From e09b41010ba33a20a87472ee821fa407a5b8da36 Mon Sep 17 00:00:00 2001 From: José Pekkarinen Date: Mon, 11 Apr 2016 10:41:07 +0300 Subject: 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. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 --- kernel/arch/arm64/Kconfig | 305 +++-- kernel/arch/arm64/Kconfig.debug | 6 +- kernel/arch/arm64/Kconfig.platforms | 131 ++ kernel/arch/arm64/Makefile | 28 +- kernel/arch/arm64/boot/Makefile | 12 + kernel/arch/arm64/boot/dts/Makefile | 11 + kernel/arch/arm64/boot/dts/altera/Makefile | 5 + .../arm64/boot/dts/altera/socfpga_stratix10.dtsi | 358 ++++++ .../boot/dts/altera/socfpga_stratix10_socdk.dts | 39 + kernel/arch/arm64/boot/dts/amd/amd-overdrive.dts | 1 - kernel/arch/arm64/boot/dts/apm/Makefile | 1 + kernel/arch/arm64/boot/dts/apm/apm-merlin.dts | 72 ++ kernel/arch/arm64/boot/dts/apm/apm-mustang.dts | 22 + kernel/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi | 271 ++++ kernel/arch/arm64/boot/dts/apm/apm-storm.dtsi | 203 ++- kernel/arch/arm64/boot/dts/arm/Makefile | 3 +- kernel/arch/arm64/boot/dts/arm/juno-base.dtsi | 213 ++++ kernel/arch/arm64/boot/dts/arm/juno-clocks.dtsi | 4 +- .../arch/arm64/boot/dts/arm/juno-motherboard.dtsi | 146 +++ kernel/arch/arm64/boot/dts/arm/juno-r1.dts | 172 +++ kernel/arch/arm64/boot/dts/arm/juno.dts | 177 +-- .../arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi | 2 + .../boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts | 191 +++ .../arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi | 1 + kernel/arch/arm64/boot/dts/broadcom/Makefile | 5 + kernel/arch/arm64/boot/dts/broadcom/ns2-svk.dts | 59 + kernel/arch/arm64/boot/dts/broadcom/ns2.dtsi | 118 ++ .../arch/arm64/boot/dts/cavium/thunder-88xx.dtsi | 9 + .../arm64/boot/dts/exynos/exynos7-pinctrl.dtsi | 103 ++ kernel/arch/arm64/boot/dts/exynos/exynos7.dtsi | 7 + kernel/arch/arm64/boot/dts/freescale/Makefile | 4 +- .../arm64/boot/dts/freescale/fsl-ls2080a-qds.dts | 204 +++ .../arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts | 166 +++ .../arm64/boot/dts/freescale/fsl-ls2080a-simu.dts | 70 + .../arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi | 520 ++++++++ .../arm64/boot/dts/freescale/fsl-ls2085a-simu.dts | 65 - .../arch/arm64/boot/dts/freescale/fsl-ls2085a.dtsi | 163 --- kernel/arch/arm64/boot/dts/hisilicon/Makefile | 5 + .../arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts | 34 + kernel/arch/arm64/boot/dts/hisilicon/hi6220.dtsi | 212 ++++ kernel/arch/arm64/boot/dts/hisilicon/hip05-d02.dts | 36 + kernel/arch/arm64/boot/dts/hisilicon/hip05.dtsi | 271 ++++ .../arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi | 191 +++ kernel/arch/arm64/boot/dts/marvell/Makefile | 6 + .../arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts | 66 + .../arch/arm64/boot/dts/marvell/berlin4ct-stb.dts | 66 + kernel/arch/arm64/boot/dts/marvell/berlin4ct.dtsi | 284 +++++ kernel/arch/arm64/boot/dts/mediatek/Makefile | 1 + kernel/arch/arm64/boot/dts/mediatek/mt6795-evb.dts | 41 + kernel/arch/arm64/boot/dts/mediatek/mt6795.dtsi | 175 +++ kernel/arch/arm64/boot/dts/mediatek/mt8173-evb.dts | 371 ++++++ kernel/arch/arm64/boot/dts/mediatek/mt8173.dtsi | 392 +++++- .../arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi | 40 + .../arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi | 13 + kernel/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi | 84 ++ kernel/arch/arm64/boot/dts/qcom/msm8916-mtp.dtsi | 1 + kernel/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi | 502 ++++++++ kernel/arch/arm64/boot/dts/qcom/msm8916.dtsi | 299 ++++- kernel/arch/arm64/boot/dts/qcom/pm8916.dtsi | 99 ++ kernel/arch/arm64/boot/dts/rockchip/Makefile | 5 + kernel/arch/arm64/boot/dts/rockchip/rk3368-r88.dts | 354 ++++++ kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi | 900 +++++++++++++ kernel/arch/arm64/boot/dts/skeleton.dtsi | 13 - kernel/arch/arm64/boot/dts/sprd/sc9836.dtsi | 99 +- kernel/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts | 89 ++ kernel/arch/arm64/boot/dts/xilinx/zynqmp.dtsi | 233 ++-- kernel/arch/arm64/configs/defconfig | 38 +- kernel/arch/arm64/crypto/aes-ce-ccm-glue.c | 70 +- kernel/arch/arm64/crypto/aes-ce-cipher.c | 2 +- kernel/arch/arm64/include/asm/Kbuild | 2 +- kernel/arch/arm64/include/asm/acpi.h | 33 +- kernel/arch/arm64/include/asm/alternative-asm.h | 29 - kernel/arch/arm64/include/asm/alternative.h | 118 +- kernel/arch/arm64/include/asm/arch_gicv3.h | 171 +++ kernel/arch/arm64/include/asm/assembler.h | 25 +- kernel/arch/arm64/include/asm/atomic.h | 320 ++--- kernel/arch/arm64/include/asm/atomic_ll_sc.h | 269 ++++ kernel/arch/arm64/include/asm/atomic_lse.h | 430 +++++++ kernel/arch/arm64/include/asm/barrier.h | 42 +- kernel/arch/arm64/include/asm/boot.h | 14 + kernel/arch/arm64/include/asm/bug.h | 64 + kernel/arch/arm64/include/asm/cache.h | 2 +- kernel/arch/arm64/include/asm/cacheflush.h | 12 +- kernel/arch/arm64/include/asm/cachetype.h | 4 +- kernel/arch/arm64/include/asm/cmpxchg.h | 351 +++-- kernel/arch/arm64/include/asm/compat.h | 3 +- kernel/arch/arm64/include/asm/cpu.h | 4 + kernel/arch/arm64/include/asm/cpu_ops.h | 27 +- kernel/arch/arm64/include/asm/cpufeature.h | 123 +- kernel/arch/arm64/include/asm/cpuidle.h | 8 +- kernel/arch/arm64/include/asm/cputype.h | 33 +- kernel/arch/arm64/include/asm/dcc.h | 55 + kernel/arch/arm64/include/asm/debug-monitors.h | 44 +- kernel/arch/arm64/include/asm/dma-mapping.h | 93 +- kernel/arch/arm64/include/asm/esr.h | 9 + kernel/arch/arm64/include/asm/exception.h | 6 + kernel/arch/arm64/include/asm/fixmap.h | 24 +- kernel/arch/arm64/include/asm/futex.h | 10 + kernel/arch/arm64/include/asm/hardirq.h | 9 - kernel/arch/arm64/include/asm/hugetlb.h | 17 - kernel/arch/arm64/include/asm/hw_breakpoint.h | 21 + kernel/arch/arm64/include/asm/hwcap.h | 8 + kernel/arch/arm64/include/asm/insn.h | 3 + kernel/arch/arm64/include/asm/io.h | 9 +- kernel/arch/arm64/include/asm/irq.h | 13 +- kernel/arch/arm64/include/asm/irq_work.h | 11 - kernel/arch/arm64/include/asm/jump_label.h | 18 +- kernel/arch/arm64/include/asm/kasan.h | 38 + kernel/arch/arm64/include/asm/kernel-pgtable.h | 83 ++ kernel/arch/arm64/include/asm/kvm_arm.h | 32 +- kernel/arch/arm64/include/asm/kvm_asm.h | 29 +- kernel/arch/arm64/include/asm/kvm_emulate.h | 18 +- kernel/arch/arm64/include/asm/kvm_host.h | 80 +- kernel/arch/arm64/include/asm/lse.h | 53 + kernel/arch/arm64/include/asm/memory.h | 13 +- kernel/arch/arm64/include/asm/mmu.h | 17 +- kernel/arch/arm64/include/asm/mmu_context.h | 113 +- kernel/arch/arm64/include/asm/page.h | 27 +- kernel/arch/arm64/include/asm/percpu.h | 8 - kernel/arch/arm64/include/asm/perf_event.h | 9 +- kernel/arch/arm64/include/asm/pgalloc.h | 1 + kernel/arch/arm64/include/asm/pgtable-hwdef.h | 51 +- kernel/arch/arm64/include/asm/pgtable.h | 207 ++- kernel/arch/arm64/include/asm/pmu.h | 83 -- kernel/arch/arm64/include/asm/proc-fns.h | 4 - kernel/arch/arm64/include/asm/processor.h | 21 +- kernel/arch/arm64/include/asm/psci.h | 20 - kernel/arch/arm64/include/asm/ptrace.h | 20 +- kernel/arch/arm64/include/asm/smp.h | 6 +- kernel/arch/arm64/include/asm/smp_plat.h | 18 +- kernel/arch/arm64/include/asm/spinlock.h | 147 ++- kernel/arch/arm64/include/asm/spinlock_types.h | 2 + kernel/arch/arm64/include/asm/string.h | 16 + kernel/arch/arm64/include/asm/suspend.h | 2 +- kernel/arch/arm64/include/asm/sysreg.h | 187 ++- kernel/arch/arm64/include/asm/system_misc.h | 14 +- kernel/arch/arm64/include/asm/thread_info.h | 8 +- kernel/arch/arm64/include/asm/tlb.h | 21 +- kernel/arch/arm64/include/asm/tlbflush.h | 96 +- kernel/arch/arm64/include/asm/topology.h | 11 +- kernel/arch/arm64/include/asm/traps.h | 23 +- kernel/arch/arm64/include/asm/uaccess.h | 11 + kernel/arch/arm64/include/asm/unistd.h | 2 +- kernel/arch/arm64/include/asm/unistd32.h | 9 + kernel/arch/arm64/include/asm/xen/events.h | 6 + kernel/arch/arm64/include/uapi/asm/hwcap.h | 1 + kernel/arch/arm64/include/uapi/asm/kvm.h | 39 +- kernel/arch/arm64/include/uapi/asm/ptrace.h | 1 + kernel/arch/arm64/include/uapi/asm/signal.h | 3 + kernel/arch/arm64/kernel/Makefile | 17 +- kernel/arch/arm64/kernel/acpi.c | 167 +-- kernel/arch/arm64/kernel/alternative.c | 101 +- kernel/arch/arm64/kernel/arm64ksyms.c | 3 + kernel/arch/arm64/kernel/armv8_deprecated.c | 35 +- kernel/arch/arm64/kernel/asm-offsets.c | 12 +- kernel/arch/arm64/kernel/cpu_errata.c | 20 +- kernel/arch/arm64/kernel/cpu_ops.c | 74 +- kernel/arch/arm64/kernel/cpufeature.c | 890 ++++++++++++- kernel/arch/arm64/kernel/cpuidle.c | 13 +- kernel/arch/arm64/kernel/cpuinfo.c | 261 ++-- kernel/arch/arm64/kernel/debug-monitors.c | 39 +- kernel/arch/arm64/kernel/efi-entry.S | 10 +- kernel/arch/arm64/kernel/efi-stub.c | 45 - kernel/arch/arm64/kernel/efi.c | 73 +- kernel/arch/arm64/kernel/entry-ftrace.S | 22 +- kernel/arch/arm64/kernel/entry.S | 61 +- kernel/arch/arm64/kernel/entry32.S | 2 - kernel/arch/arm64/kernel/fpsimd.c | 45 +- kernel/arch/arm64/kernel/head.S | 150 +-- kernel/arch/arm64/kernel/hw_breakpoint.c | 40 +- kernel/arch/arm64/kernel/image.h | 38 +- kernel/arch/arm64/kernel/insn.c | 65 +- kernel/arch/arm64/kernel/irq.c | 64 - kernel/arch/arm64/kernel/jump_label.c | 2 +- kernel/arch/arm64/kernel/kgdb.c | 12 +- kernel/arch/arm64/kernel/module.c | 16 +- kernel/arch/arm64/kernel/pci.c | 13 + kernel/arch/arm64/kernel/perf_callchain.c | 196 +++ kernel/arch/arm64/kernel/perf_event.c | 1340 ++++---------------- kernel/arch/arm64/kernel/process.c | 65 +- kernel/arch/arm64/kernel/psci.c | 416 +----- kernel/arch/arm64/kernel/ptrace.c | 98 +- kernel/arch/arm64/kernel/setup.c | 382 ++---- kernel/arch/arm64/kernel/signal32.c | 4 +- kernel/arch/arm64/kernel/sleep.S | 23 +- kernel/arch/arm64/kernel/smp.c | 283 +++-- kernel/arch/arm64/kernel/smp_spin_table.c | 8 +- kernel/arch/arm64/kernel/stacktrace.c | 6 +- kernel/arch/arm64/kernel/suspend.c | 41 +- kernel/arch/arm64/kernel/time.c | 10 +- kernel/arch/arm64/kernel/topology.c | 2 +- kernel/arch/arm64/kernel/traps.c | 112 +- kernel/arch/arm64/kernel/vdso.c | 7 +- kernel/arch/arm64/kernel/vdso/Makefile | 3 + kernel/arch/arm64/kernel/vmlinux.lds.S | 22 +- kernel/arch/arm64/kvm/Kconfig | 19 +- kernel/arch/arm64/kvm/Makefile | 4 +- kernel/arch/arm64/kvm/debug.c | 217 ++++ kernel/arch/arm64/kvm/guest.c | 45 +- kernel/arch/arm64/kvm/handle_exit.c | 46 +- kernel/arch/arm64/kvm/hyp.S | 689 ++++------ kernel/arch/arm64/kvm/inject_fault.c | 2 +- kernel/arch/arm64/kvm/reset.c | 22 +- kernel/arch/arm64/kvm/sys_regs.c | 397 ++++-- kernel/arch/arm64/kvm/sys_regs.h | 14 +- kernel/arch/arm64/kvm/sys_regs_generic_v8.c | 6 +- kernel/arch/arm64/kvm/trace.h | 123 ++ kernel/arch/arm64/kvm/vgic-v2-switch.S | 3 - kernel/arch/arm64/kvm/vgic-v3-switch.S | 2 - kernel/arch/arm64/lib/Makefile | 13 + kernel/arch/arm64/lib/atomic_ll_sc.c | 3 + kernel/arch/arm64/lib/bitops.S | 45 +- kernel/arch/arm64/lib/clear_user.S | 8 + kernel/arch/arm64/lib/copy_from_user.S | 81 +- kernel/arch/arm64/lib/copy_in_user.S | 70 +- kernel/arch/arm64/lib/copy_template.S | 193 +++ kernel/arch/arm64/lib/copy_to_user.S | 70 +- kernel/arch/arm64/lib/memchr.S | 2 +- kernel/arch/arm64/lib/memcmp.S | 2 +- kernel/arch/arm64/lib/memcpy.S | 184 +-- kernel/arch/arm64/lib/memmove.S | 9 +- kernel/arch/arm64/lib/memset.S | 5 +- kernel/arch/arm64/lib/strcmp.S | 2 +- kernel/arch/arm64/lib/strlen.S | 2 +- kernel/arch/arm64/lib/strncmp.S | 2 +- kernel/arch/arm64/mm/Makefile | 3 + kernel/arch/arm64/mm/cache.S | 92 +- kernel/arch/arm64/mm/context.c | 262 ++-- kernel/arch/arm64/mm/dma-mapping.c | 605 ++++++++- kernel/arch/arm64/mm/dump.c | 18 +- kernel/arch/arm64/mm/fault.c | 69 +- kernel/arch/arm64/mm/flush.c | 5 - kernel/arch/arm64/mm/hugetlbpage.c | 11 - kernel/arch/arm64/mm/init.c | 27 +- kernel/arch/arm64/mm/kasan_init.c | 165 +++ kernel/arch/arm64/mm/mmu.c | 150 ++- kernel/arch/arm64/mm/pageattr.c | 5 +- kernel/arch/arm64/mm/pgd.c | 2 - kernel/arch/arm64/mm/proc-macros.S | 12 + kernel/arch/arm64/mm/proc.S | 83 +- kernel/arch/arm64/net/bpf_jit.h | 3 +- kernel/arch/arm64/net/bpf_jit_comp.c | 141 +- 242 files changed, 16323 insertions(+), 5761 deletions(-) create mode 100644 kernel/arch/arm64/Kconfig.platforms create mode 100644 kernel/arch/arm64/boot/dts/altera/Makefile create mode 100644 kernel/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi create mode 100644 kernel/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts create mode 100644 kernel/arch/arm64/boot/dts/apm/apm-merlin.dts create mode 100644 kernel/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi create mode 100644 kernel/arch/arm64/boot/dts/arm/juno-base.dtsi create mode 100644 kernel/arch/arm64/boot/dts/arm/juno-r1.dts create mode 100644 kernel/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts create mode 120000 kernel/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi create mode 100644 kernel/arch/arm64/boot/dts/broadcom/Makefile create mode 100644 kernel/arch/arm64/boot/dts/broadcom/ns2-svk.dts create mode 100644 kernel/arch/arm64/boot/dts/broadcom/ns2.dtsi create mode 100644 kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts create mode 100644 kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts create mode 100644 kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts create mode 100644 kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi delete mode 100644 kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a-simu.dts delete mode 100644 kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a.dtsi create mode 100644 kernel/arch/arm64/boot/dts/hisilicon/Makefile create mode 100644 kernel/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts create mode 100644 kernel/arch/arm64/boot/dts/hisilicon/hi6220.dtsi create mode 100644 kernel/arch/arm64/boot/dts/hisilicon/hip05-d02.dts create mode 100644 kernel/arch/arm64/boot/dts/hisilicon/hip05.dtsi create mode 100644 kernel/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi create mode 100644 kernel/arch/arm64/boot/dts/marvell/Makefile create mode 100644 kernel/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts create mode 100644 kernel/arch/arm64/boot/dts/marvell/berlin4ct-stb.dts create mode 100644 kernel/arch/arm64/boot/dts/marvell/berlin4ct.dtsi create mode 100644 kernel/arch/arm64/boot/dts/mediatek/mt6795-evb.dts create mode 100644 kernel/arch/arm64/boot/dts/mediatek/mt6795.dtsi create mode 100644 kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi create mode 100644 kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi create mode 100644 kernel/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi create mode 100644 kernel/arch/arm64/boot/dts/qcom/pm8916.dtsi create mode 100644 kernel/arch/arm64/boot/dts/rockchip/Makefile create mode 100644 kernel/arch/arm64/boot/dts/rockchip/rk3368-r88.dts create mode 100644 kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi delete mode 100644 kernel/arch/arm64/boot/dts/skeleton.dtsi delete mode 100644 kernel/arch/arm64/include/asm/alternative-asm.h create mode 100644 kernel/arch/arm64/include/asm/arch_gicv3.h create mode 100644 kernel/arch/arm64/include/asm/atomic_ll_sc.h create mode 100644 kernel/arch/arm64/include/asm/atomic_lse.h create mode 100644 kernel/arch/arm64/include/asm/boot.h create mode 100644 kernel/arch/arm64/include/asm/bug.h create mode 100644 kernel/arch/arm64/include/asm/dcc.h create mode 100644 kernel/arch/arm64/include/asm/kasan.h create mode 100644 kernel/arch/arm64/include/asm/kernel-pgtable.h create mode 100644 kernel/arch/arm64/include/asm/lse.h delete mode 100644 kernel/arch/arm64/include/asm/pmu.h delete mode 100644 kernel/arch/arm64/include/asm/psci.h delete mode 100644 kernel/arch/arm64/kernel/efi-stub.c create mode 100644 kernel/arch/arm64/kernel/perf_callchain.c create mode 100644 kernel/arch/arm64/kvm/debug.c create mode 100644 kernel/arch/arm64/lib/atomic_ll_sc.c create mode 100644 kernel/arch/arm64/lib/copy_template.S create mode 100644 kernel/arch/arm64/mm/kasan_init.c (limited to 'kernel/arch/arm64') diff --git a/kernel/arch/arm64/Kconfig b/kernel/arch/arm64/Kconfig index 09a41259b..1baa6537c 100644 --- a/kernel/arch/arm64/Kconfig +++ b/kernel/arch/arm64/Kconfig @@ -1,5 +1,6 @@ config ARM64 def_bool y + select ACPI_CCA_REQUIRED if ACPI select ACPI_GENERIC_GSI if ACPI select ACPI_REDUCED_HARDWARE_ONLY if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE @@ -19,16 +20,20 @@ config ARM64 select ARM_GIC_V2M if PCI_MSI select ARM_GIC_V3 select ARM_GIC_V3_ITS if PCI_MSI + select ARM_PSCI_FW select BUILDTIME_EXTABLE_SORT select CLONE_BACKWARDS select COMMON_CLK select CPU_PM if (SUSPEND || CPU_IDLE) select DCACHE_WORD_ACCESS + select EDAC_SUPPORT + select FRAME_POINTER select GENERIC_ALLOCATOR select GENERIC_CLOCKEVENTS - select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_CPU_AUTOPROBE select GENERIC_EARLY_IOREMAP + select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -44,6 +49,7 @@ config ARM64 select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK @@ -51,6 +57,7 @@ config ARM64 select HAVE_C_RECORDMCOUNT select HAVE_CC_STACKPROTECTOR select HAVE_CMPXCHG_DOUBLE + select HAVE_CMPXCHG_LOCAL select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_API_DEBUG @@ -71,6 +78,7 @@ config ARM64 select HAVE_RCU_TABLE_FREE select HAVE_PREEMPT_LAZY select HAVE_SYSCALL_TRACEPOINTS + select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA @@ -116,6 +124,14 @@ config TRACE_IRQFLAGS_SUPPORT config RWSEM_XCHGADD_ALGORITHM def_bool y +config GENERIC_BUG + def_bool y + depends on BUG + +config GENERIC_BUG_RELATIVE_POINTERS + def_bool y + depends on GENERIC_BUG + config GENERIC_HWEIGHT def_bool y @@ -140,6 +156,9 @@ config NEED_DMA_MAP_STATE config NEED_SG_DMA_LENGTH def_bool y +config SMP + def_bool y + config SWIOTLB def_bool y @@ -154,114 +173,18 @@ config FIX_EARLYCON_MEM config PGTABLE_LEVELS int + default 2 if ARM64_16K_PAGES && ARM64_VA_BITS_36 default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42 default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48 default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39 - default 4 if ARM64_4K_PAGES && ARM64_VA_BITS_48 + default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47 + default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48 source "init/Kconfig" source "kernel/Kconfig.freezer" -menu "Platform selection" - -config ARCH_EXYNOS - bool - help - This enables support for Samsung Exynos SoC family - -config ARCH_EXYNOS7 - bool "ARMv8 based Samsung Exynos7" - select ARCH_EXYNOS - select COMMON_CLK_SAMSUNG - select HAVE_S3C2410_WATCHDOG if WATCHDOG - select HAVE_S3C_RTC if RTC_CLASS - select PINCTRL - select PINCTRL_EXYNOS - - help - This enables support for Samsung Exynos7 SoC family - -config ARCH_FSL_LS2085A - bool "Freescale LS2085A SOC" - help - This enables support for Freescale LS2085A SOC. - -config ARCH_MEDIATEK - bool "Mediatek MT65xx & MT81xx ARMv8 SoC" - select ARM_GIC - select PINCTRL - help - Support for Mediatek MT65xx & MT81xx ARMv8 SoCs - -config ARCH_QCOM - bool "Qualcomm Platforms" - select PINCTRL - help - This enables support for the ARMv8 based Qualcomm chipsets. - -config ARCH_SEATTLE - bool "AMD Seattle SoC Family" - help - This enables support for AMD Seattle SOC Family - -config ARCH_TEGRA - bool "NVIDIA Tegra SoC Family" - select ARCH_HAS_RESET_CONTROLLER - select ARCH_REQUIRE_GPIOLIB - select CLKDEV_LOOKUP - select CLKSRC_MMIO - select CLKSRC_OF - select GENERIC_CLOCKEVENTS - select HAVE_CLK - select PINCTRL - select RESET_CONTROLLER - help - This enables support for the NVIDIA Tegra SoC family. - -config ARCH_TEGRA_132_SOC - bool "NVIDIA Tegra132 SoC" - depends on ARCH_TEGRA - select PINCTRL_TEGRA124 - select USB_ULPI if USB_PHY - select USB_ULPI_VIEWPORT if USB_PHY - help - Enable support for NVIDIA Tegra132 SoC, based on the Denver - ARMv8 CPU. The Tegra132 SoC is similar to the Tegra124 SoC, - but contains an NVIDIA Denver CPU complex in place of - Tegra124's "4+1" Cortex-A15 CPU complex. - -config ARCH_SPRD - bool "Spreadtrum SoC platform" - help - Support for Spreadtrum ARM based SoCs - -config ARCH_THUNDER - bool "Cavium Inc. Thunder SoC Family" - help - This enables support for Cavium's Thunder Family of SoCs. - -config ARCH_VEXPRESS - bool "ARMv8 software model (Versatile Express)" - select ARCH_REQUIRE_GPIOLIB - select COMMON_CLK_VERSATILE - select POWER_RESET_VEXPRESS - select VEXPRESS_CONFIG - help - This enables support for the ARMv8 software model (Versatile - Express). - -config ARCH_XGENE - bool "AppliedMicro X-Gene SOC Family" - help - This enables support for AppliedMicro X-Gene SOC Family - -config ARCH_ZYNQMP - bool "Xilinx ZynqMP Family" - help - This enables support for Xilinx ZynqMP Family - -endmenu +source "arch/arm64/Kconfig.platforms" menu "Bus support" @@ -394,6 +317,27 @@ config ARM64_ERRATUM_832075 If unsure, say Y. +config ARM64_ERRATUM_834220 + bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault" + depends on KVM + default y + help + This option adds an alternative code sequence to work around ARM + erratum 834220 on Cortex-A57 parts up to r1p2. + + Affected Cortex-A57 parts might report a Stage 2 translation + fault as the result of a Stage 1 fault for load crossing a + page boundary when there is a permission or device memory + alignment fault at Stage 1 and a translation fault at Stage 2. + + The workaround is to verify that the Stage 1 translation + doesn't generate a fault before handling the Stage 2 fault. + Please note that this does not necessarily enable the workaround, + as it depends on the alternative framework, which will only patch + the kernel if an affected CPU is detected. + + If unsure, say Y. + config ARM64_ERRATUM_845719 bool "Cortex-A53: 845719: a load might read incorrect data" depends on COMPAT @@ -431,6 +375,33 @@ config ARM64_ERRATUM_843419 If unsure, say Y. +config CAVIUM_ERRATUM_22375 + bool "Cavium erratum 22375, 24313" + default y + help + Enable workaround for erratum 22375, 24313. + + This implements two gicv3-its errata workarounds for ThunderX. Both + with small impact affecting only ITS table allocation. + + erratum 22375: only alloc 8MB table size + erratum 24313: ignore memory access type + + The fixes are in ITS initialization and basically ignore memory access + type and table size provided by the TYPER and BASER registers. + + If unsure, say Y. + +config CAVIUM_ERRATUM_23154 + bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed" + default y + help + The gicv3 of ThunderX requires a modified version for + reading the IAR status to ensure data synchronization + (access to icc_iar1_el1 is not sync'ed before and after). + + If unsure, say Y. + endmenu @@ -445,25 +416,37 @@ config ARM64_4K_PAGES help This feature enables 4KB pages support. +config ARM64_16K_PAGES + bool "16KB" + help + The system will use 16KB pages support. AArch32 emulation + requires applications compiled with 16K (or a multiple of 16K) + aligned segments. + config ARM64_64K_PAGES bool "64KB" help This feature enables 64KB pages support (4KB by default) allowing only two levels of page tables and faster TLB - look-up. AArch32 emulation is not available when this feature - is enabled. + look-up. AArch32 emulation requires applications compiled + with 64K aligned segments. endchoice choice prompt "Virtual address space size" default ARM64_VA_BITS_39 if ARM64_4K_PAGES + default ARM64_VA_BITS_47 if ARM64_16K_PAGES default ARM64_VA_BITS_42 if ARM64_64K_PAGES help Allows choosing one of multiple possible virtual address space sizes. The level of translation table is determined by a combination of page size and virtual address space size. +config ARM64_VA_BITS_36 + bool "36-bit" if EXPERT + depends on ARM64_16K_PAGES + config ARM64_VA_BITS_39 bool "39-bit" depends on ARM64_4K_PAGES @@ -472,6 +455,10 @@ config ARM64_VA_BITS_42 bool "42-bit" depends on ARM64_64K_PAGES +config ARM64_VA_BITS_47 + bool "47-bit" + depends on ARM64_16K_PAGES + config ARM64_VA_BITS_48 bool "48-bit" @@ -479,8 +466,10 @@ endchoice config ARM64_VA_BITS int + default 36 if ARM64_VA_BITS_36 default 39 if ARM64_VA_BITS_39 default 42 if ARM64_VA_BITS_42 + default 47 if ARM64_VA_BITS_47 default 48 if ARM64_VA_BITS_48 config CPU_BIG_ENDIAN @@ -488,22 +477,8 @@ config CPU_BIG_ENDIAN help Say Y if you plan on running a kernel in big-endian mode. -config SMP - bool "Symmetric Multi-Processing" - help - This enables support for systems with more than one CPU. If - you say N here, the kernel will run on single and - multiprocessor machines, but will use only one CPU of a - multiprocessor machine. If you say Y here, the kernel will run - on many, but not all, single processor machines. On a single - processor machine, the kernel will run faster if you say N - here. - - If you don't know what to do here, say N. - config SCHED_MC bool "Multi-core scheduler support" - 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 @@ -511,7 +486,6 @@ config SCHED_MC config SCHED_SMT bool "SMT scheduler support" - depends on SMP help Improves the CPU scheduler's decision making when dealing with MultiThreading at a cost of slightly increased overhead in some @@ -520,26 +494,18 @@ config SCHED_SMT config NR_CPUS int "Maximum number of CPUs (2-4096)" range 2 4096 - depends on SMP # These have to remain sorted largest to smallest default "64" config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" - depends on SMP + select GENERIC_IRQ_MIGRATION help Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. source kernel/Kconfig.preempt - -config UP_LATE_INIT - def_bool y - depends on !SMP - -config HZ - int - default 100 +source kernel/Kconfig.hz config ARCH_HAS_HOLES_MEMORYMODEL def_bool y if SPARSEMEM @@ -558,12 +524,8 @@ config HAVE_ARCH_PFN_VALID def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM config HW_PERF_EVENTS - bool "Enable hardware performance counter support for perf events" - depends on PERF_EVENTS - default y - help - Enable hardware performance counter support for perf events. If - disabled, perf events will use software events only. + def_bool y + depends on ARM_PMU config SYS_SUPPORTS_HUGETLBFS def_bool y @@ -572,7 +534,7 @@ config ARCH_WANT_GENERAL_HUGETLB def_bool y config ARCH_WANT_HUGE_PMD_SHARE - def_bool y if !ARM64_64K_PAGES + def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) config HAVE_ARCH_TRANSPARENT_HUGEPAGE def_bool y @@ -609,7 +571,25 @@ config XEN config FORCE_MAX_ZONEORDER int default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE) + default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE) default "11" + help + The kernel memory allocator divides physically contiguous memory + blocks into "zones", where each zone is a power of two number of + pages. This option selects the largest power of two that the kernel + keeps in the memory allocator. If you need to allocate very large + blocks of physically contiguous memory, then you may need to + increase this value. + + This config option is actually maximum order plus one. For example, + a value of 11 means that the largest free memory block is 2^10 pages. + + We make sure that we can allocate upto a HugePage size for each configuration. + Hence we have : + MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2 + + However for 4K, we choose a higher default value, 11 as opposed to 10, giving us + 4M allocations matching the default size used by generic code. menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" @@ -678,6 +658,53 @@ config SETEND_EMULATION If unsure, say Y endif +menu "ARMv8.1 architectural features" + +config ARM64_HW_AFDBM + bool "Support for hardware updates of the Access and Dirty page flags" + default y + help + The ARMv8.1 architecture extensions introduce support for + hardware updates of the access and dirty information in page + table entries. When enabled in TCR_EL1 (HA and HD bits) on + capable processors, accesses to pages with PTE_AF cleared will + set this bit instead of raising an access flag fault. + Similarly, writes to read-only pages with the DBM bit set will + clear the read-only bit (AP[2]) instead of raising a + permission fault. + + Kernels built with this configuration option enabled continue + to work on pre-ARMv8.1 hardware and the performance impact is + minimal. If unsure, say Y. + +config ARM64_PAN + bool "Enable support for Privileged Access Never (PAN)" + default y + help + Privileged Access Never (PAN; part of the ARMv8.1 Extensions) + prevents the kernel or hypervisor from accessing user-space (EL0) + memory directly. + + Choosing this option will cause any unprotected (not using + copy_to_user et al) memory access to fail with a permission fault. + + The feature is detected at runtime, and will remain as a 'nop' + instruction if the cpu does not implement the feature. + +config ARM64_LSE_ATOMICS + bool "Atomic instructions" + help + As part of the Large System Extensions, ARMv8.1 introduces new + atomic instructions that are designed specifically to scale in + very large systems. + + Say Y here to make use of these instructions for the in-kernel + atomic routines. This incurs a small overhead on CPUs that do + not support these instructions and requires the kernel to be + built with binutils >= 2.25. + +endmenu + endmenu menu "Boot options" @@ -737,7 +764,7 @@ source "fs/Kconfig.binfmt" config COMPAT bool "Kernel support for 32-bit EL0" - depends on !ARM64_64K_PAGES || EXPERT + depends on ARM64_4K_PAGES || EXPERT select COMPAT_BINFMT_ELF select HAVE_UID16 select OLD_SIGSUSPEND3 @@ -748,9 +775,9 @@ config COMPAT the user helper functions, VFP support and the ptrace interface are handled appropriately by the kernel. - If you also enabled CONFIG_ARM64_64K_PAGES, please be aware that you - will only be able to execute AArch32 binaries that were compiled with - 64k aligned segments. + If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware + that you will only be able to execute AArch32 binaries that were compiled + with page size aligned segments. If you want to execute 32-bit userspace applications, say Y. diff --git a/kernel/arch/arm64/Kconfig.debug b/kernel/arch/arm64/Kconfig.debug index d6285ef9b..04fb73b97 100644 --- a/kernel/arch/arm64/Kconfig.debug +++ b/kernel/arch/arm64/Kconfig.debug @@ -2,10 +2,6 @@ menu "Kernel hacking" source "lib/Kconfig.debug" -config FRAME_POINTER - bool - default y - config ARM64_PTDUMP bool "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL @@ -77,7 +73,7 @@ config DEBUG_RODATA If in doubt, say Y config DEBUG_ALIGN_RODATA - depends on DEBUG_RODATA && !ARM64_64K_PAGES + depends on DEBUG_RODATA && ARM64_4K_PAGES bool "Align linker sections up to SECTION_SIZE" help If this option is enabled, sections that may potentially be marked as diff --git a/kernel/arch/arm64/Kconfig.platforms b/kernel/arch/arm64/Kconfig.platforms new file mode 100644 index 000000000..4043c3596 --- /dev/null +++ b/kernel/arch/arm64/Kconfig.platforms @@ -0,0 +1,131 @@ +menu "Platform selection" + +config ARCH_BCM_IPROC + bool "Broadcom iProc SoC Family" + help + This enables support for Broadcom iProc based SoCs + +config ARCH_BERLIN + bool "Marvell Berlin SoC Family" + select ARCH_REQUIRE_GPIOLIB + select DW_APB_ICTL + help + This enables support for Marvell Berlin SoC Family + +config ARCH_EXYNOS + bool + help + This enables support for Samsung Exynos SoC family + +config ARCH_EXYNOS7 + bool "ARMv8 based Samsung Exynos7" + select ARCH_EXYNOS + select COMMON_CLK_SAMSUNG + select HAVE_S3C2410_WATCHDOG if WATCHDOG + select HAVE_S3C_RTC if RTC_CLASS + select PINCTRL + select PINCTRL_EXYNOS + + help + This enables support for Samsung Exynos7 SoC family + +config ARCH_LAYERSCAPE + bool "ARMv8 based Freescale Layerscape SoC family" + help + This enables support for the Freescale Layerscape SoC family. + +config ARCH_HISI + bool "Hisilicon SoC Family" + help + This enables support for Hisilicon ARMv8 SoC family + +config ARCH_MEDIATEK + bool "Mediatek MT65xx & MT81xx ARMv8 SoC" + select ARM_GIC + select PINCTRL + help + Support for Mediatek MT65xx & MT81xx ARMv8 SoCs + +config ARCH_QCOM + bool "Qualcomm Platforms" + select PINCTRL + help + This enables support for the ARMv8 based Qualcomm chipsets. + +config ARCH_ROCKCHIP + bool "Rockchip Platforms" + select ARCH_HAS_RESET_CONTROLLER + select ARCH_REQUIRE_GPIOLIB + select PINCTRL + select PINCTRL_ROCKCHIP + help + This enables support for the ARMv8 based Rockchip chipsets, + like the RK3368. + +config ARCH_SEATTLE + bool "AMD Seattle SoC Family" + help + This enables support for AMD Seattle SOC Family + +config ARCH_STRATIX10 + bool "Altera's Stratix 10 SoCFPGA Family" + help + This enables support for Altera's Stratix 10 SoCFPGA Family. + +config ARCH_TEGRA + bool "NVIDIA Tegra SoC Family" + select ARCH_HAS_RESET_CONTROLLER + select ARCH_REQUIRE_GPIOLIB + select CLKDEV_LOOKUP + select CLKSRC_MMIO + select CLKSRC_OF + select GENERIC_CLOCKEVENTS + select HAVE_CLK + select PINCTRL + select RESET_CONTROLLER + help + This enables support for the NVIDIA Tegra SoC family. + +config ARCH_TEGRA_132_SOC + bool "NVIDIA Tegra132 SoC" + depends on ARCH_TEGRA + select PINCTRL_TEGRA124 + select USB_ULPI if USB_PHY + select USB_ULPI_VIEWPORT if USB_PHY + help + Enable support for NVIDIA Tegra132 SoC, based on the Denver + ARMv8 CPU. The Tegra132 SoC is similar to the Tegra124 SoC, + but contains an NVIDIA Denver CPU complex in place of + Tegra124's "4+1" Cortex-A15 CPU complex. + +config ARCH_SPRD + bool "Spreadtrum SoC platform" + help + Support for Spreadtrum ARM based SoCs + +config ARCH_THUNDER + bool "Cavium Inc. Thunder SoC Family" + help + This enables support for Cavium's Thunder Family of SoCs. + +config ARCH_VEXPRESS + bool "ARMv8 software model (Versatile Express)" + select ARCH_REQUIRE_GPIOLIB + select COMMON_CLK_VERSATILE + select POWER_RESET_VEXPRESS + select VEXPRESS_CONFIG + help + This enables support for the ARMv8 software model (Versatile + Express). + +config ARCH_XGENE + bool "AppliedMicro X-Gene SOC Family" + help + This enables support for AppliedMicro X-Gene SOC Family + +config ARCH_ZYNQMP + bool "Xilinx ZynqMP Family" + help + This enables support for Xilinx ZynqMP Family + +endmenu diff --git a/kernel/arch/arm64/Makefile b/kernel/arch/arm64/Makefile index 81151663e..b6c90e500 100644 --- a/kernel/arch/arm64/Makefile +++ b/kernel/arch/arm64/Makefile @@ -17,7 +17,19 @@ GZFLAGS :=-9 KBUILD_DEFCONFIG := defconfig -KBUILD_CFLAGS += -mgeneral-regs-only +# Check for binutils support for specific extensions +lseinstr := $(call as-instr,.arch_extension lse,-DCONFIG_AS_LSE=1) + +ifeq ($(CONFIG_ARM64_LSE_ATOMICS), y) + ifeq ($(lseinstr),) +$(warning LSE atomics not supported by binutils) + endif +endif + +KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) +KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads) +KBUILD_AFLAGS += $(lseinstr) + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian AS += -EB @@ -31,7 +43,7 @@ endif CHECKFLAGS += -D__aarch64__ ifeq ($(CONFIG_ARM64_ERRATUM_843419), y) -CFLAGS_MODULE += -mcmodel=large +KBUILD_CFLAGS_MODULE += -mcmodel=large endif # Default value @@ -44,6 +56,13 @@ else TEXT_OFFSET := 0x00080000 endif +# KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - 3)) - (1 << 61) +# in 32-bit arithmetic +KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \ + (0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 32))) \ + + (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - 3)) \ + - (1 << (64 - 32 - 3)) )) ) + export TEXT_OFFSET GZFLAGS core-y += arch/arm64/kernel/ arch/arm64/mm/ @@ -62,7 +81,10 @@ all: $(KBUILD_IMAGE) $(KBUILD_DTBS) boot := arch/arm64/boot -Image Image.gz: vmlinux +Image: vmlinux + $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + +Image.