_wmb(); - kvm->arch.vpic = vpic; - smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->slots_lock); mutex_lock(&kvm->irq_lock); kvm_ioapic_destroy(kvm); - kvm_destroy_pic(kvm); + kvm_destroy_pic(vpic); mutex_unlock(&kvm->irq_lock); mutex_unlock(&kvm->slots_lock); + goto create_irqchip_unlock; } + /* Write kvm->irq_routing before kvm->arch.vpic. */ + smp_wmb(); + kvm->arch.vpic = vpic; create_irqchip_unlock: mutex_unlock(&kvm->lock); break; @@ -3956,7 +3829,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -3980,7 +3853,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); if (r) @@ -4047,6 +3920,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_reinject(kvm, &control); break; } + case KVM_SET_BOOT_CPU_ID: + r = 0; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus) != 0) + r = -EBUSY; + else + kvm->arch.bsp_vcpu_id = arg; + mutex_unlock(&kvm->lock); + break; case KVM_XEN_HVM_CONFIG: { r = -EFAULT; if (copy_from_user(&kvm->arch.xen_hvm_config, argp, @@ -4097,7 +3979,15 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vm_ioctl_enable_cap(kvm, &cap); + break; + } default: r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } @@ -4110,23 +4000,23 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - /* skip the first msrs in the list. KVM-specific */ - for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { + for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } @@ -4136,6 +4026,22 @@ static void kvm_init_msr_list(void) j++; } num_msrs_to_save = j; + + for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) { + switch (emulated_msrs[i]) { + case MSR_IA32_SMBASE: + if (!kvm_x86_ops->cpu_has_high_real_mode_segbase()) + continue; + break; + default: + break; + } + + if (j < i) + emulated_msrs[j] = emulated_msrs[i]; + j++; + } + num_emulated_msrs = j; } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -4253,8 +4159,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data, - offset, toread); + ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, data, + offset, toread); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; @@ -4287,8 +4193,8 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, offset = addr & (PAGE_SIZE-1); if (WARN_ON(offset + bytes > PAGE_SIZE)) bytes = (unsigned)PAGE_SIZE - offset; - ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val, - offset, bytes); + ret = kvm_vcpu_read_guest_page(vcpu, gpa >> PAGE_SHIFT, val, + offset, bytes); if (unlikely(ret < 0)) return X86EMUL_IO_NEEDED; @@ -4315,6 +4221,15 @@ static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception); } +static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes); + + return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE; +} + int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, @@ -4334,7 +4249,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; - ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); + ret = kvm_vcpu_write_guest(vcpu, gpa, data, towrite); if (ret < 0) { r = X86EMUL_IO_NEEDED; goto out; @@ -4387,7 +4302,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, { int ret; - ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); + ret = kvm_vcpu_write_guest(vcpu, gpa, val, bytes); if (ret < 0) return 0; kvm_mmu_pte_write(vcpu, gpa, val, bytes); @@ -4421,7 +4336,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - return !kvm_read_guest(vcpu->kvm, gpa, val, bytes); + return !kvm_vcpu_read_guest(vcpu, gpa, val, bytes); } static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -4619,7 +4534,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) goto emul_write; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); if (is_error_page(page)) goto emul_write; @@ -4647,7 +4562,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (!exchanged) return X86EMUL_CMPXCHG_FAILED; - mark_page_dirty(vcpu->kvm, gpa >> PAGE_SHIFT); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); kvm_mmu_pte_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; @@ -4946,7 +4861,17 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector, static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata) { - return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); + struct msr_data msr; + int r; + + msr.index = msr_index; + msr.host_initiated = false; + r = kvm_get_msr(emul_to_vcpu(ctxt), &msr); + if (r) + return r; + + *pdata = msr.data; + return 0; } static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, @@ -4960,16 +4885,30 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, return kvm_set_msr(emul_to_vcpu(ctxt), &msr); } +static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + return vcpu->arch.smbase; +} + +static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + vcpu->arch.smbase = smbase; +} + static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { - return kvm_pmu_check_pmc(emul_to_vcpu(ctxt), pmc); + return kvm_pmu_is_valid_msr_idx(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata) { - return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); + return kvm_pmu_rdpmc(emul_to_vcpu(ctxt), pmc, pdata); } static void emulator_halt(struct x86_emulate_ctxt *ctxt) @@ -5026,6 +4965,7 @@ static const struct x86_emulate_ops emulate_ops = { .write_gpr = emulator_write_gpr, .read_std = kvm_read_guest_virt_system, .write_std = kvm_write_guest_virt_system, + .read_phys = kvm_read_guest_phys_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, @@ -5045,6 +4985,8 @@ static const struct x86_emulate_ops emulate_ops = { .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, + .get_smbase = emulator_get_smbase, + .set_smbase = emulator_set_smbase, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, @@ -5106,7 +5048,10 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - ctxt->guest_mode = is_guest_mode(vcpu); + BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); + BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); + BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); + ctxt->emul_flags = vcpu->arch.hflags; init_decode_cache(ctxt); vcpu->arch.emulate_regs_need_sync_from_vcpu = false; @@ -5275,6 +5220,34 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); +static void kvm_smm_changed(struct kvm_vcpu *vcpu) +{ + if (!(vcpu->arch.hflags & HF_SMM_MASK)) { + /* This is a good place to trace that we are exiting SMM. */ + trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, false); + + if (unlikely(vcpu->arch.smi_pending)) { + kvm_make_request(KVM_REQ_SMI, vcpu); + vcpu->arch.smi_pending = 0; + } else { + /* Process a latched INIT, if any. */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + } + + kvm_mmu_reset_context(vcpu); +} + +static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags) +{ + unsigned changed = vcpu->arch.hflags ^ emul_flags; + + vcpu->arch.hflags = emul_flags; + + if (changed & HF_SMM_MASK) + kvm_smm_changed(vcpu); +} + static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -5474,6 +5447,8 @@ restart: unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; + if (vcpu->arch.hflags != ctxt->emul_flags) + kvm_set_hflags(vcpu, ctxt->emul_flags); kvm_rip_write(vcpu, ctxt->eip); if (r == EMULATE_DONE) kvm_vcpu_check_singlestep(vcpu, rflags, &r); @@ -5870,7 +5845,7 @@ void kvm_arch_exit(void) int kvm_vcpu_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; - if (irqchip_in_kernel(vcpu->kvm)) { + if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = KVM_MP_STATE_HALTED; return 1; } else { @@ -5887,66 +5862,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); -int kvm_hv_hypercall(struct kvm_vcpu *vcpu) -{ - u64 param, ingpa, outgpa, ret; - uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; - bool fast, longmode; - - /* - * hypercall generates UD from non zero cpl and real mode - * per HYPER-V spec - */ - if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 0; - } - - longmode = is_64_bit_mode(vcpu); - - if (!longmode) { - param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); - ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); - outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | - (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); - } -#ifdef CONFIG_X86_64 - else { - param = kvm_register_read(vcpu, VCPU_REGS_RCX); - ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); - outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); - } -#endif - - code = param & 0xffff; - fast = (param >> 16) & 0x1; - rep_cnt = (param >> 32) & 0xfff; - rep_idx = (param >> 48) & 0xfff; - - trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); - - switch (code) { - case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: - kvm_vcpu_on_spin(vcpu); - break; - default: - res = HV_STATUS_INVALID_HYPERCALL_CODE; - break; - } - - ret = res | (((u64)rep_done & 0xfff) << 32); - if (longmode) { - kvm_register_write(vcpu, VCPU_REGS_RAX, ret); - } else { - kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); - kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); - } - - return 1; -} - /* * kvm_pv_kick_cpu_op: Kick a vcpu. * @@ -5959,6 +5874,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.shorthand = 0; lapic_irq.dest_mode = 0; lapic_irq.dest_id = apicid; + lapic_irq.msi_redir_hint = false; lapic_irq.delivery_mode = APIC_DM_REMRD; kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); @@ -6028,17 +5944,10 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -/* - * Check if userspace requested an interrupt window, and that the - * interrupt window is open. - * - * No need to exit to userspace if we already have an interrupt queued. - */ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { - return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && - vcpu->run->request_interrupt_window && - kvm_arch_interrupt_allowed(vcpu)); + return vcpu->run->request_interrupt_window && + likely(!pic_in_kernel(vcpu->kvm)); } static void post_kvm_run_save(struct kvm_vcpu *vcpu) @@ -6046,15 +5955,12 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - if (irqchip_in_kernel(vcpu->kvm)) - kvm_run->ready_for_interrupt_injection = 1; - else - kvm_run->ready_for_interrupt_injection = - kvm_arch_interrupt_allowed(vcpu) && - !kvm_cpu_has_interrupt(vcpu) && - !kvm_event_needs_reinjection(vcpu); + kvm_run->ready_for_interrupt_injection = + pic_in_kernel(vcpu->kvm) || + kvm_vcpu_ready_for_interrupt_injection(vcpu); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -6169,20 +6075,254 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } -static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) +#define put_smstate(type, buf, offset, val) \ + *(type *)((buf) + (offset) - 0x7e00) = val + +static u32 process_smi_get_segment_flags(struct kvm_segment *seg) { - u64 eoi_exit_bitmap[4]; - u32 tmr[8]; + u32 flags = 0; + flags |= seg->g << 23; + flags |= seg->db << 22; + flags |= seg->l << 21; + flags |= seg->avl << 20; + flags |= seg->present << 15; + flags |= seg->dpl << 13; + flags |= seg->s << 12; + flags |= seg->type << 8; + return flags; +} +static void process_smi_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) +{ + struct kvm_segment seg; + int offset; + + kvm_get_segment(vcpu, &seg, n); + put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector); + + if (n < 3) + offset = 0x7f84 + n * 12; + else + offset = 0x7f2c + (n - 3) * 12; + + put_smstate(u32, buf, offset + 8, seg.base); + put_smstate(u32, buf, offset + 4, seg.limit); + put_smstate(u32, buf, offset, process_smi_get_segment_flags(&seg)); +} + +#ifdef CONFIG_X86_64 +static void process_smi_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) +{ + struct kvm_segment seg; + int offset; + u16 flags; + + kvm_get_segment(vcpu, &seg, n); + offset = 0x7e00 + n * 16; + + flags = process_smi_get_segment_flags(&seg) >> 8; + put_smstate(u16, buf, offset, seg.selector); + put_smstate(u16, buf, offset + 2, flags); + put_smstate(u32, buf, offset + 4, seg.limit); + put_smstate(u64, buf, offset + 8, seg.base); +} +#endif + +static void process_smi_save_state_32(struct kvm_vcpu *vcpu, char *buf) +{ + struct desc_ptr dt; + struct kvm_segment seg; + unsigned long val; + int i; + + put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu)); + put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu)); + put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu)); + put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); + + for (i = 0; i < 8; i++) + put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read(vcpu, i)); + + kvm_get_dr(vcpu, 6, &val); + put_smstate(u32, buf, 0x7fcc, (u32)val); + kvm_get_dr(vcpu, 7, &val); + put_smstate(u32, buf, 0x7fc8, (u32)val); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); + put_smstate(u32, buf, 0x7fc4, seg.selector); + put_smstate(u32, buf, 0x7f64, seg.base); + put_smstate(u32, buf, 0x7f60, seg.limit); + put_smstate(u32, buf, 0x7f5c, process_smi_get_segment_flags(&seg)); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); + put_smstate(u32, buf, 0x7fc0, seg.selector); + put_smstate(u32, buf, 0x7f80, seg.base); + put_smstate(u32, buf, 0x7f7c, seg.limit); + put_smstate(u32, buf, 0x7f78, process_smi_get_segment_flags(&seg)); + + kvm_x86_ops->get_gdt(vcpu, &dt); + put_smstate(u32, buf, 0x7f74, dt.address); + put_smstate(u32, buf, 0x7f70, dt.size); + + kvm_x86_ops->get_idt(vcpu, &dt); + put_smstate(u32, buf, 0x7f58, dt.address); + put_smstate(u32, buf, 0x7f54, dt.size); + + for (i = 0; i < 6; i++) + process_smi_save_seg_32(vcpu, buf, i); + + put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); + + /* revision id */ + put_smstate(u32, buf, 0x7efc, 0x00020000); + put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); +} + +static void process_smi_save_state_64(struct kvm_vcpu *vcpu, char *buf) +{ +#ifdef CONFIG_X86_64 + struct desc_ptr dt; + struct kvm_segment seg; + unsigned long val; + int i; + + for (i = 0; i < 16; i++) + put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read(vcpu, i)); + + put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); + put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); + + kvm_get_dr(vcpu, 6, &val); + put_smstate(u64, buf, 0x7f68, val); + kvm_get_dr(vcpu, 7, &val); + put_smstate(u64, buf, 0x7f60, val); + + put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu)); + put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu)); + put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu)); + + put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase); + + /* revision id */ + put_smstate(u32, buf, 0x7efc, 0x00020064); + + put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); + put_smstate(u16, buf, 0x7e90, seg.selector); + put_smstate(u16, buf, 0x7e92, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u32, buf, 0x7e94, seg.limit); + put_smstate(u64, buf, 0x7e98, seg.base); + + kvm_x86_ops->get_idt(vcpu, &dt); + put_smstate(u32, buf, 0x7e84, dt.size); + put_smstate(u64, buf, 0x7e88, dt.address); + + kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); + put_smstate(u16, buf, 0x7e70, seg.selector); + put_smstate(u16, buf, 0x7e72, process_smi_get_segment_flags(&seg) >> 8); + put_smstate(u32, buf, 0x7e74, seg.limit); + put_smstate(u64, buf, 0x7e78, seg.base); + + kvm_x86_ops->get_gdt(vcpu, &dt); + put_smstate(u32, buf, 0x7e64, dt.size); + put_smstate(u64, buf, 0x7e68, dt.address); + + for (i = 0; i < 6; i++) + process_smi_save_seg_64(vcpu, buf, i); +#else + WARN_ON_ONCE(1); +#endif +} + +static void process_smi(struct kvm_vcpu *vcpu) +{ + struct kvm_segment cs, ds; + struct desc_ptr dt; + char buf[512]; + u32 cr0; + + if (is_smm(vcpu)) { + vcpu->arch.smi_pending = true; + return; + } + + trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true); + vcpu->arch.hflags |= HF_SMM_MASK; + memset(buf, 0, 512); + if (guest_cpuid_has_longmode(vcpu)) + process_smi_save_state_64(vcpu, buf); + else + process_smi_save_state_32(vcpu, buf); + + kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); + + if (kvm_x86_ops->get_nmi_mask(vcpu)) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + kvm_x86_ops->set_nmi_mask(vcpu, true); + + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0x8000); + + cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); + kvm_x86_ops->set_cr0(vcpu, cr0); + vcpu->arch.cr0 = cr0; + + kvm_x86_ops->set_cr4(vcpu, 0); + + /* Undocumented: IDT limit is set to zero on entry to SMM. */ + dt.address = dt.size = 0; + kvm_x86_ops->set_idt(vcpu, &dt); + + __kvm_set_dr(vcpu, 7, DR7_FIXED_1); + + cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; + cs.base = vcpu->arch.smbase; + + ds.selector = 0; + ds.base = 0; + + cs.limit = ds.limit = 0xffffffff; + cs.type = ds.type = 0x3; + cs.dpl = ds.dpl = 0; + cs.db = ds.db = 0; + cs.s = ds.s = 1; + cs.l = ds.l = 0; + cs.g = ds.g = 1; + cs.avl = ds.avl = 0; + cs.present = ds.present = 1; + cs.unusable = ds.unusable = 0; + cs.padding = ds.padding = 0; + + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); + kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); + + if (guest_cpuid_has_longmode(vcpu)) + kvm_x86_ops->set_efer(vcpu, 0); + + kvm_update_cpuid(vcpu); + kvm_mmu_reset_context(vcpu); +} + +static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) +{ if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - memset(eoi_exit_bitmap, 0, 32); - memset(tmr, 0, 32); + memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8); - kvm_ioapic_scan_entry(vcpu, eoi_exit_bitmap, tmr); - kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); - kvm_apic_update_tmr(vcpu, tmr); + if (irqchip_split(vcpu->kvm)) + kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap); + else { + kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap); + } + kvm_x86_ops->load_eoi_exitmap(vcpu); } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) @@ -6195,7 +6335,7 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { struct page *page = NULL; - if (!irqchip_in_kernel(vcpu->kvm)) + if (!lapic_in_kernel(vcpu)) return; if (!kvm_x86_ops->set_apic_access_page_addr) @@ -6233,8 +6373,10 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; - bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && - vcpu->run->request_interrupt_window; + bool req_int_win = + dm_request_for_irq_injection(vcpu) && + kvm_cpu_accept_dm_intr(vcpu); + bool req_immediate_exit = false; if (vcpu->requests) { @@ -6277,16 +6419,55 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_handle_pmu_event(vcpu); + kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_deliver_pmi(vcpu); + kvm_pmu_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { + BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); + if (test_bit(vcpu->arch.pending_ioapic_eoi, + (void *) vcpu->arch.eoi_exit_bitmap)) { + vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; + vcpu->run->eoi.vector = + vcpu->arch.pending_ioapic_eoi; + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); + if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; + vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET; + r = 0; + goto out; + } + } + + /* + * KVM_REQ_EVENT is not set when posted interrupts are set by + * VT-d hardware, so we have to update RVI unconditionally. + */ + if (kvm_lapic_enabled(vcpu)) { + /* + * Update architecture specific hints for APIC + * virtual interrupt delivery. + */ + if (kvm_x86_ops->hwapic_irr_update) + kvm_x86_ops->hwapic_irr_update(vcpu, + kvm_lapic_find_highest_irr(vcpu)); } if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { @@ -6305,13 +6486,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->enable_irq_window(vcpu); if (kvm_lapic_enabled(vcpu)) { - /* - * Update architecture specific hints for APIC - * virtual interrupt delivery. - */ - if (kvm_x86_ops->hwapic_irr_update) - kvm_x86_ops->hwapic_irr_update(vcpu, - kvm_lapic_find_highest_irr(vcpu)); update_cr8_intercept(vcpu); kvm_lapic_sync_to_vapic(vcpu); } @@ -6354,7 +6528,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); - kvm_guest_enter(); + trace_kvm_entry(vcpu->vcpu_id); + wait_lapic_expire(vcpu); + __kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { set_debugreg(0, 7); @@ -6366,8 +6542,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - trace_kvm_entry(vcpu->vcpu_id); - wait_lapic_expire(vcpu); kvm_x86_ops->run(vcpu); /* @@ -6377,12 +6551,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * KVM_DEBUGREG_WONT_EXIT again. */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { - int i; - WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops->sync_dirty_debug_regs(vcpu); - for (i = 0; i < KVM_NR_DB_REGS; i++) - vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + kvm_update_dr0123(vcpu); + kvm_update_dr6(vcpu); + kvm_update_dr7(vcpu); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } /* @@ -6395,8 +6569,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (hw_breakpoint_active()) hw_breakpoint_restore(); - vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu, - native_read_tsc()); + vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc()); vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -6447,10 +6620,15 @@ out: static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { - if (!kvm_arch_vcpu_runnable(vcpu)) { + if (!kvm_arch_vcpu_runnable(vcpu) && + (!kvm_x86_ops->pre_block || kvm_x86_ops->pre_block(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + + if (kvm_x86_ops->post_block) + kvm_x86_ops->post_block(vcpu); + if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) return 1; } @@ -6473,6 +6651,12 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) return 1; } +static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && + !vcpu->arch.apf.halted); +} + static int vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -6481,11 +6665,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); for (;;) { - if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) + if (kvm_vcpu_running(vcpu)) { r = vcpu_enter_guest(vcpu); - else + } else { r = vcpu_block(kvm, vcpu); + } + if (r <= 0) break; @@ -6493,9 +6678,10 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu)) { - r = -EINTR; - vcpu->run->exit_reason = KVM_EXIT_INTR; + if (dm_request_for_irq_injection(vcpu) && + kvm_vcpu_ready_for_interrupt_injection(vcpu)) { + r = 0; + vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; ++vcpu->stat.request_irq_exits; break; } @@ -6604,11 +6790,11 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { + struct fpu *fpu = ¤t->thread.fpu; int r; sigset_t sigsaved; - if (!tsk_used_math(current) && init_fpu(current)) - return -ENOMEM; + fpu__activate_curr(fpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved); @@ -6622,7 +6808,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } /* re-sync apic's tpr */ - if (!irqchip_in_kernel(vcpu->kvm)) { + if (!lapic_in_kernel(vcpu)) { if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) { r = -EINVAL; goto out; @@ -6946,7 +7132,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops->update_db_bp_intercept(vcpu); + kvm_x86_ops->update_bp_intercept(vcpu); r = 0; @@ -6978,8 +7164,8 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct i387_fxsave_struct *fxsave = - &vcpu->arch.guest_fpu.state->fxsave; + struct fxregs_state *fxsave = + &vcpu->arch.guest_fpu.state.fxsave; memcpy(fpu->fpr, fxsave->st_space, 128); fpu->fcw = fxsave->cwd; @@ -6995,8 +7181,8 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) { - struct i387_fxsave_struct *fxsave = - &vcpu->arch.guest_fpu.state->fxsave; + struct fxregs_state *fxsave = + &vcpu->arch.guest_fpu.state.fxsave; memcpy(fxsave->st_space, fpu->fpr, 128); fxsave->cwd = fpu->fcw; @@ -7010,33 +7196,19 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) return 0; } -int fx_init(struct kvm_vcpu *vcpu) +static void fx_init(struct kvm_vcpu *vcpu) { - int err; - - err = fpu_alloc(&vcpu->arch.guest_fpu); - if (err) - return err; - - fpu_finit(&vcpu->arch.guest_fpu); + fpstate_init(&vcpu->arch.guest_fpu.state); if (cpu_has_xsaves) - vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv = + vcpu->arch.guest_fpu.state.xsave.header.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED; /* * Ensure guest xcr0 is valid for loading */ - vcpu->arch.xcr0 = XSTATE_FP; + vcpu->arch.xcr0 = XFEATURE_MASK_FP; vcpu->arch.cr0 |= X86_CR0_ET; - - return 0; -} -EXPORT_SYMBOL_GPL(fx_init); - -static void fx_free(struct kvm_vcpu *vcpu) -{ - fpu_free(&vcpu->arch.guest_fpu); } void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) @@ -7052,7 +7224,7 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - fpu_restore_checking(&vcpu->arch.guest_fpu); + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); trace_kvm_fpu(1); } @@ -7060,16 +7232,25 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) + if (!vcpu->guest_fpu_loaded) { + vcpu->fpu_counter = 0; return; + } vcpu->guest_fpu_loaded = 0; - fpu_save_init(&vcpu->arch.guest_fpu); + copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu); __kernel_fpu_end(); ++vcpu->stat.fpu_reload; - if (!vcpu->arch.eager_fpu) - kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); - + /* + * If using eager FPU mode, or if the guest is a frequent user + * of the FPU, just leave the FPU active for next time. + * Every 255 times fpu_counter rolls over to 0; a guest that uses + * the FPU in bursts will revert to loading it on demand. + */ + if (!vcpu->arch.eager_fpu) { + if (++vcpu->fpu_counter < 5) + kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu); + } trace_kvm_fpu(0); } @@ -7078,7 +7259,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); - fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } @@ -7094,11 +7274,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu = kvm_x86_ops->vcpu_create(kvm, id); - /* - * Activate fpu unconditionally in case the guest needs eager FPU. It will be - * deactivated soon if it doesn't. - */ - kvm_x86_ops->fpu_activate(vcpu); return vcpu; } @@ -7106,14 +7281,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) { int r; - vcpu->arch.mtrr_state.have_fixed = 1; + kvm_vcpu_mtrr_init(vcpu); r = vcpu_load(vcpu); if (r) return r; - kvm_vcpu_reset(vcpu); + kvm_vcpu_reset(vcpu, false); kvm_mmu_setup(vcpu); vcpu_put(vcpu); - return r; } @@ -7130,6 +7304,9 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) kvm_write_tsc(vcpu, &msr); vcpu_put(vcpu); + if (!kvmclock_periodic_sync) + return; + schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); } @@ -7144,12 +7321,13 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); vcpu_put(vcpu); - fx_free(vcpu); kvm_x86_ops->vcpu_free(vcpu); } -void kvm_vcpu_reset(struct kvm_vcpu *vcpu) +void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) { + vcpu->arch.hflags = 0; + atomic_set(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = 0; vcpu->arch.nmi_injected = false; @@ -7175,13 +7353,16 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; - kvm_pmu_reset(vcpu); + if (!init_event) { + kvm_pmu_reset(vcpu); + vcpu->arch.smbase = 0x30000; + } memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_x86_ops->vcpu_reset(vcpu); + kvm_x86_ops->vcpu_reset(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -7210,7 +7391,7 @@ int kvm_arch_hardware_enable(void) if (ret != 0) return ret; - local_tsc = native_read_tsc(); + local_tsc = rdtsc(); stable = !check_tsc_unstable(); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { @@ -7300,6 +7481,20 @@ int kvm_arch_hardware_setup(void) if (r != 0) return r; + if (kvm_has_tsc_control) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated needed because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz)); + kvm_max_guest_tsc_khz = max; + + kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; + } + kvm_init_msr_list(); return 0; } @@ -7314,9 +7509,20 @@ void kvm_arch_check_processor_compat(void *rtn) kvm_x86_ops->check_processor_compatibility(rtn); } +bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) +{ + return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp); + +bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; +} + bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu) { - return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL); + return irqchip_in_kernel(vcpu->kvm) == lapic_in_kernel(vcpu); } struct static_key kvm_no_apic_vcpu __read_mostly; @@ -7370,9 +7576,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; } - r = fx_init(vcpu); - if (r) - goto fail_free_wbinvd_dirty_mask; + fx_init(vcpu); vcpu->arch.ia32_tsc_adjust_msr = 0x0; vcpu->arch.pv_time_enabled = false; @@ -7382,12 +7586,15 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); + vcpu->arch.pending_external_vector = -1; + return 0; -fail_free_wbinvd_dirty_mask: - free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); + fail_free_mce_banks: kfree(vcpu->arch.mce_banks); fail_free_lapic: @@ -7411,7 +7618,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) kvm_mmu_destroy(vcpu); srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); - if (!irqchip_in_kernel(vcpu->kvm)) + if (!lapic_in_kernel(vcpu)) static_key_slow_dec(&kvm_no_apic_vcpu); } @@ -7489,6 +7696,72 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } +int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +{ + int i, r; + unsigned long hva; + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *slot, old; + + /* Called with kvm->slots_lock held. */ + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) + return -EINVAL; + + slot = id_to_memslot(slots, id); + if (size) { + if (WARN_ON(slot->npages)) + return -EEXIST; + + /* + * MAP_SHARED to prevent internal slot pages from being moved + * by fork()/COW. + */ + hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, 0); + if (IS_ERR((void *)hva)) + return PTR_ERR((void *)hva); + } else { + if (!slot->npages) + return 0; + + hva = 0; + } + + old = *slot; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct kvm_userspace_memory_region m; + + m.slot = id | (i << 16); + m.flags = 0; + m.guest_phys_addr = gpa; + m.userspace_addr = hva; + m.memory_size = size; + r = __kvm_set_memory_region(kvm, &m); + if (r < 0) + return r; + } + + if (!size) { + r = vm_munmap(old.userspace_addr, old.npages * PAGE_SIZE); + WARN_ON(r < 0); + } + + return 0; +} +EXPORT_SYMBOL_GPL(__x86_set_memory_region); + +int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size) +{ + int r; + + mutex_lock(&kvm->slots_lock); + r = __x86_set_memory_region(kvm, id, gpa, size); + mutex_unlock(&kvm->slots_lock); + + return r; +} +EXPORT_SYMBOL_GPL(x86_set_memory_region); + void kvm_arch_destroy_vm(struct kvm *kvm) { if (current->mm == kvm->mm) { @@ -7497,16 +7770,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) * unless the the memory map has changed due to process exit * or fd copying. */ - struct kvm_userspace_memory_region mem; - memset(&mem, 0, sizeof(mem)); - mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); - - mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); - - mem.slot = TSS_PRIVATE_MEMSLOT; - kvm_set_memory_region(kvm, &mem); + x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT, 0, 0); + x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); } kvm_iommu_unmap_guest(kvm); kfree(kvm->arch.vpic); @@ -7595,41 +7861,20 @@ out_free: return -ENOMEM; } -void kvm_arch_memslots_updated(struct kvm *kvm) +void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots) { /* * memslots->generation has been incremented. * mmio generation may have reached its maximum value. */ - kvm_mmu_invalidate_mmio_sptes(kvm); + kvm_mmu_invalidate_mmio_sptes(kvm, slots); } int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, enum kvm_mr_change change) { - /* - * Only private memory slots need to be mapped here since - * KVM_SET_MEMORY_REGION ioctl is no longer supported. - */ - if ((memslot->id >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_CREATE)) { - unsigned long userspace_addr; - - /* - * MAP_SHARED to prevent internal slot pages from being moved - * by fork()/COW. - */ - userspace_addr = vm_mmap(NULL, 0, memslot->npages * PAGE_SIZE, - PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS, 0); - - if (IS_ERR((void *)userspace_addr)) - return PTR_ERR((void *)userspace_addr); - - memslot->userspace_addr = userspace_addr; - } - return 0; } @@ -7684,33 +7929,19 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, + const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_memory_slot *new; int nr_mmu_pages = 0; - if ((mem->slot >= KVM_USER_MEM_SLOTS) && (change == KVM_MR_DELETE)) { - int ret; - - ret = vm_munmap(old->userspace_addr, - old->npages * PAGE_SIZE); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } - if (!kvm->arch.n_requested_mmu_pages) nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); if (nr_mmu_pages) kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); - /* It's OK to get 'new' slot here as it has already been installed */ - new = id_to_memslot(kvm->memslots, mem->slot); - /* * Dirty logging tracks sptes in 4k granularity, meaning that large * sptes have to be split. If live migration is successful, the guest @@ -7735,9 +7966,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, * been zapped so no dirty logging staff is needed for old slot. For * KVM_MR_FLAGS_ONLY, the old slot is essentially the same one as the * new and it's also covered when dealing with the new slot. + * + * FIXME: const-ify all uses of struct kvm_memory_slot. */ if (change != KVM_MR_DELETE) - kvm_mmu_slot_apply_flags(kvm, new); + kvm_mmu_slot_apply_flags(kvm, (struct kvm_memory_slot *) new); } void kvm_arch_flush_shadow_all(struct kvm *kvm) @@ -7751,19 +7984,36 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, kvm_mmu_invalidate_zap_all_pages(kvm); } +static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) +{ + if (!list_empty_careful(&vcpu->async_pf.done)) + return true; + + if (kvm_apic_has_events(vcpu)) + return true; + + if (vcpu->arch.pv.pv_unhalted) + return true; + + if (atomic_read(&vcpu->arch.nmi_queued)) + return true; + + if (test_bit(KVM_REQ_SMI, &vcpu->requests)) + return true; + + if (kvm_arch_interrupt_allowed(vcpu) && + kvm_cpu_has_interrupt(vcpu)) + return true; + + return false; +} + int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) kvm_x86_ops->check_nested_events(vcpu, false); - return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && - !vcpu->arch.apf.halted) - || !list_empty_careful(&vcpu->async_pf.done) - || kvm_apic_has_events(vcpu) - || vcpu->arch.pv.pv_unhalted - || atomic_read(&vcpu->arch.nmi_queued) || - (kvm_arch_interrupt_allowed(vcpu) && - kvm_cpu_has_interrupt(vcpu)); + return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu); } int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) @@ -7959,6 +8209,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) kvm_x86_ops->interrupt_allowed(vcpu); } +void kvm_arch_start_assignment(struct kvm *kvm) +{ + atomic_inc(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_start_assignment); + +void kvm_arch_end_assignment(struct kvm *kvm) +{ + atomic_dec(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_end_assignment); + +bool kvm_arch_has_assigned_device(struct kvm *kvm) +{ + return atomic_read(&kvm->arch.assigned_device_count); +} +EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { atomic_inc(&kvm->arch.noncoherent_dma_count); @@ -7977,7 +8245,59 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); +int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + if (kvm_x86_ops->update_pi_irte) { + irqfd->producer = prod; + return kvm_x86_ops->update_pi_irte(irqfd->kvm, + prod->irq, irqfd->gsi, 1); + } + + return -EINVAL; +} + +void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, + struct irq_bypass_producer *prod) +{ + int ret; + struct kvm_kernel_irqfd *irqfd = + container_of(cons, struct kvm_kernel_irqfd, consumer); + + if (!kvm_x86_ops->update_pi_irte) { + WARN_ON(irqfd->producer != NULL); + return; + } + + WARN_ON(irqfd->producer != prod); + irqfd->producer = NULL; + + /* + * When producer of consumer is unregistered, we change back to + * remapped mode, so we can re-use the current implementation + * when the irq is masked/disabed or the consumer side (KVM + * int this case doesn't want to receive the interrupts. + */ + ret = kvm_x86_ops->update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); + if (ret) + printk(KERN_INFO "irq bypass consumer (token %p) unregistration" + " fails: %d\n", irqfd->consumer.token, ret); +} + +int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, + uint32_t guest_irq, bool set) +{ + if (!kvm_x86_ops->update_pi_irte) + return -EINVAL; + + return kvm_x86_ops->update_pi_irte(kvm, host_irq, guest_irq, set); +} + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); @@ -7992,3 +8312,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update); diff --git a/kernel/arch/x86/kvm/x86.h b/kernel/arch/x86/kvm/x86.h index f5fef1868..f2afa5fe4 100644 --- a/kernel/arch/x86/kvm/x86.h +++ b/kernel/arch/x86/kvm/x86.h @@ -4,6 +4,8 @@ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" +#define MSR_IA32_CR_PAT_DEFAULT 0x0007040600070406ULL + static inline void kvm_clear_exception_queue(struct kvm_vcpu *vcpu) { vcpu->arch.exception.pending = false; @@ -145,6 +147,16 @@ static inline void kvm_register_writel(struct kvm_vcpu *vcpu, return kvm_register_write(vcpu, reg, val); } +static inline u64 get_kernel_ns(void) +{ + return ktime_get_boot_ns(); +} + +static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) +{ + return !(kvm->arch.disabled_quirks & quirk); +} + void kvm_before_handle_nmi(struct kvm_vcpu *vcpu); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu); void kvm_set_pending_timer(struct kvm_vcpu *vcpu); @@ -160,11 +172,17 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +void kvm_vcpu_mtrr_init(struct kvm_vcpu *vcpu); +u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn); bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data); - -#define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ - | XSTATE_BNDREGS | XSTATE_BNDCSR \ - | XSTATE_AVX512) +int kvm_mtrr_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data); +int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); +bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, + int page_num); + +#define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ + | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ + | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512) extern u64 host_xcr0; extern u64 kvm_supported_xcr0(void); diff --git a/kernel/arch/x86/lguest/boot.c b/kernel/arch/x86/lguest/boot.c index 8f9a133cc..a43b2eafc 100644 --- a/kernel/arch/x86/lguest/boot.c +++ b/kernel/arch/x86/lguest/boot.c @@ -70,7 +70,7 @@ #include <asm/e820.h> #include <asm/mce.h> #include <asm/io.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/stackprotector.h> #include <asm/reboot.h> /* for struct machine_ops */ #include <asm/kvm_para.h> @@ -90,7 +90,7 @@ struct lguest_data lguest_data = { .noirq_iret = (u32)lguest_noirq_iret, .kernel_address = PAGE_OFFSET, .blocked_interrupts = { 1 }, /* Block timer interrupts */ - .syscall_vec = SYSCALL_VECTOR, + .syscall_vec = IA32_SYSCALL_VECTOR, }; /*G:037 @@ -835,16 +835,46 @@ static struct irq_chip lguest_irq_controller = { .irq_unmask = enable_lguest_irq, }; +/* + * Interrupt descriptors are allocated as-needed, but low-numbered ones are + * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it + * tells us the irq is already used: other errors (ie. ENOMEM) we take + * seriously. + */ +static int lguest_setup_irq(unsigned int irq) +{ + struct irq_desc *desc; + int err; + + /* Returns -ve error or vector number. */ + err = irq_alloc_desc_at(irq, 0); + if (err < 0 && err != -EEXIST) + return err; + + /* + * Tell the Linux infrastructure that the interrupt is + * controlled by our level-based lguest interrupt controller. + */ + irq_set_chip_and_handler_name(irq, &lguest_irq_controller, + handle_level_irq, "level"); + + /* Some systems map "vectors" to interrupts weirdly. Not us! */ + desc = irq_to_desc(irq); + __this_cpu_write(vector_irq[FIRST_EXTERNAL_VECTOR + irq], desc); + return 0; +} + static int lguest_enable_irq(struct pci_dev *dev) { + int err; u8 line = 0; /* We literally use the PCI interrupt line as the irq number. */ pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line); - irq_set_chip_and_handler_name(line, &lguest_irq_controller, - handle_level_irq, "level"); - dev->irq = line; - return 0; + err = lguest_setup_irq(line); + if (!err) + dev->irq = line; + return err; } /* We don't do hotplug PCI, so this shouldn't be called. */ @@ -855,18 +885,14 @@ static void lguest_disable_irq(struct pci_dev *dev) /* * This sets up the Interrupt Descriptor Table (IDT) entry for each hardware - * interrupt (except 128, which is used for system calls), and then tells the - * Linux infrastructure that each interrupt is controlled by our level-based - * lguest interrupt controller. + * interrupt (except 128, which is used for system calls). */ static void __init lguest_init_IRQ(void) { unsigned int i; for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) { - /* Some systems map "vectors" to interrupts weirdly. Not us! */ - __this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR); - if (i != SYSCALL_VECTOR) + if (i != IA32_SYSCALL_VECTOR) set_intr_gate(i, irq_entries_start + 8 * (i - FIRST_EXTERNAL_VECTOR)); } @@ -879,26 +905,6 @@ static void __init lguest_init_IRQ(void) } /* - * Interrupt descriptors are allocated as-needed, but low-numbered ones are - * reserved by the generic x86 code. So we ignore irq_alloc_desc_at if it - * tells us the irq is already used: other errors (ie. ENOMEM) we take - * seriously. - */ -int lguest_setup_irq(unsigned int irq) -{ - int err; - - /* Returns -ve error or vector number. */ - err = irq_alloc_desc_at(irq, 0); - if (err < 0 && err != -EEXIST) - return err; - - irq_set_chip_and_handler_name(irq, &lguest_irq_controller, - handle_level_irq, "level"); - return 0; -} - -/* * Time. * * It would be far better for everyone if the Guest had its own clock, but @@ -985,23 +991,11 @@ static int lguest_clockevent_set_next_event(unsigned long delta, return 0; } -static void lguest_clockevent_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int lguest_clockevent_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); - break; - case CLOCK_EVT_MODE_ONESHOT: - /* This is what we expect. */ - break; - case CLOCK_EVT_MODE_PERIODIC: - BUG(); - case CLOCK_EVT_MODE_RESUME: - break; - } + /* A 0 argument shuts the clock down. */ + hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0); + return 0; } /* This describes our primitive timer chip. */ @@ -1009,7 +1003,7 @@ static struct clock_event_device lguest_clockevent = { .name = "lguest", .features = CLOCK_EVT_FEAT_ONESHOT, .set_next_event = lguest_clockevent_set_next_event, - .set_mode = lguest_clockevent_set_mode, + .set_state_shutdown = lguest_clockevent_shutdown, .rating = INT_MAX, .mult = 1, .shift = 0, @@ -1021,7 +1015,7 @@ static struct clock_event_device lguest_clockevent = { * This is the Guest timer interrupt handler (hardware interrupt 0). We just * call the clockevent infrastructure and it does whatever needs doing. */ -static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) +static void lguest_time_irq(struct irq_desc *desc) { unsigned long flags; @@ -1040,7 +1034,8 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc) static void lguest_time_init(void) { /* Set up the timer interrupt (0) to go to our simple timer routine */ - lguest_setup_irq(0); + if (lguest_setup_irq(0) != 0) + panic("Could not set up timer irq"); irq_set_handler(0, lguest_time_irq); clocksource_register_hz(&lguest_clock, NSEC_PER_SEC); @@ -1419,6 +1414,7 @@ __init void lguest_init(void) pv_info.kernel_rpl = 1; /* Everyone except Xen runs with this set. */ pv_info.shared_kernel_pmd = 1; + pv_info.features = 0; /* * We set up all the lguest overrides for sensitive operations. These diff --git a/kernel/arch/x86/lib/Makefile b/kernel/arch/x86/lib/Makefile index 1530afb07..f2587888d 100644 --- a/kernel/arch/x86/lib/Makefile +++ b/kernel/arch/x86/lib/Makefile @@ -17,7 +17,6 @@ clean-files := inat-tables.c obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o -lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o @@ -40,6 +39,6 @@ else lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o lib-y += clear_page_64.o copy_page_64.o lib-y += memmove_64.o memset_64.o - lib-y += copy_user_64.o copy_user_nocache_64.o + lib-y += copy_user_64.o lib-y += cmpxchg16b_emu.o endif diff --git a/kernel/arch/x86/lib/atomic64_386_32.S b/kernel/arch/x86/lib/atomic64_386_32.S index 00933d5e9..9b0ca8fe8 100644 --- a/kernel/arch/x86/lib/atomic64_386_32.S +++ b/kernel/arch/x86/lib/atomic64_386_32.S @@ -11,26 +11,23 @@ #include <linux/linkage.h> #include <asm/alternative-asm.h> -#include <asm/dwarf2.h> /* if you want SMP support, implement these with real spinlocks */ .macro LOCK reg - pushfl_cfi + pushfl cli .endm .macro UNLOCK reg - popfl_cfi + popfl .endm #define BEGIN(op) \ .macro endp; \ - CFI_ENDPROC; \ ENDPROC(atomic64_##op##_386); \ .purgem endp; \ .endm; \ ENTRY(atomic64_##op##_386); \ - CFI_STARTPROC; \ LOCK v; #define ENDP endp diff --git a/kernel/arch/x86/lib/atomic64_cx8_32.S b/kernel/arch/x86/lib/atomic64_cx8_32.S index 082a85167..db3ae8544 100644 --- a/kernel/arch/x86/lib/atomic64_cx8_32.S +++ b/kernel/arch/x86/lib/atomic64_cx8_32.S @@ -11,7 +11,6 @@ #include <linux/linkage.h> #include <asm/alternative-asm.h> -#include <asm/dwarf2.h> .macro read64 reg movl %ebx, %eax @@ -22,16 +21,11 @@ .endm ENTRY(atomic64_read_cx8) - CFI_STARTPROC - read64 %ecx ret - CFI_ENDPROC ENDPROC(atomic64_read_cx8) ENTRY(atomic64_set_cx8) - CFI_STARTPROC - 1: /* we don't need LOCK_PREFIX since aligned 64-bit writes * are atomic on 586 and newer */ @@ -39,28 +33,23 @@ ENTRY(atomic64_set_cx8) jne 1b ret - CFI_ENDPROC ENDPROC(atomic64_set_cx8) ENTRY(atomic64_xchg_cx8) - CFI_STARTPROC - 1: LOCK_PREFIX cmpxchg8b (%esi) jne 1b ret - CFI_ENDPROC ENDPROC(atomic64_xchg_cx8) .macro addsub_return func ins insc ENTRY(atomic64_\func\()_return_cx8) - CFI_STARTPROC - pushl_cfi_reg ebp - pushl_cfi_reg ebx - pushl_cfi_reg esi - pushl_cfi_reg edi + pushl %ebp + pushl %ebx + pushl %esi + pushl %edi movl %eax, %esi movl %edx, %edi @@ -79,12 +68,11 @@ ENTRY(atomic64_\func\()_return_cx8) 10: movl %ebx, %eax movl %ecx, %edx - popl_cfi_reg edi - popl_cfi_reg esi - popl_cfi_reg ebx - popl_cfi_reg ebp + popl %edi + popl %esi + popl %ebx + popl %ebp ret - CFI_ENDPROC ENDPROC(atomic64_\func\()_return_cx8) .endm @@ -93,8 +81,7 @@ addsub_return sub sub sbb .macro incdec_return func ins insc ENTRY(atomic64_\func\()_return_cx8) - CFI_STARTPROC - pushl_cfi_reg ebx + pushl %ebx read64 %esi 1: @@ -109,9 +96,8 @@ ENTRY(atomic64_\func\()_return_cx8) 10: movl %ebx, %eax movl %ecx, %edx - popl_cfi_reg ebx + popl %ebx ret - CFI_ENDPROC ENDPROC(atomic64_\func\()_return_cx8) .endm @@ -119,8 +105,7 @@ incdec_return inc add adc incdec_return dec sub sbb ENTRY(atomic64_dec_if_positive_cx8) - CFI_STARTPROC - pushl_cfi_reg ebx + pushl %ebx read64 %esi 1: @@ -136,18 +121,16 @@ ENTRY(atomic64_dec_if_positive_cx8) 2: movl %ebx, %eax movl %ecx, %edx - popl_cfi_reg ebx + popl %ebx ret - CFI_ENDPROC ENDPROC(atomic64_dec_if_positive_cx8) ENTRY(atomic64_add_unless_cx8) - CFI_STARTPROC - pushl_cfi_reg ebp - pushl_cfi_reg ebx + pushl %ebp + pushl %ebx /* these just push these two parameters on the stack */ - pushl_cfi_reg edi - pushl_cfi_reg ecx + pushl %edi + pushl %ecx movl %eax, %ebp movl %edx, %edi @@ -168,21 +151,18 @@ ENTRY(atomic64_add_unless_cx8) movl $1, %eax 3: addl $8, %esp - CFI_ADJUST_CFA_OFFSET -8 - popl_cfi_reg ebx - popl_cfi_reg ebp + popl %ebx + popl %ebp ret 4: cmpl %edx, 4(%esp) jne 2b xorl %eax, %eax jmp 3b - CFI_ENDPROC ENDPROC(atomic64_add_unless_cx8) ENTRY(atomic64_inc_not_zero_cx8) - CFI_STARTPROC - pushl_cfi_reg ebx + pushl %ebx read64 %esi 1: @@ -199,7 +179,6 @@ ENTRY(atomic64_inc_not_zero_cx8) movl $1, %eax 3: - popl_cfi_reg ebx + popl %ebx ret - CFI_ENDPROC ENDPROC(atomic64_inc_not_zero_cx8) diff --git a/kernel/arch/x86/lib/checksum_32.S b/kernel/arch/x86/lib/checksum_32.S index 9bc944a91..c1e623209 100644 --- a/kernel/arch/x86/lib/checksum_32.S +++ b/kernel/arch/x86/lib/checksum_32.S @@ -26,7 +26,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/errno.h> #include <asm/asm.h> @@ -50,9 +49,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum) * alignment for the unrolled loop. */ ENTRY(csum_partial) - CFI_STARTPROC - pushl_cfi_reg esi - pushl_cfi_reg ebx + pushl %esi + pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len movl 12(%esp),%esi # Function arg: unsigned char *buff @@ -129,10 +127,9 @@ ENTRY(csum_partial) jz 8f roll $8, %eax 8: - popl_cfi_reg ebx - popl_cfi_reg esi + popl %ebx + popl %esi ret - CFI_ENDPROC ENDPROC(csum_partial) #else @@ -140,9 +137,8 @@ ENDPROC(csum_partial) /* Version for PentiumII/PPro */ ENTRY(csum_partial) - CFI_STARTPROC - pushl_cfi_reg esi - pushl_cfi_reg ebx + pushl %esi + pushl %ebx movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len movl 12(%esp),%esi # Function arg: const unsigned char *buf @@ -249,10 +245,9 @@ ENTRY(csum_partial) jz 90f roll $8, %eax 90: - popl_cfi_reg ebx - popl_cfi_reg esi + popl %ebx + popl %esi ret - CFI_ENDPROC ENDPROC(csum_partial) #endif @@ -287,12 +282,10 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst, #define FP 12 ENTRY(csum_partial_copy_generic) - CFI_STARTPROC subl $4,%esp - CFI_ADJUST_CFA_OFFSET 4 - pushl_cfi_reg edi - pushl_cfi_reg esi - pushl_cfi_reg ebx + pushl %edi + pushl %esi + pushl %ebx movl ARGBASE+16(%esp),%eax # sum movl ARGBASE+12(%esp),%ecx # len movl ARGBASE+4(%esp),%esi # src @@ -401,12 +394,11 @@ DST( movb %cl, (%edi) ) .previous - popl_cfi_reg ebx - popl_cfi_reg esi - popl_cfi_reg edi - popl_cfi %ecx # equivalent to addl $4,%esp + popl %ebx + popl %esi + popl %edi + popl %ecx # equivalent to addl $4,%esp ret - CFI_ENDPROC ENDPROC(csum_partial_copy_generic) #else @@ -426,10 +418,9 @@ ENDPROC(csum_partial_copy_generic) #define ARGBASE 12 ENTRY(csum_partial_copy_generic) - CFI_STARTPROC - pushl_cfi_reg ebx - pushl_cfi_reg edi - pushl_cfi_reg esi + pushl %ebx + pushl %edi + pushl %esi movl ARGBASE+4(%esp),%esi #src movl ARGBASE+8(%esp),%edi #dst movl ARGBASE+12(%esp),%ecx #len @@ -489,11 +480,10 @@ DST( movb %dl, (%edi) ) jmp 7b .previous - popl_cfi_reg esi - popl_cfi_reg edi - popl_cfi_reg ebx + popl %esi + popl %edi + popl %ebx ret - CFI_ENDPROC ENDPROC(csum_partial_copy_generic) #undef ROUND diff --git a/kernel/arch/x86/lib/clear_page_64.S b/kernel/arch/x86/lib/clear_page_64.S index e67e579c9..a2fe51b00 100644 --- a/kernel/arch/x86/lib/clear_page_64.S +++ b/kernel/arch/x86/lib/clear_page_64.S @@ -1,5 +1,4 @@ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -15,7 +14,6 @@ * %rdi - page */ ENTRY(clear_page) - CFI_STARTPROC ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \ "jmp clear_page_c_e", X86_FEATURE_ERMS @@ -24,11 +22,9 @@ ENTRY(clear_page) xorl %eax,%eax rep stosq ret - CFI_ENDPROC ENDPROC(clear_page) ENTRY(clear_page_orig) - CFI_STARTPROC xorl %eax,%eax movl $4096/64,%ecx @@ -48,14 +44,11 @@ ENTRY(clear_page_orig) jnz .Lloop nop ret - CFI_ENDPROC ENDPROC(clear_page_orig) ENTRY(clear_page_c_e) - CFI_STARTPROC movl $4096,%ecx xorl %eax,%eax rep stosb ret - CFI_ENDPROC ENDPROC(clear_page_c_e) diff --git a/kernel/arch/x86/lib/cmpxchg16b_emu.S b/kernel/arch/x86/lib/cmpxchg16b_emu.S index 40a172541..9b330242e 100644 --- a/kernel/arch/x86/lib/cmpxchg16b_emu.S +++ b/kernel/arch/x86/lib/cmpxchg16b_emu.S @@ -6,7 +6,6 @@ * */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/percpu.h> .text @@ -21,7 +20,6 @@ * %al : Operation successful */ ENTRY(this_cpu_cmpxchg16b_emu) -CFI_STARTPROC # # Emulate 'cmpxchg16b %gs:(%rsi)' except we return the result in %al not @@ -32,7 +30,7 @@ CFI_STARTPROC # *atomic* on a single cpu (as provided by the this_cpu_xx class of # macros). # - pushfq_cfi + pushfq cli cmpq PER_CPU_VAR((%rsi)), %rax @@ -43,17 +41,13 @@ CFI_STARTPROC movq %rbx, PER_CPU_VAR((%rsi)) movq %rcx, PER_CPU_VAR(8(%rsi)) - CFI_REMEMBER_STATE - popfq_cfi + popfq mov $1, %al ret - CFI_RESTORE_STATE .Lnot_same: - popfq_cfi + popfq xor %al,%al ret -CFI_ENDPROC - ENDPROC(this_cpu_cmpxchg16b_emu) diff --git a/kernel/arch/x86/lib/cmpxchg8b_emu.S b/kernel/arch/x86/lib/cmpxchg8b_emu.S index b4807fce5..ad5349778 100644 --- a/kernel/arch/x86/lib/cmpxchg8b_emu.S +++ b/kernel/arch/x86/lib/cmpxchg8b_emu.S @@ -7,7 +7,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> .text @@ -20,14 +19,13 @@ * %ecx : high 32 bits of new value */ ENTRY(cmpxchg8b_emu) -CFI_STARTPROC # # Emulate 'cmpxchg8b (%esi)' on UP except we don't # set the whole ZF thing (caller will just compare # eax:edx with the expected value) # - pushfl_cfi + pushfl cli cmpl (%esi), %eax @@ -38,18 +36,15 @@ CFI_STARTPROC movl %ebx, (%esi) movl %ecx, 4(%esi) - CFI_REMEMBER_STATE - popfl_cfi + popfl ret - CFI_RESTORE_STATE .Lnot_same: movl (%esi), %eax .Lhalf_same: movl 4(%esi), %edx - popfl_cfi + popfl ret -CFI_ENDPROC ENDPROC(cmpxchg8b_emu) diff --git a/kernel/arch/x86/lib/copy_page_64.S b/kernel/arch/x86/lib/copy_page_64.S index 8239dbcbf..009f98216 100644 --- a/kernel/arch/x86/lib/copy_page_64.S +++ b/kernel/arch/x86/lib/copy_page_64.S @@ -1,7 +1,6 @@ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -13,22 +12,16 @@ */ ALIGN ENTRY(copy_page) - CFI_STARTPROC ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq ret - CFI_ENDPROC ENDPROC(copy_page) ENTRY(copy_page_regs) - CFI_STARTPROC subq $2*8, %rsp - CFI_ADJUST_CFA_OFFSET 2*8 movq %rbx, (%rsp) - CFI_REL_OFFSET rbx, 0 movq %r12, 1*8(%rsp) - CFI_REL_OFFSET r12, 1*8 movl $(4096/64)-5, %ecx .p2align 4 @@ -87,11 +80,7 @@ ENTRY(copy_page_regs) jnz .Loop2 movq (%rsp), %rbx - CFI_RESTORE rbx movq 1*8(%rsp), %r12 - CFI_RESTORE r12 addq $2*8, %rsp - CFI_ADJUST_CFA_OFFSET -2*8 ret - CFI_ENDPROC ENDPROC(copy_page_regs) diff --git a/kernel/arch/x86/lib/copy_user_64.S b/kernel/arch/x86/lib/copy_user_64.S index fa997dfae..27f89c79a 100644 --- a/kernel/arch/x86/lib/copy_user_64.S +++ b/kernel/arch/x86/lib/copy_user_64.S @@ -7,7 +7,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/current.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> @@ -16,33 +15,8 @@ #include <asm/asm.h> #include <asm/smap.h> - .macro ALIGN_DESTINATION - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) - .endm - /* Standard copy_to_user with segment limit checking */ ENTRY(_copy_to_user) - CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rdi,%rcx addq %rdx,%rcx @@ -54,12 +28,10 @@ ENTRY(_copy_to_user) X86_FEATURE_REP_GOOD, \ "jmp copy_user_enhanced_fast_string", \ X86_FEATURE_ERMS - CFI_ENDPROC ENDPROC(_copy_to_user) /* Standard copy_from_user with segment limit checking */ ENTRY(_copy_from_user) - CFI_STARTPROC GET_THREAD_INFO(%rax) movq %rsi,%rcx addq %rdx,%rcx @@ -71,14 +43,12 @@ ENTRY(_copy_from_user) X86_FEATURE_REP_GOOD, \ "jmp copy_user_enhanced_fast_string", \ X86_FEATURE_ERMS - CFI_ENDPROC ENDPROC(_copy_from_user) .section .fixup,"ax" /* must zero dest */ ENTRY(bad_from_user) bad_from_user: - CFI_STARTPROC movl %edx,%ecx xorl %eax,%eax rep @@ -86,7 +56,6 @@ bad_from_user: bad_to_user: movl %edx,%eax ret - CFI_ENDPROC ENDPROC(bad_from_user) .previous @@ -104,7 +73,6 @@ ENDPROC(bad_from_user) * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_unrolled) - CFI_STARTPROC ASM_STAC cmpl $8,%edx jb 20f /* less then 8 bytes, go to byte copy loop */ @@ -186,7 +154,6 @@ ENTRY(copy_user_generic_unrolled) _ASM_EXTABLE(19b,40b) _ASM_EXTABLE(21b,50b) _ASM_EXTABLE(22b,50b) - CFI_ENDPROC ENDPROC(copy_user_generic_unrolled) /* Some CPUs run faster using the string copy instructions. @@ -208,7 +175,6 @@ ENDPROC(copy_user_generic_unrolled) * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_generic_string) - CFI_STARTPROC ASM_STAC cmpl $8,%edx jb 2f /* less than 8 bytes, go to byte copy loop */ @@ -233,7 +199,6 @@ ENTRY(copy_user_generic_string) _ASM_EXTABLE(1b,11b) _ASM_EXTABLE(3b,12b) - CFI_ENDPROC ENDPROC(copy_user_generic_string) /* @@ -249,7 +214,6 @@ ENDPROC(copy_user_generic_string) * eax uncopied bytes or 0 if successful. */ ENTRY(copy_user_enhanced_fast_string) - CFI_STARTPROC ASM_STAC movl %edx,%ecx 1: rep @@ -264,5 +228,154 @@ ENTRY(copy_user_enhanced_fast_string) .previous _ASM_EXTABLE(1b,12b) - CFI_ENDPROC ENDPROC(copy_user_enhanced_fast_string) + +/* + * copy_user_nocache - Uncached memory copy with exception handling + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + */ +ENTRY(__copy_user_nocache) + ASM_STAC + + /* If size is less than 8 bytes, go to 4-byte copy */ + cmpl $8,%edx + jb .L_4b_nocache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ + ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ + movl %edx,%ecx + andl $63,%edx + shrl $6,%ecx + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: +1: movq (%rsi),%r8 +2: movq 1*8(%rsi),%r9 +3: movq 2*8(%rsi),%r10 +4: movq 3*8(%rsi),%r11 +5: movnti %r8,(%rdi) +6: movnti %r9,1*8(%rdi) +7: movnti %r10,2*8(%rdi) +8: movnti %r11,3*8(%rdi) +9: movq 4*8(%rsi),%r8 +10: movq 5*8(%rsi),%r9 +11: movq 6*8(%rsi),%r10 +12: movq 7*8(%rsi),%r11 +13: movnti %r8,4*8(%rdi) +14: movnti %r9,5*8(%rdi) +15: movnti %r10,6*8(%rdi) +16: movnti %r11,7*8(%rdi) + leaq 64(%rsi),%rsi + leaq 64(%rdi),%rdi + decl %ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx + andl $7,%edx + shrl $3,%ecx + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) + leaq 8(%rsi),%rsi + leaq 8(%rdi),%rdi + decl %ecx + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ + movl %edx,%ecx + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: + movl %edx,%ecx +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax + ASM_CLAC + sfence + ret + + .section .fixup,"ax" +.L_fixup_4x8b_copy: + shll $6,%ecx + addl %ecx,%edx + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence + jmp copy_user_handle_tail + .previous + + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) +ENDPROC(__copy_user_nocache) diff --git a/kernel/arch/x86/lib/copy_user_nocache_64.S b/kernel/arch/x86/lib/copy_user_nocache_64.S deleted file mode 100644 index 6a4f43c2d..000000000 --- a/kernel/arch/x86/lib/copy_user_nocache_64.S +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com> - * Copyright 2002 Andi Kleen, SuSE Labs. - * Subject to the GNU Public License v2. - * - * Functions to copy from and to user space. - */ - -#include <linux/linkage.h> -#include <asm/dwarf2.h> - -#define FIX_ALIGNMENT 1 - -#include <asm/current.h> -#include <asm/asm-offsets.h> -#include <asm/thread_info.h> -#include <asm/asm.h> -#include <asm/smap.h> - - .macro ALIGN_DESTINATION -#ifdef FIX_ALIGNMENT - /* check for bad alignment of destination */ - movl %edi,%ecx - andl $7,%ecx - jz 102f /* already aligned */ - subl $8,%ecx - negl %ecx - subl %ecx,%edx -100: movb (%rsi),%al -101: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 100b -102: - .section .fixup,"ax" -103: addl %ecx,%edx /* ecx is zerorest also */ - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(100b,103b) - _ASM_EXTABLE(101b,103b) -#endif - .endm - -/* - * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. - */ -ENTRY(__copy_user_nocache) - CFI_STARTPROC - ASM_STAC - cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ - ALIGN_DESTINATION - movl %edx,%ecx - andl $63,%edx - shrl $6,%ecx - jz 17f -1: movq (%rsi),%r8 -2: movq 1*8(%rsi),%r9 -3: movq 2*8(%rsi),%r10 -4: movq 3*8(%rsi),%r11 -5: movnti %r8,(%rdi) -6: movnti %r9,1*8(%rdi) -7: movnti %r10,2*8(%rdi) -8: movnti %r11,3*8(%rdi) -9: movq 4*8(%rsi),%r8 -10: movq 5*8(%rsi),%r9 -11: movq 6*8(%rsi),%r10 -12: movq 7*8(%rsi),%r11 -13: movnti %r8,4*8(%rdi) -14: movnti %r9,5*8(%rdi) -15: movnti %r10,6*8(%rdi) -16: movnti %r11,7*8(%rdi) - leaq 64(%rsi),%rsi - leaq 64(%rdi),%rdi - decl %ecx - jnz 1b -17: movl %edx,%ecx - andl $7,%edx - shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) - leaq 8(%rsi),%rsi - leaq 8(%rdi),%rdi - decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f - movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) - incq %rsi - incq %rdi - decl %ecx - jnz 21b -23: xorl %eax,%eax - ASM_CLAC - sfence - ret - - .section .fixup,"ax" -30: shll $6,%ecx - addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence - jmp copy_user_handle_tail - .previous - - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) - CFI_ENDPROC -ENDPROC(__copy_user_nocache) diff --git a/kernel/arch/x86/lib/csum-copy_64.S b/kernel/arch/x86/lib/csum-copy_64.S index 973418296..7e48807b2 100644 --- a/kernel/arch/x86/lib/csum-copy_64.S +++ b/kernel/arch/x86/lib/csum-copy_64.S @@ -6,7 +6,6 @@ * for more details. No warranty for anything given at all. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/errno.h> #include <asm/asm.h> @@ -47,23 +46,16 @@ ENTRY(csum_partial_copy_generic) - CFI_STARTPROC cmpl $3*64, %edx jle .Lignore .Lignore: subq $7*8, %rsp - CFI_ADJUST_CFA_OFFSET 7*8 movq %rbx, 2*8(%rsp) - CFI_REL_OFFSET rbx, 2*8 movq %r12, 3*8(%rsp) - CFI_REL_OFFSET r12, 3*8 movq %r14, 4*8(%rsp) - CFI_REL_OFFSET r14, 4*8 movq %r13, 5*8(%rsp) - CFI_REL_OFFSET r13, 5*8 movq %rbp, 6*8(%rsp) - CFI_REL_OFFSET rbp, 6*8 movq %r8, (%rsp) movq %r9, 1*8(%rsp) @@ -206,22 +198,14 @@ ENTRY(csum_partial_copy_generic) addl %ebx, %eax adcl %r9d, %eax /* carry */ - CFI_REMEMBER_STATE .Lende: movq 2*8(%rsp), %rbx - CFI_RESTORE rbx movq 3*8(%rsp), %r12 - CFI_RESTORE r12 movq 4*8(%rsp), %r14 - CFI_RESTORE r14 movq 5*8(%rsp), %r13 - CFI_RESTORE r13 movq 6*8(%rsp), %rbp - CFI_RESTORE rbp addq $7*8, %rsp - CFI_ADJUST_CFA_OFFSET -7*8 ret - CFI_RESTORE_STATE /* Exception handlers. Very simple, zeroing is done in the wrappers */ .Lbad_source: @@ -237,5 +221,4 @@ ENTRY(csum_partial_copy_generic) jz .Lende movl $-EFAULT, (%rax) jmp .Lende - CFI_ENDPROC ENDPROC(csum_partial_copy_generic) diff --git a/kernel/arch/x86/lib/delay.c b/kernel/arch/x86/lib/delay.c index 39d6a3db0..e912b2f6d 100644 --- a/kernel/arch/x86/lib/delay.c +++ b/kernel/arch/x86/lib/delay.c @@ -20,6 +20,7 @@ #include <asm/processor.h> #include <asm/delay.h> #include <asm/timer.h> +#include <asm/mwait.h> #ifdef CONFIG_SMP # include <asm/smp.h> @@ -49,16 +50,14 @@ static void delay_loop(unsigned long loops) /* TSC based delay: */ static void delay_tsc(unsigned long __loops) { - u32 bclock, now, loops = __loops; + u64 bclock, now, loops = __loops; int cpu; preempt_disable(); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); for (;;) { - rdtsc_barrier(); - rdtscl(now); + now = rdtsc_ordered(); if ((now - bclock) >= loops) break; @@ -79,14 +78,51 @@ static void delay_tsc(unsigned long __loops) if (unlikely(cpu != smp_processor_id())) { loops -= (now - bclock); cpu = smp_processor_id(); - rdtsc_barrier(); - rdtscl(bclock); + bclock = rdtsc_ordered(); } } preempt_enable(); } /* + * On some AMD platforms, MWAITX has a configurable 32-bit timer, that + * counts with TSC frequency. The input value is the loop of the + * counter, it will exit when the timer expires. + */ +static void delay_mwaitx(unsigned long __loops) +{ + u64 start, end, delay, loops = __loops; + + start = rdtsc_ordered(); + + for (;;) { + delay = min_t(u64, MWAITX_MAX_LOOPS, loops); + + /* + * Use cpu_tss as a cacheline-aligned, seldomly + * accessed per-cpu variable as the monitor target. + */ + __monitorx(this_cpu_ptr(&cpu_tss), 0, 0); + + /* + * AMD, like Intel, supports the EAX hint and EAX=0xf + * means, do not enter any deep C-state and we use it + * here in delay() to minimize wakeup latency. + */ + __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE); + + end = rdtsc_ordered(); + + if (loops <= end - start) + break; + + loops -= end - start; + + start = end; + } +} + +/* * Since we calibrate only once at boot, this * function should be set once at boot and not changed */ @@ -94,13 +130,19 @@ static void (*delay_fn)(unsigned long) = delay_loop; void use_tsc_delay(void) { - delay_fn = delay_tsc; + if (delay_fn == delay_loop) + delay_fn = delay_tsc; +} + +void use_mwaitx_delay(void) +{ + delay_fn = delay_mwaitx; } int read_current_timer(unsigned long *timer_val) { if (delay_fn == delay_tsc) { - rdtscll(*timer_val); + *timer_val = rdtsc(); return 0; } return -1; diff --git a/kernel/arch/x86/lib/getuser.S b/kernel/arch/x86/lib/getuser.S index a45123596..46668cda4 100644 --- a/kernel/arch/x86/lib/getuser.S +++ b/kernel/arch/x86/lib/getuser.S @@ -26,7 +26,6 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/page_types.h> #include <asm/errno.h> #include <asm/asm-offsets.h> @@ -36,7 +35,6 @@ .text ENTRY(__get_user_1) - CFI_STARTPROC GET_THREAD_INFO(%_ASM_DX) cmp TI_addr_limit(%_ASM_DX),%_ASM_AX jae bad_get_user @@ -45,11 +43,9 @@ ENTRY(__get_user_1) xor %eax,%eax ASM_CLAC ret - CFI_ENDPROC ENDPROC(__get_user_1) ENTRY(__get_user_2) - CFI_STARTPROC add $1,%_ASM_AX jc bad_get_user GET_THREAD_INFO(%_ASM_DX) @@ -60,11 +56,9 @@ ENTRY(__get_user_2) xor %eax,%eax ASM_CLAC ret - CFI_ENDPROC ENDPROC(__get_user_2) ENTRY(__get_user_4) - CFI_STARTPROC add $3,%_ASM_AX jc bad_get_user GET_THREAD_INFO(%_ASM_DX) @@ -75,11 +69,9 @@ ENTRY(__get_user_4) xor %eax,%eax ASM_CLAC ret - CFI_ENDPROC ENDPROC(__get_user_4) ENTRY(__get_user_8) - CFI_STARTPROC #ifdef CONFIG_X86_64 add $7,%_ASM_AX jc bad_get_user @@ -104,28 +96,23 @@ ENTRY(__get_user_8) ASM_CLAC ret #endif - CFI_ENDPROC ENDPROC(__get_user_8) bad_get_user: - CFI_STARTPROC xor %edx,%edx mov $(-EFAULT),%_ASM_AX ASM_CLAC ret - CFI_ENDPROC END(bad_get_user) #ifdef CONFIG_X86_32 bad_get_user_8: - CFI_STARTPROC xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX ASM_CLAC ret - CFI_ENDPROC END(bad_get_user_8) #endif diff --git a/kernel/arch/x86/lib/iomap_copy_64.S b/kernel/arch/x86/lib/iomap_copy_64.S index 05a95e713..33147fef3 100644 --- a/kernel/arch/x86/lib/iomap_copy_64.S +++ b/kernel/arch/x86/lib/iomap_copy_64.S @@ -16,15 +16,12 @@ */ #include <linux/linkage.h> -#include <asm/dwarf2.h> /* * override generic version in lib/iomap_copy.c */ ENTRY(__iowrite32_copy) - CFI_STARTPROC movl %edx,%ecx rep movsd ret - CFI_ENDPROC ENDPROC(__iowrite32_copy) diff --git a/kernel/arch/x86/lib/memcpy_64.S b/kernel/arch/x86/lib/memcpy_64.S index b046664f5..16698bba8 100644 --- a/kernel/arch/x86/lib/memcpy_64.S +++ b/kernel/arch/x86/lib/memcpy_64.S @@ -2,7 +2,6 @@ #include <linux/linkage.h> #include <asm/cpufeature.h> -#include <asm/dwarf2.h> #include <asm/alternative-asm.h> /* @@ -53,7 +52,6 @@ ENTRY(memcpy_erms) ENDPROC(memcpy_erms) ENTRY(memcpy_orig) - CFI_STARTPROC movq %rdi, %rax cmpq $0x20, %rdx @@ -178,5 +176,4 @@ ENTRY(memcpy_orig) .Lend: retq - CFI_ENDPROC ENDPROC(memcpy_orig) diff --git a/kernel/arch/x86/lib/memmove_64.S b/kernel/arch/x86/lib/memmove_64.S index 0f8a0d033..ca2afdd6d 100644 --- a/kernel/arch/x86/lib/memmove_64.S +++ b/kernel/arch/x86/lib/memmove_64.S @@ -6,7 +6,6 @@ * - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com> */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -27,7 +26,6 @@ ENTRY(memmove) ENTRY(__memmove) - CFI_STARTPROC /* Handle more 32 bytes in loop */ mov %rdi, %rax @@ -207,6 +205,5 @@ ENTRY(__memmove) movb %r11b, (%rdi) 13: retq - CFI_ENDPROC ENDPROC(__memmove) ENDPROC(memmove) diff --git a/kernel/arch/x86/lib/memset_64.S b/kernel/arch/x86/lib/memset_64.S index 93118fb23..2661fad05 100644 --- a/kernel/arch/x86/lib/memset_64.S +++ b/kernel/arch/x86/lib/memset_64.S @@ -1,7 +1,6 @@ /* Copyright 2002 Andi Kleen, SuSE Labs */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/cpufeature.h> #include <asm/alternative-asm.h> @@ -66,7 +65,6 @@ ENTRY(memset_erms) ENDPROC(memset_erms) ENTRY(memset_orig) - CFI_STARTPROC movq %rdi,%r10 /* expand byte value */ @@ -78,7 +76,6 @@ ENTRY(memset_orig) movl %edi,%r9d andl $7,%r9d jnz .Lbad_alignment - CFI_REMEMBER_STATE .Lafter_bad_alignment: movq %rdx,%rcx @@ -128,7 +125,6 @@ ENTRY(memset_orig) movq %r10,%rax ret - CFI_RESTORE_STATE .Lbad_alignment: cmpq $7,%rdx jbe .Lhandle_7 @@ -139,5 +135,4 @@ ENTRY(memset_orig) subq %r8,%rdx jmp .Lafter_bad_alignment .Lfinal: - CFI_ENDPROC ENDPROC(memset_orig) diff --git a/kernel/arch/x86/lib/mmx_32.c b/kernel/arch/x86/lib/mmx_32.c index c9f2d9ba8..e5e3ed8dc 100644 --- a/kernel/arch/x86/lib/mmx_32.c +++ b/kernel/arch/x86/lib/mmx_32.c @@ -22,7 +22,7 @@ #include <linux/sched.h> #include <linux/types.h> -#include <asm/i387.h> +#include <asm/fpu/api.h> #include <asm/asm.h> void *_mmx_memcpy(void *to, const void *from, size_t len) diff --git a/kernel/arch/x86/lib/msr-reg.S b/kernel/arch/x86/lib/msr-reg.S index 3ca5218fb..c81556409 100644 --- a/kernel/arch/x86/lib/msr-reg.S +++ b/kernel/arch/x86/lib/msr-reg.S @@ -1,6 +1,5 @@ #include <linux/linkage.h> #include <linux/errno.h> -#include <asm/dwarf2.h> #include <asm/asm.h> #include <asm/msr.h> @@ -13,9 +12,8 @@ */ .macro op_safe_regs op ENTRY(\op\()_safe_regs) - CFI_STARTPROC - pushq_cfi_reg rbx - pushq_cfi_reg rbp + pushq %rbx + pushq %rbp movq %rdi, %r10 /* Save pointer */ xorl %r11d, %r11d /* Return value */ movl (%rdi), %eax @@ -25,7 +23,6 @@ ENTRY(\op\()_safe_regs) movl 20(%rdi), %ebp movl 24(%rdi), %esi movl 28(%rdi), %edi - CFI_REMEMBER_STATE 1: \op 2: movl %eax, (%r10) movl %r11d, %eax /* Return value */ @@ -35,16 +32,14 @@ ENTRY(\op\()_safe_regs) movl %ebp, 20(%r10) movl %esi, 24(%r10) movl %edi, 28(%r10) - popq_cfi_reg rbp - popq_cfi_reg rbx + popq %rbp + popq %rbx ret 3: - CFI_RESTORE_STATE movl $-EIO, %r11d jmp 2b _ASM_EXTABLE(1b, 3b) - CFI_ENDPROC ENDPROC(\op\()_safe_regs) .endm @@ -52,13 +47,12 @@ ENDPROC(\op\()_safe_regs) .macro op_safe_regs op ENTRY(\op\()_safe_regs) - CFI_STARTPROC - pushl_cfi_reg ebx - pushl_cfi_reg ebp - pushl_cfi_reg esi - pushl_cfi_reg edi - pushl_cfi $0 /* Return value */ - pushl_cfi %eax + pushl %ebx + pushl %ebp + pushl %esi + pushl %edi + pushl $0 /* Return value */ + pushl %eax movl 4(%eax), %ecx movl 8(%eax), %edx movl 12(%eax), %ebx @@ -66,32 +60,28 @@ ENTRY(\op\()_safe_regs) movl 24(%eax), %esi movl 28(%eax), %edi movl (%eax), %eax - CFI_REMEMBER_STATE 1: \op -2: pushl_cfi %eax +2: pushl %eax movl 4(%esp), %eax - popl_cfi (%eax) + popl (%eax) addl $4, %esp - CFI_ADJUST_CFA_OFFSET -4 movl %ecx, 4(%eax) movl %edx, 8(%eax) movl %ebx, 12(%eax) movl %ebp, 20(%eax) movl %esi, 24(%eax) movl %edi, 28(%eax) - popl_cfi %eax - popl_cfi_reg edi - popl_cfi_reg esi - popl_cfi_reg ebp - popl_cfi_reg ebx + popl %eax + popl %edi + popl %esi + popl %ebp + popl %ebx ret 3: - CFI_RESTORE_STATE movl $-EIO, 4(%esp) jmp 2b _ASM_EXTABLE(1b, 3b) - CFI_ENDPROC ENDPROC(\op\()_safe_regs) .endm diff --git a/kernel/arch/x86/lib/putuser.S b/kernel/arch/x86/lib/putuser.S index fc6ba17a7..e0817a12d 100644 --- a/kernel/arch/x86/lib/putuser.S +++ b/kernel/arch/x86/lib/putuser.S @@ -11,7 +11,6 @@ * return value. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> #include <asm/thread_info.h> #include <asm/errno.h> #include <asm/asm.h> @@ -30,11 +29,9 @@ * as they get called from within inline assembly. */ -#define ENTER CFI_STARTPROC ; \ - GET_THREAD_INFO(%_ASM_BX) +#define ENTER GET_THREAD_INFO(%_ASM_BX) #define EXIT ASM_CLAC ; \ - ret ; \ - CFI_ENDPROC + ret .text ENTRY(__put_user_1) @@ -87,7 +84,6 @@ ENTRY(__put_user_8) ENDPROC(__put_user_8) bad_put_user: - CFI_STARTPROC movl $-EFAULT,%eax EXIT END(bad_put_user) diff --git a/kernel/arch/x86/lib/rwsem.S b/kernel/arch/x86/lib/rwsem.S index 2322abe4d..40027db99 100644 --- a/kernel/arch/x86/lib/rwsem.S +++ b/kernel/arch/x86/lib/rwsem.S @@ -15,7 +15,6 @@ #include <linux/linkage.h> #include <asm/alternative-asm.h> -#include <asm/dwarf2.h> #define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg) #define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l) @@ -34,10 +33,10 @@ */ #define save_common_regs \ - pushl_cfi_reg ecx + pushl %ecx #define restore_common_regs \ - popl_cfi_reg ecx + popl %ecx /* Avoid uglifying the argument copying x86-64 needs to do. */ .macro movq src, dst @@ -64,50 +63,45 @@ */ #define save_common_regs \ - pushq_cfi_reg rdi; \ - pushq_cfi_reg rsi; \ - pushq_cfi_reg rcx; \ - pushq_cfi_reg r8; \ - pushq_cfi_reg r9; \ - pushq_cfi_reg r10; \ - pushq_cfi_reg r11 + pushq %rdi; \ + pushq %rsi; \ + pushq %rcx; \ + pushq %r8; \ + pushq %r9; \ + pushq %r10; \ + pushq %r11 #define restore_common_regs \ - popq_cfi_reg r11; \ - popq_cfi_reg r10; \ - popq_cfi_reg r9; \ - popq_cfi_reg r8; \ - popq_cfi_reg rcx; \ - popq_cfi_reg rsi; \ - popq_cfi_reg rdi + popq %r11; \ + popq %r10; \ + popq %r9; \ + popq %r8; \ + popq %rcx; \ + popq %rsi; \ + popq %rdi #endif /* Fix up special calling conventions */ ENTRY(call_rwsem_down_read_failed) - CFI_STARTPROC save_common_regs - __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(push,) %__ASM_REG(dx) movq %rax,%rdi call rwsem_down_read_failed - __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(pop,) %__ASM_REG(dx) restore_common_regs ret - CFI_ENDPROC ENDPROC(call_rwsem_down_read_failed) ENTRY(call_rwsem_down_write_failed) - CFI_STARTPROC save_common_regs movq %rax,%rdi call rwsem_down_write_failed restore_common_regs ret - CFI_ENDPROC ENDPROC(call_rwsem_down_write_failed) ENTRY(call_rwsem_wake) - CFI_STARTPROC /* do nothing if still outstanding active readers */ __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx) jnz 1f @@ -116,17 +110,14 @@ ENTRY(call_rwsem_wake) call rwsem_wake restore_common_regs 1: ret - CFI_ENDPROC ENDPROC(call_rwsem_wake) ENTRY(call_rwsem_downgrade_wake) - CFI_STARTPROC save_common_regs - __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(push,) %__ASM_REG(dx) movq %rax,%rdi call rwsem_downgrade_wake - __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx) + __ASM_SIZE(pop,) %__ASM_REG(dx) restore_common_regs ret - CFI_ENDPROC ENDPROC(call_rwsem_downgrade_wake) diff --git a/kernel/arch/x86/lib/usercopy.c b/kernel/arch/x86/lib/usercopy.c index ddf9ecb53..e342586db 100644 --- a/kernel/arch/x86/lib/usercopy.c +++ b/kernel/arch/x86/lib/usercopy.c @@ -20,7 +20,7 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) unsigned long ret; if (__range_not_ok(from, n, TASK_SIZE)) - return 0; + return n; /* * Even though this function is typically called from NMI/IRQ context diff --git a/kernel/arch/x86/lib/x86-opcode-map.txt b/kernel/arch/x86/lib/x86-opcode-map.txt index 816488c0b..d388de72e 100644 --- a/kernel/arch/x86/lib/x86-opcode-map.txt +++ b/kernel/arch/x86/lib/x86-opcode-map.txt @@ -353,8 +353,12 @@ AVXcode: 1 17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1) 18: Grp16 (1A) 19: -1a: BNDCL Ev,Gv | BNDCU Ev,Gv | BNDMOV Gv,Ev | BNDLDX Gv,Ev,Gv -1b: BNDCN Ev,Gv | BNDMOV Ev,Gv | BNDMK Gv,Ev | BNDSTX Ev,GV,Gv +# Intel SDM opcode map does not list MPX instructions. For now using Gv for +# bnd registers and Ev for everything else is OK because the instruction +# decoder does not use the information except as an indication that there is +# a ModR/M byte. +1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev +1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv 1c: 1d: 1e: @@ -732,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1) be: vfnmsub231ps/d Vx,Hx,Wx (66),(v) bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1) # 0x0f 0x38 0xc0-0xff +c8: sha1nexte Vdq,Wdq +c9: sha1msg1 Vdq,Wdq +ca: sha1msg2 Vdq,Wdq +cb: sha256rnds2 Vdq,Wdq +cc: sha256msg1 Vdq,Wdq +cd: sha256msg2 Vdq,Wdq db: VAESIMC Vdq,Wdq (66),(v1) dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) @@ -790,6 +800,7 @@ AVXcode: 3 61: vpcmpestri Vdq,Wdq,Ib (66),(v1) 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1) 63: vpcmpistri Vdq,Wdq,Ib (66),(v1) +cc: sha1rnds4 Vdq,Wdq,Ib df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1) f0: RORX Gy,Ey,Ib (F2),(v) EndTable @@ -874,7 +885,7 @@ GrpTable: Grp7 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) 3: LIDT Ms 4: SMSW Mw/Rv -5: +5: rdpkru (110),(11B) | wrpkru (111),(11B) 6: LMSW Ew 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B) EndTable @@ -888,6 +899,9 @@ EndTable GrpTable: Grp9 1: CMPXCHG8B/16B Mq/Mdq +3: xrstors +4: xsavec +5: xsaves 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) 7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B) EndTable @@ -932,8 +946,8 @@ GrpTable: Grp15 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) 4: XSAVE 5: XRSTOR | lfence (11B) -6: XSAVEOPT | mfence (11B) -7: clflush | sfence (11B) +6: XSAVEOPT | clwb (66) | mfence (11B) +7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B) EndTable GrpTable: Grp16 diff --git a/kernel/arch/x86/math-emu/fpu_aux.c b/kernel/arch/x86/math-emu/fpu_aux.c index dc8adad10..024f6e971 100644 --- a/kernel/arch/x86/math-emu/fpu_aux.c +++ b/kernel/arch/x86/math-emu/fpu_aux.c @@ -30,7 +30,7 @@ static void fclex(void) } /* Needs to be externally visible */ -void finit_soft_fpu(struct i387_soft_struct *soft) +void fpstate_init_soft(struct swregs_state *soft) { struct address *oaddr, *iaddr; memset(soft, 0, sizeof(*soft)); @@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft) void finit(void) { - finit_soft_fpu(¤t->thread.fpu.state->soft); + fpstate_init_soft(¤t->thread.fpu.state.soft); } /* @@ -169,6 +169,76 @@ void fxch_i(void) fpu_tag_word = tag_word; } +static void fcmovCC(void) +{ + /* fcmovCC st(i) */ + int i = FPU_rm; + FPU_REG *st0_ptr = &st(0); + FPU_REG *sti_ptr = &st(i); + long tag_word = fpu_tag_word; + int regnr = top & 7; + int regnri = (top + i) & 7; + u_char sti_tag = (tag_word >> (regnri * 2)) & 3; + + if (sti_tag == TAG_Empty) { + FPU_stack_underflow(); + clear_C1(); + return; + } + reg_copy(sti_ptr, st0_ptr); + tag_word &= ~(3 << (regnr * 2)); + tag_word |= (sti_tag << (regnr * 2)); + fpu_tag_word = tag_word; +} + +void fcmovb(void) +{ + if (FPU_EFLAGS & X86_EFLAGS_CF) + fcmovCC(); +} + +void fcmove(void) +{ + if (FPU_EFLAGS & X86_EFLAGS_ZF) + fcmovCC(); +} + +void fcmovbe(void) +{ + if (FPU_EFLAGS & (X86_EFLAGS_CF|X86_EFLAGS_ZF)) + fcmovCC(); +} + +void fcmovu(void) +{ + if (FPU_EFLAGS & X86_EFLAGS_PF) + fcmovCC(); +} + +void fcmovnb(void) +{ + if (!(FPU_EFLAGS & X86_EFLAGS_CF)) + fcmovCC(); +} + +void fcmovne(void) +{ + if (!(FPU_EFLAGS & X86_EFLAGS_ZF)) + fcmovCC(); +} + +void fcmovnbe(void) +{ + if (!(FPU_EFLAGS & (X86_EFLAGS_CF|X86_EFLAGS_ZF))) + fcmovCC(); +} + +void fcmovnu(void) +{ + if (!(FPU_EFLAGS & X86_EFLAGS_PF)) + fcmovCC(); +} + void ffree_(void) { /* ffree st(i) */ diff --git a/kernel/arch/x86/math-emu/fpu_emu.h b/kernel/arch/x86/math-emu/fpu_emu.h index 4dae511c8..afbc4d805 100644 --- a/kernel/arch/x86/math-emu/fpu_emu.h +++ b/kernel/arch/x86/math-emu/fpu_emu.h @@ -71,7 +71,7 @@ #include "fpu_system.h" -#include <asm/sigcontext.h> /* for struct _fpstate */ +#include <uapi/asm/sigcontext.h> /* for struct _fpstate */ #include <asm/math_emu.h> #include <linux/linkage.h> diff --git a/kernel/arch/x86/math-emu/fpu_entry.c b/kernel/arch/x86/math-emu/fpu_entry.c index 274a52b11..e945fedf1 100644 --- a/kernel/arch/x86/math-emu/fpu_entry.c +++ b/kernel/arch/x86/math-emu/fpu_entry.c @@ -30,7 +30,7 @@ #include <asm/uaccess.h> #include <asm/traps.h> #include <asm/user.h> -#include <asm/i387.h> +#include <asm/fpu/internal.h> #include "fpu_system.h" #include "fpu_emu.h" @@ -40,49 +40,33 @@ #define __BAD__ FPU_illegal /* Illegal on an 80486, causes SIGILL */ -#ifndef NO_UNDOC_CODE /* Un-documented FPU op-codes supported by default. */ +/* fcmovCC and f(u)comi(p) are enabled if CPUID(1).EDX(15) "cmov" is set */ -/* WARNING: These codes are not documented by Intel in their 80486 manual - and may not work on FPU clones or later Intel FPUs. */ - -/* Changes to support the un-doc codes provided by Linus Torvalds. */ - -#define _d9_d8_ fstp_i /* unofficial code (19) */ -#define _dc_d0_ fcom_st /* unofficial code (14) */ -#define _dc_d8_ fcompst /* unofficial code (1c) */ -#define _dd_c8_ fxch_i /* unofficial code (0d) */ -#define _de_d0_ fcompst /* unofficial code (16) */ -#define _df_c0_ ffreep /* unofficial code (07) ffree + pop */ -#define _df_c8_ fxch_i /* unofficial code (0f) */ -#define _df_d0_ fstp_i /* unofficial code (17) */ -#define _df_d8_ fstp_i /* unofficial code (1f) */ +/* WARNING: "u" entries are not documented by Intel in their 80486 manual + and may not work on FPU clones or later Intel FPUs. + Changes to support them provided by Linus Torvalds. */ static FUNC const st_instr_table[64] = { - fadd__, fld_i_, __BAD__, __BAD__, fadd_i, ffree_, faddp_, _df_c0_, - fmul__, fxch_i, __BAD__, __BAD__, fmul_i, _dd_c8_, fmulp_, _df_c8_, - fcom_st, fp_nop, __BAD__, __BAD__, _dc_d0_, fst_i_, _de_d0_, _df_d0_, - fcompst, _d9_d8_, __BAD__, __BAD__, _dc_d8_, fstp_i, fcompp, _df_d8_, - fsub__, FPU_etc, __BAD__, finit_, fsubri, fucom_, fsubrp, fstsw_, - fsubr_, fconst, fucompp, __BAD__, fsub_i, fucomp, fsubp_, __BAD__, - fdiv__, FPU_triga, __BAD__, __BAD__, fdivri, __BAD__, fdivrp, __BAD__, - fdivr_, FPU_trigb, __BAD__, __BAD__, fdiv_i, __BAD__, fdivp_, __BAD__, +/* Opcode: d8 d9 da db */ +/* dc dd de df */ +/* c0..7 */ fadd__, fld_i_, fcmovb, fcmovnb, +/* c0..7 */ fadd_i, ffree_, faddp_, ffreep,/*u*/ +/* c8..f */ fmul__, fxch_i, fcmove, fcmovne, +/* c8..f */ fmul_i, fxch_i,/*u*/ fmulp_, fxch_i,/*u*/ +/* d0..7 */ fcom_st, fp_nop, fcmovbe, fcmovnbe, +/* d0..7 */ fcom_st,/*u*/ fst_i_, fcompst,/*u*/ fstp_i,/*u*/ +/* d8..f */ fcompst, fstp_i,/*u*/ fcmovu, fcmovnu, +/* d8..f */ fcompst,/*u*/ fstp_i, fcompp, fstp_i,/*u*/ +/* e0..7 */ fsub__, FPU_etc, __BAD__, finit_, +/* e0..7 */ fsubri, fucom_, fsubrp, fstsw_, +/* e8..f */ fsubr_, fconst, fucompp, fucomi_, +/* e8..f */ fsub_i, fucomp, fsubp_, fucomip, +/* f0..7 */ fdiv__, FPU_triga, __BAD__, fcomi_, +/* f0..7 */ fdivri, __BAD__, fdivrp, fcomip, +/* f8..f */ fdivr_, FPU_trigb, __BAD__, __BAD__, +/* f8..f */ fdiv_i, __BAD__, fdivp_, __BAD__, }; -#else /* Support only documented FPU op-codes */ - -static FUNC const st_instr_table[64] = { - fadd__, fld_i_, __BAD__, __BAD__, fadd_i, ffree_, faddp_, __BAD__, - fmul__, fxch_i, __BAD__, __BAD__, fmul_i, __BAD__, fmulp_, __BAD__, - fcom_st, fp_nop, __BAD__, __BAD__, __BAD__, fst_i_, __BAD__, __BAD__, - fcompst, __BAD__, __BAD__, __BAD__, __BAD__, fstp_i, fcompp, __BAD__, - fsub__, FPU_etc, __BAD__, finit_, fsubri, fucom_, fsubrp, fstsw_, - fsubr_, fconst, fucompp, __BAD__, fsub_i, fucomp, fsubp_, __BAD__, - fdiv__, FPU_triga, __BAD__, __BAD__, fdivri, __BAD__, fdivrp, __BAD__, - fdivr_, FPU_trigb, __BAD__, __BAD__, fdiv_i, __BAD__, fdivp_, __BAD__, -}; - -#endif /* NO_UNDOC_CODE */ - #define _NONE_ 0 /* Take no special action */ #define _REG0_ 1 /* Need to check for not empty st(0) */ #define _REGI_ 2 /* Need to check for not empty st(0) and st(rm) */ @@ -94,36 +78,18 @@ static FUNC const st_instr_table[64] = { #define _REGIc 0 /* Compare st(0) and st(rm) */ #define _REGIn 0 /* Uses st(0) and st(rm), but handle checks later */ -#ifndef NO_UNDOC_CODE - -/* Un-documented FPU op-codes supported by default. (see above) */ - static u_char const type_table[64] = { - _REGI_, _NONE_, _null_, _null_, _REGIi, _REGi_, _REGIp, _REGi_, - _REGI_, _REGIn, _null_, _null_, _REGIi, _REGI_, _REGIp, _REGI_, - _REGIc, _NONE_, _null_, _null_, _REGIc, _REG0_, _REGIc, _REG0_, - _REGIc, _REG0_, _null_, _null_, _REGIc, _REG0_, _REGIc, _REG0_, - _REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_, - _REGI_, _NONE_, _REGIc, _null_, _REGIi, _REGIc, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_ +/* Opcode: d8 d9 da db dc dd de df */ +/* c0..7 */ _REGI_, _NONE_, _REGIn, _REGIn, _REGIi, _REGi_, _REGIp, _REGi_, +/* c8..f */ _REGI_, _REGIn, _REGIn, _REGIn, _REGIi, _REGI_, _REGIp, _REGI_, +/* d0..7 */ _REGIc, _NONE_, _REGIn, _REGIn, _REGIc, _REG0_, _REGIc, _REG0_, +/* d8..f */ _REGIc, _REG0_, _REGIn, _REGIn, _REGIc, _REG0_, _REGIc, _REG0_, +/* e0..7 */ _REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_, +/* e8..f */ _REGI_, _NONE_, _REGIc, _REGIc, _REGIi, _REGIc, _REGIp, _REGIc, +/* f0..7 */ _REGI_, _NONE_, _null_, _REGIc, _REGIi, _null_, _REGIp, _REGIc, +/* f8..f */ _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_, }; -#else /* Support only documented FPU op-codes */ - -static u_char const type_table[64] = { - _REGI_, _NONE_, _null_, _null_, _REGIi, _REGi_, _REGIp, _null_, - _REGI_, _REGIn, _null_, _null_, _REGIi, _null_, _REGIp, _null_, - _REGIc, _NONE_, _null_, _null_, _null_, _REG0_, _null_, _null_, - _REGIc, _null_, _null_, _null_, _null_, _REG0_, _REGIc, _null_, - _REGI_, _NONE_, _null_, _NONE_, _REGIi, _REGIc, _REGIp, _NONE_, - _REGI_, _NONE_, _REGIc, _null_, _REGIi, _REGIc, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_, - _REGI_, _NONE_, _null_, _null_, _REGIi, _null_, _REGIp, _null_ -}; - -#endif /* NO_UNDOC_CODE */ - #ifdef RE_ENTRANT_CHECKING u_char emulating = 0; #endif /* RE_ENTRANT_CHECKING */ @@ -146,13 +112,9 @@ void math_emulate(struct math_emu_info *info) unsigned long code_base = 0; unsigned long code_limit = 0; /* Initialized to stop compiler warnings */ struct desc_struct code_descriptor; + struct fpu *fpu = ¤t->thread.fpu; - if (!used_math()) { - if (init_fpu(current)) { - do_group_exit(SIGKILL); - return; - } - } + fpu__activate_curr(fpu); #ifdef RE_ENTRANT_CHECKING if (emulating) { @@ -672,7 +634,7 @@ void math_abort(struct math_emu_info *info, unsigned int signal) #endif /* PARANOID */ } -#define S387 ((struct i387_soft_struct *)s387) +#define S387 ((struct swregs_state *)s387) #define sstatus_word() \ ((S387->swd & ~SW_Top & 0xffff) | ((S387->ftop << SW_Top_Shift) & SW_Top)) @@ -681,14 +643,14 @@ int fpregs_soft_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; + struct swregs_state *s387 = &target->thread.fpu.state.soft; void *space = s387->st_space; int ret; int offset, other, i, tags, regnr, tag, newtop; RE_ENTRANT_CHECK_OFF; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, s387, 0, - offsetof(struct i387_soft_struct, st_space)); + offsetof(struct swregs_state, st_space)); RE_ENTRANT_CHECK_ON; if (ret) @@ -733,7 +695,7 @@ int fpregs_soft_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct i387_soft_struct *s387 = &target->thread.fpu.state->soft; + struct swregs_state *s387 = &target->thread.fpu.state.soft; const void *space = s387->st_space; int ret; int offset = (S387->ftop & 7) * 10, other = 80 - offset; @@ -751,7 +713,7 @@ int fpregs_soft_get(struct task_struct *target, #endif /* PECULIAR_486 */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, s387, 0, - offsetof(struct i387_soft_struct, st_space)); + offsetof(struct swregs_state, st_space)); /* Copy all registers in stack order. */ if (!ret) diff --git a/kernel/arch/x86/math-emu/fpu_proto.h b/kernel/arch/x86/math-emu/fpu_proto.h index 9779df436..caff438b9 100644 --- a/kernel/arch/x86/math-emu/fpu_proto.h +++ b/kernel/arch/x86/math-emu/fpu_proto.h @@ -46,6 +46,14 @@ extern void fstsw_(void); extern void fp_nop(void); extern void fld_i_(void); extern void fxch_i(void); +extern void fcmovb(void); +extern void fcmove(void); +extern void fcmovbe(void); +extern void fcmovu(void); +extern void fcmovnb(void); +extern void fcmovne(void); +extern void fcmovnbe(void); +extern void fcmovnu(void); extern void ffree_(void); extern void ffreep(void); extern void fst_i_(void); @@ -108,6 +116,10 @@ extern void fcompp(void); extern void fucom_(void); extern void fucomp(void); extern void fucompp(void); +extern void fcomi_(void); +extern void fcomip(void); +extern void fucomi_(void); +extern void fucomip(void); /* reg_constant.c */ extern void fconst(void); /* reg_ld_str.c */ diff --git a/kernel/arch/x86/math-emu/fpu_system.h b/kernel/arch/x86/math-emu/fpu_system.h index d342fce49..5e044d506 100644 --- a/kernel/arch/x86/math-emu/fpu_system.h +++ b/kernel/arch/x86/math-emu/fpu_system.h @@ -46,7 +46,7 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) #define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \ == (1 << 10)) -#define I387 (current->thread.fpu.state) +#define I387 (¤t->thread.fpu.state) #define FPU_info (I387->soft.info) #define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs)) diff --git a/kernel/arch/x86/math-emu/get_address.c b/kernel/arch/x86/math-emu/get_address.c index 8300db71c..8db26591d 100644 --- a/kernel/arch/x86/math-emu/get_address.c +++ b/kernel/arch/x86/math-emu/get_address.c @@ -20,6 +20,7 @@ #include <linux/stddef.h> #include <asm/uaccess.h> +#include <asm/vm86.h> #include "fpu_system.h" #include "exception.h" diff --git a/kernel/arch/x86/math-emu/load_store.c b/kernel/arch/x86/math-emu/load_store.c index 2931ff355..95228ff04 100644 --- a/kernel/arch/x86/math-emu/load_store.c +++ b/kernel/arch/x86/math-emu/load_store.c @@ -33,11 +33,12 @@ #define pop_0() { FPU_settag0(TAG_Empty); top++; } +/* index is a 5-bit value: (3-bit FPU_modrm.reg field | opcode[2,1]) */ static u_char const type_table[32] = { - _PUSH_, _PUSH_, _PUSH_, _PUSH_, - _null_, _null_, _null_, _null_, - _REG0_, _REG0_, _REG0_, _REG0_, - _REG0_, _REG0_, _REG0_, _REG0_, + _PUSH_, _PUSH_, _PUSH_, _PUSH_, /* /0: d9:fld f32, db:fild m32, dd:fld f64, df:fild m16 */ + _null_, _REG0_, _REG0_, _REG0_, /* /1: d9:undef, db,dd,df:fisttp m32/64/16 */ + _REG0_, _REG0_, _REG0_, _REG0_, /* /2: d9:fst f32, db:fist m32, dd:fst f64, df:fist m16 */ + _REG0_, _REG0_, _REG0_, _REG0_, /* /3: d9:fstp f32, db:fistp m32, dd:fstp f64, df:fistp m16 */ _NONE_, _null_, _NONE_, _PUSH_, _NONE_, _PUSH_, _null_, _PUSH_, _NONE_, _null_, _NONE_, _REG0_, @@ -45,15 +46,19 @@ static u_char const type_table[32] = { }; u_char const data_sizes_16[32] = { - 4, 4, 8, 2, 0, 0, 0, 0, - 4, 4, 8, 2, 4, 4, 8, 2, + 4, 4, 8, 2, + 0, 4, 8, 2, /* /1: d9:undef, db,dd,df:fisttp */ + 4, 4, 8, 2, + 4, 4, 8, 2, 14, 0, 94, 10, 2, 10, 0, 8, 14, 0, 94, 10, 2, 10, 2, 8 }; static u_char const data_sizes_32[32] = { - 4, 4, 8, 2, 0, 0, 0, 0, - 4, 4, 8, 2, 4, 4, 8, 2, + 4, 4, 8, 2, + 0, 4, 8, 2, /* /1: d9:undef, db,dd,df:fisttp */ + 4, 4, 8, 2, + 4, 4, 8, 2, 28, 0, 108, 10, 2, 10, 0, 8, 28, 0, 108, 10, 2, 10, 2, 8 }; @@ -65,6 +70,7 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, FPU_REG *st0_ptr; u_char st0_tag = TAG_Empty; /* This is just to stop a gcc warning. */ u_char loaded_tag; + int sv_cw; st0_ptr = NULL; /* Initialized just to stop compiler warnings. */ @@ -111,7 +117,8 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, } switch (type) { - case 000: /* fld m32real */ + /* type is a 5-bit value: (3-bit FPU_modrm.reg field | opcode[2,1]) */ + case 000: /* fld m32real (d9 /0) */ clear_C1(); loaded_tag = FPU_load_single((float __user *)data_address, &loaded_data); @@ -123,13 +130,13 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, } FPU_copy_to_reg0(&loaded_data, loaded_tag); break; - case 001: /* fild m32int */ + case 001: /* fild m32int (db /0) */ clear_C1(); loaded_tag = FPU_load_int32((long __user *)data_address, &loaded_data); FPU_copy_to_reg0(&loaded_data, loaded_tag); break; - case 002: /* fld m64real */ + case 002: /* fld m64real (dd /0) */ clear_C1(); loaded_tag = FPU_load_double((double __user *)data_address, @@ -142,12 +149,44 @@ int FPU_load_store(u_char type, fpu_addr_modes addr_modes, } FPU_copy_to_reg0(&loaded_data, loaded_tag); break; - case 003: /* fild m16int */ + case 003: /* fild m16int (df /0) */ clear_C1(); loaded_tag = FPU_load_int16((short __user *)data_address, &loaded_data); FPU_copy_to_reg0(&loaded_data, loaded_tag); break; + /* case 004: undefined (d9 /1) */ + /* fisttp are enabled if CPUID(1).ECX(0) "sse3" is set */ + case 005: /* fisttp m32int (db /1) */ + clear_C1(); + sv_cw = control_word; + control_word |= RC_CHOP; + if (FPU_store_int32 + (st0_ptr, st0_tag, (long __user *)data_address)) + pop_0(); /* pop only if the number was actually stored + (see the 80486 manual p16-28) */ + control_word = sv_cw; + break; + case 006: /* fisttp m64int (dd /1) */ + clear_C1(); + sv_cw = control_word; + control_word |= RC_CHOP; + if (FPU_store_int64 + (st0_ptr, st0_tag, (long long __user *)data_address)) + pop_0(); /* pop only if the number was actually stored + (see the 80486 manual p16-28) */ + control_word = sv_cw; + break; + case 007: /* fisttp m16int (df /1) */ + clear_C1(); + sv_cw = control_word; + control_word |= RC_CHOP; + if (FPU_store_int16 + (st0_ptr, st0_tag, (short __user *)data_address)) + pop_0(); /* pop only if the number was actually stored + (see the 80486 manual p16-28) */ + control_word = sv_cw; + break; case 010: /* fst m32real */ clear_C1(); FPU_store_single(st0_ptr, st0_tag, diff --git a/kernel/arch/x86/math-emu/reg_compare.c b/kernel/arch/x86/math-emu/reg_compare.c index ecce55fc2..b77360fdb 100644 --- a/kernel/arch/x86/math-emu/reg_compare.c +++ b/kernel/arch/x86/math-emu/reg_compare.c @@ -249,6 +249,54 @@ static int compare_st_st(int nr) return 0; } +static int compare_i_st_st(int nr) +{ + int f, c; + FPU_REG *st_ptr; + + if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + /* Stack fault */ + EXCEPTION(EX_StackUnder); + return !(control_word & CW_Invalid); + } + + partial_status &= ~SW_C0; + st_ptr = &st(nr); + c = compare(st_ptr, FPU_gettagi(nr)); + if (c & COMP_NaN) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + EXCEPTION(EX_Invalid); + return !(control_word & CW_Invalid); + } + + switch (c & 7) { + case COMP_A_lt_B: + f = X86_EFLAGS_CF; + break; + case COMP_A_eq_B: + f = X86_EFLAGS_ZF; + break; + case COMP_A_gt_B: + f = 0; + break; + case COMP_No_Comp: + f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; + break; +#ifdef PARANOID + default: + EXCEPTION(EX_INTERNAL | 0x122); + f = 0; + break; +#endif /* PARANOID */ + } + FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; + if (c & COMP_Denormal) { + return denormal_operand() < 0; + } + return 0; +} + static int compare_u_st_st(int nr) { int f = 0, c; @@ -299,6 +347,58 @@ static int compare_u_st_st(int nr) return 0; } +static int compare_ui_st_st(int nr) +{ + int f = 0, c; + FPU_REG *st_ptr; + + if (!NOT_EMPTY(0) || !NOT_EMPTY(nr)) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + /* Stack fault */ + EXCEPTION(EX_StackUnder); + return !(control_word & CW_Invalid); + } + + partial_status &= ~SW_C0; + st_ptr = &st(nr); + c = compare(st_ptr, FPU_gettagi(nr)); + if (c & COMP_NaN) { + FPU_EFLAGS |= (X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF); + if (c & COMP_SNaN) { /* This is the only difference between + un-ordered and ordinary comparisons */ + EXCEPTION(EX_Invalid); + return !