%: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ zinstall install: vmlinux diff --git a/kernel/arch/arm64/boot/Makefile b/kernel/arch/arm64/boot/Makefile index 5a0e3ab85..abcbba2f0 100644 --- a/kernel/arch/arm64/boot/Makefile +++ b/kernel/arch/arm64/boot/Makefile @@ -19,9 +19,21 @@ targets := Image Image.gz $(obj)/Image: vmlinux FORCE $(call if_changed,objcopy) +$(obj)/Image.bz2: $(obj)/Image FORCE + $(call if_changed,bzip2) + $(obj)/Image.gz: $(obj)/Image FORCE $(call if_changed,gzip) +$(obj)/Image.lz4: $(obj)/Image FORCE + $(call if_changed,lz4) + +$(obj)/Image.lzma: $(obj)/Image FORCE + $(call if_changed,lzma) + +$(obj)/Image.lzo: $(obj)/Image FORCE + $(call if_changed,lzo) + install: $(obj)/Image $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \ $(obj)/Image System.map "$(INSTALL_PATH)" diff --git a/kernel/arch/arm64/boot/dts/Makefile b/kernel/arch/arm64/boot/dts/Makefile index ad26a752b..eb3c42d97 100644 --- a/kernel/arch/arm64/boot/dts/Makefile +++ b/kernel/arch/arm64/boot/dts/Makefile @@ -1,12 +1,23 @@ +dts-dirs += altera dts-dirs += amd dts-dirs += apm dts-dirs += arm +dts-dirs += broadcom dts-dirs += cavium dts-dirs += exynos dts-dirs += freescale +dts-dirs += hisilicon +dts-dirs += marvell dts-dirs += mediatek dts-dirs += qcom +dts-dirs += rockchip dts-dirs += sprd dts-dirs += xilinx subdir-y := $(dts-dirs) + +dtstree := $(srctree)/$(src) + +dtb-$(CONFIG_OF_ALL_DTBS) := $(patsubst $(dtstree)/%.dts,%.dtb, $(foreach d,$(dts-dirs), $(wildcard $(dtstree)/$(d)/*.dts))) + +always := $(dtb-y) diff --git a/kernel/arch/arm64/boot/dts/altera/Makefile b/kernel/arch/arm64/boot/dts/altera/Makefile new file mode 100644 index 000000000..d7a641698 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/altera/Makefile @@ -0,0 +1,5 @@ +dtb-$(CONFIG_ARCH_STRATIX10) += socfpga_stratix10_socdk.dtb + +always := $(dtb-y) +subdir-y := $(dts-dirs) +clean-files := *.dtb diff --git a/kernel/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/kernel/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi new file mode 100644 index 000000000..445aa678f --- /dev/null +++ b/kernel/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -0,0 +1,358 @@ +/* + * Copyright Altera Corporation (C) 2015. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + */ + +/dts-v1/; + +/ { + compatible = "altr,socfpga-stratix10"; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + enable-method = "psci"; + reg = <0x0>; + }; + + cpu1: cpu@1 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + enable-method = "psci"; + reg = <0x1>; + }; + + cpu2: cpu@2 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + enable-method = "psci"; + reg = <0x2>; + }; + + cpu3: cpu@3 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + enable-method = "psci"; + reg = <0x3>; + }; + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = <0 120 8>, + <0 121 8>, + <0 122 8>, + <0 123 8>; + interrupt-affinity = <&cpu0>, + <&cpu1>, + <&cpu2>, + <&cpu3>; + }; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + intc: intc@fffc1000 { + compatible = "arm,gic-400", "arm,cortex-a15-gic"; + #interrupt-cells = <3>; + interrupt-controller; + reg = <0x0 0xfffc1000 0x1000>, + <0x0 0xfffc2000 0x2000>, + <0x0 0xfffc4000 0x2000>, + <0x0 0xfffc6000 0x2000>; + }; + + soc { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + device_type = "soc"; + interrupt-parent = <&intc>; + ranges = <0 0 0 0xffffffff>; + + clkmgr@ffd1000 { + compatible = "altr,clk-mgr"; + reg = <0xffd10000 0x1000>; + }; + + gmac0: ethernet@ff800000 { + compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + reg = <0xff800000 0x2000>; + interrupts = <0 90 4>; + interrupt-names = "macirq"; + mac-address = [00 00 00 00 00 00]; + status = "disabled"; + }; + + gmac1: ethernet@ff802000 { + compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + reg = <0xff802000 0x2000>; + interrupts = <0 91 4>; + interrupt-names = "macirq"; + mac-address = [00 00 00 00 00 00]; + status = "disabled"; + }; + + gmac2: ethernet@ff804000 { + compatible = "altr,socfpga-stmmac", "snps,dwmac-3.74a", "snps,dwmac"; + reg = <0xff804000 0x2000>; + interrupts = <0 92 4>; + interrupt-names = "macirq"; + mac-address = [00 00 00 00 00 00]; + status = "disabled"; + }; + + gpio0: gpio@ffc03200 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dw-apb-gpio"; + reg = <0xffc03200 0x100>; + status = "disabled"; + + porta: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <24>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <0 110 4>; + }; + }; + + gpio1: gpio@ffc03300 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dw-apb-gpio"; + reg = <0xffc03300 0x100>; + status = "disabled"; + + portb: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <24>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <0 110 4>; + }; + }; + + i2c0: i2c@ffc02800 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,designware-i2c"; + reg = <0xffc02800 0x100>; + interrupts = <0 103 4>; + status = "disabled"; + }; + + i2c1: i2c@ffc02900 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,designware-i2c"; + reg = <0xffc02900 0x100>; + interrupts = <0 104 4>; + status = "disabled"; + }; + + i2c2: i2c@ffc02a00 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,designware-i2c"; + reg = <0xffc02a00 0x100>; + interrupts = <0 105 4>; + status = "disabled"; + }; + + i2c3: i2c@ffc02b00 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,designware-i2c"; + reg = <0xffc02b00 0x100>; + interrupts = <0 106 4>; + status = "disabled"; + }; + + i2c4: i2c@ffc02c00 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,designware-i2c"; + reg = <0xffc02c00 0x100>; + interrupts = <0 107 4>; + status = "disabled"; + }; + + mmc: dwmmc0@ff808000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "altr,socfpga-dw-mshc"; + reg = <0xff808000 0x1000>; + interrupts = <0 96 4>; + fifo-depth = <0x400>; + status = "disabled"; + }; + + ocram: sram@ffe00000 { + compatible = "mmio-sram"; + reg = <0xffe00000 0x100000>; + }; + + rst: rstmgr@ffd11000 { + #reset-cells = <1>; + compatible = "altr,rst-mgr"; + reg = <0xffd11000 0x1000>; + }; + + spi0: spi@ffda4000 { + compatible = "snps,dw-apb-ssi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0xffda4000 0x1000>; + interrupts = <0 101 4>; + num-chipselect = <4>; + bus-num = <0>; + status = "disabled"; + }; + + spi1: spi@ffda5000 { + compatible = "snps,dw-apb-ssi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0xffda5000 0x1000>; + interrupts = <0 102 4>; + num-chipselect = <4>; + bus-num = <0>; + status = "disabled"; + }; + + sysmgr: sysmgr@ffd12000 { + compatible = "altr,sys-mgr", "syscon"; + reg = <0xffd12000 0x1000>; + }; + + /* Local timer */ + timer { + compatible = "arm,armv8-timer"; + interrupts = <1 13 0xf01>, + <1 14 0xf01>, + <1 11 0xf01>, + <1 10 0xf01>; + }; + + timer0: timer0@ffc03000 { + compatible = "snps,dw-apb-timer"; + interrupts = <0 113 4>; + reg = <0xffc03000 0x100>; + }; + + timer1: timer1@ffc03100 { + compatible = "snps,dw-apb-timer"; + interrupts = <0 114 4>; + reg = <0xffc03100 0x100>; + }; + + timer2: timer2@ffd00000 { + compatible = "snps,dw-apb-timer"; + interrupts = <0 115 4>; + reg = <0xffd00000 0x100>; + }; + + timer3: timer3@ffd00100 { + compatible = "snps,dw-apb-timer"; + interrupts = <0 116 4>; + reg = <0xffd00100 0x100>; + }; + + uart0: serial0@ffc02000 { + compatible = "snps,dw-apb-uart"; + reg = <0xffc02000 0x100>; + interrupts = <0 108 4>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart1: serial1@ffc02100 { + compatible = "snps,dw-apb-uart"; + reg = <0xffc02100 0x100>; + interrupts = <0 109 4>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + usbphy0: usbphy@0 { + #phy-cells = <0>; + compatible = "usb-nop-xceiv"; + status = "okay"; + }; + + usb0: usb@ffb00000 { + compatible = "snps,dwc2"; + reg = <0xffb00000 0x40000>; + interrupts = <0 93 4>; + phys = <&usbphy0>; + phy-names = "usb2-phy"; + status = "disabled"; + }; + + usb1: usb@ffb40000 { + compatible = "snps,dwc2"; + reg = <0xffb40000 0x40000>; + interrupts = <0 94 4>; + phys = <&usbphy0>; + phy-names = "usb2-phy"; + status = "disabled"; + }; + + watchdog0: watchdog@ffd00200 { + compatible = "snps,dw-wdt"; + reg = <0xffd00200 0x100>; + interrupts = <0 117 4>; + status = "disabled"; + }; + + watchdog1: watchdog@ffd00300 { + compatible = "snps,dw-wdt"; + reg = <0xffd00300 0x100>; + interrupts = <0 118 4>; + status = "disabled"; + }; + + watchdog2: watchdog@ffd00400 { + compatible = "snps,dw-wdt"; + reg = <0xffd00400 0x100>; + interrupts = <0 125 4>; + status = "disabled"; + }; + + watchdog3: watchdog@ffd00500 { + compatible = "snps,dw-wdt"; + reg = <0xffd00500 0x100>; + interrupts = <0 126 4>; + status = "disabled"; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/kernel/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts new file mode 100644 index 000000000..41ea2dba2 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts @@ -0,0 +1,39 @@ +/* + * Copyright Altera Corporation (C) 2015. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see . + */ + +/include/ "socfpga_stratix10.dtsi" + +/ { + model = "SoCFPGA Stratix 10 SoCDK"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory { + device_type = "memory"; + /* We expect the bootloader to fill in the reg */ + reg = <0 0 0 0>; + }; +}; + +&uart0 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/amd/amd-overdrive.dts b/kernel/arch/arm64/boot/dts/amd/amd-overdrive.dts index 564a3f7df..128fa942f 100644 --- a/kernel/arch/arm64/boot/dts/amd/amd-overdrive.dts +++ b/kernel/arch/arm64/boot/dts/amd/amd-overdrive.dts @@ -14,7 +14,6 @@ chosen { stdout-path = &serial0; - linux,pci-probe-only; }; }; diff --git a/kernel/arch/arm64/boot/dts/apm/Makefile b/kernel/arch/arm64/boot/dts/apm/Makefile index a2afabbc1..c75f17a49 100644 --- a/kernel/arch/arm64/boot/dts/apm/Makefile +++ b/kernel/arch/arm64/boot/dts/apm/Makefile @@ -1,4 +1,5 @@ dtb-$(CONFIG_ARCH_XGENE) += apm-mustang.dtb +dtb-$(CONFIG_ARCH_XGENE) += apm-merlin.dtb always := $(dtb-y) subdir-y := $(dts-dirs) diff --git a/kernel/arch/arm64/boot/dts/apm/apm-merlin.dts b/kernel/arch/arm64/boot/dts/apm/apm-merlin.dts new file mode 100644 index 000000000..119a469bd --- /dev/null +++ b/kernel/arch/arm64/boot/dts/apm/apm-merlin.dts @@ -0,0 +1,72 @@ +/* + * dts file for AppliedMicro (APM) Merlin Board + * + * Copyright (C) 2015, Applied Micro Circuits Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + */ + +/dts-v1/; + +/include/ "apm-shadowcat.dtsi" + +/ { + model = "APM X-Gene Merlin board"; + compatible = "apm,merlin", "apm,xgene-shadowcat"; + + chosen { }; + + memory { + device_type = "memory"; + reg = < 0x1 0x00000000 0x0 0x80000000 >; + }; + + gpio-keys { + compatible = "gpio-keys"; + button@1 { + label = "POWER"; + linux,code = <116>; + linux,input-type = <0x1>; + interrupts = <0x0 0x28 0x1>; + }; + }; + + poweroff_mbox: poweroff_mbox@10548000 { + compatible = "syscon"; + reg = <0x0 0x10548000 0x0 0x30>; + }; + + poweroff: poweroff@10548010 { + compatible = "syscon-poweroff"; + regmap = <&poweroff_mbox>; + offset = <0x10>; + mask = <0x1>; + }; +}; + +&serial0 { + status = "ok"; +}; + +&sata1 { + status = "ok"; +}; + +&sata2 { + status = "ok"; +}; + +&sata3 { + status = "ok"; +}; + +&sgenet0 { + status = "ok"; +}; + +&xgenet1 { + status = "ok"; +}; diff --git a/kernel/arch/arm64/boot/dts/apm/apm-mustang.dts b/kernel/arch/arm64/boot/dts/apm/apm-mustang.dts index 83578e766..01cdeda93 100644 --- a/kernel/arch/arm64/boot/dts/apm/apm-mustang.dts +++ b/kernel/arch/arm64/boot/dts/apm/apm-mustang.dts @@ -23,6 +23,28 @@ device_type = "memory"; reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */ }; + + gpio-keys { + compatible = "gpio-keys"; + button@1 { + label = "POWER"; + linux,code = <116>; + linux,input-type = <0x1>; + interrupts = <0x0 0x2d 0x1>; + }; + }; + + poweroff_mbox: poweroff_mbox@10548000 { + compatible = "syscon"; + reg = <0x0 0x10548000 0x0 0x30>; + }; + + poweroff: poweroff@10548010 { + compatible = "syscon-poweroff"; + regmap = <&poweroff_mbox>; + offset = <0x10>; + mask = <0x1>; + }; }; &pcie0clk { diff --git a/kernel/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi b/kernel/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi new file mode 100644 index 000000000..c804f8f1f --- /dev/null +++ b/kernel/arch/arm64/boot/dts/apm/apm-shadowcat.dtsi @@ -0,0 +1,271 @@ +/* + * dts file for AppliedMicro (APM) X-Gene Shadowcat SOC + * + * Copyright (C) 2015, Applied Micro Circuits Corporation + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + */ + +/ { + compatible = "apm,xgene-shadowcat"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu@000 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x000>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@001 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x001>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@100 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x100>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@101 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x101>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@200 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x200>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@201 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x201>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@300 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x300>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + cpu@301 { + device_type = "cpu"; + compatible = "apm,strega", "arm,armv8"; + reg = <0x0 0x301>; + enable-method = "spin-table"; + cpu-release-addr = <0x1 0x0000fff8>; + }; + }; + + gic: interrupt-controller@78090000 { + compatible = "arm,cortex-a15-gic"; + #interrupt-cells = <3>; + #address-cells = <2>; + #size-cells = <2>; + interrupt-controller; + interrupts = <1 9 0xf04>; /* GIC Maintenence IRQ */ + ranges = <0 0 0 0x79000000 0x0 0x800000>; /* MSI Range */ + reg = <0x0 0x78090000 0x0 0x10000>, /* GIC Dist */ + <0x0 0x780A0000 0x0 0x20000>, /* GIC CPU */ + <0x0 0x780C0000 0x0 0x10000>, /* GIC VCPU Control */ + <0x0 0x780E0000 0x0 0x20000>; /* GIC VCPU */ + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = <1 12 0xff04>; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = <1 0 0xff04>, /* Secure Phys IRQ */ + <1 13 0xff04>, /* Non-secure Phys IRQ */ + <1 14 0xff04>, /* Virt IRQ */ + <1 15 0xff04>; /* Hyp IRQ */ + clock-frequency = <50000000>; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clocks { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + refclk: refclk { + compatible = "fixed-clock"; + #clock-cells = <1>; + clock-frequency = <100000000>; + clock-output-names = "refclk"; + }; + + socpll: socpll@17000120 { + compatible = "apm,xgene-socpll-clock"; + #clock-cells = <1>; + clocks = <&refclk 0>; + reg = <0x0 0x17000120 0x0 0x1000>; + clock-output-names = "socpll"; + }; + + socplldiv2: socplldiv2 { + compatible = "fixed-factor-clock"; + #clock-cells = <1>; + clocks = <&socpll 0>; + clock-mult = <1>; + clock-div = <2>; + clock-output-names = "socplldiv2"; + }; + + pcie0clk: pcie0clk@1f2bc000 { + compatible = "apm,xgene-device-clock"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x1f2bc000 0x0 0x1000>; + reg-names = "csr-reg"; + clock-output-names = "pcie0clk"; + }; + + xge0clk: xge0clk@1f61c000 { + compatible = "apm,xgene-device-clock"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x1f61c000 0x0 0x1000>; + reg-names = "csr-reg"; + enable-mask = <0x3>; + csr-mask = <0x3>; + clock-output-names = "xge0clk"; + }; + + xge1clk: xge1clk@1f62c000 { + compatible = "apm,xgene-device-clock"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x1f62c000 0x0 0x1000>; + reg-names = "csr-reg"; + enable-mask = <0x3>; + csr-mask = <0x3>; + clock-output-names = "xge1clk"; + }; + }; + + scu: system-clk-controller@17000000 { + compatible = "apm,xgene-scu","syscon"; + reg = <0x0 0x17000000 0x0 0x400>; + }; + + reboot: reboot@17000014 { + compatible = "syscon-reboot"; + regmap = <&scu>; + offset = <0x14>; + mask = <0x1>; + }; + + serial0: serial@10600000 { + device_type = "serial"; + compatible = "ns16550"; + reg = <0 0x10600000 0x0 0x1000>; + reg-shift = <2>; + clock-frequency = <10000000>; + interrupt-parent = <&gic>; + interrupts = <0x0 0x4c 0x4>; + }; + + sata1: sata@1a000000 { + compatible = "apm,xgene-ahci"; + reg = <0x0 0x1a000000 0x0 0x1000>, + <0x0 0x1f200000 0x0 0x1000>, + <0x0 0x1f20d000 0x0 0x1000>, + <0x0 0x1f20e000 0x0 0x1000>; + interrupts = <0x0 0x5a 0x4>; + dma-coherent; + }; + + sata2: sata@1a200000 { + compatible = "apm,xgene-ahci"; + reg = <0x0 0x1a200000 0x0 0x1000>, + <0x0 0x1f210000 0x0 0x1000>, + <0x0 0x1f21d000 0x0 0x1000>, + <0x0 0x1f21e000 0x0 0x1000>; + interrupts = <0x0 0x5b 0x4>; + dma-coherent; + }; + + sata3: sata@1a400000 { + compatible = "apm,xgene-ahci"; + reg = <0x0 0x1a400000 0x0 0x1000>, + <0x0 0x1f220000 0x0 0x1000>, + <0x0 0x1f22d000 0x0 0x1000>, + <0x0 0x1f22e000 0x0 0x1000>; + interrupts = <0x0 0x5c 0x4>; + dma-coherent; + }; + + sbgpio: sbgpio@17001000{ + compatible = "apm,xgene-gpio-sb"; + reg = <0x0 0x17001000 0x0 0x400>; + #gpio-cells = <2>; + gpio-controller; + interrupts = <0x0 0x28 0x1>, + <0x0 0x29 0x1>, + <0x0 0x2a 0x1>, + <0x0 0x2b 0x1>, + <0x0 0x2c 0x1>, + <0x0 0x2d 0x1>, + <0x0 0x2e 0x1>, + <0x0 0x2f 0x1>; + }; + + sgenet0: ethernet@1f610000 { + compatible = "apm,xgene2-sgenet"; + status = "disabled"; + reg = <0x0 0x1f610000 0x0 0x10000>, + <0x0 0x1f600000 0x0 0Xd100>, + <0x0 0x20000000 0x0 0X20000>; + interrupts = <0 96 4>, + <0 97 4>; + dma-coherent; + clocks = <&xge0clk 0>; + local-mac-address = [00 01 73 00 00 01]; + phy-connection-type = "sgmii"; + }; + + xgenet1: ethernet@1f620000 { + compatible = "apm,xgene2-xgenet"; + status = "disabled"; + reg = <0x0 0x1f620000 0x0 0x10000>, + <0x0 0x1f600000 0x0 0Xd100>, + <0x0 0x20000000 0x0 0X220000>; + interrupts = <0 108 4>, + <0 109 4>; + port-id = <1>; + dma-coherent; + clocks = <&xge1clk 0>; + local-mac-address = [00 01 73 00 00 02]; + phy-connection-type = "xgmii"; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/apm/apm-storm.dtsi b/kernel/arch/arm64/boot/dts/apm/apm-storm.dtsi index c8d3e0e86..6c5ed1199 100644 --- a/kernel/arch/arm64/boot/dts/apm/apm-storm.dtsi +++ b/kernel/arch/arm64/boot/dts/apm/apm-storm.dtsi @@ -97,6 +97,11 @@ clock-frequency = <50000000>; }; + pmu { + compatible = "apm,potenza-pmu", "arm,armv8-pmuv3"; + interrupts = <1 12 0xff04>; + }; + soc { compatible = "simple-bus"; #address-cells = <2>; @@ -207,6 +212,17 @@ clock-output-names = "xge0clk"; }; + xge1clk: xge1clk@1f62c000 { + compatible = "apm,xgene-device-clock"; + status = "disabled"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x1f62c000 0x0 0x1000>; + reg-names = "csr-reg"; + csr-mask = <0x3>; + clock-output-names = "xge1clk"; + }; + sataphy1clk: sataphy1clk@1f21c000 { compatible = "apm,xgene-device-clock"; #clock-cells = <1>; @@ -374,6 +390,133 @@ }; }; + msi: msi@79000000 { + compatible = "apm,xgene1-msi"; + msi-controller; + reg = <0x00 0x79000000 0x0 0x900000>; + interrupts = < 0x0 0x10 0x4 + 0x0 0x11 0x4 + 0x0 0x12 0x4 + 0x0 0x13 0x4 + 0x0 0x14 0x4 + 0x0 0x15 0x4 + 0x0 0x16 0x4 + 0x0 0x17 0x4 + 0x0 0x18 0x4 + 0x0 0x19 0x4 + 0x0 0x1a 0x4 + 0x0 0x1b 0x4 + 0x0 0x1c 0x4 + 0x0 0x1d 0x4 + 0x0 0x1e 0x4 + 0x0 0x1f 0x4>; + }; + + scu: system-clk-controller@17000000 { + compatible = "apm,xgene-scu","syscon"; + reg = <0x0 0x17000000 0x0 0x400>; + }; + + reboot: reboot@17000014 { + compatible = "syscon-reboot"; + regmap = <&scu>; + offset = <0x14>; + mask = <0x1>; + }; + + csw: csw@7e200000 { + compatible = "apm,xgene-csw", "syscon"; + reg = <0x0 0x7e200000 0x0 0x1000>; + }; + + mcba: mcba@7e700000 { + compatible = "apm,xgene-mcb", "syscon"; + reg = <0x0 0x7e700000 0x0 0x1000>; + }; + + mcbb: mcbb@7e720000 { + compatible = "apm,xgene-mcb", "syscon"; + reg = <0x0 0x7e720000 0x0 0x1000>; + }; + + efuse: efuse@1054a000 { + compatible = "apm,xgene-efuse", "syscon"; + reg = <0x0 0x1054a000 0x0 0x20>; + }; + + edac@78800000 { + compatible = "apm,xgene-edac"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + regmap-csw = <&csw>; + regmap-mcba = <&mcba>; + regmap-mcbb = <&mcbb>; + regmap-efuse = <&efuse>; + reg = <0x0 0x78800000 0x0 0x100>; + interrupts = <0x0 0x20 0x4>, + <0x0 0x21 0x4>, + <0x0 0x27 0x4>; + + edacmc@7e800000 { + compatible = "apm,xgene-edac-mc"; + reg = <0x0 0x7e800000 0x0 0x1000>; + memory-controller = <0>; + }; + + edacmc@7e840000 { + compatible = "apm,xgene-edac-mc"; + reg = <0x0 0x7e840000 0x0 0x1000>; + memory-controller = <1>; + }; + + edacmc@7e880000 { + compatible = "apm,xgene-edac-mc"; + reg = <0x0 0x7e880000 0x0 0x1000>; + memory-controller = <2>; + }; + + edacmc@7e8c0000 { + compatible = "apm,xgene-edac-mc"; + reg = <0x0 0x7e8c0000 0x0 0x1000>; + memory-controller = <3>; + }; + + edacpmd@7c000000 { + compatible = "apm,xgene-edac-pmd"; + reg = <0x0 0x7c000000 0x0 0x200000>; + pmd-controller = <0>; + }; + + edacpmd@7c200000 { + compatible = "apm,xgene-edac-pmd"; + reg = <0x0 0x7c200000 0x0 0x200000>; + pmd-controller = <1>; + }; + + edacpmd@7c400000 { + compatible = "apm,xgene-edac-pmd"; + reg = <0x0 0x7c400000 0x0 0x200000>; + pmd-controller = <2>; + }; + + edacpmd@7c600000 { + compatible = "apm,xgene-edac-pmd"; + reg = <0x0 0x7c600000 0x0 0x200000>; + pmd-controller = <3>; + }; + + edacl3@7e600000 { + compatible = "apm,xgene-edac-l3"; + reg = <0x0 0x7e600000 0x0 0x1000>; + }; + + edacsoc@7e930000 { + compatible = "apm,xgene-edac-soc-v1"; + reg = <0x0 0x7e930000 0x0 0x1000>; + }; + }; + pcie0: pcie@1f2b0000 { status = "disabled"; device_type = "pci"; @@ -385,7 +528,8 @@ 0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */ reg-names = "csr", "cfg"; ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000 /* io */ - 0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */ + 0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000 /* mem */ + 0x43000000 0xf0 0x00000000 0xf0 0x00000000 0x10 0x00000000>; /* mem */ dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000 0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; @@ -395,6 +539,7 @@ 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>; dma-coherent; clocks = <&pcie0clk 0>; + msi-parent = <&msi>; }; pcie1: pcie@1f2c0000 { @@ -407,8 +552,9 @@ reg = < 0x00 0x1f2c0000 0x0 0x00010000 /* Controller registers */ 0xd0 0xd0000000 0x0 0x00040000>; /* PCI config space */ reg-names = "csr", "cfg"; - ranges = <0x01000000 0x0 0x00000000 0xd0 0x10000000 0x00 0x00010000 /* io */ - 0x02000000 0x0 0x80000000 0xd1 0x80000000 0x00 0x80000000>; /* mem */ + ranges = <0x01000000 0x00 0x00000000 0xd0 0x10000000 0x00 0x00010000 /* io */ + 0x02000000 0x00 0x80000000 0xd1 0x80000000 0x00 0x80000000 /* mem */ + 0x43000000 0xd8 0x00000000 0xd8 0x00000000 0x08 0x00000000>; /* mem */ dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000 0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; @@ -418,6 +564,7 @@ 0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>; dma-coherent; clocks = <&pcie1clk 0>; + msi-parent = <&msi>; }; pcie2: pcie@1f2d0000 { @@ -430,8 +577,9 @@ reg = < 0x00 0x1f2d0000 0x0 0x00010000 /* Controller registers */ 0x90 0xd0000000 0x0 0x00040000>; /* PCI config space */ reg-names = "csr", "cfg"; - ranges = <0x01000000 0x0 0x00000000 0x90 0x10000000 0x0 0x00010000 /* io */ - 0x02000000 0x0 0x80000000 0x91 0x80000000 0x0 0x80000000>; /* mem */ + ranges = <0x01000000 0x00 0x00000000 0x90 0x10000000 0x00 0x00010000 /* io */ + 0x02000000 0x00 0x80000000 0x91 0x80000000 0x00 0x80000000 /* mem */ + 0x43000000 0x94 0x00000000 0x94 0x00000000 0x04 0x00000000>; /* mem */ dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000 0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; @@ -441,6 +589,7 @@ 0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>; dma-coherent; clocks = <&pcie2clk 0>; + msi-parent = <&msi>; }; pcie3: pcie@1f500000 { @@ -453,8 +602,9 @@ reg = < 0x00 0x1f500000 0x0 0x00010000 /* Controller registers */ 0xa0 0xd0000000 0x0 0x00040000>; /* PCI config space */ reg-names = "csr", "cfg"; - ranges = <0x01000000 0x0 0x00000000 0xa0 0x10000000 0x0 0x00010000 /* io */ - 0x02000000 0x0 0x80000000 0xa1 0x80000000 0x0 0x80000000>; /* mem */ + ranges = <0x01000000 0x00 0x00000000 0xa0 0x10000000 0x00 0x00010000 /* io */ + 0x02000000 0x00 0x80000000 0xa1 0x80000000 0x00 0x80000000 /* mem */ + 0x43000000 0xb0 0x00000000 0xb0 0x00000000 0x10 0x00000000>; /* mem */ dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000 0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; @@ -464,6 +614,7 @@ 0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>; dma-coherent; clocks = <&pcie3clk 0>; + msi-parent = <&msi>; }; pcie4: pcie@1f510000 { @@ -476,8 +627,9 @@ reg = < 0x00 0x1f510000 0x0 0x00010000 /* Controller registers */ 0xc0 0xd0000000 0x0 0x00200000>; /* PCI config space */ reg-names = "csr", "cfg"; - ranges = <0x01000000 0x0 0x00000000 0xc0 0x10000000 0x0 0x00010000 /* io */ - 0x02000000 0x0 0x80000000 0xc1 0x80000000 0x0 0x80000000>; /* mem */ + ranges = <0x01000000 0x00 0x00000000 0xc0 0x10000000 0x00 0x00010000 /* io */ + 0x02000000 0x00 0x80000000 0xc1 0x80000000 0x00 0x80000000 /* mem */ + 0x43000000 0xc8 0x00000000 0xc8 0x00000000 0x08 0x00000000>; /* mem */ dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000 0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>; interrupt-map-mask = <0x0 0x0 0x0 0x7>; @@ -487,6 +639,7 @@ 0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>; dma-coherent; clocks = <&pcie4clk 0>; + msi-parent = <&msi>; }; serial0: serial@1c020000 { @@ -607,6 +760,19 @@ phy-names = "sata-phy"; }; + sbgpio: sbgpio@17001000{ + compatible = "apm,xgene-gpio-sb"; + reg = <0x0 0x17001000 0x0 0x400>; + #gpio-cells = <2>; + gpio-controller; + interrupts = <0x0 0x28 0x1>, + <0x0 0x29 0x1>, + <0x0 0x2a 0x1>, + <0x0 0x2b 0x1>, + <0x0 0x2c 0x1>, + <0x0 0x2d 0x1>; + }; + rtc: rtc@10510000 { compatible = "apm,xgene-rtc"; reg = <0x0 0x10510000 0x0 0x400>; @@ -688,6 +854,23 @@ phy-connection-type = "xgmii"; }; + xgenet1: ethernet@1f620000 { + compatible = "apm,xgene1-xgenet"; + status = "disabled"; + reg = <0x0 0x1f620000 0x0 0xd100>, + <0x0 0x1f600000 0x0 0Xc300>, + <0x0 0x18000000 0x0 0X8000>; + reg-names = "enet_csr", "ring_csr", "ring_cmd"; + interrupts = <0x0 0x6C 0x4>, + <0x0 0x6D 0x4>; + port-id = <1>; + dma-coherent; + clocks = <&xge1clk 0>; + /* mac address will be overwritten by the bootloader */ + local-mac-address = [00 00 00 00 00 00]; + phy-connection-type = "xgmii"; + }; + rng: rng@10520000 { compatible = "apm,xgene-rng"; reg = <0x0 0x10520000 0x0 0x100>; @@ -700,7 +883,7 @@ device_type = "dma"; reg = <0x0 0x1f270000 0x0 0x10000>, <0x0 0x1f200000 0x0 0x10000>, - <0x0 0x1b008000 0x0 0x2000>, + <0x0 0x1b000000 0x0 0x400000>, <0x0 0x1054a000 0x0 0x100>; interrupts = <0x0 0x82 0x4>, <0x0 0xb8 0x4>, diff --git a/kernel/arch/arm64/boot/dts/arm/Makefile b/kernel/arch/arm64/boot/dts/arm/Makefile index 301a0dada..bb3c07209 100644 --- a/kernel/arch/arm64/boot/dts/arm/Makefile +++ b/kernel/arch/arm64/boot/dts/arm/Makefile @@ -1,6 +1,7 @@ dtb-$(CONFIG_ARCH_VEXPRESS) += foundation-v8.dtb -dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb +dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb juno-r1.dtb dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb +dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2f-1xv7-ca53x2.dtb always := $(dtb-y) subdir-y := $(dts-dirs) diff --git a/kernel/arch/arm64/boot/dts/arm/juno-base.dtsi b/kernel/arch/arm64/boot/dts/arm/juno-base.dtsi new file mode 100644 index 000000000..dd5158eb5 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -0,0 +1,213 @@ + /* + * Devices shared by all Juno boards + */ + + memtimer: timer@2a810000 { + compatible = "arm,armv7-timer-mem"; + reg = <0x0 0x2a810000 0x0 0x10000>; + clock-frequency = <50000000>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + status = "disabled"; + frame@2a830000 { + frame-number = <1>; + interrupts = <0 60 4>; + reg = <0x0 0x2a830000 0x0 0x10000>; + }; + }; + + mailbox: mhu@2b1f0000 { + compatible = "arm,mhu", "arm,primecell"; + reg = <0x0 0x2b1f0000 0x0 0x1000>; + interrupts = , + ; + interrupt-names = "mhu_lpri_rx", + "mhu_hpri_rx"; + #mbox-cells = <1>; + clocks = <&soc_refclk100mhz>; + clock-names = "apb_pclk"; + }; + + gic: interrupt-controller@2c010000 { + compatible = "arm,gic-400", "arm,cortex-a15-gic"; + reg = <0x0 0x2c010000 0 0x1000>, + <0x0 0x2c02f000 0 0x2000>, + <0x0 0x2c04f000 0 0x2000>, + <0x0 0x2c06f000 0 0x2000>; + #address-cells = <2>; + #interrupt-cells = <3>; + #size-cells = <2>; + interrupt-controller; + interrupts = ; + ranges = <0 0 0 0x2c1c0000 0 0x40000>; + v2m_0: v2m@0 { + compatible = "arm,gic-v2m-frame"; + msi-controller; + reg = <0 0 0 0x1000>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + sram: sram@2e000000 { + compatible = "arm,juno-sram-ns", "mmio-sram"; + reg = <0x0 0x2e000000 0x0 0x8000>; + + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0x0 0x2e000000 0x8000>; + + cpu_scp_lpri: scp-shmem@0 { + compatible = "arm,juno-scp-shmem"; + reg = <0x0 0x200>; + }; + + cpu_scp_hpri: scp-shmem@200 { + compatible = "arm,juno-scp-shmem"; + reg = <0x200 0x200>; + }; + }; + + scpi { + compatible = "arm,scpi"; + mboxes = <&mailbox 1>; + shmem = <&cpu_scp_hpri>; + + clocks { + compatible = "arm,scpi-clocks"; + + scpi_dvfs: scpi_clocks@0 { + compatible = "arm,scpi-dvfs-clocks"; + #clock-cells = <1>; + clock-indices = <0>, <1>, <2>; + clock-output-names = "atlclk", "aplclk","gpuclk"; + }; + scpi_clk: scpi_clocks@3 { + compatible = "arm,scpi-variable-clocks"; + #clock-cells = <1>; + clock-indices = <3>, <4>; + clock-output-names = "pxlclk0", "pxlclk1"; + }; + }; + + scpi_sensors0: sensors { + compatible = "arm,scpi-sensors"; + #thermal-sensor-cells = <1>; + }; + }; + + /include/ "juno-clocks.dtsi" + + dma@7ff00000 { + compatible = "arm,pl330", "arm,primecell"; + reg = <0x0 0x7ff00000 0 0x1000>; + #dma-cells = <1>; + #dma-channels = <8>; + #dma-requests = <32>; + interrupts = , + , + , + , + , + , + , + ; + clocks = <&soc_faxiclk>; + clock-names = "apb_pclk"; + }; + + soc_uart0: uart@7ff80000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0 0x7ff80000 0x0 0x1000>; + interrupts = ; + clocks = <&soc_uartclk>, <&soc_refclk100mhz>; + clock-names = "uartclk", "apb_pclk"; + }; + + i2c@7ffa0000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x7ffa0000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = ; + clock-frequency = <400000>; + i2c-sda-hold-time-ns = <500>; + clocks = <&soc_smc50mhz>; + + dvi0: dvi-transmitter@70 { + compatible = "nxp,tda998x"; + reg = <0x70>; + }; + + dvi1: dvi-transmitter@71 { + compatible = "nxp,tda998x"; + reg = <0x71>; + }; + }; + + ohci@7ffb0000 { + compatible = "generic-ohci"; + reg = <0x0 0x7ffb0000 0x0 0x10000>; + interrupts = ; + clocks = <&soc_usb48mhz>; + }; + + ehci@7ffc0000 { + compatible = "generic-ehci"; + reg = <0x0 0x7ffc0000 0x0 0x10000>; + interrupts = ; + clocks = <&soc_usb48mhz>; + }; + + memory-controller@7ffd0000 { + compatible = "arm,pl354", "arm,primecell"; + reg = <0 0x7ffd0000 0 0x1000>; + interrupts = , + ; + clocks = <&soc_smc50mhz>; + clock-names = "apb_pclk"; + }; + + memory@80000000 { + device_type = "memory"; + /* last 16MB of the first memory area is reserved for secure world use by firmware */ + reg = <0x00000000 0x80000000 0x0 0x7f000000>, + <0x00000008 0x80000000 0x1 0x80000000>; + }; + + smb { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 15>; + interrupt-map = <0 0 0 &gic 0 0 0 68 IRQ_TYPE_LEVEL_HIGH>, + <0 0 1 &gic 0 0 0 69 IRQ_TYPE_LEVEL_HIGH>, + <0 0 2 &gic 0 0 0 70 IRQ_TYPE_LEVEL_HIGH>, + <0 0 3 &gic 0 0 0 160 IRQ_TYPE_LEVEL_HIGH>, + <0 0 4 &gic 0 0 0 161 IRQ_TYPE_LEVEL_HIGH>, + <0 0 5 &gic 0 0 0 162 IRQ_TYPE_LEVEL_HIGH>, + <0 0 6 &gic 0 0 0 163 IRQ_TYPE_LEVEL_HIGH>, + <0 0 7 &gic 0 0 0 164 IRQ_TYPE_LEVEL_HIGH>, + <0 0 8 &gic 0 0 0 165 IRQ_TYPE_LEVEL_HIGH>, + <0 0 9 &gic 0 0 0 166 IRQ_TYPE_LEVEL_HIGH>, + <0 0 10 &gic 0 0 0 167 IRQ_TYPE_LEVEL_HIGH>, + <0 0 11 &gic 0 0 0 168 IRQ_TYPE_LEVEL_HIGH>, + <0 0 12 &gic 0 0 0 169 IRQ_TYPE_LEVEL_HIGH>; + + /include/ "juno-motherboard.dtsi" + }; diff --git a/kernel/arch/arm64/boot/dts/arm/juno-clocks.dtsi b/kernel/arch/arm64/boot/dts/arm/juno-clocks.dtsi index c9b89efe0..25352ed94 100644 --- a/kernel/arch/arm64/boot/dts/arm/juno-clocks.dtsi +++ b/kernel/arch/arm64/boot/dts/arm/juno-clocks.dtsi @@ -36,9 +36,9 @@ clock-output-names = "apb_pclk"; }; - soc_faxiclk: refclk533mhz { + soc_faxiclk: refclk400mhz { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <533000000>; + clock-frequency = <400000000>; clock-output-names = "faxi_clk"; }; diff --git a/kernel/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/kernel/arch/arm64/boot/dts/arm/juno-motherboard.dtsi index 351c95bda..413f1b9eb 100644 --- a/kernel/arch/arm64/boot/dts/arm/juno-motherboard.dtsi +++ b/kernel/arch/arm64/boot/dts/arm/juno-motherboard.dtsi @@ -54,6 +54,70 @@ regulator-always-on; }; + gpio_keys { + compatible = "gpio-keys"; + #address-cells = <1>; + #size-cells = <0>; + + button@1 { + debounce_interval = <50>; + wakeup-source; + linux,code = <116>; + label = "POWER"; + gpios = <&iofpga_gpio0 0 0x4>; + }; + button@2 { + debounce_interval = <50>; + wakeup-source; + linux,code = <102>; + label = "HOME"; + gpios = <&iofpga_gpio0 1 0x4>; + }; + button@3 { + debounce_interval = <50>; + wakeup-source; + linux,code = <152>; + label = "RLOCK"; + gpios = <&iofpga_gpio0 2 0x4>; + }; + button@4 { + debounce_interval = <50>; + wakeup-source; + linux,code = <115>; + label = "VOL+"; + gpios = <&iofpga_gpio0 3 0x4>; + }; + button@5 { + debounce_interval = <50>; + wakeup-source; + linux,code = <114>; + label = "VOL-"; + gpios = <&iofpga_gpio0 4 0x4>; + }; + button@6 { + debounce_interval = <50>; + wakeup-source; + linux,code = <99>; + label = "NMI"; + gpios = <&iofpga_gpio0 5 0x4>; + }; + }; + + flash@0,00000000 { + /* 2 * 32MiB NOR Flash memory mounted on CS0 */ + compatible = "arm,vexpress-flash", "cfi-flash"; + linux,part-probe = "afs"; + reg = <0 0x00000000 0x04000000>; + bank-width = <4>; + /* + * Unfortunately, accessing the flash disturbs + * the CPU idle states (suspend) and CPU + * hotplug of the platform. For this reason, + * flash hardware access is disabled by default. + */ + status = "disabled"; + }; + ethernet@2,00000000 { compatible = "smsc,lan9118", "smsc,lan9115"; reg = <2 0x00000000 0x10000>; @@ -87,6 +151,76 @@ clock-names = "refclk", "timclk", "apb_pclk"; #clock-cells = <1>; clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3"; + assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>; + assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>; + }; + + apbregs@010000 { + compatible = "syscon", "simple-mfd"; + reg = <0x010000 0x1000>; + + led@08.0 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x01>; + label = "vexpress:0"; + linux,default-trigger = "heartbeat"; + default-state = "on"; + }; + led@08.1 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x02>; + label = "vexpress:1"; + linux,default-trigger = "mmc0"; + default-state = "off"; + }; + led@08.2 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x04>; + label = "vexpress:2"; + linux,default-trigger = "cpu0"; + default-state = "off"; + }; + led@08.3 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x08>; + label = "vexpress:3"; + linux,default-trigger = "cpu1"; + default-state = "off"; + }; + led@08.4 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x10>; + label = "vexpress:4"; + linux,default-trigger = "cpu2"; + default-state = "off"; + }; + led@08.5 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x20>; + label = "vexpress:5"; + linux,default-trigger = "cpu3"; + default-state = "off"; + }; + led@08.6 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x40>; + label = "vexpress:6"; + default-state = "off"; + }; + led@08.7 { + compatible = "register-bit-led"; + offset = <0x08>; + mask = <0x80>; + label = "vexpress:7"; + default-state = "off"; + }; }; mmci@050000 { @@ -148,5 +282,17 @@ clocks = <&soc_smc50mhz>; clock-names = "apb_pclk"; }; + + iofpga_gpio0: gpio@1d0000 { + compatible = "arm,pl061", "arm,primecell"; + reg = <0x1d0000 0x1000>; + interrupts = <6>; + clocks = <&soc_smc50mhz>; + clock-names = "apb_pclk"; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; }; }; diff --git a/kernel/arch/arm64/boot/dts/arm/juno-r1.dts b/kernel/arch/arm64/boot/dts/arm/juno-r1.dts new file mode 100644 index 000000000..93bc3d7d5 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/arm/juno-r1.dts @@ -0,0 +1,172 @@ +/* + * ARM Ltd. Juno Platform + * + * Copyright (c) 2015 ARM Ltd. + * + * This file is licensed under a dual GPLv2 or BSD license. + */ + +/dts-v1/; + +#include + +/ { + model = "ARM Juno development board (r1)"; + compatible = "arm,juno-r1", "arm,juno", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + aliases { + serial0 = &soc_uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&A57_0>; + }; + core1 { + cpu = <&A57_1>; + }; + }; + + cluster1 { + core0 { + cpu = <&A53_0>; + }; + core1 { + cpu = <&A53_1>; + }; + core2 { + cpu = <&A53_2>; + }; + core3 { + cpu = <&A53_3>; + }; + }; + }; + + A57_0: cpu@0 { + compatible = "arm,cortex-a57","arm,armv8"; + reg = <0x0 0x0>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A57_L2>; + clocks = <&scpi_dvfs 0>; + }; + + A57_1: cpu@1 { + compatible = "arm,cortex-a57","arm,armv8"; + reg = <0x0 0x1>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A57_L2>; + clocks = <&scpi_dvfs 0>; + }; + + A53_0: cpu@100 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x100>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + }; + + A53_1: cpu@101 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x101>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + }; + + A53_2: cpu@102 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x102>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + }; + + A53_3: cpu@103 { + compatible = "arm,cortex-a53","arm,armv8"; + reg = <0x0 0x103>; + device_type = "cpu"; + enable-method = "psci"; + next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; + }; + + A57_L2: l2-cache0 { + compatible = "cache"; + }; + + A53_L2: l2-cache1 { + compatible = "cache"; + }; + }; + + pmu_a57 { + compatible = "arm,cortex-a57-pmu"; + interrupts = , + ; + interrupt-affinity = <&A57_0>, + <&A57_1>; + }; + + pmu_a53 { + compatible = "arm,cortex-a53-pmu"; + interrupts = , + , + , + ; + interrupt-affinity = <&A53_0>, + <&A53_1>, + <&A53_2>, + <&A53_3>; + }; + + #include "juno-base.dtsi" + + pcie-controller@40000000 { + compatible = "arm,juno-r1-pcie", "plda,xpressrich3-axi", "pci-host-ecam-generic"; + device_type = "pci"; + reg = <0 0x40000000 0 0x10000000>; /* ECAM config space */ + bus-range = <0 255>; + linux,pci-domain = <0>; + #address-cells = <3>; + #size-cells = <2>; + dma-coherent; + ranges = <0x01000000 0x00 0x5f800000 0x00 0x5f800000 0x0 0x00800000>, + <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>, + <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &gic 0 0 0 136 4>, + <0 0 0 2 &gic 0 0 0 137 4>, + <0 0 0 3 &gic 0 0 0 138 4>, + <0 0 0 4 &gic 0 0 0 139 4>; + msi-parent = <&v2m_0>; + }; +}; + +&memtimer { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/arm/juno.dts b/kernel/arch/arm64/boot/dts/arm/juno.dts index 5e9110a33..53442b5ee 100644 --- a/kernel/arch/arm64/boot/dts/arm/juno.dts +++ b/kernel/arch/arm64/boot/dts/arm/juno.dts @@ -34,12 +34,39 @@ #address-cells = <2>; #size-cells = <0>; + cpu-map { + cluster0 { + core0 { + cpu = <&A57_0>; + }; + core1 { + cpu = <&A57_1>; + }; + }; + + cluster1 { + core0 { + cpu = <&A53_0>; + }; + core1 { + cpu = <&A53_1>; + }; + core2 { + cpu = <&A53_2>; + }; + core3 { + cpu = <&A53_3>; + }; + }; + }; + A57_0: cpu@0 { compatible = "arm,cortex-a57","arm,armv8"; reg = <0x0 0x0>; device_type = "cpu"; enable-method = "psci"; next-level-cache = <&A57_L2>; + clocks = <&scpi_dvfs 0>; }; A57_1: cpu@1 { @@ -48,6 +75,7 @@ device_type = "cpu"; enable-method = "psci"; next-level-cache = <&A57_L2>; + clocks = <&scpi_dvfs 0>; }; A53_0: cpu@100 { @@ -56,6 +84,7 @@ device_type = "cpu"; enable-method = "psci"; next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; }; A53_1: cpu@101 { @@ -64,6 +93,7 @@ device_type = "cpu"; enable-method = "psci"; next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; }; A53_2: cpu@102 { @@ -72,6 +102,7 @@ device_type = "cpu"; enable-method = "psci"; next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; }; A53_3: cpu@103 { @@ -80,6 +111,7 @@ device_type = "cpu"; enable-method = "psci"; next-level-cache = <&A53_L2>; + clocks = <&scpi_dvfs 1>; }; A57_L2: l2-cache0 { @@ -91,148 +123,25 @@ }; }; - memory@80000000 { - device_type = "memory"; - /* last 16MB of the first memory area is reserved for secure world use by firmware */ - reg = <0x00000000 0x80000000 0x0 0x7f000000>, - <0x00000008 0x80000000 0x1 0x80000000>; - }; - - gic: interrupt-controller@2c001000 { - compatible = "arm,gic-400", "arm,cortex-a15-gic"; - reg = <0x0 0x2c010000 0 0x1000>, - <0x0 0x2c02f000 0 0x2000>, - <0x0 0x2c04f000 0 0x2000>, - <0x0 0x2c06f000 0 0x2000>; - #address-cells = <0>; - #interrupt-cells = <3>; - interrupt-controller; - interrupts = ; - }; - - timer { - compatible = "arm,armv8-timer"; - interrupts = , - , - , - ; + pmu_a57 { + compatible = "arm,cortex-a57-pmu"; + interrupts = , + ; + interrupt-affinity = <&A57_0>, + <&A57_1>; }; - pmu { - compatible = "arm,armv8-pmuv3"; - interrupts = , - , - , + pmu_a53 { + compatible = "arm,cortex-a53-pmu"; + interrupts = , , , ; - interrupt-affinity = <&A57_0>, - <&A57_1>, - <&A53_0>, + interrupt-affinity = <&A53_0>, <&A53_1>, <&A53_2>, <&A53_3>; }; - /include/ "juno-clocks.dtsi" - - dma@7ff00000 { - compatible = "arm,pl330", "arm,primecell"; - reg = <0x0 0x7ff00000 0 0x1000>; - #dma-cells = <1>; - #dma-channels = <8>; - #dma-requests = <32>; - interrupts = , - , - , - , - , - , - , - ; - clocks = <&soc_faxiclk>; - clock-names = "apb_pclk"; - }; - - soc_uart0: uart@7ff80000 { - compatible = "arm,pl011", "arm,primecell"; - reg = <0x0 0x7ff80000 0x0 0x1000>; - interrupts = ; - clocks = <&soc_uartclk>, <&soc_refclk100mhz>; - clock-names = "uartclk", "apb_pclk"; - }; - - i2c@7ffa0000 { - compatible = "snps,designware-i2c"; - reg = <0x0 0x7ffa0000 0x0 0x1000>; - #address-cells = <1>; - #size-cells = <0>; - interrupts = ; - clock-frequency = <400000>; - i2c-sda-hold-time-ns = <500>; - clocks = <&soc_smc50mhz>; - - dvi0: dvi-transmitter@70 { - compatible = "nxp,tda998x"; - reg = <0x70>; - }; - - dvi1: dvi-transmitter@71 { - compatible = "nxp,tda998x"; - reg = <0x71>; - }; - }; - - ohci@7ffb0000 { - compatible = "generic-ohci"; - reg = <0x0 0x7ffb0000 0x0 0x10000>; - interrupts = ; - clocks = <&soc_usb48mhz>; - }; - - ehci@7ffc0000 { - compatible = "generic-ehci"; - reg = <0x0 0x7ffc0000 0x0 0x10000>; - interrupts = ; - clocks = <&soc_usb48mhz>; - }; - - memory-controller@7ffd0000 { - compatible = "arm,pl354", "arm,primecell"; - reg = <0 0x7ffd0000 0 0x1000>; - interrupts = , - ; - clocks = <&soc_smc50mhz>; - clock-names = "apb_pclk"; - }; - - smb { - compatible = "simple-bus"; - #address-cells = <2>; - #size-cells = <1>; - ranges = <0 0 0 0x08000000 0x04000000>, - <1 0 0 0x14000000 0x04000000>, - <2 0 0 0x18000000 0x04000000>, - <3 0 0 0x1c000000 0x04000000>, - <4 0 0 0x0c000000 0x04000000>, - <5 0 0 0x10000000 0x04000000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 15>; - interrupt-map = <0 0 0 &gic 0 68 IRQ_TYPE_LEVEL_HIGH>, - <0 0 1 &gic 0 69 IRQ_TYPE_LEVEL_HIGH>, - <0 0 2 &gic 0 70 IRQ_TYPE_LEVEL_HIGH>, - <0 0 3 &gic 0 160 IRQ_TYPE_LEVEL_HIGH>, - <0 0 4 &gic 0 161 IRQ_TYPE_LEVEL_HIGH>, - <0 0 5 &gic 0 162 IRQ_TYPE_LEVEL_HIGH>, - <0 0 6 &gic 0 163 IRQ_TYPE_LEVEL_HIGH>, - <0 0 7 &gic 0 164 IRQ_TYPE_LEVEL_HIGH>, - <0 0 8 &gic 0 165 IRQ_TYPE_LEVEL_HIGH>, - <0 0 9 &gic 0 166 IRQ_TYPE_LEVEL_HIGH>, - <0 0 10 &gic 0 167 IRQ_TYPE_LEVEL_HIGH>, - <0 0 11 &gic 0 168 IRQ_TYPE_LEVEL_HIGH>, - <0 0 12 &gic 0 169 IRQ_TYPE_LEVEL_HIGH>; - - /include/ "juno-motherboard.dtsi" - }; + #include "juno-base.dtsi" }; diff --git a/kernel/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi b/kernel/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi index c46cbb29f..88a7583ed 100644 --- a/kernel/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi +++ b/kernel/arch/arm64/boot/dts/arm/rtsm_ve-motherboard.dtsi @@ -74,6 +74,8 @@ clock-names = "refclk", "timclk", "apb_pclk"; #clock-cells = <1>; clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3"; + assigned-clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&v2m_sysctl 3>, <&v2m_sysctl 3>; + assigned-clock-parents = <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>, <&v2m_refclk1mhz>; }; aaci@040000 { diff --git a/kernel/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/kernel/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts new file mode 100644 index 000000000..bb3c26d11 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts @@ -0,0 +1,191 @@ +/* + * ARM Ltd. Versatile Express + * + * LogicTile Express 20MG + * V2F-1XV7 + * + * Cortex-A53 (2 cores) Soft Macrocell Model + * + * HBI-0247C + */ + +/dts-v1/; + +#include + +/ { + model = "V2F-1XV7 Cortex-A53x2 SMM"; + arm,hbi = <0x247>; + arm,vexpress,site = <0xf>; + compatible = "arm,vexpress,v2f-1xv7,ca53x2", "arm,vexpress,v2f-1xv7", "arm,vexpress"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + chosen { + stdout-path = "serial0:38400n8"; + }; + + aliases { + serial0 = &v2m_serial0; + serial1 = &v2m_serial1; + serial2 = &v2m_serial2; + serial3 = &v2m_serial3; + i2c0 = &v2m_i2c_dvi; + i2c1 = &v2m_i2c_pcie; + }; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0 0>; + next-level-cache = <&L2_0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0 1>; + next-level-cache = <&L2_0>; + }; + + L2_0: l2-cache0 { + compatible = "cache"; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0 0x80000000 0 0x80000000>; /* 2GB @ 2GB */ + }; + + gic: interrupt-controller@2c001000 { + compatible = "arm,gic-400"; + #interrupt-cells = <3>; + #address-cells = <0>; + interrupt-controller; + reg = <0 0x2c001000 0 0x1000>, + <0 0x2c002000 0 0x2000>, + <0 0x2c004000 0 0x2000>, + <0 0x2c006000 0 0x2000>; + interrupts = ; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = , + ; + }; + + dcc { + compatible = "arm,vexpress,config-bus"; + arm,vexpress,config-bridge = <&v2m_sysreg>; + + smbclk: osc@4 { + /* SMC clock */ + compatible = "arm,vexpress-osc"; + arm,vexpress-sysreg,func = <1 4>; + freq-range = <40000000 40000000>; + #clock-cells = <0>; + clock-output-names = "smclk"; + }; + + volt@0 { + /* VIO to expansion board above */ + compatible = "arm,vexpress-volt"; + arm,vexpress-sysreg,func = <2 0>; + regulator-name = "VIO_UP"; + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + + volt@1 { + /* 12V from power connector J6 */ + compatible = "arm,vexpress-volt"; + arm,vexpress-sysreg,func = <2 1>; + regulator-name = "12"; + regulator-always-on; + }; + + temp@0 { + /* FPGA temperature */ + compatible = "arm,vexpress-temp"; + arm,vexpress-sysreg,func = <4 0>; + label = "FPGA"; + }; + }; + + smb { + compatible = "simple-bus"; + + #address-cells = <2>; + #size-cells = <1>; + ranges = <0 0 0 0x08000000 0x04000000>, + <1 0 0 0x14000000 0x04000000>, + <2 0 0 0x18000000 0x04000000>, + <3 0 0 0x1c000000 0x04000000>, + <4 0 0 0x0c000000 0x04000000>, + <5 0 0 0x10000000 0x04000000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 63>; + interrupt-map = <0 0 0 &gic GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, + <0 0 1 &gic GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>, + <0 0 2 &gic GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>, + <0 0 3 &gic GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>, + <0 0 4 &gic GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>, + <0 0 5 &gic GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>, + <0 0 6 &gic GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>, + <0 0 7 &gic GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>, + <0 0 8 &gic GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>, + <0 0 9 &gic GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>, + <0 0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>, + <0 0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>, + <0 0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>, + <0 0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>, + <0 0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, + <0 0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>, + <0 0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>, + <0 0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>, + <0 0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>, + <0 0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>, + <0 0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>, + <0 0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>, + <0 0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>, + <0 0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>, + <0 0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>, + <0 0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>, + <0 0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>, + <0 0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>, + <0 0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>, + <0 0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>, + <0 0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>, + <0 0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, + <0 0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>, + <0 0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>, + <0 0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>, + <0 0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>, + <0 0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>, + <0 0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>, + <0 0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>, + <0 0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>, + <0 0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>, + <0 0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>, + <0 0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; + + /include/ "vexpress-v2m-rs1.dtsi" + }; +}; diff --git a/kernel/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi b/kernel/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi new file mode 120000 index 000000000..68fd0f8f1 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/arm/vexpress-v2m-rs1.dtsi @@ -0,0 +1 @@ +../../../../arm/boot/dts/vexpress-v2m-rs1.dtsi \ No newline at end of file diff --git a/kernel/arch/arm64/boot/dts/broadcom/Makefile b/kernel/arch/arm64/boot/dts/broadcom/Makefile new file mode 100644 index 000000000..e21fe66f1 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/broadcom/Makefile @@ -0,0 +1,5 @@ +dtb-$(CONFIG_ARCH_BCM_IPROC) += ns2-svk.dtb + +always := $(dtb-y) +subdir-y := $(dts-dirs) +clean-files := *.dtb diff --git a/kernel/arch/arm64/boot/dts/broadcom/ns2-svk.dts b/kernel/arch/arm64/boot/dts/broadcom/ns2-svk.dts new file mode 100644 index 000000000..244baf879 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/broadcom/ns2-svk.dts @@ -0,0 +1,59 @@ +/* + * BSD LICENSE + * + * Copyright(c) 2015 Broadcom Corporation. All rights reserved. + * + * 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 Broadcom 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. + */ + +/dts-v1/; + +#include "ns2.dtsi" + +/ { + model = "Broadcom NS2 SVK"; + compatible = "brcm,ns2-svk", "brcm,ns2"; + + aliases { + serial0 = &uart3; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory { + device_type = "memory"; + reg = <0x000000000 0x80000000 0x00000000 0x40000000>; + }; + + soc: soc { + uart3: serial@66130000 { + status = "ok"; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/broadcom/ns2.dtsi b/kernel/arch/arm64/boot/dts/broadcom/ns2.dtsi new file mode 100644 index 000000000..3c92d9227 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/broadcom/ns2.dtsi @@ -0,0 +1,118 @@ +/* + * BSD LICENSE + * + * Copyright(c) 2015 Broadcom Corporation. All rights reserved. + * + * 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 Broadcom 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 + +/memreserve/ 0x84b00000 0x00000008; + +/ { + compatible = "brcm,ns2"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0 0>; + enable-method = "spin-table"; + cpu-release-addr = <0 0x84b00000>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0 1>; + enable-method = "spin-table"; + cpu-release-addr = <0 0x84b00000>; + }; + + cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0 2>; + enable-method = "spin-table"; + cpu-release-addr = <0 0x84b00000>; + }; + + cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0 3>; + enable-method = "spin-table"; + cpu-release-addr = <0 0x84b00000>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + soc: soc { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0 0 0xffffffff>; + + gic: interrupt-controller@65210000 { + compatible = "arm,gic-400"; + #interrupt-cells = <3>; + interrupt-controller; + reg = <0x65210000 0x1000>, + <0x65220000 0x1000>, + <0x65240000 0x2000>, + <0x65260000 0x1000>; + }; + + uart3: serial@66130000 { + compatible = "snps,dw-apb-uart"; + reg = <0x66130000 0x100>; + interrupts = ; + reg-shift = <2>; + reg-io-width = <4>; + clock-frequency = <23961600>; + status = "disabled"; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/kernel/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi index d8c0bdc51..9cb7cf942 100644 --- a/kernel/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi +++ b/kernel/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi @@ -376,10 +376,19 @@ gic0: interrupt-controller@8010,00000000 { compatible = "arm,gic-v3"; #interrupt-cells = <3>; + #address-cells = <2>; + #size-cells = <2>; + ranges; interrupt-controller; reg = <0x8010 0x00000000 0x0 0x010000>, /* GICD */ <0x8010 0x80000000 0x0 0x600000>; /* GICR */ interrupts = <1 9 0xf04>; + + its: gic-its@8010,00020000 { + compatible = "arm,gic-v3-its"; + msi-controller; + reg = <0x8010 0x20000 0x0 0x200000>; + }; }; uaa0: serial@87e0,24000000 { diff --git a/kernel/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi b/kernel/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi index 2eef4a279..f77ddaf21 100644 --- a/kernel/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi +++ b/kernel/arch/arm64/boot/dts/exynos/exynos7-pinctrl.dtsi @@ -586,3 +586,106 @@ samsung,pin-drv = <2>; }; }; + +&pinctrl_bus1 { + gpf0: gpf0 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpf1: gpf1 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpf2: gpf2 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpf3: gpf3 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpf4: gpf4 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpf5: gpf5 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpg1: gpg1 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpg2: gpg2 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gph1: gph1 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpv6: gpv6 { + gpio-controller; + #gpio-cells = <2>; + + interrupt-controller; + #interrupt-cells = <2>; + }; + + spi5_bus: spi5-bus { + samsung,pins = "gpf2-0", "gpf2-1", "gpf2-2", "gpf2-3"; + samsung,pin-function = <2>; + samsung,pin-pud = <3>; + samsung,pin-drv = <0>; + }; + + ufs_refclk_out: ufs-refclk-out { + samsung,pins = "gpg2-4"; + samsung,pin-function = <2>; + samsung,pin-pud = <0>; + samsung,pin-drv = <2>; + }; + + ufs_rst_n: ufs-rst-n { + samsung,pins = "gph1-5"; + samsung,pin-function = <2>; + samsung,pin-pud = <3>; + samsung,pin-drv = <0>; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/exynos/exynos7.dtsi b/kernel/arch/arm64/boot/dts/exynos/exynos7.dtsi index d7a37c3a6..f9c5a549c 100644 --- a/kernel/arch/arm64/boot/dts/exynos/exynos7.dtsi +++ b/kernel/arch/arm64/boot/dts/exynos/exynos7.dtsi @@ -26,6 +26,7 @@ pinctrl5 = &pinctrl_ese; pinctrl6 = &pinctrl_fsys0; pinctrl7 = &pinctrl_fsys1; + pinctrl8 = &pinctrl_bus1; }; cpus { @@ -278,6 +279,12 @@ interrupts = <0 203 0>; }; + pinctrl_bus1: pinctrl@14870000 { + compatible = "samsung,exynos7-pinctrl"; + reg = <0x14870000 0x1000>; + interrupts = <0 384 0>; + }; + hsi2c_0: hsi2c@13640000 { compatible = "samsung,exynos7-hsi2c"; reg = <0x13640000 0x1000>; diff --git a/kernel/arch/arm64/boot/dts/freescale/Makefile b/kernel/arch/arm64/boot/dts/freescale/Makefile index 4f2de3e78..c4957a4aa 100644 --- a/kernel/arch/arm64/boot/dts/freescale/Makefile +++ b/kernel/arch/arm64/boot/dts/freescale/Makefile @@ -1,4 +1,6 @@ -dtb-$(CONFIG_ARCH_FSL_LS2085A) += fsl-ls2085a-simu.dtb +dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-qds.dtb +dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-rdb.dtb +dtb-$(CONFIG_ARCH_LAYERSCAPE) += fsl-ls2080a-simu.dtb always := $(dtb-y) subdir-y := $(dts-dirs) diff --git a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts new file mode 100644 index 000000000..4cb996d6e --- /dev/null +++ b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-qds.dts @@ -0,0 +1,204 @@ +/* + * Device Tree file for Freescale LS2080a QDS Board. + * + * Copyright (C) 2015, Freescale Semiconductor + * + * Bhupesh Sharma + * + * This file is dual-licensed: you can use it either under the terms + * of the GPLv2 or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +/dts-v1/; + +/include/ "fsl-ls2080a.dtsi" + +/ { + model = "Freescale Layerscape 2080a QDS Board"; + compatible = "fsl,ls2080a-qds", "fsl,ls2080a"; + + aliases { + serial0 = &serial0; + serial1 = &serial1; + }; + +}; + +&esdhc { + status = "okay"; +}; + +&ifc { + status = "okay"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0x0 0x0 0x5 0x80000000 0x08000000 + 0x2 0x0 0x5 0x30000000 0x00010000 + 0x3 0x0 0x5 0x20000000 0x00010000>; + + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + bank-width = <2>; + device-width = <1>; + }; + + nand@2,0 { + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + }; + + cpld@3,0 { + reg = <0x3 0x0 0x10000>; + compatible = "fsl,ls2080aqds-fpga", "fsl,fpga-qixis"; + }; +}; + +&i2c0 { + status = "okay"; + pca9547@77 { + compatible = "nxp,pca9547"; + reg = <0x77>; + #address-cells = <1>; + #size-cells = <0>; + i2c@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x00>; + rtc@68 { + compatible = "dallas,ds3232"; + reg = <0x68>; + }; + }; + + i2c@2 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x02>; + + ina220@40 { + compatible = "ti,ina220"; + reg = <0x40>; + shunt-resistor = <500>; + }; + + ina220@41 { + compatible = "ti,ina220"; + reg = <0x41>; + shunt-resistor = <1000>; + }; + }; + + i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x3>; + + adt7481@4c { + compatible = "adi,adt7461"; + reg = <0x4c>; + }; + }; + }; +}; + +&i2c1 { + status = "disabled"; +}; + +&i2c2 { + status = "disabled"; +}; + +&i2c3 { + status = "disabled"; +}; + +&dspi { + status = "okay"; + dflash0: n25q128a { + #address-cells = <1>; + #size-cells = <1>; + compatible = "st,m25p80"; + spi-max-frequency = <3000000>; + reg = <0>; + }; + dflash1: sst25wf040b { + #address-cells = <1>; + #size-cells = <1>; + compatible = "st,m25p80"; + spi-max-frequency = <3000000>; + reg = <1>; + }; + dflash2: en25s64 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "st,m25p80"; + spi-max-frequency = <3000000>; + reg = <2>; + }; +}; + +&qspi { + status = "okay"; + qflash0: s25fl008k { + #address-cells = <1>; + #size-cells = <1>; + compatible = "st,m25p80"; + spi-max-frequency = <20000000>; + reg = <0>; + }; +}; + +&sata0 { + status = "okay"; +}; + +&sata1 { + status = "okay"; +}; + +&usb0 { + status = "okay"; +}; + +&usb1 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts new file mode 100644 index 000000000..e127f0baa --- /dev/null +++ b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-rdb.dts @@ -0,0 +1,166 @@ +/* + * Device Tree file for Freescale LS2080a RDB Board. + * + * Copyright (C) 2015, Freescale Semiconductor + * + * Bhupesh Sharma + * + * This file is dual-licensed: you can use it either under the terms + * of the GPLv2 or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +/dts-v1/; + +/include/ "fsl-ls2080a.dtsi" + +/ { + model = "Freescale Layerscape 2080a RDB Board"; + compatible = "fsl,ls2080a-rdb", "fsl,ls2080a"; + + aliases { + serial0 = &serial0; + serial1 = &serial1; + }; +}; + +&esdhc { + status = "okay"; +}; + +&ifc { + status = "okay"; + #address-cells = <2>; + #size-cells = <1>; + ranges = <0x0 0x0 0x5 0x80000000 0x08000000 + 0x2 0x0 0x5 0x30000000 0x00010000 + 0x3 0x0 0x5 0x20000000 0x00010000>; + + nor@0,0 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "cfi-flash"; + reg = <0x0 0x0 0x8000000>; + bank-width = <2>; + device-width = <1>; + }; + + nand@2,0 { + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + }; + + cpld@3,0 { + reg = <0x3 0x0 0x10000>; + compatible = "fsl,ls2080aqds-fpga", "fsl,fpga-qixis"; + }; + +}; + +&i2c0 { + status = "okay"; + pca9547@75 { + compatible = "nxp,pca9547"; + reg = <0x75>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + i2c@1 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x01>; + rtc@68 { + compatible = "dallas,ds3232"; + reg = <0x68>; + }; + }; + + i2c@3 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x3>; + + adt7481@4c { + compatible = "adi,adt7461"; + reg = <0x4c>; + }; + }; + }; +}; + +&i2c1 { + status = "disabled"; +}; + +&i2c2 { + status = "disabled"; +}; + +&i2c3 { + status = "disabled"; +}; + +&dspi { + status = "okay"; + dflash0: n25q512a { + #address-cells = <1>; + #size-cells = <1>; + compatible = "st,m25p80"; + spi-max-frequency = <3000000>; + reg = <0>; + }; +}; + +&qspi { + status = "disabled"; +}; + +&sata0 { + status = "okay"; +}; + +&sata1 { + status = "okay"; +}; + +&usb0 { + status = "okay"; +}; + +&usb1 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts new file mode 100644 index 000000000..505d03807 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a-simu.dts @@ -0,0 +1,70 @@ +/* + * Device Tree file for Freescale LS2080a software Simulator model + * + * Copyright (C) 2014-2015, Freescale Semiconductor + * + * Bhupesh Sharma + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +/dts-v1/; + +/include/ "fsl-ls2080a.dtsi" + +/ { + model = "Freescale Layerscape 2080a software Simulator model"; + compatible = "fsl,ls2080a-simu", "fsl,ls2080a"; + + aliases { + serial0 = &serial0; + serial1 = &serial1; + }; + + ethernet@2210000 { + compatible = "smsc,lan91c111"; + reg = <0x0 0x2210000 0x0 0x100>; + interrupts = <0 58 0x1>; + }; +}; + +&ifc { + status = "okay"; +}; + diff --git a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi new file mode 100644 index 000000000..925552e7b --- /dev/null +++ b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi @@ -0,0 +1,520 @@ +/* + * Device Tree Include file for Freescale Layerscape-2080A family SoC. + * + * Copyright (C) 2014-2015, Freescale Semiconductor + * + * Bhupesh Sharma + * + * This file is dual-licensed: you can use it either under the terms + * of the GPLv2 or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +/ { + compatible = "fsl,ls2080a"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + /* + * We expect the enable-method for cpu's to be "psci", but this + * is dependent on the SoC FW, which will fill this in. + * + * Currently supported enable-method is psci v0.2 + */ + + /* We have 4 clusters having 2 Cortex-A57 cores each */ + cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x0>; + clocks = <&clockgen 1 0>; + }; + + cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x1>; + clocks = <&clockgen 1 0>; + }; + + cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x100>; + clocks = <&clockgen 1 1>; + }; + + cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x101>; + clocks = <&clockgen 1 1>; + }; + + cpu@200 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x200>; + clocks = <&clockgen 1 2>; + }; + + cpu@201 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x201>; + clocks = <&clockgen 1 2>; + }; + + cpu@300 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x300>; + clocks = <&clockgen 1 3>; + }; + + cpu@301 { + device_type = "cpu"; + compatible = "arm,cortex-a57"; + reg = <0x0 0x301>; + clocks = <&clockgen 1 3>; + }; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x00000000 0x80000000 0 0x80000000>; + /* DRAM space - 1, size : 2 GB DRAM */ + }; + + sysclk: sysclk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <100000000>; + clock-output-names = "sysclk"; + }; + + gic: interrupt-controller@6000000 { + compatible = "arm,gic-v3"; + reg = <0x0 0x06000000 0 0x10000>, /* GIC Dist */ + <0x0 0x06100000 0 0x100000>, /* GICR (RD_base + SGI_base) */ + <0x0 0x0c0c0000 0 0x2000>, /* GICC */ + <0x0 0x0c0d0000 0 0x1000>, /* GICH */ + <0x0 0x0c0e0000 0 0x20000>; /* GICV */ + #interrupt-cells = <3>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + interrupt-controller; + interrupts = <1 9 0x4>; + + its: gic-its@6020000 { + compatible = "arm,gic-v3-its"; + msi-controller; + reg = <0x0 0x6020000 0 0x20000>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */ + <1 14 0x8>, /* Physical Non-Secure PPI, active-low */ + <1 11 0x8>, /* Virtual PPI, active-low */ + <1 10 0x8>; /* Hypervisor PPI, active-low */ + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = <1 7 0x8>; /* PMU PPI, Level low type */ + }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clockgen: clocking@1300000 { + compatible = "fsl,ls2080a-clockgen"; + reg = <0 0x1300000 0 0xa0000>; + #clock-cells = <2>; + clocks = <&sysclk>; + }; + + serial0: serial@21c0500 { + compatible = "fsl,ns16550", "ns16550a"; + reg = <0x0 0x21c0500 0x0 0x100>; + clocks = <&clockgen 4 3>; + interrupts = <0 32 0x4>; /* Level high type */ + }; + + serial1: serial@21c0600 { + compatible = "fsl,ns16550", "ns16550a"; + reg = <0x0 0x21c0600 0x0 0x100>; + clocks = <&clockgen 4 3>; + interrupts = <0 32 0x4>; /* Level high type */ + }; + + fsl_mc: fsl-mc@80c000000 { + compatible = "fsl,qoriq-mc"; + reg = <0x00000008 0x0c000000 0 0x40>, /* MC portal base */ + <0x00000000 0x08340000 0 0x40000>; /* MC control reg */ + }; + + smmu: iommu@5000000 { + compatible = "arm,mmu-500"; + reg = <0 0x5000000 0 0x800000>; + #global-interrupts = <12>; + interrupts = <0 13 4>, /* global secure fault */ + <0 14 4>, /* combined secure interrupt */ + <0 15 4>, /* global non-secure fault */ + <0 16 4>, /* combined non-secure interrupt */ + /* performance counter interrupts 0-7 */ + <0 211 4>, <0 212 4>, + <0 213 4>, <0 214 4>, + <0 215 4>, <0 216 4>, + <0 217 4>, <0 218 4>, + /* per context interrupt, 64 interrupts */ + <0 146 4>, <0 147 4>, + <0 148 4>, <0 149 4>, + <0 150 4>, <0 151 4>, + <0 152 4>, <0 153 4>, + <0 154 4>, <0 155 4>, + <0 156 4>, <0 157 4>, + <0 158 4>, <0 159 4>, + <0 160 4>, <0 161 4>, + <0 162 4>, <0 163 4>, + <0 164 4>, <0 165 4>, + <0 166 4>, <0 167 4>, + <0 168 4>, <0 169 4>, + <0 170 4>, <0 171 4>, + <0 172 4>, <0 173 4>, + <0 174 4>, <0 175 4>, + <0 176 4>, <0 177 4>, + <0 178 4>, <0 179 4>, + <0 180 4>, <0 181 4>, + <0 182 4>, <0 183 4>, + <0 184 4>, <0 185 4>, + <0 186 4>, <0 187 4>, + <0 188 4>, <0 189 4>, + <0 190 4>, <0 191 4>, + <0 192 4>, <0 193 4>, + <0 194 4>, <0 195 4>, + <0 196 4>, <0 197 4>, + <0 198 4>, <0 199 4>, + <0 200 4>, <0 201 4>, + <0 202 4>, <0 203 4>, + <0 204 4>, <0 205 4>, + <0 206 4>, <0 207 4>, + <0 208 4>, <0 209 4>; + mmu-masters = <&fsl_mc 0x300 0>; + }; + + dspi: dspi@2100000 { + status = "disabled"; + compatible = "fsl,vf610-dspi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x2100000 0x0 0x10000>; + interrupts = <0 26 0x4>; /* Level high type */ + clocks = <&clockgen 4 3>; + clock-names = "dspi"; + spi-num-chipselects = <5>; + bus-num = <0>; + }; + + esdhc: esdhc@2140000 { + status = "disabled"; + compatible = "fsl,ls2080a-esdhc", "fsl,esdhc"; + reg = <0x0 0x2140000 0x0 0x10000>; + interrupts = <0 28 0x4>; /* Level high type */ + clock-frequency = <0>; /* Updated by bootloader */ + voltage-ranges = <1800 1800 3300 3300>; + sdhci,auto-cmd12; + little-endian; + bus-width = <4>; + }; + + gpio0: gpio@2300000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x0 0x2300000 0x0 0x10000>; + interrupts = <0 36 0x4>; /* Level high type */ + gpio-controller; + little-endian; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpio1: gpio@2310000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x0 0x2310000 0x0 0x10000>; + interrupts = <0 36 0x4>; /* Level high type */ + gpio-controller; + little-endian; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpio2: gpio@2320000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x0 0x2320000 0x0 0x10000>; + interrupts = <0 37 0x4>; /* Level high type */ + gpio-controller; + little-endian; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + gpio3: gpio@2330000 { + compatible = "fsl,qoriq-gpio"; + reg = <0x0 0x2330000 0x0 0x10000>; + interrupts = <0 37 0x4>; /* Level high type */ + gpio-controller; + little-endian; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + i2c0: i2c@2000000 { + status = "disabled"; + compatible = "fsl,vf610-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x2000000 0x0 0x10000>; + interrupts = <0 34 0x4>; /* Level high type */ + clock-names = "i2c"; + clocks = <&clockgen 4 3>; + }; + + i2c1: i2c@2010000 { + status = "disabled"; + compatible = "fsl,vf610-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x2010000 0x0 0x10000>; + interrupts = <0 34 0x4>; /* Level high type */ + clock-names = "i2c"; + clocks = <&clockgen 4 3>; + }; + + i2c2: i2c@2020000 { + status = "disabled"; + compatible = "fsl,vf610-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x2020000 0x0 0x10000>; + interrupts = <0 35 0x4>; /* Level high type */ + clock-names = "i2c"; + clocks = <&clockgen 4 3>; + }; + + i2c3: i2c@2030000 { + status = "disabled"; + compatible = "fsl,vf610-i2c"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x2030000 0x0 0x10000>; + interrupts = <0 35 0x4>; /* Level high type */ + clock-names = "i2c"; + clocks = <&clockgen 4 3>; + }; + + ifc: ifc@2240000 { + compatible = "fsl,ifc", "simple-bus"; + reg = <0x0 0x2240000 0x0 0x20000>; + interrupts = <0 21 0x4>; /* Level high type */ + little-endian; + #address-cells = <2>; + #size-cells = <1>; + + ranges = <0 0 0x5 0x80000000 0x08000000 + 2 0 0x5 0x30000000 0x00010000 + 3 0 0x5 0x20000000 0x00010000>; + }; + + qspi: quadspi@20c0000 { + status = "disabled"; + compatible = "fsl,vf610-qspi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x20c0000 0x0 0x10000>, + <0x0 0x20000000 0x0 0x10000000>; + reg-names = "QuadSPI", "QuadSPI-memory"; + interrupts = <0 25 0x4>; /* Level high type */ + clocks = <&clockgen 4 3>, <&clockgen 4 3>; + clock-names = "qspi_en", "qspi"; + }; + + pcie@3400000 { + compatible = "fsl,ls2080a-pcie", "snps,dw-pcie"; + reg = <0x00 0x03400000 0x0 0x00100000 /* controller registers */ + 0x10 0x00000000 0x0 0x00002000>; /* configuration space */ + reg-names = "regs", "config"; + interrupts = <0 108 0x4>; /* Level high type */ + interrupt-names = "intr"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + num-lanes = <4>; + bus-range = <0x0 0xff>; + ranges = <0x81000000 0x0 0x00000000 0x10 0x00010000 0x0 0x00010000 /* downstream I/O */ + 0x82000000 0x0 0x40000000 0x10 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */ + msi-parent = <&its>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0000 0 0 1 &gic 0 0 0 109 4>, + <0000 0 0 2 &gic 0 0 0 110 4>, + <0000 0 0 3 &gic 0 0 0 111 4>, + <0000 0 0 4 &gic 0 0 0 112 4>; + }; + + pcie@3500000 { + compatible = "fsl,ls2080a-pcie", "snps,dw-pcie"; + reg = <0x00 0x03500000 0x0 0x00100000 /* controller registers */ + 0x12 0x00000000 0x0 0x00002000>; /* configuration space */ + reg-names = "regs", "config"; + interrupts = <0 113 0x4>; /* Level high type */ + interrupt-names = "intr"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + num-lanes = <4>; + bus-range = <0x0 0xff>; + ranges = <0x81000000 0x0 0x00000000 0x12 0x00010000 0x0 0x00010000 /* downstream I/O */ + 0x82000000 0x0 0x40000000 0x12 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */ + msi-parent = <&its>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0000 0 0 1 &gic 0 0 0 114 4>, + <0000 0 0 2 &gic 0 0 0 115 4>, + <0000 0 0 3 &gic 0 0 0 116 4>, + <0000 0 0 4 &gic 0 0 0 117 4>; + }; + + pcie@3600000 { + compatible = "fsl,ls2080a-pcie", "snps,dw-pcie"; + reg = <0x00 0x03600000 0x0 0x00100000 /* controller registers */ + 0x14 0x00000000 0x0 0x00002000>; /* configuration space */ + reg-names = "regs", "config"; + interrupts = <0 118 0x4>; /* Level high type */ + interrupt-names = "intr"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + num-lanes = <8>; + bus-range = <0x0 0xff>; + ranges = <0x81000000 0x0 0x00000000 0x14 0x00010000 0x0 0x00010000 /* downstream I/O */ + 0x82000000 0x0 0x40000000 0x14 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */ + msi-parent = <&its>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0000 0 0 1 &gic 0 0 0 119 4>, + <0000 0 0 2 &gic 0 0 0 120 4>, + <0000 0 0 3 &gic 0 0 0 121 4>, + <0000 0 0 4 &gic 0 0 0 122 4>; + }; + + pcie@3700000 { + compatible = "fsl,ls2080a-pcie", "snps,dw-pcie"; + reg = <0x00 0x03700000 0x0 0x00100000 /* controller registers */ + 0x16 0x00000000 0x0 0x00002000>; /* configuration space */ + reg-names = "regs", "config"; + interrupts = <0 123 0x4>; /* Level high type */ + interrupt-names = "intr"; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + num-lanes = <4>; + bus-range = <0x0 0xff>; + ranges = <0x81000000 0x0 0x00000000 0x16 0x00010000 0x0 0x00010000 /* downstream I/O */ + 0x82000000 0x0 0x40000000 0x16 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */ + msi-parent = <&its>; + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0000 0 0 1 &gic 0 0 0 124 4>, + <0000 0 0 2 &gic 0 0 0 125 4>, + <0000 0 0 3 &gic 0 0 0 126 4>, + <0000 0 0 4 &gic 0 0 0 127 4>; + }; + + sata0: sata@3200000 { + status = "disabled"; + compatible = "fsl,ls2080a-ahci"; + reg = <0x0 0x3200000 0x0 0x10000>; + interrupts = <0 133 0x4>; /* Level high type */ + clocks = <&clockgen 4 3>; + }; + + sata1: sata@3210000 { + status = "disabled"; + compatible = "fsl,ls2080a-ahci"; + reg = <0x0 0x3210000 0x0 0x10000>; + interrupts = <0 136 0x4>; /* Level high type */ + clocks = <&clockgen 4 3>; + }; + + usb0: usb3@3100000 { + status = "disabled"; + compatible = "snps,dwc3"; + reg = <0x0 0x3100000 0x0 0x10000>; + interrupts = <0 80 0x4>; /* Level high type */ + dr_mode = "host"; + }; + + usb1: usb3@3110000 { + status = "disabled"; + compatible = "snps,dwc3"; + reg = <0x0 0x3110000 0x0 0x10000>; + interrupts = <0 81 0x4>; /* Level high type */ + dr_mode = "host"; + }; + + ccn@4000000 { + compatible = "arm,ccn-504"; + reg = <0x0 0x04000000 0x0 0x01000000>; + interrupts = <0 12 4>; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a-simu.dts b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a-simu.dts deleted file mode 100644 index 82e2a6fcc..000000000 --- a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a-simu.dts +++ /dev/null @@ -1,65 +0,0 @@ -/* - * Device Tree file for Freescale LS2085a software Simulator model - * - * Copyright (C) 2014, Freescale Semiconductor - * - * Bhupesh Sharma - * - * This file is dual-licensed: you can use it either under the terms - * of the GPL or the X11 license, at your option. Note that this dual - * licensing only applies to this file, and not this project as a - * whole. - * - * a) This library 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 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 General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this library; if not, write to the Free - * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, - * MA 02110-1301 USA - * - * Or, alternatively, - * - * b) 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. - */ - -/dts-v1/; - -/include/ "fsl-ls2085a.dtsi" - -/ { - model = "Freescale Layerscape 2085a software Simulator model"; - compatible = "fsl,ls2085a-simu", "fsl,ls2085a"; - - ethernet@2210000 { - compatible = "smsc,lan91c111"; - reg = <0x0 0x2210000 0x0 0x100>; - interrupts = <0 58 0x1>; - }; -}; diff --git a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a.dtsi b/kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a.dtsi deleted file mode 100644 index e281ceb33..000000000 --- a/kernel/arch/arm64/boot/dts/freescale/fsl-ls2085a.dtsi +++ /dev/null @@ -1,163 +0,0 @@ -/* - * Device Tree Include file for Freescale Layerscape-2085A family SoC. - * - * Copyright (C) 2014, Freescale Semiconductor - * - * Bhupesh Sharma - * - * This file is dual-licensed: you can use it either under the terms - * of the GPLv2 or the X11 license, at your option. Note that this dual - * licensing only applies to this file, and not this project as a - * whole. - * - * a) This library 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 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 General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this library; if not, write to the Free - * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, - * MA 02110-1301 USA - * - * Or, alternatively, - * - * b) 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. - */ - -/ { - compatible = "fsl,ls2085a"; - interrupt-parent = <&gic>; - #address-cells = <2>; - #size-cells = <2>; - - cpus { - #address-cells = <2>; - #size-cells = <0>; - - /* - * We expect the enable-method for cpu's to be "psci", but this - * is dependent on the SoC FW, which will fill this in. - * - * Currently supported enable-method is psci v0.2 - */ - - /* We have 4 clusters having 2 Cortex-A57 cores each */ - cpu@0 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x0>; - }; - - cpu@1 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x1>; - }; - - cpu@100 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x100>; - }; - - cpu@101 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x101>; - }; - - cpu@200 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x200>; - }; - - cpu@201 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x201>; - }; - - cpu@300 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x300>; - }; - - cpu@301 { - device_type = "cpu"; - compatible = "arm,cortex-a57"; - reg = <0x0 0x301>; - }; - }; - - memory@80000000 { - device_type = "memory"; - reg = <0x00000000 0x80000000 0 0x80000000>; - /* DRAM space - 1, size : 2 GB DRAM */ - }; - - gic: interrupt-controller@6000000 { - compatible = "arm,gic-v3"; - reg = <0x0 0x06000000 0 0x10000>, /* GIC Dist */ - <0x0 0x06100000 0 0x100000>; /* GICR (RD_base + SGI_base) */ - #interrupt-cells = <3>; - interrupt-controller; - interrupts = <1 9 0x4>; - }; - - timer { - compatible = "arm,armv8-timer"; - interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */ - <1 14 0x8>, /* Physical Non-Secure PPI, active-low */ - <1 11 0x8>, /* Virtual PPI, active-low */ - <1 10 0x8>; /* Hypervisor PPI, active-low */ - }; - - serial0: serial@21c0500 { - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550a"; - reg = <0x0 0x21c0500 0x0 0x100>; - clock-frequency = <0>; /* Updated by bootloader */ - interrupts = <0 32 0x1>; /* edge triggered */ - }; - - serial1: serial@21c0600 { - device_type = "serial"; - compatible = "fsl,ns16550", "ns16550a"; - reg = <0x0 0x21c0600 0x0 0x100>; - clock-frequency = <0>; /* Updated by bootloader */ - interrupts = <0 32 0x1>; /* edge triggered */ - }; - - fsl_mc: fsl-mc@80c000000 { - compatible = "fsl,qoriq-mc"; - reg = <0x00000008 0x0c000000 0 0x40>, /* MC portal base */ - <0x00000000 0x08340000 0 0x40000>; /* MC control reg */ - }; -}; diff --git a/kernel/arch/arm64/boot/dts/hisilicon/Makefile b/kernel/arch/arm64/boot/dts/hisilicon/Makefile new file mode 100644 index 000000000..cd158b80e --- /dev/null +++ b/kernel/arch/arm64/boot/dts/hisilicon/Makefile @@ -0,0 +1,5 @@ +dtb-$(CONFIG_ARCH_HISI) += hi6220-hikey.dtb hip05-d02.dtb + +always := $(dtb-y) +subdir-y := $(dts-dirs) +clean-files := *.dtb diff --git a/kernel/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/kernel/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts new file mode 100644 index 000000000..8d43a0fce --- /dev/null +++ b/kernel/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts @@ -0,0 +1,34 @@ +/* + * dts file for Hisilicon HiKey Development Board + * + * Copyright (C) 2015, Hisilicon Ltd. + * + */ + +/dts-v1/; + +/*Reserved 1MB memory for MCU*/ +/memreserve/ 0x05e00000 0x00100000; + +#include "hi6220.dtsi" + +/ { + model = "HiKey Development Board"; + compatible = "hisilicon,hi6220-hikey", "hisilicon,hi6220"; + + aliases { + serial0 = &uart0; /* On board UART0 */ + serial1 = &uart1; /* BT UART */ + serial2 = &uart2; /* LS Expansion UART0 */ + serial3 = &uart3; /* LS Expansion UART1 */ + }; + + chosen { + stdout-path = "serial3:115200n8"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x40000000>; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/hisilicon/hi6220.dtsi b/kernel/arch/arm64/boot/dts/hisilicon/hi6220.dtsi new file mode 100644 index 000000000..82d2488a0 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/hisilicon/hi6220.dtsi @@ -0,0 +1,212 @@ +/* + * dts file for Hisilicon Hi6220 SoC + * + * Copyright (C) 2015, Hisilicon Ltd. + */ + +#include +#include + +/ { + compatible = "hisilicon,hi6220"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + cpus { + #address-cells = <2>; + #size-cells = <0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + core1 { + cpu = <&cpu1>; + }; + core2 { + cpu = <&cpu2>; + }; + core3 { + cpu = <&cpu3>; + }; + }; + cluster1 { + core0 { + cpu = <&cpu4>; + }; + core1 { + cpu = <&cpu5>; + }; + core2 { + cpu = <&cpu6>; + }; + core3 { + cpu = <&cpu7>; + }; + }; + }; + + cpu0: cpu@0 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x0>; + enable-method = "psci"; + }; + + cpu1: cpu@1 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x1>; + enable-method = "psci"; + }; + + cpu2: cpu@2 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x2>; + enable-method = "psci"; + }; + + cpu3: cpu@3 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x3>; + enable-method = "psci"; + }; + + cpu4: cpu@100 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x100>; + enable-method = "psci"; + }; + + cpu5: cpu@101 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x101>; + enable-method = "psci"; + }; + + cpu6: cpu@102 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x102>; + enable-method = "psci"; + }; + + cpu7: cpu@103 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0 0x103>; + enable-method = "psci"; + }; + }; + + gic: interrupt-controller@f6801000 { + compatible = "arm,gic-400"; + reg = <0x0 0xf6801000 0 0x1000>, /* GICD */ + <0x0 0xf6802000 0 0x2000>, /* GICC */ + <0x0 0xf6804000 0 0x2000>, /* GICH */ + <0x0 0xf6806000 0 0x2000>; /* GICV */ + #address-cells = <0>; + #interrupt-cells = <3>; + interrupt-controller; + interrupts = ; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupt-parent = <&gic>; + interrupts = , + , + , + ; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + ao_ctrl: ao_ctrl@f7800000 { + compatible = "hisilicon,hi6220-aoctrl", "syscon"; + reg = <0x0 0xf7800000 0x0 0x2000>; + #clock-cells = <1>; + }; + + sys_ctrl: sys_ctrl@f7030000 { + compatible = "hisilicon,hi6220-sysctrl", "syscon"; + reg = <0x0 0xf7030000 0x0 0x2000>; + #clock-cells = <1>; + }; + + media_ctrl: media_ctrl@f4410000 { + compatible = "hisilicon,hi6220-mediactrl", "syscon"; + reg = <0x0 0xf4410000 0x0 0x1000>; + #clock-cells = <1>; + }; + + pm_ctrl: pm_ctrl@f7032000 { + compatible = "hisilicon,hi6220-pmctrl", "syscon"; + reg = <0x0 0xf7032000 0x0 0x1000>; + #clock-cells = <1>; + }; + + uart0: uart@f8015000 { /* console */ + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0 0xf8015000 0x0 0x1000>; + interrupts = ; + clocks = <&ao_ctrl HI6220_UART0_PCLK>, + <&ao_ctrl HI6220_UART0_PCLK>; + clock-names = "uartclk", "apb_pclk"; + }; + + uart1: uart@f7111000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0 0xf7111000 0x0 0x1000>; + interrupts = ; + clocks = <&sys_ctrl HI6220_UART1_PCLK>, + <&sys_ctrl HI6220_UART1_PCLK>; + clock-names = "uartclk", "apb_pclk"; + status = "disabled"; + }; + + uart2: uart@f7112000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0 0xf7112000 0x0 0x1000>; + interrupts = ; + clocks = <&sys_ctrl HI6220_UART2_PCLK>, + <&sys_ctrl HI6220_UART2_PCLK>; + clock-names = "uartclk", "apb_pclk"; + status = "disabled"; + }; + + uart3: uart@f7113000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0 0xf7113000 0x0 0x1000>; + interrupts = ; + clocks = <&sys_ctrl HI6220_UART3_PCLK>, + <&sys_ctrl HI6220_UART3_PCLK>; + clock-names = "uartclk", "apb_pclk"; + }; + + uart4: uart@f7114000 { + compatible = "arm,pl011", "arm,primecell"; + reg = <0x0 0xf7114000 0x0 0x1000>; + interrupts = ; + clocks = <&sys_ctrl HI6220_UART4_PCLK>, + <&sys_ctrl HI6220_UART4_PCLK>; + clock-names = "uartclk", "apb_pclk"; + status = "disabled"; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/hisilicon/hip05-d02.dts b/kernel/arch/arm64/boot/dts/hisilicon/hip05-d02.dts new file mode 100644 index 000000000..ae34e2504 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/hisilicon/hip05-d02.dts @@ -0,0 +1,36 @@ +/** + * dts file for Hisilicon D02 Development Board + * + * Copyright (C) 2014,2015 Hisilicon Ltd. + * + * 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 + * publishhed by the Free Software Foundation. + * + */ + +/dts-v1/; + +#include "hip05.dtsi" + +/ { + model = "Hisilicon Hip05 D02 Development Board"; + compatible = "hisilicon,hip05-d02"; + + memory@00000000 { + device_type = "memory"; + reg = <0x0 0x00000000 0x0 0x80000000>; + }; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&uart0 { + status = "ok"; +}; diff --git a/kernel/arch/arm64/boot/dts/hisilicon/hip05.dtsi b/kernel/arch/arm64/boot/dts/hisilicon/hip05.dtsi new file mode 100644 index 000000000..4ff16d016 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/hisilicon/hip05.dtsi @@ -0,0 +1,271 @@ +/** + * dts file for Hisilicon D02 Development Board + * + * Copyright (C) 2014,2015 Hisilicon Ltd. + * + * 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 + * publishhed by the Free Software Foundation. + * + */ + +#include + +/ { + compatible = "hisilicon,hip05-d02"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + core1 { + cpu = <&cpu1>; + }; + core2 { + cpu = <&cpu2>; + }; + core3 { + cpu = <&cpu3>; + }; + }; + cluster1 { + core0 { + cpu = <&cpu4>; + }; + core1 { + cpu = <&cpu5>; + }; + core2 { + cpu = <&cpu6>; + }; + core3 { + cpu = <&cpu7>; + }; + }; + cluster2 { + core0 { + cpu = <&cpu8>; + }; + core1 { + cpu = <&cpu9>; + }; + core2 { + cpu = <&cpu10>; + }; + core3 { + cpu = <&cpu11>; + }; + }; + cluster3 { + core0 { + cpu = <&cpu12>; + }; + core1 { + cpu = <&cpu13>; + }; + core2 { + cpu = <&cpu14>; + }; + core3 { + cpu = <&cpu15>; + }; + }; + }; + + cpu0: cpu@20000 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20000>; + enable-method = "psci"; + }; + + cpu1: cpu@20001 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20001>; + enable-method = "psci"; + }; + + cpu2: cpu@20002 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20002>; + enable-method = "psci"; + }; + + cpu3: cpu@20003 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20003>; + enable-method = "psci"; + }; + + cpu4: cpu@20100 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20100>; + enable-method = "psci"; + }; + + cpu5: cpu@20101 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20101>; + enable-method = "psci"; + }; + + cpu6: cpu@20102 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20102>; + enable-method = "psci"; + }; + + cpu7: cpu@20103 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20103>; + enable-method = "psci"; + }; + + cpu8: cpu@20200 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20200>; + enable-method = "psci"; + }; + + cpu9: cpu@20201 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20201>; + enable-method = "psci"; + }; + + cpu10: cpu@20202 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20202>; + enable-method = "psci"; + }; + + cpu11: cpu@20203 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20203>; + enable-method = "psci"; + }; + + cpu12: cpu@20300 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20300>; + enable-method = "psci"; + }; + + cpu13: cpu@20301 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20301>; + enable-method = "psci"; + }; + + cpu14: cpu@20302 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20302>; + enable-method = "psci"; + }; + + cpu15: cpu@20303 { + device_type = "cpu"; + compatible = "arm,cortex-a57", "arm,armv8"; + reg = <0x20303>; + enable-method = "psci"; + }; + }; + + gic: interrupt-controller@8d000000 { + compatible = "arm,gic-v3"; + #interrupt-cells = <3>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + interrupt-controller; + #redistributor-regions = <1>; + redistributor-stride = <0x0 0x30000>; + reg = <0x0 0x8d000000 0 0x10000>, /* GICD */ + <0x0 0x8d100000 0 0x300000>, /* GICR */ + <0x0 0xfe000000 0 0x10000>, /* GICC */ + <0x0 0xfe010000 0 0x10000>, /* GICH */ + <0x0 0xfe020000 0 0x10000>; /* GICV */ + interrupts = ; + + its_totems: interrupt-controller@8c000000 { + compatible = "arm,gic-v3-its"; + msi-controller; + reg = <0x0 0x8c000000 0x0 0x40000>; + }; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = ; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + refclk200mhz: refclk200mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <200000000>; + }; + + uart0: uart@80300000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x80300000 0x0 0x10000>; + interrupts = ; + clocks = <&refclk200mhz>; + clock-names = "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart1: uart@80310000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x80310000 0x0 0x10000>; + interrupts = ; + clocks = <&refclk200mhz>; + clock-names = "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/kernel/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi new file mode 100644 index 000000000..606dd5a05 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi @@ -0,0 +1,191 @@ +soc0: soc@000000000 { + #address-cells = <2>; + #size-cells = <2>; + device_type = "soc"; + compatible = "simple-bus"; + ranges = <0x0 0x0 0x0 0x0 0x1 0x0>; + chip-id = <0>; + + soc0_mdio0: mdio@803c0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "hisilicon,hns-mdio"; + reg = <0x0 0x803c0000 0x0 0x10000 + 0x0 0x80000000 0x0 0x10000>; + + soc0_phy0: ethernet-phy@0 { + reg = <0x0>; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + soc0_phy1: ethernet-phy@1 { + reg = <0x1>; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + }; + + dsa: dsa@c7000000 { + compatible = "hisilicon,hns-dsaf-v1"; + dsa_name = "dsaf0"; + mode = "6port-16rss"; + interrupt-parent = <&mbigen_dsa>; + + reg = <0x0 0xC0000000 0x0 0x420000 + 0x0 0xC2000000 0x0 0x300000 + 0x0 0xc5000000 0x0 0x890000 + 0x0 0xc7000000 0x0 0x60000 + >; + + phy-handle = <0 0 0 0 &soc0_phy0 &soc0_phy1 0 0>; + interrupts = < + /* [14] ge fifo err 8 / xge 6**/ + 149 0x4 150 0x4 151 0x4 152 0x4 + 153 0x4 154 0x4 26 0x4 27 0x4 + 155 0x4 156 0x4 157 0x4 158 0x4 159 0x4 160 0x4 + /* [12] rcb com 4*3**/ + 0x6 0x4 0x7 0x4 0x8 0x4 0x9 0x4 + 16 0x4 17 0x4 18 0x4 19 0x4 + 22 0x4 23 0x4 24 0x4 25 0x4 + /* [8] ppe tnl 0-7***/ + 0x0 0x4 0x1 0x4 0x2 0x4 0x3 0x4 + 0x4 0x4 0x5 0x4 12 0x4 13 0x4 + /* [21] dsaf event int 3+18**/ + 128 0x4 129 0x4 130 0x4 + 0x83 0x4 0x84 0x4 0x85 0x4 0x86 0x4 0x87 0x4 0x88 0x4 + 0x89 0x4 0x8a 0x4 0x8b 0x4 0x8c 0x4 0x8d 0x4 0x8e 0x4 + 0x8f 0x4 0x90 0x4 0x91 0x4 0x92 0x4 0x93 0x4 0x94 0x4 + /* [4] debug rcb 2*2*/ + 0xe 0x1 0xf 0x1 0x14 0x1 0x15 0x1 + /* [256] sevice rcb 2*128*/ + 0x180 0x1 0x181 0x1 0x182 0x1 0x183 0x1 + 0x184 0x1 0x185 0x1 0x186 0x1 0x187 0x1 + 0x188 0x1 0x189 0x1 0x18a 0x1 0x18b 0x1 + 0x18c 0x1 0x18d 0x1 0x18e 0x1 0x18f 0x1 + 0x190 0x1 0x191 0x1 0x192 0x1 0x193 0x1 + 0x194 0x1 0x195 0x1 0x196 0x1 0x197 0x1 + 0x198 0x1 0x199 0x1 0x19a 0x1 0x19b 0x1 + 0x19c 0x1 0x19d 0x1 0x19e 0x1 0x19f 0x1 + 0x1a0 0x1 0x1a1 0x1 0x1a2 0x1 0x1a3 0x1 + 0x1a4 0x1 0x1a5 0x1 0x1a6 0x1 0x1a7 0x1 + 0x1a8 0x1 0x1a9 0x1 0x1aa 0x1 0x1ab 0x1 + 0x1ac 0x1 0x1ad 0x1 0x1ae 0x1 0x1af 0x1 + 0x1b0 0x1 0x1b1 0x1 0x1b2 0x1 0x1b3 0x1 + 0x1b4 0x1 0x1b5 0x1 0x1b6 0x1 0x1b7 0x1 + 0x1b8 0x1 0x1b9 0x1 0x1ba 0x1 0x1bb 0x1 + 0x1bc 0x1 0x1bd 0x1 0x1be 0x1 0x1bf 0x1 + 0x1c0 0x1 0x1c1 0x1 0x1c2 0x1 0x1c3 0x1 + 0x1c4 0x1 0x1c5 0x1 0x1c6 0x1 0x1c7 0x1 + 0x1c8 0x1 0x1c9 0x1 0x1ca 0x1 0x1cb 0x1 + 0x1cc 0x1 0x1cd 0x1 0x1ce 0x1 0x1cf 0x1 + 0x1d0 0x1 0x1d1 0x1 0x1d2 0x1 0x1d3 0x1 + 0x1d4 0x1 0x1d5 0x1 0x1d6 0x1 0x1d7 0x1 + 0x1d8 0x1 0x1d9 0x1 0x1da 0x1 0x1db 0x1 + 0x1dc 0x1 0x1dd 0x1 0x1de 0x1 0x1df 0x1 + 0x1e0 0x1 0x1e1 0x1 0x1e2 0x1 0x1e3 0x1 + 0x1e4 0x1 0x1e5 0x1 0x1e6 0x1 0x1e7 0x1 + 0x1e8 0x1 0x1e9 0x1 0x1ea 0x1 0x1eb 0x1 + 0x1ec 0x1 0x1ed 0x1 0x1ee 0x1 0x1ef 0x1 + 0x1f0 0x1 0x1f1 0x1 0x1f2 0x1 0x1f3 0x1 + 0x1f4 0x1 0x1f5 0x1 0x1f6 0x1 0x1f7 0x1 + 0x1f8 0x1 0x1f9 0x1 0x1fa 0x1 0x1fb 0x1 + 0x1fc 0x1 0x1fd 0x1 0x1fe 0x1 0x1ff 0x1 + 0x200 0x1 0x201 0x1 0x202 0x1 0x203 0x1 + 0x204 0x1 0x205 0x1 0x206 0x1 0x207 0x1 + 0x208 0x1 0x209 0x1 0x20a 0x1 0x20b 0x1 + 0x20c 0x1 0x20d 0x1 0x20e 0x1 0x20f 0x1 + 0x210 0x1 0x211 0x1 0x212 0x1 0x213 0x1 + 0x214 0x1 0x215 0x1 0x216 0x1 0x217 0x1 + 0x218 0x1 0x219 0x1 0x21a 0x1 0x21b 0x1 + 0x21c 0x1 0x21d 0x1 0x21e 0x1 0x21f 0x1 + 0x220 0x1 0x221 0x1 0x222 0x1 0x223 0x1 + 0x224 0x1 0x225 0x1 0x226 0x1 0x227 0x1 + 0x228 0x1 0x229 0x1 0x22a 0x1 0x22b 0x1 + 0x22c 0x1 0x22d 0x1 0x22e 0x1 0x22f 0x1 + 0x230 0x1 0x231 0x1 0x232 0x1 0x233 0x1 + 0x234 0x1 0x235 0x1 0x236 0x1 0x237 0x1 + 0x238 0x1 0x239 0x1 0x23a 0x1 0x23b 0x1 + 0x23c 0x1 0x23d 0x1 0x23e 0x1 0x23f 0x1 + 0x240 0x1 0x241 0x1 0x242 0x1 0x243 0x1 + 0x244 0x1 0x245 0x1 0x246 0x1 0x247 0x1 + 0x248 0x1 0x249 0x1 0x24a 0x1 0x24b 0x1 + 0x24c 0x1 0x24d 0x1 0x24e 0x1 0x24f 0x1 + 0x250 0x1 0x251 0x1 0x252 0x1 0x253 0x1 + 0x254 0x1 0x255 0x1 0x256 0x1 0x257 0x1 + 0x258 0x1 0x259 0x1 0x25a 0x1 0x25b 0x1 + 0x25c 0x1 0x25d 0x1 0x25e 0x1 0x25f 0x1 + 0x260 0x1 0x261 0x1 0x262 0x1 0x263 0x1 + 0x264 0x1 0x265 0x1 0x266 0x1 0x267 0x1 + 0x268 0x1 0x269 0x1 0x26a 0x1 0x26b 0x1 + 0x26c 0x1 0x26d 0x1 0x26e 0x1 0x26f 0x1 + 0x270 0x1 0x271 0x1 0x272 0x1 0x273 0x1 + 0x274 0x1 0x275 0x1 0x276 0x1 0x277 0x1 + 0x278 0x1 0x279 0x1 0x27a 0x1 0x27b 0x1 + 0x27c 0x1 0x27d 0x1 0x27e 0x1 0x27f 0x1>; + buf-size = <4096>; + desc-num = <1024>; + dma-coherent; + }; + + eth0: ethernet@0{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <0>; + local-mac-address = [00 00 00 01 00 58]; + status = "disabled"; + dma-coherent; + }; + eth1: ethernet@1{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <1>; + status = "disabled"; + dma-coherent; + }; + eth2: ethernet@2{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <2>; + local-mac-address = [00 00 00 01 00 5a]; + status = "disabled"; + dma-coherent; + }; + eth3: ethernet@3{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <3>; + local-mac-address = [00 00 00 01 00 5b]; + status = "disabled"; + dma-coherent; + }; + eth4: ethernet@4{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <4>; + local-mac-address = [00 00 00 01 00 5c]; + status = "disabled"; + dma-coherent; + }; + eth5: ethernet@5{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <5>; + local-mac-address = [00 00 00 01 00 5d]; + status = "disabled"; + dma-coherent; + }; + eth6: ethernet@6{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <6>; + local-mac-address = [00 00 00 01 00 5e]; + status = "disabled"; + dma-coherent; + }; + eth7: ethernet@7{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <7>; + local-mac-address = [00 00 00 01 00 5f]; + status = "disabled"; + dma-coherent; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/marvell/Makefile b/kernel/arch/arm64/boot/dts/marvell/Makefile new file mode 100644 index 000000000..348f4db4f --- /dev/null +++ b/kernel/arch/arm64/boot/dts/marvell/Makefile @@ -0,0 +1,6 @@ +dtb-$(CONFIG_ARCH_BERLIN) += berlin4ct-dmp.dtb +dtb-$(CONFIG_ARCH_BERLIN) += berlin4ct-stb.dtb + +always := $(dtb-y) +subdir-y := $(dts-dirs) +clean-files := *.dtb diff --git a/kernel/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts b/kernel/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts new file mode 100644 index 000000000..0d70d39fa --- /dev/null +++ b/kernel/arch/arm64/boot/dts/marvell/berlin4ct-dmp.dts @@ -0,0 +1,66 @@ +/* + * Copyright (C) 2015 Marvell Technology Group Ltd. + * + * Author: Jisheng Zhang + * + * This file is dual-licensed: you can use it either under the terms + * of the GPLv2 or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +/dts-v1/; + +#include "berlin4ct.dtsi" + +/ { + model = "Marvell BG4CT DMP board"; + compatible = "marvell,berlin4ct-dmp", "marvell,berlin4ct", "marvell,berlin"; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory { + device_type = "memory"; + /* the first 16MB is for firmwares' usage */ + reg = <0 0x01000000 0 0x7f000000>; + }; +}; + +&uart0 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/marvell/berlin4ct-stb.dts b/kernel/arch/arm64/boot/dts/marvell/berlin4ct-stb.dts new file mode 100644 index 000000000..348c37ecf --- /dev/null +++ b/kernel/arch/arm64/boot/dts/marvell/berlin4ct-stb.dts @@ -0,0 +1,66 @@ +/* + * Copyright (C) 2015 Marvell Technology Group Ltd. + * + * Author: Jisheng Zhang + * + * This file is dual-licensed: you can use it either under the terms + * of the GPLv2 or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +/dts-v1/; + +#include "berlin4ct.dtsi" + +/ { + model = "Marvell BG4CT STB board"; + compatible = "marvell,berlin4ct-stb", "marvell,berlin4ct", "marvell,berlin"; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory { + device_type = "memory"; + /* the first 16MB is for firmwares' usage */ + reg = <0 0x01000000 0 0x7f000000>; + }; +}; + +&uart0 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/marvell/berlin4ct.dtsi b/kernel/arch/arm64/boot/dts/marvell/berlin4ct.dtsi new file mode 100644 index 000000000..a3b5f1d4a --- /dev/null +++ b/kernel/arch/arm64/boot/dts/marvell/berlin4ct.dtsi @@ -0,0 +1,284 @@ +/* + * Copyright (C) 2015 Marvell Technology Group Ltd. + * + * Author: Jisheng Zhang + * + * This file is dual-licensed: you can use it either under the terms + * of the GPLv2 or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +#include + +/ { + compatible = "marvell,berlin4ct", "marvell,berlin"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + aliases { + serial0 = &uart0; + }; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x0>; + enable-method = "psci"; + }; + + cpu1: cpu@1 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x1>; + enable-method = "psci"; + }; + + cpu2: cpu@2 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x2>; + enable-method = "psci"; + }; + + cpu3: cpu@3 { + compatible = "arm,cortex-a53", "arm,armv8"; + device_type = "cpu"; + reg = <0x3>; + enable-method = "psci"; + }; + }; + + osc: osc { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <25000000>; + }; + + pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = , + , + , + ; + interrupt-affinity = <&cpu0>, + <&cpu1>, + <&cpu2>, + <&cpu3>; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0 0xf7000000 0x1000000>; + + gic: interrupt-controller@901000 { + compatible = "arm,gic-400"; + #interrupt-cells = <3>; + interrupt-controller; + reg = <0x901000 0x1000>, + <0x902000 0x2000>, + <0x904000 0x2000>, + <0x906000 0x2000>; + interrupts = ; + }; + + apb@e80000 { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + + ranges = <0 0xe80000 0x10000>; + interrupt-parent = <&aic>; + + gpio0: gpio@0400 { + compatible = "snps,dw-apb-gpio"; + reg = <0x0400 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + porta: gpio-port@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <0>; + }; + }; + + gpio1: gpio@0800 { + compatible = "snps,dw-apb-gpio"; + reg = <0x0800 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + portb: gpio-port@1 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <1>; + }; + }; + + gpio2: gpio@0c00 { + compatible = "snps,dw-apb-gpio"; + reg = <0x0c00 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + portc: gpio-port@2 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <2>; + }; + }; + + gpio3: gpio@1000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x1000 