(control_word & CW_Invalid); + } + return 0; + } + + switch (c & 7) { + case COMP_A_lt_B: + f = X86_EFLAGS_CF; + break; + case COMP_A_eq_B: + f = X86_EFLAGS_ZF; + break; + case COMP_A_gt_B: + f = 0; + break; + case COMP_No_Comp: + f = X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF; + break; +#ifdef PARANOID + default: + EXCEPTION(EX_INTERNAL | 0x123); + f = 0; + break; +#endif /* PARANOID */ + } + FPU_EFLAGS = (FPU_EFLAGS & ~(X86_EFLAGS_ZF | X86_EFLAGS_PF | X86_EFLAGS_CF)) | f; + if (c & COMP_Denormal) { + return denormal_operand() < 0; + } + return 0; +} + /*---------------------------------------------------------------------------*/ void fcom_st(void) @@ -348,3 +448,31 @@ void fucompp(void) } else FPU_illegal(); } + +/* P6+ compare-to-EFLAGS ops */ + +void fcomi_(void) +{ + /* fcomi st(i) */ + compare_i_st_st(FPU_rm); +} + +void fcomip(void) +{ + /* fcomip st(i) */ + if (!compare_i_st_st(FPU_rm)) + FPU_pop(); +} + +void fucomi_(void) +{ + /* fucomi st(i) */ + compare_ui_st_st(FPU_rm); +} + +void fucomip(void) +{ + /* fucomip st(i) */ + if (!compare_ui_st_st(FPU_rm)) + FPU_pop(); +} diff --git a/kernel/arch/x86/mm/Makefile b/kernel/arch/x86/mm/Makefile index a482d1051..65c47fda2 100644 --- a/kernel/arch/x86/mm/Makefile +++ b/kernel/arch/x86/mm/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_SMP) += tlb.o obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/kernel/arch/x86/mm/dump_pagetables.c b/kernel/arch/x86/mm/dump_pagetables.c index f0cedf339..0f1c6fc3d 100644 --- a/kernel/arch/x86/mm/dump_pagetables.c +++ b/kernel/arch/x86/mm/dump_pagetables.c @@ -32,6 +32,8 @@ struct pg_state { const struct addr_marker *marker; unsigned long lines; bool to_dmesg; + bool check_wx; + unsigned long wx_pages; }; struct addr_marker { @@ -87,7 +89,7 @@ static struct addr_marker address_markers[] = { { 0/* VMALLOC_START */, "vmalloc() Area" }, { 0/*VMALLOC_END*/, "vmalloc() End" }, # ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persisent kmap() Area" }, + { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, # endif { 0/*FIXADDR_START*/, "Fixmap Area" }, #endif @@ -155,7 +157,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) pt_dump_cont_printf(m, dmsg, " "); if ((level == 4 && pr & _PAGE_PAT) || ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE)) - pt_dump_cont_printf(m, dmsg, "pat "); + pt_dump_cont_printf(m, dmsg, "PAT "); else pt_dump_cont_printf(m, dmsg, " "); if (pr & _PAGE_GLOBAL) @@ -198,8 +200,8 @@ static void note_page(struct seq_file *m, struct pg_state *st, * we have now. "break" is either changing perms, levels or * address space marker. */ - prot = pgprot_val(new_prot) & PTE_FLAGS_MASK; - cur = pgprot_val(st->current_prot) & PTE_FLAGS_MASK; + prot = pgprot_val(new_prot); + cur = pgprot_val(st->current_prot); if (!st->level) { /* First entry */ @@ -214,6 +216,16 @@ static void note_page(struct seq_file *m, struct pg_state *st, const char *unit = units; unsigned long delta; int width = sizeof(unsigned long) * 2; + pgprotval_t pr = pgprot_val(st->current_prot); + + if (st->check_wx && (pr & _PAGE_RW) && !(pr & _PAGE_NX)) { + WARN_ONCE(1, + "x86/mm: Found insecure W+X mapping at address %p/%pS\n", + (void *)st->start_address, + (void *)st->start_address); + st->wx_pages += (st->current_address - + st->start_address) / PAGE_SIZE; + } /* * Now print the actual finished series @@ -269,13 +281,13 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t addr, { int i; pte_t *start; + pgprotval_t prot; start = (pte_t *) pmd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PTE; i++) { - pgprot_t prot = pte_pgprot(*start); - + prot = pte_flags(*start); st->current_address = normalize_addr(P + i * PTE_LEVEL_MULT); - note_page(m, st, prot, 4); + note_page(m, st, __pgprot(prot), 4); start++; } } @@ -287,18 +299,19 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr, { int i; pmd_t *start; + pgprotval_t prot; start = (pmd_t *) pud_page_vaddr(addr); for (i = 0; i < PTRS_PER_PMD; i++) { st->current_address = normalize_addr(P + i * PMD_LEVEL_MULT); if (!pmd_none(*start)) { - pgprotval_t prot = pmd_val(*start) & PTE_FLAGS_MASK; - - if (pmd_large(*start) || !pmd_present(*start)) + if (pmd_large(*start) || !pmd_present(*start)) { + prot = pmd_flags(*start); note_page(m, st, __pgprot(prot), 3); - else + } else { walk_pte_level(m, st, *start, P + i * PMD_LEVEL_MULT); + } } else note_page(m, st, __pgprot(0), 3); start++; @@ -318,19 +331,20 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, { int i; pud_t *start; + pgprotval_t prot; start = (pud_t *) pgd_page_vaddr(addr); for (i = 0; i < PTRS_PER_PUD; i++) { st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT); if (!pud_none(*start)) { - pgprotval_t prot = pud_val(*start) & PTE_FLAGS_MASK; - - if (pud_large(*start) || !pud_present(*start)) + if (pud_large(*start) || !pud_present(*start)) { + prot = pud_flags(*start); note_page(m, st, __pgprot(prot), 2); - else + } else { walk_pmd_level(m, st, *start, P + i * PUD_LEVEL_MULT); + } } else note_page(m, st, __pgprot(0), 2); @@ -344,13 +358,30 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr, #define pgd_none(a) pud_none(__pud(pgd_val(a))) #endif -void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +#ifdef CONFIG_X86_64 +static inline bool is_hypervisor_range(int idx) +{ + /* + * ffff800000000000 - ffff87ffffffffff is reserved for + * the hypervisor. + */ + return paravirt_enabled() && + (idx >= pgd_index(__PAGE_OFFSET) - 16) && + (idx < pgd_index(__PAGE_OFFSET)); +} +#else +static inline bool is_hypervisor_range(int idx) { return false; } +#endif + +static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, + bool checkwx) { #ifdef CONFIG_X86_64 pgd_t *start = (pgd_t *) &init_level4_pgt; #else pgd_t *start = swapper_pg_dir; #endif + pgprotval_t prot; int i; struct pg_state st = {}; @@ -359,16 +390,20 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) st.to_dmesg = true; } + st.check_wx = checkwx; + if (checkwx) + st.wx_pages = 0; + for (i = 0; i < PTRS_PER_PGD; i++) { st.current_address = normalize_addr(i * PGD_LEVEL_MULT); - if (!pgd_none(*start)) { - pgprotval_t prot = pgd_val(*start) & PTE_FLAGS_MASK; - - if (pgd_large(*start) || !pgd_present(*start)) + if (!pgd_none(*start) && !is_hypervisor_range(i)) { + if (pgd_large(*start) || !pgd_present(*start)) { + prot = pgd_flags(*start); note_page(m, &st, __pgprot(prot), 1); - else + } else { walk_pud_level(m, &st, *start, i * PGD_LEVEL_MULT); + } } else note_page(m, &st, __pgprot(0), 1); @@ -378,8 +413,26 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) /* Flush out the last page */ st.current_address = normalize_addr(PTRS_PER_PGD*PGD_LEVEL_MULT); note_page(m, &st, __pgprot(0), 0); + if (!checkwx) + return; + if (st.wx_pages) + pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n", + st.wx_pages); + else + pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n"); +} + +void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) +{ + ptdump_walk_pgd_level_core(m, pgd, false); +} + +void ptdump_walk_pgd_level_checkwx(void) +{ + ptdump_walk_pgd_level_core(NULL, NULL, true); } +#ifdef CONFIG_X86_PTDUMP static int ptdump_show(struct seq_file *m, void *v) { ptdump_walk_pgd_level(m, NULL); @@ -397,10 +450,13 @@ static const struct file_operations ptdump_fops = { .llseek = seq_lseek, .release = single_release, }; +#endif static int pt_dump_init(void) { +#ifdef CONFIG_X86_PTDUMP struct dentry *pe; +#endif #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ @@ -412,10 +468,12 @@ static int pt_dump_init(void) address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif +#ifdef CONFIG_X86_PTDUMP pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, &ptdump_fops); if (!pe) return -ENOMEM; +#endif return 0; } diff --git a/kernel/arch/x86/mm/fault.c b/kernel/arch/x86/mm/fault.c index 9dc909841..e830c71a1 100644 --- a/kernel/arch/x86/mm/fault.c +++ b/kernel/arch/x86/mm/fault.c @@ -20,6 +20,7 @@ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ +#include <asm/vm86.h> /* struct vm86 */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -286,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -301,14 +305,16 @@ static inline void check_v8086_mode(struct pt_regs *regs, unsigned long address, struct task_struct *tsk) { +#ifdef CONFIG_VM86 unsigned long bit; - if (!v8086_mode(regs)) + if (!v8086_mode(regs) || !tsk->thread.vm86) return; bit = (address - 0xA0000) >> PAGE_SHIFT; if (bit < 32) - tsk->thread.screen_bitmap |= 1 << bit; + tsk->thread.vm86->screen_bitmap |= 1 << bit; +#endif } static bool low_pfn(unsigned long pfn) @@ -357,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -400,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; diff --git a/kernel/arch/x86/mm/gup.c b/kernel/arch/x86/mm/gup.c index 81bf3d2af..ae9a37bf1 100644 --- a/kernel/arch/x86/mm/gup.c +++ b/kernel/arch/x86/mm/gup.c @@ -118,21 +118,20 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; - pte_t pte = *(pte_t *)&pmd; struct page *head, *page; int refs; mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_flags(pte) & mask) != mask) + if ((pmd_flags(pmd) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); refs = 0; - head = pte_page(pte); + head = pmd_page(pmd); page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); @@ -195,21 +194,20 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr, unsigned long end, int write, struct page **pages, int *nr) { unsigned long mask; - pte_t pte = *(pte_t *)&pud; struct page *head, *page; int refs; mask = _PAGE_PRESENT|_PAGE_USER; if (write) mask |= _PAGE_RW; - if ((pte_flags(pte) & mask) != mask) + if ((pud_flags(pud) & mask) != mask) return 0; /* hugepages are never "special" */ - VM_BUG_ON(pte_flags(pte) & _PAGE_SPECIAL); - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); + VM_BUG_ON(!pfn_valid(pud_pfn(pud))); refs = 0; - head = pte_page(pte); + head = pud_page(pud); page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); do { VM_BUG_ON_PAGE(compound_head(page) != head, page); diff --git a/kernel/arch/x86/mm/highmem_32.c b/kernel/arch/x86/mm/highmem_32.c index 0d1cbcf47..bd24ba1c4 100644 --- a/kernel/arch/x86/mm/highmem_32.c +++ b/kernel/arch/x86/mm/highmem_32.c @@ -111,20 +111,6 @@ void __kunmap_atomic(void *kvaddr) } EXPORT_SYMBOL(__kunmap_atomic); -struct page *kmap_atomic_to_page(void *ptr) -{ - unsigned long idx, vaddr = (unsigned long)ptr; - pte_t *pte; - - if (vaddr < FIXADDR_START) - return virt_to_page(ptr); - - idx = virt_to_fix(vaddr); - pte = kmap_pte - (idx - FIX_KMAP_BEGIN); - return pte_page(*pte); -} -EXPORT_SYMBOL(kmap_atomic_to_page); - void __init set_highmem_pages_init(void) { struct zone *zone; diff --git a/kernel/arch/x86/mm/init.c b/kernel/arch/x86/mm/init.c index 1d553186c..493f54172 100644 --- a/kernel/arch/x86/mm/init.c +++ b/kernel/arch/x86/mm/init.c @@ -30,8 +30,11 @@ /* * Tables translating between page_cache_type_t and pte encoding. * - * Minimal supported modes are defined statically, they are modified - * during bootup if more supported cache modes are available. + * The default values are defined statically as minimal supported mode; + * WC and WT fall back to UC-. pat_init() updates these values to support + * more cache modes, WC and WT, when it is safe to do so. See pat_init() + * for the details. Note, __early_ioremap() used during early boot-time + * takes pgprot_t (pte encoding) and does not use these tables. * * Index into __cachemode2pte_tbl[] is the cachemode. * @@ -40,7 +43,7 @@ */ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { [_PAGE_CACHE_MODE_WB ] = 0 | 0 , - [_PAGE_CACHE_MODE_WC ] = _PAGE_PWT | 0 , + [_PAGE_CACHE_MODE_WC ] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, @@ -50,11 +53,11 @@ EXPORT_SYMBOL(__cachemode2pte_tbl); uint8_t __pte2cachemode_tbl[8] = { [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; @@ -351,7 +354,7 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, } for (i = 0; i < nr_range; i++) - printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n", + pr_debug(" [mem %#010lx-%#010lx] page %s\n", mr[i].start, mr[i].end - 1, page_size_string(&mr[i])); @@ -398,7 +401,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long ret = 0; int nr_range, i; - pr_info("init_memory_mapping: [mem %#010lx-%#010lx]\n", + pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n", start, end - 1); memset(mr, 0, sizeof(mr)); @@ -690,14 +693,12 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void __init free_initrd_mem(unsigned long start, unsigned long end) { -#ifdef CONFIG_MICROCODE_EARLY /* * Remember, initrd memory may contain microcode or other useful things. * Before we lose initrd mem, we need to find a place to hold them * now that normal virtual memory is enabled. */ save_microcode_in_initrd(); -#endif /* * end could be not aligned, and We can not align that, diff --git a/kernel/arch/x86/mm/init_32.c b/kernel/arch/x86/mm/init_32.c index c23ab1ee3..cb4ef3de6 100644 --- a/kernel/arch/x86/mm/init_32.c +++ b/kernel/arch/x86/mm/init_32.c @@ -434,7 +434,7 @@ void __init add_highpages_with_active_regions(int nid, phys_addr_t start, end; u64 i; - for_each_free_mem_range(i, nid, &start, &end, NULL) { + for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &start, &end, NULL) { unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), start_pfn, end_pfn); unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), @@ -823,11 +823,11 @@ void __init mem_init(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int arch_add_memory(int nid, u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { struct pglist_data *pgdata = NODE_DATA(nid); struct zone *zone = pgdata->node_zones + - zone_for_memory(nid, start, size, ZONE_HIGHMEM); + zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; @@ -957,6 +957,8 @@ void mark_rodata_ro(void) set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif mark_nxdata_nx(); + if (__supported_pte_mask & _PAGE_NX) + debug_checkwx(); } #endif diff --git a/kernel/arch/x86/mm/init_64.c b/kernel/arch/x86/mm/init_64.c index 3fba623e3..ec081fe0c 100644 --- a/kernel/arch/x86/mm/init_64.c +++ b/kernel/arch/x86/mm/init_64.c @@ -687,11 +687,11 @@ static void update_end_of_memory_vars(u64 start, u64 size) * Memory is added always to NORMAL zone. This means you will never get * additional DMA/DMA32 memory. */ -int arch_add_memory(int nid, u64 start, u64 size) +int arch_add_memory(int nid, u64 start, u64 size, bool for_device) { struct pglist_data *pgdat = NODE_DATA(nid); struct zone *zone = pgdat->node_zones + - zone_for_memory(nid, start, size, ZONE_NORMAL); + zone_for_memory(nid, start, size, ZONE_NORMAL, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; @@ -1132,7 +1132,7 @@ void mark_rodata_ro(void) * has been zapped already via cleanup_highmem(). */ all_end = roundup((unsigned long)_brk_end, PMD_SIZE); - set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); + set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); rodata_test(); @@ -1150,6 +1150,8 @@ void mark_rodata_ro(void) free_init_pages("unused kernel", (unsigned long) __va(__pa_symbol(rodata_end)), (unsigned long) __va(__pa_symbol(_sdata))); + + debug_checkwx(); } #endif @@ -1268,7 +1270,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, /* check to see if we have contiguous blocks */ if (p_end != p || node_start != node) { if (p_start) - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); addr_start = addr; node_start = node; @@ -1366,7 +1368,7 @@ void register_page_bootmem_memmap(unsigned long section_nr, void __meminit vmemmap_populate_print_last(void) { if (p_start) { - printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n", + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", addr_start, addr_end-1, p_start, p_end-1, node_start); p_start = NULL; p_end = NULL; diff --git a/kernel/arch/x86/mm/iomap_32.c b/kernel/arch/x86/mm/iomap_32.c index b2ffa5c7d..dd25dd167 100644 --- a/kernel/arch/x86/mm/iomap_32.c +++ b/kernel/arch/x86/mm/iomap_32.c @@ -84,13 +84,13 @@ void __iomem * iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) { /* - * For non-PAT systems, promote PAGE_KERNEL_WC to PAGE_KERNEL_UC_MINUS. - * PAGE_KERNEL_WC maps to PWT, which translates to uncached if the - * MTRR is UC or WC. UC_MINUS gets the real intention, of the - * user, which is "WC if the MTRR is WC, UC if you can't do that." + * For non-PAT systems, translate non-WB request to UC- just in + * case the caller set the PWT bit to prot directly without using + * pgprot_writecombine(). UC- translates to uncached if the MTRR + * is UC or WC. UC- gets the real intention, of the user, which is + * "WC if the MTRR is WC, UC if you can't do that." */ - if (!pat_enabled && pgprot_val(prot) == - (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC))) + if (!pat_enabled() && pgprot2cachemode(prot) != _PAGE_CACHE_MODE_WB) prot = __pgprot(__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS)); diff --git a/kernel/arch/x86/mm/ioremap.c b/kernel/arch/x86/mm/ioremap.c index 70e7444c6..b9c78f3bc 100644 --- a/kernel/arch/x86/mm/ioremap.c +++ b/kernel/arch/x86/mm/ioremap.c @@ -42,6 +42,9 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, case _PAGE_CACHE_MODE_WC: err = _set_memory_wc(vaddr, nrpages); break; + case _PAGE_CACHE_MODE_WT: + err = _set_memory_wt(vaddr, nrpages); + break; case _PAGE_CACHE_MODE_WB: err = _set_memory_wb(vaddr, nrpages); break; @@ -60,8 +63,6 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, !PageReserved(pfn_to_page(start_pfn + i))) return 1; - WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); - return 0; } @@ -91,7 +92,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, pgprot_t prot; int retval; void __iomem *ret_addr; - int ram_region; /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; @@ -114,23 +114,15 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ - /* First check if whole region can be identified as RAM or not */ - ram_region = region_is_ram(phys_addr, size); - if (ram_region > 0) { - WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n", - (unsigned long int)phys_addr, - (unsigned long int)last_addr); + pfn = phys_addr >> PAGE_SHIFT; + last_pfn = last_addr >> PAGE_SHIFT; + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) { + WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n", + &phys_addr, &last_addr); return NULL; } - /* If could not be identified(-1), check page by page */ - if (ram_region < 0) { - pfn = phys_addr >> PAGE_SHIFT; - last_pfn = last_addr >> PAGE_SHIFT; - if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, - __ioremap_check_ram) == 1) - return NULL; - } /* * Mappings have to be page-aligned */ @@ -172,6 +164,10 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, prot = __pgprot(pgprot_val(prot) | cachemode2protval(_PAGE_CACHE_MODE_WC)); break; + case _PAGE_CACHE_MODE_WT: + prot = __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WT)); + break; case _PAGE_CACHE_MODE_WB: break; } @@ -234,10 +230,11 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) { /* * Ideally, this should be: - * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; + * pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS; * * Till we fix all X drivers to use ioremap_wc(), we will use - * UC MINUS. + * UC MINUS. Drivers that are certain they need or can already + * be converted over to strong UC can use ioremap_uc(). */ enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS; @@ -247,6 +244,39 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size) EXPORT_SYMBOL(ioremap_nocache); /** + * ioremap_uc - map bus memory into CPU space as strongly uncachable + * @phys_addr: bus address of the memory + * @size: size of the resource to map + * + * ioremap_uc performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + * + * This version of ioremap ensures that the memory is marked with a strong + * preference as completely uncachable on the CPU when possible. For non-PAT + * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT + * systems this will set the PAT entry for the pages as strong UC. This call + * will honor existing caching rules from things like the PCI bus. Note that + * there are other caches and buffers on many busses. In particular driver + * authors should read up on PCI writes. + * + * It's useful if some control registers are in such an area and + * write combining or read caching is not desirable: + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size) +{ + enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC; + + return __ioremap_caller(phys_addr, size, pcm, + __builtin_return_address(0)); +} +EXPORT_SYMBOL_GPL(ioremap_uc); + +/** * ioremap_wc - map memory into CPU space write combined * @phys_addr: bus address of the memory * @size: size of the resource to map @@ -258,14 +288,28 @@ EXPORT_SYMBOL(ioremap_nocache); */ void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size) { - if (pat_enabled) - return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC, __builtin_return_address(0)); - else - return ioremap_nocache(phys_addr, size); } EXPORT_SYMBOL(ioremap_wc); +/** + * ioremap_wt - map memory into CPU space write through + * @phys_addr: bus address of the memory + * @size: size of the resource to map + * + * This version of ioremap ensures that the memory is marked write through. + * Write through stores data into memory while keeping the cache up-to-date. + * + * Must be freed with iounmap. + */ +void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size) +{ + return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT, + __builtin_return_address(0)); +} +EXPORT_SYMBOL(ioremap_wt); + void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) { return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB, @@ -331,7 +375,7 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); -int arch_ioremap_pud_supported(void) +int __init arch_ioremap_pud_supported(void) { #ifdef CONFIG_X86_64 return cpu_has_gbpages; @@ -340,7 +384,7 @@ int arch_ioremap_pud_supported(void) #endif } -int arch_ioremap_pmd_supported(void) +int __init arch_ioremap_pmd_supported(void) { return cpu_has_pse; } @@ -353,18 +397,18 @@ void *xlate_dev_mem_ptr(phys_addr_t phys) { unsigned long start = phys & PAGE_MASK; unsigned long offset = phys & ~PAGE_MASK; - unsigned long vaddr; + void *vaddr; /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE); + vaddr = ioremap_cache(start, PAGE_SIZE); /* Only add the offset on success and return NULL if the ioremap() failed: */ if (vaddr) vaddr += offset; - return (void *)vaddr; + return vaddr; } void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) @@ -373,7 +417,6 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) return; iounmap((void __iomem *)((unsigned long)addr & PAGE_MASK)); - return; } static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; diff --git a/kernel/arch/x86/mm/kasan_init_64.c b/kernel/arch/x86/mm/kasan_init_64.c index 9a54dbe98..d470cf219 100644 --- a/kernel/arch/x86/mm/kasan_init_64.c +++ b/kernel/arch/x86/mm/kasan_init_64.c @@ -1,3 +1,4 @@ +#define pr_fmt(fmt) "kasan: " fmt #include <linux/bootmem.h> #include <linux/kasan.h> #include <linux/kdebug.h> @@ -11,20 +12,6 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_X_MAX]; -static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss; -static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss; -static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss; - -/* - * This page used as early shadow. We don't use empty_zero_page - * at early stages, stack instrumentation could write some garbage - * to this page. - * Latter we reuse it as zero shadow for large ranges of memory - * that allowed to access, but not instrumented by kasan - * (vmalloc/vmemmap ...). - */ -static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss; - static int __init map_range(struct range *range) { unsigned long start; @@ -61,106 +48,6 @@ static void __init kasan_map_early_shadow(pgd_t *pgd) } } -static int __init zero_pte_populate(pmd_t *pmd, unsigned long addr, - unsigned long end) -{ - pte_t *pte = pte_offset_kernel(pmd, addr); - - while (addr + PAGE_SIZE <= end) { - WARN_ON(!pte_none(*pte)); - set_pte(pte, __pte(__pa_nodebug(kasan_zero_page) - | __PAGE_KERNEL_RO)); - addr += PAGE_SIZE; - pte = pte_offset_kernel(pmd, addr); - } - return 0; -} - -static int __init zero_pmd_populate(pud_t *pud, unsigned long addr, - unsigned long end) -{ - int ret = 0; - pmd_t *pmd = pmd_offset(pud, addr); - - while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) { - WARN_ON(!pmd_none(*pmd)); - set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte) - | _KERNPG_TABLE)); - addr += PMD_SIZE; - pmd = pmd_offset(pud, addr); - } - if (addr < end) { - if (pmd_none(*pmd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pmd(pmd, __pmd(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pte_populate(pmd, addr, end); - } - return ret; -} - - -static int __init zero_pud_populate(pgd_t *pgd, unsigned long addr, - unsigned long end) -{ - int ret = 0; - pud_t *pud = pud_offset(pgd, addr); - - while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) { - WARN_ON(!pud_none(*pud)); - set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd) - | _KERNPG_TABLE)); - addr += PUD_SIZE; - pud = pud_offset(pgd, addr); - } - - if (addr < end) { - if (pud_none(*pud)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pud(pud, __pud(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pmd_populate(pud, addr, end); - } - return ret; -} - -static int __init zero_pgd_populate(unsigned long addr, unsigned long end) -{ - int ret = 0; - pgd_t *pgd = pgd_offset_k(addr); - - while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) { - WARN_ON(!pgd_none(*pgd)); - set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud) - | _KERNPG_TABLE)); - addr += PGDIR_SIZE; - pgd = pgd_offset_k(addr); - } - - if (addr < end) { - if (pgd_none(*pgd)) { - void *p = vmemmap_alloc_block(PAGE_SIZE, NUMA_NO_NODE); - if (!p) - return -ENOMEM; - set_pgd(pgd, __pgd(__pa_nodebug(p) | _KERNPG_TABLE)); - } - ret = zero_pud_populate(pgd, addr, end); - } - return ret; -} - - -static void __init populate_zero_shadow(const void *start, const void *end) -{ - if (zero_pgd_populate((unsigned long)start, (unsigned long)end)) - panic("kasan: unable to map zero shadow!"); -} - - #ifdef CONFIG_KASAN_INLINE static int kasan_die_handler(struct notifier_block *self, unsigned long val, @@ -212,7 +99,7 @@ void __init kasan_init(void) clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); - populate_zero_shadow((void *)KASAN_SHADOW_START, + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, kasan_mem_to_shadow((void *)PAGE_OFFSET)); for (i = 0; i < E820_X_MAX; i++) { @@ -222,14 +109,15 @@ void __init kasan_init(void) if (map_range(&pfn_mapped[i])) panic("kasan: unable to allocate shadow!"); } - populate_zero_shadow(kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), - kasan_mem_to_shadow((void *)__START_KERNEL_map)); + kasan_populate_zero_shadow( + kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), + kasan_mem_to_shadow((void *)__START_KERNEL_map)); vmemmap_populate((unsigned long)kasan_mem_to_shadow(_stext), (unsigned long)kasan_mem_to_shadow(_end), NUMA_NO_NODE); - populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), + kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); memset(kasan_zero_page, 0, PAGE_SIZE); @@ -237,4 +125,6 @@ void __init kasan_init(void) load_cr3(init_level4_pgt); __flush_tlb_all(); init_task.kasan_depth = 0; + + pr_info("KernelAddressSanitizer initialized\n"); } diff --git a/kernel/arch/x86/mm/mpx.c b/kernel/arch/x86/mm/mpx.c index 4d1c11c07..ef05755a1 100644 --- a/kernel/arch/x86/mm/mpx.c +++ b/kernel/arch/x86/mm/mpx.c @@ -10,13 +10,31 @@ #include <linux/syscalls.h> #include <linux/sched/sysctl.h> -#include <asm/i387.h> #include <asm/insn.h> #include <asm/mman.h> #include <asm/mmu_context.h> #include <asm/mpx.h> #include <asm/processor.h> -#include <asm/fpu-internal.h> +#include <asm/fpu/internal.h> + +#define CREATE_TRACE_POINTS +#include <asm/trace/mpx.h> + +static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BD_SIZE_BYTES_64; + else + return MPX_BD_SIZE_BYTES_32; +} + +static inline unsigned long mpx_bt_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_SIZE_BYTES_64; + else + return MPX_BT_SIZE_BYTES_32; +} /* * This is really a simplified "vm_mmap". it only handles MPX @@ -24,58 +42,21 @@ */ static unsigned long mpx_mmap(unsigned long len) { - unsigned long ret; - unsigned long addr, pgoff; struct mm_struct *mm = current->mm; - vm_flags_t vm_flags; - struct vm_area_struct *vma; + unsigned long addr, populate; - /* Only bounds table and bounds directory can be allocated here */ - if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES) + /* Only bounds table can be allocated here */ + if (len != mpx_bt_size_bytes(mm)) return -EINVAL; down_write(&mm->mmap_sem); - - /* Too many mappings? */ - if (mm->map_count > sysctl_max_map_count) { - ret = -ENOMEM; - goto out; - } - - /* Obtain the address to map to. we verify (or select) it and ensure - * that it represents a valid section of the address space. - */ - addr = get_unmapped_area(NULL, 0, len, 0, MAP_ANONYMOUS | MAP_PRIVATE); - if (addr & ~PAGE_MASK) { - ret = addr; - goto out; - } - - vm_flags = VM_READ | VM_WRITE | VM_MPX | - mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; - - /* Set pgoff according to addr for anon_vma */ - pgoff = addr >> PAGE_SHIFT; - - ret = mmap_region(NULL, addr, len, vm_flags, pgoff); - if (IS_ERR_VALUE(ret)) - goto out; - - vma = find_vma(mm, ret); - if (!vma) { - ret = -ENOMEM; - goto out; - } - - if (vm_flags & VM_LOCKED) { - up_write(&mm->mmap_sem); - mm_populate(ret, len); - return ret; - } - -out: + addr = do_mmap(NULL, 0, len, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS | MAP_PRIVATE, VM_MPX, 0, &populate); up_write(&mm->mmap_sem); - return ret; + if (populate) + mm_populate(addr, populate); + + return addr; } enum reg_type { @@ -120,19 +101,19 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, switch (type) { case REG_TYPE_RM: regno = X86_MODRM_RM(insn->modrm.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_INDEX: regno = X86_SIB_INDEX(insn->sib.value); - if (X86_REX_X(insn->rex_prefix.value) == 1) + if (X86_REX_X(insn->rex_prefix.value)) regno += 8; break; case REG_TYPE_BASE: regno = X86_SIB_BASE(insn->sib.value); - if (X86_REX_B(insn->rex_prefix.value) == 1) + if (X86_REX_B(insn->rex_prefix.value)) regno += 8; break; @@ -142,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } @@ -254,10 +235,10 @@ bad_opcode: * * The caller is expected to kfree() the returned siginfo_t. */ -siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, - struct xsave_struct *xsave_buf) +siginfo_t *mpx_generate_siginfo(struct pt_regs *regs) { - struct bndreg *bndregs, *bndreg; + const struct mpx_bndreg_state *bndregs; + const struct mpx_bndreg *bndreg; siginfo_t *info = NULL; struct insn insn; uint8_t bndregno; @@ -277,14 +258,14 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } - /* get the bndregs _area_ of the xsave structure */ - bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS); + /* get bndregs field from current task's xsave area */ + bndregs = get_xsave_field_ptr(XFEATURE_MASK_BNDREGS); if (!bndregs) { err = -EINVAL; goto err_out; } /* now go select the individual register in the set of 4 */ - bndreg = &bndregs[bndregno]; + bndreg = &bndregs->bndreg[bndregno]; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { @@ -316,6 +297,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs, err = -EINVAL; goto err_out; } + trace_mpx_bounds_register_exception(info->si_addr, bndreg); return info; err_out: /* info might be NULL, but kfree() handles that */ @@ -323,25 +305,18 @@ err_out: return ERR_PTR(err); } -static __user void *task_get_bounds_dir(struct task_struct *tsk) +static __user void *mpx_get_bounds_dir(void) { - struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; if (!cpu_feature_enabled(X86_FEATURE_MPX)) return MPX_INVALID_BOUNDS_DIR; /* - * 32-bit binaries on 64-bit kernels are currently - * unsupported. - */ - if (IS_ENABLED(CONFIG_X86_64) && test_thread_flag(TIF_IA32)) - return MPX_INVALID_BOUNDS_DIR; - /* * The bounds directory pointer is stored in a register * only accessible if we first do an xsave. */ - fpu_save_init(&tsk->thread.fpu); - bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) return MPX_INVALID_BOUNDS_DIR; @@ -360,10 +335,10 @@ static __user void *task_get_bounds_dir(struct task_struct *tsk) (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK); } -int mpx_enable_management(struct task_struct *tsk) +int mpx_enable_management(void) { void __user *bd_base = MPX_INVALID_BOUNDS_DIR; - struct mm_struct *mm = tsk->mm; + struct mm_struct *mm = current->mm; int ret = 0; /* @@ -372,11 +347,12 @@ int mpx_enable_management(struct task_struct *tsk) * directory into XSAVE/XRSTOR Save Area and enable MPX through * XRSTOR instruction. * - * fpu_xsave() is expected to be very expensive. Storing the bounds - * directory here means that we do not have to do xsave in the unmap - * path; we can just use mm->bd_addr instead. + * The copy_xregs_to_kernel() beneath get_xsave_field_ptr() is + * expected to be relatively expensive. Storing the bounds + * directory here means that we do not have to do xsave in the + * unmap path; we can just use mm->bd_addr instead. */ - bd_base = task_get_bounds_dir(tsk); + bd_base = mpx_get_bounds_dir(); down_write(&mm->mmap_sem); mm->bd_addr = bd_base; if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR) @@ -386,7 +362,7 @@ int mpx_enable_management(struct task_struct *tsk) return ret; } -int mpx_disable_management(struct task_struct *tsk) +int mpx_disable_management(void) { struct mm_struct *mm = current->mm; @@ -399,29 +375,59 @@ int mpx_disable_management(struct task_struct *tsk) return 0; } +static int mpx_cmpxchg_bd_entry(struct mm_struct *mm, + unsigned long *curval, + unsigned long __user *addr, + unsigned long old_val, unsigned long new_val) +{ + int ret; + /* + * user_atomic_cmpxchg_inatomic() actually uses sizeof() + * the pointer that we pass to it to figure out how much + * data to cmpxchg. We have to be careful here not to + * pass a pointer to a 64-bit data type when we only want + * a 32-bit copy. + */ + if (is_64bit_mm(mm)) { + ret = user_atomic_cmpxchg_inatomic(curval, + addr, old_val, new_val); + } else { + u32 uninitialized_var(curval_32); + u32 old_val_32 = old_val; + u32 new_val_32 = new_val; + u32 __user *addr_32 = (u32 __user *)addr; + + ret = user_atomic_cmpxchg_inatomic(&curval_32, + addr_32, old_val_32, new_val_32); + *curval = curval_32; + } + return ret; +} + /* - * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each - * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB, + * With 32-bit mode, a bounds directory is 4MB, and the size of each + * bounds table is 16KB. With 64-bit mode, a bounds directory is 2GB, * and the size of each bounds table is 4MB. */ -static int allocate_bt(long __user *bd_entry) +static int allocate_bt(struct mm_struct *mm, long __user *bd_entry) { unsigned long expected_old_val = 0; unsigned long actual_old_val = 0; unsigned long bt_addr; + unsigned long bd_new_entry; int ret = 0; /* * Carve the virtual space out of userspace for the new * bounds table: */ - bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES); + bt_addr = mpx_mmap(mpx_bt_size_bytes(mm)); if (IS_ERR((void *)bt_addr)) return PTR_ERR((void *)bt_addr); /* * Set the valid flag (kinda like _PAGE_PRESENT in a pte) */ - bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG; + bd_new_entry = bt_addr | MPX_BD_ENTRY_VALID_FLAG; /* * Go poke the address of the new bounds table in to the @@ -434,8 +440,8 @@ static int allocate_bt(long __user *bd_entry) * mmap_sem at this point, unlike some of the other part * of the MPX code that have to pagefault_disable(). */ - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, bt_addr); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, bd_entry, + expected_old_val, bd_new_entry); if (ret) goto out_unmap; @@ -463,9 +469,10 @@ static int allocate_bt(long __user *bd_entry) ret = -EINVAL; goto out_unmap; } + trace_mpx_new_bounds_table(bt_addr); return 0; out_unmap: - vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES); + vm_munmap(bt_addr, mpx_bt_size_bytes(mm)); return ret; } @@ -480,12 +487,13 @@ out_unmap: * bound table is 16KB. With 64-bit mode, the size of BD is 2GB, * and the size of each bound table is 4MB. */ -static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) +static int do_mpx_bt_fault(void) { unsigned long bd_entry, bd_base; - struct bndcsr *bndcsr; + const struct mpx_bndcsr *bndcsr; + struct mm_struct *mm = current->mm; - bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR); + bndcsr = get_xsave_field_ptr(XFEATURE_MASK_BNDCSR); if (!bndcsr) return -EINVAL; /* @@ -502,13 +510,13 @@ static int do_mpx_bt_fault(struct xsave_struct *xsave_buf) * the directory is. */ if ((bd_entry < bd_base) || - (bd_entry >= bd_base + MPX_BD_SIZE_BYTES)) + (bd_entry >= bd_base + mpx_bd_size_bytes(mm))) return -EINVAL; - return allocate_bt((long __user *)bd_entry); + return allocate_bt(mm, (long __user *)bd_entry); } -int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) +int mpx_handle_bd_fault(void) { /* * Userspace never asked us to manage the bounds tables, @@ -517,7 +525,7 @@ int mpx_handle_bd_fault(struct xsave_struct *xsave_buf) if (!kernel_managing_mpx_tables(current->mm)) return -EINVAL; - if (do_mpx_bt_fault(xsave_buf)) { + if (do_mpx_bt_fault()) { force_sig(SIGSEGV, current); /* * The force_sig() is essentially "handling" this @@ -554,29 +562,78 @@ static int mpx_resolve_fault(long __user *addr, int write) return 0; } +static unsigned long mpx_bd_entry_to_bt_addr(struct mm_struct *mm, + unsigned long bd_entry) +{ + unsigned long bt_addr = bd_entry; + int align_to_bytes; + /* + * Bit 0 in a bt_entry is always the valid bit. + */ + bt_addr &= ~MPX_BD_ENTRY_VALID_FLAG; + /* + * Tables are naturally aligned at 8-byte boundaries + * on 64-bit and 4-byte boundaries on 32-bit. The + * documentation makes it appear that the low bits + * are ignored by the hardware, so we do the same. + */ + if (is_64bit_mm(mm)) + align_to_bytes = 8; + else + align_to_bytes = 4; + bt_addr &= ~(align_to_bytes-1); + return bt_addr; +} + +/* + * We only want to do a 4-byte get_user() on 32-bit. Otherwise, + * we might run off the end of the bounds table if we are on + * a 64-bit kernel and try to get 8 bytes. + */ +int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret, + long __user *bd_entry_ptr) +{ + u32 bd_entry_32; + int ret; + + if (is_64bit_mm(mm)) + return get_user(*bd_entry_ret, bd_entry_ptr); + + /* + * Note that get_user() uses the type of the *pointer* to + * establish the size of the get, not the destination. + */ + ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr); + *bd_entry_ret = bd_entry_32; + return ret; +} + /* * Get the base of bounds tables pointed by specific bounds * directory entry. */ static int get_bt_addr(struct mm_struct *mm, - long __user *bd_entry, unsigned long *bt_addr) + long __user *bd_entry_ptr, + unsigned long *bt_addr_result) { int ret; int valid_bit; + unsigned long bd_entry; + unsigned long bt_addr; - if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry))) + if (!access_ok(VERIFY_READ, (bd_entry_ptr), sizeof(*bd_entry_ptr))) return -EFAULT; while (1) { int need_write = 0; pagefault_disable(); - ret = get_user(*bt_addr, bd_entry); + ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr); pagefault_enable(); if (!ret) break; if (ret == -EFAULT) - ret = mpx_resolve_fault(bd_entry, need_write); + ret = mpx_resolve_fault(bd_entry_ptr, need_write); /* * If we could not resolve the fault, consider it * userspace's fault and error out. @@ -585,8 +642,8 @@ static int get_bt_addr(struct mm_struct *mm, return ret; } - valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG; - *bt_addr &= MPX_BT_ADDR_MASK; + valid_bit = bd_entry & MPX_BD_ENTRY_VALID_FLAG; + bt_addr = mpx_bd_entry_to_bt_addr(mm, bd_entry); /* * When the kernel is managing bounds tables, a bounds directory @@ -595,7 +652,7 @@ static int get_bt_addr(struct mm_struct *mm, * data in the address field, we know something is wrong. This * -EINVAL return will cause a SIGSEGV. */ - if (!valid_bit && *bt_addr) + if (!valid_bit && bt_addr) return -EINVAL; /* * Do we have an completely zeroed bt entry? That is OK. It @@ -606,19 +663,112 @@ static int get_bt_addr(struct mm_struct *mm, if (!valid_bit) return -ENOENT; + *bt_addr_result = bt_addr; return 0; } +static inline int bt_entry_size_bytes(struct mm_struct *mm) +{ + if (is_64bit_mm(mm)) + return MPX_BT_ENTRY_BYTES_64; + else + return MPX_BT_ENTRY_BYTES_32; +} + +/* + * Take a virtual address and turns it in to the offset in bytes + * inside of the bounds table where the bounds table entry + * controlling 'addr' can be found. + */ +static unsigned long mpx_get_bt_entry_offset_bytes(struct mm_struct *mm, + unsigned long addr) +{ + unsigned long bt_table_nr_entries; + unsigned long offset = addr; + + if (is_64bit_mm(mm)) { + /* Bottom 3 bits are ignored on 64-bit */ + offset >>= 3; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_64; + } else { + /* Bottom 2 bits are ignored on 32-bit */ + offset >>= 2; + bt_table_nr_entries = MPX_BT_NR_ENTRIES_32; + } + /* + * We know the size of the table in to which we are + * indexing, and we have eliminated all the low bits + * which are ignored for indexing. + * + * Mask out all the high bits which we do not need + * to index in to the table. Note that the tables + * are always powers of two so this gives us a proper + * mask. + */ + offset &= (bt_table_nr_entries-1); + /* + * We now have an entry offset in terms of *entries* in + * the table. We need to scale it back up to bytes. + */ + offset *= bt_entry_size_bytes(mm); + return offset; +} + +/* + * How much virtual address space does a single bounds + * directory entry cover? + * + * Note, we need a long long because 4GB doesn't fit in + * to a long on 32-bit. + */ +static inline unsigned long bd_entry_virt_space(struct mm_struct *mm) +{ + unsigned long long virt_space; + unsigned long long GB = (1ULL << 30); + + /* + * This covers 32-bit emulation as well as 32-bit kernels + * running on 64-bit harware. + */ + if (!is_64bit_mm(mm)) + return (4ULL * GB) / MPX_BD_NR_ENTRIES_32; + + /* + * 'x86_virt_bits' returns what the hardware is capable + * of, and returns the full >32-bit adddress space when + * running 32-bit kernels on 64-bit hardware. + */ + virt_space = (1ULL << boot_cpu_data.x86_virt_bits); + return virt_space / MPX_BD_NR_ENTRIES_64; +} + /* * Free the backing physical pages of bounds table 'bt_addr'. * Assume start...end is within that bounds table. */ -static int zap_bt_entries(struct mm_struct *mm, +static noinline int zap_bt_entries_mapping(struct mm_struct *mm, unsigned long bt_addr, - unsigned long start, unsigned long end) + unsigned long start_mapping, unsigned long end_mapping) { struct vm_area_struct *vma; unsigned long addr, len; + unsigned long start; + unsigned long end; + + /* + * if we 'end' on a boundary, the offset will be 0 which + * is not what we want. Back it up a byte to get the + * last bt entry. Then once we have the entry itself, + * move 'end' back up by the table entry size. + */ + start = bt_addr + mpx_get_bt_entry_offset_bytes(mm, start_mapping); + end = bt_addr + mpx_get_bt_entry_offset_bytes(mm, end_mapping - 1); + /* + * Move end back up by one entry. Among other things + * this ensures that it remains page-aligned and does + * not screw up zap_page_range() + */ + end += bt_entry_size_bytes(mm); /* * Find the first overlapping vma. If vma->vm_start > start, there @@ -630,7 +780,7 @@ static int zap_bt_entries(struct mm_struct *mm, return -EINVAL; /* - * A NUMA policy on a VM_MPX VMA could cause this bouds table to + * A NUMA policy on a VM_MPX VMA could cause this bounds table to * be split. So we need to look across the entire 'start -> end' * range of this bounds table, find all of the VM_MPX VMAs, and * zap only those. @@ -648,27 +798,65 @@ static int zap_bt_entries(struct mm_struct *mm, len = min(vma->vm_end, end) - addr; zap_page_range(vma, addr, len, NULL); + trace_mpx_unmap_zap(addr, addr+len); vma = vma->vm_next; addr = vma->vm_start; } - return 0; } -static int unmap_single_bt(struct mm_struct *mm, +static unsigned long mpx_get_bd_entry_offset(struct mm_struct *mm, + unsigned long addr) +{ + /* + * There are several ways to derive the bd offsets. We + * use the following approach here: + * 1. We know the size of the virtual address space + * 2. We know the number of entries in a bounds table + * 3. We know that each entry covers a fixed amount of + * virtual address space. + * So, we can just divide the virtual address by the + * virtual space used by one entry to determine which + * entry "controls" the given virtual address. + */ + if (is_64bit_mm(mm)) { + int bd_entry_size = 8; /* 64-bit pointer */ + /* + * Take the 64-bit addressing hole in to account. + */ + addr &= ((1UL << boot_cpu_data.x86_virt_bits) - 1); + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } else { + int bd_entry_size = 4; /* 32-bit pointer */ + /* + * 32-bit has no hole so this case needs no mask + */ + return (addr / bd_entry_virt_space(mm)) * bd_entry_size; + } + /* + * The two return calls above are exact copies. If we + * pull out a single copy and put it in here, gcc won't + * realize that we're doing a power-of-2 divide and use + * shifts. It uses a real divide. If we put them up + * there, it manages to figure it out (gcc 4.8.3). + */ +} + +static int unmap_entire_bt(struct mm_struct *mm, long __user *bd_entry, unsigned long bt_addr) { unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG; - unsigned long actual_old_val = 0; + unsigned long uninitialized_var(actual_old_val); int ret; while (1) { int need_write = 1; + unsigned long cleared_bd_entry = 0; pagefault_disable(); - ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry, - expected_old_val, 0); + ret = mpx_cmpxchg_bd_entry(mm, &actual_old_val, + bd_entry, expected_old_val, cleared_bd_entry); pagefault_enable(); if (!ret) break; @@ -687,9 +875,8 @@ static int unmap_single_bt(struct mm_struct *mm, if (actual_old_val != expected_old_val) { /* * Someone else raced with us to unmap the table. - * There was no bounds table pointed to by the - * directory, so declare success. Somebody freed - * it. + * That is OK, since we were both trying to do + * the same thing. Declare success. */ if (!actual_old_val) return 0; @@ -702,176 +889,113 @@ static int unmap_single_bt(struct mm_struct *mm, */ return -EINVAL; } - /* * Note, we are likely being called under do_munmap() already. To * avoid recursion, do_munmap() will check whether it comes * from one bounds table through VM_MPX flag. */ - return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES); + return do_munmap(mm, bt_addr, mpx_bt_size_bytes(mm)); } -/* - * If the bounds table pointed by bounds directory 'bd_entry' is - * not shared, unmap this whole bounds table. Otherwise, only free - * those backing physical pages of bounds table entries covered - * in this virtual address region start...end. - */ -static int unmap_shared_bt(struct mm_struct *mm, - long __user *bd_entry, unsigned long start, - unsigned long end, bool prev_shared, bool next_shared) +static int try_unmap_single_bt(struct mm_struct *mm, + unsigned long start, unsigned long end) { - unsigned long bt_addr; - int ret; - - ret = get_bt_addr(mm, bd_entry, &bt_addr); + struct vm_area_struct *next; + struct vm_area_struct *prev; /* - * We could see an "error" ret for not-present bounds - * tables (not really an error), or actual errors, but - * stop unmapping either way. + * "bta" == Bounds Table Area: the area controlled by the + * bounds table that we are unmapping. */ - if (ret) - return ret; - - if (prev_shared && next_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else if (prev_shared) - ret = zap_bt_entries(mm, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(start), - bt_addr+MPX_BT_SIZE_BYTES); - else if (next_shared) - ret = zap_bt_entries(mm, bt_addr, bt_addr, - bt_addr+MPX_GET_BT_ENTRY_OFFSET(end)); - else - ret = unmap_single_bt(mm, bd_entry, bt_addr); - - return ret; -} - -/* - * A virtual address region being munmap()ed might share bounds table - * with adjacent VMAs. We only need to free the backing physical - * memory of these shared bounds tables entries covered in this virtual - * address region. - */ -static int unmap_edge_bts(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ + unsigned long bta_start_vaddr = start & ~(bd_entry_virt_space(mm)-1); + unsigned long bta_end_vaddr = bta_start_vaddr + bd_entry_virt_space(mm); + unsigned long uninitialized_var(bt_addr); + void __user *bde_vaddr; int ret; - long __user *bde_start, *bde_end; - struct vm_area_struct *prev, *next; - bool prev_shared = false, next_shared = false; - - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - /* - * Check whether bde_start and bde_end are shared with adjacent - * VMAs. - * - * We already unliked the VMAs from the mm's rbtree so 'start' + * We already unlinked the VMAs from the mm's rbtree so 'start' * is guaranteed to be in a hole. This gets us the first VMA * before the hole in to 'prev' and the next VMA after the hole * in to 'next'. */ next = find_vma_prev(mm, start, &prev); - if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1)) - == bde_start) - prev_shared = true; - if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start)) - == bde_end) - next_shared = true; - /* - * This virtual address region being munmap()ed is only - * covered by one bounds table. - * - * In this case, if this table is also shared with adjacent - * VMAs, only part of the backing physical memory of the bounds - * table need be freeed. Otherwise the whole bounds table need - * be unmapped. - */ - if (bde_start == bde_end) { - return unmap_shared_bt(mm, bde_start, start, end, - prev_shared, next_shared); + * Do not count other MPX bounds table VMAs as neighbors. + * Although theoretically possible, we do not allow bounds + * tables for bounds tables so our heads do not explode. + * If we count them as neighbors here, we may end up with + * lots of tables even though we have no actual table + * entries in use. + */ + while (next && (next->vm_flags & VM_MPX)) + next = next->vm_next; + while (prev && (prev->vm_flags & VM_MPX)) + prev = prev->vm_prev; + /* + * We know 'start' and 'end' lie within an area controlled + * by a single bounds table. See if there are any other + * VMAs controlled by that bounds table. If there are not + * then we can "expand" the are we are unmapping to possibly + * cover the entire table. + */ + next = find_vma_prev(mm, start, &prev); + if ((!prev || prev->vm_end <= bta_start_vaddr) && + (!next || next->vm_start >= bta_end_vaddr)) { + /* + * No neighbor VMAs controlled by same bounds + * table. Try to unmap the whole thing + */ + start = bta_start_vaddr; + end = bta_end_vaddr; } + bde_vaddr = mm->bd_addr + mpx_get_bd_entry_offset(mm, start); + ret = get_bt_addr(mm, bde_vaddr, &bt_addr); /* - * If more than one bounds tables are covered in this virtual - * address region being munmap()ed, we need to separately check - * whether bde_start and bde_end are shared with adjacent VMAs. + * No bounds table there, so nothing to unmap. */ - ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false); - if (ret) - return ret; - ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared); + if (ret == -ENOENT) { + ret = 0; + return 0; + } if (ret) return ret; - - return 0; + /* + * We are unmapping an entire table. Either because the + * unmap that started this whole process was large enough + * to cover an entire table, or that the unmap was small + * but was the area covered by a bounds table. + */ + if ((start == bta_start_vaddr) && + (end == bta_end_vaddr)) + return unmap_entire_bt(mm, bde_vaddr, bt_addr); + return zap_bt_entries_mapping(mm, bt_addr, start, end); } static int mpx_unmap_tables(struct mm_struct *mm, unsigned long start, unsigned long end) { - int ret; - long __user *bd_entry, *bde_start, *bde_end; - unsigned long bt_addr; - - /* - * "Edge" bounds tables are those which are being used by the region - * (start -> end), but that may be shared with adjacent areas. If they - * turn out to be completely unshared, they will be freed. If they are - * shared, we will free the backing store (like an MADV_DONTNEED) for - * areas used by this region. - */ - ret = unmap_edge_bts(mm, start, end); - switch (ret) { - /* non-present tables are OK */ - case 0: - case -ENOENT: - /* Success, or no tables to unmap */ - break; - case -EINVAL: - case -EFAULT: - default: - return ret; - } - - /* - * Only unmap the bounds table that are - * 1. fully covered - * 2. not at the edges of the mapping, even if full aligned - */ - bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start); - bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1); - for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) { - ret = get_bt_addr(mm, bd_entry, &bt_addr); - switch (ret) { - case 0: - break; - case -ENOENT: - /* No table here, try the next one */ - continue; - case -EINVAL: - case -EFAULT: - default: - /* - * Note: we are being strict here. - * Any time we run in to an issue - * unmapping tables, we stop and - * SIGSEGV. - */ - return ret; - } - - ret = unmap_single_bt(mm, bd_entry, bt_addr); + unsigned long one_unmap_start; + trace_mpx_unmap_search(start, end); + + one_unmap_start = start; + while (one_unmap_start < end) { + int ret; + unsigned long next_unmap_start = ALIGN(one_unmap_start+1, + bd_entry_virt_space(mm)); + unsigned long one_unmap_end = end; + /* + * if the end is beyond the current bounds table, + * move it back so we only deal with a single one + * at a time + */ + if (one_unmap_end > next_unmap_start) + one_unmap_end = next_unmap_start; + ret = try_unmap_single_bt(mm, one_unmap_start, one_unmap_end); if (ret) return ret; - } + one_unmap_start = next_unmap_start; + } return 0; } diff --git a/kernel/arch/x86/mm/numa.c b/kernel/arch/x86/mm/numa.c index 4053bb58b..c3b3f653e 100644 --- a/kernel/arch/x86/mm/numa.c +++ b/kernel/arch/x86/mm/numa.c @@ -246,8 +246,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) bi->start = max(bi->start, low); bi->end = min(bi->end, high); - /* and there's no empty block */ - if (bi->start >= bi->end) + /* and there's no empty or non-exist block */ + if (bi->start >= bi->end || + !memblock_overlaps_region(&memblock.memory, + bi->start, bi->end - bi->start)) numa_remove_memblk_from(i--, mi); } diff --git a/kernel/arch/x86/mm/pageattr-test.c b/kernel/arch/x86/mm/pageattr-test.c index 6629f397b..5f169d5d7 100644 --- a/kernel/arch/x86/mm/pageattr-test.c +++ b/kernel/arch/x86/mm/pageattr-test.c @@ -8,7 +8,9 @@ #include <linux/kthread.h> #include <linux/random.h> #include <linux/kernel.h> +#include <linux/init.h> #include <linux/mm.h> +#include <linux/vmalloc.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> @@ -255,5 +257,4 @@ static int start_pageattr_test(void) return 0; } - -module_init(start_pageattr_test); +device_initcall(start_pageattr_test); diff --git a/kernel/arch/x86/mm/pageattr.c b/kernel/arch/x86/mm/pageattr.c index 89af288ec..b599a780a 100644 --- a/kernel/arch/x86/mm/pageattr.c +++ b/kernel/arch/x86/mm/pageattr.c @@ -4,7 +4,6 @@ */ #include <linux/highmem.h> #include <linux/bootmem.h> -#include <linux/module.h> #include <linux/sched.h> #include <linux/mm.h> #include <linux/interrupt.h> @@ -14,6 +13,7 @@ #include <linux/percpu.h> #include <linux/gfp.h> #include <linux/pci.h> +#include <linux/vmalloc.h> #include <asm/e820.h> #include <asm/processor.h> @@ -33,7 +33,7 @@ struct cpa_data { pgd_t *pgd; pgprot_t mask_set; pgprot_t mask_clr; - int numpages; + unsigned long numpages; int flags; unsigned long pfn; unsigned force_split : 1; @@ -129,16 +129,15 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - void *vend = vaddr + size - 1; + unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + void *vend = vaddr + size; + void *p; mb(); - for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size) - clflushopt(vaddr); - /* - * Flush any possible final partial cacheline: - */ - clflushopt(vend); + for (p = (void *)((unsigned long)vaddr & ~clflush_mask); + p < vend; p += boot_cpu_data.x86_clflush_size) + clflushopt(p); mb(); } @@ -418,17 +417,31 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) phys_addr_t phys_addr; unsigned long offset; enum pg_level level; - unsigned long psize; - unsigned long pmask; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); - psize = page_level_size(level); - pmask = page_level_mask(level); - offset = virt_addr & ~pmask; - phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; - return (phys_addr | offset); + + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ + switch (level) { + case PG_LEVEL_1G: + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + offset = virt_addr & ~PUD_PAGE_MASK; + break; + case PG_LEVEL_2M: + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + offset = virt_addr & ~PMD_PAGE_MASK; + break; + default: + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; + offset = virt_addr & ~PAGE_MASK; + } + + return (phys_addr_t)(phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); @@ -461,7 +474,7 @@ static int try_preserve_large_page(pte_t *kpte, unsigned long address, struct cpa_data *cpa) { - unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn; + unsigned long nextpage_addr, numpages, pmask, psize, addr, pfn, old_pfn; pte_t new_pte, old_pte, *tmp; pgprot_t old_prot, new_prot, req_prot; int i, do_split = 1; @@ -481,17 +494,21 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, switch (level) { case PG_LEVEL_2M: -#ifdef CONFIG_X86_64 + old_prot = pmd_pgprot(*(pmd_t *)kpte); + old_pfn = pmd_pfn(*(pmd_t *)kpte); + break; case PG_LEVEL_1G: -#endif - psize = page_level_size(level); - pmask = page_level_mask(level); + old_prot = pud_pgprot(*(pud_t *)kpte); + old_pfn = pud_pfn(*(pud_t *)kpte); break; default: do_split = -EINVAL; goto out_unlock; } + psize = page_level_size(level); + pmask = page_level_mask(level); + /* * Calculate the number of pages, which fit into this large * page starting at address: @@ -507,7 +524,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * up accordingly. */ old_pte = *kpte; - old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte)); + req_prot = pgprot_large_2_4k(old_prot); pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr); pgprot_val(req_prot) |= pgprot_val(cpa->mask_set); @@ -533,10 +550,10 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, req_prot = canon_pgprot(req_prot); /* - * old_pte points to the large page base address. So we need + * old_pfn points to the large page base pfn. So we need * to add the offset of the virtual address: */ - pfn = pte_pfn(old_pte) + ((address & (psize - 1)) >> PAGE_SHIFT); + pfn = old_pfn + ((address & (psize - 1)) >> PAGE_SHIFT); cpa->pfn = pfn; new_prot = static_protections(req_prot, address, pfn); @@ -547,7 +564,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * the pages in the range we try to preserve: */ addr = address & pmask; - pfn = pte_pfn(old_pte); + pfn = old_pfn; for (i = 0; i < (psize >> PAGE_SHIFT); i++, addr += PAGE_SIZE, pfn++) { pgprot_t chk_prot = static_protections(req_prot, addr, pfn); @@ -577,7 +594,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address, * The address is aligned and the number of pages * covers the full page. */ - new_pte = pfn_pte(pte_pfn(old_pte), new_prot); + new_pte = pfn_pte(old_pfn, new_prot); __set_pmd_pte(kpte, address, new_pte); cpa->flags |= CPA_FLUSHTLB; do_split = 0; @@ -594,7 +611,7 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, struct page *base) { pte_t *pbase = (pte_t *)page_address(base); - unsigned long pfn, pfninc = 1; + unsigned long ref_pfn, pfn, pfninc = 1; unsigned int i, level; pte_t *tmp; pgprot_t ref_prot; @@ -611,26 +628,33 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, } paravirt_alloc_pte(&init_mm, page_to_pfn(base)); - ref_prot = pte_pgprot(pte_clrhuge(*kpte)); - /* promote PAT bit to correct position */ - if (level == PG_LEVEL_2M) + switch (level) { + case PG_LEVEL_2M: + ref_prot = pmd_pgprot(*(pmd_t *)kpte); + /* clear PSE and promote PAT bit to correct position */ ref_prot = pgprot_large_2_4k(ref_prot); + ref_pfn = pmd_pfn(*(pmd_t *)kpte); + break; -#ifdef CONFIG_X86_64 - if (level == PG_LEVEL_1G) { + case PG_LEVEL_1G: + ref_prot = pud_pgprot(*(pud_t *)kpte); + ref_pfn = pud_pfn(*(pud_t *)kpte); pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT; + /* - * Set the PSE flags only if the PRESENT flag is set + * Clear the PSE flags if the PRESENT flag is not set * otherwise pmd_present/pmd_huge will return true * even on a non present pmd. */ - if (pgprot_val(ref_prot) & _PAGE_PRESENT) - pgprot_val(ref_prot) |= _PAGE_PSE; - else + if (!(pgprot_val(ref_prot) & _PAGE_PRESENT)) pgprot_val(ref_prot) &= ~_PAGE_PSE; + break; + + default: + spin_unlock(&pgd_lock); + return 1; } -#endif /* * Set the GLOBAL flags only if the PRESENT flag is set @@ -646,13 +670,16 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address, /* * Get the target pfn from the original entry: */ - pfn = pte_pfn(*kpte); + pfn = ref_pfn; for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc) set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot))); - if (pfn_range_is_mapped(PFN_DOWN(__pa(address)), - PFN_DOWN(__pa(address)) + 1)) - split_page_count(level); + if (virt_addr_valid(address)) { + unsigned long pfn = PFN_DOWN(__pa(address)); + + if (pfn_range_is_mapped(pfn, pfn + 1)) + split_page_count(level); + } /* * Install the new, split up pagetable. @@ -1324,7 +1351,7 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) * CPA operation. Either a large page has been * preserved or a single page update happened. */ - BUG_ON(cpa->numpages > numpages); + BUG_ON(cpa->numpages > numpages || !cpa->numpages); numpages -= cpa->numpages; if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) cpa->curpage++; @@ -1468,6 +1495,9 @@ int _set_memory_uc(unsigned long addr, int numpages) { /* * for now UC MINUS. see comments in ioremap_nocache() + * If you really need strong UC use ioremap_uc(), but note + * that you cannot override IO areas with set_memory_*() as + * these helpers cannot work with IO memory. */ return change_page_attr_set(&addr, numpages, cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), @@ -1502,12 +1532,10 @@ EXPORT_SYMBOL(set_memory_uc); static int _set_memory_array(unsigned long *addr, int addrinarray, enum page_cache_mode new_type) { + enum page_cache_mode set_type; int i, j; int ret; - /* - * for now UC MINUS. see comments in ioremap_nocache() - */ for (i = 0; i < addrinarray; i++) { ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, new_type, NULL); @@ -1515,9 +1543,12 @@ static int _set_memory_array(unsigned long *addr, int addrinarray, goto out_free; } + /* If WC, set to UC- first and then WC */ + set_type = (new_type == _PAGE_CACHE_MODE_WC) ? + _PAGE_CACHE_MODE_UC_MINUS : new_type; + ret = change_page_attr_set(addr, addrinarray, - cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS), - 1); + cachemode2pgprot(set_type), 1); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(addr, addrinarray, @@ -1549,6 +1580,12 @@ int set_memory_array_wc(unsigned long *addr, int addrinarray) } EXPORT_SYMBOL(set_memory_array_wc); +int set_memory_array_wt(unsigned long *addr, int addrinarray) +{ + return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WT); +} +EXPORT_SYMBOL_GPL(set_memory_array_wt); + int _set_memory_wc(unsigned long addr, int numpages) { int ret; @@ -1571,27 +1608,42 @@ int set_memory_wc(unsigned long addr, int numpages) { int ret; - if (!pat_enabled) - return set_memory_uc(addr, numpages); - ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_MODE_WC, NULL); if (ret) - goto out_err; + return ret; ret = _set_memory_wc(addr, numpages); if (ret) - goto out_free; + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); - return 0; - -out_free: - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); -out_err: return ret; } EXPORT_SYMBOL(set_memory_wc); +int _set_memory_wt(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, + cachemode2pgprot(_PAGE_CACHE_MODE_WT), 0); +} + +int set_memory_wt(unsigned long addr, int numpages) +{ + int ret; + + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_MODE_WT, NULL); + if (ret) + return ret; + + ret = _set_memory_wt(addr, numpages); + if (ret) + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + + return ret; +} +EXPORT_SYMBOL_GPL(set_memory_wt); + int _set_memory_wb(unsigned long addr, int numpages) { /* WB cache mode is hard wired to all cache attribute bits being 0 */ @@ -1682,6 +1734,7 @@ static int _set_pages_array(struct page **pages, int addrinarray, { unsigned long start; unsigned long end; + enum page_cache_mode set_type; int i; int free_idx; int ret; @@ -1695,8 +1748,12 @@ static int _set_pages_array(struct page **pages, int addrinarray, goto err_out; } + /* If WC, set to UC- first and then WC */ + set_type = (new_type == _PAGE_CACHE_MODE_WC) ? + _PAGE_CACHE_MODE_UC_MINUS : new_type; + ret = cpa_set_pages_array(pages, addrinarray, - cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS)); + cachemode2pgprot(set_type)); if (!ret && new_type == _PAGE_CACHE_MODE_WC) ret = change_page_attr_set_clr(NULL, addrinarray, cachemode2pgprot( @@ -1730,6 +1787,12 @@ int set_pages_array_wc(struct page **pages, int addrinarray) } EXPORT_SYMBOL(set_pages_array_wc); +int set_pages_array_wt(struct page **pages, int addrinarray) +{ + return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WT); +} +EXPORT_SYMBOL_GPL(set_pages_array_wt); + int set_pages_wb(struct page *page, int numpages) { unsigned long addr = (unsigned long)page_address(page); diff --git a/kernel/arch/x86/mm/pat.c b/kernel/arch/x86/mm/pat.c index 35af6771a..188e3e07e 100644 --- a/kernel/arch/x86/mm/pat.c +++ b/kernel/arch/x86/mm/pat.c @@ -33,13 +33,17 @@ #include "pat_internal.h" #include "mm_internal.h" -#ifdef CONFIG_X86_PAT -int __read_mostly pat_enabled = 1; +#undef pr_fmt +#define pr_fmt(fmt) "" fmt + +static bool boot_cpu_done; + +static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); static inline void pat_disable(const char *reason) { - pat_enabled = 0; - printk(KERN_INFO "%s\n", reason); + __pat_enabled = 0; + pr_info("x86/PAT: %s\n", reason); } static int __init nopat(char *str) @@ -48,13 +52,12 @@ static int __init nopat(char *str) return 0; } early_param("nopat", nopat); -#else -static inline void pat_disable(const char *reason) + +bool pat_enabled(void) { - (void)reason; + return !!__pat_enabled; } -#endif - +EXPORT_SYMBOL_GPL(pat_enabled); int pat_debug_enable; @@ -65,22 +68,24 @@ static int __init pat_debug_setup(char *str) } __setup("debugpat", pat_debug_setup); -static u64 __read_mostly boot_pat_state; - #ifdef CONFIG_X86_PAT /* - * X86 PAT uses page flags WC and Uncached together to keep track of - * memory type of pages that have backing page struct. X86 PAT supports 3 - * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and - * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not - * been changed from its default (value of -1 used to denote this). - * Note we do not support _PAGE_CACHE_MODE_UC here. + * X86 PAT uses page flags arch_1 and uncached together to keep track of + * memory type of pages that have backing page struct. + * + * X86 PAT supports 4 different memory types: + * - _PAGE_CACHE_MODE_WB + * - _PAGE_CACHE_MODE_WC + * - _PAGE_CACHE_MODE_UC_MINUS + * - _PAGE_CACHE_MODE_WT + * + * _PAGE_CACHE_MODE_WB is the default type. */ -#define _PGMT_DEFAULT 0 +#define _PGMT_WB 0 #define _PGMT_WC (1UL << PG_arch_1) #define _PGMT_UC_MINUS (1UL << PG_uncached) -#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1) +#define _PGMT_WT (1UL << PG_uncached | 1UL << PG_arch_1) #define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1) #define _PGMT_CLEAR_MASK (~_PGMT_MASK) @@ -88,14 +93,14 @@ static inline enum page_cache_mode get_page_memtype(struct page *pg) { unsigned long pg_flags = pg->flags & _PGMT_MASK; - if (pg_flags == _PGMT_DEFAULT) - return -1; + if (pg_flags == _PGMT_WB) + return _PAGE_CACHE_MODE_WB; else if (pg_flags == _PGMT_WC) return _PAGE_CACHE_MODE_WC; else if (pg_flags == _PGMT_UC_MINUS) return _PAGE_CACHE_MODE_UC_MINUS; else - return _PAGE_CACHE_MODE_WB; + return _PAGE_CACHE_MODE_WT; } static inline void set_page_memtype(struct page *pg, @@ -112,11 +117,12 @@ static inline void set_page_memtype(struct page *pg, case _PAGE_CACHE_MODE_UC_MINUS: memtype_flags = _PGMT_UC_MINUS; break; - case _PAGE_CACHE_MODE_WB: - memtype_flags = _PGMT_WB; + case _PAGE_CACHE_MODE_WT: + memtype_flags = _PGMT_WT; break; + case _PAGE_CACHE_MODE_WB: default: - memtype_flags = _PGMT_DEFAULT; + memtype_flags = _PGMT_WB; break; } @@ -174,78 +180,154 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -void pat_init_cache_modes(void) +void pat_init_cache_modes(u64 pat) { - int i; enum page_cache_mode cache; char pat_msg[33]; - u64 pat; + int i; - rdmsrl(MSR_IA32_CR_PAT, pat); pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, pat_msg + 4 * i); update_cache_mode_entry(i, cache); } - pr_info("PAT configuration [0-7]: %s\n", pat_msg); + pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) -void pat_init(void) +static void pat_bsp_init(u64 pat) { - u64 pat; - bool boot_cpu = !boot_pat_state; + u64 tmp_pat; - if (!pat_enabled) + if (!cpu_has_pat) { + pat_disable("PAT not supported by CPU."); return; + } - if (!cpu_has_pat) { - if (!boot_pat_state) { - pat_disable("PAT not supported by CPU."); - return; - } else { - /* - * If this happens we are on a secondary CPU, but - * switched to PAT on the boot CPU. We have no way to - * undo PAT. - */ - printk(KERN_ERR "PAT enabled, " - "but not supported by secondary CPU\n"); - BUG(); - } + if (!pat_enabled()) + goto done; + + rdmsrl(MSR_IA32_CR_PAT, tmp_pat); + if (!tmp_pat) { + pat_disable("PAT MSR is 0, disabled."); + return; } - /* Set PWT to Write-Combining. All other bits stay the same */ - /* - * PTE encoding used in Linux: - * PAT - * |PCD - * ||PWT - * ||| - * 000 WB _PAGE_CACHE_WB - * 001 WC _PAGE_CACHE_WC - * 010 UC- _PAGE_CACHE_UC_MINUS - * 011 UC _PAGE_CACHE_UC - * PAT bit unused - */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); - - /* Boot CPU check */ - if (!boot_pat_state) { - rdmsrl(MSR_IA32_CR_PAT, boot_pat_state); - if (!boot_pat_state) { - pat_disable("PAT read returns always zero, disabled."); - return; - } + wrmsrl(MSR_IA32_CR_PAT, pat); + +done: + pat_init_cache_modes(pat); +} + +static void pat_ap_init(u64 pat) +{ + if (!pat_enabled()) + return; + + if (!cpu_has_pat) { + /* + * If this happens we are on a secondary CPU, but switched to + * PAT on the boot CPU. We have no way to undo PAT. + */ + panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n"); } wrmsrl(MSR_IA32_CR_PAT, pat); +} + +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + /* + * No PAT. Emulate the PAT table that corresponds to the two + * cache bits, PWT (Write Through) and PCD (Cache Disable). This + * setup is the same as the BIOS default setup when the system + * has PAT but the "nopat" boot option has been specified. This + * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * + * PTE encoding: + * + * PCD + * |PWT PAT + * || slot + * 00 0 WB : _PAGE_CACHE_MODE_WB + * 01 1 WT : _PAGE_CACHE_MODE_WT + * 10 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 11 3 UC : _PAGE_CACHE_MODE_UC + * + * NOTE: When WC or WP is used, it is redirected to UC- per + * the default setup in __cachemode2pte_tbl[]. + */ + pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); - if (boot_cpu) - pat_init_cache_modes(); + } else if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + /* + * PAT support with the lower four entries. Intel Pentium 2, + * 3, M, and 4 are affected by PAT errata, which makes the + * upper four entries unusable. To be on the safe side, we don't + * use those. + * + * PTE encoding: + * PAT + * |PCD + * ||PWT PAT + * ||| slot + * 000 0 WB : _PAGE_CACHE_MODE_WB + * 001 1 WC : _PAGE_CACHE_MODE_WC + * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 011 3 UC : _PAGE_CACHE_MODE_UC + * PAT bit unused + * + * NOTE: When WT or WP is used, it is redirected to UC- per + * the default setup in __cachemode2pte_tbl[]. + */ + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); + } else { + /* + * Full PAT support. We put WT in slot 7 to improve + * robustness in the presence of errata that might cause + * the high PAT bit to be ignored. This way, a buggy slot 7 + * access will hit slot 3, and slot 3 is UC, so at worst + * we lose performance without causing a correctness issue. + * Pentium 4 erratum N46 is an example for such an erratum, + * although we try not to use PAT at all on affected CPUs. + * + * PTE encoding: + * PAT + * |PCD + * ||PWT PAT + * ||| slot + * 000 0 WB : _PAGE_CACHE_MODE_WB + * 001 1 WC : _PAGE_CACHE_MODE_WC + * 010 2 UC-: _PAGE_CACHE_MODE_UC_MINUS + * 011 3 UC : _PAGE_CACHE_MODE_UC + * 100 4 WB : Reserved + * 101 5 WC : Reserved + * 110 6 UC-: Reserved + * 111 7 WT : _PAGE_CACHE_MODE_WT + * + * The reserved slots are unused, but mapped to their + * corresponding types in the presence of PAT errata. + */ + pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | + PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, WT); + } + + if (!boot_cpu_done) { + pat_bsp_init(pat); + boot_cpu_done = true; + } else { + pat_ap_init(pat); + } } #undef PAT @@ -267,9 +349,9 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, * request is for WB. */ if (req_type == _PAGE_CACHE_MODE_WB) { - u8 mtrr_type; + u8 mtrr_type, uniform; - mtrr_type = mtrr_type_lookup(start, end); + mtrr_type = mtrr_type_lookup(start, end, &uniform); if (mtrr_type != MTRR_TYPE_WRBACK) return _PAGE_CACHE_MODE_UC_MINUS; @@ -324,9 +406,14 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end) /* * For RAM pages, we use page flags to mark the pages with appropriate type. - * Here we do two pass: - * - Find the memtype of all the pages in the range, look for any conflicts - * - In case of no conflicts, set the new memtype for pages in the range + * The page flags are limited to four types, WB (default), WC, WT and UC-. + * WP request fails with -EINVAL, and UC gets redirected to UC-. Setting + * a new memory type is only allowed for a page mapped with the default WB + * type. + * + * Here we do two passes: + * - Find the memtype of all the pages in the range, look for any conflicts. + * - In case of no conflicts, set the new memtype for pages in the range. */ static int reserve_ram_pages_type(u64 start, u64 end, enum page_cache_mode req_type, @@ -335,6 +422,12 @@ static int reserve_ram_pages_type(u64 start, u64 end, struct page *page; u64 pfn; + if (req_type == _PAGE_CACHE_MODE_WP) { + if (new_type) + *new_type = _PAGE_CACHE_MODE_UC_MINUS; + return -EINVAL; + } + if (req_type == _PAGE_CACHE_MODE_UC) { /* We do not support strong UC */ WARN_ON_ONCE(1); @@ -346,8 +439,8 @@ static int reserve_ram_pages_type(u64 start, u64 end, page = pfn_to_page(pfn); type = get_page_memtype(page); - if (type != -1) { - pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", + if (type != _PAGE_CACHE_MODE_WB) { + pr_info("x86/PAT: reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n", start, end - 1, type, req_type); if (new_type) *new_type = type; @@ -373,7 +466,7 @@ static int free_ram_pages_type(u64 start, u64 end) for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) { page = pfn_to_page(pfn); - set_page_memtype(page, -1); + set_page_memtype(page, _PAGE_CACHE_MODE_WB); } return 0; } @@ -384,6 +477,7 @@ static int free_ram_pages_type(u64 start, u64 end) * - _PAGE_CACHE_MODE_WC * - _PAGE_CACHE_MODE_UC_MINUS * - _PAGE_CACHE_MODE_UC + * - _PAGE_CACHE_MODE_WT * * If new_type is NULL, function will return an error if it cannot reserve the * region with req_type. If new_type is non-NULL, function will return @@ -400,14 +494,10 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, BUG_ON(start >= end); /* end is exclusive */ - if (!pat_enabled) { + if (!pat_enabled()) { /* This is identical to page table setting without PAT */ - if (new_type) { - if (req_type == _PAGE_CACHE_MODE_WC) - *new_type = _PAGE_CACHE_MODE_UC_MINUS; - else - *new_type = req_type; - } + if (new_type) + *new_type = req_type; return 0; } @@ -451,9 +541,9 @@ int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type, err = rbt_memtype_check_insert(new, new_type); if (err) { - printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", - start, end - 1, - cattr_name(new->type), cattr_name(req_type)); + pr_info("x86/PAT: reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n", + start, end - 1, + cattr_name(new->type), cattr_name(req_type)); kfree(new); spin_unlock(&memtype_lock); @@ -475,7 +565,7 @@ int free_memtype(u64 start, u64 end) int is_range_ram; struct memtype *entry; - if (!pat_enabled) + if (!pat_enabled()) return 0; /* Low ISA region is always mapped WB. No need to track */ @@ -497,8 +587,8 @@ int free_memtype(u64 start, u64 end) spin_unlock(&memtype_lock); if (!entry) { - printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", - current->comm, current->pid, start, end - 1); + pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", + current->comm, current->pid, start, end - 1); return -EINVAL; } @@ -517,7 +607,7 @@ int free_memtype(u64 start, u64 end) * Only to be called when PAT is enabled * * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS - * or _PAGE_CACHE_MODE_UC + * or _PAGE_CACHE_MODE_WT. */ static enum page_cache_mode lookup_memtype(u64 paddr) { @@ -529,16 +619,9 @@ static enum page_cache_mode lookup_memtype(u64 paddr) if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) { struct page *page; - page = pfn_to_page(paddr >> PAGE_SHIFT); - rettype = get_page_memtype(page); - /* - * -1 from get_page_memtype() implies RAM page is in its - * default state and not reserved, and hence of type WB - */ - if (rettype == -1) - rettype = _PAGE_CACHE_MODE_WB; - return rettype; + page = pfn_to_page(paddr >> PAGE_SHIFT); + return get_page_memtype(page); } spin_lock(&memtype_lock); @@ -623,13 +706,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) u64 to = from + size; u64 cursor = from; - if (!pat_enabled) + if (!pat_enabled()) return 1; while (cursor < to) { if (!devmem_is_allowed(pfn)) { - printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", - current->comm, from, to - 1); + pr_info("x86/PAT: Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", + current->comm, from, to - 1); return 0; } cursor += PAGE_SIZE; @@ -659,7 +742,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, * caching for the high addresses through the KEN pin, but * we maintain the tradition of paranoia in this code. */ - if (!pat_enabled && + if (!pat_enabled() && !(boot_cpu_has(X86_FEATURE_MTRR) || boot_cpu_has(X86_FEATURE_K6_MTRR) || boot_cpu_has(X86_FEATURE_CYRIX_ARR) || @@ -698,8 +781,7 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, size; if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) { - printk(KERN_INFO "%s:%d ioremap_change_attr failed %s " - "for [mem %#010Lx-%#010Lx]\n", + pr_info("x86/PAT: %s:%d ioremap_change_attr failed %s for [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, cattr_name(pcm), base, (unsigned long long)(base + size-1)); @@ -729,12 +811,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, * the type requested matches the type of first page in the range. */ if (is_ram) { - if (!pat_enabled) + if (!pat_enabled()) return 0; pcm = lookup_memtype(paddr); if (want_pcm != pcm) { - printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", + pr_warn("x86/PAT: %s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n", current->comm, current->pid, cattr_name(want_pcm), (unsigned long long)paddr, @@ -755,13 +837,12 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, if (strict_prot || !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) { free_memtype(paddr, paddr + size); - printk(KERN_ERR "%s:%d map pfn expected mapping type %s" - " for [mem %#010Lx-%#010Lx], got %s\n", - current->comm, current->pid, - cattr_name(want_pcm), - (unsigned long long)paddr, - (unsigned long long)(paddr + size - 1), - cattr_name(pcm)); + pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n", + current->comm, current->pid, + cattr_name(want_pcm), + (unsigned long long)paddr, + (unsigned long long)(paddr + size - 1), + cattr_name(pcm)); return -EINVAL; } /* @@ -844,7 +925,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot, return ret; } - if (!pat_enabled) + if (!pat_enabled()) return 0; /* @@ -872,7 +953,7 @@ int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, { enum page_cache_mode pcm; - if (!pat_enabled) + if (!pat_enabled()) return 0; /* Set prot based on lookup */ @@ -913,14 +994,18 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, pgprot_t pgprot_writecombine(pgprot_t prot) { - if (pat_enabled) - return __pgprot(pgprot_val(prot) | + return __pgprot(pgprot_val(prot) | cachemode2protval(_PAGE_CACHE_MODE_WC)); - else - return pgprot_noncached(prot); } EXPORT_SYMBOL_GPL(pgprot_writecombine); +pgprot_t pgprot_writethrough(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) | + cachemode2protval(_PAGE_CACHE_MODE_WT)); +} +EXPORT_SYMBOL_GPL(pgprot_writethrough); + #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT) static struct memtype *memtype_get_idx(loff_t pos) @@ -996,7 +1081,7 @@ static const struct file_operations memtype_fops = { static int __init pat_memtype_list_init(void) { - if (pat_enabled) { + if (pat_enabled()) { debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir, NULL, &memtype_fops); } diff --git a/kernel/arch/x86/mm/pat_internal.h b/kernel/arch/x86/mm/pat_internal.h index f64116203..a739bfc40 100644 --- a/kernel/arch/x86/mm/pat_internal.h +++ b/kernel/arch/x86/mm/pat_internal.h @@ -4,7 +4,7 @@ extern int pat_debug_enable; #define dprintk(fmt, arg...) \ - do { if (pat_debug_enable) printk(KERN_INFO fmt, ##arg); } while (0) + do { if (pat_debug_enable) pr_info("x86/PAT: " fmt, ##arg); } while (0) struct memtype { u64 start; diff --git a/kernel/arch/x86/mm/pat_rbtree.c b/kernel/arch/x86/mm/pat_rbtree.c index 6582adcc8..639310803 100644 --- a/kernel/arch/x86/mm/pat_rbtree.c +++ b/kernel/arch/x86/mm/pat_rbtree.c @@ -160,9 +160,9 @@ success: return 0; failure: - printk(KERN_INFO "%s:%d conflicting memory types " - "%Lx-%Lx %s<->%s\n", current->comm, current->pid, start, - end, cattr_name(found_type), cattr_name(match->type)); + pr_info("x86/PAT: %s:%d conflicting memory types %Lx-%Lx %s<->%s\n", + current->comm, current->pid, start, end, + cattr_name(found_type), cattr_name(match->type)); return -EBUSY; } diff --git a/kernel/arch/x86/mm/pgtable.c b/kernel/arch/x86/mm/pgtable.c index 0b97d2c75..fb0a9dd1d 100644 --- a/kernel/arch/x86/mm/pgtable.c +++ b/kernel/arch/x86/mm/pgtable.c @@ -563,16 +563,31 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, } #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +/** + * pud_set_huge - setup kernel PUD mapping + * + * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this + * function sets up a huge page only if any of the following conditions are met: + * + * - MTRRs are disabled, or + * + * - MTRRs are enabled and the range is completely covered by a single MTRR, or + * + * - MTRRs are enabled and the corresponding MTRR memory type is WB, which + * has no effect on the requested PAT memory type. + * + * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger + * page mapping attempt fails. + * + * Returns 1 on success and 0 on failure. + */ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) { - u8 mtrr; + u8 mtrr, uniform; - /* - * Do not use a huge page when the range is covered by non-WB type - * of MTRRs. - */ - mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE); - if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform); + if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) && + (mtrr != MTRR_TYPE_WRBACK)) return 0; prot = pgprot_4k_2_large(prot); @@ -584,17 +599,24 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pmd_set_huge - setup kernel PMD mapping + * + * See text over pud_set_huge() above. + * + * Returns 1 on success and 0 on failure. + */ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) { - u8 mtrr; + u8 mtrr, uniform; - /* - * Do not use a huge page when the range is covered by non-WB type - * of MTRRs. - */ - mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE); - if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform); + if ((mtrr != MTRR_TYPE_INVALID) && (!uniform) && + (mtrr != MTRR_TYPE_WRBACK)) { + pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n", + __func__, addr, addr + PMD_SIZE); return 0; + } prot = pgprot_4k_2_large(prot); @@ -605,6 +627,11 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) return 1; } +/** + * pud_clear_huge - clear kernel PUD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PUD map is found). + */ int pud_clear_huge(pud_t *pud) { if (pud_large(*pud)) { @@ -615,6 +642,11 @@ int pud_clear_huge(pud_t *pud) return 0; } +/** + * pmd_clear_huge - clear kernel PMD mapping when it is set + * + * Returns 1 on success and 0 on failure (no PMD map is found). + */ int pmd_clear_huge(pmd_t *pmd) { if (pmd_large(*pmd)) { diff --git a/kernel/arch/x86/mm/srat.c b/kernel/arch/x86/mm/srat.c index 66338a60a..c2aea63be 100644 --- a/kernel/arch/x86/mm/srat.c +++ b/kernel/arch/x86/mm/srat.c @@ -192,10 +192,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n", + pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n", node, pxm, (unsigned long long) start, (unsigned long long) end - 1, - hotpluggable ? " hotplug" : ""); + hotpluggable ? " hotplug" : "", + ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : ""); /* Mark hotplug range in memblock. */ if (hotpluggable && memblock_mark_hotplug(start, ma->length)) diff --git a/kernel/arch/x86/mm/tlb.c b/kernel/arch/x86/mm/tlb.c index 90b924acd..8f4cc3dfa 100644 --- a/kernel/arch/x86/mm/tlb.c +++ b/kernel/arch/x86/mm/tlb.c @@ -140,6 +140,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask, info.flush_end = end; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); + trace_tlb_flush(TLB_REMOTE_SEND_IPI, end - start); if (is_uv_system()) { unsigned int cpu; @@ -160,7 +161,10 @@ void flush_tlb_current_task(void) preempt_disable(); count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + + /* This is an implicit full barrier that synchronizes with switch_mm. */ local_flush_tlb(); + trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL); @@ -187,17 +191,29 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long base_pages_to_flush = TLB_FLUSH_ALL; preempt_disable(); - if (current->active_mm != mm) + if (current->active_mm != mm) { + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; + } if (!current->mm) { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + goto out; } if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) base_pages_to_flush = (end - start) >> PAGE_SHIFT; + /* + * Both branches below are implicit full barriers (MOV to CR or + * INVLPG) that synchronize with switch_mm. + */ if (base_pages_to_flush > tlb_single_page_flush_ceiling) { base_pages_to_flush = TLB_FLUSH_ALL; count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); @@ -227,10 +243,18 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) preempt_disable(); if (current->active_mm == mm) { - if (current->mm) + if (current->mm) { + /* + * Implicit full barrier (INVLPG) that synchronizes + * with switch_mm. + */ __flush_tlb_one(start); - else + } else { leave_mm(smp_processor_id()); + + /* Synchronize with switch_mm. */ + smp_mb(); + } } if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) diff --git a/kernel/arch/x86/net/bpf_jit.S b/kernel/arch/x86/net/bpf_jit.S index 6440221ce..4093216b3 100644 --- a/kernel/arch/x86/net/bpf_jit.S +++ b/kernel/arch/x86/net/bpf_jit.S @@ -8,7 +8,6 @@ * of the License. */ #include <linux/linkage.h> -#include <asm/dwarf2.h> /* * Calling convention : diff --git a/kernel/arch/x86/net/bpf_jit_comp.c b/kernel/arch/x86/net/bpf_jit_comp.c index ddeff4844..75991979f 100644 --- a/kernel/arch/x86/net/bpf_jit_comp.c +++ b/kernel/arch/x86/net/bpf_jit_comp.c @@ -12,6 +12,7 @@ #include <linux/filter.h> #include <linux/if_vlan.h> #include <asm/cacheflush.h> +#include <linux/bpf.h> int bpf_jit_enable __read_mostly; @@ -37,7 +38,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) return ptr + len; } -#define EMIT(bytes, len) do { prog = emit_code(prog, bytes, len); } while (0) +#define EMIT(bytes, len) \ + do { prog = emit_code(prog, bytes, len); cnt += len; } while (0) #define EMIT1(b1) EMIT(b1, 1) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) @@ -186,31 +188,31 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, - int oldproglen, struct jit_context *ctx) +#define STACKSIZE \ + (MAX_BPF_STACK + \ + 32 /* space for rbx, r13, r14, r15 */ + \ + 8 /* space for skb_copy_bits() buffer */) + +#define PROLOGUE_SIZE 51 + +/* emit x64 prologue code for BPF program and check it's size. + * bpf_tail_call helper will skip it while jumping into another program + */ +static void emit_prologue(u8 **pprog) { - struct bpf_insn *insn = bpf_prog->insnsi; - int insn_cnt = bpf_prog->len; - bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0); - bool seen_exit = false; - u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; - int i; - int proglen = 0; - u8 *prog = temp; - int stacksize = MAX_BPF_STACK + - 32 /* space for rbx, r13, r14, r15 */ + - 8 /* space for skb_copy_bits() buffer */; + u8 *prog = *pprog; + int cnt = 0; EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ - /* sub rsp, stacksize */ - EMIT3_off32(0x48, 0x81, 0xEC, stacksize); + /* sub rsp, STACKSIZE */ + EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE); /* all classic BPF filters use R6(rbx) save it */ /* mov qword ptr [rbp-X],rbx */ - EMIT3_off32(0x48, 0x89, 0x9D, -stacksize); + EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE); /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and @@ -221,46 +223,134 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, */ /* mov qword ptr [rbp-X],r13 */ - EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8); + EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8); /* mov qword ptr [rbp-X],r14 */ - EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16); + EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16); /* mov qword ptr [rbp-X],r15 */ - EMIT3_off32(0x4C, 0x89, 0xBD, -stacksize + 24); + EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); /* clear A and X registers */ EMIT2(0x31, 0xc0); /* xor eax, eax */ EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */ - if (seen_ld_abs) { - /* r9d : skb->len - skb->data_len (headlen) - * r10 : skb->data - */ - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov %r9d, off8(%rdi) */ - EMIT4(0x44, 0x8b, 0x4f, - offsetof(struct sk_buff, len)); - else - /* mov %r9d, off32(%rdi) */ - EMIT3_off32(0x44, 0x8b, 0x8f, - offsetof(struct sk_buff, len)); - - if (is_imm8(offsetof(struct sk_buff, data_len))) - /* sub %r9d, off8(%rdi) */ - EMIT4(0x44, 0x2b, 0x4f, - offsetof(struct sk_buff, data_len)); - else - EMIT3_off32(0x44, 0x2b, 0x8f, - offsetof(struct sk_buff, data_len)); - - if (is_imm8(offsetof(struct sk_buff, data))) - /* mov %r10, off8(%rdi) */ - EMIT4(0x4c, 0x8b, 0x57, - offsetof(struct sk_buff, data)); - else - /* mov %r10, off32(%rdi) */ - EMIT3_off32(0x4c, 0x8b, 0x97, - offsetof(struct sk_buff, data)); - } + /* clear tail_cnt: mov qword ptr [rbp-X], rax */ + EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); + + BUILD_BUG_ON(cnt != PROLOGUE_SIZE); + *pprog = prog; +} + +/* generate the following code: + * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... + * if (index >= array->map.max_entries) + * goto out; + * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + * prog = array->ptrs[index]; + * if (prog == NULL) + * goto out; + * goto *(prog->bpf_func + prologue_size); + * out: + */ +static void emit_bpf_tail_call(u8 **pprog) +{ + u8 *prog = *pprog; + int label1, label2, label3; + int cnt = 0; + + /* rdi - pointer to ctx + * rsi - pointer to bpf_array + * rdx - index in bpf_array + */ + + /* if (index >= array->map.max_entries) + * goto out; + */ + EMIT4(0x48, 0x8B, 0x46, /* mov rax, qword ptr [rsi + 16] */ + offsetof(struct bpf_array, map.max_entries)); + EMIT3(0x48, 0x39, 0xD0); /* cmp rax, rdx */ +#define OFFSET1 47 /* number of bytes to jump */ + EMIT2(X86_JBE, OFFSET1); /* jbe out */ + label1 = cnt; + + /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + */ + EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ + EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ +#define OFFSET2 36 + EMIT2(X86_JA, OFFSET2); /* ja out */ + label2 = cnt; + EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ + EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ + + /* prog = array->ptrs[index]; */ + EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ + offsetof(struct bpf_array, ptrs)); + EMIT3(0x48, 0x8B, 0x00); /* mov rax, qword ptr [rax] */ + + /* if (prog == NULL) + * goto out; + */ + EMIT4(0x48, 0x83, 0xF8, 0x00); /* cmp rax, 0 */ +#define OFFSET3 10 + EMIT2(X86_JE, OFFSET3); /* je out */ + label3 = cnt; + + /* goto *(prog->bpf_func + prologue_size); */ + EMIT4(0x48, 0x8B, 0x40, /* mov rax, qword ptr [rax + 32] */ + offsetof(struct bpf_prog, bpf_func)); + EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */ + + /* now we're ready to jump into next BPF program + * rdi == ctx (1st arg) + * rax == prog->bpf_func + prologue_size + */ + EMIT2(0xFF, 0xE0); /* jmp rax */ + + /* out: */ + BUILD_BUG_ON(cnt - label1 != OFFSET1); + BUILD_BUG_ON(cnt - label2 != OFFSET2); + BUILD_BUG_ON(cnt - label3 != OFFSET3); + *pprog = prog; +} + + +static void emit_load_skb_data_hlen(u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + /* r9d = skb->len - skb->data_len (headlen) + * r10 = skb->data + */ + /* mov %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len)); + + /* sub %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len)); + + /* mov %r10, off32(%rdi) */ + EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data)); + *pprog = prog; +} + +static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, + int oldproglen, struct jit_context *ctx) +{ + struct bpf_insn *insn = bpf_prog->insnsi; + int insn_cnt = bpf_prog->len; + bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0); + bool seen_exit = false; + u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; + int i, cnt = 0; + int proglen = 0; + u8 *prog = temp; + + emit_prologue(&prog); + + if (seen_ld_abs) + emit_load_skb_data_hlen(&prog); for (i = 0; i < insn_cnt; i++, insn++) { const s32 imm32 = insn->imm; @@ -269,6 +359,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 b1 = 0, b2 = 0, b3 = 0; s64 jmp_offset; u8 jmp_cond; + bool reload_skb_data; int ilen; u8 *func; @@ -720,12 +811,18 @@ xadd: if (is_imm8(insn->off)) func = (u8 *) __bpf_call_base + imm32; jmp_offset = func - (image + addrs[i]); if (seen_ld_abs) { - EMIT2(0x41, 0x52); /* push %r10 */ - EMIT2(0x41, 0x51); /* push %r9 */ - /* need to adjust jmp offset, since - * pop %r9, pop %r10 take 4 bytes after call insn - */ - jmp_offset += 4; + reload_skb_data = bpf_helper_changes_skb_data(func); + if (reload_skb_data) { + EMIT1(0x57); /* push %rdi */ + jmp_offset += 22; /* pop, mov, sub, mov */ + } else { + EMIT2(0x41, 0x52); /* push %r10 */ + EMIT2(0x41, 0x51); /* push %r9 */ + /* need to adjust jmp offset, since + * pop %r9, pop %r10 take 4 bytes after call insn + */ + jmp_offset += 4; + } } if (!imm32 || !is_simm32(jmp_offset)) { pr_err("unsupported bpf func %d addr %p image %p\n", @@ -734,11 +831,20 @@ xadd: if (is_imm8(insn->off)) } EMIT1_off32(0xE8, jmp_offset); if (seen_ld_abs) { - EMIT2(0x41, 0x59); /* pop %r9 */ - EMIT2(0x41, 0x5A); /* pop %r10 */ + if (reload_skb_data) { + EMIT1(0x5F); /* pop %rdi */ + emit_load_skb_data_hlen(&prog); + } else { + EMIT2(0x41, 0x59); /* pop %r9 */ + EMIT2(0x41, 0x5A); /* pop %r10 */ + } } break; + case BPF_JMP | BPF_CALL | BPF_X: + emit_bpf_tail_call(&prog); + break; + /* cond jump */ case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JNE | BPF_X: @@ -891,13 +997,13 @@ common_load: /* update cleanup_addr */ ctx->cleanup_addr = proglen; /* mov rbx, qword ptr [rbp-X] */ - EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize); + EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE); /* mov r13, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8); + EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8); /* mov r14, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16); + EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16); /* mov r15, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24); + EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24); EMIT1(0xC9); /* leave */ EMIT1(0xC3); /* ret */ @@ -997,13 +1103,13 @@ void bpf_int_jit_compile(struct bpf_prog *prog) } if (bpf_jit_enable > 1) - bpf_jit_dump(prog->len, proglen, 0, image); + bpf_jit_dump(prog->len, proglen, pass + 1, image); if (image) { bpf_flush_icache(header, image + proglen); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)image; - prog->jited = true; + prog->jited = 1; } out: kfree(addrs); diff --git a/kernel/arch/x86/pci/acpi.c b/kernel/arch/x86/pci/acpi.c index ff9911707..3cd69832d 100644 --- a/kernel/arch/x86/pci/acpi.c +++ b/kernel/arch/x86/pci/acpi.c @@ -4,16 +4,15 @@ #include <linux/irq.h> #include <linux/dmi.h> #include <linux/slab.h> +#include <linux/pci-acpi.h> #include <asm/numa.h> #include <asm/pci_x86.h> struct pci_root_info { - struct acpi_device *bridge; - char name[16]; + struct acpi_pci_root_info common; struct pci_sysdata sd; #ifdef CONFIG_PCI_MMCONFIG bool mcfg_added; - u16 segment; u8 start_bus; u8 end_bus; #endif @@ -178,15 +177,18 @@ static int check_segment(u16 seg, struct device *dev, char *estr) return 0; } -static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, - u8 end, phys_addr_t addr) +static int setup_mcfg_map(struct acpi_pci_root_info *ci) { - int result; - struct device *dev = &info->bridge->dev; + int result, seg; + struct pci_root_info *info; + struct acpi_pci_root *root = ci->root; + struct device *dev = &ci->bridge->dev; - info->start_bus = start; - info->end_bus = end; + info = container_of(ci, struct pci_root_info, common); + info->start_bus = (u8)root->secondary.start; + info->end_bus = (u8)root->secondary.end; info->mcfg_added = false; + seg = info->sd.domain; /* return success if MMCFG is not in use */ if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) @@ -195,7 +197,8 @@ static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, if (!(pci_probe & PCI_PROBE_MMCONF)) return check_segment(seg, dev, "MMCONFIG is disabled,"); - result = pci_mmconfig_insert(dev, seg, start, end, addr); + result = pci_mmconfig_insert(dev, seg, info->start_bus, info->end_bus, + root->mcfg_addr); if (result == 0) { /* enable MMCFG if it hasn't been enabled yet */ if (raw_pci_ext_ops == NULL) @@ -208,134 +211,55 @@ static int setup_mcfg_map(struct pci_root_info *info, u16 seg, u8 start, return 0; } -static void teardown_mcfg_map(struct pci_root_info *info) +static void teardown_mcfg_map(struct acpi_pci_root_info *ci) { + struct pci_root_info *info; + + info = container_of(ci, struct pci_root_info, common); if (info->mcfg_added) { - pci_mmconfig_delete(info->segment, info->start_bus, - info->end_bus); + pci_mmconfig_delete(info->sd.domain, + info->start_bus, info->end_bus); info->mcfg_added = false; } } #else -static int setup_mcfg_map(struct pci_root_info *info, - u16 seg, u8 start, u8 end, - phys_addr_t addr) +static int setup_mcfg_map(struct acpi_pci_root_info *ci) { return 0; } -static void teardown_mcfg_map(struct pci_root_info *info) + +static void teardown_mcfg_map(struct acpi_pci_root_info *ci) { } #endif -static void validate_resources(struct device *dev, struct list_head *crs_res, - unsigned long type) +static int pci_acpi_root_get_node(struct acpi_pci_root *root) { - LIST_HEAD(list); - struct resource *res1, *res2, *root = NULL; - struct resource_entry *tmp, *entry, *entry2; - - BUG_ON((type & (IORESOURCE_MEM | IORESOURCE_IO)) == 0); - root = (type & IORESOURCE_MEM) ? &iomem_resource : &ioport_resource; - - list_splice_init(crs_res, &list); - resource_list_for_each_entry_safe(entry, tmp, &list) { - bool free = false; - resource_size_t end; - - res1 = entry->res; - if (!(res1->flags & type)) - goto next; - - /* Exclude non-addressable range or non-addressable portion */ - end = min(res1->end, root->end); - if (end <= res1->start) { - dev_info(dev, "host bridge window %pR (ignored, not CPU addressable)\n", - res1); - free = true; - goto next; - } else if (res1->end != end) { - dev_info(dev, "host bridge window %pR ([%#llx-%#llx] ignored, not CPU addressable)\n", - res1, (unsigned long long)end + 1, - (unsigned long long)res1->end); - res1->end = end; - } - - resource_list_for_each_entry(entry2, crs_res) { - res2 = entry2->res; - if (!(res2->flags & type)) - continue; - - /* - * I don't like throwing away windows because then - * our resources no longer match the ACPI _CRS, but - * the kernel resource tree doesn't allow overlaps. - */ - if (resource_overlaps(res1, res2)) { - res2->start = min(res1->start, res2->start); - res2->end = max(res1->end, res2->end); - dev_info(dev, "host bridge window expanded to %pR; %pR ignored\n", - res2, res1); - free = true; - goto next; - } - } + int busnum = root->secondary.start; + struct acpi_device *device = root->device; + int node = acpi_get_node(device->handle); -next: - resource_list_del(entry); - if (free) - resource_list_free_entry(entry); - else - resource_list_add_tail(entry, crs_res); + if (node == NUMA_NO_NODE) { + node = x86_pci_root_bus_node(busnum); + if (node != 0 && node != NUMA_NO_NODE) + dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", + node); } + if (node != NUMA_NO_NODE && !node_online(node)) + node = NUMA_NO_NODE; + + return node; } -static void add_resources(struct pci_root_info *info, - struct list_head *resources, - struct list_head *crs_res) +static int pci_acpi_root_init_info(struct acpi_pci_root_info *ci) { - struct resource_entry *entry, *tmp; - struct resource *res, *conflict, *root = NULL; - - validate_resources(&info->bridge->dev, crs_res, IORESOURCE_MEM); - validate_resources(&info->bridge->dev, crs_res, IORESOURCE_IO); - - resource_list_for_each_entry_safe(entry, tmp, crs_res) { - res = entry->res; - if (res->flags & IORESOURCE_MEM) - root = &iomem_resource; - else if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - BUG_ON(res); - - conflict = insert_resource_conflict(root, res); - if (conflict) { - dev_info(&info->bridge->dev, - "ignoring host bridge window %pR (conflicts with %s %pR)\n", - res, conflict->name, conflict); - resource_list_destroy_entry(entry); - } - } - - list_splice_tail(crs_res, resources); + return setup_mcfg_map(ci); } -static void release_pci_root_info(struct pci_host_bridge *bridge) +static void pci_acpi_root_release_info(struct acpi_pci_root_info *ci) { - struct resource *res; - struct resource_entry *entry; - struct pci_root_info *info = bridge->release_data; - - resource_list_for_each_entry(entry, &bridge->windows) { - res = entry->res; - if (res->parent && - (res->flags & (IORESOURCE_MEM | IORESOURCE_IO))) - release_resource(res); - } - - teardown_mcfg_map(info); - kfree(info); + teardown_mcfg_map(ci); + kfree(container_of(ci, struct pci_root_info, common)); } /* @@ -358,50 +282,47 @@ static bool resource_is_pcicfg_ioport(struct resource *res) res->start == 0xCF8 && res->end == 0xCFF; } -static void probe_pci_root_info(struct pci_root_info *info, - struct acpi_device *device, - int busnum, int domain, - struct list_head *list) +static int pci_acpi_root_prepare_resources(struct acpi_pci_root_info *ci) { - int ret; + struct acpi_device *device = ci->bridge; + int busnum = ci->root->secondary.start; struct resource_entry *entry, *tmp; + int status; - sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum); - info->bridge = device; - ret = acpi_dev_get_resources(device, list, - acpi_dev_filter_resource_type_cb, - (void *)(IORESOURCE_IO | IORESOURCE_MEM)); - if (ret < 0) - dev_warn(&device->dev, - "failed to parse _CRS method, error code %d\n", ret); - else if (ret == 0) - dev_dbg(&device->dev, - "no IO and memory resources present in _CRS\n"); - else - resource_list_for_each_entry_safe(entry, tmp, list) { - if ((entry->res->flags & IORESOURCE_DISABLED) || - resource_is_pcicfg_ioport(entry->res)) + status = acpi_pci_probe_root_resources(ci); + if (pci_use_crs) { + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) + if (resource_is_pcicfg_ioport(entry->res)) resource_list_destroy_entry(entry); - else - entry->res->name = info->name; - } + return status; + } + + resource_list_for_each_entry_safe(entry, tmp, &ci->resources) { + dev_printk(KERN_DEBUG, &device->dev, + "host bridge window %pR (ignored)\n", entry->res); + resource_list_destroy_entry(entry); + } + x86_pci_root_bus_resources(busnum, &ci->resources); + + return 0; } +static struct acpi_pci_root_ops acpi_pci_root_ops = { + .pci_ops = &pci_root_ops, + .init_info = pci_acpi_root_init_info, + .release_info = pci_acpi_root_release_info, + .prepare_resources = pci_acpi_root_prepare_resources, +}; + struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) { - struct acpi_device *device = root->device; - struct pci_root_info *info; int domain = root->segment; int busnum = root->secondary.start; - struct resource_entry *res_entry; - LIST_HEAD(crs_res); - LIST_HEAD(resources); + int node = pci_acpi_root_get_node(root); struct pci_bus *bus; - struct pci_sysdata *sd; - int node; if (pci_ignore_seg) - domain = 0; + root->segment = domain = 0; if (domain && !pci_domains_supported) { printk(KERN_WARNING "pci_bus %04x:%02x: " @@ -410,71 +331,33 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) return NULL; } - node = acpi_get_node(device->handle); - if (node == NUMA_NO_NODE) { - node = x86_pci_root_bus_node(busnum); - if (node != 0 && node != NUMA_NO_NODE) - dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", - node); - } - - if (node != NUMA_NO_NODE && !node_online(node)) - node = NUMA_NO_NODE; - - info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); - if (!info) { - printk(KERN_WARNING "pci_bus %04x:%02x: " - "ignored (out of memory)\n", domain, busnum); - return NULL; - } - - sd = &info->sd; - sd->domain = domain; - sd->node = node; - sd->companion = device; - bus = pci_find_bus(domain, busnum); if (bus) { /* * If the desired bus has been scanned already, replace * its bus->sysdata. */ - memcpy(bus->sysdata, sd, sizeof(*sd)); - kfree(info); - } else { - /* insert busn res at first */ - pci_add_resource(&resources, &root->secondary); + struct pci_sysdata sd = { + .domain = domain, + .node = node, + .companion = root->device + }; - /* - * _CRS with no apertures is normal, so only fall back to - * defaults or native bridge info if we're ignoring _CRS. - */ - probe_pci_root_info(info, device, busnum, domain, &crs_res); - if (pci_use_crs) { - add_resources(info, &resources, &crs_res); - } else { - resource_list_for_each_entry(res_entry, &crs_res) - dev_printk(KERN_DEBUG, &device->dev, - "host bridge window %pR (ignored)\n", - res_entry->res); - resource_list_free(&crs_res); - x86_pci_root_bus_resources(busnum, &resources); - } - - if (!setup_mcfg_map(info, domain, (u8)root->secondary.start, - (u8)root->secondary.end, root->mcfg_addr)) - bus = pci_create_root_bus(NULL, busnum, &pci_root_ops, - sd, &resources); - - if (bus) { - pci_scan_child_bus(bus); - pci_set_host_bridge_release( - to_pci_host_bridge(bus->bridge), - release_pci_root_info, info); - } else { - resource_list_free(&resources); - teardown_mcfg_map(info); - kfree(info); + memcpy(bus->sysdata, &sd, sizeof(sd)); + } else { + struct pci_root_info *info; + + info = kzalloc_node(sizeof(*info), GFP_KERNEL, node); + if (!info) + dev_err(&root->device->dev, + "pci_bus %04x:%02x: ignored (out of memory)\n", + domain, busnum); + else { + info->sd.domain = domain; + info->sd.node = node; + info->sd.companion = root->device; + bus = acpi_pci_root_create(root, &acpi_pci_root_ops, + &info->common, &info->sd); } } @@ -487,9 +370,6 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) pcie_bus_configure_settings(child); } - if (bus && node != NUMA_NO_NODE) - dev_printk(KERN_DEBUG, &bus->dev, "on NUMA node %d\n", node); - return bus; } diff --git a/kernel/arch/x86/pci/bus_numa.c b/kernel/arch/x86/pci/bus_numa.c index 7bcf06a7c..6eb3c8af9 100644 --- a/kernel/arch/x86/pci/bus_numa.c +++ b/kernel/arch/x86/pci/bus_numa.c @@ -50,18 +50,9 @@ void x86_pci_root_bus_resources(int bus, struct list_head *resources) if (!found) pci_add_resource(resources, &info->busn); - list_for_each_entry(root_res, &info->resources, list) { - struct resource *res; - struct resource *root; + list_for_each_entry(root_res, &info->resources, list) + pci_add_resource(resources, &root_res->res); - res = &root_res->res; - pci_add_resource(resources, res); - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; - else - root = &iomem_resource; - insert_resource(root, res); - } return; default_resources: diff --git a/kernel/arch/x86/pci/common.c b/kernel/arch/x86/pci/common.c index 8fd6f44ae..eccd4d99e 100644 --- a/kernel/arch/x86/pci/common.c +++ b/kernel/arch/x86/pci/common.c @@ -673,24 +673,30 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_enable_device(struct pci_dev *dev, int mask) +int pcibios_alloc_irq(struct pci_dev *dev) { - int err; - - if ((err = pci_enable_resources(dev, mask)) < 0) - return err; + /* + * If the PCI device was already claimed by core code and has + * MSI enabled, probing of the pcibios IRQ will overwrite + * dev->irq. So bail out if MSI is already enabled. + */ + if (pci_dev_msi_enabled(dev)) + return -EBUSY; - if (!pci_dev_msi_enabled(dev)) - return pcibios_enable_irq(dev); - return 0; + return pcibios_enable_irq(dev); } -void pcibios_disable_device (struct pci_dev *dev) +void pcibios_free_irq(struct pci_dev *dev) { - if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + if (pcibios_disable_irq) pcibios_disable_irq(dev); } +int pcibios_enable_device(struct pci_dev *dev, int mask) +{ + return pci_enable_resources(dev, mask); +} + int pci_ext_cfg_avail(void) { if (raw_pci_ext_ops) diff --git a/kernel/arch/x86/pci/fixup.c b/kernel/arch/x86/pci/fixup.c index 9a2b7101a..e58565556 100644 --- a/kernel/arch/x86/pci/fixup.c +++ b/kernel/arch/x86/pci/fixup.c @@ -62,19 +62,6 @@ static void pci_fixup_umc_ide(struct pci_dev *d) } DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_UMC, PCI_DEVICE_ID_UMC_UM8886BF, pci_fixup_umc_ide); -static void pci_fixup_ncr53c810(struct pci_dev *d) -{ - /* - * NCR 53C810 returns class code 0 (at least on some systems). - * Fix class to be PCI_CLASS_STORAGE_SCSI - */ - if (!d->class) { - dev_warn(&d->dev, "Fixing NCR 53C810 class code\n"); - d->class = PCI_CLASS_STORAGE_SCSI << 8; - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NCR, PCI_DEVICE_ID_NCR_53C810, pci_fixup_ncr53c810); - static void pci_fixup_latency(struct pci_dev *d) { /* diff --git a/kernel/arch/x86/pci/i386.c b/kernel/arch/x86/pci/i386.c index 349c0d32c..0a9f2caf3 100644 --- a/kernel/arch/x86/pci/i386.c +++ b/kernel/arch/x86/pci/i386.c @@ -429,12 +429,12 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, * Caller can followup with UC MINUS request and add a WC mtrr if there * is a free mtrr slot. */ - if (!pat_enabled && write_combine) + if (!pat_enabled() && write_combine) return -EINVAL; - if (pat_enabled && write_combine) + if (pat_enabled() && write_combine) prot |= cachemode2protval(_PAGE_CACHE_MODE_WC); - else if (pat_enabled || boot_cpu_data.x86 > 3) + else if (pat_enabled() || boot_cpu_data.x86 > 3) /* * ioremap() and ioremap_nocache() defaults to UC MINUS for now. * To avoid attribute conflicts, request UC MINUS here diff --git a/kernel/arch/x86/pci/intel_mid_pci.c b/kernel/arch/x86/pci/intel_mid_pci.c index 852aa4c92..0d24e7c10 100644 --- a/kernel/arch/x86/pci/intel_mid_pci.c +++ b/kernel/arch/x86/pci/intel_mid_pci.c @@ -35,6 +35,9 @@ #define PCIE_CAP_OFFSET 0x100 +/* Quirks for the listed devices */ +#define PCI_DEVICE_ID_INTEL_MRFL_MMC 0x1190 + /* Fixed BAR fields */ #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00 /* Fixed BAR (TBD) */ #define PCI_FIXED_BAR_0_SIZE 0x04 @@ -208,24 +211,43 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, static int intel_mid_pci_irq_enable(struct pci_dev *dev) { + struct irq_alloc_info info; int polarity; + int ret; - if (dev->irq_managed && dev->irq > 0) + if (pci_has_managed_irq(dev)) return 0; - if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) - polarity = 0; /* active high */ - else - polarity = 1; /* active low */ + switch (intel_mid_identify_cpu()) { + case INTEL_MID_CPU_CHIP_TANGIER: + polarity = IOAPIC_POL_HIGH; + + /* Special treatment for IRQ0 */ + if (dev->irq == 0) { + /* + * TNG has IRQ0 assigned to eMMC controller. But there + * are also other devices with bogus PCI configuration + * that have IRQ0 assigned. This check ensures that + * eMMC gets it. + */ + if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC) + return -EBUSY; + } + break; + default: + polarity = IOAPIC_POL_LOW; + break; + } + + ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity); /* * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to * IOAPIC RTE entries, so we just enable RTE for the device. */ - if (mp_set_gsi_attr(dev->irq, 1, polarity, dev_to_node(&dev->dev))) - return -EBUSY; - if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0) - return -EBUSY; + ret = mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC, &info); + if (ret < 0) + return ret; dev->irq_managed = 1; @@ -234,14 +256,17 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && - dev->irq > 0) { + if (pci_has_managed_irq(dev)) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; + /* + * Don't reset dev->irq here, otherwise + * intel_mid_pci_irq_enable() will fail on next call. + */ } } -struct pci_ops intel_mid_pci_ops = { +static struct pci_ops intel_mid_pci_ops = { .read = pci_read, .write = pci_write, }; diff --git a/kernel/arch/x86/pci/irq.c b/kernel/arch/x86/pci/irq.c index 5dc6ca5e1..32e70343e 100644 --- a/kernel/arch/x86/pci/irq.c +++ b/kernel/arch/x86/pci/irq.c @@ -146,19 +146,20 @@ static void __init pirq_peer_trick(void) /* * Code for querying and setting of IRQ routes on various interrupt routers. + * PIC Edge/Level Control Registers (ELCR) 0x4d0 & 0x4d1. */ -void eisa_set_level_irq(unsigned int irq) +void elcr_set_level_irq(unsigned int irq) { unsigned char mask = 1 << (irq & 7); unsigned int port = 0x4d0 + (irq >> 3); unsigned char val; - static u16 eisa_irq_mask; + static u16 elcr_irq_mask; - if (irq >= 16 || (1 << irq) & eisa_irq_mask) + if (irq >= 16 || (1 << irq) & elcr_irq_mask) return; - eisa_irq_mask |= (1 << irq); + elcr_irq_mask |= (1 << irq); printk(KERN_DEBUG "PCI: setting IRQ %u as level-triggered\n", irq); val = inb(port); if (!(val & mask)) { @@ -965,11 +966,11 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign) } else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) { msg = "found"; - eisa_set_level_irq(irq); + elcr_set_level_irq(irq); } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { if (r->set(pirq_router_dev, dev, pirq, newirq)) { - eisa_set_level_irq(newirq); + elcr_set_level_irq(newirq); msg = "assigned"; irq = newirq; } @@ -1201,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (dev->irq_managed && dev->irq > 0) + if (pci_has_managed_irq(dev)) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1229,8 +1230,7 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - dev->irq_managed = 1; - dev->irq = irq; + pci_set_managed_irq(dev, irq); dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1256,24 +1256,10 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } -bool mp_should_keep_irq(struct device *dev) -{ - if (dev->power.is_prepared) - return true; -#ifdef CONFIG_PM - if (dev->power.runtime_status == RPM_SUSPENDING) - return true; -#endif - - return false; -} - static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && - dev->irq_managed && dev->irq) { + if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { mp_unmap_irq(dev->irq); - dev->irq = 0; - dev->irq_managed = 0; + pci_reset_managed_irq(dev); } } diff --git a/kernel/arch/x86/pci/legacy.c b/kernel/arch/x86/pci/legacy.c index 5b662c0fa..ea6f3802c 100644 --- a/kernel/arch/x86/pci/legacy.c +++ b/kernel/arch/x86/pci/legacy.c @@ -54,7 +54,7 @@ void pcibios_scan_specific_bus(int busn) } EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus); -int __init pci_subsys_init(void) +static int __init pci_subsys_init(void) { /* * The init function returns an non zero value when diff --git a/kernel/arch/x86/pci/xen.c b/kernel/arch/x86/pci/xen.c index d22f4b5bb..ff31ab464 100644 --- a/kernel/arch/x86/pci/xen.c +++ b/kernel/arch/x86/pci/xen.c @@ -179,7 +179,7 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (ret) goto error; i = 0; - list_for_each_entry(msidesc, &dev->msi_list, list) { + for_each_pci_msi_entry(msidesc, dev) { irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i], (type == PCI_CAP_ID_MSI) ? nvec : 1, (type == PCI_CAP_ID_MSIX) ? @@ -230,7 +230,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) if (type == PCI_CAP_ID_MSI && nvec > 1) return 1; - list_for_each_entry(msidesc, &dev->msi_list, list) { + for_each_pci_msi_entry(msidesc, dev) { __pci_read_msi_msg(msidesc, &msg); pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); @@ -274,7 +274,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) int ret = 0; struct msi_desc *msidesc; - list_for_each_entry(msidesc, &dev->msi_list, list) { + for_each_pci_msi_entry(msidesc, dev) { struct physdev_map_pirq map_irq; domid_t domid; @@ -386,7 +386,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) { struct msi_desc *msidesc; - msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); + msidesc = first_pci_msi_entry(dev); if (msidesc->msi_attrib.is_msix) xen_pci_frontend_disable_msix(dev); else diff --git a/kernel/arch/x86/platform/Makefile b/kernel/arch/x86/platform/Makefile index a62e0be3a..184842ef3 100644 --- a/kernel/arch/x86/platform/Makefile +++ b/kernel/arch/x86/platform/Makefile @@ -1,9 +1,11 @@ # Platform specific code goes here +obj-y += atom/ obj-y += ce4100/ obj-y += efi/ obj-y += geode/ obj-y += goldfish/ obj-y += iris/ +obj-y += intel/ obj-y += intel-mid/ obj-y += intel-quark/ obj-y += olpc/ diff --git a/kernel/arch/x86/platform/atom/Makefile b/kernel/arch/x86/platform/atom/Makefile new file mode 100644 index 000000000..40983f5b0 --- /dev/null +++ b/kernel/arch/x86/platform/atom/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_PMC_ATOM) += pmc_atom.o +obj-$(CONFIG_PUNIT_ATOM_DEBUG) += punit_atom_debug.o diff --git a/kernel/arch/x86/kernel/pmc_atom.c b/kernel/arch/x86/platform/atom/pmc_atom.c index d66a4fe6c..964ff4fc6 100644 --- a/kernel/arch/x86/kernel/pmc_atom.c +++ b/kernel/arch/x86/platform/atom/pmc_atom.c @@ -15,7 +15,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/device.h> @@ -25,80 +24,149 @@ #include <asm/pmc_atom.h> +struct pmc_bit_map { + const char *name; + u32 bit_mask; +}; + +struct pmc_reg_map { + const struct pmc_bit_map *d3_sts_0; + const struct pmc_bit_map *d3_sts_1; + const struct pmc_bit_map *func_dis; + const struct pmc_bit_map *func_dis_2; + const struct pmc_bit_map *pss; +}; + struct pmc_dev { u32 base_addr; void __iomem *regmap; + const struct pmc_reg_map *map; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ + bool init; }; static struct pmc_dev pmc_device; static u32 acpi_base_addr; -struct pmc_bit_map { - const char *name; - u32 bit_mask; +static const struct pmc_bit_map d3_sts_0_map[] = { + {"LPSS1_F0_DMA", BIT_LPSS1_F0_DMA}, + {"LPSS1_F1_PWM1", BIT_LPSS1_F1_PWM1}, + {"LPSS1_F2_PWM2", BIT_LPSS1_F2_PWM2}, + {"LPSS1_F3_HSUART1", BIT_LPSS1_F3_HSUART1}, + {"LPSS1_F4_HSUART2", BIT_LPSS1_F4_HSUART2}, + {"LPSS1_F5_SPI", BIT_LPSS1_F5_SPI}, + {"LPSS1_F6_Reserved", BIT_LPSS1_F6_XXX}, + {"LPSS1_F7_Reserved", BIT_LPSS1_F7_XXX}, + {"SCC_EMMC", BIT_SCC_EMMC}, + {"SCC_SDIO", BIT_SCC_SDIO}, + {"SCC_SDCARD", BIT_SCC_SDCARD}, + {"SCC_MIPI", BIT_SCC_MIPI}, + {"HDA", BIT_HDA}, + {"LPE", BIT_LPE}, + {"OTG", BIT_OTG}, + {"USH", BIT_USH}, + {"GBE", BIT_GBE}, + {"SATA", BIT_SATA}, + {"USB_EHCI", BIT_USB_EHCI}, + {"SEC", BIT_SEC}, + {"PCIE_PORT0", BIT_PCIE_PORT0}, + {"PCIE_PORT1", BIT_PCIE_PORT1}, + {"PCIE_PORT2", BIT_PCIE_PORT2}, + {"PCIE_PORT3", BIT_PCIE_PORT3}, + {"LPSS2_F0_DMA", BIT_LPSS2_F0_DMA}, + {"LPSS2_F1_I2C1", BIT_LPSS2_F1_I2C1}, + {"LPSS2_F2_I2C2", BIT_LPSS2_F2_I2C2}, + {"LPSS2_F3_I2C3", BIT_LPSS2_F3_I2C3}, + {"LPSS2_F3_I2C4", BIT_LPSS2_F4_I2C4}, + {"LPSS2_F5_I2C5", BIT_LPSS2_F5_I2C5}, + {"LPSS2_F6_I2C6", BIT_LPSS2_F6_I2C6}, + {"LPSS2_F7_I2C7", BIT_LPSS2_F7_I2C7}, + {}, +}; + +static struct pmc_bit_map byt_d3_sts_1_map[] = { + {"SMB", BIT_SMB}, + {"OTG_SS_PHY", BIT_OTG_SS_PHY}, + {"USH_SS_PHY", BIT_USH_SS_PHY}, + {"DFX", BIT_DFX}, + {}, }; -static const struct pmc_bit_map dev_map[] = { - {"0 - LPSS1_F0_DMA", BIT_LPSS1_F0_DMA}, - {"1 - LPSS1_F1_PWM1", BIT_LPSS1_F1_PWM1}, - {"2 - LPSS1_F2_PWM2", BIT_LPSS1_F2_PWM2}, - {"3 - LPSS1_F3_HSUART1", BIT_LPSS1_F3_HSUART1}, - {"4 - LPSS1_F4_HSUART2", BIT_LPSS1_F4_HSUART2}, - {"5 - LPSS1_F5_SPI", BIT_LPSS1_F5_SPI}, - {"6 - LPSS1_F6_Reserved", BIT_LPSS1_F6_XXX}, - {"7 - LPSS1_F7_Reserved", BIT_LPSS1_F7_XXX}, - {"8 - SCC_EMMC", BIT_SCC_EMMC}, - {"9 - SCC_SDIO", BIT_SCC_SDIO}, - {"10 - SCC_SDCARD", BIT_SCC_SDCARD}, - {"11 - SCC_MIPI", BIT_SCC_MIPI}, - {"12 - HDA", BIT_HDA}, - {"13 - LPE", BIT_LPE}, - {"14 - OTG", BIT_OTG}, - {"15 - USH", BIT_USH}, - {"16 - GBE", BIT_GBE}, - {"17 - SATA", BIT_SATA}, - {"18 - USB_EHCI", BIT_USB_EHCI}, - {"19 - SEC", BIT_SEC}, - {"20 - PCIE_PORT0", BIT_PCIE_PORT0}, - {"21 - PCIE_PORT1", BIT_PCIE_PORT1}, - {"22 - PCIE_PORT2", BIT_PCIE_PORT2}, - {"23 - PCIE_PORT3", BIT_PCIE_PORT3}, - {"24 - LPSS2_F0_DMA", BIT_LPSS2_F0_DMA}, - {"25 - LPSS2_F1_I2C1", BIT_LPSS2_F1_I2C1}, - {"26 - LPSS2_F2_I2C2", BIT_LPSS2_F2_I2C2}, - {"27 - LPSS2_F3_I2C3", BIT_LPSS2_F3_I2C3}, - {"28 - LPSS2_F3_I2C4", BIT_LPSS2_F4_I2C4}, - {"29 - LPSS2_F5_I2C5", BIT_LPSS2_F5_I2C5}, - {"30 - LPSS2_F6_I2C6", BIT_LPSS2_F6_I2C6}, - {"31 - LPSS2_F7_I2C7", BIT_LPSS2_F7_I2C7}, - {"32 - SMB", BIT_SMB}, - {"33 - OTG_SS_PHY", BIT_OTG_SS_PHY}, - {"34 - USH_SS_PHY", BIT_USH_SS_PHY}, - {"35 - DFX", BIT_DFX}, +static struct pmc_bit_map cht_d3_sts_1_map[] = { + {"SMB", BIT_SMB}, + {"GMM", BIT_STS_GMM}, + {"ISH", BIT_STS_ISH}, + {}, }; -static const struct pmc_bit_map pss_map[] = { - {"0 - GBE", PMC_PSS_BIT_GBE}, - {"1 - SATA", PMC_PSS_BIT_SATA}, - {"2 - HDA", PMC_PSS_BIT_HDA}, - {"3 - SEC", PMC_PSS_BIT_SEC}, - {"4 - PCIE", PMC_PSS_BIT_PCIE}, - {"5 - LPSS", PMC_PSS_BIT_LPSS}, - {"6 - LPE", PMC_PSS_BIT_LPE}, - {"7 - DFX", PMC_PSS_BIT_DFX}, - {"8 - USH_CTRL", PMC_PSS_BIT_USH_CTRL}, - {"9 - USH_SUS", PMC_PSS_BIT_USH_SUS}, - {"10 - USH_VCCS", PMC_PSS_BIT_USH_VCCS}, - {"11 - USH_VCCA", PMC_PSS_BIT_USH_VCCA}, - {"12 - OTG_CTRL", PMC_PSS_BIT_OTG_CTRL}, - {"13 - OTG_VCCS", PMC_PSS_BIT_OTG_VCCS}, - {"14 - OTG_VCCA_CLK", PMC_PSS_BIT_OTG_VCCA_CLK}, - {"15 - OTG_VCCA", PMC_PSS_BIT_OTG_VCCA}, - {"16 - USB", PMC_PSS_BIT_USB}, - {"17 - USB_SUS", PMC_PSS_BIT_USB_SUS}, +static struct pmc_bit_map cht_func_dis_2_map[] = { + {"SMB", BIT_SMB}, + {"GMM", BIT_FD_GMM}, + {"ISH", BIT_FD_ISH}, + {}, +}; + +static const struct pmc_bit_map byt_pss_map[] = { + {"GBE", PMC_PSS_BIT_GBE}, + {"SATA", PMC_PSS_BIT_SATA}, + {"HDA", PMC_PSS_BIT_HDA}, + {"SEC", PMC_PSS_BIT_SEC}, + {"PCIE", PMC_PSS_BIT_PCIE}, + {"LPSS", PMC_PSS_BIT_LPSS}, + {"LPE", PMC_PSS_BIT_LPE}, + {"DFX", PMC_PSS_BIT_DFX}, + {"USH_CTRL", PMC_PSS_BIT_USH_CTRL}, + {"USH_SUS", PMC_PSS_BIT_USH_SUS}, + {"USH_VCCS", PMC_PSS_BIT_USH_VCCS}, + {"USH_VCCA", PMC_PSS_BIT_USH_VCCA}, + {"OTG_CTRL", PMC_PSS_BIT_OTG_CTRL}, + {"OTG_VCCS", PMC_PSS_BIT_OTG_VCCS}, + {"OTG_VCCA_CLK", PMC_PSS_BIT_OTG_VCCA_CLK}, + {"OTG_VCCA", PMC_PSS_BIT_OTG_VCCA}, + {"USB", PMC_PSS_BIT_USB}, + {"USB_SUS", PMC_PSS_BIT_USB_SUS}, + {}, +}; + +static const struct pmc_bit_map cht_pss_map[] = { + {"SATA", PMC_PSS_BIT_SATA}, + {"HDA", PMC_PSS_BIT_HDA}, + {"SEC", PMC_PSS_BIT_SEC}, + {"PCIE", PMC_PSS_BIT_PCIE}, + {"LPSS", PMC_PSS_BIT_LPSS}, + {"LPE", PMC_PSS_BIT_LPE}, + {"UFS", PMC_PSS_BIT_CHT_UFS}, + {"UXD", PMC_PSS_BIT_CHT_UXD}, + {"UXD_FD", PMC_PSS_BIT_CHT_UXD_FD}, + {"UX_ENG", PMC_PSS_BIT_CHT_UX_ENG}, + {"USB_SUS", PMC_PSS_BIT_CHT_USB_SUS}, + {"GMM", PMC_PSS_BIT_CHT_GMM}, + {"ISH", PMC_PSS_BIT_CHT_ISH}, + {"DFX_MASTER", PMC_PSS_BIT_CHT_DFX_MASTER}, + {"DFX_CLUSTER1", PMC_PSS_BIT_CHT_DFX_CLUSTER1}, + {"DFX_CLUSTER2", PMC_PSS_BIT_CHT_DFX_CLUSTER2}, + {"DFX_CLUSTER3", PMC_PSS_BIT_CHT_DFX_CLUSTER3}, + {"DFX_CLUSTER4", PMC_PSS_BIT_CHT_DFX_CLUSTER4}, + {"DFX_CLUSTER5", PMC_PSS_BIT_CHT_DFX_CLUSTER5}, + {}, +}; + +static const struct pmc_reg_map byt_reg_map = { + .d3_sts_0 = d3_sts_0_map, + .d3_sts_1 = byt_d3_sts_1_map, + .func_dis = d3_sts_0_map, + .func_dis_2 = byt_d3_sts_1_map, + .pss = byt_pss_map, +}; + +static const struct pmc_reg_map cht_reg_map = { + .d3_sts_0 = d3_sts_0_map, + .d3_sts_1 = cht_d3_sts_1_map, + .func_dis = d3_sts_0_map, + .func_dis_2 = cht_func_dis_2_map, + .pss = cht_pss_map, }; static inline u32 pmc_reg_read(struct pmc_dev *pmc, int reg_offset) @@ -111,6 +179,30 @@ static inline void pmc_reg_write(struct pmc_dev *pmc, int reg_offset, u32 val) writel(val, pmc->regmap + reg_offset); } +int pmc_atom_read(int offset, u32 *value) +{ + struct pmc_dev *pmc = &pmc_device; + + if (!pmc->init) + return -ENODEV; + + *value = pmc_reg_read(pmc, offset); + return 0; +} +EXPORT_SYMBOL_GPL(pmc_atom_read); + +int pmc_atom_write(int offset, u32 value) +{ + struct pmc_dev *pmc = &pmc_device; + + if (!pmc->init) + return -ENODEV; + + pmc_reg_write(pmc, offset, value); + return 0; +} +EXPORT_SYMBOL_GPL(pmc_atom_write); + static void pmc_power_off(void) { u16 pm1_cnt_port; @@ -142,37 +234,39 @@ static void pmc_hw_reg_setup(struct pmc_dev *pmc) } #ifdef CONFIG_DEBUG_FS +static void pmc_dev_state_print(struct seq_file *s, int reg_index, + u32 sts, const struct pmc_bit_map *sts_map, + u32 fd, const struct pmc_bit_map *fd_map) +{ + int offset = PMC_REG_BIT_WIDTH * reg_index; + int index; + + for (index = 0; sts_map[index].name; index++) { + seq_printf(s, "Dev: %-2d - %-32s\tState: %s [%s]\n", + offset + index, sts_map[index].name, + fd_map[index].bit_mask & fd ? "Disabled" : "Enabled ", + sts_map[index].bit_mask & sts ? "D3" : "D0"); + } +} + static int pmc_dev_state_show(struct seq_file *s, void *unused) { struct pmc_dev *pmc = s->private; - u32 func_dis, func_dis_2, func_dis_index; - u32 d3_sts_0, d3_sts_1, d3_sts_index; - int dev_num, dev_index, reg_index; + const struct pmc_reg_map *m = pmc->map; + u32 func_dis, func_dis_2; + u32 d3_sts_0, d3_sts_1; func_dis = pmc_reg_read(pmc, PMC_FUNC_DIS); func_dis_2 = pmc_reg_read(pmc, PMC_FUNC_DIS_2); d3_sts_0 = pmc_reg_read(pmc, PMC_D3_STS_0); d3_sts_1 = pmc_reg_read(pmc, PMC_D3_STS_1); - dev_num = ARRAY_SIZE(dev_map); - - for (dev_index = 0; dev_index < dev_num; dev_index++) { - reg_index = dev_index / PMC_REG_BIT_WIDTH; - if (reg_index) { - func_dis_index = func_dis_2; - d3_sts_index = d3_sts_1; - } else { - func_dis_index = func_dis; - d3_sts_index = d3_sts_0; - } - - seq_printf(s, "Dev: %-32s\tState: %s [%s]\n", - dev_map[dev_index].name, - dev_map[dev_index].bit_mask & func_dis_index ? - "Disabled" : "Enabled ", - dev_map[dev_index].bit_mask & d3_sts_index ? - "D3" : "D0"); - } + /* Low part */ + pmc_dev_state_print(s, 0, d3_sts_0, m->d3_sts_0, func_dis, m->func_dis); + + /* High part */ + pmc_dev_state_print(s, 1, d3_sts_1, m->d3_sts_1, func_dis_2, m->func_dis_2); + return 0; } @@ -191,13 +285,14 @@ static const struct file_operations pmc_dev_state_ops = { static int pmc_pss_state_show(struct seq_file *s, void *unused) { struct pmc_dev *pmc = s->private; + const struct pmc_bit_map *map = pmc->map->pss; u32 pss = pmc_reg_read(pmc, PMC_PSS); - int pss_index; + int index; - for (pss_index = 0; pss_index < ARRAY_SIZE(pss_map); pss_index++) { - seq_printf(s, "Island: %-32s\tState: %s\n", - pss_map[pss_index].name, - pss_map[pss_index].bit_mask & pss ? "Off" : "On"); + for (index = 0; map[index].name; index++) { + seq_printf(s, "Island: %-2d - %-32s\tState: %s\n", + index, map[index].name, + map[index].bit_mask & pss ? "Off" : "On"); } return 0; } @@ -250,7 +345,7 @@ static void pmc_dbgfs_unregister(struct pmc_dev *pmc) debugfs_remove_recursive(pmc->dbgfs_dir); } -static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +static int pmc_dbgfs_register(struct pmc_dev *pmc) { struct dentry *dir, *f; @@ -262,24 +357,18 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) f = debugfs_create_file("dev_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_dev_state_ops); - if (!f) { - dev_err(&pdev->dev, "dev_state register failed\n"); + if (!f) goto err; - } f = debugfs_create_file("pss_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_pss_state_ops); - if (!f) { - dev_err(&pdev->dev, "pss_state register failed\n"); + if (!f) goto err; - } f = debugfs_create_file("sleep_state", S_IFREG | S_IRUGO, dir, pmc, &pmc_sleep_tmr_ops); - if (!f) { - dev_err(&pdev->dev, "sleep_state register failed\n"); + if (!f) goto err; - } return 0; err: @@ -287,15 +376,16 @@ err: return -ENODEV; } #else -static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev) +static int pmc_dbgfs_register(struct pmc_dev *pmc) { return 0; } #endif /* CONFIG_DEBUG_FS */ -static int pmc_setup_dev(struct pci_dev *pdev) +static int pmc_setup_dev(struct pci_dev *pdev, const struct pci_device_id *ent) { struct pmc_dev *pmc = &pmc_device; + const struct pmc_reg_map *map = (struct pmc_reg_map *)ent->driver_data; int ret; /* Obtain ACPI base address */ @@ -315,32 +405,30 @@ static int pmc_setup_dev(struct pci_dev *pdev) return -ENOMEM; } + pmc->map = map; + /* PMC hardware registers setup */ pmc_hw_reg_setup(pmc); - ret = pmc_dbgfs_register(pmc, pdev); - if (ret) { - iounmap(pmc->regmap); - } + ret = pmc_dbgfs_register(pmc); + if (ret) + dev_warn(&pdev->dev, "debugfs register failed\n"); + pmc->init = true; return ret; } /* * Data for PCI driver interface * - * This data only exists for exporting the supported - * PCI ids via MODULE_DEVICE_TABLE. We do not actually - * register a pci_driver, because lpc_ich will register - * a driver on the same PCI id. + * used by pci_match_id() call below. */ static const struct pci_device_id pmc_pci_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_VLV_PMC) }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_VLV_PMC), (kernel_ulong_t)&byt_reg_map }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_CHT_PMC), (kernel_ulong_t)&cht_reg_map }, { 0, }, }; -MODULE_DEVICE_TABLE(pci, pmc_pci_ids); - static int __init pmc_atom_init(void) { struct pci_dev *pdev = NULL; @@ -357,15 +445,16 @@ static int __init pmc_atom_init(void) for_each_pci_dev(pdev) { ent = pci_match_id(pmc_pci_ids, pdev); if (ent) - return pmc_setup_dev(pdev); + return pmc_setup_dev(pdev, ent); } /* Device not found. */ return -ENODEV; } -module_init(pmc_atom_init); -/* no module_exit, this driver shouldn't be unloaded */ +device_initcall(pmc_atom_init); +/* MODULE_AUTHOR("Aubrey Li <aubrey.li@linux.intel.com>"); MODULE_DESCRIPTION("Intel Atom SOC Power Management Controller Interface"); MODULE_LICENSE("GPL v2"); +*/ diff --git a/kernel/arch/x86/platform/atom/punit_atom_debug.c b/kernel/arch/x86/platform/atom/punit_atom_debug.c new file mode 100644 index 000000000..5ca8ead91 --- /dev/null +++ b/kernel/arch/x86/platform/atom/punit_atom_debug.c @@ -0,0 +1,183 @@ +/* + * Intel SOC Punit device state debug driver + * Punit controls power management for North Complex devices (Graphics + * blocks, Image Signal Processing, video processing, display, DSP etc.) + * + * Copyright (c) 2015, Intel Corporation. + * + * 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. + * + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/device.h> +#include <linux/debugfs.h> +#include <linux/seq_file.h> +#include <linux/io.h> +#include <asm/cpu_device_id.h> +#include <asm/iosf_mbi.h> + +/* Side band Interface port */ +#define PUNIT_PORT 0x04 +/* Power gate status reg */ +#define PWRGT_STATUS 0x61 +/* Subsystem config/status Video processor */ +#define VED_SS_PM0 0x32 +/* Subsystem config/status ISP (Image Signal Processor) */ +#define ISP_SS_PM0 0x39 +/* Subsystem config/status Input/output controller */ +#define MIO_SS_PM 0x3B +/* Shift bits for getting status for video, isp and i/o */ +#define SSS_SHIFT 24 +/* Shift bits for getting status for graphics rendering */ +#define RENDER_POS 0 +/* Shift bits for getting status for media control */ +#define MEDIA_POS 2 +/* Shift bits for getting status for Valley View/Baytrail display */ +#define VLV_DISPLAY_POS 6 +/* Subsystem config/status display for Cherry Trail SOC */ +#define CHT_DSP_SSS 0x36 +/* Shift bits for getting status for display */ +#define CHT_DSP_SSS_POS 16 + +struct punit_device { + char *name; + int reg; + int sss_pos; +}; + +static const struct punit_device punit_device_byt[] = { + { "GFX RENDER", PWRGT_STATUS, RENDER_POS }, + { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS }, + { "DISPLAY", PWRGT_STATUS, VLV_DISPLAY_POS }, + { "VED", VED_SS_PM0, SSS_SHIFT }, + { "ISP", ISP_SS_PM0, SSS_SHIFT }, + { "MIO", MIO_SS_PM, SSS_SHIFT }, + { NULL } +}; + +static const struct punit_device punit_device_cht[] = { + { "GFX RENDER", PWRGT_STATUS, RENDER_POS }, + { "GFX MEDIA", PWRGT_STATUS, MEDIA_POS }, + { "DISPLAY", CHT_DSP_SSS, CHT_DSP_SSS_POS }, + { "VED", VED_SS_PM0, SSS_SHIFT }, + { "ISP", ISP_SS_PM0, SSS_SHIFT }, + { "MIO", MIO_SS_PM, SSS_SHIFT }, + { NULL } +}; + +static const char * const dstates[] = {"D0", "D0i1", "D0i2", "D0i3"}; + +static int punit_dev_state_show(struct seq_file *seq_file, void *unused) +{ + u32 punit_pwr_status; + struct punit_device *punit_devp = seq_file->private; + int index; + int status; + + seq_puts(seq_file, "\n\nPUNIT NORTH COMPLEX DEVICES :\n"); + while (punit_devp->name) { + status = iosf_mbi_read(PUNIT_PORT, BT_MBI_PMC_READ, + punit_devp->reg, + &punit_pwr_status); + if (status) { + seq_printf(seq_file, "%9s : Read Failed\n", + punit_devp->name); + } else { + index = (punit_pwr_status >> punit_devp->sss_pos) & 3; + seq_printf(seq_file, "%9s : %s\n", punit_devp->name, + dstates[index]); + } + punit_devp++; + } + + return 0; +} + +static int punit_dev_state_open(struct inode *inode, struct file *file) +{ + return single_open(file, punit_dev_state_show, inode->i_private); +} + +static const struct file_operations punit_dev_state_ops = { + .open = punit_dev_state_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *punit_dbg_file; + +static int punit_dbgfs_register(struct punit_device *punit_device) +{ + static struct dentry *dev_state; + + punit_dbg_file = debugfs_create_dir("punit_atom", NULL); + if (!punit_dbg_file) + return -ENXIO; + + dev_state = debugfs_create_file("dev_power_state", S_IFREG | S_IRUGO, + punit_dbg_file, punit_device, + &punit_dev_state_ops); + if (!dev_state) { + pr_err("punit_dev_state register failed\n"); + debugfs_remove(punit_dbg_file); + return -ENXIO; + } + + return 0; +} + +static void punit_dbgfs_unregister(void) +{ + debugfs_remove_recursive(punit_dbg_file); +} + +#define ICPU(model, drv_data) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_MWAIT,\ + (kernel_ulong_t)&drv_data } + +static const struct x86_cpu_id intel_punit_cpu_ids[] = { + ICPU(55, punit_device_byt), /* Valleyview, Bay Trail */ + ICPU(76, punit_device_cht), /* Braswell, Cherry Trail */ + {} +}; + +MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids); + +static int __init punit_atom_debug_init(void) +{ + const struct x86_cpu_id *id; + int ret; + + id = x86_match_cpu(intel_punit_cpu_ids); + if (!id) + return -ENODEV; + + ret = punit_dbgfs_register((struct punit_device *)id->driver_data); + if (ret < 0) + return ret; + + return 0; +} + +static void __exit punit_atom_debug_exit(void) +{ + punit_dbgfs_unregister(); +} + +module_init(punit_atom_debug_init); +module_exit(punit_atom_debug_exit); + +MODULE_AUTHOR("Kumar P, Mahesh <mahesh.kumar.p@intel.com>"); +MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>"); +MODULE_DESCRIPTION("Driver for Punit devices states debugging"); +MODULE_LICENSE("GPL v2"); diff --git a/kernel/arch/x86/platform/efi/efi-bgrt.c b/kernel/arch/x86/platform/efi/efi-bgrt.c index d7f997f7c..ea48449b2 100644 --- a/kernel/arch/x86/platform/efi/efi-bgrt.c +++ b/kernel/arch/x86/platform/efi/efi-bgrt.c @@ -50,11 +50,16 @@ void __init efi_bgrt_init(void) bgrt_tab->version); return; } - if (bgrt_tab->status != 1) { - pr_err("Ignoring BGRT: invalid status %u (expected 1)\n", + if (bgrt_tab->status & 0xfe) { + pr_err("Ignoring BGRT: reserved status bits are non-zero %u\n", bgrt_tab->status); return; } + if (bgrt_tab->status != 1) { + pr_debug("Ignoring BGRT: invalid status %u (expected 1)\n", + bgrt_tab->status); + return; + } if (bgrt_tab->image_type != 0) { pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n", bgrt_tab->image_type); diff --git a/kernel/arch/x86/platform/efi/efi.c b/kernel/arch/x86/platform/efi/efi.c index 841ea05e1..ad285404e 100644 --- a/kernel/arch/x86/platform/efi/efi.c +++ b/kernel/arch/x86/platform/efi/efi.c @@ -117,6 +117,27 @@ void efi_get_time(struct timespec *now) now->tv_nsec = 0; } +void __init efi_find_mirror(void) +{ + void *p; + u64 mirror_size = 0, total_size = 0; + + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + efi_memory_desc_t *md = p; + unsigned long long start = md->phys_addr; + unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + + total_size += size; + if (md->attribute & EFI_MEMORY_MORE_RELIABLE) { + memblock_mark_mirror(start, size); + mirror_size += size; + } + } + if (mirror_size) + pr_info("Memory: %lldM/%lldM mirrored memory\n", + mirror_size>>20, total_size>>20); +} + /* * Tell the kernel about the EFI memory map. This might include * more than the max 128 entries that can fit in the e820 legacy @@ -153,6 +174,9 @@ static void __init do_add_efi_memmap(void) case EFI_UNUSABLE_MEMORY: e820_type = E820_UNUSABLE; break; + case EFI_PERSISTENT_MEMORY: + e820_type = E820_PMEM; + break; default: /* * EFI_RESERVED_TYPE EFI_RUNTIME_SERVICES_CODE @@ -170,7 +194,7 @@ static void __init do_add_efi_memmap(void) int __init efi_memblock_x86_reserve_range(void) { struct efi_info *e = &boot_params.efi_info; - unsigned long pmap; + phys_addr_t pmap; if (efi_enabled(EFI_PARAVIRT)) return 0; @@ -185,7 +209,7 @@ int __init efi_memblock_x86_reserve_range(void) #else pmap = (e->efi_memmap | ((__u64)e->efi_memmap_hi << 32)); #endif - memmap.phys_map = (void *)pmap; + memmap.phys_map = pmap; memmap.nr_map = e->efi_memmap_size / e->efi_memdesc_size; memmap.desc_size = e->efi_memdesc_size; @@ -198,7 +222,7 @@ int __init efi_memblock_x86_reserve_range(void) return 0; } -static void __init print_efi_memmap(void) +void __init efi_print_memmap(void) { #ifdef EFI_DEBUG efi_memory_desc_t *md; @@ -500,7 +524,9 @@ void __init efi_init(void) return; if (efi_enabled(EFI_DBG)) - print_efi_memmap(); + efi_print_memmap(); + + efi_esrt_init(); } void __init efi_late_init(void) @@ -624,7 +650,7 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) static void __init save_runtime_map(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; void *tmp, *p, *q = NULL; int count = 0; @@ -679,6 +705,70 @@ out: } /* + * Iterate the EFI memory map in reverse order because the regions + * will be mapped top-down. The end result is the same as if we had + * mapped things forward, but doesn't require us to change the + * existing implementation of efi_map_region(). + */ +static inline void *efi_map_next_entry_reverse(void *entry) +{ + /* Initial call */ + if (!entry) + return memmap.map_end - memmap.desc_size; + + entry -= memmap.desc_size; + if (entry < memmap.map) + return NULL; + + return entry; +} + +/* + * efi_map_next_entry - Return the next EFI memory map descriptor + * @entry: Previous EFI memory map descriptor + * + * This is a helper function to iterate over the EFI memory map, which + * we do in different orders depending on the current configuration. + * + * To begin traversing the memory map @entry must be %NULL. + * + * Returns %NULL when we reach the end of the memory map. + */ +static void *efi_map_next_entry(void *entry) +{ + if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) { + /* + * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE + * config table feature requires us to map all entries + * in the same order as they appear in the EFI memory + * map. That is to say, entry N must have a lower + * virtual address than entry N+1. This is because the + * firmware toolchain leaves relative references in + * the code/data sections, which are split and become + * separate EFI memory regions. Mapping things + * out-of-order leads to the firmware accessing + * unmapped addresses. + * + * Since we need to map things this way whether or not + * the kernel actually makes use of + * EFI_PROPERTIES_TABLE, let's just switch to this + * scheme by default for 64-bit. + */ + return efi_map_next_entry_reverse(entry); + } + + /* Initial call */ + if (!entry) + return memmap.map; + + entry += memmap.desc_size; + if (entry >= memmap.map_end) + return NULL; + + return entry; +} + +/* * Map the efi memory ranges of the runtime services and update new_mmap with * virtual addresses. */ @@ -688,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift) unsigned long left = 0; efi_memory_desc_t *md; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + p = NULL; + while ((p = efi_map_next_entry(p))) { md = p; if (!(md->attribute & EFI_MEMORY_RUNTIME)) { #ifdef CONFIG_X86_64 @@ -722,7 +813,7 @@ static void * __init efi_map_regions(int *count, int *pg_shift) static void __init kexec_enter_virtual_mode(void) { -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE efi_memory_desc_t *md; void *p; @@ -926,24 +1017,6 @@ u32 efi_mem_type(unsigned long phys_addr) return 0; } -u64 efi_mem_attributes(unsigned long phys_addr) -{ - efi_memory_desc_t *md; - void *p; - - if (!efi_enabled(EFI_MEMMAP)) - return 0; - - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; - if ((md->phys_addr <= phys_addr) && - (phys_addr < (md->phys_addr + - (md->num_pages << EFI_PAGE_SHIFT)))) - return md->attribute; - } - return 0; -} - static int __init arch_parse_efi_cmdline(char *str) { if (!str) { @@ -953,8 +1026,6 @@ static int __init arch_parse_efi_cmdline(char *str) if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); - if (parse_option_str(str, "debug")) - set_bit(EFI_DBG, &efi.flags); return 0; } diff --git a/kernel/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/kernel/arch/x86/platform/intel-mid/device_libs/platform_wdt.c index 0b283d4d0..de734134b 100644 --- a/kernel/arch/x86/platform/intel-mid/device_libs/platform_wdt.c +++ b/kernel/arch/x86/platform/intel-mid/device_libs/platform_wdt.c @@ -27,6 +27,7 @@ static struct platform_device wdt_dev = { static int tangier_probe(struct platform_device *pdev) { int gsi; + struct irq_alloc_info info; struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; if (!pdata) @@ -34,8 +35,8 @@ static int tangier_probe(struct platform_device *pdev) /* IOAPIC builds identity mapping between GSI and IRQ on MID */ gsi = pdata->irq; - if (mp_set_gsi_attr(gsi, 1, 0, cpu_to_node(0)) || - mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC) <= 0) { + ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0); + if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) { dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", gsi); return -EINVAL; diff --git a/kernel/arch/x86/platform/intel-mid/intel-mid.c b/kernel/arch/x86/platform/intel-mid/intel-mid.c index 3005f0c89..1bbc21e2e 100644 --- a/kernel/arch/x86/platform/intel-mid/intel-mid.c +++ b/kernel/arch/x86/platform/intel-mid/intel-mid.c @@ -61,7 +61,7 @@ enum intel_mid_timer_options intel_mid_timer_options; /* intel_mid_ops to store sub arch ops */ -struct intel_mid_ops *intel_mid_ops; +static struct intel_mid_ops *intel_mid_ops; /* getter function for sub arch ops*/ static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT; enum intel_mid_cpu_type __intel_mid_cpu_chip; @@ -81,26 +81,34 @@ static unsigned long __init intel_mid_calibrate_tsc(void) return 0; } +static void __init intel_mid_setup_bp_timer(void) +{ + apbt_time_init(); + setup_boot_APIC_clock(); +} + static void __init intel_mid_time_init(void) { sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr); + switch (intel_mid_timer_options) { case INTEL_MID_TIMER_APBT_ONLY: break; case INTEL_MID_TIMER_LAPIC_APBT: - x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; + /* Use apbt and local apic */ + x86_init.timers.setup_percpu_clockev = intel_mid_setup_bp_timer; x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; - break; + return; default: if (!boot_cpu_has(X86_FEATURE_ARAT)) break; + /* Lapic only, no apbt */ x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock; x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock; return; } - /* we need at least one APB timer */ - pre_init_apic_IRQ0(); - apbt_time_init(); + + x86_init.timers.setup_percpu_clockev = apbt_time_init; } static void intel_mid_arch_setup(void) diff --git a/kernel/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/kernel/arch/x86/platform/intel-mid/intel_mid_vrtc.c index 32947ba0f..ee40fcb6e 100644 --- a/kernel/arch/x86/platform/intel-mid/intel_mid_vrtc.c +++ b/kernel/arch/x86/platform/intel-mid/intel_mid_vrtc.c @@ -173,5 +173,4 @@ static int __init intel_mid_device_create(void) return platform_device_register(&vrtc_device); } - -module_init(intel_mid_device_create); +device_initcall(intel_mid_device_create); diff --git a/kernel/arch/x86/platform/intel-mid/sfi.c b/kernel/arch/x86/platform/intel-mid/sfi.c index c14ad3477..5ee360a95 100644 --- a/kernel/arch/x86/platform/intel-mid/sfi.c +++ b/kernel/arch/x86/platform/intel-mid/sfi.c @@ -95,18 +95,16 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table) pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n", totallen, (u32)pentry->phys_addr, pentry->freq_hz, pentry->irq); - if (!pentry->irq) - continue; - mp_irq.type = MP_INTSRC; - mp_irq.irqtype = mp_INT; -/* triggering mode edge bit 2-3, active high polarity bit 0-1 */ - mp_irq.irqflag = 5; - mp_irq.srcbus = MP_BUS_ISA; - mp_irq.srcbusirq = pentry->irq; /* IRQ */ - mp_irq.dstapic = MP_APIC_ALL; - mp_irq.dstirq = pentry->irq; - mp_save_irq(&mp_irq); - mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC); + mp_irq.type = MP_INTSRC; + mp_irq.irqtype = mp_INT; + /* triggering mode edge bit 2-3, active high polarity bit 0-1 */ + mp_irq.irqflag = 5; + mp_irq.srcbus = MP_BUS_ISA; + mp_irq.srcbusirq = pentry->irq; /* IRQ */ + mp_irq.dstapic = MP_APIC_ALL; + mp_irq.dstirq = pentry->irq; + mp_save_irq(&mp_irq); + mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL); } return 0; @@ -177,7 +175,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table) mp_irq.dstapic = MP_APIC_ALL; mp_irq.dstirq = pentry->irq; mp_save_irq(&mp_irq); - mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC); + mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC, NULL); } return 0; } @@ -199,10 +197,9 @@ static int __init sfi_parse_gpio(struct sfi_table_header *table) num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry); pentry = (struct sfi_gpio_table_entry *)sb->pentry; - gpio_table = kmalloc(num * sizeof(*pentry), GFP_KERNEL); + gpio_table = kmemdup(pentry, num * sizeof(*pentry), GFP_KERNEL); if (!gpio_table) return -1; - memcpy(gpio_table, pentry, num * sizeof(*pentry)); gpio_num_entry = num; pr_debug("GPIO pin info:\n"); @@ -436,6 +433,7 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) struct devs_id *dev = NULL; int num, i, ret; int polarity; + struct irq_alloc_info info; sb = (struct sfi_table_simple *)table; num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry); @@ -469,9 +467,8 @@ static int __init sfi_parse_devs(struct sfi_table_header *table) polarity = 1; } - ret = mp_set_gsi_attr(irq, 1, polarity, NUMA_NO_NODE); - if (ret == 0) - ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC); + ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, polarity); + ret = mp_map_gsi_to_irq(irq, IOAPIC_MAP_ALLOC, &info); WARN_ON(ret < 0); } diff --git a/kernel/arch/x86/platform/intel/Makefile b/kernel/arch/x86/platform/intel/Makefile new file mode 100644 index 000000000..b878032fb --- /dev/null +++ b/kernel/arch/x86/platform/intel/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_IOSF_MBI) += iosf_mbi.o diff --git a/kernel/arch/x86/kernel/iosf_mbi.c b/kernel/arch/x86/platform/intel/iosf_mbi.c index 82f8d02f0..edf2c54bf 100644 --- a/kernel/arch/x86/kernel/iosf_mbi.c +++ b/kernel/arch/x86/platform/intel/iosf_mbi.c @@ -30,7 +30,9 @@ #define PCI_DEVICE_ID_BAYTRAIL 0x0F00 #define PCI_DEVICE_ID_BRASWELL 0x2280 #define PCI_DEVICE_ID_QUARK_X1000 0x0958 +#define PCI_DEVICE_ID_TANGIER 0x1170 +static struct pci_dev *mbi_pdev; static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -38,8 +40,6 @@ static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) return (op << 24) | (port << 16) | (offset << 8) | MBI_ENABLE; } -static struct pci_dev *mbi_pdev; /* one mbi device */ - static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) { int result; @@ -104,7 +104,7 @@ int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) unsigned long flags; int ret; - /*Access to the GFX unit is handled by GPU code */ + /* Access to the GFX unit is handled by GPU code */ if (port == BT_MBI_UNIT_GFX) { WARN_ON(1); return -EPERM; @@ -127,7 +127,7 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) unsigned long flags; int ret; - /*Access to the GFX unit is handled by GPU code */ + /* Access to the GFX unit is handled by GPU code */ if (port == BT_MBI_UNIT_GFX) { WARN_ON(1); return -EPERM; @@ -151,7 +151,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) unsigned long flags; int ret; - /*Access to the GFX unit is handled by GPU code */ + /* Access to the GFX unit is handled by GPU code */ if (port == BT_MBI_UNIT_GFX) { WARN_ON(1); return -EPERM; @@ -240,17 +240,17 @@ static void iosf_sideband_debug_init(void) /* mdr */ d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr); - if (IS_ERR_OR_NULL(d)) + if (!d) goto cleanup; /* mcrx */ - debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); - if (IS_ERR_OR_NULL(d)) + d = debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); + if (!d) goto cleanup; /* mcr - initiates mailbox tranaction */ - debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); - if (IS_ERR_OR_NULL(d)) + d = debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); + if (!d) goto cleanup; return; @@ -292,6 +292,7 @@ static const struct pci_device_id iosf_mbi_pci_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_TANGIER) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); @@ -314,10 +315,8 @@ static void __exit iosf_mbi_exit(void) iosf_debugfs_remove(); pci_unregister_driver(&iosf_mbi_pci_driver); - if (mbi_pdev) { - pci_dev_put(mbi_pdev); - mbi_pdev = NULL; - } + pci_dev_put(mbi_pdev); + mbi_pdev = NULL; } module_init(iosf_mbi_init); diff --git a/kernel/arch/x86/platform/sfi/sfi.c b/kernel/arch/x86/platform/sfi/sfi.c index 2a8a74f3b..6c7111bbd 100644 --- a/kernel/arch/x86/platform/sfi/sfi.c +++ b/kernel/arch/x86/platform/sfi/sfi.c @@ -25,8 +25,8 @@ #include <linux/init.h> #include <linux/sfi.h> #include <linux/io.h> -#include <linux/irqdomain.h> +#include <asm/irqdomain.h> #include <asm/io_apic.h> #include <asm/mpspec.h> #include <asm/setup.h> @@ -71,9 +71,6 @@ static int __init sfi_parse_cpus(struct sfi_table_header *table) #endif /* CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_IO_APIC -static struct irq_domain_ops sfi_ioapic_irqdomain_ops = { - .map = mp_irqdomain_map, -}; static int __init sfi_parse_ioapic(struct sfi_table_header *table) { @@ -82,7 +79,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table) int i, num; struct ioapic_domain_cfg cfg = { .type = IOAPIC_DOMAIN_STRICT, - .ops = &sfi_ioapic_irqdomain_ops, + .ops = &mp_ioapic_irqdomain_ops, }; sb = (struct sfi_table_simple *)table; diff --git a/kernel/arch/x86/platform/uv/uv_irq.c b/kernel/arch/x86/platform/uv/uv_irq.c index 0ce673645..e1c24631a 100644 --- a/kernel/arch/x86/platform/uv/uv_irq.c +++ b/kernel/arch/x86/platform/uv/uv_irq.c @@ -13,22 +13,37 @@ #include <linux/slab.h> #include <linux/irq.h> +#include <asm/irqdomain.h> #include <asm/apic.h> #include <asm/uv/uv_irq.h> #include <asm/uv/uv_hub.h> /* MMR offset and pnode of hub sourcing interrupts for a given irq */ -struct uv_irq_2_mmr_pnode{ - struct rb_node list; +struct uv_irq_2_mmr_pnode { unsigned long offset; int pnode; - int irq; }; -static DEFINE_SPINLOCK(uv_irq_lock); -static struct rb_root uv_irq_root; +static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info) +{ + unsigned long mmr_value; + struct uv_IO_APIC_route_entry *entry; + + BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != + sizeof(unsigned long)); + + mmr_value = 0; + entry = (struct uv_IO_APIC_route_entry *)&mmr_value; + entry->vector = cfg->vector; + entry->delivery_mode = apic->irq_delivery_mode; + entry->dest_mode = apic->irq_dest_mode; + entry->polarity = 0; + entry->trigger = 0; + entry->mask = 0; + entry->dest = cfg->dest_apicid; -static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool); + uv_write_global_mmr64(info->pnode, info->offset, mmr_value); +} static void uv_noop(struct irq_data *data) { } @@ -37,6 +52,23 @@ static void uv_ack_apic(struct irq_data *data) ack_APIC_irq(); } +static int +uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, + bool force) +{ + struct irq_data *parent = data->parent_data; + struct irq_cfg *cfg = irqd_cfg(data); + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0) { + uv_program_mmr(cfg, data->chip_data); + send_cleanup_vector(cfg); + } + + return ret; +} + static struct irq_chip uv_irq_chip = { .name = "UV-CORE", .irq_mask = uv_noop, @@ -45,189 +77,99 @@ static struct irq_chip uv_irq_chip = { .irq_set_affinity = uv_set_irq_affinity, }; -/* - * Add offset and pnode information of the hub sourcing interrupts to the - * rb tree for a specific irq. - */ -static int uv_set_irq_2_mmr_info(int irq, unsigned long offset, unsigned blade) +static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - struct rb_node **link = &uv_irq_root.rb_node; - struct rb_node *parent = NULL; - struct uv_irq_2_mmr_pnode *n; - struct uv_irq_2_mmr_pnode *e; - unsigned long irqflags; - - n = kmalloc_node(sizeof(struct uv_irq_2_mmr_pnode), GFP_KERNEL, - uv_blade_to_memory_nid(blade)); - if (!n) + struct uv_irq_2_mmr_pnode *chip_data; + struct irq_alloc_info *info = arg; + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + int ret; + + if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_UV) + return -EINVAL; + + chip_data = kmalloc_node(sizeof(*chip_data), GFP_KERNEL, + irq_data_get_node(irq_data)); + if (!chip_data) return -ENOMEM; - n->irq = irq; - n->offset = offset; - n->pnode = uv_blade_to_pnode(blade); - spin_lock_irqsave(&uv_irq_lock, irqflags); - /* Find the right place in the rbtree: */ - while (*link) { - parent = *link; - e = rb_entry(parent, struct uv_irq_2_mmr_pnode, list); - - if (unlikely(irq == e->irq)) { - /* irq entry exists */ - e->pnode = uv_blade_to_pnode(blade); - e->offset = offset; - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - kfree(n); - return 0; - } - - if (irq < e->irq) - link = &(*link)->rb_left; + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret >= 0) { + if (info->uv_limit == UV_AFFINITY_CPU) + irq_set_status_flags(virq, IRQ_NO_BALANCING); else - link = &(*link)->rb_right; + irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); + + chip_data->pnode = uv_blade_to_pnode(info->uv_blade); + chip_data->offset = info->uv_offset; + irq_domain_set_info(domain, virq, virq, &uv_irq_chip, chip_data, + handle_percpu_irq, NULL, info->uv_name); + } else { + kfree(chip_data); } - /* Insert the node into the rbtree. */ - rb_link_node(&n->list, parent, link); - rb_insert_color(&n->list, &uv_irq_root); - - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - return 0; + return ret; } -/* Retrieve offset and pnode information from the rb tree for a specific irq */ -int uv_irq_2_mmr_info(int irq, unsigned long *offset, int *pnode) +static void uv_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { - struct uv_irq_2_mmr_pnode *e; - struct rb_node *n; - unsigned long irqflags; - - spin_lock_irqsave(&uv_irq_lock, irqflags); - n = uv_irq_root.rb_node; - while (n) { - e = rb_entry(n, struct uv_irq_2_mmr_pnode, list); - - if (e->irq == irq) { - *offset = e->offset; - *pnode = e->pnode; - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - return 0; - } - - if (irq < e->irq) - n = n->rb_left; - else - n = n->rb_right; - } - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - return -1; + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + BUG_ON(nr_irqs != 1); + kfree(irq_data->chip_data); + irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); + irq_clear_status_flags(virq, IRQ_NO_BALANCING); + irq_domain_free_irqs_top(domain, virq, nr_irqs); } /* * Re-target the irq to the specified CPU and enable the specified MMR located * on the specified blade to allow the sending of MSIs to the specified CPU. */ -static int -arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade, - unsigned long mmr_offset, int limit) +static void uv_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) { - const struct cpumask *eligible_cpu = cpumask_of(cpu); - struct irq_cfg *cfg = irq_cfg(irq); - unsigned long mmr_value; - struct uv_IO_APIC_route_entry *entry; - int mmr_pnode, err; - unsigned int dest; - - BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != - sizeof(unsigned long)); - - err = assign_irq_vector(irq, cfg, eligible_cpu); - if (err != 0) - return err; - - err = apic->cpu_mask_to_apicid_and(eligible_cpu, eligible_cpu, &dest); - if (err != 0) - return err; - - if (limit == UV_AFFINITY_CPU) - irq_set_status_flags(irq, IRQ_NO_BALANCING); - else - irq_set_status_flags(irq, IRQ_MOVE_PCNTXT); - - irq_set_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq, - irq_name); - - mmr_value = 0; - entry = (struct uv_IO_APIC_route_entry *)&mmr_value; - entry->vector = cfg->vector; - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->polarity = 0; - entry->trigger = 0; - entry->mask = 0; - entry->dest = dest; - - mmr_pnode = uv_blade_to_pnode(mmr_blade); - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); - - if (cfg->move_in_progress) - send_cleanup_vector(cfg); - - return irq; + uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); } /* * Disable the specified MMR located on the specified blade so that MSIs are * longer allowed to be sent. */ -static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset) +static void uv_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) { unsigned long mmr_value; struct uv_IO_APIC_route_entry *entry; - BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != - sizeof(unsigned long)); - mmr_value = 0; entry = (struct uv_IO_APIC_route_entry *)&mmr_value; entry->mask = 1; - - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); + uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); } -static int -uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, - bool force) -{ - struct irq_cfg *cfg = irqd_cfg(data); - unsigned int dest; - unsigned long mmr_value, mmr_offset; - struct uv_IO_APIC_route_entry *entry; - int mmr_pnode; - - if (apic_set_affinity(data, mask, &dest)) - return -1; - - mmr_value = 0; - entry = (struct uv_IO_APIC_route_entry *)&mmr_value; - - entry->vector = cfg->vector; - entry->delivery_mode = apic->irq_delivery_mode; - entry->dest_mode = apic->irq_dest_mode; - entry->polarity = 0; - entry->trigger = 0; - entry->mask = 0; - entry->dest = dest; - - /* Get previously stored MMR and pnode of hub sourcing interrupts */ - if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode)) - return -1; - - uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value); +static const struct irq_domain_ops uv_domain_ops = { + .alloc = uv_domain_alloc, + .free = uv_domain_free, + .activate = uv_domain_activate, + .deactivate = uv_domain_deactivate, +}; - if (cfg->move_in_progress) - send_cleanup_vector(cfg); +static struct irq_domain *uv_get_irq_domain(void) +{ + static struct irq_domain *uv_domain; + static DEFINE_MUTEX(uv_lock); + + mutex_lock(&uv_lock); + if (uv_domain == NULL) { + uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL); + if (uv_domain) + uv_domain->parent = x86_vector_domain; + } + mutex_unlock(&uv_lock); - return IRQ_SET_MASK_OK_NOCOPY; + return uv_domain; } /* @@ -238,19 +180,21 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, unsigned long mmr_offset, int limit) { - int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade)); + struct irq_alloc_info info; + struct irq_domain *domain = uv_get_irq_domain(); - if (!irq) - return -EBUSY; + if (!domain) + return -ENOMEM; - ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, - limit); - if (ret == irq) - uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); - else - irq_free_hwirq(irq); + init_irq_alloc_info(&info, cpumask_of(cpu)); + info.type = X86_IRQ_ALLOC_TYPE_UV; + info.uv_limit = limit; + info.uv_blade = mmr_blade; + info.uv_offset = mmr_offset; + info.uv_name = irq_name; - return ret; + return irq_domain_alloc_irqs(domain, 1, + uv_blade_to_memory_nid(mmr_blade), &info); } EXPORT_SYMBOL_GPL(uv_setup_irq); @@ -263,26 +207,6 @@ EXPORT_SYMBOL_GPL(uv_setup_irq); */ void uv_teardown_irq(unsigned int irq) { - struct uv_irq_2_mmr_pnode *e; - struct rb_node *n; - unsigned long irqflags; - - spin_lock_irqsave(&uv_irq_lock, irqflags); - n = uv_irq_root.rb_node; - while (n) { - e = rb_entry(n, struct uv_irq_2_mmr_pnode, list); - if (e->irq == irq) { - arch_disable_uv_irq(e->pnode, e->offset); - rb_erase(n, &uv_irq_root); - kfree(e); - break; - } - if (irq < e->irq) - n = n->rb_left; - else - n = n->rb_right; - } - spin_unlock_irqrestore(&uv_irq_lock, irqflags); - irq_free_hwirq(irq); + irq_domain_free_irqs(irq, 1); } EXPORT_SYMBOL_GPL(uv_teardown_irq); diff --git a/kernel/arch/x86/platform/uv/uv_nmi.c b/kernel/arch/x86/platform/uv/uv_nmi.c index 7488cafab..327f21c3b 100644 --- a/kernel/arch/x86/platform/uv/uv_nmi.c +++ b/kernel/arch/x86/platform/uv/uv_nmi.c @@ -104,7 +104,7 @@ static int param_set_local64(const char *val, const struct kernel_param *kp) return 0; } -static struct kernel_param_ops param_ops_local64 = { +static const struct kernel_param_ops param_ops_local64 = { .get = param_get_local64, .set = param_set_local64, }; @@ -376,38 +376,42 @@ static void uv_nmi_wait(int master) atomic_read(&uv_nmi_cpus_in_nmi), num_online_cpus()); } +/* Dump Instruction Pointer header */ static void uv_nmi_dump_cpu_ip_hdr(void) { - printk(KERN_DEFAULT - "\nUV: %4s %6s %-32s %s (Note: PID 0 not listed)\n", + pr_info("\nUV: %4s %6s %-32s %s (Note: PID 0 not listed)\n", "CPU", "PID", "COMMAND", "IP"); } +/* Dump Instruction Pointer info */ static void uv_nmi_dump_cpu_ip(int cpu, struct pt_regs *regs) { - printk(KERN_DEFAULT "UV: %4d %6d %-32.32s ", - cpu, current->pid, current->comm); - + pr_info("UV: %4d %6d %-32.32s ", cpu, current->pid, current->comm); printk_address(regs->ip); } -/* Dump this cpu's state */ +/* + * Dump this CPU's state. If action was set to "kdump" and the crash_kexec + * failed, then we provide "dump" as an alternate action. Action "dump" now + * also includes the show "ips" (instruction pointers) action whereas the + * action "ips" only displays instruction pointers for the non-idle CPU's. + * This is an abbreviated form of the "ps" command. + */ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs) { const char *dots = " ................................. "; - if (uv_nmi_action_is("ips")) { - if (cpu == 0) - uv_nmi_dump_cpu_ip_hdr(); + if (cpu == 0) + uv_nmi_dump_cpu_ip_hdr(); - if (current->pid != 0) - uv_nmi_dump_cpu_ip(cpu, regs); + if (current->pid != 0 || !uv_nmi_action_is("ips")) + uv_nmi_dump_cpu_ip(cpu, regs); - } else if (uv_nmi_action_is("dump")) { - printk(KERN_DEFAULT - "UV:%sNMI process trace for CPU %d\n", dots, cpu); + if (uv_nmi_action_is("dump")) { + pr_info("UV:%sNMI process trace for CPU %d\n", dots, cpu); show_regs(regs); } + this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE); } @@ -469,8 +473,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master) uv_nmi_trigger_dump(tcpu); } if (ignored) - printk(KERN_DEFAULT "UV: %d CPUs ignored NMI\n", - ignored); + pr_alert("UV: %d CPUs ignored NMI\n", ignored); console_loglevel = saved_console_loglevel; pr_alert("UV: process trace complete\n"); @@ -492,8 +495,9 @@ static void uv_nmi_touch_watchdogs(void) touch_nmi_watchdog(); } -#if defined(CONFIG_KEXEC) static atomic_t uv_nmi_kexec_failed; + +#if defined(CONFIG_KEXEC_CORE) static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) { /* Call crash to dump system state */ @@ -502,10 +506,9 @@ static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) crash_kexec(regs); pr_emerg("UV: crash_kexec unexpectedly returned, "); + atomic_set(&uv_nmi_kexec_failed, 1); if (!kexec_crash_image) { pr_cont("crash kernel not loaded\n"); - atomic_set(&uv_nmi_kexec_failed, 1); - uv_nmi_sync_exit(1); return; } pr_cont("kexec busy, stalling cpus while waiting\n"); @@ -514,18 +517,16 @@ static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) /* If crash exec fails the slaves should return, otherwise stall */ while (atomic_read(&uv_nmi_kexec_failed) == 0) mdelay(10); - - /* Crash kernel most likely not loaded, return in an orderly fashion */ - uv_nmi_sync_exit(0); } -#else /* !CONFIG_KEXEC */ +#else /* !CONFIG_KEXEC_CORE */ static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) { if (master) pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n"); + atomic_set(&uv_nmi_kexec_failed, 1); } -#endif /* !CONFIG_KEXEC */ +#endif /* !CONFIG_KEXEC_CORE */ #ifdef CONFIG_KGDB #ifdef CONFIG_KGDB_KDB @@ -613,9 +614,14 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) master = (atomic_read(&uv_nmi_cpu) == cpu); /* If NMI action is "kdump", then attempt to do it */ - if (uv_nmi_action_is("kdump")) + if (uv_nmi_action_is("kdump")) { uv_nmi_kdump(cpu, master, regs); + /* Unexpected return, revert action to "dump" */ + if (master) + strncpy(uv_nmi_action, "dump", strlen(uv_nmi_action)); + } + /* Pause as all cpus enter the NMI handler */ uv_nmi_wait(master); @@ -640,6 +646,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) atomic_set(&uv_nmi_cpus_in_nmi, -1); atomic_set(&uv_nmi_cpu, -1); atomic_set(&uv_in_nmi, 0); + atomic_set(&uv_nmi_kexec_failed, 0); } uv_nmi_touch_watchdogs(); diff --git a/kernel/arch/x86/platform/uv/uv_time.c b/kernel/arch/x86/platform/uv/uv_time.c index a718fe0d2..5e0b12262 100644 --- a/kernel/arch/x86/platform/uv/uv_time.c +++ b/kernel/arch/x86/platform/uv/uv_time.c @@ -32,8 +32,7 @@ static cycle_t uv_read_rtc(struct clocksource *cs); static int uv_rtc_next_event(unsigned long, struct clock_event_device *); -static void uv_rtc_timer_setup(enum clock_event_mode, - struct clock_event_device *); +static int uv_rtc_shutdown(struct clock_event_device *evt); static struct clocksource clocksource_uv = { .name = RTC_NAME, @@ -44,14 +43,14 @@ static struct clocksource clocksource_uv = { }; static struct clock_event_device clock_event_device_uv = { - .name = RTC_NAME, - .features = CLOCK_EVT_FEAT_ONESHOT, - .shift = 20, - .rating = 400, - .irq = -1, - .set_next_event = uv_rtc_next_event, - .set_mode = uv_rtc_timer_setup, - .event_handler = NULL, + .name = RTC_NAME, + .features = CLOCK_EVT_FEAT_ONESHOT, + .shift = 20, + .rating = 400, + .irq = -1, + .set_next_event = uv_rtc_next_event, + .set_state_shutdown = uv_rtc_shutdown, + .event_handler = NULL, }; static DEFINE_PER_CPU(struct clock_event_device, cpu_ced); @@ -326,24 +325,14 @@ static int uv_rtc_next_event(unsigned long delta, } /* - * Setup the RTC timer in oneshot mode + * Shutdown the RTC timer */ -static void uv_rtc_timer_setup(enum clock_event_mode mode, - struct clock_event_device *evt) +static int uv_rtc_shutdown(struct clock_event_device *evt) { int ced_cpu = cpumask_first(evt->cpumask); - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - case CLOCK_EVT_MODE_ONESHOT: - case CLOCK_EVT_MODE_RESUME: - /* Nothing to do here yet */ - break; - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - uv_rtc_unset_timer(ced_cpu, 1); - break; - } + uv_rtc_unset_timer(ced_cpu, 1); + return 0; } static void uv_rtc_interrupt(void) diff --git a/kernel/arch/x86/power/cpu.c b/kernel/arch/x86/power/cpu.c index bf9384488..9ab52791f 100644 --- a/kernel/arch/x86/power/cpu.c +++ b/kernel/arch/x86/power/cpu.c @@ -18,10 +18,9 @@ #include <asm/mtrr.h> #include <asm/page.h> #include <asm/mce.h> -#include <asm/xcr.h> #include <asm/suspend.h> +#include <asm/fpu/internal.h> #include <asm/debugreg.h> -#include <asm/fpu-internal.h> /* pcntxt_mask */ #include <asm/cpu.h> #include <asm/mmu_context.h> @@ -156,6 +155,8 @@ static void fix_processor_context(void) #endif load_TR_desc(); /* This does ltr */ load_mm_ldt(current->active_mm); /* This does lldt */ + + fpu__resume_cpu(); } /** @@ -222,12 +223,6 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base); #endif - /* - * restore XCR0 for xsave capable cpu's. - */ - if (cpu_has_xsave) - xsetbv(XCR_XFEATURE_ENABLED_MASK, pcntxt_mask); - fix_processor_context(); do_fpu_end(); diff --git a/kernel/arch/x86/power/hibernate_asm_64.S b/kernel/arch/x86/power/hibernate_asm_64.S index 3c4469a7a..e2386cb4e 100644 --- a/kernel/arch/x86/power/hibernate_asm_64.S +++ b/kernel/arch/x86/power/hibernate_asm_64.S @@ -78,9 +78,9 @@ ENTRY(restore_image) /* code below has been relocated to a safe page */ ENTRY(core_restore_code) -loop: +.Lloop: testq %rdx, %rdx - jz done + jz .Ldone /* get addresses from the pbe and copy the page */ movq pbe_address(%rdx), %rsi @@ -91,8 +91,8 @@ loop: /* progress to the next pbe */ movq pbe_next(%rdx), %rdx - jmp loop -done: + jmp .Lloop +.Ldone: /* jump to the restore_registers address from the image header */ jmpq *%rax /* diff --git a/kernel/arch/x86/ras/Kconfig b/kernel/arch/x86/ras/Kconfig new file mode 100644 index 000000000..df280da34 --- /dev/null +++ b/kernel/arch/x86/ras/Kconfig @@ -0,0 +1,9 @@ +config AMD_MCE_INJ + tristate "Simple MCE injection interface for AMD processors" + depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB + default n + help + This is a simple debugfs interface to inject MCEs and test different + aspects of the MCE handling code. + + WARNING: Do not even assume this interface is staying stable! diff --git a/kernel/arch/x86/ras/Makefile b/kernel/arch/x86/ras/Makefile new file mode 100644 index 000000000..dd2c98b84 --- /dev/null +++ b/kernel/arch/x86/ras/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_AMD_MCE_INJ) += mce_amd_inj.o + diff --git a/kernel/arch/x86/ras/mce_amd_inj.c b/kernel/arch/x86/ras/mce_amd_inj.c new file mode 100644 index 000000000..55d38cfa4 --- /dev/null +++ b/kernel/arch/x86/ras/mce_amd_inj.c @@ -0,0 +1,464 @@ +/* + * A simple MCE injection facility for testing different aspects of the RAS + * code. This driver should be built as module so that it can be loaded + * on production kernels for testing purposes. + * + * This file may be distributed under the terms of the GNU General Public + * License version 2. + * + * Copyright (c) 2010-15: Borislav Petkov <bp@alien8.de> + * Advanced Micro Devices Inc. + */ + +#include <linux/kobject.h> +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/string.h> +#include <linux/uaccess.h> +#include <linux/pci.h> + +#include <asm/mce.h> +#include <asm/amd_nb.h> +#include <asm/irq_vectors.h> + +#include "../kernel/cpu/mcheck/mce-internal.h" + +/* + * Collect all the MCi_XXX settings + */ +static struct mce i_mce; +static struct dentry *dfs_inj; + +static u8 n_banks; + +#define MAX_FLAG_OPT_SIZE 3 +#define NBCFG 0x44 + +enum injection_type { + SW_INJ = 0, /* SW injection, simply decode the error */ + HW_INJ, /* Trigger a #MC */ + DFR_INT_INJ, /* Trigger Deferred error interrupt */ + THR_INT_INJ, /* Trigger threshold interrupt */ + N_INJ_TYPES, +}; + +static const char * const flags_options[] = { + [SW_INJ] = "sw", + [HW_INJ] = "hw", + [DFR_INT_INJ] = "df", + [THR_INT_INJ] = "th", + NULL +}; + +/* Set default injection to SW_INJ */ +static enum injection_type inj_type = SW_INJ; + +#define MCE_INJECT_SET(reg) \ +static int inj_##reg##_set(void *data, u64 val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + m->reg = val; \ + return 0; \ +} + +MCE_INJECT_SET(status); +MCE_INJECT_SET(misc); +MCE_INJECT_SET(addr); + +#define MCE_INJECT_GET(reg) \ +static int inj_##reg##_get(void *data, u64 *val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + *val = m->reg; \ + return 0; \ +} + +MCE_INJECT_GET(status); +MCE_INJECT_GET(misc); +MCE_INJECT_GET(addr); + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); + +/* + * Caller needs to be make sure this cpu doesn't disappear + * from under us, i.e.: get_cpu/put_cpu. + */ +static int toggle_hw_mce_inject(unsigned int cpu, bool enable) +{ + u32 l, h; + int err; + + err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); + if (err) { + pr_err("%s: error reading HWCR\n", __func__); + return err; + } + + enable ? (l |= BIT(18)) : (l &= ~BIT(18)); + + err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); + if (err) + pr_err("%s: error writing HWCR\n", __func__); + + return err; +} + +static int __set_inj(const char *buf) +{ + int i; + + for (i = 0; i < N_INJ_TYPES; i++) { + if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { + inj_type = i; + return 0; + } + } + return -EINVAL; +} + +static ssize_t flags_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE]; + int n; + + n = sprintf(buf, "%s\n", flags_options[inj_type]); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static ssize_t flags_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE], *__buf; + int err; + + if (cnt > MAX_FLAG_OPT_SIZE) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt - 1] = 0; + + /* strip whitespace */ + __buf = strstrip(buf); + + err = __set_inj(__buf); + if (err) { + pr_err("%s: Invalid flags value: %s\n", __func__, __buf); + return err; + } + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations flags_fops = { + .read = flags_read, + .write = flags_write, + .llseek = generic_file_llseek, +}; + +/* + * On which CPU to inject? + */ +MCE_INJECT_GET(extcpu); + +static int inj_extcpu_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= nr_cpu_ids || !cpu_online(val)) { + pr_err("%s: Invalid CPU: %llu\n", __func__, val); + return -EINVAL; + } + m->extcpu = val; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); + +static void trigger_mce(void *info) +{ + asm volatile("int $18"); +} + +static void trigger_dfr_int(void *info) +{ + asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); +} + +static void trigger_thr_int(void *info) +{ + asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); +} + +static u32 get_nbc_for_node(int node_id) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + u32 cores_per_node; + + cores_per_node = c->x86_max_cores / amd_get_nodes_per_socket(); + + return cores_per_node * node_id; +} + +static void toggle_nb_mca_mst_cpu(u16 nid) +{ + struct pci_dev *F3 = node_to_amd_nb(nid)->misc; + u32 val; + int err; + + if (!F3) + return; + + err = pci_read_config_dword(F3, NBCFG, &val); + if (err) { + pr_err("%s: Error reading F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); + return; + } + + if (val & BIT(27)) + return; + + pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", + __func__); + + val |= BIT(27); + err = pci_write_config_dword(F3, NBCFG, val); + if (err) + pr_err("%s: Error writing F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); +} + +static void do_inject(void) +{ + u64 mcg_status = 0; + unsigned int cpu = i_mce.extcpu; + u8 b = i_mce.bank; + + if (i_mce.misc) + i_mce.status |= MCI_STATUS_MISCV; + + if (inj_type == SW_INJ) { + mce_inject_log(&i_mce); + return; + } + + /* prep MCE global settings for the injection */ + mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; + + if (!(i_mce.status & MCI_STATUS_PCC)) + mcg_status |= MCG_STATUS_RIPV; + + /* + * Ensure necessary status bits for deferred errors: + * - MCx_STATUS[Deferred]: make sure it is a deferred error + * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC + */ + if (inj_type == DFR_INT_INJ) { + i_mce.status |= MCI_STATUS_DEFERRED; + i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + } + + /* + * For multi node CPUs, logging and reporting of bank 4 errors happens + * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for + * Fam10h and later BKDGs. + */ + if (static_cpu_has(X86_FEATURE_AMD_DCM) && b == 4) { + toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); + cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + } + + get_online_cpus(); + if (!cpu_online(cpu)) + goto err; + + toggle_hw_mce_inject(cpu, true); + + wrmsr_on_cpu(cpu, MSR_IA32_MCG_STATUS, + (u32)mcg_status, (u32)(mcg_status >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_STATUS(b), + (u32)i_mce.status, (u32)(i_mce.status >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_ADDR(b), + (u32)i_mce.addr, (u32)(i_mce.addr >> 32)); + + wrmsr_on_cpu(cpu, MSR_IA32_MCx_MISC(b), + (u32)i_mce.misc, (u32)(i_mce.misc >> 32)); + + toggle_hw_mce_inject(cpu, false); + + switch (inj_type) { + case DFR_INT_INJ: + smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); + break; + case THR_INT_INJ: + smp_call_function_single(cpu, trigger_thr_int, NULL, 0); + break; + default: + smp_call_function_single(cpu, trigger_mce, NULL, 0); + } + +err: + put_online_cpus(); + +} + +/* + * This denotes into which bank we're injecting and triggers + * the injection, at the same time. + */ +static int inj_bank_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= n_banks) { + pr_err("Non-existent MCE bank: %llu\n", val); + return -EINVAL; + } + + m->bank = val; + do_inject(); + + return 0; +} + +MCE_INJECT_GET(bank); + +DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); + +static const char readme_msg[] = +"Description of the files and their usages:\n" +"\n" +"Note1: i refers to the bank number below.\n" +"Note2: See respective BKDGs for the exact bit definitions of the files below\n" +"as they mirror the hardware registers.\n" +"\n" +"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" +"\t attributes of the error which caused the MCE.\n" +"\n" +"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" +"\t used for error thresholding purposes and its validity is indicated by\n" +"\t MCi_STATUS[MiscV].\n" +"\n" +"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" +"\t associated with the error.\n" +"\n" +"cpu:\t The CPU to inject the error on.\n" +"\n" +"bank:\t Specify the bank you want to inject the error into: the number of\n" +"\t banks in a processor varies and is family/model-specific, therefore, the\n" +"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" +"\t injection.\n" +"\n" +"flags:\t Injection type to be performed. Writing to this file will trigger a\n" +"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" +"\t for AMD processors.\n" +"\n" +"\t Allowed error injection types:\n" +"\t - \"sw\": Software error injection. Decode error to a human-readable \n" +"\t format only. Safe to use.\n" +"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" +"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" +"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" +"\t before injecting.\n" +"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" +"\t error APIC interrupt handler to handle the error if the feature is \n" +"\t is present in hardware. \n" +"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" +"\t APIC interrupt handler to handle the error. \n" +"\n"; + +static ssize_t +inj_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 readme_fops = { + .read = inj_readme_read, +}; + +static struct dfs_node { + char *name; + struct dentry *d; + const struct file_operations *fops; + umode_t perm; +} dfs_fls[] = { + { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, +}; + +static int __init init_mce_inject(void) +{ + int i; + u64 cap; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + n_banks = cap & MCG_BANKCNT_MASK; + + dfs_inj = debugfs_create_dir("mce-inject", NULL); + if (!dfs_inj) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { + dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, + dfs_fls[i].perm, + dfs_inj, + &i_mce, + dfs_fls[i].fops); + + if (!dfs_fls[i].d) + goto err_dfs_add; + } + + return 0; + +err_dfs_add: + while (--i >= 0) + debugfs_remove(dfs_fls[i].d); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; + + return -ENOMEM; +} + +static void __exit exit_mce_inject(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) + debugfs_remove(dfs_fls[i].d); + + memset(&dfs_fls, 0, sizeof(dfs_fls)); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; +} +module_init(init_mce_inject); +module_exit(exit_mce_inject); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Borislav Petkov <bp@alien8.de>"); +MODULE_AUTHOR("AMD Inc."); +MODULE_DESCRIPTION("MCE injection facility for RAS testing"); diff --git a/kernel/arch/x86/um/Makefile b/kernel/arch/x86/um/Makefile index acb384d24..a8fecc226 100644 --- a/kernel/arch/x86/um/Makefile +++ b/kernel/arch/x86/um/Makefile @@ -26,7 +26,7 @@ else obj-y += syscalls_64.o vdso/ -subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../lib/thunk_64.o \ +subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \ ../lib/rwsem.o endif diff --git a/kernel/arch/x86/um/asm/barrier.h b/kernel/arch/x86/um/asm/barrier.h index 7e8a1a650..755481f14 100644 --- a/kernel/arch/x86/um/asm/barrier.h +++ b/kernel/arch/x86/um/asm/barrier.h @@ -39,22 +39,10 @@ #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() -#define set_mb(var, value) do { var = value; barrier(); } while (0) + +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0) #define read_barrier_depends() do { } while (0) #define smp_read_barrier_depends() do { } while (0) -/* - * Stop RDTSC speculation. This is needed when you need to use RDTSC - * (or get_cycles or vread that possibly accesses the TSC) in a defined - * code region. - * - * (Could use an alternative three way for this if there was one.) - */ -static inline void rdtsc_barrier(void) -{ - alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, - "lfence", X86_FEATURE_LFENCE_RDTSC); -} - #endif diff --git a/kernel/arch/x86/um/asm/checksum.h b/kernel/arch/x86/um/asm/checksum.h index 4b181b744..ee940185e 100644 --- a/kernel/arch/x86/um/asm/checksum.h +++ b/kernel/arch/x86/um/asm/checksum.h @@ -3,6 +3,7 @@ #include <linux/string.h> #include <linux/in6.h> +#include <linux/uaccess.h> /* * computes the checksum of a memory block at buff, length len, diff --git a/kernel/arch/x86/um/asm/elf.h b/kernel/arch/x86/um/asm/elf.h index 0a656b727..548197212 100644 --- a/kernel/arch/x86/um/asm/elf.h +++ b/kernel/arch/x86/um/asm/elf.h @@ -200,8 +200,6 @@ typedef elf_greg_t elf_gregset_t[ELF_NGREG]; typedef struct user_i387_struct elf_fpregset_t; -#define task_pt_regs(t) (&(t)->thread.regs) - struct task_struct; extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu); diff --git a/kernel/arch/x86/um/asm/processor.h b/kernel/arch/x86/um/asm/processor.h index 2a206d2b1..233ee09c1 100644 --- a/kernel/arch/x86/um/asm/processor.h +++ b/kernel/arch/x86/um/asm/processor.h @@ -28,6 +28,8 @@ static inline void rep_nop(void) #define cpu_relax() rep_nop() #define cpu_relax_lowlatency() cpu_relax() +#define task_pt_regs(t) (&(t)->thread.regs) + #include <asm/processor-generic.h> #endif diff --git a/kernel/arch/x86/um/asm/segment.h b/kernel/arch/x86/um/asm/segment.h index 45183fcd1..41dd5e1f3 100644 --- a/kernel/arch/x86/um/asm/segment.h +++ b/kernel/arch/x86/um/asm/segment.h @@ -7,4 +7,12 @@ extern int host_gdt_entry_tls_min; #define GDT_ENTRY_TLS_MIN host_gdt_entry_tls_min #define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) +typedef struct { + unsigned long seg; +} mm_segment_t; + +#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) +#define KERNEL_DS MAKE_MM_SEG(~0UL) +#define USER_DS MAKE_MM_SEG(TASK_SIZE) + #endif diff --git a/kernel/arch/x86/um/asm/syscall.h b/kernel/arch/x86/um/asm/syscall.h index 9fe77b7b5..81d6562ce 100644 --- a/kernel/arch/x86/um/asm/syscall.h +++ b/kernel/arch/x86/um/asm/syscall.h @@ -3,6 +3,10 @@ #include <uapi/linux/audit.h> +typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, + unsigned long, unsigned long, + unsigned long, unsigned long); + static inline int syscall_get_arch(void) { #ifdef CONFIG_X86_32 diff --git a/kernel/arch/x86/um/ldt.c b/kernel/arch/x86/um/ldt.c index 5c0b711d2..836a1eb5d 100644 --- a/kernel/arch/x86/um/ldt.c +++ b/kernel/arch/x86/um/ldt.c @@ -6,12 +6,16 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/uaccess.h> #include <asm/unistd.h> #include <os.h> #include <skas.h> #include <sysdep/tls.h> -extern int modify_ldt(int func, void *ptr, unsigned long bytecount); +static inline int modify_ldt (int func, void *ptr, unsigned long bytecount) +{ + return syscall(__NR_modify_ldt, func, ptr, bytecount); +} static long write_ldt_entry(struct mm_id *mm_idp, int func, struct user_desc *desc, void **addr, int done) diff --git a/kernel/arch/x86/um/mem_32.c b/kernel/arch/x86/um/mem_32.c index f40281e5d..744afdc18 100644 --- a/kernel/arch/x86/um/mem_32.c +++ b/kernel/arch/x86/um/mem_32.c @@ -7,8 +7,7 @@ */ #include <linux/mm.h> -#include <asm/page.h> -#include <asm/mman.h> +#include <asm/elf.h> static struct vm_area_struct gate_vma; diff --git a/kernel/arch/x86/um/mem_64.c b/kernel/arch/x86/um/mem_64.c index f8fecaddc..7642e2e2a 100644 --- a/kernel/arch/x86/um/mem_64.c +++ b/kernel/arch/x86/um/mem_64.c @@ -1,6 +1,5 @@ #include <linux/mm.h> -#include <asm/page.h> -#include <asm/mman.h> +#include <asm/elf.h> const char *arch_vma_name(struct vm_area_struct *vma) { diff --git a/kernel/arch/x86/um/ptrace_32.c b/kernel/arch/x86/um/ptrace_32.c index ce3dd4f36..a29756f2d 100644 --- a/kernel/arch/x86/um/ptrace_32.c +++ b/kernel/arch/x86/um/ptrace_32.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/sched.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> #include <skas.h> extern int arch_switch_tls(struct task_struct *to); diff --git a/kernel/arch/x86/um/ptrace_64.c b/kernel/arch/x86/um/ptrace_64.c index 3b52bf0b4..a629694ee 100644 --- a/kernel/arch/x86/um/ptrace_64.c +++ b/kernel/arch/x86/um/ptrace_64.c @@ -11,6 +11,7 @@ #define __FRAME_OFFSETS #include <asm/ptrace.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> /* * determines which flags the user has access to. diff --git a/kernel/arch/x86/um/shared/sysdep/tls.h b/kernel/arch/x86/um/shared/sysdep/tls.h index 27cce00c6..a682db13d 100644 --- a/kernel/arch/x86/um/shared/sysdep/tls.h +++ b/kernel/arch/x86/um/shared/sysdep/tls.h @@ -1,7 +1,7 @@ #ifndef _SYSDEP_TLS_H #define _SYSDEP_TLS_H -# ifndef __KERNEL__ +#ifdef __UM_HOST__ /* Change name to avoid conflicts with the original one from <asm/ldt.h>, which * may be named user_desc (but in 2.4 and in header matching its API was named @@ -22,11 +22,11 @@ typedef struct um_dup_user_desc { #endif } user_desc_t; -# else /* __KERNEL__ */ +#else /* __UM_HOST__ */ typedef struct user_desc user_desc_t; -# endif /* __KERNEL__ */ +#endif /* __UM_HOST__ */ extern int os_set_thread_area(user_desc_t *info, int pid); extern int os_get_thread_area(user_desc_t *info, int pid); diff --git a/kernel/arch/x86/um/signal.c b/kernel/arch/x86/um/signal.c index 592491d1d..14fcd01ed 100644 --- a/kernel/arch/x86/um/signal.c +++ b/kernel/arch/x86/um/signal.c @@ -211,7 +211,7 @@ static int copy_sc_from_user(struct pt_regs *regs, if (err) return 1; - err = convert_fxsr_from_user(&fpx, sc.fpstate); + err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate); if (err) return 1; @@ -227,7 +227,7 @@ static int copy_sc_from_user(struct pt_regs *regs, { struct user_i387_struct fp; - err = copy_from_user(&fp, sc.fpstate, + err = copy_from_user(&fp, (void *)sc.fpstate, sizeof(struct user_i387_struct)); if (err) return 1; @@ -291,7 +291,7 @@ static int copy_sc_to_user(struct sigcontext __user *to, #endif #undef PUTREG sc.oldmask = mask; - sc.fpstate = to_fp; + sc.fpstate = (unsigned long)to_fp; err = copy_to_user(to, &sc, sizeof(struct sigcontext)); if (err) @@ -468,12 +468,10 @@ long sys_sigreturn(void) struct sigframe __user *frame = (struct sigframe __user *)(sp - 8); sigset_t set; struct sigcontext __user *sc = &frame->sc; - unsigned long __user *oldmask = &sc->oldmask; - unsigned long __user *extramask = frame->extramask; int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long); - if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) || - copy_from_user(&set.sig[1], extramask, sig_size)) + if (copy_from_user(&set.sig[0], &sc->oldmask, sizeof(set.sig[0])) || + copy_from_user(&set.sig[1], frame->extramask, sig_size)) goto segfault; set_current_blocked(&set); @@ -505,6 +503,7 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, { struct rt_sigframe __user *frame; int err = 0, sig = ksig->sig; + unsigned long fp_to; frame = (struct rt_sigframe __user *) round_down(stack_top - sizeof(struct rt_sigframe), 16); @@ -526,7 +525,10 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs)); err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs, set->sig[0]); - err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate); + + fp_to = (unsigned long)&frame->fpstate; + + err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); @@ -541,7 +543,8 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, */ /* x86-64 should always use SA_RESTORER. */ if (ksig->ka.sa.sa_flags & SA_RESTORER) - err |= __put_user(ksig->ka.sa.sa_restorer, &frame->pretcode); + err |= __put_user((void *)ksig->ka.sa.sa_restorer, + &frame->pretcode); else /* could use a vstub here */ return err; diff --git a/kernel/arch/x86/um/stub_32.S b/kernel/arch/x86/um/stub_32.S index b972649d3..98816804e 100644 --- a/kernel/arch/x86/um/stub_32.S +++ b/kernel/arch/x86/um/stub_32.S @@ -1,6 +1,5 @@ #include <as-layout.h> - .globl syscall_stub .section .__syscall_stub, "ax" .globl batch_syscall_stub diff --git a/kernel/arch/x86/um/stub_64.S b/kernel/arch/x86/um/stub_64.S index 7160b2017..ba914b3b8 100644 --- a/kernel/arch/x86/um/stub_64.S +++ b/kernel/arch/x86/um/stub_64.S @@ -1,25 +1,9 @@ #include <as-layout.h> - .globl syscall_stub .section .__syscall_stub, "ax" -syscall_stub: - syscall - /* We don't have 64-bit constants, so this constructs the address - * we need. - */ - movq $(STUB_DATA >> 32), %rbx - salq $32, %rbx - movq $(STUB_DATA & 0xffffffff), %rcx - or %rcx, %rbx - movq %rax, (%rbx) - int3 - .globl batch_syscall_stub batch_syscall_stub: - mov $(STUB_DATA >> 32), %rbx - sal $32, %rbx - mov $(STUB_DATA & 0xffffffff), %rax - or %rax, %rbx + mov $(STUB_DATA), %rbx /* load pointer to first operation */ mov %rbx, %rsp add $0x10, %rsp diff --git a/kernel/arch/x86/um/sys_call_table_32.c b/kernel/arch/x86/um/sys_call_table_32.c index bd16d6c37..439c0994b 100644 --- a/kernel/arch/x86/um/sys_call_table_32.c +++ b/kernel/arch/x86/um/sys_call_table_32.c @@ -7,6 +7,7 @@ #include <linux/sys.h> #include <linux/cache.h> #include <generated/user_constants.h> +#include <asm/syscall.h> #define __NO_STUBS @@ -24,15 +25,13 @@ #define old_mmap sys_old_mmap -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 #define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym, -typedef asmlinkage void (*sys_call_ptr_t)(void); - -extern asmlinkage void sys_ni_syscall(void); +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* diff --git a/kernel/arch/x86/um/sys_call_table_64.c b/kernel/arch/x86/um/sys_call_table_64.c index a75d87004..b74ea6c2c 100644 --- a/kernel/arch/x86/um/sys_call_table_64.c +++ b/kernel/arch/x86/um/sys_call_table_64.c @@ -7,6 +7,7 @@ #include <linux/sys.h> #include <linux/cache.h> #include <generated/user_constants.h> +#include <asm/syscall.h> #define __NO_STUBS @@ -37,15 +38,13 @@ #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) #define __SYSCALL_X32(nr, sym, compat) /* Not supported */ -#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ; +#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ; #include <asm/syscalls_64.h> #undef __SYSCALL_64 #define __SYSCALL_64(nr, sym, compat) [ nr ] = sym, -typedef void (*sys_call_ptr_t)(void); - -extern void sys_ni_syscall(void); +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* diff --git a/kernel/arch/x86/um/syscalls_64.c b/kernel/arch/x86/um/syscalls_64.c index adb08eb5c..e65522753 100644 --- a/kernel/arch/x86/um/syscalls_64.c +++ b/kernel/arch/x86/um/syscalls_64.c @@ -6,6 +6,7 @@ */ #include <linux/sched.h> +#include <linux/uaccess.h> #include <asm/prctl.h> /* XXX This should get the constants from libc */ #include <os.h> diff --git a/kernel/arch/x86/um/tls_32.c b/kernel/arch/x86/um/tls_32.c index 80ffa5b99..48e38584d 100644 --- a/kernel/arch/x86/um/tls_32.c +++ b/kernel/arch/x86/um/tls_32.c @@ -7,6 +7,7 @@ #include <linux/sched.h> #include <linux/syscalls.h> #include <asm/uaccess.h> +#include <asm/ptrace-abi.h> #include <os.h> #include <skas.h> #include <sysdep/tls.h> diff --git a/kernel/arch/x86/um/tls_64.c b/kernel/arch/x86/um/tls_64.c index d22363cb8..3ad714373 100644 --- a/kernel/arch/x86/um/tls_64.c +++ b/kernel/arch/x86/um/tls_64.c @@ -1,4 +1,5 @@ #include <linux/sched.h> +#include <asm/ptrace-abi.h> void clear_flushed_tls(struct task_struct *task) { diff --git a/kernel/arch/x86/um/vdso/vma.c b/kernel/arch/x86/um/vdso/vma.c index 916cda4cd..237c6831e 100644 --- a/kernel/arch/x86/um/vdso/vma.c +++ b/kernel/arch/x86/um/vdso/vma.c @@ -10,6 +10,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <asm/page.h> +#include <asm/elf.h> #include <linux/init.h> static unsigned int __read_mostly vdso_enabled = 1; diff --git a/kernel/arch/x86/vdso/vdso32/int80.S b/kernel/arch/x86/vdso/vdso32/int80.S deleted file mode 100644 index b15b7c01a..000000000 --- a/kernel/arch/x86/vdso/vdso32/int80.S +++ /dev/null @@ -1,56 +0,0 @@ -/* - * Code for the vDSO. This version uses the old int $0x80 method. - * - * First get the common code for the sigreturn entry points. - * This must come first. - */ -#include "sigreturn.S" - - .text - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function - ALIGN -__kernel_vsyscall: -.LSTART_vsyscall: - int $0x80 - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - .previous - - .section .eh_frame,"a",@progbits -.LSTARTFRAMEDLSI: - .long .LENDCIEDLSI-.LSTARTCIEDLSI -.LSTARTCIEDLSI: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIEDLSI: - .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */ -.LSTARTFDEDLSI: - .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 - .align 4 -.LENDFDEDLSI: - .previous - - /* - * Pad out the segment to match the size of the sysenter.S version. - */ -VDSO32_vsyscall_eh_frame_size = 0x40 - .section .data,"aw",@progbits - .space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0 - .previous diff --git a/kernel/arch/x86/vdso/vdso32/syscall.S b/kernel/arch/x86/vdso/vdso32/syscall.S deleted file mode 100644 index 6b286bb52..000000000 --- a/kernel/arch/x86/vdso/vdso32/syscall.S +++ /dev/null @@ -1,75 +0,0 @@ -/* - * Code for the vDSO. This version uses the syscall instruction. - * - * First get the common code for the sigreturn entry points. - * This must come first. - */ -#define SYSCALL_ENTER_KERNEL syscall -#include "sigreturn.S" - -#include <asm/segment.h> - - .text - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function - ALIGN -__kernel_vsyscall: -.LSTART_vsyscall: - push %ebp -.Lpush_ebp: - movl %ecx, %ebp - syscall - movl %ebp, %ecx - popl %ebp -.Lpop_ebp: - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - - .section .eh_frame,"a",@progbits -.LSTARTFRAME: - .long .LENDCIE-.LSTARTCIE -.LSTARTCIE: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIE: - - .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */ -.LSTARTFDE1: - .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 /* Augmentation length */ - /* What follows are the instructions for the table generation. - We have to record all changes of the stack pointer. */ - .byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .uleb128 8 - .byte 0x85, 0x02 /* DW_CFA_offset %ebp -8 */ - .byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */ - .byte 0xc5 /* DW_CFA_restore %ebp */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .uleb128 4 - .align 4 -.LENDFDE1: - .previous - - /* - * Pad out the segment to match the size of the sysenter.S version. - */ -VDSO32_vsyscall_eh_frame_size = 0x40 - .section .data,"aw",@progbits - .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0 - .previous diff --git a/kernel/arch/x86/vdso/vdso32/sysenter.S b/kernel/arch/x86/vdso/vdso32/sysenter.S deleted file mode 100644 index e354bceee..000000000 --- a/kernel/arch/x86/vdso/vdso32/sysenter.S +++ /dev/null @@ -1,116 +0,0 @@ -/* - * Code for the vDSO. This version uses the sysenter instruction. - * - * First get the common code for the sigreturn entry points. - * This must come first. - */ -#include "sigreturn.S" - -/* - * The caller puts arg2 in %ecx, which gets pushed. The kernel will use - * %ecx itself for arg2. The pushing is because the sysexit instruction - * (found in entry.S) requires that we clobber %ecx with the desired %esp. - * User code might expect that %ecx is unclobbered though, as it would be - * for returning via the iret instruction, so we must push and pop. - * - * The caller puts arg3 in %edx, which the sysexit instruction requires - * for %eip. Thus, exactly as for arg2, we must push and pop. - * - * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter - * instruction clobbers %esp, the user's %esp won't even survive entry - * into the kernel. We store %esp in %ebp. Code in entry.S must fetch - * arg6 from the stack. - * - * You can not use this vsyscall for the clone() syscall because the - * three words on the parent stack do not get copied to the child. - */ - .text - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function - ALIGN -__kernel_vsyscall: -.LSTART_vsyscall: - push %ecx -.Lpush_ecx: - push %edx -.Lpush_edx: - push %ebp -.Lenter_kernel: - movl %esp,%ebp - sysenter - - /* 7: align return point with nop's to make disassembly easier */ - .space 7,0x90 - - /* 14: System call restart point is here! (SYSENTER_RETURN-2) */ - int $0x80 - /* 16: System call normal return point is here! */ -VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */ - pop %ebp -.Lpop_ebp: - pop %edx -.Lpop_edx: - pop %ecx -.Lpop_ecx: - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - .previous - - .section .eh_frame,"a",@progbits -.LSTARTFRAMEDLSI: - .long .LENDCIEDLSI-.LSTARTCIEDLSI -.LSTARTCIEDLSI: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIEDLSI: - .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */ -.LSTARTFDEDLSI: - .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 - /* What follows are the instructions for the table generation. - We have to record all changes of the stack pointer. */ - .byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x08 /* RA at offset 8 now */ - .byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x0c /* RA at offset 12 now */ - .byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x10 /* RA at offset 16 now */ - .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */ - /* Finally the epilogue. */ - .byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x0c /* RA at offset 12 now */ - .byte 0xc5 /* DW_CFA_restore %ebp */ - .byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x08 /* RA at offset 8 now */ - .byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */ - .byte 0x0e /* DW_CFA_def_cfa_offset */ - .byte 0x04 /* RA at offset 4 now */ - .align 4 -.LENDFDEDLSI: - .previous - - /* - * Emit a symbol with the size of this .eh_frame data, - * to verify it matches the other versions. - */ -VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI) diff --git a/kernel/arch/x86/xen/Kconfig b/kernel/arch/x86/xen/Kconfig index 484145368..c7b15f3e2 100644 --- a/kernel/arch/x86/xen/Kconfig +++ b/kernel/arch/x86/xen/Kconfig @@ -7,6 +7,7 @@ config XEN depends on PARAVIRT select PARAVIRT_CLOCK select XEN_HAVE_PVMMU + select XEN_HAVE_VPMU depends on X86_64 || (X86_32 && X86_PAE) depends on X86_LOCAL_APIC && X86_TSC help @@ -23,14 +24,18 @@ config XEN_PVHVM def_bool y depends on XEN && PCI && X86_LOCAL_APIC -config XEN_MAX_DOMAIN_MEMORY - int - default 500 if X86_64 - default 64 if X86_32 - depends on XEN - help - This only affects the sizing of some bss arrays, the unused - portions of which are freed. +config XEN_512GB + bool "Limit Xen pv-domain memory to 512GB" + depends on XEN && X86_64 + default y + help + Limit paravirtualized user domains to 512GB of RAM. + + The Xen tools and crash dump analysis tools might not support + pv-domains with more than 512 GB of RAM. This option controls the + default setting of the kernel to use only up to 512 GB or more. + It is always possible to change the default via specifying the + boot parameter "xen_512gb_limit". config XEN_SAVE_RESTORE bool diff --git a/kernel/arch/x86/xen/Makefile b/kernel/arch/x86/xen/Makefile index 4b6e29ac0..e47e52787 100644 --- a/kernel/arch/x86/xen/Makefile +++ b/kernel/arch/x86/xen/Makefile @@ -13,7 +13,7 @@ CFLAGS_mmu.o := $(nostackp) obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ time.o xen-asm.o xen-asm_$(BITS).o \ grant-table.o suspend.o platform-pci-unplug.o \ - p2m.o apic.o + p2m.o apic.o pmu.o obj-$(CONFIG_EVENT_TRACING) += trace.o diff --git a/kernel/arch/x86/xen/apic.c b/kernel/arch/x86/xen/apic.c index 70e060ad8..acda713ab 100644 --- a/kernel/arch/x86/xen/apic.c +++ b/kernel/arch/x86/xen/apic.c @@ -7,6 +7,7 @@ #include <xen/xen.h> #include <xen/interface/physdev.h> #include "xen-ops.h" +#include "pmu.h" #include "smp.h" static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) @@ -72,6 +73,11 @@ static u32 xen_apic_read(u32 reg) static void xen_apic_write(u32 reg, u32 val) { + if (reg == APIC_LVTPC) { + (void)pmu_apic_update(reg); + return; + } + /* Warn to see if there's any stray references */ WARN(1,"register: %x, value: %x\n", reg, val); } diff --git a/kernel/arch/x86/xen/enlighten.c b/kernel/arch/x86/xen/enlighten.c index a671e8372..b7de78bdc 100644 --- a/kernel/arch/x86/xen/enlighten.c +++ b/kernel/arch/x86/xen/enlighten.c @@ -33,6 +33,10 @@ #include <linux/memblock.h> #include <linux/edd.h> +#ifdef CONFIG_KEXEC_CORE +#include <linux/kexec.h> +#endif + #include <xen/xen.h> #include <xen/events.h> #include <xen/interface/xen.h> @@ -71,6 +75,7 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/pat.h> +#include <asm/cpu.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -84,6 +89,7 @@ #include "mmu.h" #include "smp.h" #include "multicalls.h" +#include "pmu.h" EXPORT_SYMBOL_GPL(hypercall_page); @@ -1010,8 +1016,7 @@ static void xen_write_cr0(unsigned long cr0) static void xen_write_cr4(unsigned long cr4) { - cr4 &= ~X86_CR4_PGE; - cr4 &= ~X86_CR4_PSE; + cr4 &= ~(X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PCE); native_write_cr4(cr4); } @@ -1030,6 +1035,9 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) { u64 val; + if (pmu_msr_read(msr, &val, err)) + return val; + val = native_read_msr_safe(msr, err); switch (msr) { case MSR_IA32_APICBASE: @@ -1074,9 +1082,11 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) /* Fast syscall setup is all done in hypercalls, so these are all ignored. Stub them out here to stop Xen console noise. */ + break; default: - ret = native_write_msr_safe(msr, low, high); + if (!pmu_msr_write(msr, low, high, &ret)) + ret = native_write_msr_safe(msr, low, high); } return ret; @@ -1182,7 +1192,7 @@ static const struct pv_info xen_info __initconst = { #ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, #endif - + .features = 0, .name = "Xen", }; @@ -1215,16 +1225,14 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_msr = xen_read_msr_safe, .write_msr = xen_write_msr_safe, - .read_tsc = native_read_tsc, - .read_pmc = native_read_pmc, - - .read_tscp = native_read_tscp, + .read_pmc = xen_read_pmc, .iret = xen_iret, - .irq_enable_sysexit = xen_sysexit, #ifdef CONFIG_X86_64 .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, +#else + .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1266,6 +1274,10 @@ static const struct pv_apic_ops xen_apic_ops __initconst = { static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; + int cpu; + + for_each_online_cpu(cpu) + xen_pmu_finish(cpu); if (HYPERVISOR_sched_op(SCHEDOP_shutdown, &r)) BUG(); @@ -1463,7 +1475,7 @@ static void xen_pvh_set_cr_flags(int cpu) return; /* * For BSP, PSE PGE are set in probe_page_size_mask(), for APs - * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu_init. + * set them here. For all, OSFXSR OSXMMEXCPT are set in fpu__init_cpu(). */ if (cpu_has_pse) cr4_set_bits_and_update_boot(X86_CR4_PSE); @@ -1507,6 +1519,7 @@ asmlinkage __visible void __init xen_start_kernel(void) { struct physdev_set_iopl set_iopl; unsigned long initrd_start = 0; + u64 pat; int rc; if (!xen_start_info) @@ -1522,6 +1535,8 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; + if (xen_initial_domain()) + pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; pv_apic_ops = xen_apic_ops; if (!xen_pvh_domain()) { @@ -1608,14 +1623,16 @@ asmlinkage __visible void __init xen_start_kernel(void) early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); - xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages); + xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, + xen_start_info->nr_pages); + xen_reserve_special_pages(); /* * Modify the cache mode translation tables to match Xen's PAT * configuration. */ - - pat_init_cache_modes(); + rdmsrl(MSR_IA32_CR_PAT, pat); + pat_init_cache_modes(pat); /* keep using Xen gdt for now; no urgent need to change it */ @@ -1798,6 +1815,21 @@ static struct notifier_block xen_hvm_cpu_notifier = { .notifier_call = xen_hvm_cpu_notify, }; +#ifdef CONFIG_KEXEC_CORE +static void xen_hvm_shutdown(void) +{ + native_machine_shutdown(); + if (kexec_in_progress) + xen_reboot(SHUTDOWN_soft_reset); +} + +static void xen_hvm_crash_shutdown(struct pt_regs *regs) +{ + native_machine_crash_shutdown(regs); + xen_reboot(SHUTDOWN_soft_reset); +} +#endif + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -1817,6 +1849,10 @@ static void __init xen_hvm_guest_init(void) x86_init.irqs.intr_init = xen_init_IRQ; xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); +#ifdef CONFIG_KEXEC_CORE + machine_ops.shutdown = xen_hvm_shutdown; + machine_ops.crash_shutdown = xen_hvm_crash_shutdown; +#endif } #endif @@ -1852,8 +1888,10 @@ EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); static void xen_set_cpu_features(struct cpuinfo_x86 *c) { - if (xen_pv_domain()) + if (xen_pv_domain()) { clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + set_cpu_cap(c, X86_FEATURE_XENPV); + } } const struct hypervisor_x86 x86_hyper_xen = { @@ -1866,3 +1904,17 @@ const struct hypervisor_x86 x86_hyper_xen = { .set_cpu_features = xen_set_cpu_features, }; EXPORT_SYMBOL(x86_hyper_xen); + +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num) +{ + arch_register_cpu(num); +} +EXPORT_SYMBOL(xen_arch_register_cpu); + +void xen_arch_unregister_cpu(int num) +{ + arch_unregister_cpu(num); +} +EXPORT_SYMBOL(xen_arch_unregister_cpu); +#endif diff --git a/kernel/arch/x86/xen/grant-table.c b/kernel/arch/x86/xen/grant-table.c index 1580e7a5a..e079500b1 100644 --- a/kernel/arch/x86/xen/grant-table.c +++ b/kernel/arch/x86/xen/grant-table.c @@ -133,7 +133,7 @@ static int __init xlated_setup_gnttab_pages(void) kfree(pages); return -ENOMEM; } - rc = alloc_xenballooned_pages(nr_grant_frames, pages, 0 /* lowmem */); + rc = alloc_xenballooned_pages(nr_grant_frames, pages); if (rc) { pr_warn("%s Couldn't balloon alloc %ld pfns rc:%d\n", __func__, nr_grant_frames, rc); diff --git a/kernel/arch/x86/xen/mmu.c b/kernel/arch/x86/xen/mmu.c index dd151b204..cb5e266a8 100644 --- a/kernel/arch/x86/xen/mmu.c +++ b/kernel/arch/x86/xen/mmu.c @@ -116,6 +116,7 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ +static phys_addr_t xen_pt_base, xen_pt_size __initdata; /* * Just beyond the highest usermode address. STACK_TOP_MAX has a @@ -1093,6 +1094,16 @@ static void xen_exit_mmap(struct mm_struct *mm) static void xen_post_allocator_init(void); +static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + #ifdef CONFIG_X86_64 static void __init xen_cleanhighmap(unsigned long vaddr, unsigned long vaddr_end) @@ -1114,6 +1125,83 @@ static void __init xen_cleanhighmap(unsigned long vaddr, xen_mc_flush(); } +/* + * Make a page range writeable and free it. + */ +static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size) +{ + void *vaddr = __va(paddr); + void *vaddr_end = vaddr + size; + + for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) + make_lowmem_page_readwrite(vaddr); + + memblock_free(paddr, size); +} + +static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) +{ + unsigned long pa = __pa(pgtbl) & PHYSICAL_PAGE_MASK; + + if (unpin) + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(pa)); + ClearPagePinned(virt_to_page(__va(pa))); + xen_free_ro_pages(pa, PAGE_SIZE); +} + +/* + * Since it is well isolated we can (and since it is perhaps large we should) + * also free the page tables mapping the initial P->M table. + */ +static void __init xen_cleanmfnmap(unsigned long vaddr) +{ + unsigned long va = vaddr & PMD_MASK; + unsigned long pa; + pgd_t *pgd = pgd_offset_k(va); + pud_t *pud_page = pud_offset(pgd, 0); + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned int i; + bool unpin; + + unpin = (vaddr == 2 * PGDIR_SIZE); + set_pgd(pgd, __pgd(0)); + do { + pud = pud_page + pud_index(va); + if (pud_none(*pud)) { + va += PUD_SIZE; + } else if (pud_large(*pud)) { + pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PUD_SIZE); + va += PUD_SIZE; + } else { + pmd = pmd_offset(pud, va); + if (pmd_large(*pmd)) { + pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; + xen_free_ro_pages(pa, PMD_SIZE); + } else if (!pmd_none(*pmd)) { + pte = pte_offset_kernel(pmd, va); + set_pmd(pmd, __pmd(0)); + for (i = 0; i < PTRS_PER_PTE; ++i) { + if (pte_none(pte[i])) + break; + pa = pte_pfn(pte[i]) << PAGE_SHIFT; + xen_free_ro_pages(pa, PAGE_SIZE); + } + xen_cleanmfnmap_free_pgtbl(pte, unpin); + } + va += PMD_SIZE; + if (pmd_index(va)) + continue; + set_pud(pud, __pud(0)); + xen_cleanmfnmap_free_pgtbl(pmd, unpin); + } + + } while (pud_index(va) || pmd_index(va)); + xen_cleanmfnmap_free_pgtbl(pud_page, unpin); +} + static void __init xen_pagetable_p2m_free(void) { unsigned long size; @@ -1128,18 +1216,31 @@ static void __init xen_pagetable_p2m_free(void) /* using __ka address and sticking INVALID_P2M_ENTRY! */ memset((void *)xen_start_info->mfn_list, 0xff, size); - /* We should be in __ka space. */ - BUG_ON(xen_start_info->mfn_list < __START_KERNEL_map); addr = xen_start_info->mfn_list; - /* We roundup to the PMD, which means that if anybody at this stage is - * using the __ka address of xen_start_info or xen_start_info->shared_info - * they are in going to crash. Fortunatly we have already revectored - * in xen_setup_kernel_pagetable and in xen_setup_shared_info. */ + /* + * We could be in __ka space. + * We roundup to the PMD, which means that if anybody at this stage is + * using the __ka address of xen_start_info or + * xen_start_info->shared_info they are in going to crash. Fortunatly + * we have already revectored in xen_setup_kernel_pagetable and in + * xen_setup_shared_info. + */ size = roundup(size, PMD_SIZE); - xen_cleanhighmap(addr, addr + size); - size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_free(__pa(xen_start_info->mfn_list), size); + if (addr >= __START_KERNEL_map) { + xen_cleanhighmap(addr, addr + size); + size = PAGE_ALIGN(xen_start_info->nr_pages * + sizeof(unsigned long)); + memblock_free(__pa(addr), size); + } else { + xen_cleanmfnmap(addr); + } +} + +static void __init xen_pagetable_cleanhighmap(void) +{ + unsigned long size; + unsigned long addr; /* At this stage, cleanup_highmap has already cleaned __ka space * from _brk_limit way up to the max_pfn_mapped (which is the end of @@ -1172,6 +1273,8 @@ static void __init xen_pagetable_p2m_setup(void) #ifdef CONFIG_X86_64 xen_pagetable_p2m_free(); + + xen_pagetable_cleanhighmap(); #endif /* And revector! Bye bye old array */ xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; @@ -1461,6 +1564,24 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) #else /* CONFIG_X86_64 */ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte) { + unsigned long pfn; + + if (xen_feature(XENFEAT_writable_page_tables) || + xen_feature(XENFEAT_auto_translated_physmap) || + xen_start_info->mfn_list >= __START_KERNEL_map) + return pte; + + /* + * Pages belonging to the initial p2m list mapped outside the default + * address range must be mapped read-only. This region contains the + * page tables for mapping the p2m list, too, and page tables MUST be + * mapped read-only. + */ + pfn = pte_pfn(pte); + if (pfn >= xen_start_info->first_p2m_pfn && + pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) + pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW); + return pte; } #endif /* CONFIG_X86_64 */ @@ -1489,15 +1610,6 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) native_set_pte(ptep, pte); } -static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) -{ - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); -} - /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static void __init xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1815,7 +1927,10 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) * mappings. Considering that on Xen after the kernel mappings we * have the mappings of some pages that don't exist in pfn space, we * set max_pfn_mapped to the last real pfn mapped. */ - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); + if (xen_start_info->mfn_list < __START_KERNEL_map) + max_pfn_mapped = xen_start_info->first_p2m_pfn; + else + max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list)); pt_base = PFN_DOWN(__pa(xen_start_info->pt_base)); pt_end = pt_base + xen_start_info->nr_pt_frames; @@ -1855,6 +1970,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); + /* Copy the initial P->M table mappings if necessary. */ + i = pgd_index(xen_start_info->mfn_list); + if (i && i < pgd_index(__START_KERNEL_map)) + init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; + if (!xen_feature(XENFEAT_auto_translated_physmap)) { /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); @@ -1894,10 +2014,192 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) check_pt_base(&pt_base, &pt_end, addr[i]); /* Our (by three pages) smaller Xen pagetable that we are using */ - memblock_reserve(PFN_PHYS(pt_base), (pt_end - pt_base) * PAGE_SIZE); + xen_pt_base = PFN_PHYS(pt_base); + xen_pt_size = (pt_end - pt_base) * PAGE_SIZE; + memblock_reserve(xen_pt_base, xen_pt_size); + /* Revector the xen_start_info */ xen_start_info = (struct start_info *)__va(__pa(xen_start_info)); } + +/* + * Read a value from a physical address. + */ +static unsigned long __init xen_read_phys_ulong(phys_addr_t addr) +{ + unsigned long *vaddr; + unsigned long val; + + vaddr = early_memremap_ro(addr, sizeof(val)); + val = *vaddr; + early_memunmap(vaddr, sizeof(val)); + return val; +} + +/* + * Translate a virtual address to a physical one without relying on mapped + * page tables. + */ +static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) +{ + phys_addr_t pa; + pgd_t pgd; + pud_t pud; + pmd_t pmd; + pte_t pte; + + pa = read_cr3(); + pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) * + sizeof(pgd))); + if (!pgd_present(pgd)) + return 0; + + pa = pgd_val(pgd) & PTE_PFN_MASK; + pud = native_make_pud(xen_read_phys_ulong(pa + pud_index(vaddr) * + sizeof(pud))); + if (!pud_present(pud)) + return 0; + pa = pud_pfn(pud) << PAGE_SHIFT; + if (pud_large(pud)) + return pa + (vaddr & ~PUD_MASK); + + pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) * + sizeof(pmd))); + if (!pmd_present(pmd)) + return 0; + pa = pmd_pfn(pmd) << PAGE_SHIFT; + if (pmd_large(pmd)) + return pa + (vaddr & ~PMD_MASK); + + pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) * + sizeof(pte))); + if (!pte_present(pte)) + return 0; + pa = pte_pfn(pte) << PAGE_SHIFT; + + return pa | (vaddr & ~PAGE_MASK); +} + +/* + * Find a new area for the hypervisor supplied p2m list and relocate the p2m to + * this area. + */ +void __init xen_relocate_p2m(void) +{ + phys_addr_t size, new_area, pt_phys, pmd_phys, pud_phys; + unsigned long p2m_pfn, p2m_pfn_end, n_frames, pfn, pfn_end; + int n_pte, n_pt, n_pmd, n_pud, idx_pte, idx_pt, idx_pmd, idx_pud; + pte_t *pt; + pmd_t *pmd; + pud_t *pud; + pgd_t *pgd; + unsigned long *new_p2m; + + size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); + n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT; + n_pt = roundup(size, PMD_SIZE) >> PMD_SHIFT; + n_pmd = roundup(size, PUD_SIZE) >> PUD_SHIFT; + n_pud = roundup(size, PGDIR_SIZE) >> PGDIR_SHIFT; + n_frames = n_pte + n_pt + n_pmd + n_pud; + + new_area = xen_find_free_area(PFN_PHYS(n_frames)); + if (!new_area) { + xen_raw_console_write("Can't find new memory area for p2m needed due to E820 map conflict\n"); + BUG(); + } + + /* + * Setup the page tables for addressing the new p2m list. + * We have asked the hypervisor to map the p2m list at the user address + * PUD_SIZE. It may have done so, or it may have used a kernel space + * address depending on the Xen version. + * To avoid any possible virtual address collision, just use + * 2 * PUD_SIZE for the new area. + */ + pud_phys = new_area; + pmd_phys = pud_phys + PFN_PHYS(n_pud); + pt_phys = pmd_phys + PFN_PHYS(n_pmd); + p2m_pfn = PFN_DOWN(pt_phys) + n_pt; + + pgd = __va(read_cr3()); + new_p2m = (unsigned long *)(2 * PGDIR_SIZE); + for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { + pud = early_memremap(pud_phys, PAGE_SIZE); + clear_page(pud); + for (idx_pmd = 0; idx_pmd < min(n_pmd, PTRS_PER_PUD); + idx_pmd++) { + pmd = early_memremap(pmd_phys, PAGE_SIZE); + clear_page(pmd); + for (idx_pt = 0; idx_pt < min(n_pt, PTRS_PER_PMD); + idx_pt++) { + pt = early_memremap(pt_phys, PAGE_SIZE); + clear_page(pt); + for (idx_pte = 0; + idx_pte < min(n_pte, PTRS_PER_PTE); + idx_pte++) { + set_pte(pt + idx_pte, + pfn_pte(p2m_pfn, PAGE_KERNEL)); + p2m_pfn++; + } + n_pte -= PTRS_PER_PTE; + early_memunmap(pt, PAGE_SIZE); + make_lowmem_page_readonly(__va(pt_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, + PFN_DOWN(pt_phys)); + set_pmd(pmd + idx_pt, + __pmd(_PAGE_TABLE | pt_phys)); + pt_phys += PAGE_SIZE; + } + n_pt -= PTRS_PER_PMD; + early_memunmap(pmd, PAGE_SIZE); + make_lowmem_page_readonly(__va(pmd_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L2_TABLE, + PFN_DOWN(pmd_phys)); + set_pud(pud + idx_pmd, __pud(_PAGE_TABLE | pmd_phys)); + pmd_phys += PAGE_SIZE; + } + n_pmd -= PTRS_PER_PUD; + early_memunmap(pud, PAGE_SIZE); + make_lowmem_page_readonly(__va(pud_phys)); + pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(pud_phys)); + set_pgd(pgd + 2 + idx_pud, __pgd(_PAGE_TABLE | pud_phys)); + pud_phys += PAGE_SIZE; + } + + /* Now copy the old p2m info to the new area. */ + memcpy(new_p2m, xen_p2m_addr, size); + xen_p2m_addr = new_p2m; + + /* Release the old p2m list and set new list info. */ + p2m_pfn = PFN_DOWN(xen_early_virt_to_phys(xen_start_info->mfn_list)); + BUG_ON(!p2m_pfn); + p2m_pfn_end = p2m_pfn + PFN_DOWN(size); + + if (xen_start_info->mfn_list < __START_KERNEL_map) { + pfn = xen_start_info->first_p2m_pfn; + pfn_end = xen_start_info->first_p2m_pfn + + xen_start_info->nr_p2m_frames; + set_pgd(pgd + 1, __pgd(0)); + } else { + pfn = p2m_pfn; + pfn_end = p2m_pfn_end; + } + + memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); + while (pfn < pfn_end) { + if (pfn == p2m_pfn) { + pfn = p2m_pfn_end; + continue; + } + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); + pfn++; + } + + xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; + xen_start_info->first_p2m_pfn = PFN_DOWN(new_area); + xen_start_info->nr_p2m_frames = n_frames; +} + #else /* !CONFIG_X86_64 */ static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD); @@ -1938,18 +2240,41 @@ static void __init xen_write_cr3_init(unsigned long cr3) pv_mmu_ops.write_cr3 = &xen_write_cr3; } +/* + * For 32 bit domains xen_start_info->pt_base is the pgd address which might be + * not the first page table in the page table pool. + * Iterate through the initial page tables to find the real page table base. + */ +static phys_addr_t xen_find_pt_base(pmd_t *pmd) +{ + phys_addr_t pt_base, paddr; + unsigned pmdidx; + + pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd)); + + for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) + if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) { + paddr = m2p(pmd[pmdidx].pmd); + pt_base = min(pt_base, paddr); + } + + return pt_base; +} + void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { pmd_t *kernel_pmd; + kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); + + xen_pt_base = xen_find_pt_base(kernel_pmd); + xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE; + initial_kernel_pmd = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) + - xen_start_info->nr_pt_frames * PAGE_SIZE + - 512*1024); + max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024); - kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); copy_page(initial_kernel_pmd, kernel_pmd); xen_map_identity_early(initial_kernel_pmd, max_pfn); @@ -1968,11 +2293,33 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) PFN_DOWN(__pa(initial_page_table))); xen_write_cr3(__pa(initial_page_table)); - memblock_reserve(__pa(xen_start_info->pt_base), - xen_start_info->nr_pt_frames * PAGE_SIZE); + memblock_reserve(xen_pt_base, xen_pt_size); } #endif /* CONFIG_X86_64 */ +void __init xen_reserve_special_pages(void) +{ + phys_addr_t paddr; + + memblock_reserve(__pa(xen_start_info), PAGE_SIZE); + if (xen_start_info->store_mfn) { + paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->store_mfn)); + memblock_reserve(paddr, PAGE_SIZE); + } + if (!xen_initial_domain()) { + paddr = PFN_PHYS(mfn_to_pfn(xen_start_info->console.domU.mfn)); + memblock_reserve(paddr, PAGE_SIZE); + } +} + +void __init xen_pt_check_e820(void) +{ + if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) { + xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n"); + BUG(); + } +} + static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss; static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) @@ -2148,14 +2495,9 @@ void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; - /* Optimization - we can use the HVM one but it has no idea which - * VCPUs are descheduled - which means that it will needlessly IPI - * them. Xen knows so let it do the job. - */ - if (xen_feature(XENFEAT_auto_translated_physmap)) { - pv_mmu_ops.flush_tlb_others = xen_flush_tlb_others; + if (xen_feature(XENFEAT_auto_translated_physmap)) return; - } + pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); @@ -2465,9 +2807,9 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, return 0; } -static int do_remap_mfn(struct vm_area_struct *vma, +static int do_remap_gfn(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *mfn, int nr, + xen_pfn_t *gfn, int nr, int *err_ptr, pgprot_t prot, unsigned domid, struct page **pages) @@ -2483,14 +2825,14 @@ static int do_remap_mfn(struct vm_area_struct *vma, if (xen_feature(XENFEAT_auto_translated_physmap)) { #ifdef CONFIG_XEN_PVH /* We need to update the local page tables and the xen HAP */ - return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr, + return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr, prot, domid, pages); #else return -EINVAL; #endif } - rmd.mfn = mfn; + rmd.mfn = gfn; rmd.prot = prot; /* We use the err_ptr to indicate if there we are doing a contigious * mapping or a discontigious mapping. */ @@ -2518,8 +2860,8 @@ static int do_remap_mfn(struct vm_area_struct *vma, batch_left, &done, domid); /* - * @err_ptr may be the same buffer as @mfn, so - * only clear it after each chunk of @mfn is + * @err_ptr may be the same buffer as @gfn, so + * only clear it after each chunk of @gfn is * used. */ if (err_ptr) { @@ -2541,6 +2883,7 @@ static int do_remap_mfn(struct vm_area_struct *vma, addr += range; if (err_ptr) err_ptr += batch; + cond_resched(); } out: @@ -2549,19 +2892,19 @@ out: return err < 0 ? err : mapped; } -int xen_remap_domain_mfn_range(struct vm_area_struct *vma, +int xen_remap_domain_gfn_range(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t mfn, int nr, + xen_pfn_t gfn, int nr, pgprot_t prot, unsigned domid, struct page **pages) { - return do_remap_mfn(vma, addr, &mfn, nr, NULL, prot, domid, pages); + return do_remap_gfn(vma, addr, &gfn, nr, NULL, prot, domid, pages); } -EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); +EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range); -int xen_remap_domain_mfn_array(struct vm_area_struct *vma, +int xen_remap_domain_gfn_array(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *mfn, int nr, + xen_pfn_t *gfn, int nr, int *err_ptr, pgprot_t prot, unsigned domid, struct page **pages) { @@ -2570,13 +2913,13 @@ int xen_remap_domain_mfn_array(struct vm_area_struct *vma, * cause of "wrong memory was mapped in". */ BUG_ON(err_ptr == NULL); - return do_remap_mfn(vma, addr, mfn, nr, err_ptr, prot, domid, pages); + return do_remap_gfn(vma, addr, gfn, nr, err_ptr, prot, domid, pages); } -EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array); +EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array); /* Returns: 0 success */ -int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, +int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, int numpgs, struct page **pages) { if (!pages || !xen_feature(XENFEAT_auto_translated_physmap)) @@ -2588,4 +2931,4 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, return -EINVAL; #endif } -EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range); +EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); diff --git a/kernel/arch/x86/xen/p2m.c b/kernel/arch/x86/xen/p2m.c index b47124d4c..cab9f766b 100644 --- a/kernel/arch/x86/xen/p2m.c +++ b/kernel/arch/x86/xen/p2m.c @@ -67,6 +67,7 @@ #include <linux/seq_file.h> #include <linux/bootmem.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <asm/cache.h> #include <asm/setup.h> @@ -78,10 +79,14 @@ #include <xen/balloon.h> #include <xen/grant_table.h> -#include "p2m.h" #include "multicalls.h" #include "xen-ops.h" +#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) +#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) + +#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) + #define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE) unsigned long *xen_p2m_addr __read_mostly; @@ -107,6 +112,15 @@ static unsigned long *p2m_identity; static pte_t *p2m_missing_pte; static pte_t *p2m_identity_pte; +/* + * Hint at last populated PFN. + * + * Used to set HYPERVISOR_shared_info->arch.max_pfn so the toolstack + * can avoid scanning the whole P2M (which may be sized to account for + * hotplugged memory). + */ +static unsigned long xen_p2m_last_pfn; + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -198,7 +212,8 @@ void __ref xen_build_mfn_list_list(void) unsigned int level, topidx, mididx; unsigned long *mid_mfn_p; - if (xen_feature(XENFEAT_auto_translated_physmap)) + if (xen_feature(XENFEAT_auto_translated_physmap) || + xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) return; /* Pre-initialize p2m_top_mfn to be completely missing */ @@ -259,9 +274,16 @@ void xen_setup_mfn_list_list(void) BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); - HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = - virt_to_mfn(p2m_top_mfn); - HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn; + if (xen_start_info->flags & SIF_VIRT_P2M_4TOOLS) + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = ~0UL; + else + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(p2m_top_mfn); + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; + HYPERVISOR_shared_info->arch.p2m_generation = 0; + HYPERVISOR_shared_info->arch.p2m_vaddr = (unsigned long)xen_p2m_addr; + HYPERVISOR_shared_info->arch.p2m_cr3 = + xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir)); } /* Set up p2m_top to point to the domain-builder provided p2m pages */ @@ -393,6 +415,8 @@ void __init xen_vmalloc_p2m_tree(void) static struct vm_struct vm; unsigned long p2m_limit; + xen_p2m_last_pfn = xen_max_p2m_pfn; + p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), @@ -477,8 +501,12 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) ptechk = lookup_address(vaddr, &level); if (ptechk == pte_pg) { + HYPERVISOR_shared_info->arch.p2m_generation++; + wmb(); /* Tools are synchronizing via p2m_generation. */ set_pmd(pmdp, __pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE)); + wmb(); /* Tools are synchronizing via p2m_generation. */ + HYPERVISOR_shared_info->arch.p2m_generation++; pte_newpg[i] = NULL; } @@ -502,9 +530,9 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) * the new pages are installed with cmpxchg; if we lose the race then * simply free the page we allocated and use the one that's there. */ -static bool alloc_p2m(unsigned long pfn) +int xen_alloc_p2m_entry(unsigned long pfn) { - unsigned topidx, mididx; + unsigned topidx; unsigned long *top_mfn_p, *mid_mfn; pte_t *ptep, *pte_pg; unsigned int level; @@ -512,8 +540,8 @@ static bool alloc_p2m(unsigned long pfn) unsigned long addr = (unsigned long)(xen_p2m_addr + pfn); unsigned long p2m_pfn; - topidx = p2m_top_index(pfn); - mididx = p2m_mid_index(pfn); + if (xen_feature(XENFEAT_auto_translated_physmap)) + return 0; ptep = lookup_address(addr, &level); BUG_ON(!ptep || level != PG_LEVEL_4K); @@ -523,10 +551,11 @@ static bool alloc_p2m(unsigned long pfn) /* PMD level is missing, allocate a new one */ ptep = alloc_p2m_pmd(addr, pte_pg); if (!ptep) - return false; + return -ENOMEM; } - if (p2m_top_mfn) { + if (p2m_top_mfn && pfn < MAX_P2M_PFN) { + topidx = p2m_top_index(pfn); top_mfn_p = &p2m_top_mfn[topidx]; mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]); @@ -540,7 +569,7 @@ static bool alloc_p2m(unsigned long pfn) mid_mfn = alloc_p2m_page(); if (!mid_mfn) - return false; + return -ENOMEM; p2m_mid_mfn_init(mid_mfn, p2m_missing); @@ -566,7 +595,7 @@ static bool alloc_p2m(unsigned long pfn) p2m = alloc_p2m_page(); if (!p2m) - return false; + return -ENOMEM; if (p2m_pfn == PFN_DOWN(__pa(p2m_missing))) p2m_init(p2m); @@ -576,10 +605,14 @@ static bool alloc_p2m(unsigned long pfn) spin_lock_irqsave(&p2m_update_lock, flags); if (pte_pfn(*ptep) == p2m_pfn) { + HYPERVISOR_shared_info->arch.p2m_generation++; + wmb(); /* Tools are synchronizing via p2m_generation. */ set_pte(ptep, pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL)); + wmb(); /* Tools are synchronizing via p2m_generation. */ + HYPERVISOR_shared_info->arch.p2m_generation++; if (mid_mfn) - mid_mfn[mididx] = virt_to_mfn(p2m); + mid_mfn[p2m_mid_index(pfn)] = virt_to_mfn(p2m); p2m = NULL; } @@ -589,8 +622,15 @@ static bool alloc_p2m(unsigned long pfn) free_p2m_page(p2m); } - return true; + /* Expanded the p2m? */ + if (pfn > xen_p2m_last_pfn) { + xen_p2m_last_pfn = pfn; + HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn; + } + + return 0; } +EXPORT_SYMBOL(xen_alloc_p2m_entry); unsigned long __init set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e) @@ -629,6 +669,11 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } + /* + * The interface requires atomic updates on p2m elements. + * xen_safe_write_ulong() is using __put_user which does an atomic + * store via asm(). + */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; @@ -647,7 +692,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { - if (!alloc_p2m(pfn)) + int ret; + + ret = xen_alloc_p2m_entry(pfn); + if (ret < 0) return false; return __set_phys_to_machine(pfn, mfn); diff --git a/kernel/arch/x86/xen/p2m.h b/kernel/arch/x86/xen/p2m.h deleted file mode 100644 index ad8aee24a..000000000 --- a/kernel/arch/x86/xen/p2m.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef _XEN_P2M_H -#define _XEN_P2M_H - -#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) -#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *)) -#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **)) - -#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE) - -#define MAX_REMAP_RANGES 10 - -extern unsigned long __init set_phys_range_identity(unsigned long pfn_s, - unsigned long pfn_e); - -#endif /* _XEN_P2M_H */ diff --git a/kernel/arch/x86/xen/platform-pci-unplug.c b/kernel/arch/x86/xen/platform-pci-unplug.c index a8261716d..9586ff328 100644 --- a/kernel/arch/x86/xen/platform-pci-unplug.c +++ b/kernel/arch/x86/xen/platform-pci-unplug.c @@ -68,7 +68,7 @@ static int check_platform_magic(void) return 0; } -bool xen_has_pv_devices() +bool xen_has_pv_devices(void) { if (!xen_domain()) return false; diff --git a/kernel/arch/x86/xen/pmu.c b/kernel/arch/x86/xen/pmu.c new file mode 100644 index 000000000..724a08740 --- /dev/null +++ b/kernel/arch/x86/xen/pmu.c @@ -0,0 +1,570 @@ +#include <linux/types.h> +#include <linux/interrupt.h> + +#include <asm/xen/hypercall.h> +#include <xen/page.h> +#include <xen/interface/xen.h> +#include <xen/interface/vcpu.h> +#include <xen/interface/xenpmu.h> + +#include "xen-ops.h" +#include "pmu.h" + +/* x86_pmu.handle_irq definition */ +#include "../kernel/cpu/perf_event.h" + +#define XENPMU_IRQ_PROCESSING 1 +struct xenpmu { + /* Shared page between hypervisor and domain */ + struct xen_pmu_data *xenpmu_data; + + uint8_t flags; +}; +static DEFINE_PER_CPU(struct xenpmu, xenpmu_shared); +#define get_xenpmu_data() (this_cpu_ptr(&xenpmu_shared)->xenpmu_data) +#define get_xenpmu_flags() (this_cpu_ptr(&xenpmu_shared)->flags) + +/* Macro for computing address of a PMU MSR bank */ +#define field_offset(ctxt, field) ((void *)((uintptr_t)ctxt + \ + (uintptr_t)ctxt->field)) + +/* AMD PMU */ +#define F15H_NUM_COUNTERS 6 +#define F10H_NUM_COUNTERS 4 + +static __read_mostly uint32_t amd_counters_base; +static __read_mostly uint32_t amd_ctrls_base; +static __read_mostly int amd_msr_step; +static __read_mostly int k7_counters_mirrored; +static __read_mostly int amd_num_counters; + +/* Intel PMU */ +#define MSR_TYPE_COUNTER 0 +#define MSR_TYPE_CTRL 1 +#define MSR_TYPE_GLOBAL 2 +#define MSR_TYPE_ARCH_COUNTER 3 +#define MSR_TYPE_ARCH_CTRL 4 + +/* Number of general pmu registers (CPUID.EAX[0xa].EAX[8..15]) */ +#define PMU_GENERAL_NR_SHIFT 8 +#define PMU_GENERAL_NR_BITS 8 +#define PMU_GENERAL_NR_MASK (((1 << PMU_GENERAL_NR_BITS) - 1) \ + << PMU_GENERAL_NR_SHIFT) + +/* Number of fixed pmu registers (CPUID.EDX[0xa].EDX[0..4]) */ +#define PMU_FIXED_NR_SHIFT 0 +#define PMU_FIXED_NR_BITS 5 +#define PMU_FIXED_NR_MASK (((1 << PMU_FIXED_NR_BITS) - 1) \ + << PMU_FIXED_NR_SHIFT) + +/* Alias registers (0x4c1) for full-width writes to PMCs */ +#define MSR_PMC_ALIAS_MASK (~(MSR_IA32_PERFCTR0 ^ MSR_IA32_PMC0)) + +#define INTEL_PMC_TYPE_SHIFT 30 + +static __read_mostly int intel_num_arch_counters, intel_num_fixed_counters; + + +static void xen_pmu_arch_init(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + + switch (boot_cpu_data.x86) { + case 0x15: + amd_num_counters = F15H_NUM_COUNTERS; + amd_counters_base = MSR_F15H_PERF_CTR; + amd_ctrls_base = MSR_F15H_PERF_CTL; + amd_msr_step = 2; + k7_counters_mirrored = 1; + break; + case 0x10: + case 0x12: + case 0x14: + case 0x16: + default: + amd_num_counters = F10H_NUM_COUNTERS; + amd_counters_base = MSR_K7_PERFCTR0; + amd_ctrls_base = MSR_K7_EVNTSEL0; + amd_msr_step = 1; + k7_counters_mirrored = 0; + break; + } + } else { + uint32_t eax, ebx, ecx, edx; + + cpuid(0xa, &eax, &ebx, &ecx, &edx); + + intel_num_arch_counters = (eax & PMU_GENERAL_NR_MASK) >> + PMU_GENERAL_NR_SHIFT; + intel_num_fixed_counters = (edx & PMU_FIXED_NR_MASK) >> + PMU_FIXED_NR_SHIFT; + } +} + +static inline uint32_t get_fam15h_addr(u32 addr) +{ + switch (addr) { + case MSR_K7_PERFCTR0: + case MSR_K7_PERFCTR1: + case MSR_K7_PERFCTR2: + case MSR_K7_PERFCTR3: + return MSR_F15H_PERF_CTR + (addr - MSR_K7_PERFCTR0); + case MSR_K7_EVNTSEL0: + case MSR_K7_EVNTSEL1: + case MSR_K7_EVNTSEL2: + case MSR_K7_EVNTSEL3: + return MSR_F15H_PERF_CTL + (addr - MSR_K7_EVNTSEL0); + default: + break; + } + + return addr; +} + +static inline bool is_amd_pmu_msr(unsigned int msr) +{ + if ((msr >= MSR_F15H_PERF_CTL && + msr < MSR_F15H_PERF_CTR + (amd_num_counters * 2)) || + (msr >= MSR_K7_EVNTSEL0 && + msr < MSR_K7_PERFCTR0 + amd_num_counters)) + return true; + + return false; +} + +static int is_intel_pmu_msr(u32 msr_index, int *type, int *index) +{ + u32 msr_index_pmc; + + switch (msr_index) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_IA32_DS_AREA: + case MSR_IA32_PEBS_ENABLE: + *type = MSR_TYPE_CTRL; + return true; + + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *type = MSR_TYPE_GLOBAL; + return true; + + default: + + if ((msr_index >= MSR_CORE_PERF_FIXED_CTR0) && + (msr_index < MSR_CORE_PERF_FIXED_CTR0 + + intel_num_fixed_counters)) { + *index = msr_index - MSR_CORE_PERF_FIXED_CTR0; + *type = MSR_TYPE_COUNTER; + return true; + } + + if ((msr_index >= MSR_P6_EVNTSEL0) && + (msr_index < MSR_P6_EVNTSEL0 + intel_num_arch_counters)) { + *index = msr_index - MSR_P6_EVNTSEL0; + *type = MSR_TYPE_ARCH_CTRL; + return true; + } + + msr_index_pmc = msr_index & MSR_PMC_ALIAS_MASK; + if ((msr_index_pmc >= MSR_IA32_PERFCTR0) && + (msr_index_pmc < MSR_IA32_PERFCTR0 + + intel_num_arch_counters)) { + *type = MSR_TYPE_ARCH_COUNTER; + *index = msr_index_pmc - MSR_IA32_PERFCTR0; + return true; + } + return false; + } +} + +static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type, + int index, bool is_read) +{ + uint64_t *reg = NULL; + struct xen_pmu_intel_ctxt *ctxt; + uint64_t *fix_counters; + struct xen_pmu_cntr_pair *arch_cntr_pair; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) + return false; + + ctxt = &xenpmu_data->pmu.c.intel; + + switch (msr) { + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + reg = &ctxt->global_ovf_ctrl; + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + reg = &ctxt->global_status; + break; + case MSR_CORE_PERF_GLOBAL_CTRL: + reg = &ctxt->global_ctrl; + break; + case MSR_CORE_PERF_FIXED_CTR_CTRL: + reg = &ctxt->fixed_ctrl; + break; + default: + switch (type) { + case MSR_TYPE_COUNTER: + fix_counters = field_offset(ctxt, fixed_counters); + reg = &fix_counters[index]; + break; + case MSR_TYPE_ARCH_COUNTER: + arch_cntr_pair = field_offset(ctxt, arch_counters); + reg = &arch_cntr_pair[index].counter; + break; + case MSR_TYPE_ARCH_CTRL: + arch_cntr_pair = field_offset(ctxt, arch_counters); + reg = &arch_cntr_pair[index].control; + break; + default: + return false; + } + } + + if (reg) { + if (is_read) + *val = *reg; + else { + *reg = *val; + + if (msr == MSR_CORE_PERF_GLOBAL_OVF_CTRL) + ctxt->global_status &= (~(*val)); + } + return true; + } + + return false; +} + +static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read) +{ + uint64_t *reg = NULL; + int i, off = 0; + struct xen_pmu_amd_ctxt *ctxt; + uint64_t *counter_regs, *ctrl_regs; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) + return false; + + if (k7_counters_mirrored && + ((msr >= MSR_K7_EVNTSEL0) && (msr <= MSR_K7_PERFCTR3))) + msr = get_fam15h_addr(msr); + + ctxt = &xenpmu_data->pmu.c.amd; + for (i = 0; i < amd_num_counters; i++) { + if (msr == amd_ctrls_base + off) { + ctrl_regs = field_offset(ctxt, ctrls); + reg = &ctrl_regs[i]; + break; + } else if (msr == amd_counters_base + off) { + counter_regs = field_offset(ctxt, counters); + reg = &counter_regs[i]; + break; + } + off += amd_msr_step; + } + + if (reg) { + if (is_read) + *val = *reg; + else + *reg = *val; + + return true; + } + return false; +} + +bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (is_amd_pmu_msr(msr)) { + if (!xen_amd_pmu_emulate(msr, val, 1)) + *val = native_read_msr_safe(msr, err); + return true; + } + } else { + int type, index; + + if (is_intel_pmu_msr(msr, &type, &index)) { + if (!xen_intel_pmu_emulate(msr, val, type, index, 1)) + *val = native_read_msr_safe(msr, err); + return true; + } + } + + return false; +} + +bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err) +{ + uint64_t val = ((uint64_t)high << 32) | low; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (is_amd_pmu_msr(msr)) { + if (!xen_amd_pmu_emulate(msr, &val, 0)) + *err = native_write_msr_safe(msr, low, high); + return true; + } + } else { + int type, index; + + if (is_intel_pmu_msr(msr, &type, &index)) { + if (!xen_intel_pmu_emulate(msr, &val, type, index, 0)) + *err = native_write_msr_safe(msr, low, high); + return true; + } + } + + return false; +} + +static unsigned long long xen_amd_read_pmc(int counter) +{ + struct xen_pmu_amd_ctxt *ctxt; + uint64_t *counter_regs; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) { + uint32_t msr; + int err; + + msr = amd_counters_base + (counter * amd_msr_step); + return native_read_msr_safe(msr, &err); + } + + ctxt = &xenpmu_data->pmu.c.amd; + counter_regs = field_offset(ctxt, counters); + return counter_regs[counter]; +} + +static unsigned long long xen_intel_read_pmc(int counter) +{ + struct xen_pmu_intel_ctxt *ctxt; + uint64_t *fixed_counters; + struct xen_pmu_cntr_pair *arch_cntr_pair; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) { + uint32_t msr; + int err; + + if (counter & (1 << INTEL_PMC_TYPE_SHIFT)) + msr = MSR_CORE_PERF_FIXED_CTR0 + (counter & 0xffff); + else + msr = MSR_IA32_PERFCTR0 + counter; + + return native_read_msr_safe(msr, &err); + } + + ctxt = &xenpmu_data->pmu.c.intel; + if (counter & (1 << INTEL_PMC_TYPE_SHIFT)) { + fixed_counters = field_offset(ctxt, fixed_counters); + return fixed_counters[counter & 0xffff]; + } + + arch_cntr_pair = field_offset(ctxt, arch_counters); + return arch_cntr_pair[counter].counter; +} + +unsigned long long xen_read_pmc(int counter) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return xen_amd_read_pmc(counter); + else + return xen_intel_read_pmc(counter); +} + +int pmu_apic_update(uint32_t val) +{ + int ret; + struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return -EINVAL; + } + + xenpmu_data->pmu.l.lapic_lvtpc = val; + + if (get_xenpmu_flags() & XENPMU_IRQ_PROCESSING) + return 0; + + ret = HYPERVISOR_xenpmu_op(XENPMU_lvtpc_set, NULL); + + return ret; +} + +/* perf callbacks */ +static int xen_is_in_guest(void) +{ + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return 0; + } + + if (!xen_initial_domain() || (xenpmu_data->domain_id >= DOMID_SELF)) + return 0; + + return 1; +} + +static int xen_is_user_mode(void) +{ + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return 0; + } + + if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV) + return (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER); + else + return !!(xenpmu_data->pmu.r.regs.cpl & 3); +} + +static unsigned long xen_get_guest_ip(void) +{ + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return 0; + } + + return xenpmu_data->pmu.r.regs.ip; +} + +static struct perf_guest_info_callbacks xen_guest_cbs = { + .is_in_guest = xen_is_in_guest, + .is_user_mode = xen_is_user_mode, + .get_guest_ip = xen_get_guest_ip, +}; + +/* Convert registers from Xen's format to Linux' */ +static void xen_convert_regs(const struct xen_pmu_regs *xen_regs, + struct pt_regs *regs, uint64_t pmu_flags) +{ + regs->ip = xen_regs->ip; + regs->cs = xen_regs->cs; + regs->sp = xen_regs->sp; + + if (pmu_flags & PMU_SAMPLE_PV) { + if (pmu_flags & PMU_SAMPLE_USER) + regs->cs |= 3; + else + regs->cs &= ~3; + } else { + if (xen_regs->cpl) + regs->cs |= 3; + else + regs->cs &= ~3; + } +} + +irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) +{ + int err, ret = IRQ_NONE; + struct pt_regs regs; + const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + uint8_t xenpmu_flags = get_xenpmu_flags(); + + if (!xenpmu_data) { + pr_warn_once("%s: pmudata not initialized\n", __func__); + return ret; + } + + this_cpu_ptr(&xenpmu_shared)->flags = + xenpmu_flags | XENPMU_IRQ_PROCESSING; + xen_convert_regs(&xenpmu_data->pmu.r.regs, ®s, + xenpmu_data->pmu.pmu_flags); + if (x86_pmu.handle_irq(®s)) + ret = IRQ_HANDLED; + + /* Write out cached context to HW */ + err = HYPERVISOR_xenpmu_op(XENPMU_flush, NULL); + this_cpu_ptr(&xenpmu_shared)->flags = xenpmu_flags; + if (err) { + pr_warn_once("%s: failed hypercall, err: %d\n", __func__, err); + return IRQ_NONE; + } + + return ret; +} + +bool is_xen_pmu(int cpu) +{ + return (get_xenpmu_data() != NULL); +} + +void xen_pmu_init(int cpu) +{ + int err; + struct xen_pmu_params xp; + unsigned long pfn; + struct xen_pmu_data *xenpmu_data; + + BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE); + + if (xen_hvm_domain()) + return; + + xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL); + if (!xenpmu_data) { + pr_err("VPMU init: No memory\n"); + return; + } + pfn = virt_to_pfn(xenpmu_data); + + xp.val = pfn_to_mfn(pfn); + xp.vcpu = cpu; + xp.version.maj = XENPMU_VER_MAJ; + xp.version.min = XENPMU_VER_MIN; + err = HYPERVISOR_xenpmu_op(XENPMU_init, &xp); + if (err) + goto fail; + + per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data; + per_cpu(xenpmu_shared, cpu).flags = 0; + + if (cpu == 0) { + perf_register_guest_info_callbacks(&xen_guest_cbs); + xen_pmu_arch_init(); + } + + return; + +fail: + pr_warn_once("Could not initialize VPMU for cpu %d, error %d\n", + cpu, err); + free_pages((unsigned long)xenpmu_data, 0); +} + +void xen_pmu_finish(int cpu) +{ + struct xen_pmu_params xp; + + if (xen_hvm_domain()) + return; + + xp.vcpu = cpu; + xp.version.maj = XENPMU_VER_MAJ; + xp.version.min = XENPMU_VER_MIN; + + (void)HYPERVISOR_xenpmu_op(XENPMU_finish, &xp); + + free_pages((unsigned long)per_cpu(xenpmu_shared, cpu).xenpmu_data, 0); + per_cpu(xenpmu_shared, cpu).xenpmu_data = NULL; +} diff --git a/kernel/arch/x86/xen/pmu.h b/kernel/arch/x86/xen/pmu.h new file mode 100644 index 000000000..af5f0ad94 --- /dev/null +++ b/kernel/arch/x86/xen/pmu.h @@ -0,0 +1,15 @@ +#ifndef __XEN_PMU_H +#define __XEN_PMU_H + +#include <xen/interface/xenpmu.h> + +irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id); +void xen_pmu_init(int cpu); +void xen_pmu_finish(int cpu); +bool is_xen_pmu(int cpu); +bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err); +bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err); +int pmu_apic_update(uint32_t reg); +unsigned long long xen_read_pmc(int counter); + +#endif /* __XEN_PMU_H */ diff --git a/kernel/arch/x86/xen/setup.c b/kernel/arch/x86/xen/setup.c index 55f388ef4..7ab29518a 100644 --- a/kernel/arch/x86/xen/setup.c +++ b/kernel/arch/x86/xen/setup.c @@ -27,17 +27,23 @@ #include <xen/interface/memory.h> #include <xen/interface/physdev.h> #include <xen/features.h> +#include <xen/hvc-console.h> #include "xen-ops.h" #include "vdso.h" -#include "p2m.h" #include "mmu.h" +#define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) + /* Amount of extra memory space we add to the e820 ranges */ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; +/* E820 map used during setting up memory. */ +static struct e820entry xen_e820_map[E820MAX] __initdata; +static u32 xen_e820_map_entries __initdata; + /* * Buffer used to remap identity mapped pages. We only need the virtual space. * The physical page behind this address is remapped as needed to different @@ -64,62 +70,89 @@ static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; */ #define EXTRA_MEM_RATIO (10) -static void __init xen_add_extra_mem(phys_addr_t start, phys_addr_t size) +static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); + +static void __init xen_parse_512gb(void) +{ + bool val = false; + char *arg; + + arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit"); + if (!arg) + return; + + arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit="); + if (!arg) + val = true; + else if (strtobool(arg + strlen("xen_512gb_limit="), &val)) + return; + + xen_512gb_limit = val; +} + +static void __init xen_add_extra_mem(unsigned long start_pfn, + unsigned long n_pfns) { int i; + /* + * No need to check for zero size, should happen rarely and will only + * write a new entry regarded to be unused due to zero size. + */ for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { /* Add new region. */ - if (xen_extra_mem[i].size == 0) { - xen_extra_mem[i].start = start; - xen_extra_mem[i].size = size; + if (xen_extra_mem[i].n_pfns == 0) { + xen_extra_mem[i].start_pfn = start_pfn; + xen_extra_mem[i].n_pfns = n_pfns; break; } /* Append to existing region. */ - if (xen_extra_mem[i].start + xen_extra_mem[i].size == start) { - xen_extra_mem[i].size += size; + if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == + start_pfn) { + xen_extra_mem[i].n_pfns += n_pfns; break; } } if (i == XEN_EXTRA_MEM_MAX_REGIONS) printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - memblock_reserve(start, size); + memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } -static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size) +static void __init xen_del_extra_mem(unsigned long start_pfn, + unsigned long n_pfns) { int i; - phys_addr_t start_r, size_r; + unsigned long start_r, size_r; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - start_r = xen_extra_mem[i].start; - size_r = xen_extra_mem[i].size; + start_r = xen_extra_mem[i].start_pfn; + size_r = xen_extra_mem[i].n_pfns; /* Start of region. */ - if (start_r == start) { - BUG_ON(size > size_r); - xen_extra_mem[i].start += size; - xen_extra_mem[i].size -= size; + if (start_r == start_pfn) { + BUG_ON(n_pfns > size_r); + xen_extra_mem[i].start_pfn += n_pfns; + xen_extra_mem[i].n_pfns -= n_pfns; break; } /* End of region. */ - if (start_r + size_r == start + size) { - BUG_ON(size > size_r); - xen_extra_mem[i].size -= size; + if (start_r + size_r == start_pfn + n_pfns) { + BUG_ON(n_pfns > size_r); + xen_extra_mem[i].n_pfns -= n_pfns; break; } /* Mid of region. */ - if (start > start_r && start < start_r + size_r) { - BUG_ON(start + size > start_r + size_r); - xen_extra_mem[i].size = start - start_r; + if (start_pfn > start_r && start_pfn < start_r + size_r) { + BUG_ON(start_pfn + n_pfns > start_r + size_r); + xen_extra_mem[i].n_pfns = start_pfn - start_r; /* Calling memblock_reserve() again is okay. */ - xen_add_extra_mem(start + size, start_r + size_r - - (start + size)); + xen_add_extra_mem(start_pfn + n_pfns, start_r + size_r - + (start_pfn + n_pfns)); break; } } - memblock_free(start, size); + memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } /* @@ -130,11 +163,10 @@ static void __init xen_del_extra_mem(phys_addr_t start, phys_addr_t size) unsigned long __ref xen_chk_extra_mem(unsigned long pfn) { int i; - phys_addr_t addr = PFN_PHYS(pfn); for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - if (addr >= xen_extra_mem[i].start && - addr < xen_extra_mem[i].start + xen_extra_mem[i].size) + if (pfn >= xen_extra_mem[i].start_pfn && + pfn < xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns) return INVALID_P2M_ENTRY; } @@ -150,10 +182,10 @@ void __init xen_inv_extra_mem(void) int i; for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - if (!xen_extra_mem[i].size) + if (!xen_extra_mem[i].n_pfns) continue; - pfn_s = PFN_DOWN(xen_extra_mem[i].start); - pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size); + pfn_s = xen_extra_mem[i].start_pfn; + pfn_e = pfn_s + xen_extra_mem[i].n_pfns; for (pfn = pfn_s; pfn < pfn_e; pfn++) set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } @@ -164,15 +196,13 @@ void __init xen_inv_extra_mem(void) * This function updates min_pfn with the pfn found and returns * the size of that range or zero if not found. */ -static unsigned long __init xen_find_pfn_range( - const struct e820entry *list, size_t map_size, - unsigned long *min_pfn) +static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn) { - const struct e820entry *entry; + const struct e820entry *entry = xen_e820_map; unsigned int i; unsigned long done = 0; - for (i = 0, entry = list; i < map_size; i++, entry++) { + for (i = 0; i < xen_e820_map_entries; i++, entry++) { unsigned long s_pfn; unsigned long e_pfn; @@ -182,7 +212,7 @@ static unsigned long __init xen_find_pfn_range( e_pfn = PFN_DOWN(entry->addr + entry->size); /* We only care about E820 after this */ - if (e_pfn < *min_pfn) + if (e_pfn <= *min_pfn) continue; s_pfn = PFN_UP(entry->addr); @@ -221,7 +251,7 @@ static int __init xen_free_mfn(unsigned long mfn) * as a fallback if the remapping fails. */ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages, unsigned long *released) + unsigned long end_pfn, unsigned long nr_pages) { unsigned long pfn, end; int ret; @@ -241,7 +271,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn, WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret); if (ret == 1) { - (*released)++; + xen_released_pages++; if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY)) break; } else @@ -356,9 +386,8 @@ static void __init xen_do_set_identity_and_remap_chunk( * to Xen and not remapped. */ static unsigned long __init xen_set_identity_and_remap_chunk( - const struct e820entry *list, size_t map_size, unsigned long start_pfn, - unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn, - unsigned long *released, unsigned long *remapped) + unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages, + unsigned long remap_pfn) { unsigned long pfn; unsigned long i = 0; @@ -379,12 +408,11 @@ static unsigned long __init xen_set_identity_and_remap_chunk( if (cur_pfn + size > nr_pages) size = nr_pages - cur_pfn; - remap_range_size = xen_find_pfn_range(list, map_size, - &remap_pfn); + remap_range_size = xen_find_pfn_range(&remap_pfn); if (!remap_range_size) { pr_warning("Unable to find available pfn range, not remapping identity pages\n"); xen_set_identity_and_release_chunk(cur_pfn, - cur_pfn + left, nr_pages, released); + cur_pfn + left, nr_pages); break; } /* Adjust size to fit in current e820 RAM region */ @@ -396,7 +424,6 @@ static unsigned long __init xen_set_identity_and_remap_chunk( /* Update variables to reflect new mappings. */ i += size; remap_pfn += size; - *remapped += size; } /* @@ -411,15 +438,11 @@ static unsigned long __init xen_set_identity_and_remap_chunk( return remap_pfn; } -static void __init xen_set_identity_and_remap( - const struct e820entry *list, size_t map_size, unsigned long nr_pages, - unsigned long *released, unsigned long *remapped) +static void __init xen_set_identity_and_remap(unsigned long nr_pages) { phys_addr_t start = 0; unsigned long last_pfn = nr_pages; - const struct e820entry *entry; - unsigned long num_released = 0; - unsigned long num_remapped = 0; + const struct e820entry *entry = xen_e820_map; int i; /* @@ -433,9 +456,9 @@ static void __init xen_set_identity_and_remap( * example) the DMI tables in a reserved region that begins on * a non-page boundary. */ - for (i = 0, entry = list; i < map_size; i++, entry++) { + for (i = 0; i < xen_e820_map_entries; i++, entry++) { phys_addr_t end = entry->addr + entry->size; - if (entry->type == E820_RAM || i == map_size - 1) { + if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); @@ -444,17 +467,13 @@ static void __init xen_set_identity_and_remap( if (start_pfn < end_pfn) last_pfn = xen_set_identity_and_remap_chunk( - list, map_size, start_pfn, - end_pfn, nr_pages, last_pfn, - &num_released, &num_remapped); + start_pfn, end_pfn, nr_pages, + last_pfn); start = end; } } - *released = num_released; - *remapped = num_remapped; - - pr_info("Released %ld page(s)\n", num_released); + pr_info("Released %ld page(s)\n", xen_released_pages); } /* @@ -494,7 +513,7 @@ void __init xen_remap_memory(void) } else if (pfn_s + len == xen_remap_buf.target_pfn) { len += xen_remap_buf.size; } else { - xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len)); + xen_del_extra_mem(pfn_s, len); pfn_s = xen_remap_buf.target_pfn; len = xen_remap_buf.size; } @@ -504,18 +523,35 @@ void __init xen_remap_memory(void) } if (pfn_s != ~0UL && len) - xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len)); + xen_del_extra_mem(pfn_s, len); set_pte_mfn(buf, mfn_save, PAGE_KERNEL); pr_info("Remapped %ld page(s)\n", remapped); } +static unsigned long __init xen_get_pages_limit(void) +{ + unsigned long limit; + +#ifdef CONFIG_X86_32 + limit = GB(64) / PAGE_SIZE; +#else + limit = MAXMEM / PAGE_SIZE; + if (!xen_initial_domain() && xen_512gb_limit) + limit = GB(512) / PAGE_SIZE; +#endif + return limit; +} + static unsigned long __init xen_get_max_pages(void) { - unsigned long max_pages = MAX_DOMAIN_PAGES; + unsigned long max_pages, limit; domid_t domid = DOMID_SELF; - int ret; + long ret; + + limit = xen_get_pages_limit(); + max_pages = limit; /* * For the initial domain we use the maximum reservation as @@ -532,7 +568,7 @@ static unsigned long __init xen_get_max_pages(void) max_pages = ret; } - return min(max_pages, MAX_DOMAIN_PAGES); + return min(max_pages, limit); } static void __init xen_align_and_add_e820_region(phys_addr_t start, @@ -549,39 +585,188 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start, e820_add_region(start, end - start, type); } -static void __init xen_ignore_unusable(struct e820entry *list, size_t map_size) +static void __init xen_ignore_unusable(void) { - struct e820entry *entry; + struct e820entry *entry = xen_e820_map; unsigned int i; - for (i = 0, entry = list; i < map_size; i++, entry++) { + for (i = 0; i < xen_e820_map_entries; i++, entry++) { if (entry->type == E820_UNUSABLE) entry->type = E820_RAM; } } +static unsigned long __init xen_count_remap_pages(unsigned long max_pfn) +{ + unsigned long extra = 0; + unsigned long start_pfn, end_pfn; + const struct e820entry *entry = xen_e820_map; + int i; + + end_pfn = 0; + for (i = 0; i < xen_e820_map_entries; i++, entry++) { + start_pfn = PFN_DOWN(entry->addr); + /* Adjacent regions on non-page boundaries handling! */ + end_pfn = min(end_pfn, start_pfn); + + if (start_pfn >= max_pfn) + return extra + max_pfn - end_pfn; + + /* Add any holes in map to result. */ + extra += start_pfn - end_pfn; + + end_pfn = PFN_UP(entry->addr + entry->size); + end_pfn = min(end_pfn, max_pfn); + + if (entry->type != E820_RAM) + extra += end_pfn - start_pfn; + } + + return extra; +} + +bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) +{ + struct e820entry *entry; + unsigned mapcnt; + phys_addr_t end; + + if (!size) + return false; + + end = start + size; + entry = xen_e820_map; + + for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) { + if (entry->type == E820_RAM && entry->addr <= start && + (entry->addr + entry->size) >= end) + return false; + + entry++; + } + + return true; +} + +/* + * Find a free area in physical memory not yet reserved and compliant with + * E820 map. + * Used to relocate pre-allocated areas like initrd or p2m list which are in + * conflict with the to be used E820 map. + * In case no area is found, return 0. Otherwise return the physical address + * of the area which is already reserved for convenience. + */ +phys_addr_t __init xen_find_free_area(phys_addr_t size) +{ + unsigned mapcnt; + phys_addr_t addr, start; + struct e820entry *entry = xen_e820_map; + + for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) { + if (entry->type != E820_RAM || entry->size < size) + continue; + start = entry->addr; + for (addr = start; addr < start + size; addr += PAGE_SIZE) { + if (!memblock_is_reserved(addr)) + continue; + start = addr + PAGE_SIZE; + if (start + size > entry->addr + entry->size) + break; + } + if (addr >= start + size) { + memblock_reserve(start, size); + return start; + } + } + + return 0; +} + +/* + * Like memcpy, but with physical addresses for dest and src. + */ +static void __init xen_phys_memcpy(phys_addr_t dest, phys_addr_t src, + phys_addr_t n) +{ + phys_addr_t dest_off, src_off, dest_len, src_len, len; + void *from, *to; + + while (n) { + dest_off = dest & ~PAGE_MASK; + src_off = src & ~PAGE_MASK; + dest_len = n; + if (dest_len > (NR_FIX_BTMAPS << PAGE_SHIFT) - dest_off) + dest_len = (NR_FIX_BTMAPS << PAGE_SHIFT) - dest_off; + src_len = n; + if (src_len > (NR_FIX_BTMAPS << PAGE_SHIFT) - src_off) + src_len = (NR_FIX_BTMAPS << PAGE_SHIFT) - src_off; + len = min(dest_len, src_len); + to = early_memremap(dest - dest_off, dest_len + dest_off); + from = early_memremap(src - src_off, src_len + src_off); + memcpy(to, from, len); + early_memunmap(to, dest_len + dest_off); + early_memunmap(from, src_len + src_off); + n -= len; + dest += len; + src += len; + } +} + +/* + * Reserve Xen mfn_list. + */ +static void __init xen_reserve_xen_mfnlist(void) +{ + phys_addr_t start, size; + + if (xen_start_info->mfn_list >= __START_KERNEL_map) { + start = __pa(xen_start_info->mfn_list); + size = PFN_ALIGN(xen_start_info->nr_pages * + sizeof(unsigned long)); + } else { + start = PFN_PHYS(xen_start_info->first_p2m_pfn); + size = PFN_PHYS(xen_start_info->nr_p2m_frames); + } + + if (!xen_is_e820_reserved(start, size)) { + memblock_reserve(start, size); + return; + } + +#ifdef CONFIG_X86_32 + /* + * Relocating the p2m on 32 bit system to an arbitrary virtual address + * is not supported, so just give up. + */ + xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n"); + BUG(); +#else + xen_relocate_p2m(); +#endif +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ char * __init xen_memory_setup(void) { - static struct e820entry map[E820MAX] __initdata; - - unsigned long max_pfn = xen_start_info->nr_pages; - phys_addr_t mem_end; + unsigned long max_pfn, pfn_s, n_pfns; + phys_addr_t mem_end, addr, size, chunk_size; + u32 type; int rc; struct xen_memory_map memmap; unsigned long max_pages; unsigned long extra_pages = 0; - unsigned long remapped_pages; int i; int op; - max_pfn = min(MAX_DOMAIN_PAGES, max_pfn); + xen_parse_512gb(); + max_pfn = xen_get_pages_limit(); + max_pfn = min(max_pfn, xen_start_info->nr_pages); mem_end = PFN_PHYS(max_pfn); memmap.nr_entries = E820MAX; - set_xen_guest_handle(memmap.buffer, map); + set_xen_guest_handle(memmap.buffer, xen_e820_map); op = xen_initial_domain() ? XENMEM_machine_memory_map : @@ -590,15 +775,16 @@ char * __init xen_memory_setup(void) if (rc == -ENOSYS) { BUG_ON(xen_initial_domain()); memmap.nr_entries = 1; - map[0].addr = 0ULL; - map[0].size = mem_end; + xen_e820_map[0].addr = 0ULL; + xen_e820_map[0].size = mem_end; /* 8MB slack (to balance backend allocations). */ - map[0].size += 8ULL << 20; - map[0].type = E820_RAM; + xen_e820_map[0].size += 8ULL << 20; + xen_e820_map[0].type = E820_RAM; rc = 0; } BUG_ON(rc); BUG_ON(memmap.nr_entries == 0); + xen_e820_map_entries = memmap.nr_entries; /* * Xen won't allow a 1:1 mapping to be created to UNUSABLE @@ -609,24 +795,19 @@ char * __init xen_memory_setup(void) * a patch in the future. */ if (xen_initial_domain()) - xen_ignore_unusable(map, memmap.nr_entries); + xen_ignore_unusable(); /* Make sure the Xen-supplied memory map is well-ordered. */ - sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); + sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), + &xen_e820_map_entries); max_pages = xen_get_max_pages(); - if (max_pages > max_pfn) - extra_pages += max_pages - max_pfn; - /* - * Set identity map on non-RAM pages and prepare remapping the - * underlying RAM. - */ - xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn, - &xen_released_pages, &remapped_pages); + /* How many extra pages do we need due to remapping? */ + max_pages += xen_count_remap_pages(max_pfn); - extra_pages += xen_released_pages; - extra_pages += remapped_pages; + if (max_pages > max_pfn) + extra_pages += max_pages - max_pfn; /* * Clamp the amount of extra memory to a EXTRA_MEM_RATIO @@ -635,46 +816,57 @@ char * __init xen_memory_setup(void) * is limited to the max size of lowmem, so that it doesn't * get completely filled. * + * Make sure we have no memory above max_pages, as this area + * isn't handled by the p2m management. + * * In principle there could be a problem in lowmem systems if * the initial memory is also very large with respect to * lowmem, but we won't try to deal with that here. */ - extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), - extra_pages); + extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages, max_pages - max_pfn); i = 0; - while (i < memmap.nr_entries) { - phys_addr_t addr = map[i].addr; - phys_addr_t size = map[i].size; - u32 type = map[i].type; + addr = xen_e820_map[0].addr; + size = xen_e820_map[0].size; + while (i < xen_e820_map_entries) { + bool discard = false; + + chunk_size = size; + type = xen_e820_map[i].type; if (type == E820_RAM) { if (addr < mem_end) { - size = min(size, mem_end - addr); + chunk_size = min(size, mem_end - addr); } else if (extra_pages) { - size = min(size, PFN_PHYS(extra_pages)); - extra_pages -= PFN_DOWN(size); - xen_add_extra_mem(addr, size); - xen_max_p2m_pfn = PFN_DOWN(addr + size); + chunk_size = min(size, PFN_PHYS(extra_pages)); + pfn_s = PFN_UP(addr); + n_pfns = PFN_DOWN(addr + chunk_size) - pfn_s; + extra_pages -= n_pfns; + xen_add_extra_mem(pfn_s, n_pfns); + xen_max_p2m_pfn = pfn_s + n_pfns; } else - type = E820_UNUSABLE; + discard = true; } - xen_align_and_add_e820_region(addr, size, type); + if (!discard) + xen_align_and_add_e820_region(addr, chunk_size, type); - map[i].addr += size; - map[i].size -= size; - if (map[i].size == 0) + addr += chunk_size; + size -= chunk_size; + if (size == 0) { i++; + if (i < xen_e820_map_entries) { + addr = xen_e820_map[i].addr; + size = xen_e820_map[i].size; + } + } } /* * Set the rest as identity mapped, in case PCI BARs are * located here. - * - * PFNs above MAX_P2M_PFN are considered identity mapped as - * well. */ - set_phys_range_identity(map[i-1].addr / PAGE_SIZE, ~0ul); + set_phys_range_identity(addr / PAGE_SIZE, ~0ul); /* * In domU, the ISA region is normal, usable memory, but we @@ -684,34 +876,53 @@ char * __init xen_memory_setup(void) e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_RESERVED); + sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + /* - * Reserve Xen bits: - * - mfn_list - * - xen_start_info - * See comment above "struct start_info" in <xen/interface/xen.h> - * We tried to make the the memblock_reserve more selective so - * that it would be clear what region is reserved. Sadly we ran - * in the problem wherein on a 64-bit hypervisor with a 32-bit - * initial domain, the pt_base has the cr3 value which is not - * neccessarily where the pagetable starts! As Jan put it: " - * Actually, the adjustment turns out to be correct: The page - * tables for a 32-on-64 dom0 get allocated in the order "first L1", - * "first L2", "first L3", so the offset to the page table base is - * indeed 2. When reading xen/include/public/xen.h's comment - * very strictly, this is not a violation (since there nothing is said - * that the first thing in the page table space is pointed to by - * pt_base; I admit that this seems to be implied though, namely - * do I think that it is implied that the page table space is the - * range [pt_base, pt_base + nt_pt_frames), whereas that - * range here indeed is [pt_base - 2, pt_base - 2 + nt_pt_frames), - * which - without a priori knowledge - the kernel would have - * difficulty to figure out)." - so lets just fall back to the - * easy way and reserve the whole region. + * Check whether the kernel itself conflicts with the target E820 map. + * Failing now is better than running into weird problems later due + * to relocating (and even reusing) pages with kernel text or data. */ - memblock_reserve(__pa(xen_start_info->mfn_list), - xen_start_info->pt_base - xen_start_info->mfn_list); + if (xen_is_e820_reserved(__pa_symbol(_text), + __pa_symbol(__bss_stop) - __pa_symbol(_text))) { + xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n"); + BUG(); + } - sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + /* + * Check for a conflict of the hypervisor supplied page tables with + * the target E820 map. + */ + xen_pt_check_e820(); + + xen_reserve_xen_mfnlist(); + + /* Check for a conflict of the initrd with the target E820 map. */ + if (xen_is_e820_reserved(boot_params.hdr.ramdisk_image, + boot_params.hdr.ramdisk_size)) { + phys_addr_t new_area, start, size; + + new_area = xen_find_free_area(boot_params.hdr.ramdisk_size); + if (!new_area) { + xen_raw_console_write("Can't find new memory area for initrd needed due to E820 map conflict\n"); + BUG(); + } + + start = boot_params.hdr.ramdisk_image; + size = boot_params.hdr.ramdisk_size; + xen_phys_memcpy(new_area, start, size); + pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n", + start, start + size, new_area, new_area + size); + memblock_free(start, size); + boot_params.hdr.ramdisk_image = new_area; + boot_params.ext_ramdisk_image = new_area >> 32; + } + + /* + * Set identity map on non-RAM pages and prepare remapping the + * underlying RAM. + */ + xen_set_identity_and_remap(max_pfn); return "Xen"; } @@ -721,26 +932,30 @@ char * __init xen_memory_setup(void) */ char * __init xen_auto_xlated_memory_setup(void) { - static struct e820entry map[E820MAX] __initdata; - struct xen_memory_map memmap; int i; int rc; memmap.nr_entries = E820MAX; - set_xen_guest_handle(memmap.buffer, map); + set_xen_guest_handle(memmap.buffer, xen_e820_map); rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); if (rc < 0) panic("No memory map (%d)\n", rc); - sanitize_e820_map(map, ARRAY_SIZE(map), &memmap.nr_entries); + xen_e820_map_entries = memmap.nr_entries; + + sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), + &xen_e820_map_entries); - for (i = 0; i < memmap.nr_entries; i++) - e820_add_region(map[i].addr, map[i].size, map[i].type); + for (i = 0; i < xen_e820_map_entries; i++) + e820_add_region(xen_e820_map[i].addr, xen_e820_map[i].size, + xen_e820_map[i].type); - memblock_reserve(__pa(xen_start_info->mfn_list), - xen_start_info->pt_base - xen_start_info->mfn_list); + /* Remove p2m info, it is not needed. */ + xen_start_info->mfn_list = 0; + xen_start_info->first_p2m_pfn = 0; + xen_start_info->nr_p2m_frames = 0; return "Xen"; } @@ -753,17 +968,8 @@ char * __init xen_auto_xlated_memory_setup(void) static void __init fiddle_vdso(void) { #ifdef CONFIG_X86_32 - /* - * This could be called before selected_vdso32 is initialized, so - * just fiddle with both possible images. vdso_image_32_syscall - * can't be selected, since it only exists on 64-bit systems. - */ - u32 *mask; - mask = vdso_image_32_int80.data + - vdso_image_32_int80.sym_VDSO32_NOTE_MASK; - *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; - mask = vdso_image_32_sysenter.data + - vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK; + u32 *mask = vdso_image_32.data + + vdso_image_32.sym_VDSO32_NOTE_MASK; *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; #endif } diff --git a/kernel/arch/x86/xen/smp.c b/kernel/arch/x86/xen/smp.c index 864843844..3f4ebf026 100644 --- a/kernel/arch/x86/xen/smp.c +++ b/kernel/arch/x86/xen/smp.c @@ -26,6 +26,7 @@ #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> +#include <xen/interface/xenpmu.h> #include <asm/xen/interface.h> #include <asm/xen/hypercall.h> @@ -38,6 +39,7 @@ #include "xen-ops.h" #include "mmu.h" #include "smp.h" +#include "pmu.h" cpumask_var_t xen_cpu_initialized_map; @@ -50,6 +52,7 @@ static DEFINE_PER_CPU(struct xen_common_irq, xen_callfunc_irq) = { .irq = -1 }; static DEFINE_PER_CPU(struct xen_common_irq, xen_callfuncsingle_irq) = { .irq = -1 }; static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 }; static DEFINE_PER_CPU(struct xen_common_irq, xen_debug_irq) = { .irq = -1 }; +static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 }; static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id); static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id); @@ -148,11 +151,18 @@ static void xen_smp_intr_free(unsigned int cpu) kfree(per_cpu(xen_irq_work, cpu).name); per_cpu(xen_irq_work, cpu).name = NULL; } + + if (per_cpu(xen_pmu_irq, cpu).irq >= 0) { + unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL); + per_cpu(xen_pmu_irq, cpu).irq = -1; + kfree(per_cpu(xen_pmu_irq, cpu).name); + per_cpu(xen_pmu_irq, cpu).name = NULL; + } }; static int xen_smp_intr_init(unsigned int cpu) { int rc; - char *resched_name, *callfunc_name, *debug_name; + char *resched_name, *callfunc_name, *debug_name, *pmu_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, @@ -218,6 +228,18 @@ static int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_irq_work, cpu).irq = rc; per_cpu(xen_irq_work, cpu).name = callfunc_name; + if (is_xen_pmu(cpu)) { + pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); + rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, + xen_pmu_irq_handler, + IRQF_PERCPU|IRQF_NOBALANCING, + pmu_name, NULL); + if (rc < 0) + goto fail; + per_cpu(xen_pmu_irq, cpu).irq = rc; + per_cpu(xen_pmu_irq, cpu).name = pmu_name; + } + return 0; fail: @@ -335,6 +357,8 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) } set_cpu_sibling_map(0); + xen_pmu_init(0); + if (xen_smp_intr_init(0)) BUG(); @@ -429,7 +453,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) } #endif ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs); - ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir)); + ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir)); if (HYPERVISOR_vcpu_op(VCPUOP_initialise, cpu, ctxt)) BUG(); @@ -462,6 +486,8 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) if (rc) return rc; + xen_pmu_init(cpu); + rc = xen_smp_intr_init(cpu); if (rc) return rc; @@ -503,6 +529,7 @@ static void xen_cpu_die(unsigned int cpu) xen_smp_intr_free(cpu); xen_uninit_lock_cpu(cpu); xen_teardown_timer(cpu); + xen_pmu_finish(cpu); } } diff --git a/kernel/arch/x86/xen/spinlock.c b/kernel/arch/x86/xen/spinlock.c index 956374c1e..9e2ba5c6e 100644 --- a/kernel/arch/x86/xen/spinlock.c +++ b/kernel/arch/x86/xen/spinlock.c @@ -17,6 +17,56 @@ #include "xen-ops.h" #include "debugfs.h" +static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; +static DEFINE_PER_CPU(char *, irq_name); +static bool xen_pvspin = true; + +#ifdef CONFIG_QUEUED_SPINLOCKS + +#include <asm/qspinlock.h> + +static void xen_qlock_kick(int cpu) +{ + xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); +} + +/* + * Halt the current CPU & release it back to the host + */ +static void xen_qlock_wait(u8 *byte, u8 val) +{ + int irq = __this_cpu_read(lock_kicker_irq); + + /* If kicker interrupts not initialized yet, just spin */ + if (irq == -1) + return; + + /* clear pending */ + xen_clear_irq_pending(irq); + barrier(); + + /* + * We check the byte value after clearing pending IRQ to make sure + * that we won't miss a wakeup event because of the clearing. + * + * The sync_clear_bit() call in xen_clear_irq_pending() is atomic. + * So it is effectively a memory barrier for x86. + */ + if (READ_ONCE(*byte) != val) + return; + + /* + * If an interrupt happens here, it will leave the wakeup irq + * pending, which will cause xen_poll_irq() to return + * immediately. + */ + + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ + xen_poll_irq(irq); +} + +#else /* CONFIG_QUEUED_SPINLOCKS */ + enum xen_contention_stat { TAKEN_SLOW, TAKEN_SLOW_PICKUP, @@ -100,12 +150,9 @@ struct xen_lock_waiting { __ticket_t want; }; -static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; -static DEFINE_PER_CPU(char *, irq_name); static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); static cpumask_t waiting_cpus; -static bool xen_pvspin = true; __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { int irq = __this_cpu_read(lock_kicker_irq); @@ -217,6 +264,7 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) } } } +#endif /* CONFIG_QUEUED_SPINLOCKS */ static irqreturn_t dummy_handler(int irq, void *dev_id) { @@ -280,8 +328,16 @@ void __init xen_init_spinlocks(void) return; } printk(KERN_DEBUG "xen: PV spinlocks enabled\n"); +#ifdef CONFIG_QUEUED_SPINLOCKS + __pv_init_lock_hash(); + pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath; + pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock); + pv_lock_ops.wait = xen_qlock_wait; + pv_lock_ops.kick = xen_qlock_kick; +#else pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; +#endif } /* @@ -310,7 +366,7 @@ static __init int xen_parse_nopvspin(char *arg) } early_param("xen_nopvspin", xen_parse_nopvspin); -#ifdef CONFIG_XEN_DEBUG_FS +#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS) static struct dentry *d_spin_debug; diff --git a/kernel/arch/x86/xen/suspend.c b/kernel/arch/x86/xen/suspend.c index 53b4c0811..7f664c416 100644 --- a/kernel/arch/x86/xen/suspend.c +++ b/kernel/arch/x86/xen/suspend.c @@ -1,6 +1,7 @@ #include <linux/types.h> #include <linux/tick.h> +#include <xen/xen.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> #include <xen/events.h> @@ -11,6 +12,7 @@ #include "xen-ops.h" #include "mmu.h" +#include "pmu.h" static void xen_pv_pre_suspend(void) { @@ -32,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { @@ -67,16 +70,16 @@ static void xen_pv_post_suspend(int suspend_cancelled) void xen_arch_pre_suspend(void) { - if (xen_pv_domain()) - xen_pv_pre_suspend(); + if (xen_pv_domain()) + xen_pv_pre_suspend(); } void xen_arch_post_suspend(int cancelled) { - if (xen_pv_domain()) - xen_pv_post_suspend(cancelled); - else - xen_hvm_post_suspend(cancelled); + if (xen_pv_domain()) + xen_pv_post_suspend(cancelled); + else + xen_hvm_post_suspend(cancelled); } static void xen_vcpu_notify_restore(void *data) @@ -95,10 +98,20 @@ static void xen_vcpu_notify_suspend(void *data) void xen_arch_resume(void) { + int cpu; + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); + + for_each_online_cpu(cpu) + xen_pmu_init(cpu); } void xen_arch_suspend(void) { + int cpu; + + for_each_online_cpu(cpu) + xen_pmu_finish(cpu); + on_each_cpu(xen_vcpu_notify_suspend, NULL, 1); } diff --git a/kernel/arch/x86/xen/time.c b/kernel/arch/x86/xen/time.c index 55da33b1d..f1ba6a092 100644 --- a/kernel/arch/x86/xen/time.c +++ b/kernel/arch/x86/xen/time.c @@ -274,30 +274,18 @@ static s64 get_abs_timeout(unsigned long delta) return xen_clocksource_read() + delta; } -static void xen_timerop_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int xen_timerop_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - /* unsupported */ - WARN_ON(1); - break; - - case CLOCK_EVT_MODE_ONESHOT: - case CLOCK_EVT_MODE_RESUME: - break; - - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - HYPERVISOR_set_timer_op(0); /* cancel timeout */ - break; - } + /* cancel timeout */ + HYPERVISOR_set_timer_op(0); + + return 0; } static int xen_timerop_set_next_event(unsigned long delta, struct clock_event_device *evt) { - WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT); + WARN_ON(!clockevent_state_oneshot(evt)); if (HYPERVISOR_set_timer_op(get_abs_timeout(delta)) < 0) BUG(); @@ -310,46 +298,39 @@ static int xen_timerop_set_next_event(unsigned long delta, } static const struct clock_event_device xen_timerop_clockevent = { - .name = "xen", - .features = CLOCK_EVT_FEAT_ONESHOT, + .name = "xen", + .features = CLOCK_EVT_FEAT_ONESHOT, - .max_delta_ns = 0xffffffff, - .min_delta_ns = TIMER_SLOP, + .max_delta_ns = 0xffffffff, + .min_delta_ns = TIMER_SLOP, - .mult = 1, - .shift = 0, - .rating = 500, + .mult = 1, + .shift = 0, + .rating = 500, - .set_mode = xen_timerop_set_mode, - .set_next_event = xen_timerop_set_next_event, + .set_state_shutdown = xen_timerop_shutdown, + .set_next_event = xen_timerop_set_next_event, }; +static int xen_vcpuop_shutdown(struct clock_event_device *evt) +{ + int cpu = smp_processor_id(); + if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) || + HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); + + return 0; +} -static void xen_vcpuop_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int xen_vcpuop_set_oneshot(struct clock_event_device *evt) { int cpu = smp_processor_id(); - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - WARN_ON(1); /* unsupported */ - break; - - case CLOCK_EVT_MODE_ONESHOT: - if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) - BUG(); - break; + if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) + BUG(); - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - if (HYPERVISOR_vcpu_op(VCPUOP_stop_singleshot_timer, cpu, NULL) || - HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL)) - BUG(); - break; - case CLOCK_EVT_MODE_RESUME: - break; - } + return 0; } static int xen_vcpuop_set_next_event(unsigned long delta, @@ -359,7 +340,7 @@ static int xen_vcpuop_set_next_event(unsigned long delta, struct vcpu_set_singleshot_timer single; int ret; - WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT); + WARN_ON(!clockevent_state_oneshot(evt)); single.timeout_abs_ns = get_abs_timeout(delta); single.flags = VCPU_SSHOTTMR_future; @@ -382,7 +363,8 @@ static const struct clock_event_device xen_vcpuop_clockevent = { .shift = 0, .rating = 500, - .set_mode = xen_vcpuop_set_mode, + .set_state_shutdown = xen_vcpuop_shutdown, + .set_state_oneshot = xen_vcpuop_set_oneshot, .set_next_event = xen_vcpuop_set_next_event, }; diff --git a/kernel/arch/x86/xen/xen-asm_64.S b/kernel/arch/x86/xen/xen-asm_64.S index 985fc3ee0..f22667abf 100644 --- a/kernel/arch/x86/xen/xen-asm_64.S +++ b/kernel/arch/x86/xen/xen-asm_64.S @@ -15,6 +15,8 @@ #include <asm/percpu.h> #include <asm/processor-flags.h> #include <asm/segment.h> +#include <asm/asm-offsets.h> +#include <asm/thread_info.h> #include <xen/interface/xen.h> @@ -47,29 +49,13 @@ ENTRY(xen_iret) ENDPATCH(xen_iret) RELOC(xen_iret, 1b+1) -/* - * sysexit is not used for 64-bit processes, so it's only ever used to - * return to 32-bit compat userspace. - */ -ENTRY(xen_sysexit) - pushq $__USER32_DS - pushq %rcx - pushq $X86_EFLAGS_IF - pushq $__USER32_CS - pushq %rdx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysexit) -RELOC(xen_sysexit, 1b+1) - ENTRY(xen_sysret64) /* * We're already on the usermode stack at this point, but * still with the kernel gs, so we can easily switch back */ movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack), %rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq $__USER_DS pushq PER_CPU_VAR(rsp_scratch) @@ -88,7 +74,7 @@ ENTRY(xen_sysret32) * still with the kernel gs, so we can easily switch back */ movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(kernel_stack), %rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq $__USER32_DS pushq PER_CPU_VAR(rsp_scratch) @@ -128,7 +114,7 @@ RELOC(xen_sysret32, 1b+1) /* Normal 64-bit system call target */ ENTRY(xen_syscall_target) undo_xen_syscall - jmp system_call_after_swapgs + jmp entry_SYSCALL_64_after_swapgs ENDPROC(xen_syscall_target) #ifdef CONFIG_IA32_EMULATION @@ -136,13 +122,13 @@ ENDPROC(xen_syscall_target) /* 32-bit compat syscall target */ ENTRY(xen_syscall32_target) undo_xen_syscall - jmp ia32_cstar_target + jmp entry_SYSCALL_compat ENDPROC(xen_syscall32_target) /* 32-bit compat sysenter target */ ENTRY(xen_sysenter_target) undo_xen_syscall - jmp ia32_sysenter_target + jmp entry_SYSENTER_compat ENDPROC(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ diff --git a/kernel/arch/x86/xen/xen-head.S b/kernel/arch/x86/xen/xen-head.S index 8afdfccf6..b65f59a35 100644 --- a/kernel/arch/x86/xen/xen-head.S +++ b/kernel/arch/x86/xen/xen-head.S @@ -104,6 +104,8 @@ ENTRY(hypercall_page) ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE, _ASM_PTR __PAGE_OFFSET) #else ELFNOTE(Xen, XEN_ELFNOTE_VIRT_BASE, _ASM_PTR __START_KERNEL_map) + /* Map the p2m table to a 512GB-aligned user address. */ + ELFNOTE(Xen, XEN_ELFNOTE_INIT_P2M, .quad PGDIR_SIZE) #endif ELFNOTE(Xen, XEN_ELFNOTE_ENTRY, _ASM_PTR startup_xen) ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, _ASM_PTR hypercall_page) diff --git a/kernel/arch/x86/xen/xen-ops.h b/kernel/arch/x86/xen/xen-ops.h index bef30cbb5..1399423f3 100644 --- a/kernel/arch/x86/xen/xen-ops.h +++ b/kernel/arch/x86/xen/xen-ops.h @@ -35,13 +35,20 @@ void xen_build_mfn_list_list(void); void xen_setup_machphys_mapping(void); void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); void xen_reserve_top(void); +void __init xen_reserve_special_pages(void); +void __init xen_pt_check_e820(void); void xen_mm_pin_all(void); void xen_mm_unpin_all(void); +#ifdef CONFIG_X86_64 +void __init xen_relocate_p2m(void); +#endif +bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size); unsigned long __ref xen_chk_extra_mem(unsigned long pfn); void __init xen_inv_extra_mem(void); void __init xen_remap_memory(void); +phys_addr_t __init xen_find_free_area(phys_addr_t size); char * __init xen_memory_setup(void); char * xen_auto_xlated_memory_setup(void); void __init xen_arch_setup(void); @@ -132,7 +139,9 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); +#ifdef CONFIG_X86_32 __visible void xen_sysexit(void); +#endif __visible void xen_sysret32(void); __visible void xen_sysret64(void); __visible void xen_adjust_exception_frame(void); |