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + portd: gpio-port@3 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <3>; + }; + }; + + aic: interrupt-controller@3800 { + compatible = "snps,dw-apb-ictl"; + reg = <0x3800 0x30>; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&gic>; + interrupts = ; + }; + }; + + apb@fc0000 { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0 0xfc0000 0x10000>; + interrupt-parent = <&sic>; + + sic: interrupt-controller@1000 { + compatible = "snps,dw-apb-ictl"; + reg = <0x1000 0x30>; + interrupt-controller; + #interrupt-cells = <1>; + interrupt-parent = <&gic>; + interrupts = ; + }; + + sm_gpio0: gpio@8000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x8000 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + porte: gpio-port@4 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + }; + }; + + sm_gpio1: gpio@9000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x9000 0x400>; + #address-cells = <1>; + #size-cells = <0>; + + portf: gpio-port@5 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + snps,nr-gpios = <32>; + reg = <0>; + }; + }; + + uart0: uart@d000 { + compatible = "snps,dw-apb-uart"; + reg = <0xd000 0x100>; + interrupts = <8>; + clocks = <&osc>; + reg-shift = <2>; + status = "disabled"; + }; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/mediatek/Makefile b/kernel/arch/arm64/boot/dts/mediatek/Makefile index 3ce24622b..e0a4bff2f 100644 --- a/kernel/arch/arm64/boot/dts/mediatek/Makefile +++ b/kernel/arch/arm64/boot/dts/mediatek/Makefile @@ -1,3 +1,4 @@ +dtb-$(CONFIG_ARCH_MEDIATEK) += mt6795-evb.dtb dtb-$(CONFIG_ARCH_MEDIATEK) += mt8173-evb.dtb always := $(dtb-y) diff --git a/kernel/arch/arm64/boot/dts/mediatek/mt6795-evb.dts b/kernel/arch/arm64/boot/dts/mediatek/mt6795-evb.dts new file mode 100644 index 000000000..ad665f583 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/mediatek/mt6795-evb.dts @@ -0,0 +1,41 @@ +/* + * Copyright (c) 2015 MediaTek Inc. + * Author: Mars.C + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +/dts-v1/; +#include "mt6795.dtsi" + +/ { + model = "MediaTek MT6795 Evaluation Board"; + compatible = "mediatek,mt6795-evb", "mediatek,mt6795"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + }; + + memory@40000000 { + device_type = "memory"; + reg = <0 0x40000000 0 0x1e800000>; + }; + + chosen { + stdout-path = "serial0:921600n8"; + }; +}; + +&uart0 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/mediatek/mt6795.dtsi b/kernel/arch/arm64/boot/dts/mediatek/mt6795.dtsi new file mode 100644 index 000000000..c85659d0f --- /dev/null +++ b/kernel/arch/arm64/boot/dts/mediatek/mt6795.dtsi @@ -0,0 +1,175 @@ +/* + * Copyright (c) 2015 MediaTek Inc. + * Author: Mars.C + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include +#include + +/ { + compatible = "mediatek,mt6795"; + interrupt-parent = <&sysirq>; + #address-cells = <2>; + #size-cells = <2>; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x000>; + }; + + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x001>; + }; + + cpu2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x002>; + }; + + cpu3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x003>; + }; + + cpu4: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x100>; + }; + + cpu5: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x101>; + }; + + cpu6: cpu@102 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x102>; + }; + + cpu7: cpu@103 { + device_type = "cpu"; + compatible = "arm,cortex-a53"; + enable-method = "psci"; + reg = <0x103>; + }; + }; + + system_clk: dummy13m { + compatible = "fixed-clock"; + clock-frequency = <13000000>; + #clock-cells = <0>; + }; + + rtc_clk: dummy32k { + compatible = "fixed-clock"; + clock-frequency = <32000>; + #clock-cells = <0>; + }; + + uart_clk: dummy26m { + compatible = "fixed-clock"; + clock-frequency = <26000000>; + #clock-cells = <0>; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupt-parent = <&gic>; + interrupts = , + , + , + ; + }; + + sysirq: intpol-controller@10200620 { + compatible = "mediatek,mt6795-sysirq", + "mediatek,mt6577-sysirq"; + interrupt-controller; + #interrupt-cells = <3>; + interrupt-parent = <&gic>; + reg = <0 0x10200620 0 0x20>; + }; + + gic: interrupt-controller@10221000 { + compatible = "arm,gic-400"; + #interrupt-cells = <3>; + interrupt-parent = <&gic>; + interrupt-controller; + reg = <0 0x10221000 0 0x1000>, + <0 0x10222000 0 0x2000>, + <0 0x10224000 0 0x2000>, + <0 0x10226000 0 0x2000>; + }; + + uart0: serial@11002000 { + compatible = "mediatek,mt6795-uart", + "mediatek,mt6577-uart"; + reg = <0 0x11002000 0 0x400>; + interrupts = ; + clocks = <&uart_clk>; + status = "disabled"; + }; + + uart1: serial@11003000 { + compatible = "mediatek,mt6795-uart", + "mediatek,mt6577-uart"; + reg = <0 0x11003000 0 0x400>; + interrupts = ; + clocks = <&uart_clk>; + status = "disabled"; + }; + + uart2: serial@11004000 { + compatible = "mediatek,mt6795-uart", + "mediatek,mt6577-uart"; + reg = <0 0x11004000 0 0x400>; + interrupts = ; + clocks = <&uart_clk>; + status = "disabled"; + }; + + uart3: serial@11005000 { + compatible = "mediatek,mt6795-uart", + "mediatek,mt6577-uart"; + reg = <0 0x11005000 0 0x400>; + interrupts = ; + clocks = <&uart_clk>; + status = "disabled"; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/mediatek/mt8173-evb.dts b/kernel/arch/arm64/boot/dts/mediatek/mt8173-evb.dts index d0ab012fa..811cb760b 100644 --- a/kernel/arch/arm64/boot/dts/mediatek/mt8173-evb.dts +++ b/kernel/arch/arm64/boot/dts/mediatek/mt8173-evb.dts @@ -34,6 +34,377 @@ chosen { }; }; +&i2c1 { + status = "okay"; + + buck: da9211@68 { + compatible = "dlg,da9211"; + reg = <0x68>; + + regulators { + da9211_vcpu_reg: BUCKA { + regulator-name = "VBUCKA"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1310000>; + regulator-min-microamp = <2000000>; + regulator-max-microamp = <4400000>; + regulator-ramp-delay = <10000>; + regulator-always-on; + }; + + da9211_vgpu_reg: BUCKB { + regulator-name = "VBUCKB"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1310000>; + regulator-min-microamp = <2000000>; + regulator-max-microamp = <3000000>; + regulator-ramp-delay = <10000>; + }; + }; + }; +}; + +&mmc0 { + status = "okay"; + pinctrl-names = "default", "state_uhs"; + pinctrl-0 = <&mmc0_pins_default>; + pinctrl-1 = <&mmc0_pins_uhs>; + bus-width = <8>; + max-frequency = <50000000>; + cap-mmc-highspeed; + vmmc-supply = <&mt6397_vemc_3v3_reg>; + vqmmc-supply = <&mt6397_vio18_reg>; + non-removable; +}; + +&mmc1 { + status = "okay"; + pinctrl-names = "default", "state_uhs"; + pinctrl-0 = <&mmc1_pins_default>; + pinctrl-1 = <&mmc1_pins_uhs>; + bus-width = <4>; + max-frequency = <50000000>; + cap-sd-highspeed; + sd-uhs-sdr25; + cd-gpios = <&pio 132 0>; + vmmc-supply = <&mt6397_vmch_reg>; + vqmmc-supply = <&mt6397_vmc_reg>; +}; + +&pio { + mmc0_pins_default: mmc0default { + pins_cmd_dat { + pinmux = , + , + , + , + , + , + , + , + ; + input-enable; + bias-pull-up; + }; + + pins_clk { + pinmux = ; + bias-pull-down; + }; + + pins_rst { + pinmux = ; + bias-pull-up; + }; + }; + + mmc1_pins_default: mmc1default { + pins_cmd_dat { + pinmux = , + , + , + , + ; + input-enable; + drive-strength = ; + bias-pull-up = ; + }; + + pins_clk { + pinmux = ; + bias-pull-down; + drive-strength = ; + }; + + pins_insert { + pinmux = ; + bias-pull-up; + }; + }; + + mmc0_pins_uhs: mmc0 { + pins_cmd_dat { + pinmux = , + , + , + , + , + , + , + , + ; + input-enable; + drive-strength = ; + bias-pull-up = ; + }; + + pins_clk { + pinmux = ; + drive-strength = ; + bias-pull-down = ; + }; + + pins_rst { + pinmux = ; + bias-pull-up; + }; + }; + + mmc1_pins_uhs: mmc1 { + pins_cmd_dat { + pinmux = , + , + , + , + ; + input-enable; + drive-strength = ; + bias-pull-up = ; + }; + + pins_clk { + pinmux = ; + drive-strength = ; + bias-pull-down = ; + }; + }; +}; + +&pwrap { + pmic: mt6397 { + compatible = "mediatek,mt6397"; + interrupt-parent = <&pio>; + interrupts = <11 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + #interrupt-cells = <2>; + + mt6397regulator: mt6397regulator { + compatible = "mediatek,mt6397-regulator"; + + mt6397_vpca15_reg: buck_vpca15 { + regulator-compatible = "buck_vpca15"; + regulator-name = "vpca15"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-always-on; + }; + + mt6397_vpca7_reg: buck_vpca7 { + regulator-compatible = "buck_vpca7"; + regulator-name = "vpca7"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + }; + + mt6397_vsramca15_reg: buck_vsramca15 { + regulator-compatible = "buck_vsramca15"; + regulator-name = "vsramca15"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-always-on; + }; + + mt6397_vsramca7_reg: buck_vsramca7 { + regulator-compatible = "buck_vsramca7"; + regulator-name = "vsramca7"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-always-on; + }; + + mt6397_vcore_reg: buck_vcore { + regulator-compatible = "buck_vcore"; + regulator-name = "vcore"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-always-on; + }; + + mt6397_vgpu_reg: buck_vgpu { + regulator-compatible = "buck_vgpu"; + regulator-name = "vgpu"; + regulator-min-microvolt = < 700000>; + regulator-max-microvolt = <1350000>; + regulator-ramp-delay = <12500>; + regulator-enable-ramp-delay = <115>; + }; + + mt6397_vdrm_reg: buck_vdrm { + regulator-compatible = "buck_vdrm"; + regulator-name = "vdrm"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1400000>; + regulator-ramp-delay = <12500>; + regulator-always-on; + }; + + mt6397_vio18_reg: buck_vio18 { + regulator-compatible = "buck_vio18"; + regulator-name = "vio18"; + regulator-min-microvolt = <1620000>; + regulator-max-microvolt = <1980000>; + regulator-ramp-delay = <12500>; + regulator-always-on; + }; + + mt6397_vtcxo_reg: ldo_vtcxo { + regulator-compatible = "ldo_vtcxo"; + regulator-name = "vtcxo"; + regulator-always-on; + }; + + mt6397_va28_reg: ldo_va28 { + regulator-compatible = "ldo_va28"; + regulator-name = "va28"; + regulator-always-on; + }; + + mt6397_vcama_reg: ldo_vcama { + regulator-compatible = "ldo_vcama"; + regulator-name = "vcama"; + regulator-min-microvolt = <1500000>; + regulator-max-microvolt = <2800000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vio28_reg: ldo_vio28 { + regulator-compatible = "ldo_vio28"; + regulator-name = "vio28"; + regulator-always-on; + }; + + mt6397_vusb_reg: ldo_vusb { + regulator-compatible = "ldo_vusb"; + regulator-name = "vusb"; + }; + + mt6397_vmc_reg: ldo_vmc { + regulator-compatible = "ldo_vmc"; + regulator-name = "vmc"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vmch_reg: ldo_vmch { + regulator-compatible = "ldo_vmch"; + regulator-name = "vmch"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vemc_3v3_reg: ldo_vemc3v3 { + regulator-compatible = "ldo_vemc3v3"; + regulator-name = "vemc_3v3"; + regulator-min-microvolt = <3000000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp1_reg: ldo_vgp1 { + regulator-compatible = "ldo_vgp1"; + regulator-name = "vcamd"; + regulator-min-microvolt = <1220000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <240>; + }; + + mt6397_vgp2_reg: ldo_vgp2 { + regulator-compatible = "ldo_vgp2"; + regulator-name = "vcamio"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp3_reg: ldo_vgp3 { + regulator-compatible = "ldo_vgp3"; + regulator-name = "vcamaf"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp4_reg: ldo_vgp4 { + regulator-compatible = "ldo_vgp4"; + regulator-name = "vgp4"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp5_reg: ldo_vgp5 { + regulator-compatible = "ldo_vgp5"; + regulator-name = "vgp5"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3000000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vgp6_reg: ldo_vgp6 { + regulator-compatible = "ldo_vgp6"; + regulator-name = "vgp6"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + + mt6397_vibr_reg: ldo_vibr { + regulator-compatible = "ldo_vibr"; + regulator-name = "vibr"; + regulator-min-microvolt = <1300000>; + regulator-max-microvolt = <3300000>; + regulator-enable-ramp-delay = <218>; + }; + }; + }; +}; + +&pio { + spi_pins_a: spi0 { + pins_spi { + pinmux = , + , + , + ; + }; + }; +}; + +&spi { + pinctrl-names = "default"; + pinctrl-0 = <&spi_pins_a>; + mediatek,pad-select = <0>; + status = "okay"; +}; + &uart0 { status = "okay"; }; diff --git a/kernel/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/kernel/arch/arm64/boot/dts/mediatek/mt8173.dtsi index 924fdb667..4dd5f93d0 100644 --- a/kernel/arch/arm64/boot/dts/mediatek/mt8173.dtsi +++ b/kernel/arch/arm64/boot/dts/mediatek/mt8173.dtsi @@ -11,8 +11,11 @@ * GNU General Public License for more details. */ +#include #include #include +#include +#include #include "mt8173-pinfunc.h" / { @@ -49,6 +52,8 @@ device_type = "cpu"; compatible = "arm,cortex-a53"; reg = <0x000>; + enable-method = "psci"; + cpu-idle-states = <&CPU_SLEEP_0>; }; cpu1: cpu@1 { @@ -56,6 +61,7 @@ compatible = "arm,cortex-a53"; reg = <0x001>; enable-method = "psci"; + cpu-idle-states = <&CPU_SLEEP_0>; }; cpu2: cpu@100 { @@ -63,6 +69,7 @@ compatible = "arm,cortex-a57"; reg = <0x100>; enable-method = "psci"; + cpu-idle-states = <&CPU_SLEEP_0>; }; cpu3: cpu@101 { @@ -70,6 +77,20 @@ compatible = "arm,cortex-a57"; reg = <0x101>; enable-method = "psci"; + cpu-idle-states = <&CPU_SLEEP_0>; + }; + + idle-states { + entry-method = "psci"; + + CPU_SLEEP_0: cpu-sleep-0 { + compatible = "arm,idle-state"; + local-timer-stop; + entry-latency-us = <639>; + exit-latency-us = <680>; + min-residency-us = <1088>; + arm,psci-suspend-param = <0x0010000>; + }; }; }; @@ -81,23 +102,38 @@ cpu_on = <0x84000003>; }; - uart_clk: dummy26m { + clk26m: oscillator@0 { compatible = "fixed-clock"; + #clock-cells = <0>; clock-frequency = <26000000>; + clock-output-names = "clk26m"; + }; + + clk32k: oscillator@1 { + compatible = "fixed-clock"; #clock-cells = <0>; + clock-frequency = <32000>; + clock-output-names = "clk32k"; + }; + + cpum_ck: oscillator@2 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + clock-output-names = "cpum_ck"; }; timer { compatible = "arm,armv8-timer"; interrupt-parent = <&gic>; interrupts = , + (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, , + (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, , + (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, ; + (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>; }; soc { @@ -106,6 +142,26 @@ compatible = "simple-bus"; ranges; + topckgen: clock-controller@10000000 { + compatible = "mediatek,mt8173-topckgen"; + reg = <0 0x10000000 0 0x1000>; + #clock-cells = <1>; + }; + + infracfg: power-controller@10001000 { + compatible = "mediatek,mt8173-infracfg", "syscon"; + reg = <0 0x10001000 0 0x1000>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + pericfg: power-controller@10003000 { + compatible = "mediatek,mt8173-pericfg", "syscon"; + reg = <0 0x10003000 0 0x1000>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + syscfg_pctl_a: syscfg_pctl_a@10005000 { compatible = "mediatek,mt8173-pctl-a-syscfg", "syscon"; reg = <0 0x10005000 0 0x1000>; @@ -113,7 +169,7 @@ pio: pinctrl@0x10005000 { compatible = "mediatek,mt8173-pinctrl"; - reg = <0 0x1000B000 0 0x1000>; + reg = <0 0x1000b000 0 0x1000>; mediatek,pctl-regmap = <&syscfg_pctl_a>; pins-are-numbered; gpio-controller; @@ -121,19 +177,102 @@ interrupt-controller; #interrupt-cells = <2>; interrupts = , - , - ; + , + ; + + i2c0_pins_a: i2c0 { + pins1 { + pinmux = , + ; + bias-disable; + }; + }; + + i2c1_pins_a: i2c1 { + pins1 { + pinmux = , + ; + bias-disable; + }; + }; + + i2c2_pins_a: i2c2 { + pins1 { + pinmux = , + ; + bias-disable; + }; + }; + + i2c3_pins_a: i2c3 { + pins1 { + pinmux = , + ; + bias-disable; + }; + }; + + i2c4_pins_a: i2c4 { + pins1 { + pinmux = , + ; + bias-disable; + }; + }; + + i2c6_pins_a: i2c6 { + pins1 { + pinmux = , + ; + bias-disable; + }; + }; + }; + + scpsys: scpsys@10006000 { + compatible = "mediatek,mt8173-scpsys"; + #power-domain-cells = <1>; + reg = <0 0x10006000 0 0x1000>; + clocks = <&clk26m>, + <&topckgen CLK_TOP_MM_SEL>, + <&topckgen CLK_TOP_VENC_SEL>, + <&topckgen CLK_TOP_VENC_LT_SEL>; + clock-names = "mfg", "mm", "venc", "venc_lt"; + infracfg = <&infracfg>; + }; + + watchdog: watchdog@10007000 { + compatible = "mediatek,mt8173-wdt", + "mediatek,mt6589-wdt"; + reg = <0 0x10007000 0 0x100>; + }; + + pwrap: pwrap@1000d000 { + compatible = "mediatek,mt8173-pwrap"; + reg = <0 0x1000d000 0 0x1000>; + reg-names = "pwrap"; + interrupts = ; + resets = <&infracfg MT8173_INFRA_PMIC_WRAP_RST>; + reset-names = "pwrap"; + clocks = <&infracfg CLK_INFRA_PMICSPI>, <&infracfg CLK_INFRA_PMICWRAP>; + clock-names = "spi", "wrap"; }; sysirq: intpol-controller@10200620 { compatible = "mediatek,mt8173-sysirq", - "mediatek,mt6577-sysirq"; + "mediatek,mt6577-sysirq"; interrupt-controller; #interrupt-cells = <3>; interrupt-parent = <&gic>; reg = <0 0x10200620 0 0x20>; }; + apmixedsys: clock-controller@10209000 { + compatible = "mediatek,mt8173-apmixedsys"; + reg = <0 0x10209000 0 0x1000>; + #clock-cells = <1>; + }; + gic: interrupt-controller@10220000 { compatible = "arm,gic-400"; #interrupt-cells = <3>; @@ -149,40 +288,257 @@ uart0: serial@11002000 { compatible = "mediatek,mt8173-uart", - "mediatek,mt6577-uart"; + "mediatek,mt6577-uart"; reg = <0 0x11002000 0 0x400>; interrupts = ; - clocks = <&uart_clk>; + clocks = <&pericfg CLK_PERI_UART0_SEL>, <&pericfg CLK_PERI_UART0>; + clock-names = "baud", "bus"; status = "disabled"; }; uart1: serial@11003000 { compatible = "mediatek,mt8173-uart", - "mediatek,mt6577-uart"; + "mediatek,mt6577-uart"; reg = <0 0x11003000 0 0x400>; interrupts = ; - clocks = <&uart_clk>; + clocks = <&pericfg CLK_PERI_UART1_SEL>, <&pericfg CLK_PERI_UART1>; + clock-names = "baud", "bus"; status = "disabled"; }; uart2: serial@11004000 { compatible = "mediatek,mt8173-uart", - "mediatek,mt6577-uart"; + "mediatek,mt6577-uart"; reg = <0 0x11004000 0 0x400>; interrupts = ; - clocks = <&uart_clk>; + clocks = <&pericfg CLK_PERI_UART2_SEL>, <&pericfg CLK_PERI_UART2>; + clock-names = "baud", "bus"; status = "disabled"; }; uart3: serial@11005000 { compatible = "mediatek,mt8173-uart", - "mediatek,mt6577-uart"; + "mediatek,mt6577-uart"; reg = <0 0x11005000 0 0x400>; interrupts = ; - clocks = <&uart_clk>; + clocks = <&pericfg CLK_PERI_UART3_SEL>, <&pericfg CLK_PERI_UART3>; + clock-names = "baud", "bus"; status = "disabled"; }; - }; + i2c0: i2c@11007000 { + compatible = "mediatek,mt8173-i2c"; + reg = <0 0x11007000 0 0x70>, + <0 0x11000100 0 0x80>; + interrupts = ; + clock-div = <16>; + clocks = <&pericfg CLK_PERI_I2C0>, + <&pericfg CLK_PERI_AP_DMA>; + clock-names = "main", "dma"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins_a>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@11008000 { + compatible = "mediatek,mt8173-i2c"; + reg = <0 0x11008000 0 0x70>, + <0 0x11000180 0 0x80>; + interrupts = ; + clock-div = <16>; + clocks = <&pericfg CLK_PERI_I2C1>, + <&pericfg CLK_PERI_AP_DMA>; + clock-names = "main", "dma"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins_a>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c2: i2c@11009000 { + compatible = "mediatek,mt8173-i2c"; + reg = <0 0x11009000 0 0x70>, + <0 0x11000200 0 0x80>; + interrupts = ; + clock-div = <16>; + clocks = <&pericfg CLK_PERI_I2C2>, + <&pericfg CLK_PERI_AP_DMA>; + clock-names = "main", "dma"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins_a>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi: spi@1100a000 { + compatible = "mediatek,mt8173-spi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0 0x1100a000 0 0x1000>; + interrupts = ; + clocks = <&topckgen CLK_TOP_SYSPLL3_D2>, + <&topckgen CLK_TOP_SPI_SEL>, + <&pericfg CLK_PERI_SPI0>; + clock-names = "parent-clk", "sel-clk", "spi-clk"; + status = "disabled"; + }; + + i2c3: i2c@11010000 { + compatible = "mediatek,mt8173-i2c"; + reg = <0 0x11010000 0 0x70>, + <0 0x11000280 0 0x80>; + interrupts = ; + clock-div = <16>; + clocks = <&pericfg CLK_PERI_I2C3>, + <&pericfg CLK_PERI_AP_DMA>; + clock-names = "main", "dma"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins_a>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c4: i2c@11011000 { + compatible = "mediatek,mt8173-i2c"; + reg = <0 0x11011000 0 0x70>, + <0 0x11000300 0 0x80>; + interrupts = ; + clock-div = <16>; + clocks = <&pericfg CLK_PERI_I2C4>, + <&pericfg CLK_PERI_AP_DMA>; + clock-names = "main", "dma"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c4_pins_a>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c6: i2c@11013000 { + compatible = "mediatek,mt8173-i2c"; + reg = <0 0x11013000 0 0x70>, + <0 0x11000080 0 0x80>; + interrupts = ; + clock-div = <16>; + clocks = <&pericfg CLK_PERI_I2C6>, + <&pericfg CLK_PERI_AP_DMA>; + clock-names = "main", "dma"; + pinctrl-names = "default"; + pinctrl-0 = <&i2c6_pins_a>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + afe: audio-controller@11220000 { + compatible = "mediatek,mt8173-afe-pcm"; + reg = <0 0x11220000 0 0x1000>; + interrupts = ; + power-domains = <&scpsys MT8173_POWER_DOMAIN_AUDIO>; + clocks = <&infracfg CLK_INFRA_AUDIO>, + <&topckgen CLK_TOP_AUDIO_SEL>, + <&topckgen CLK_TOP_AUD_INTBUS_SEL>, + <&topckgen CLK_TOP_APLL1_DIV0>, + <&topckgen CLK_TOP_APLL2_DIV0>, + <&topckgen CLK_TOP_I2S0_M_SEL>, + <&topckgen CLK_TOP_I2S1_M_SEL>, + <&topckgen CLK_TOP_I2S2_M_SEL>, + <&topckgen CLK_TOP_I2S3_M_SEL>, + <&topckgen CLK_TOP_I2S3_B_SEL>; + clock-names = "infra_sys_audio_clk", + "top_pdn_audio", + "top_pdn_aud_intbus", + "bck0", + "bck1", + "i2s0_m", + "i2s1_m", + "i2s2_m", + "i2s3_m", + "i2s3_b"; + assigned-clocks = <&topckgen CLK_TOP_AUD_1_SEL>, + <&topckgen CLK_TOP_AUD_2_SEL>; + assigned-clock-parents = <&topckgen CLK_TOP_APLL1>, + <&topckgen CLK_TOP_APLL2>; + }; + + mmc0: mmc@11230000 { + compatible = "mediatek,mt8173-mmc", + "mediatek,mt8135-mmc"; + reg = <0 0x11230000 0 0x1000>; + interrupts = ; + clocks = <&pericfg CLK_PERI_MSDC30_0>, + <&topckgen CLK_TOP_MSDC50_0_H_SEL>; + clock-names = "source", "hclk"; + status = "disabled"; + }; + + mmc1: mmc@11240000 { + compatible = "mediatek,mt8173-mmc", + "mediatek,mt8135-mmc"; + reg = <0 0x11240000 0 0x1000>; + interrupts = ; + clocks = <&pericfg CLK_PERI_MSDC30_1>, + <&topckgen CLK_TOP_AXI_SEL>; + clock-names = "source", "hclk"; + status = "disabled"; + }; + + mmc2: mmc@11250000 { + compatible = "mediatek,mt8173-mmc", + "mediatek,mt8135-mmc"; + reg = <0 0x11250000 0 0x1000>; + interrupts = ; + clocks = <&pericfg CLK_PERI_MSDC30_2>, + <&topckgen CLK_TOP_AXI_SEL>; + clock-names = "source", "hclk"; + status = "disabled"; + }; + + mmc3: mmc@11260000 { + compatible = "mediatek,mt8173-mmc", + "mediatek,mt8135-mmc"; + reg = <0 0x11260000 0 0x1000>; + interrupts = ; + clocks = <&pericfg CLK_PERI_MSDC30_3>, + <&topckgen CLK_TOP_MSDC50_2_H_SEL>; + clock-names = "source", "hclk"; + status = "disabled"; + }; + + mmsys: clock-controller@14000000 { + compatible = "mediatek,mt8173-mmsys", "syscon"; + reg = <0 0x14000000 0 0x1000>; + #clock-cells = <1>; + }; + + imgsys: clock-controller@15000000 { + compatible = "mediatek,mt8173-imgsys", "syscon"; + reg = <0 0x15000000 0 0x1000>; + #clock-cells = <1>; + }; + + vdecsys: clock-controller@16000000 { + compatible = "mediatek,mt8173-vdecsys", "syscon"; + reg = <0 0x16000000 0 0x1000>; + #clock-cells = <1>; + }; + + vencsys: clock-controller@18000000 { + compatible = "mediatek,mt8173-vencsys", "syscon"; + reg = <0 0x18000000 0 0x1000>; + #clock-cells = <1>; + }; + + vencltsys: clock-controller@19000000 { + compatible = "mediatek,mt8173-vencltsys", "syscon"; + reg = <0 0x19000000 0 0x1000>; + #clock-cells = <1>; + }; + }; }; diff --git a/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi b/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi new file mode 100644 index 000000000..e03c11d9d --- /dev/null +++ b/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-pmic-pins.dtsi @@ -0,0 +1,40 @@ +#include + +&pm8916_gpios { + + usb_hub_reset_pm: usb_hub_reset_pm { + pinconf { + pins = "gpio3"; + function = PMIC_GPIO_FUNC_NORMAL; + output-low; + }; + }; + + usb_sw_sel_pm: usb_sw_sel_pm { + pinconf { + pins = "gpio4"; + function = PMIC_GPIO_FUNC_NORMAL; + power-source = ; + input-disable; + }; + }; + + pm8916_gpios_leds: pm8916_gpios_leds { + pinconf { + pins = "gpio1", "gpio2"; + function = PMIC_GPIO_FUNC_NORMAL; + output-low; + }; + }; +}; + +&pm8916_mpps { + + pm8916_mpps_leds: pm8916_mpps_leds { + pinconf { + pins = "mpp2", "mpp3"; + function = PMIC_GPIO_FUNC_NORMAL; + output-low; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi b/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi new file mode 100644 index 000000000..cbeee0bcd --- /dev/null +++ b/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc-soc-pins.dtsi @@ -0,0 +1,13 @@ + +#include + +&msmgpio { + + msmgpio_leds: msmgpio_leds { + pinconf { + pins = "gpio21", "gpio120"; + function = "gpio"; + output-low; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi b/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi index 703a4f16e..6b8abbe68 100644 --- a/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi +++ b/kernel/arch/arm64/boot/dts/qcom/apq8016-sbc.dtsi @@ -12,10 +12,14 @@ */ #include "msm8916.dtsi" +#include "pm8916.dtsi" +#include "apq8016-sbc-soc-pins.dtsi" +#include "apq8016-sbc-pmic-pins.dtsi" / { aliases { serial0 = &blsp1_uart2; + serial1 = &blsp1_uart1; }; chosen { @@ -29,5 +33,85 @@ pinctrl-0 = <&blsp1_uart2_default>; pinctrl-1 = <&blsp1_uart2_sleep>; }; + + i2c@78b6000 { + /* On Low speed expansion */ + status = "okay"; + }; + + i2c@78b8000 { + /* On High speed expansion */ + status = "okay"; + }; + + i2c@78ba000 { + /* On Low speed expansion */ + status = "okay"; + }; + + spi@78b7000 { + /* On High speed expansion */ + status = "okay"; + }; + + spi@78b9000 { + /* On Low speed expansion */ + status = "okay"; + }; + + leds { + pinctrl-names = "default"; + pinctrl-0 = <&msmgpio_leds>, + <&pm8916_gpios_leds>, + <&pm8916_mpps_leds>; + + compatible = "gpio-leds"; + + led@1 { + label = "apq8016-sbc:green:user1"; + gpios = <&msmgpio 21 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + default-state = "off"; + }; + + led@2 { + label = "apq8016-sbc:green:user2"; + gpios = <&msmgpio 120 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "mmc0"; + default-state = "off"; + }; + + led@3 { + label = "apq8016-sbc:green:user3"; + gpios = <&pm8916_gpios 1 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "mmc1"; + default-state = "off"; + }; + + led@4 { + label = "apq8016-sbc:green:user4"; + gpios = <&pm8916_gpios 2 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "none"; + default-state = "off"; + }; + + led@5 { + label = "apq8016-sbc:yellow:wlan"; + gpios = <&pm8916_mpps 2 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "wlan"; + default-state = "off"; + }; + + led@6 { + label = "apq8016-sbc:blue:bt"; + gpios = <&pm8916_mpps 3 GPIO_ACTIVE_HIGH>; + linux,default-trigger = "bt"; + default-state = "off"; + }; + }; }; }; + +&sdhc_1 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/qcom/msm8916-mtp.dtsi b/kernel/arch/arm64/boot/dts/qcom/msm8916-mtp.dtsi index bea871b0d..a1aa0b201 100644 --- a/kernel/arch/arm64/boot/dts/qcom/msm8916-mtp.dtsi +++ b/kernel/arch/arm64/boot/dts/qcom/msm8916-mtp.dtsi @@ -12,6 +12,7 @@ */ #include "msm8916.dtsi" +#include "pm8916.dtsi" / { aliases { diff --git a/kernel/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi b/kernel/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi new file mode 100644 index 000000000..49ec55a37 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/qcom/msm8916-pins.dtsi @@ -0,0 +1,502 @@ +/* + * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +&msmgpio { + + blsp1_uart1_default: blsp1_uart1_default { + pinmux { + function = "blsp_uart1"; + pins = "gpio0", "gpio1"; + }; + pinconf { + pins = "gpio0", "gpio1"; + drive-strength = <16>; + bias-disable; + }; + }; + + blsp1_uart1_sleep: blsp1_uart1_sleep { + pinmux { + function = "gpio"; + pins = "gpio0", "gpio1"; + }; + pinconf { + pins = "gpio0", "gpio1"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + blsp1_uart2_default: blsp1_uart2_default { + pinmux { + function = "blsp_uart2"; + pins = "gpio4", "gpio5"; + }; + pinconf { + pins = "gpio4", "gpio5"; + drive-strength = <16>; + bias-disable; + }; + }; + + blsp1_uart2_sleep: blsp1_uart2_sleep { + pinmux { + function = "gpio"; + pins = "gpio4", "gpio5"; + }; + pinconf { + pins = "gpio4", "gpio5"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + spi1_default: spi1_default { + pinmux { + function = "blsp_spi1"; + pins = "gpio0", "gpio1", "gpio3"; + }; + pinmux_cs { + function = "gpio"; + pins = "gpio2"; + }; + pinconf { + pins = "gpio0", "gpio1", "gpio3"; + drive-strength = <12>; + bias-disable; + }; + pinconf_cs { + pins = "gpio2"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + spi1_sleep: spi1_sleep { + pinmux { + function = "gpio"; + pins = "gpio0", "gpio1", "gpio2", "gpio3"; + }; + pinconf { + pins = "gpio0", "gpio1", "gpio2", "gpio3"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + spi2_default: spi2_default { + pinmux { + function = "blsp_spi2"; + pins = "gpio4", "gpio5", "gpio7"; + }; + pinmux_cs { + function = "gpio"; + pins = "gpio6"; + }; + pinconf { + pins = "gpio4", "gpio5", "gpio6", "gpio7"; + drive-strength = <12>; + bias-disable; + }; + pinconf_cs { + pins = "gpio6"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + spi2_sleep: spi2_sleep { + pinmux { + function = "gpio"; + pins = "gpio4", "gpio5", "gpio6", "gpio7"; + }; + pinconf { + pins = "gpio4", "gpio5", "gpio6", "gpio7"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + spi3_default: spi3_default { + pinmux { + function = "blsp_spi3"; + pins = "gpio8", "gpio9", "gpio11"; + }; + pinmux_cs { + function = "gpio"; + pins = "gpio10"; + }; + pinconf { + pins = "gpio8", "gpio9", "gpio10", "gpio11"; + drive-strength = <12>; + bias-disable; + }; + pinconf_cs { + pins = "gpio10"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + spi3_sleep: spi3_sleep { + pinmux { + function = "gpio"; + pins = "gpio8", "gpio9", "gpio10", "gpio11"; + }; + pinconf { + pins = "gpio8", "gpio9", "gpio10", "gpio11"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + spi4_default: spi4_default { + pinmux { + function = "blsp_spi4"; + pins = "gpio12", "gpio13", "gpio15"; + }; + pinmux_cs { + function = "gpio"; + pins = "gpio14"; + }; + pinconf { + pins = "gpio12", "gpio13", "gpio14", "gpio15"; + drive-strength = <12>; + bias-disable; + }; + pinconf_cs { + pins = "gpio14"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + spi4_sleep: spi4_sleep { + pinmux { + function = "gpio"; + pins = "gpio12", "gpio13", "gpio14", "gpio15"; + }; + pinconf { + pins = "gpio12", "gpio13", "gpio14", "gpio15"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + spi5_default: spi5_default { + pinmux { + function = "blsp_spi5"; + pins = "gpio16", "gpio17", "gpio19"; + }; + pinmux_cs { + function = "gpio"; + pins = "gpio18"; + }; + pinconf { + pins = "gpio16", "gpio17", "gpio18", "gpio19"; + drive-strength = <12>; + bias-disable; + }; + pinconf_cs { + pins = "gpio18"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + spi5_sleep: spi5_sleep { + pinmux { + function = "gpio"; + pins = "gpio16", "gpio17", "gpio18", "gpio19"; + }; + pinconf { + pins = "gpio16", "gpio17", "gpio18", "gpio19"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + spi6_default: spi6_default { + pinmux { + function = "blsp_spi6"; + pins = "gpio20", "gpio21", "gpio23"; + }; + pinmux_cs { + function = "gpio"; + pins = "gpio22"; + }; + pinconf { + pins = "gpio20", "gpio21", "gpio22", "gpio23"; + drive-strength = <12>; + bias-disable; + }; + pinconf_cs { + pins = "gpio22"; + drive-strength = <2>; + bias-disable; + output-high; + }; + }; + + spi6_sleep: spi6_sleep { + pinmux { + function = "gpio"; + pins = "gpio20", "gpio21", "gpio22", "gpio23"; + }; + pinconf { + pins = "gpio20", "gpio21", "gpio22", "gpio23"; + drive-strength = <2>; + bias-pull-down; + }; + }; + + i2c2_default: i2c2_default { + pinmux { + function = "blsp_i2c2"; + pins = "gpio6", "gpio7"; + }; + pinconf { + pins = "gpio6", "gpio7"; + drive-strength = <2>; + bias-disable = <0>; + }; + }; + + i2c2_sleep: i2c2_sleep { + pinmux { + function = "gpio"; + pins = "gpio6", "gpio7"; + }; + pinconf { + pins = "gpio6", "gpio7"; + drive-strength = <2>; + bias-disable = <0>; + }; + }; + + i2c4_default: i2c4_default { + pinmux { + function = "blsp_i2c4"; + pins = "gpio14", "gpio15"; + }; + pinconf { + pins = "gpio14", "gpio15"; + drive-strength = <2>; + bias-disable = <0>; + }; + }; + + i2c4_sleep: i2c4_sleep { + pinmux { + function = "gpio"; + pins = "gpio14", "gpio15"; + }; + pinconf { + pins = "gpio14", "gpio15"; + drive-strength = <2>; + bias-disable = <0>; + }; + }; + + i2c6_default: i2c6_default { + pinmux { + function = "blsp_i2c6"; + pins = "gpio22", "gpio23"; + }; + pinconf { + pins = "gpio22", "gpio23"; + drive-strength = <2>; + bias-disable = <0>; + }; + }; + + i2c6_sleep: i2c6_sleep { + pinmux { + function = "gpio"; + pins = "gpio22", "gpio23"; + }; + pinconf { + pins = "gpio22", "gpio23"; + drive-strength = <2>; + bias-disable = <0>; + }; + }; + + sdhc2_cd_pin { + sdc2_cd_on: cd_on { + pinmux { + function = "gpio"; + pins = "gpio38"; + }; + pinconf { + pins = "gpio38"; + drive-strength = <2>; + bias-pull-up; + }; + }; + sdc2_cd_off: cd_off { + pinmux { + function = "gpio"; + pins = "gpio38"; + }; + pinconf { + pins = "gpio38"; + drive-strength = <2>; + bias-disable; + }; + }; + }; + + pmx_sdc1_clk { + sdc1_clk_on: clk_on { + pinmux { + pins = "sdc1_clk"; + }; + pinconf { + pins = "sdc1_clk"; + bias-disable; + drive-strength = <16>; + }; + }; + sdc1_clk_off: clk_off { + pinmux { + pins = "sdc1_clk"; + }; + pinconf { + pins = "sdc1_clk"; + bias-disable; + drive-strength = <2>; + }; + }; + }; + + pmx_sdc1_cmd { + sdc1_cmd_on: cmd_on { + pinmux { + pins = "sdc1_cmd"; + }; + pinconf { + pins = "sdc1_cmd"; + bias-pull-up; + drive-strength = <10>; + }; + }; + sdc1_cmd_off: cmd_off { + pinmux { + pins = "sdc1_cmd"; + }; + pinconf { + pins = "sdc1_cmd"; + bias-pull-up; + drive-strength = <2>; + }; + }; + }; + + pmx_sdc1_data { + sdc1_data_on: data_on { + pinmux { + pins = "sdc1_data"; + }; + pinconf { + pins = "sdc1_data"; + bias-pull-up; + drive-strength = <10>; + }; + }; + sdc1_data_off: data_off { + pinmux { + pins = "sdc1_data"; + }; + pinconf { + pins = "sdc1_data"; + bias-pull-up; + drive-strength = <2>; + }; + }; + }; + + pmx_sdc2_clk { + sdc2_clk_on: clk_on { + pinmux { + pins = "sdc2_clk"; + }; + pinconf { + pins = "sdc2_clk"; + bias-disable; + drive-strength = <16>; + }; + }; + sdc2_clk_off: clk_off { + pinmux { + pins = "sdc2_clk"; + }; + pinconf { + pins = "sdc2_clk"; + bias-disable; + drive-strength = <2>; + }; + }; + }; + + pmx_sdc2_cmd { + sdc2_cmd_on: cmd_on { + pinmux { + pins = "sdc2_cmd"; + }; + pinconf { + pins = "sdc2_cmd"; + bias-pull-up; + drive-strength = <10>; + }; + }; + sdc2_cmd_off: cmd_off { + pinmux { + pins = "sdc2_cmd"; + }; + pinconf { + pins = "sdc2_cmd"; + bias-pull-up; + drive-strength = <2>; + }; + }; + }; + + pmx_sdc2_data { + sdc2_data_on: data_on { + pinmux { + pins = "sdc2_data"; + }; + pinconf { + pins = "sdc2_data"; + bias-pull-up; + drive-strength = <10>; + }; + }; + sdc2_data_off: data_off { + pinmux { + pins = "sdc2_data"; + }; + pinconf { + pins = "sdc2_data"; + bias-pull-up; + drive-strength = <2>; + }; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/qcom/msm8916.dtsi b/kernel/arch/arm64/boot/dts/qcom/msm8916.dtsi index f212b8303..8d184ff19 100644 --- a/kernel/arch/arm64/boot/dts/qcom/msm8916.dtsi +++ b/kernel/arch/arm64/boot/dts/qcom/msm8916.dtsi @@ -24,7 +24,10 @@ #address-cells = <2>; #size-cells = <2>; - aliases { }; + aliases { + sdhc1 = &sdhc_1; /* SDC1 eMMC slot */ + sdhc2 = &sdhc_2; /* SDC2 SD card slot */ + }; chosen { }; @@ -77,7 +80,12 @@ ranges = <0 0 0 0xffffffff>; compatible = "simple-bus"; - pinctrl@1000000 { + restart@4ab000 { + compatible = "qcom,pshold"; + reg = <0x4ab000 0x4>; + }; + + msmgpio: pinctrl@1000000 { compatible = "qcom,msm8916-pinctrl"; reg = <0x1000000 0x300000>; interrupts = ; @@ -85,39 +93,25 @@ #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; - - blsp1_uart2_default: blsp1_uart2_default { - pinmux { - function = "blsp_uart2"; - pins = "gpio4", "gpio5"; - }; - pinconf { - pins = "gpio4", "gpio5"; - drive-strength = <16>; - bias-disable; - }; - }; - - blsp1_uart2_sleep: blsp1_uart2_sleep { - pinmux { - function = "blsp_uart2"; - pins = "gpio4", "gpio5"; - }; - pinconf { - pins = "gpio4", "gpio5"; - drive-strength = <2>; - bias-pull-down; - }; - }; }; gcc: qcom,gcc@1800000 { compatible = "qcom,gcc-msm8916"; #clock-cells = <1>; #reset-cells = <1>; + #power-domain-cells = <1>; reg = <0x1800000 0x80000>; }; + blsp1_uart1: serial@78af000 { + compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; + reg = <0x78af000 0x200>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_UART1_APPS_CLK>, <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + status = "disabled"; + }; + blsp1_uart2: serial@78b0000 { compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; reg = <0x78b0000 0x200>; @@ -127,6 +121,232 @@ status = "disabled"; }; + blsp_dma: dma@7884000 { + compatible = "qcom,bam-v1.7.0"; + reg = <0x07884000 0x23000>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "bam_clk"; + #dma-cells = <1>; + qcom,ee = <0>; + status = "disabled"; + }; + + blsp_spi1: spi@78b5000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078b5000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP1_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp_dma 5>, <&blsp_dma 4>; + dma-names = "rx", "tx"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi1_default>; + pinctrl-1 = <&spi1_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_spi2: spi@78b6000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078b6000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP2_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp_dma 7>, <&blsp_dma 6>; + dma-names = "rx", "tx"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi2_default>; + pinctrl-1 = <&spi2_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_spi3: spi@78b7000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078b7000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP3_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp_dma 9>, <&blsp_dma 8>; + dma-names = "rx", "tx"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi3_default>; + pinctrl-1 = <&spi3_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_spi4: spi@78b8000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078b8000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP4_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp_dma 11>, <&blsp_dma 10>; + dma-names = "rx", "tx"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi4_default>; + pinctrl-1 = <&spi4_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_spi5: spi@78b9000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078b9000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP5_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp_dma 13>, <&blsp_dma 12>; + dma-names = "rx", "tx"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi5_default>; + pinctrl-1 = <&spi5_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_spi6: spi@78ba000 { + compatible = "qcom,spi-qup-v2.2.1"; + reg = <0x078ba000 0x600>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_QUP6_SPI_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", "iface"; + dmas = <&blsp_dma 15>, <&blsp_dma 14>; + dma-names = "rx", "tx"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&spi6_default>; + pinctrl-1 = <&spi6_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_i2c2: i2c@78b6000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x78b6000 0x1000>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_AHB_CLK>, + <&gcc GCC_BLSP1_QUP2_I2C_APPS_CLK>; + clock-names = "iface", "core"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&i2c2_default>; + pinctrl-1 = <&i2c2_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_i2c4: i2c@78b8000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x78b8000 0x1000>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_AHB_CLK>, + <&gcc GCC_BLSP1_QUP4_I2C_APPS_CLK>; + clock-names = "iface", "core"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&i2c4_default>; + pinctrl-1 = <&i2c4_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + blsp_i2c6: i2c@78ba000 { + compatible = "qcom,i2c-qup-v2.2.1"; + reg = <0x78ba000 0x1000>; + interrupts = ; + clocks = <&gcc GCC_BLSP1_AHB_CLK>, + <&gcc GCC_BLSP1_QUP6_I2C_APPS_CLK>; + clock-names = "iface", "core"; + pinctrl-names = "default", "sleep"; + pinctrl-0 = <&i2c6_default>; + pinctrl-1 = <&i2c6_sleep>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + sdhc_1: sdhci@07824000 { + compatible = "qcom,sdhci-msm-v4"; + reg = <0x07824900 0x11c>, <0x07824000 0x800>; + reg-names = "hc_mem", "core_mem"; + + interrupts = <0 123 0>, <0 138 0>; + interrupt-names = "hc_irq", "pwr_irq"; + clocks = <&gcc GCC_SDCC1_APPS_CLK>, + <&gcc GCC_SDCC1_AHB_CLK>; + clock-names = "core", "iface"; + bus-width = <8>; + non-removable; + status = "disabled"; + }; + + sdhc_2: sdhci@07864000 { + compatible = "qcom,sdhci-msm-v4"; + reg = <0x07864900 0x11c>, <0x07864000 0x800>; + reg-names = "hc_mem", "core_mem"; + + interrupts = <0 125 0>, <0 221 0>; + interrupt-names = "hc_irq", "pwr_irq"; + clocks = <&gcc GCC_SDCC2_APPS_CLK>, + <&gcc GCC_SDCC2_AHB_CLK>; + clock-names = "core", "iface"; + bus-width = <4>; + status = "disabled"; + }; + + usb_dev: usb@78d9000 { + compatible = "qcom,ci-hdrc"; + reg = <0x78d9000 0x400>; + dr_mode = "peripheral"; + interrupts = ; + usb-phy = <&usb_otg>; + status = "disabled"; + }; + + usb_host: ehci@78d9000 { + compatible = "qcom,ehci-host"; + reg = <0x78d9000 0x400>; + interrupts = ; + usb-phy = <&usb_otg>; + status = "disabled"; + }; + + usb_otg: phy@78d9000 { + compatible = "qcom,usb-otg-snps"; + reg = <0x78d9000 0x400>; + interrupts = , + ; + + qcom,vdd-levels = <1 5 7>; + qcom,phy-init-sequence = <0x44 0x6B 0x24 0x13>; + dr_mode = "peripheral"; + qcom,otg-control = <2>; // PMIC + + clocks = <&gcc GCC_USB_HS_AHB_CLK>, + <&gcc GCC_USB_HS_SYSTEM_CLK>, + <&gcc GCC_USB2A_PHY_SLEEP_CLK>; + clock-names = "iface", "core", "sleep"; + + resets = <&gcc GCC_USB2A_PHY_BCR>, + <&gcc GCC_USB_HS_BCR>; + reset-names = "phy", "link"; + status = "disabled"; + }; + intc: interrupt-controller@b000000 { compatible = "qcom,msm-qgic2"; interrupt-controller; @@ -192,5 +412,32 @@ status = "disabled"; }; }; + + spmi_bus: spmi@200f000 { + compatible = "qcom,spmi-pmic-arb"; + reg = <0x200f000 0x001000>, + <0x2400000 0x400000>, + <0x2c00000 0x400000>, + <0x3800000 0x200000>, + <0x200a000 0x002100>; + reg-names = "core", "chnls", "obsrvr", "intr", "cnfg"; + interrupt-names = "periph_irq"; + interrupts = ; + qcom,ee = <0>; + qcom,channel = <0>; + #address-cells = <2>; + #size-cells = <0>; + interrupt-controller; + #interrupt-cells = <4>; + }; + + rng@22000 { + compatible = "qcom,prng"; + reg = <0x00022000 0x200>; + clocks = <&gcc GCC_PRNG_AHB_CLK>; + clock-names = "core"; + }; }; }; + +#include "msm8916-pins.dtsi" diff --git a/kernel/arch/arm64/boot/dts/qcom/pm8916.dtsi b/kernel/arch/arm64/boot/dts/qcom/pm8916.dtsi new file mode 100644 index 000000000..b222ece7e --- /dev/null +++ b/kernel/arch/arm64/boot/dts/qcom/pm8916.dtsi @@ -0,0 +1,99 @@ +#include +#include +#include + +&spmi_bus { + + usid0: pm8916@0 { + compatible = "qcom,spmi-pmic"; + reg = <0x0 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + + rtc@6000 { + compatible = "qcom,pm8941-rtc"; + reg = <0x6000 0x6100>; + reg-names = "rtc", "alarm"; + interrupts = <0x0 0x61 0x1 IRQ_TYPE_EDGE_RISING>; + }; + + pwrkey@800 { + compatible = "qcom,pm8941-pwrkey"; + reg = <0x800>; + interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>; + debounce = <15625>; + bias-pull-up; + }; + + pm8916_gpios: gpios@c000 { + compatible = "qcom,pm8916-gpio"; + reg = <0xc000 0x400>; + gpio-controller; + #gpio-cells = <2>; + interrupts = <0 0xc0 0 IRQ_TYPE_NONE>, + <0 0xc1 0 IRQ_TYPE_NONE>, + <0 0xc2 0 IRQ_TYPE_NONE>, + <0 0xc3 0 IRQ_TYPE_NONE>; + }; + + pm8916_mpps: mpps@a000 { + compatible = "qcom,pm8916-mpp"; + reg = <0xa000 0x400>; + gpio-controller; + #gpio-cells = <2>; + interrupts = <0 0xa0 0 IRQ_TYPE_NONE>, + <0 0xa1 0 IRQ_TYPE_NONE>, + <0 0xa2 0 IRQ_TYPE_NONE>, + <0 0xa3 0 IRQ_TYPE_NONE>; + }; + + pm8916_temp: temp-alarm@2400 { + compatible = "qcom,spmi-temp-alarm"; + reg = <0x2400 0x100>; + interrupts = <0 0x24 0 IRQ_TYPE_EDGE_RISING>; + io-channels = <&pm8916_vadc VADC_DIE_TEMP>; + io-channel-names = "thermal"; + #thermal-sensor-cells = <0>; + }; + + pm8916_vadc: vadc@3100 { + compatible = "qcom,spmi-vadc"; + reg = <0x3100 0x100>; + interrupts = <0x0 0x31 0x0 IRQ_TYPE_EDGE_RISING>; + #address-cells = <1>; + #size-cells = <0>; + #io-channel-cells = <1>; + + usb_in { + reg = ; + qcom,pre-scaling = <1 10>; + }; + vph_pwr { + reg = ; + qcom,pre-scaling = <1 3>; + }; + die_temp { + reg = ; + }; + ref_625mv { + reg = ; + }; + ref_1250v { + reg = ; + }; + ref_gnd { + reg = ; + }; + ref_vdd { + reg = ; + }; + }; + }; + + usid1: pm8916@1 { + compatible = "qcom,spmi-pmic"; + reg = <0x1 SPMI_USID>; + #address-cells = <1>; + #size-cells = <0>; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/rockchip/Makefile b/kernel/arch/arm64/boot/dts/rockchip/Makefile new file mode 100644 index 000000000..601e6a236 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/rockchip/Makefile @@ -0,0 +1,5 @@ +dtb-$(CONFIG_ARCH_ROCKCHIP) += rk3368-r88.dtb + +always := $(dtb-y) +subdir-y := $(dts-dirs) +clean-files := *.dtb diff --git a/kernel/arch/arm64/boot/dts/rockchip/rk3368-r88.dts b/kernel/arch/arm64/boot/dts/rockchip/rk3368-r88.dts new file mode 100644 index 000000000..401a81231 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/rockchip/rk3368-r88.dts @@ -0,0 +1,354 @@ +/* + * Copyright (c) 2015 Heiko Stuebner + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This file 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 file 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. + * + * Or, alternatively, + * + * b) 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. + */ + +/dts-v1/; +#include "rk3368.dtsi" + +/ { + model = "Rockchip R88"; + compatible = "rockchip,r88", "rockchip,rk3368"; + + chosen { + stdout-path = "serial2:115200n8"; + }; + + memory { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x40000000>; + }; + + emmc_pwrseq: emmc-pwrseq { + compatible = "mmc-pwrseq-emmc"; + pinctrl-0 = <&emmc_reset>; + pinctrl-names = "default"; + reset-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>; + }; + + keys: gpio-keys { + compatible = "gpio-keys"; + #address-cells = <1>; + #size-cells = <0>; + pinctrl-names = "default"; + pinctrl-0 = <&pwr_key>; + + button@0 { + gpio-key,wakeup = <1>; + gpios = <&gpio0 2 GPIO_ACTIVE_LOW>; + label = "GPIO Power"; + linux,code = <116>; + }; + }; + + leds: gpio-leds { + compatible = "gpio-leds"; + + work { + gpios = <&gpio3 29 GPIO_ACTIVE_HIGH>; + label = "r88:green:led"; + pinctrl-names = "default"; + pinctrl-0 = <&led_ctl>; + }; + }; + + ir: ir-receiver { + compatible = "gpio-ir-receiver"; + gpios = <&gpio3 30 GPIO_ACTIVE_LOW>; + pinctrl-names = "default"; + pinctrl-0 = <&ir_int>; + }; + + sdio_pwrseq: sdio-pwrseq { + compatible = "mmc-pwrseq-simple"; + clocks = <&hym8563>; + clock-names = "ext_clock"; + pinctrl-names = "default"; + pinctrl-0 = <&bt_rst>, <&wifi_reg_on>; + + reset-gpios = + /* BT_RST_N */ + <&gpio3 5 GPIO_ACTIVE_LOW>, + + /* WL_REG_ON */ + <&gpio3 4 GPIO_ACTIVE_LOW>; + }; + + vcc_18: vcc18-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_18"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + }; + + /* supplies both host and otg */ + vcc_host: vcc-host-regulator { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&gpio0 4 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&host_vbus_drv>; + regulator-name = "vcc_host"; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + }; + + vcc_io: vcc-io-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_io"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + }; + + vcc_lan: vcc-lan-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_lan"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_io>; + }; + + vcc_sys: vcc-sys-regulator { + compatible = "regulator-fixed"; + regulator-name = "vcc_sys"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + regulator-boot-on; + }; + + vccio_wl: vccio-wl-regulator { + compatible = "regulator-fixed"; + regulator-name = "vccio_wl"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_io>; + }; + + vdd_10: vdd-10-regulator { + compatible = "regulator-fixed"; + regulator-name = "vdd_10"; + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + }; +}; + +&emmc { + broken-cd; + bus-width = <8>; + cap-mmc-highspeed; + disable-wp; + mmc-pwrseq = <&emmc_pwrseq>; + non-removable; + num-slots = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>; + status = "okay"; +}; + +&gmac { + phy-supply = <&vcc_lan>; + phy-mode = "rmii"; + clock_in_out = "output"; + snps,reset-gpio = <&gpio3 12 0>; + snps,reset-active-low; + snps,reset-delays-us = <0 10000 1000000>; + pinctrl-names = "default"; + pinctrl-0 = <&rmii_pins>; + tx_delay = <0x30>; + rx_delay = <0x10>; + status = "ok"; +}; + +&i2c0 { + status = "okay"; + + vdd_cpu: syr827@40 { + compatible = "silergy,syr827"; + reg = <0x40>; + fcs,suspend-voltage-selector = <1>; + regulator-name = "vdd_cpu"; + regulator-enable-ramp-delay = <300>; + regulator-min-microvolt = <712500>; + regulator-max-microvolt = <1500000>; + regulator-ramp-delay = <8000>; + regulator-always-on; + regulator-boot-on; + vin-supply = <&vcc_sys>; + }; + + hym8563: hym8563@51 { + compatible = "haoyu,hym8563"; + reg = <0x51>; + #clock-cells = <0>; + clock-frequency = <32768>; + clock-output-names = "xin32k"; + /* rtc_int is not connected */ + }; +}; + +&sdio0 { + assigned-clocks = <&cru SCLK_SDIO0>; + assigned-clock-parents = <&cru PLL_CPLL>; + broken-cd; + bus-width = <4>; + cap-sd-highspeed; + cap-sdio-irq; + keep-power-in-suspend; + mmc-pwrseq = <&sdio_pwrseq>; + non-removable; + num-slots = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&sdio0_clk &sdio0_cmd &sdio0_bus4>; + vmmc-supply = <&vcc_io>; + vqmmc-supply = <&vccio_wl>; + status = "okay"; +}; + +&pinctrl { + pcfg_pull_none_drv_8ma: pcfg-pull-none-drv-8ma { + bias-disable; + drive-strength = <8>; + }; + + pcfg_pull_up_drv_8ma: pcfg-pull-up-drv-8ma { + bias-pull-up; + drive-strength = <8>; + }; + + emmc { + emmc_bus8: emmc-bus8 { + rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 19 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 20 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 21 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 22 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 23 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 24 RK_FUNC_2 &pcfg_pull_up_drv_8ma>, + <1 25 RK_FUNC_2 &pcfg_pull_up_drv_8ma>; + }; + + emmc-clk { + rockchip,pins = <2 4 RK_FUNC_2 &pcfg_pull_none_drv_8ma>; + }; + + emmc-cmd { + rockchip,pins = <1 26 RK_FUNC_2 &pcfg_pull_up_drv_8ma>; + }; + + emmc_reset: emmc-reset { + rockchip,pins = <2 3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + ir { + ir_int: ir-int { + rockchip,pins = <3 30 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + keys { + pwr_key: pwr-key { + rockchip,pins = <0 2 RK_FUNC_GPIO &pcfg_pull_up>; + }; + }; + + leds { + stby_pwren: stby-pwren { + rockchip,pins = <0 12 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + led_ctl: led-ctl { + rockchip,pins = <3 29 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + sdio { + wifi_reg_on: wifi-reg-on { + rockchip,pins = <3 4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + bt_rst: bt-rst { + rockchip,pins = <3 5 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + usb { + host_vbus_drv: host-vbus-drv { + rockchip,pins = <0 4 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; +}; + +&saradc { + vref-supply = <&vcc_18>; + status = "okay"; +}; + +&uart2 { + status = "okay"; +}; + +&usb_host0_ehci { + status = "okay"; +}; + +&usb_otg { + dr_mode = "host"; + status = "okay"; +}; + +&wdt { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi new file mode 100644 index 000000000..cc093a482 --- /dev/null +++ b/kernel/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -0,0 +1,900 @@ +/* + * Copyright (c) 2015 Heiko Stuebner + * + * This file is dual-licensed: you can use it either under the terms + * of the GPL or the X11 license, at your option. Note that this dual + * licensing only applies to this file, and not this project as a + * whole. + * + * a) This library 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 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 General Public License for more details. + * + * Or, alternatively, + * + * b) 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. + */ + +#include +#include +#include +#include +#include + +/ { + compatible = "rockchip,rk3368"; + interrupt-parent = <&gic>; + #address-cells = <2>; + #size-cells = <2>; + + aliases { + i2c0 = &i2c0; + i2c1 = &i2c1; + i2c2 = &i2c2; + i2c3 = &i2c3; + i2c4 = &i2c4; + i2c5 = &i2c5; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + spi0 = &spi0; + spi1 = &spi1; + spi2 = &spi2; + }; + + cpus { + #address-cells = <0x2>; + #size-cells = <0x0>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu_b0>; + }; + core1 { + cpu = <&cpu_b1>; + }; + core2 { + cpu = <&cpu_b2>; + }; + core3 { + cpu = <&cpu_b3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu_l0>; + }; + core1 { + cpu = <&cpu_l1>; + }; + core2 { + cpu = <&cpu_l2>; + }; + core3 { + cpu = <&cpu_l3>; + }; + }; + }; + + idle-states { + entry-method = "psci"; + + cpu_sleep: cpu-sleep-0 { + compatible = "arm,idle-state"; + arm,psci-suspend-param = <0x1010000>; + entry-latency-us = <0x3fffffff>; + exit-latency-us = <0x40000000>; + min-residency-us = <0xffffffff>; + }; + }; + + cpu_l0: cpu@0 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x0>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_l1: cpu@1 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x1>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_l2: cpu@2 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x2>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_l3: cpu@3 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x3>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_b0: cpu@100 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x100>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_b1: cpu@101 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x101>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_b2: cpu@102 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x102>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + + cpu_b3: cpu@103 { + device_type = "cpu"; + compatible = "arm,cortex-a53", "arm,armv8"; + reg = <0x0 0x103>; + cpu-idle-states = <&cpu_sleep>; + enable-method = "psci"; + }; + }; + + arm-pmu { + compatible = "arm,armv8-pmuv3"; + interrupts = , + , + , + , + , + , + , + ; + interrupt-affinity = <&cpu_l0>, <&cpu_l1>, <&cpu_l2>, + <&cpu_l3>, <&cpu_b0>, <&cpu_b1>, + <&cpu_b2>, <&cpu_b3>; + }; + + psci { + compatible = "arm,psci-0.2"; + method = "smc"; + }; + + timer { + compatible = "arm,armv8-timer"; + interrupts = , + , + , + ; + }; + + xin24m: oscillator { + compatible = "fixed-clock"; + clock-frequency = <24000000>; + clock-output-names = "xin24m"; + #clock-cells = <0>; + }; + + sdmmc: dwmmc@ff0c0000 { + compatible = "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc"; + reg = <0x0 0xff0c0000 0x0 0x4000>; + clock-freq-min-max = <400000 150000000>; + clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>; + clock-names = "biu", "ciu"; + fifo-depth = <0x100>; + interrupts = ; + status = "disabled"; + }; + + sdio0: dwmmc@ff0d0000 { + compatible = "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc"; + reg = <0x0 0xff0d0000 0x0 0x4000>; + clock-freq-min-max = <400000 150000000>; + clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>, + <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>; + clock-names = "biu", "ciu", "ciu_drv", "ciu_sample"; + fifo-depth = <0x100>; + interrupts = ; + status = "disabled"; + }; + + emmc: dwmmc@ff0f0000 { + compatible = "rockchip,rk3368-dw-mshc", "rockchip,rk3288-dw-mshc"; + reg = <0x0 0xff0f0000 0x0 0x4000>; + clock-freq-min-max = <400000 150000000>; + clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>; + clock-names = "biu", "ciu"; + fifo-depth = <0x100>; + interrupts = ; + status = "disabled"; + }; + + saradc: saradc@ff100000 { + compatible = "rockchip,saradc"; + reg = <0x0 0xff100000 0x0 0x100>; + interrupts = ; + #io-channel-cells = <1>; + clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>; + clock-names = "saradc", "apb_pclk"; + status = "disabled"; + }; + + spi0: spi@ff110000 { + compatible = "rockchip,rk3368-spi", "rockchip,rk3066-spi"; + reg = <0x0 0xff110000 0x0 0x1000>; + clocks = <&cru SCLK_SPI0>, <&cru PCLK_SPI0>; + clock-names = "spiclk", "apb_pclk"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&spi0_clk &spi0_tx &spi0_rx &spi0_cs0>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi1: spi@ff120000 { + compatible = "rockchip,rk3368-spi", "rockchip,rk3066-spi"; + reg = <0x0 0xff120000 0x0 0x1000>; + clocks = <&cru SCLK_SPI1>, <&cru PCLK_SPI1>; + clock-names = "spiclk", "apb_pclk"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&spi1_clk &spi1_tx &spi1_rx &spi1_cs0>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi2: spi@ff130000 { + compatible = "rockchip,rk3368-spi", "rockchip,rk3066-spi"; + reg = <0x0 0xff130000 0x0 0x1000>; + clocks = <&cru SCLK_SPI2>, <&cru PCLK_SPI2>; + clock-names = "spiclk", "apb_pclk"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&spi2_clk &spi2_tx &spi2_rx &spi2_cs0>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@ff140000 { + compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c"; + reg = <0x0 0xff140000 0x0 0x1000>; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + clock-names = "i2c"; + clocks = <&cru PCLK_I2C1>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_xfer>; + status = "disabled"; + }; + + i2c3: i2c@ff150000 { + compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c"; + reg = <0x0 0xff150000 0x0 0x1000>; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + clock-names = "i2c"; + clocks = <&cru PCLK_I2C3>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_xfer>; + status = "disabled"; + }; + + i2c4: i2c@ff160000 { + compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c"; + reg = <0x0 0xff160000 0x0 0x1000>; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + clock-names = "i2c"; + clocks = <&cru PCLK_I2C4>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c4_xfer>; + status = "disabled"; + }; + + i2c5: i2c@ff170000 { + compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c"; + reg = <0x0 0xff170000 0x0 0x1000>; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + clock-names = "i2c"; + clocks = <&cru PCLK_I2C5>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c5_xfer>; + status = "disabled"; + }; + + uart0: serial@ff180000 { + compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart"; + reg = <0x0 0xff180000 0x0 0x100>; + clock-frequency = <24000000>; + clocks = <&cru SCLK_UART0>, <&cru PCLK_UART0>; + clock-names = "baudclk", "apb_pclk"; + interrupts = ; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart1: serial@ff190000 { + compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart"; + reg = <0x0 0xff190000 0x0 0x100>; + clock-frequency = <24000000>; + clocks = <&cru SCLK_UART1>, <&cru PCLK_UART1>; + clock-names = "baudclk", "apb_pclk"; + interrupts = ; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart3: serial@ff1b0000 { + compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart"; + reg = <0x0 0xff1b0000 0x0 0x100>; + clock-frequency = <24000000>; + clocks = <&cru SCLK_UART3>, <&cru PCLK_UART3>; + clock-names = "baudclk", "apb_pclk"; + interrupts = ; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart4: serial@ff1c0000 { + compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart"; + reg = <0x0 0xff1c0000 0x0 0x100>; + clock-frequency = <24000000>; + clocks = <&cru SCLK_UART4>, <&cru PCLK_UART4>; + clock-names = "baudclk", "apb_pclk"; + interrupts = ; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + gmac: ethernet@ff290000 { + compatible = "rockchip,rk3368-gmac"; + reg = <0x0 0xff290000 0x0 0x10000>; + interrupts = ; + interrupt-names = "macirq"; + rockchip,grf = <&grf>; + clocks = <&cru SCLK_MAC>, + <&cru SCLK_MAC_RX>, <&cru SCLK_MAC_TX>, + <&cru SCLK_MACREF>, <&cru SCLK_MACREF_OUT>, + <&cru ACLK_GMAC>, <&cru PCLK_GMAC>; + clock-names = "stmmaceth", + "mac_clk_rx", "mac_clk_tx", + "clk_mac_ref", "clk_mac_refout", + "aclk_mac", "pclk_mac"; + status = "disabled"; + }; + + usb_host0_ehci: usb@ff500000 { + compatible = "generic-ehci"; + reg = <0x0 0xff500000 0x0 0x100>; + interrupts = ; + clocks = <&cru HCLK_HOST0>; + clock-names = "usbhost"; + status = "disabled"; + }; + + usb_otg: usb@ff580000 { + compatible = "rockchip,rk3368-usb", "rockchip,rk3066-usb", + "snps,dwc2"; + reg = <0x0 0xff580000 0x0 0x40000>; + interrupts = ; + clocks = <&cru HCLK_OTG0>; + clock-names = "otg"; + dr_mode = "otg"; + g-np-tx-fifo-size = <16>; + g-rx-fifo-size = <275>; + g-tx-fifo-size = <256 128 128 64 64 32>; + g-use-dma; + status = "disabled"; + }; + + i2c0: i2c@ff650000 { + compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c"; + reg = <0x0 0xff650000 0x0 0x1000>; + clocks = <&cru PCLK_I2C0>; + clock-names = "i2c"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_xfer>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c2: i2c@ff660000 { + compatible = "rockchip,rk3368-i2c", "rockchip,rk3288-i2c"; + reg = <0x0 0xff660000 0x0 0x1000>; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + clock-names = "i2c"; + clocks = <&cru PCLK_I2C2>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_xfer>; + status = "disabled"; + }; + + uart2: serial@ff690000 { + compatible = "rockchip,rk3368-uart", "snps,dw-apb-uart"; + reg = <0x0 0xff690000 0x0 0x100>; + clocks = <&cru SCLK_UART2>, <&cru PCLK_UART2>; + clock-names = "baudclk", "apb_pclk"; + interrupts = ; + pinctrl-names = "default"; + pinctrl-0 = <&uart2_xfer>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + pmugrf: syscon@ff738000 { + compatible = "rockchip,rk3368-pmugrf", "syscon"; + reg = <0x0 0xff738000 0x0 0x1000>; + }; + + cru: clock-controller@ff760000 { + compatible = "rockchip,rk3368-cru"; + reg = <0x0 0xff760000 0x0 0x1000>; + rockchip,grf = <&grf>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + grf: syscon@ff770000 { + compatible = "rockchip,rk3368-grf", "syscon"; + reg = <0x0 0xff770000 0x0 0x1000>; + }; + + wdt: watchdog@ff800000 { + compatible = "rockchip,rk3368-wdt", "snps,dw-wdt"; + reg = <0x0 0xff800000 0x0 0x100>; + clocks = <&cru PCLK_WDT>; + interrupts = ; + status = "disabled"; + }; + + gic: interrupt-controller@ffb71000 { + compatible = "arm,gic-400"; + interrupt-controller; + #interrupt-cells = <3>; + #address-cells = <0>; + + reg = <0x0 0xffb71000 0x0 0x1000>, + <0x0 0xffb72000 0x0 0x1000>, + <0x0 0xffb74000 0x0 0x2000>, + <0x0 0xffb76000 0x0 0x2000>; + interrupts = ; + }; + + pinctrl: pinctrl { + compatible = "rockchip,rk3368-pinctrl"; + rockchip,grf = <&grf>; + rockchip,pmu = <&pmugrf>; + #address-cells = <0x2>; + #size-cells = <0x2>; + ranges; + + gpio0: gpio0@ff750000 { + compatible = "rockchip,gpio-bank"; + reg = <0x0 0xff750000 0x0 0x100>; + clocks = <&cru PCLK_GPIO0>; + interrupts = ; + + gpio-controller; + #gpio-cells = <0x2>; + + interrupt-controller; + #interrupt-cells = <0x2>; + }; + + gpio1: gpio1@ff780000 { + compatible = "rockchip,gpio-bank"; + reg = <0x0 0xff780000 0x0 0x100>; + clocks = <&cru PCLK_GPIO1>; + interrupts = ; + + gpio-controller; + #gpio-cells = <0x2>; + + interrupt-controller; + #interrupt-cells = <0x2>; + }; + + gpio2: gpio2@ff790000 { + compatible = "rockchip,gpio-bank"; + reg = <0x0 0xff790000 0x0 0x100>; + clocks = <&cru PCLK_GPIO2>; + interrupts = ; + + gpio-controller; + #gpio-cells = <0x2>; + + interrupt-controller; + #interrupt-cells = <0x2>; + }; + + gpio3: gpio3@ff7a0000 { + compatible = "rockchip,gpio-bank"; + reg = <0x0 0xff7a0000 0x0 0x100>; + clocks = <&cru PCLK_GPIO3>; + interrupts = ; + + gpio-controller; + #gpio-cells = <0x2>; + + interrupt-controller; + #interrupt-cells = <0x2>; + }; + + pcfg_pull_up: pcfg-pull-up { + bias-pull-up; + }; + + pcfg_pull_down: pcfg-pull-down { + bias-pull-down; + }; + + pcfg_pull_none: pcfg-pull-none { + bias-disable; + }; + + pcfg_pull_none_12ma: pcfg-pull-none-12ma { + bias-disable; + drive-strength = <12>; + }; + + emmc { + emmc_clk: emmc-clk { + rockchip,pins = <2 4 RK_FUNC_2 &pcfg_pull_none>; + }; + + emmc_cmd: emmc-cmd { + rockchip,pins = <1 26 RK_FUNC_2 &pcfg_pull_up>; + }; + + emmc_pwr: emmc-pwr { + rockchip,pins = <1 27 RK_FUNC_2 &pcfg_pull_up>; + }; + + emmc_bus1: emmc-bus1 { + rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>; + }; + + emmc_bus4: emmc-bus4 { + rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>, + <1 19 RK_FUNC_2 &pcfg_pull_up>, + <1 20 RK_FUNC_2 &pcfg_pull_up>, + <1 21 RK_FUNC_2 &pcfg_pull_up>; + }; + + emmc_bus8: emmc-bus8 { + rockchip,pins = <1 18 RK_FUNC_2 &pcfg_pull_up>, + <1 19 RK_FUNC_2 &pcfg_pull_up>, + <1 20 RK_FUNC_2 &pcfg_pull_up>, + <1 21 RK_FUNC_2 &pcfg_pull_up>, + <1 22 RK_FUNC_2 &pcfg_pull_up>, + <1 23 RK_FUNC_2 &pcfg_pull_up>, + <1 24 RK_FUNC_2 &pcfg_pull_up>, + <1 25 RK_FUNC_2 &pcfg_pull_up>; + }; + }; + + gmac { + rgmii_pins: rgmii-pins { + rockchip,pins = <3 22 RK_FUNC_1 &pcfg_pull_none>, + <3 24 RK_FUNC_1 &pcfg_pull_none>, + <3 19 RK_FUNC_1 &pcfg_pull_none>, + <3 8 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 9 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 10 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 14 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 28 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 13 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 15 RK_FUNC_1 &pcfg_pull_none>, + <3 16 RK_FUNC_1 &pcfg_pull_none>, + <3 17 RK_FUNC_1 &pcfg_pull_none>, + <3 18 RK_FUNC_1 &pcfg_pull_none>, + <3 25 RK_FUNC_1 &pcfg_pull_none>, + <3 20 RK_FUNC_1 &pcfg_pull_none>; + }; + + rmii_pins: rmii-pins { + rockchip,pins = <3 22 RK_FUNC_1 &pcfg_pull_none>, + <3 24 RK_FUNC_1 &pcfg_pull_none>, + <3 19 RK_FUNC_1 &pcfg_pull_none>, + <3 8 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 9 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 13 RK_FUNC_1 &pcfg_pull_none_12ma>, + <3 15 RK_FUNC_1 &pcfg_pull_none>, + <3 16 RK_FUNC_1 &pcfg_pull_none>, + <3 20 RK_FUNC_1 &pcfg_pull_none>, + <3 21 RK_FUNC_1 &pcfg_pull_none>; + }; + }; + + i2c0 { + i2c0_xfer: i2c0-xfer { + rockchip,pins = <0 6 RK_FUNC_1 &pcfg_pull_none>, + <0 7 RK_FUNC_1 &pcfg_pull_none>; + }; + }; + + i2c1 { + i2c1_xfer: i2c1-xfer { + rockchip,pins = <2 21 RK_FUNC_1 &pcfg_pull_none>, + <2 22 RK_FUNC_1 &pcfg_pull_none>; + }; + }; + + i2c2 { + i2c2_xfer: i2c2-xfer { + rockchip,pins = <0 9 RK_FUNC_2 &pcfg_pull_none>, + <3 31 RK_FUNC_2 &pcfg_pull_none>; + }; + }; + + i2c3 { + i2c3_xfer: i2c3-xfer { + rockchip,pins = <1 16 RK_FUNC_1 &pcfg_pull_none>, + <1 17 RK_FUNC_1 &pcfg_pull_none>; + }; + }; + + i2c4 { + i2c4_xfer: i2c4-xfer { + rockchip,pins = <3 24 RK_FUNC_2 &pcfg_pull_none>, + <3 25 RK_FUNC_2 &pcfg_pull_none>; + }; + }; + + i2c5 { + i2c5_xfer: i2c5-xfer { + rockchip,pins = <3 26 RK_FUNC_2 &pcfg_pull_none>, + <3 27 RK_FUNC_2 &pcfg_pull_none>; + }; + }; + + sdio0 { + sdio0_bus1: sdio0-bus1 { + rockchip,pins = <2 28 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_bus4: sdio0-bus4 { + rockchip,pins = <2 28 RK_FUNC_1 &pcfg_pull_up>, + <2 29 RK_FUNC_1 &pcfg_pull_up>, + <2 30 RK_FUNC_1 &pcfg_pull_up>, + <2 31 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_cmd: sdio0-cmd { + rockchip,pins = <3 0 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_clk: sdio0-clk { + rockchip,pins = <3 1 RK_FUNC_1 &pcfg_pull_none>; + }; + + sdio0_cd: sdio0-cd { + rockchip,pins = <3 2 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_wp: sdio0-wp { + rockchip,pins = <3 3 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_pwr: sdio0-pwr { + rockchip,pins = <3 4 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_bkpwr: sdio0-bkpwr { + rockchip,pins = <3 5 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdio0_int: sdio0-int { + rockchip,pins = <3 6 RK_FUNC_1 &pcfg_pull_up>; + }; + }; + + sdmmc { + sdmmc_clk: sdmmc-clk { + rockchip,pins = <2 9 RK_FUNC_1 &pcfg_pull_none>; + }; + + sdmmc_cmd: sdmmc-cmd { + rockchip,pins = <2 10 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_cd: sdmcc-cd { + rockchip,pins = <2 11 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_bus1: sdmmc-bus1 { + rockchip,pins = <2 5 RK_FUNC_1 &pcfg_pull_up>; + }; + + sdmmc_bus4: sdmmc-bus4 { + rockchip,pins = <2 5 RK_FUNC_1 &pcfg_pull_up>, + <2 6 RK_FUNC_1 &pcfg_pull_up>, + <2 7 RK_FUNC_1 &pcfg_pull_up>, + <2 8 RK_FUNC_1 &pcfg_pull_up>; + }; + }; + + spi0 { + spi0_clk: spi0-clk { + rockchip,pins = <1 29 RK_FUNC_2 &pcfg_pull_up>; + }; + spi0_cs0: spi0-cs0 { + rockchip,pins = <1 24 RK_FUNC_3 &pcfg_pull_up>; + }; + spi0_cs1: spi0-cs1 { + rockchip,pins = <1 25 RK_FUNC_3 &pcfg_pull_up>; + }; + spi0_tx: spi0-tx { + rockchip,pins = <1 23 RK_FUNC_3 &pcfg_pull_up>; + }; + spi0_rx: spi0-rx { + rockchip,pins = <1 22 RK_FUNC_3 &pcfg_pull_up>; + }; + }; + + spi1 { + spi1_clk: spi1-clk { + rockchip,pins = <1 14 RK_FUNC_2 &pcfg_pull_up>; + }; + spi1_cs0: spi1-cs0 { + rockchip,pins = <1 15 RK_FUNC_2 &pcfg_pull_up>; + }; + spi1_cs1: spi1-cs1 { + rockchip,pins = <3 28 RK_FUNC_2 &pcfg_pull_up>; + }; + spi1_rx: spi1-rx { + rockchip,pins = <1 16 RK_FUNC_2 &pcfg_pull_up>; + }; + spi1_tx: spi1-tx { + rockchip,pins = <1 17 RK_FUNC_2 &pcfg_pull_up>; + }; + }; + + spi2 { + spi2_clk: spi2-clk { + rockchip,pins = <0 12 RK_FUNC_2 &pcfg_pull_up>; + }; + spi2_cs0: spi2-cs0 { + rockchip,pins = <0 13 RK_FUNC_2 &pcfg_pull_up>; + }; + spi2_rx: spi2-rx { + rockchip,pins = <0 10 RK_FUNC_2 &pcfg_pull_up>; + }; + spi2_tx: spi2-tx { + rockchip,pins = <0 11 RK_FUNC_2 &pcfg_pull_up>; + }; + }; + + uart0 { + uart0_xfer: uart0-xfer { + rockchip,pins = <2 24 RK_FUNC_1 &pcfg_pull_up>, + <2 25 RK_FUNC_1 &pcfg_pull_none>; + }; + + uart0_cts: uart0-cts { + rockchip,pins = <2 26 RK_FUNC_1 &pcfg_pull_none>; + }; + + uart0_rts: uart0-rts { + rockchip,pins = <2 27 RK_FUNC_1 &pcfg_pull_none>; + }; + }; + + uart1 { + uart1_xfer: uart1-xfer { + rockchip,pins = <0 20 RK_FUNC_3 &pcfg_pull_up>, + <0 21 RK_FUNC_3 &pcfg_pull_none>; + }; + + uart1_cts: uart1-cts { + rockchip,pins = <0 22 RK_FUNC_3 &pcfg_pull_none>; + }; + + uart1_rts: uart1-rts { + rockchip,pins = <0 23 RK_FUNC_3 &pcfg_pull_none>; + }; + }; + + uart2 { + uart2_xfer: uart2-xfer { + rockchip,pins = <2 6 RK_FUNC_2 &pcfg_pull_up>, + <2 5 RK_FUNC_2 &pcfg_pull_none>; + }; + /* no rts / cts for uart2 */ + }; + + uart3 { + uart3_xfer: uart3-xfer { + rockchip,pins = <3 29 RK_FUNC_2 &pcfg_pull_up>, + <3 30 RK_FUNC_3 &pcfg_pull_none>; + }; + + uart3_cts: uart3-cts { + rockchip,pins = <3 16 RK_FUNC_2 &pcfg_pull_none>; + }; + + uart3_rts: uart3-rts { + rockchip,pins = <3 17 RK_FUNC_2 &pcfg_pull_none>; + }; + }; + + uart4 { + uart4_xfer: uart4-xfer { + rockchip,pins = <0 27 RK_FUNC_3 &pcfg_pull_up>, + <0 26 RK_FUNC_3 &pcfg_pull_none>; + }; + + uart4_cts: uart4-cts { + rockchip,pins = <0 24 RK_FUNC_3 &pcfg_pull_none>; + }; + + uart4_rts: uart4-rts { + rockchip,pins = <0 25 RK_FUNC_3 &pcfg_pull_none>; + }; + }; + }; +}; diff --git a/kernel/arch/arm64/boot/dts/skeleton.dtsi b/kernel/arch/arm64/boot/dts/skeleton.dtsi deleted file mode 100644 index 38ead821b..000000000 --- a/kernel/arch/arm64/boot/dts/skeleton.dtsi +++ /dev/null @@ -1,13 +0,0 @@ -/* - * Skeleton device tree; the bare minimum needed to boot; just include and - * add a compatible value. The bootloader will typically populate the memory - * node. - */ - -/ { - #address-cells = <2>; - #size-cells = <1>; - chosen { }; - aliases { }; - memory { device_type = "memory"; reg = <0 0 0>; }; -}; diff --git a/kernel/arch/arm64/boot/dts/sprd/sc9836.dtsi b/kernel/arch/arm64/boot/dts/sprd/sc9836.dtsi index ee34e1a36..63894c456 100644 --- a/kernel/arch/arm64/boot/dts/sprd/sc9836.dtsi +++ b/kernel/arch/arm64/boot/dts/sprd/sc9836.dtsi @@ -16,28 +16,28 @@ #address-cells = <2>; #size-cells = <0>; - cpu@0 { + cpu0: cpu@0 { device_type = "cpu"; compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x0>; enable-method = "psci"; }; - cpu@1 { + cpu1: cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x1>; enable-method = "psci"; }; - cpu@2 { + cpu2: cpu@2 { device_type = "cpu"; compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x2>; enable-method = "psci"; }; - cpu@3 { + cpu3: cpu@3 { device_type = "cpu"; compatible = "arm,cortex-a53", "arm,armv8"; reg = <0x0 0x3>; @@ -75,14 +75,103 @@ }; }; - /* funnel input port 0~3 is reserved for ETMs */ + /* funnel input port 0-4 */ port@1 { + reg = <0>; + funnel_in_port0: endpoint { + slave-mode; + remote-endpoint = <&etm0_out>; + }; + }; + + port@2 { + reg = <1>; + funnel_in_port1: endpoint { + slave-mode; + remote-endpoint = <&etm1_out>; + }; + }; + + port@3 { + reg = <2>; + funnel_in_port2: endpoint { + slave-mode; + remote-endpoint = <&etm2_out>; + }; + }; + + port@4 { + reg = <3>; + funnel_in_port3: endpoint { + slave-mode; + remote-endpoint = <&etm3_out>; + }; + }; + + port@5 { reg = <4>; funnel_in_port4: endpoint { slave-mode; remote-endpoint = <&stm_out>; }; }; + /* Other input ports aren't connected to anyone */ + }; + }; + + etm@10440000 { + compatible = "arm,coresight-etm4x", "arm,primecell"; + reg = <0 0x10440000 0 0x1000>; + + cpu = <&cpu0>; + clocks = <&clk26mhz>; + clock-names = "apb_pclk"; + port { + etm0_out: endpoint { + remote-endpoint = <&funnel_in_port0>; + }; + }; + }; + + etm@10540000 { + compatible = "arm,coresight-etm4x", "arm,primecell"; + reg = <0 0x10540000 0 0x1000>; + + cpu = <&cpu1>; + clocks = <&clk26mhz>; + clock-names = "apb_pclk"; + port { + etm1_out: endpoint { + remote-endpoint = <&funnel_in_port1>; + }; + }; + }; + + etm@10640000 { + compatible = "arm,coresight-etm4x", "arm,primecell"; + reg = <0 0x10640000 0 0x1000>; + + cpu = <&cpu2>; + clocks = <&clk26mhz>; + clock-names = "apb_pclk"; + port { + etm2_out: endpoint { + remote-endpoint = <&funnel_in_port2>; + }; + }; + }; + + etm@10740000 { + compatible = "arm,coresight-etm4x", "arm,primecell"; + reg = <0 0x10740000 0 0x1000>; + + cpu = <&cpu3>; + clocks = <&clk26mhz>; + clock-names = "apb_pclk"; + port { + etm3_out: endpoint { + remote-endpoint = <&funnel_in_port3>; + }; }; }; diff --git a/kernel/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts b/kernel/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts index 0a3f40ecd..ce5d84825 100644 --- a/kernel/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts +++ b/kernel/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts @@ -32,6 +32,10 @@ }; }; +&can0 { + status = "okay"; +}; + &gem0 { status = "okay"; phy-handle = <&phy0>; @@ -42,6 +46,91 @@ }; }; +&gpio { + status = "okay"; +}; + +&i2c0 { + status = "okay"; + clock-frequency = <400000>; + eeprom@54 { + compatible = "at,24c64"; + reg = <0x54>; + }; +}; + +&i2c1 { + status = "okay"; + clock-frequency = <400000>; + eeprom@55 { + compatible = "at,24c64"; + reg = <0x55>; + }; +}; + +&sata { + status = "okay"; + ceva,broken-gen2; +}; + +&sdhci0 { + status = "okay"; +}; + +&sdhci1 { + status = "okay"; +}; + +&spi0 { + status = "okay"; + num-cs = <1>; + spi0_flash0: spi0_flash0@0 { + compatible = "m25p80"; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <50000000>; + reg = <0>; + + spi0_flash0@00000000 { + label = "spi0_flash0"; + reg = <0x0 0x100000>; + }; + }; +}; + +&spi1 { + status = "okay"; + num-cs = <1>; + spi1_flash0: spi1_flash0@0 { + compatible = "m25p80"; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <50000000>; + reg = <0>; + + spi1_flash0@00000000 { + label = "spi1_flash0"; + reg = <0x0 0x100000>; + }; + }; +}; + &uart0 { status = "okay"; }; + +&usb0 { + status = "okay"; + dr_mode = "peripheral"; + maximum-speed = "high-speed"; +}; + +&usb1 { + status = "okay"; + dr_mode = "host"; + maximum-speed = "high-speed"; +}; + +&watchdog0 { + status = "okay"; +}; diff --git a/kernel/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/kernel/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 11e0b0004..857eda5c7 100644 --- a/kernel/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/kernel/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -96,74 +96,38 @@ #size-cells = <1>; ranges; - misc_clk: misc_clk { - compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <25000000>; - }; - - ttc0: timer@ff110000 { - compatible = "cdns,ttc"; - status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 36 4>, <0 37 4>, <0 38 4>; - reg = <0x0 0xff110000 0x1000>; - clocks = <&misc_clk>; - timer-width = <32>; - }; - - ttc1: timer@ff120000 { - compatible = "cdns,ttc"; - status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 39 4>, <0 40 4>, <0 41 4>; - reg = <0x0 0xff120000 0x1000>; - clocks = <&misc_clk>; - timer-width = <32>; - }; - - ttc2: timer@ff130000 { - compatible = "cdns,ttc"; - status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 42 4>, <0 43 4>, <0 44 4>; - reg = <0x0 0xff130000 0x1000>; - clocks = <&misc_clk>; - timer-width = <32>; - }; - - ttc3: timer@ff140000 { - compatible = "cdns,ttc"; + can0: can@ff060000 { + compatible = "xlnx,zynq-can-1.0"; status = "disabled"; + clocks = <&misc_clk &misc_clk>; + clock-names = "can_clk", "pclk"; + reg = <0x0 0xff060000 0x1000>; + interrupts = <0 23 4>; interrupt-parent = <&gic>; - interrupts = <0 45 4>, <0 46 4>, <0 47 4>; - reg = <0x0 0xff140000 0x1000>; - clocks = <&misc_clk>; - timer-width = <32>; + tx-fifo-depth = <0x40>; + rx-fifo-depth = <0x40>; }; - uart0: serial@ff000000 { - compatible = "cdns,uart-r1p8"; + can1: can@ff070000 { + compatible = "xlnx,zynq-can-1.0"; status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 21 4>; - reg = <0x0 0xff000000 0x1000>; - clock-names = "uart_clk", "pclk"; clocks = <&misc_clk &misc_clk>; + clock-names = "can_clk", "pclk"; + reg = <0x0 0xff070000 0x1000>; + interrupts = <0 24 4>; + interrupt-parent = <&gic>; + tx-fifo-depth = <0x40>; + rx-fifo-depth = <0x40>; }; - uart1: serial@ff010000 { - compatible = "cdns,uart-r1p8"; - status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 22 4>; - reg = <0x0 0xff010000 0x1000>; - clock-names = "uart_clk", "pclk"; - clocks = <&misc_clk &misc_clk>; + misc_clk: misc_clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <25000000>; }; gpio: gpio@ff0a0000 { - compatible = "xlnx,zynq-gpio-1.0"; + compatible = "xlnx,zynqmp-gpio-1.0"; status = "disabled"; #gpio-cells = <0x2>; clocks = <&misc_clk>; @@ -220,30 +184,6 @@ #size-cells = <0>; }; - spi0: spi@ff040000 { - compatible = "cdns,spi-r1p6"; - status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 19 4>; - reg = <0x0 0xff040000 0x1000>; - clock-names = "ref_clk", "pclk"; - clocks = <&misc_clk &misc_clk>; - #address-cells = <1>; - #size-cells = <0>; - }; - - spi1: spi@ff050000 { - compatible = "cdns,spi-r1p6"; - status = "disabled"; - interrupt-parent = <&gic>; - interrupts = <0 20 4>; - reg = <0x0 0xff050000 0x1000>; - clock-names = "ref_clk", "pclk"; - clocks = <&misc_clk &misc_clk>; - #address-cells = <1>; - #size-cells = <0>; - }; - i2c_clk: i2c_clk { compatible = "fixed-clock"; #clock-cells = <0x0>; @@ -272,6 +212,21 @@ #size-cells = <0>; }; + sata_clk: sata_clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <75000000>; + }; + + sata: ahci@fd0c0000 { + compatible = "ceva,ahci-1v84"; + status = "disabled"; + reg = <0x0 0xfd0c0000 0x2000>; + interrupt-parent = <&gic>; + interrupts = <0 133 4>; + clocks = <&sata_clk>; + }; + sdhci0: sdhci@ff160000 { compatible = "arasan,sdhci-8.9a"; status = "disabled"; @@ -292,6 +247,122 @@ clocks = <&misc_clk>, <&misc_clk>; }; + smmu: smmu@fd800000 { + compatible = "arm,mmu-500"; + reg = <0x0 0xfd800000 0x20000>; + #global-interrupts = <1>; + interrupt-parent = <&gic>; + interrupts = <0 157 4>, + <0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>, + <0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>, + <0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>, + <0 157 4>, <0 157 4>, <0 157 4>, <0 157 4>; + }; + + spi0: spi@ff040000 { + compatible = "cdns,spi-r1p6"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 19 4>; + reg = <0x0 0xff040000 0x1000>; + clock-names = "ref_clk", "pclk"; + clocks = <&misc_clk &misc_clk>; + #address-cells = <1>; + #size-cells = <0>; + }; + + spi1: spi@ff050000 { + compatible = "cdns,spi-r1p6"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 20 4>; + reg = <0x0 0xff050000 0x1000>; + clock-names = "ref_clk", "pclk"; + clocks = <&misc_clk &misc_clk>; + #address-cells = <1>; + #size-cells = <0>; + }; + + ttc0: timer@ff110000 { + compatible = "cdns,ttc"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 36 4>, <0 37 4>, <0 38 4>; + reg = <0x0 0xff110000 0x1000>; + clocks = <&misc_clk>; + timer-width = <32>; + }; + + ttc1: timer@ff120000 { + compatible = "cdns,ttc"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 39 4>, <0 40 4>, <0 41 4>; + reg = <0x0 0xff120000 0x1000>; + clocks = <&misc_clk>; + timer-width = <32>; + }; + + ttc2: timer@ff130000 { + compatible = "cdns,ttc"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 42 4>, <0 43 4>, <0 44 4>; + reg = <0x0 0xff130000 0x1000>; + clocks = <&misc_clk>; + timer-width = <32>; + }; + + ttc3: timer@ff140000 { + compatible = "cdns,ttc"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 45 4>, <0 46 4>, <0 47 4>; + reg = <0x0 0xff140000 0x1000>; + clocks = <&misc_clk>; + timer-width = <32>; + }; + + uart0: serial@ff000000 { + compatible = "cdns,uart-r1p8"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 21 4>; + reg = <0x0 0xff000000 0x1000>; + clock-names = "uart_clk", "pclk"; + clocks = <&misc_clk &misc_clk>; + }; + + uart1: serial@ff010000 { + compatible = "cdns,uart-r1p8"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 22 4>; + reg = <0x0 0xff010000 0x1000>; + clock-names = "uart_clk", "pclk"; + clocks = <&misc_clk &misc_clk>; + }; + + usb0: usb@fe200000 { + compatible = "snps,dwc3"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 65 4>; + reg = <0x0 0xfe200000 0x40000>; + clock-names = "clk_xin", "clk_ahb"; + clocks = <&misc_clk>, <&misc_clk>; + }; + + usb1: usb@fe300000 { + compatible = "snps,dwc3"; + status = "disabled"; + interrupt-parent = <&gic>; + interrupts = <0 70 4>; + reg = <0x0 0xfe300000 0x40000>; + clock-names = "clk_xin", "clk_ahb"; + clocks = <&misc_clk>, <&misc_clk>; + }; + watchdog0: watchdog@fd4d0000 { compatible = "cdns,wdt-r1p2"; status = "disabled"; diff --git a/kernel/arch/arm64/configs/defconfig b/kernel/arch/arm64/configs/defconfig index 2ed7449d9..bdd7aa358 100644 --- a/kernel/arch/arm64/configs/defconfig +++ b/kernel/arch/arm64/configs/defconfig @@ -31,10 +31,15 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set +CONFIG_ARCH_BCM_IPROC=y +CONFIG_ARCH_BERLIN=y CONFIG_ARCH_EXYNOS7=y -CONFIG_ARCH_FSL_LS2085A=y +CONFIG_ARCH_LAYERSCAPE=y +CONFIG_ARCH_HISI=y CONFIG_ARCH_MEDIATEK=y +CONFIG_ARCH_ROCKCHIP=y CONFIG_ARCH_SEATTLE=y +CONFIG_ARCH_STRATIX10=y CONFIG_ARCH_TEGRA=y CONFIG_ARCH_TEGRA_132_SOC=y CONFIG_ARCH_QCOM=y @@ -45,8 +50,10 @@ CONFIG_ARCH_XGENE=y CONFIG_ARCH_ZYNQMP=y CONFIG_PCI=y CONFIG_PCI_MSI=y +CONFIG_PCI_HOST_GENERIC=y CONFIG_PCI_XGENE=y CONFIG_SMP=y +CONFIG_SCHED_MC=y CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y @@ -82,6 +89,7 @@ CONFIG_BLK_DEV_SD=y CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_AHCI_CEVA=y CONFIG_AHCI_XGENE=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y @@ -94,14 +102,20 @@ CONFIG_SMC91X=y CONFIG_SMSC911X=y # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y +CONFIG_KEYBOARD_GPIO=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_AMBAKMI=y CONFIG_LEGACY_PTY_COUNT=16 CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y CONFIG_SERIAL_8250_MT6577=y CONFIG_SERIAL_AMBA_PL011=y CONFIG_SERIAL_AMBA_PL011_CONSOLE=y +CONFIG_SERIAL_SAMSUNG=y +CONFIG_SERIAL_SAMSUNG_UARTS_4=y +CONFIG_SERIAL_SAMSUNG_UARTS=4 +CONFIG_SERIAL_SAMSUNG_CONSOLE=y CONFIG_SERIAL_MSM=y CONFIG_SERIAL_MSM_CONSOLE=y CONFIG_SERIAL_OF_PLATFORM=y @@ -109,8 +123,11 @@ CONFIG_SERIAL_XILINX_PS_UART=y CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y CONFIG_VIRTIO_CONSOLE=y # CONFIG_HW_RANDOM is not set +CONFIG_I2C=y +CONFIG_I2C_QUP=y CONFIG_SPI=y CONFIG_SPI_PL022=y +CONFIG_SPI_QUP=y CONFIG_PINCTRL_MSM8916=y CONFIG_GPIO_PL061=y CONFIG_GPIO_XGENE=y @@ -119,6 +136,7 @@ CONFIG_POWER_RESET_SYSCON=y # CONFIG_HWMON is not set CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y +CONFIG_REGULATOR_QCOM_SMD_RPM=y CONFIG_FB=y CONFIG_FB_ARMCLCD=y CONFIG_FRAMEBUFFER_CONSOLE=y @@ -138,15 +156,31 @@ CONFIG_MMC_ARMMMCI=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SPI=y +CONFIG_MMC_DW=y +CONFIG_MMC_DW_IDMAC=y +CONFIG_MMC_DW_PLTFM=y +CONFIG_MMC_DW_EXYNOS=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_SYSCON=y +CONFIG_LEDS_TRIGGERS=y +CONFIG_LEDS_TRIGGER_HEARTBEAT=y +CONFIG_LEDS_TRIGGER_CPU=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_EFI=y CONFIG_RTC_DRV_XGENE=y +CONFIG_DMADEVICES=y +CONFIG_QCOM_BAM_DMA=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_MMIO=y CONFIG_COMMON_CLK_QCOM=y CONFIG_MSM_GCC_8916=y +CONFIG_HWSPINLOCK_QCOM=y # CONFIG_IOMMU_SUPPORT is not set +CONFIG_QCOM_SMEM=y +CONFIG_QCOM_SMD=y +CONFIG_QCOM_SMD_RPM=y CONFIG_PHY_XGENE=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y @@ -180,6 +214,7 @@ CONFIG_LOCKUP_DETECTOR=y # CONFIG_SCHED_DEBUG is not set # CONFIG_DEBUG_PREEMPT is not set # CONFIG_FTRACE is not set +CONFIG_MEMTEST=y CONFIG_SECURITY=y CONFIG_CRYPTO_ANSI_CPRNG=y CONFIG_ARM64_CRYPTO=y @@ -189,3 +224,4 @@ CONFIG_CRYPTO_GHASH_ARM64_CE=y CONFIG_CRYPTO_AES_ARM64_CE_CCM=y CONFIG_CRYPTO_AES_ARM64_CE_BLK=y CONFIG_CRYPTO_AES_ARM64_NEON_BLK=y +CONFIG_CRYPTO_CRC32_ARM64=y diff --git a/kernel/arch/arm64/crypto/aes-ce-ccm-glue.c b/kernel/arch/arm64/crypto/aes-ce-ccm-glue.c index 6c348df5b..f4bf2f2a0 100644 --- a/kernel/arch/arm64/crypto/aes-ce-ccm-glue.c +++ b/kernel/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include "aes-ce-setkey.h" @@ -124,7 +124,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[]) ce_aes_ccm_auth_data(mac, (u8 *)<ag, ltag.len, &macp, ctx->key_enc, num_rounds(ctx)); - scatterwalk_start(&walk, req->assoc); + scatterwalk_start(&walk, req->src); do { u32 n = scatterwalk_clamp(&walk, len); @@ -151,6 +151,10 @@ static int ccm_encrypt(struct aead_request *req) struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead); struct blkcipher_desc desc = { .info = req->iv }; struct blkcipher_walk walk; + struct scatterlist srcbuf[2]; + struct scatterlist dstbuf[2]; + struct scatterlist *src; + struct scatterlist *dst; u8 __aligned(8) mac[AES_BLOCK_SIZE]; u8 buf[AES_BLOCK_SIZE]; u32 len = req->cryptlen; @@ -168,7 +172,12 @@ static int ccm_encrypt(struct aead_request *req) /* preserve the original iv for the final round */ memcpy(buf, req->iv, AES_BLOCK_SIZE); - blkcipher_walk_init(&walk, req->dst, req->src, len); + src = scatterwalk_ffwd(srcbuf, req->src, req->assoclen); + dst = src; + if (req->src != req->dst) + dst = scatterwalk_ffwd(dstbuf, req->dst, req->assoclen); + + blkcipher_walk_init(&walk, dst, src, len); err = blkcipher_aead_walk_virt_block(&desc, &walk, aead, AES_BLOCK_SIZE); @@ -194,7 +203,7 @@ static int ccm_encrypt(struct aead_request *req) return err; /* copy authtag to end of dst */ - scatterwalk_map_and_copy(mac, req->dst, req->cryptlen, + scatterwalk_map_and_copy(mac, dst, req->cryptlen, crypto_aead_authsize(aead), 1); return 0; @@ -207,6 +216,10 @@ static int ccm_decrypt(struct aead_request *req) unsigned int authsize = crypto_aead_authsize(aead); struct blkcipher_desc desc = { .info = req->iv }; struct blkcipher_walk walk; + struct scatterlist srcbuf[2]; + struct scatterlist dstbuf[2]; + struct scatterlist *src; + struct scatterlist *dst; u8 __aligned(8) mac[AES_BLOCK_SIZE]; u8 buf[AES_BLOCK_SIZE]; u32 len = req->cryptlen - authsize; @@ -224,7 +237,12 @@ static int ccm_decrypt(struct aead_request *req) /* preserve the original iv for the final round */ memcpy(buf, req->iv, AES_BLOCK_SIZE); - blkcipher_walk_init(&walk, req->dst, req->src, len); + src = scatterwalk_ffwd(srcbuf, req->src, req->assoclen); + dst = src; + if (req->src != req->dst) + dst = scatterwalk_ffwd(dstbuf, req->dst, req->assoclen); + + blkcipher_walk_init(&walk, dst, src, len); err = blkcipher_aead_walk_virt_block(&desc, &walk, aead, AES_BLOCK_SIZE); @@ -250,44 +268,42 @@ static int ccm_decrypt(struct aead_request *req) return err; /* compare calculated auth tag with the stored one */ - scatterwalk_map_and_copy(buf, req->src, req->cryptlen - authsize, + scatterwalk_map_and_copy(buf, src, req->cryptlen - authsize, authsize, 0); - if (memcmp(mac, buf, authsize)) + if (crypto_memneq(mac, buf, authsize)) return -EBADMSG; return 0; } -static struct crypto_alg ccm_aes_alg = { - .cra_name = "ccm(aes)", - .cra_driver_name = "ccm-aes-ce", - .cra_priority = 300, - .cra_flags = CRYPTO_ALG_TYPE_AEAD, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct crypto_aes_ctx), - .cra_alignmask = 7, - .cra_type = &crypto_aead_type, - .cra_module = THIS_MODULE, - .cra_aead = { - .ivsize = AES_BLOCK_SIZE, - .maxauthsize = AES_BLOCK_SIZE, - .setkey = ccm_setkey, - .setauthsize = ccm_setauthsize, - .encrypt = ccm_encrypt, - .decrypt = ccm_decrypt, - } +static struct aead_alg ccm_aes_alg = { + .base = { + .cra_name = "ccm(aes)", + .cra_driver_name = "ccm-aes-ce", + .cra_priority = 300, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_alignmask = 7, + .cra_module = THIS_MODULE, + }, + .ivsize = AES_BLOCK_SIZE, + .maxauthsize = AES_BLOCK_SIZE, + .setkey = ccm_setkey, + .setauthsize = ccm_setauthsize, + .encrypt = ccm_encrypt, + .decrypt = ccm_decrypt, }; static int __init aes_mod_init(void) { if (!(elf_hwcap & HWCAP_AES)) return -ENODEV; - return crypto_register_alg(&ccm_aes_alg); + return crypto_register_aead(&ccm_aes_alg); } static void __exit aes_mod_exit(void) { - crypto_unregister_alg(&ccm_aes_alg); + crypto_unregister_aead(&ccm_aes_alg); } module_init(aes_mod_init); diff --git a/kernel/arch/arm64/crypto/aes-ce-cipher.c b/kernel/arch/arm64/crypto/aes-ce-cipher.c index ce47792a9..f7bd9bf0b 100644 --- a/kernel/arch/arm64/crypto/aes-ce-cipher.c +++ b/kernel/arch/arm64/crypto/aes-ce-cipher.c @@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey); static struct crypto_alg aes_alg = { .cra_name = "aes", .cra_driver_name = "aes-ce", - .cra_priority = 300, + .cra_priority = 250, .cra_flags = CRYPTO_ALG_TYPE_CIPHER, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx), diff --git a/kernel/arch/arm64/include/asm/Kbuild b/kernel/arch/arm64/include/asm/Kbuild index 55103e50c..70fd9ffb5 100644 --- a/kernel/arch/arm64/include/asm/Kbuild +++ b/kernel/arch/arm64/include/asm/Kbuild @@ -25,6 +25,7 @@ generic-y += kvm_para.h generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h +generic-y += mm-arch-hooks.h generic-y += mman.h generic-y += msgbuf.h generic-y += msi.h @@ -35,7 +36,6 @@ generic-y += poll.h generic-y += preempt.h generic-y += resource.h generic-y += rwsem.h -generic-y += scatterlist.h generic-y += sections.h generic-y += segment.h generic-y += sembuf.h diff --git a/kernel/arch/arm64/include/asm/acpi.h b/kernel/arch/arm64/include/asm/acpi.h index 59c05d8ea..caafd63b8 100644 --- a/kernel/arch/arm64/include/asm/acpi.h +++ b/kernel/arch/arm64/include/asm/acpi.h @@ -13,11 +13,19 @@ #define _ASM_ACPI_H #include -#include +#include #include #include +/* Macros for consistency checks of the GICC subtable of MADT */ +#define ACPI_MADT_GICC_LENGTH \ + (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) + +#define BAD_MADT_GICC_ENTRY(entry, end) \ + (!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) || \ + (entry)->header.length != ACPI_MADT_GICC_LENGTH) + /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI /* ACPI table mapping after acpi_gbl_permanent_mmap is set */ @@ -39,18 +47,6 @@ extern int acpi_disabled; extern int acpi_noirq; extern int acpi_pci_disabled; -/* 1 to indicate PSCI 0.2+ is implemented */ -static inline bool acpi_psci_present(void) -{ - return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT; -} - -/* 1 to indicate HVC must be used instead of SMC as the PSCI conduit */ -static inline bool acpi_psci_use_hvc(void) -{ - return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC; -} - static inline void disable_acpi(void) { acpi_disabled = 1; @@ -88,9 +84,16 @@ static inline void arch_fix_phys_package_id(int num, u32 slot) { } void __init acpi_init_cpus(void); #else -static inline bool acpi_psci_present(void) { return false; } -static inline bool acpi_psci_use_hvc(void) { return false; } static inline void acpi_init_cpus(void) { } #endif /* CONFIG_ACPI */ +static inline const char *acpi_get_enable_method(int cpu) +{ + return acpi_psci_present() ? "psci" : NULL; +} + +#ifdef CONFIG_ACPI_APEI +pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr); +#endif + #endif /*_ASM_ACPI_H*/ diff --git a/kernel/arch/arm64/include/asm/alternative-asm.h b/kernel/arch/arm64/include/asm/alternative-asm.h deleted file mode 100644 index 919a67855..000000000 --- a/kernel/arch/arm64/include/asm/alternative-asm.h +++ /dev/null @@ -1,29 +0,0 @@ -#ifndef __ASM_ALTERNATIVE_ASM_H -#define __ASM_ALTERNATIVE_ASM_H - -#ifdef __ASSEMBLY__ - -.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len - .word \orig_offset - . - .word \alt_offset - . - .hword \feature - .byte \orig_len - .byte \alt_len -.endm - -.macro alternative_insn insn1 insn2 cap -661: \insn1 -662: .pushsection .altinstructions, "a" - altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f - .popsection - .pushsection .altinstr_replacement, "ax" -663: \insn2 -664: .popsection - .if ((664b-663b) != (662b-661b)) - .error "Alternatives instruction length mismatch" - .endif -.endm - -#endif /* __ASSEMBLY__ */ - -#endif /* __ASM_ALTERNATIVE_ASM_H */ diff --git a/kernel/arch/arm64/include/asm/alternative.h b/kernel/arch/arm64/include/asm/alternative.h index d261f01e2..d56ec0715 100644 --- a/kernel/arch/arm64/include/asm/alternative.h +++ b/kernel/arch/arm64/include/asm/alternative.h @@ -1,6 +1,10 @@ #ifndef __ASM_ALTERNATIVE_H #define __ASM_ALTERNATIVE_H +#ifndef __ASSEMBLY__ + +#include +#include #include #include #include @@ -13,7 +17,7 @@ struct alt_instr { u8 alt_len; /* size of new instruction(s), <= orig_len */ }; -void apply_alternatives_all(void); +void __init apply_alternatives_all(void); void apply_alternatives(void *start, size_t length); void free_alternatives_memory(void); @@ -24,8 +28,22 @@ void free_alternatives_memory(void); " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ -/* alternative assembly primitive: */ -#define ALTERNATIVE(oldinstr, newinstr, feature) \ +/* + * alternative assembly primitive: + * + * If any of these .org directive fail, it means that insn1 and insn2 + * don't have the same length. This used to be written as + * + * .if ((664b-663b) != (662b-661b)) + * .error "Alternatives instruction length mismatch" + * .endif + * + * but most assemblers die if insn1 or insn2 have a .inst. This should + * be fixed in a binutils release posterior to 2.25.51.0.2 (anything + * containing commit 4e4d08cf7399b606 or c1baaddf8861). + */ +#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled) \ + ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ @@ -37,8 +55,98 @@ void free_alternatives_memory(void); newinstr "\n" \ "664:\n\t" \ ".popsection\n\t" \ - ".if ((664b-663b) != (662b-661b))\n\t" \ - " .error \"Alternatives instruction length mismatch\"\n\t"\ + ".org . - (664b-663b) + (662b-661b)\n\t" \ + ".org . - (662b-661b) + (664b-663b)\n" \ ".endif\n" +#define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ + __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) + +#else + +.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len + .word \orig_offset - . + .word \alt_offset - . + .hword \feature + .byte \orig_len + .byte \alt_len +.endm + +.macro alternative_insn insn1, insn2, cap, enable = 1 + .if \enable +661: \insn1 +662: .pushsection .altinstructions, "a" + altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f + .popsection + .pushsection .altinstr_replacement, "ax" +663: \insn2 +664: .popsection + .org . - (664b-663b) + (662b-661b) + .org . - (662b-661b) + (664b-663b) + .endif +.endm + +/* + * Begin an alternative code sequence. + * + * The code that follows this macro will be assembled and linked as + * normal. There are no restrictions on this code. + */ +.macro alternative_if_not cap, enable = 1 + .if \enable + .pushsection .altinstructions, "a" + altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f + .popsection +661: + .endif +.endm + +/* + * Provide the alternative code sequence. + * + * The code that follows this macro is assembled into a special + * section to be used for dynamic patching. Code that follows this + * macro must: + * + * 1. Be exactly the same length (in bytes) as the default code + * sequence. + * + * 2. Not contain a branch target that is used outside of the + * alternative sequence it is defined in (branches into an + * alternative sequence are not fixed up). + */ +.macro alternative_else, enable = 1 + .if \enable +662: .pushsection .altinstr_replacement, "ax" +663: + .endif +.endm + +/* + * Complete an alternative code sequence. + */ +.macro alternative_endif, enable = 1 + .if \enable +664: .popsection + .org . - (664b-663b) + (662b-661b) + .org . - (662b-661b) + (664b-663b) + .endif +.endm + +#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ + alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) + + +#endif /* __ASSEMBLY__ */ + +/* + * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature)); + * + * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature, CONFIG_FOO)); + * N.B. If CONFIG_FOO is specified, but not selected, the whole block + * will be omitted, including oldinstr. + */ +#define ALTERNATIVE(oldinstr, newinstr, ...) \ + _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) + #endif /* __ASM_ALTERNATIVE_H */ diff --git a/kernel/arch/arm64/include/asm/arch_gicv3.h b/kernel/arch/arm64/include/asm/arch_gicv3.h new file mode 100644 index 000000000..2731d3b25 --- /dev/null +++ b/kernel/arch/arm64/include/asm/arch_gicv3.h @@ -0,0 +1,171 @@ +/* + * arch/arm64/include/asm/arch_gicv3.h + * + * Copyright (C) 2015 ARM Ltd. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#ifndef __ASM_ARCH_GICV3_H +#define __ASM_ARCH_GICV3_H + +#include + +#define ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1) +#define ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1) +#define ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0) +#define ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5) +#define ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) +#define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4) +#define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5) +#define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7) + +#define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5) + +/* + * System register definitions + */ +#define ICH_VSEIR_EL2 sys_reg(3, 4, 12, 9, 4) +#define ICH_HCR_EL2 sys_reg(3, 4, 12, 11, 0) +#define ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1) +#define ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2) +#define ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3) +#define ICH_ELSR_EL2 sys_reg(3, 4, 12, 11, 5) +#define ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7) + +#define __LR0_EL2(x) sys_reg(3, 4, 12, 12, x) +#define __LR8_EL2(x) sys_reg(3, 4, 12, 13, x) + +#define ICH_LR0_EL2 __LR0_EL2(0) +#define ICH_LR1_EL2 __LR0_EL2(1) +#define ICH_LR2_EL2 __LR0_EL2(2) +#define ICH_LR3_EL2 __LR0_EL2(3) +#define ICH_LR4_EL2 __LR0_EL2(4) +#define ICH_LR5_EL2 __LR0_EL2(5) +#define ICH_LR6_EL2 __LR0_EL2(6) +#define ICH_LR7_EL2 __LR0_EL2(7) +#define ICH_LR8_EL2 __LR8_EL2(0) +#define ICH_LR9_EL2 __LR8_EL2(1) +#define ICH_LR10_EL2 __LR8_EL2(2) +#define ICH_LR11_EL2 __LR8_EL2(3) +#define ICH_LR12_EL2 __LR8_EL2(4) +#define ICH_LR13_EL2 __LR8_EL2(5) +#define ICH_LR14_EL2 __LR8_EL2(6) +#define ICH_LR15_EL2 __LR8_EL2(7) + +#define __AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x) +#define ICH_AP0R0_EL2 __AP0Rx_EL2(0) +#define ICH_AP0R1_EL2 __AP0Rx_EL2(1) +#define ICH_AP0R2_EL2 __AP0Rx_EL2(2) +#define ICH_AP0R3_EL2 __AP0Rx_EL2(3) + +#define __AP1Rx_EL2(x) sys_reg(3, 4, 12, 9, x) +#define ICH_AP1R0_EL2 __AP1Rx_EL2(0) +#define ICH_AP1R1_EL2 __AP1Rx_EL2(1) +#define ICH_AP1R2_EL2 __AP1Rx_EL2(2) +#define ICH_AP1R3_EL2 __AP1Rx_EL2(3) + +#ifndef __ASSEMBLY__ + +#include +#include + +/* + * Low-level accessors + * + * These system registers are 32 bits, but we make sure that the compiler + * sets the GP register's most significant bits to 0 with an explicit cast. + */ + +static inline void gic_write_eoir(u32 irq) +{ + asm volatile("msr_s " __stringify(ICC_EOIR1_EL1) ", %0" : : "r" ((u64)irq)); + isb(); +} + +static inline void gic_write_dir(u32 irq) +{ + asm volatile("msr_s " __stringify(ICC_DIR_EL1) ", %0" : : "r" ((u64)irq)); + isb(); +} + +static inline u64 gic_read_iar_common(void) +{ + u64 irqstat; + + asm volatile("mrs_s %0, " __stringify(ICC_IAR1_EL1) : "=r" (irqstat)); + return irqstat; +} + +/* + * Cavium ThunderX erratum 23154 + * + * The gicv3 of ThunderX requires a modified version for reading the + * IAR status to ensure data synchronization (access to icc_iar1_el1 + * is not sync'ed before and after). + */ +static inline u64 gic_read_iar_cavium_thunderx(void) +{ + u64 irqstat; + + asm volatile( + "nop;nop;nop;nop\n\t" + "nop;nop;nop;nop\n\t" + "mrs_s %0, " __stringify(ICC_IAR1_EL1) "\n\t" + "nop;nop;nop;nop" + : "=r" (irqstat)); + mb(); + + return irqstat; +} + +static inline void gic_write_pmr(u32 val) +{ + asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" ((u64)val)); +} + +static inline void gic_write_ctlr(u32 val) +{ + asm volatile("msr_s " __stringify(ICC_CTLR_EL1) ", %0" : : "r" ((u64)val)); + isb(); +} + +static inline void gic_write_grpen1(u32 val) +{ + asm volatile("msr_s " __stringify(ICC_GRPEN1_EL1) ", %0" : : "r" ((u64)val)); + isb(); +} + +static inline void gic_write_sgi1r(u64 val) +{ + asm volatile("msr_s " __stringify(ICC_SGI1R_EL1) ", %0" : : "r" (val)); +} + +static inline u32 gic_read_sre(void) +{ + u64 val; + + asm volatile("mrs_s %0, " __stringify(ICC_SRE_EL1) : "=r" (val)); + return val; +} + +static inline void gic_write_sre(u32 val) +{ + asm volatile("msr_s " __stringify(ICC_SRE_EL1) ", %0" : : "r" ((u64)val)); + isb(); +} + +#define gic_read_typer(c) readq_relaxed(c) +#define gic_write_irouter(v, c) writeq_relaxed(v, c) + +#endif /* __ASSEMBLY__ */ +#endif /* __ASM_ARCH_GICV3_H */ diff --git a/kernel/arch/arm64/include/asm/assembler.h b/kernel/arch/arm64/include/asm/assembler.h index 144b64ad9..12eff928e 100644 --- a/kernel/arch/arm64/include/asm/assembler.h +++ b/kernel/arch/arm64/include/asm/assembler.h @@ -49,18 +49,6 @@ msr daifclr, #2 .endm -/* - * Save/disable and restore interrupts. - */ - .macro save_and_disable_irqs, olddaif - mrs \olddaif, daif - disable_irq - .endm - - .macro restore_irqs, olddaif - msr daif, \olddaif - .endm - /* * Enable and disable debug exceptions. */ @@ -103,9 +91,7 @@ * SMP data memory barrier */ .macro smp_dmb, opt -#ifdef CONFIG_SMP dmb \opt -#endif .endm #define USER(l, x...) \ @@ -207,4 +193,15 @@ lr .req x30 // link register str \src, [\tmp, :lo12:\sym] .endm +/* + * Annotate a function as position independent, i.e., safe to be called before + * the kernel virtual mapping is activated. + */ +#define ENDPIPROC(x) \ + .globl __pi_##x; \ + .type __pi_##x, %function; \ + .set __pi_##x, x; \ + .size __pi_##x, . - x; \ + ENDPROC(x) + #endif /* __ASM_ASSEMBLER_H */ diff --git a/kernel/arch/arm64/include/asm/atomic.h b/kernel/arch/arm64/include/asm/atomic.h index 7047051de..f3a3586a4 100644 --- a/kernel/arch/arm64/include/asm/atomic.h +++ b/kernel/arch/arm64/include/asm/atomic.h @@ -24,233 +24,127 @@ #include #include -#include - -#define ATOMIC_INIT(i) { (i) } +#include #ifdef __KERNEL__ -/* - * On ARM, ordinary assignment (str instruction) doesn't clear the local - * strex/ldrex monitor on some implementations. The reason we can use it for - * atomic_set() is the clrex or dummy strex done on every exception return. - */ -#define atomic_read(v) ACCESS_ONCE((v)->counter) -#define atomic_set(v,i) (((v)->counter) = (i)) - -/* - * AArch64 UP and SMP safe atomic ops. We use load exclusive and - * store exclusive to ensure that these are atomic. We may loop - * to ensure that the update happens. - */ - -#define ATOMIC_OP(op, asm_op) \ -static inline void atomic_##op(int i, atomic_t *v) \ -{ \ - unsigned long tmp; \ - int result; \ - \ - asm volatile("// atomic_" #op "\n" \ -"1: ldxr %w0, %2\n" \ -" " #asm_op " %w0, %w0, %w3\n" \ -" stxr %w1, %w0, %2\n" \ -" cbnz %w1, 1b" \ - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ -} \ +#define __ARM64_IN_ATOMIC_IMPL -#define ATOMIC_OP_RETURN(op, asm_op) \ -static inline int atomic_##op##_return(int i, atomic_t *v) \ -{ \ - unsigned long tmp; \ - int result; \ - \ - asm volatile("// atomic_" #op "_return\n" \ -"1: ldxr %w0, %2\n" \ -" " #asm_op " %w0, %w0, %w3\n" \ -" stlxr %w1, %w0, %2\n" \ -" cbnz %w1, 1b" \ - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ - : "memory"); \ - \ - smp_mb(); \ - return result; \ -} - -#define ATOMIC_OPS(op, asm_op) \ - ATOMIC_OP(op, asm_op) \ - ATOMIC_OP_RETURN(op, asm_op) - -ATOMIC_OPS(add, add) -ATOMIC_OPS(sub, sub) - -#undef ATOMIC_OPS -#undef ATOMIC_OP_RETURN -#undef ATOMIC_OP - -static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new) -{ - unsigned long tmp; - int oldval; - - smp_mb(); - - asm volatile("// atomic_cmpxchg\n" -"1: ldxr %w1, %2\n" -" cmp %w1, %w3\n" -" b.ne 2f\n" -" stxr %w0, %w4, %2\n" -" cbnz %w0, 1b\n" -"2:" - : "=&r" (tmp), "=&r" (oldval), "+Q" (ptr->counter) - : "Ir" (old), "r" (new) - : "cc"); - - smp_mb(); - return oldval; -} - -#define atomic_xchg(v, new) (xchg(&((v)->counter), new)) +#if defined(CONFIG_ARM64_LSE_ATOMICS) && defined(CONFIG_AS_LSE) +#include +#else +#include +#endif -static inline int __atomic_add_unless(atomic_t *v, int a, int u) -{ - int c, old; +#undef __ARM64_IN_ATOMIC_IMPL - c = atomic_read(v); - while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c) - c = old; - return c; -} +#include -#define atomic_inc(v) atomic_add(1, v) -#define atomic_dec(v) atomic_sub(1, v) +#define ___atomic_add_unless(v, a, u, sfx) \ +({ \ + typeof((v)->counter) c, old; \ + \ + c = atomic##sfx##_read(v); \ + while (c != (u) && \ + (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c) \ + c = old; \ + c; \ + }) -#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0) -#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0) -#define atomic_inc_return(v) (atomic_add_return(1, v)) -#define atomic_dec_return(v) (atomic_sub_return(1, v)) -#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0) +#define ATOMIC_INIT(i) { (i) } -#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0) +#define atomic_read(v) READ_ONCE((v)->counter) +#define atomic_set(v, i) WRITE_ONCE(((v)->counter), (i)) + +#define atomic_add_return_relaxed atomic_add_return_relaxed +#define atomic_add_return_acquire atomic_add_return_acquire +#define atomic_add_return_release atomic_add_return_release +#define atomic_add_return atomic_add_return + +#define atomic_inc_return_relaxed(v) atomic_add_return_relaxed(1, (v)) +#define atomic_inc_return_acquire(v) atomic_add_return_acquire(1, (v)) +#define atomic_inc_return_release(v) atomic_add_return_release(1, (v)) +#define atomic_inc_return(v) atomic_add_return(1, (v)) + +#define atomic_sub_return_relaxed atomic_sub_return_relaxed +#define atomic_sub_return_acquire atomic_sub_return_acquire +#define atomic_sub_return_release atomic_sub_return_release +#define atomic_sub_return atomic_sub_return + +#define atomic_dec_return_relaxed(v) atomic_sub_return_relaxed(1, (v)) +#define atomic_dec_return_acquire(v) atomic_sub_return_acquire(1, (v)) +#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v)) +#define atomic_dec_return(v) atomic_sub_return(1, (v)) + +#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) +#define atomic_xchg_acquire(v, new) xchg_acquire(&((v)->counter), (new)) +#define atomic_xchg_release(v, new) xchg_release(&((v)->counter), (new)) +#define atomic_xchg(v, new) xchg(&((v)->counter), (new)) + +#define atomic_cmpxchg_relaxed(v, old, new) \ + cmpxchg_relaxed(&((v)->counter), (old), (new)) +#define atomic_cmpxchg_acquire(v, old, new) \ + cmpxchg_acquire(&((v)->counter), (old), (new)) +#define atomic_cmpxchg_release(v, old, new) \ + cmpxchg_release(&((v)->counter), (old), (new)) +#define atomic_cmpxchg(v, old, new) cmpxchg(&((v)->counter), (old), (new)) + +#define atomic_inc(v) atomic_add(1, (v)) +#define atomic_dec(v) atomic_sub(1, (v)) +#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0) +#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0) +#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0) +#define atomic_add_negative(i, v) (atomic_add_return((i), (v)) < 0) +#define __atomic_add_unless(v, a, u) ___atomic_add_unless(v, a, u,) +#define atomic_andnot atomic_andnot /* * 64-bit atomic operations. */ -#define ATOMIC64_INIT(i) { (i) } - -#define atomic64_read(v) ACCESS_ONCE((v)->counter) -#define atomic64_set(v,i) (((v)->counter) = (i)) - -#define ATOMIC64_OP(op, asm_op) \ -static inline void atomic64_##op(long i, atomic64_t *v) \ -{ \ - long result; \ - unsigned long tmp; \ - \ - asm volatile("// atomic64_" #op "\n" \ -"1: ldxr %0, %2\n" \ -" " #asm_op " %0, %0, %3\n" \ -" stxr %w1, %0, %2\n" \ -" cbnz %w1, 1b" \ - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i)); \ -} \ - -#define ATOMIC64_OP_RETURN(op, asm_op) \ -static inline long atomic64_##op##_return(long i, atomic64_t *v) \ -{ \ - long result; \ - unsigned long tmp; \ - \ - asm volatile("// atomic64_" #op "_return\n" \ -"1: ldxr %0, %2\n" \ -" " #asm_op " %0, %0, %3\n" \ -" stlxr %w1, %0, %2\n" \ -" cbnz %w1, 1b" \ - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ - : "Ir" (i) \ - : "memory"); \ - \ - smp_mb(); \ - return result; \ -} - -#define ATOMIC64_OPS(op, asm_op) \ - ATOMIC64_OP(op, asm_op) \ - ATOMIC64_OP_RETURN(op, asm_op) - -ATOMIC64_OPS(add, add) -ATOMIC64_OPS(sub, sub) - -#undef ATOMIC64_OPS -#undef ATOMIC64_OP_RETURN -#undef ATOMIC64_OP - -static inline long atomic64_cmpxchg(atomic64_t *ptr, long old, long new) -{ - long oldval; - unsigned long res; - - smp_mb(); - - asm volatile("// atomic64_cmpxchg\n" -"1: ldxr %1, %2\n" -" cmp %1, %3\n" -" b.ne 2f\n" -" stxr %w0, %4, %2\n" -" cbnz %w0, 1b\n" -"2:" - : "=&r" (res), "=&r" (oldval), "+Q" (ptr->counter) - : "Ir" (old), "r" (new) - : "cc"); - - smp_mb(); - return oldval; -} - -#define atomic64_xchg(v, new) (xchg(&((v)->counter), new)) - -static inline long atomic64_dec_if_positive(atomic64_t *v) -{ - long result; - unsigned long tmp; - - asm volatile("// atomic64_dec_if_positive\n" -"1: ldxr %0, %2\n" -" subs %0, %0, #1\n" -" b.mi 2f\n" -" stlxr %w1, %0, %2\n" -" cbnz %w1, 1b\n" -" dmb ish\n" -"2:" - : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) - : - : "cc", "memory"); - - return result; -} - -static inline int atomic64_add_unless(atomic64_t *v, long a, long u) -{ - long c, old; - - c = atomic64_read(v); - while (c != u && (old = atomic64_cmpxchg((v), c, c + a)) != c) - c = old; - - return c != u; -} - -#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0) -#define atomic64_inc(v) atomic64_add(1LL, (v)) -#define atomic64_inc_return(v) atomic64_add_return(1LL, (v)) +#define ATOMIC64_INIT ATOMIC_INIT +#define atomic64_read atomic_read +#define atomic64_set atomic_set + +#define atomic64_add_return_relaxed atomic64_add_return_relaxed +#define atomic64_add_return_acquire atomic64_add_return_acquire +#define atomic64_add_return_release atomic64_add_return_release +#define atomic64_add_return atomic64_add_return + +#define atomic64_inc_return_relaxed(v) atomic64_add_return_relaxed(1, (v)) +#define atomic64_inc_return_acquire(v) atomic64_add_return_acquire(1, (v)) +#define atomic64_inc_return_release(v) atomic64_add_return_release(1, (v)) +#define atomic64_inc_return(v) atomic64_add_return(1, (v)) + +#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed +#define atomic64_sub_return_acquire atomic64_sub_return_acquire +#define atomic64_sub_return_release atomic64_sub_return_release +#define atomic64_sub_return atomic64_sub_return + +#define atomic64_dec_return_relaxed(v) atomic64_sub_return_relaxed(1, (v)) +#define atomic64_dec_return_acquire(v) atomic64_sub_return_acquire(1, (v)) +#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v)) +#define atomic64_dec_return(v) atomic64_sub_return(1, (v)) + +#define atomic64_xchg_relaxed atomic_xchg_relaxed +#define atomic64_xchg_acquire atomic_xchg_acquire +#define atomic64_xchg_release atomic_xchg_release +#define atomic64_xchg atomic_xchg + +#define atomic64_cmpxchg_relaxed atomic_cmpxchg_relaxed +#define atomic64_cmpxchg_acquire atomic_cmpxchg_acquire +#define atomic64_cmpxchg_release atomic_cmpxchg_release +#define atomic64_cmpxchg atomic_cmpxchg + +#define atomic64_inc(v) atomic64_add(1, (v)) +#define atomic64_dec(v) atomic64_sub(1, (v)) #define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0) -#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0) -#define atomic64_dec(v) atomic64_sub(1LL, (v)) -#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v)) -#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0) -#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL) +#define atomic64_dec_and_test(v) (atomic64_dec_return(v) == 0) +#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0) +#define atomic64_add_negative(i, v) (atomic64_add_return((i), (v)) < 0) +#define atomic64_add_unless(v, a, u) (___atomic_add_unless(v, a, u, 64) != u) +#define atomic64_andnot atomic64_andnot + +#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0) #endif #endif diff --git a/kernel/arch/arm64/include/asm/atomic_ll_sc.h b/kernel/arch/arm64/include/asm/atomic_ll_sc.h new file mode 100644 index 000000000..f61c84f6b --- /dev/null +++ b/kernel/arch/arm64/include/asm/atomic_ll_sc.h @@ -0,0 +1,269 @@ +/* + * Based on arch/arm/include/asm/atomic.h + * + * Copyright (C) 1996 Russell King. + * Copyright (C) 2002 Deep Blue Solutions Ltd. + * Copyright (C) 2012 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __ASM_ATOMIC_LL_SC_H +#define __ASM_ATOMIC_LL_SC_H + +#ifndef __ARM64_IN_ATOMIC_IMPL +#error "please don't include this file directly" +#endif + +/* + * AArch64 UP and SMP safe atomic ops. We use load exclusive and + * store exclusive to ensure that these are atomic. We may loop + * to ensure that the update happens. + * + * NOTE: these functions do *not* follow the PCS and must explicitly + * save any clobbered registers other than x0 (regardless of return + * value). This is achieved through -fcall-saved-* compiler flags for + * this file, which unfortunately don't work on a per-function basis + * (the optimize attribute silently ignores these options). + */ + +#define ATOMIC_OP(op, asm_op) \ +__LL_SC_INLINE void \ +__LL_SC_PREFIX(atomic_##op(int i, atomic_t *v)) \ +{ \ + unsigned long tmp; \ + int result; \ + \ + asm volatile("// atomic_" #op "\n" \ +" prfm pstl1strm, %2\n" \ +"1: ldxr %w0, %2\n" \ +" " #asm_op " %w0, %w0, %w3\n" \ +" stxr %w1, %w0, %2\n" \ +" cbnz %w1, 1b" \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i)); \ +} \ +__LL_SC_EXPORT(atomic_##op); + +#define ATOMIC_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +__LL_SC_INLINE int \ +__LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \ +{ \ + unsigned long tmp; \ + int result; \ + \ + asm volatile("// atomic_" #op "_return" #name "\n" \ +" prfm pstl1strm, %2\n" \ +"1: ld" #acq "xr %w0, %2\n" \ +" " #asm_op " %w0, %w0, %w3\n" \ +" st" #rel "xr %w1, %w0, %2\n" \ +" cbnz %w1, 1b\n" \ +" " #mb \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i) \ + : cl); \ + \ + return result; \ +} \ +__LL_SC_EXPORT(atomic_##op##_return##name); + +#define ATOMIC_OPS(...) \ + ATOMIC_OP(__VA_ARGS__) \ + ATOMIC_OP_RETURN( , dmb ish, , l, "memory", __VA_ARGS__) + +#define ATOMIC_OPS_RLX(...) \ + ATOMIC_OPS(__VA_ARGS__) \ + ATOMIC_OP_RETURN(_relaxed, , , , , __VA_ARGS__)\ + ATOMIC_OP_RETURN(_acquire, , a, , "memory", __VA_ARGS__)\ + ATOMIC_OP_RETURN(_release, , , l, "memory", __VA_ARGS__) + +ATOMIC_OPS_RLX(add, add) +ATOMIC_OPS_RLX(sub, sub) + +ATOMIC_OP(and, and) +ATOMIC_OP(andnot, bic) +ATOMIC_OP(or, orr) +ATOMIC_OP(xor, eor) + +#undef ATOMIC_OPS_RLX +#undef ATOMIC_OPS +#undef ATOMIC_OP_RETURN +#undef ATOMIC_OP + +#define ATOMIC64_OP(op, asm_op) \ +__LL_SC_INLINE void \ +__LL_SC_PREFIX(atomic64_##op(long i, atomic64_t *v)) \ +{ \ + long result; \ + unsigned long tmp; \ + \ + asm volatile("// atomic64_" #op "\n" \ +" prfm pstl1strm, %2\n" \ +"1: ldxr %0, %2\n" \ +" " #asm_op " %0, %0, %3\n" \ +" stxr %w1, %0, %2\n" \ +" cbnz %w1, 1b" \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i)); \ +} \ +__LL_SC_EXPORT(atomic64_##op); + +#define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op) \ +__LL_SC_INLINE long \ +__LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \ +{ \ + long result; \ + unsigned long tmp; \ + \ + asm volatile("// atomic64_" #op "_return" #name "\n" \ +" prfm pstl1strm, %2\n" \ +"1: ld" #acq "xr %0, %2\n" \ +" " #asm_op " %0, %0, %3\n" \ +" st" #rel "xr %w1, %0, %2\n" \ +" cbnz %w1, 1b\n" \ +" " #mb \ + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) \ + : "Ir" (i) \ + : cl); \ + \ + return result; \ +} \ +__LL_SC_EXPORT(atomic64_##op##_return##name); + +#define ATOMIC64_OPS(...) \ + ATOMIC64_OP(__VA_ARGS__) \ + ATOMIC64_OP_RETURN(, dmb ish, , l, "memory", __VA_ARGS__) + +#define ATOMIC64_OPS_RLX(...) \ + ATOMIC64_OPS(__VA_ARGS__) \ + ATOMIC64_OP_RETURN(_relaxed,, , , , __VA_ARGS__) \ + ATOMIC64_OP_RETURN(_acquire,, a, , "memory", __VA_ARGS__) \ + ATOMIC64_OP_RETURN(_release,, , l, "memory", __VA_ARGS__) + +ATOMIC64_OPS_RLX(add, add) +ATOMIC64_OPS_RLX(sub, sub) + +ATOMIC64_OP(and, and) +ATOMIC64_OP(andnot, bic) +ATOMIC64_OP(or, orr) +ATOMIC64_OP(xor, eor) + +#undef ATOMIC64_OPS_RLX +#undef ATOMIC64_OPS +#undef ATOMIC64_OP_RETURN +#undef ATOMIC64_OP + +__LL_SC_INLINE long +__LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v)) +{ + long result; + unsigned long tmp; + + asm volatile("// atomic64_dec_if_positive\n" +" prfm pstl1strm, %2\n" +"1: ldxr %0, %2\n" +" subs %0, %0, #1\n" +" b.lt 2f\n" +" stlxr %w1, %0, %2\n" +" cbnz %w1, 1b\n" +" dmb ish\n" +"2:" + : "=&r" (result), "=&r" (tmp), "+Q" (v->counter) + : + : "cc", "memory"); + + return result; +} +__LL_SC_EXPORT(atomic64_dec_if_positive); + +#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl) \ +__LL_SC_INLINE unsigned long \ +__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \ + unsigned long old, \ + unsigned long new)) \ +{ \ + unsigned long tmp, oldval; \ + \ + asm volatile( \ + " prfm pstl1strm, %[v]\n" \ + "1: ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n" \ + " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ + " cbnz %" #w "[tmp], 2f\n" \ + " st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \ + " cbnz %w[tmp], 1b\n" \ + " " #mb "\n" \ + " mov %" #w "[oldval], %" #w "[old]\n" \ + "2:" \ + : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ + [v] "+Q" (*(unsigned long *)ptr) \ + : [old] "Lr" (old), [new] "r" (new) \ + : cl); \ + \ + return oldval; \ +} \ +__LL_SC_EXPORT(__cmpxchg_case_##name); + +__CMPXCHG_CASE(w, b, 1, , , , ) +__CMPXCHG_CASE(w, h, 2, , , , ) +__CMPXCHG_CASE(w, , 4, , , , ) +__CMPXCHG_CASE( , , 8, , , , ) +__CMPXCHG_CASE(w, b, acq_1, , a, , "memory") +__CMPXCHG_CASE(w, h, acq_2, , a, , "memory") +__CMPXCHG_CASE(w, , acq_4, , a, , "memory") +__CMPXCHG_CASE( , , acq_8, , a, , "memory") +__CMPXCHG_CASE(w, b, rel_1, , , l, "memory") +__CMPXCHG_CASE(w, h, rel_2, , , l, "memory") +__CMPXCHG_CASE(w, , rel_4, , , l, "memory") +__CMPXCHG_CASE( , , rel_8, , , l, "memory") +__CMPXCHG_CASE(w, b, mb_1, dmb ish, , l, "memory") +__CMPXCHG_CASE(w, h, mb_2, dmb ish, , l, "memory") +__CMPXCHG_CASE(w, , mb_4, dmb ish, , l, "memory") +__CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory") + +#undef __CMPXCHG_CASE + +#define __CMPXCHG_DBL(name, mb, rel, cl) \ +__LL_SC_INLINE long \ +__LL_SC_PREFIX(__cmpxchg_double##name(unsigned long old1, \ + unsigned long old2, \ + unsigned long new1, \ + unsigned long new2, \ + volatile void *ptr)) \ +{ \ + unsigned long tmp, ret; \ + \ + asm volatile("// __cmpxchg_double" #name "\n" \ + " prfm pstl1strm, %2\n" \ + "1: ldxp %0, %1, %2\n" \ + " eor %0, %0, %3\n" \ + " eor %1, %1, %4\n" \ + " orr %1, %0, %1\n" \ + " cbnz %1, 2f\n" \ + " st" #rel "xp %w0, %5, %6, %2\n" \ + " cbnz %w0, 1b\n" \ + " " #mb "\n" \ + "2:" \ + : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ + : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ + : cl); \ + \ + return ret; \ +} \ +__LL_SC_EXPORT(__cmpxchg_double##name); + +__CMPXCHG_DBL( , , , ) +__CMPXCHG_DBL(_mb, dmb ish, l, "memory") + +#undef __CMPXCHG_DBL + +#endif /* __ASM_ATOMIC_LL_SC_H */ diff --git a/kernel/arch/arm64/include/asm/atomic_lse.h b/kernel/arch/arm64/include/asm/atomic_lse.h new file mode 100644 index 000000000..197e06afb --- /dev/null +++ b/kernel/arch/arm64/include/asm/atomic_lse.h @@ -0,0 +1,430 @@ +/* + * Based on arch/arm/include/asm/atomic.h + * + * Copyright (C) 1996 Russell King. + * Copyright (C) 2002 Deep Blue Solutions Ltd. + * Copyright (C) 2012 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __ASM_ATOMIC_LSE_H +#define __ASM_ATOMIC_LSE_H + +#ifndef __ARM64_IN_ATOMIC_IMPL +#error "please don't include this file directly" +#endif + +#define __LL_SC_ATOMIC(op) __LL_SC_CALL(atomic_##op) + +static inline void atomic_andnot(int i, atomic_t *v) +{ + register int w0 asm ("w0") = i; + register atomic_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(andnot), + " stclr %w[i], %[v]\n") + : [i] "+r" (w0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic_or(int i, atomic_t *v) +{ + register int w0 asm ("w0") = i; + register atomic_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(or), + " stset %w[i], %[v]\n") + : [i] "+r" (w0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic_xor(int i, atomic_t *v) +{ + register int w0 asm ("w0") = i; + register atomic_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(xor), + " steor %w[i], %[v]\n") + : [i] "+r" (w0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic_add(int i, atomic_t *v) +{ + register int w0 asm ("w0") = i; + register atomic_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(add), + " stadd %w[i], %[v]\n") + : [i] "+r" (w0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +#define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \ +static inline int atomic_add_return##name(int i, atomic_t *v) \ +{ \ + register int w0 asm ("w0") = i; \ + register atomic_t *x1 asm ("x1") = v; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " nop\n" \ + __LL_SC_ATOMIC(add_return##name), \ + /* LSE atomics */ \ + " ldadd" #mb " %w[i], w30, %[v]\n" \ + " add %w[i], %w[i], w30") \ + : [i] "+r" (w0), [v] "+Q" (v->counter) \ + : "r" (x1) \ + : "x30" , ##cl); \ + \ + return w0; \ +} + +ATOMIC_OP_ADD_RETURN(_relaxed, ) +ATOMIC_OP_ADD_RETURN(_acquire, a, "memory") +ATOMIC_OP_ADD_RETURN(_release, l, "memory") +ATOMIC_OP_ADD_RETURN( , al, "memory") + +#undef ATOMIC_OP_ADD_RETURN + +static inline void atomic_and(int i, atomic_t *v) +{ + register int w0 asm ("w0") = i; + register atomic_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " nop\n" + __LL_SC_ATOMIC(and), + /* LSE atomics */ + " mvn %w[i], %w[i]\n" + " stclr %w[i], %[v]") + : [i] "+r" (w0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic_sub(int i, atomic_t *v) +{ + register int w0 asm ("w0") = i; + register atomic_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " nop\n" + __LL_SC_ATOMIC(sub), + /* LSE atomics */ + " neg %w[i], %w[i]\n" + " stadd %w[i], %[v]") + : [i] "+r" (w0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +#define ATOMIC_OP_SUB_RETURN(name, mb, cl...) \ +static inline int atomic_sub_return##name(int i, atomic_t *v) \ +{ \ + register int w0 asm ("w0") = i; \ + register atomic_t *x1 asm ("x1") = v; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " nop\n" \ + __LL_SC_ATOMIC(sub_return##name) \ + " nop", \ + /* LSE atomics */ \ + " neg %w[i], %w[i]\n" \ + " ldadd" #mb " %w[i], w30, %[v]\n" \ + " add %w[i], %w[i], w30") \ + : [i] "+r" (w0), [v] "+Q" (v->counter) \ + : "r" (x1) \ + : "x30" , ##cl); \ + \ + return w0; \ +} + +ATOMIC_OP_SUB_RETURN(_relaxed, ) +ATOMIC_OP_SUB_RETURN(_acquire, a, "memory") +ATOMIC_OP_SUB_RETURN(_release, l, "memory") +ATOMIC_OP_SUB_RETURN( , al, "memory") + +#undef ATOMIC_OP_SUB_RETURN +#undef __LL_SC_ATOMIC + +#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(atomic64_##op) + +static inline void atomic64_andnot(long i, atomic64_t *v) +{ + register long x0 asm ("x0") = i; + register atomic64_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(andnot), + " stclr %[i], %[v]\n") + : [i] "+r" (x0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic64_or(long i, atomic64_t *v) +{ + register long x0 asm ("x0") = i; + register atomic64_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(or), + " stset %[i], %[v]\n") + : [i] "+r" (x0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic64_xor(long i, atomic64_t *v) +{ + register long x0 asm ("x0") = i; + register atomic64_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(xor), + " steor %[i], %[v]\n") + : [i] "+r" (x0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic64_add(long i, atomic64_t *v) +{ + register long x0 asm ("x0") = i; + register atomic64_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(add), + " stadd %[i], %[v]\n") + : [i] "+r" (x0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +#define ATOMIC64_OP_ADD_RETURN(name, mb, cl...) \ +static inline long atomic64_add_return##name(long i, atomic64_t *v) \ +{ \ + register long x0 asm ("x0") = i; \ + register atomic64_t *x1 asm ("x1") = v; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " nop\n" \ + __LL_SC_ATOMIC64(add_return##name), \ + /* LSE atomics */ \ + " ldadd" #mb " %[i], x30, %[v]\n" \ + " add %[i], %[i], x30") \ + : [i] "+r" (x0), [v] "+Q" (v->counter) \ + : "r" (x1) \ + : "x30" , ##cl); \ + \ + return x0; \ +} + +ATOMIC64_OP_ADD_RETURN(_relaxed, ) +ATOMIC64_OP_ADD_RETURN(_acquire, a, "memory") +ATOMIC64_OP_ADD_RETURN(_release, l, "memory") +ATOMIC64_OP_ADD_RETURN( , al, "memory") + +#undef ATOMIC64_OP_ADD_RETURN + +static inline void atomic64_and(long i, atomic64_t *v) +{ + register long x0 asm ("x0") = i; + register atomic64_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " nop\n" + __LL_SC_ATOMIC64(and), + /* LSE atomics */ + " mvn %[i], %[i]\n" + " stclr %[i], %[v]") + : [i] "+r" (x0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +static inline void atomic64_sub(long i, atomic64_t *v) +{ + register long x0 asm ("x0") = i; + register atomic64_t *x1 asm ("x1") = v; + + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " nop\n" + __LL_SC_ATOMIC64(sub), + /* LSE atomics */ + " neg %[i], %[i]\n" + " stadd %[i], %[v]") + : [i] "+r" (x0), [v] "+Q" (v->counter) + : "r" (x1) + : "x30"); +} + +#define ATOMIC64_OP_SUB_RETURN(name, mb, cl...) \ +static inline long atomic64_sub_return##name(long i, atomic64_t *v) \ +{ \ + register long x0 asm ("x0") = i; \ + register atomic64_t *x1 asm ("x1") = v; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " nop\n" \ + __LL_SC_ATOMIC64(sub_return##name) \ + " nop", \ + /* LSE atomics */ \ + " neg %[i], %[i]\n" \ + " ldadd" #mb " %[i], x30, %[v]\n" \ + " add %[i], %[i], x30") \ + : [i] "+r" (x0), [v] "+Q" (v->counter) \ + : "r" (x1) \ + : "x30" , ##cl); \ + \ + return x0; \ +} + +ATOMIC64_OP_SUB_RETURN(_relaxed, ) +ATOMIC64_OP_SUB_RETURN(_acquire, a, "memory") +ATOMIC64_OP_SUB_RETURN(_release, l, "memory") +ATOMIC64_OP_SUB_RETURN( , al, "memory") + +#undef ATOMIC64_OP_SUB_RETURN + +static inline long atomic64_dec_if_positive(atomic64_t *v) +{ + register long x0 asm ("x0") = (long)v; + + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " nop\n" + __LL_SC_ATOMIC64(dec_if_positive) + " nop\n" + " nop\n" + " nop\n" + " nop\n" + " nop", + /* LSE atomics */ + "1: ldr x30, %[v]\n" + " subs %[ret], x30, #1\n" + " b.lt 2f\n" + " casal x30, %[ret], %[v]\n" + " sub x30, x30, #1\n" + " sub x30, x30, %[ret]\n" + " cbnz x30, 1b\n" + "2:") + : [ret] "+&r" (x0), [v] "+Q" (v->counter) + : + : "x30", "cc", "memory"); + + return x0; +} + +#undef __LL_SC_ATOMIC64 + +#define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op) + +#define __CMPXCHG_CASE(w, sz, name, mb, cl...) \ +static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ + unsigned long old, \ + unsigned long new) \ +{ \ + register unsigned long x0 asm ("x0") = (unsigned long)ptr; \ + register unsigned long x1 asm ("x1") = old; \ + register unsigned long x2 asm ("x2") = new; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " nop\n" \ + __LL_SC_CMPXCHG(name) \ + " nop", \ + /* LSE atomics */ \ + " mov " #w "30, %" #w "[old]\n" \ + " cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \ + " mov %" #w "[ret], " #w "30") \ + : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ + : [old] "r" (x1), [new] "r" (x2) \ + : "x30" , ##cl); \ + \ + return x0; \ +} + +__CMPXCHG_CASE(w, b, 1, ) +__CMPXCHG_CASE(w, h, 2, ) +__CMPXCHG_CASE(w, , 4, ) +__CMPXCHG_CASE(x, , 8, ) +__CMPXCHG_CASE(w, b, acq_1, a, "memory") +__CMPXCHG_CASE(w, h, acq_2, a, "memory") +__CMPXCHG_CASE(w, , acq_4, a, "memory") +__CMPXCHG_CASE(x, , acq_8, a, "memory") +__CMPXCHG_CASE(w, b, rel_1, l, "memory") +__CMPXCHG_CASE(w, h, rel_2, l, "memory") +__CMPXCHG_CASE(w, , rel_4, l, "memory") +__CMPXCHG_CASE(x, , rel_8, l, "memory") +__CMPXCHG_CASE(w, b, mb_1, al, "memory") +__CMPXCHG_CASE(w, h, mb_2, al, "memory") +__CMPXCHG_CASE(w, , mb_4, al, "memory") +__CMPXCHG_CASE(x, , mb_8, al, "memory") + +#undef __LL_SC_CMPXCHG +#undef __CMPXCHG_CASE + +#define __LL_SC_CMPXCHG_DBL(op) __LL_SC_CALL(__cmpxchg_double##op) + +#define __CMPXCHG_DBL(name, mb, cl...) \ +static inline long __cmpxchg_double##name(unsigned long old1, \ + unsigned long old2, \ + unsigned long new1, \ + unsigned long new2, \ + volatile void *ptr) \ +{ \ + unsigned long oldval1 = old1; \ + unsigned long oldval2 = old2; \ + register unsigned long x0 asm ("x0") = old1; \ + register unsigned long x1 asm ("x1") = old2; \ + register unsigned long x2 asm ("x2") = new1; \ + register unsigned long x3 asm ("x3") = new2; \ + register unsigned long x4 asm ("x4") = (unsigned long)ptr; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " nop\n" \ + " nop\n" \ + " nop\n" \ + __LL_SC_CMPXCHG_DBL(name), \ + /* LSE atomics */ \ + " casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\ + " eor %[old1], %[old1], %[oldval1]\n" \ + " eor %[old2], %[old2], %[oldval2]\n" \ + " orr %[old1], %[old1], %[old2]") \ + : [old1] "+r" (x0), [old2] "+r" (x1), \ + [v] "+Q" (*(unsigned long *)ptr) \ + : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ + [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ + : "x30" , ##cl); \ + \ + return x0; \ +} + +__CMPXCHG_DBL( , ) +__CMPXCHG_DBL(_mb, al, "memory") + +#undef __LL_SC_CMPXCHG_DBL +#undef __CMPXCHG_DBL + +#endif /* __ASM_ATOMIC_LSE_H */ diff --git a/kernel/arch/arm64/include/asm/barrier.h b/kernel/arch/arm64/include/asm/barrier.h index 71f19c4dc..9622eb48f 100644 --- a/kernel/arch/arm64/include/asm/barrier.h +++ b/kernel/arch/arm64/include/asm/barrier.h @@ -35,28 +35,6 @@ #define dma_rmb() dmb(oshld) #define dma_wmb() dmb(oshst) -#ifndef CONFIG_SMP -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() - -#define smp_store_release(p, v) \ -do { \ - compiletime_assert_atomic_type(*p); \ - barrier(); \ - ACCESS_ONCE(*p) = (v); \ -} while (0) - -#define smp_load_acquire(p) \ -({ \ - typeof(*p) ___p1 = ACCESS_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ - barrier(); \ - ___p1; \ -}) - -#else - #define smp_mb() dmb(ish) #define smp_rmb() dmb(ishld) #define smp_wmb() dmb(ishst) @@ -86,35 +64,37 @@ do { \ #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1; \ + union { typeof(*p) __val; char __c[1]; } __u; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ case 1: \ asm volatile ("ldarb %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u8 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 2: \ asm volatile ("ldarh %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u16 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 4: \ asm volatile ("ldar %w0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u32 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ case 8: \ asm volatile ("ldar %0, %1" \ - : "=r" (___p1) : "Q" (*p) : "memory"); \ + : "=r" (*(__u64 *)__u.__c) \ + : "Q" (*p) : "memory"); \ break; \ } \ - ___p1; \ + __u.__val; \ }) -#endif - #define read_barrier_depends() do { } while(0) #define smp_read_barrier_depends() do { } while(0) -#define set_mb(var, value) do { var = value; smp_mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #define nop() asm volatile("nop"); #define smp_mb__before_atomic() smp_mb() diff --git a/kernel/arch/arm64/include/asm/boot.h b/kernel/arch/arm64/include/asm/boot.h new file mode 100644 index 000000000..81151b67b --- /dev/null +++ b/kernel/arch/arm64/include/asm/boot.h @@ -0,0 +1,14 @@ + +#ifndef __ASM_BOOT_H +#define __ASM_BOOT_H + +#include + +/* + * arm64 requires the DTB to be 8 byte aligned and + * not exceed 2MB in size. + */ +#define MIN_FDT_ALIGN 8 +#define MAX_FDT_SIZE SZ_2M + +#endif diff --git a/kernel/arch/arm64/include/asm/bug.h b/kernel/arch/arm64/include/asm/bug.h new file mode 100644 index 000000000..4a748ce9b --- /dev/null +++ b/kernel/arch/arm64/include/asm/bug.h @@ -0,0 +1,64 @@ +/* + * Copyright (C) 2015 ARM Limited + * Author: Dave Martin + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef _ARCH_ARM64_ASM_BUG_H +#define _ARCH_ARM64_ASM_BUG_H + +#include + +#ifdef CONFIG_GENERIC_BUG +#define HAVE_ARCH_BUG + +#ifdef CONFIG_DEBUG_BUGVERBOSE +#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line) +#define __BUGVERBOSE_LOCATION(file, line) \ + ".pushsection .rodata.str,\"aMS\",@progbits,1\n" \ + "2: .string \"" file "\"\n\t" \ + ".popsection\n\t" \ + \ + ".long 2b - 0b\n\t" \ + ".short " #line "\n\t" +#else +#define _BUGVERBOSE_LOCATION(file, line) +#endif + +#define _BUG_FLAGS(flags) __BUG_FLAGS(flags) + +#define __BUG_FLAGS(flags) asm volatile ( \ + ".pushsection __bug_table,\"a\"\n\t" \ + ".align 2\n\t" \ + "0: .long 1f - 0b\n\t" \ +_BUGVERBOSE_LOCATION(__FILE__, __LINE__) \ + ".short " #flags "\n\t" \ + ".popsection\n" \ + \ + "1: brk %[imm]" \ + :: [imm] "i" (BUG_BRK_IMM) \ +) + +#define BUG() do { \ + _BUG_FLAGS(0); \ + unreachable(); \ +} while (0) + +#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint)) + +#endif /* ! CONFIG_GENERIC_BUG */ + +#include + +#endif /* ! _ARCH_ARM64_ASM_BUG_H */ diff --git a/kernel/arch/arm64/include/asm/cache.h b/kernel/arch/arm64/include/asm/cache.h index bde449936..5082b30bc 100644 --- a/kernel/arch/arm64/include/asm/cache.h +++ b/kernel/arch/arm64/include/asm/cache.h @@ -18,7 +18,7 @@ #include -#define L1_CACHE_SHIFT 6 +#define L1_CACHE_SHIFT 7 #define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) /* diff --git a/kernel/arch/arm64/include/asm/cacheflush.h b/kernel/arch/arm64/include/asm/cacheflush.h index 67d309cc3..54efedaf3 100644 --- a/kernel/arch/arm64/include/asm/cacheflush.h +++ b/kernel/arch/arm64/include/asm/cacheflush.h @@ -40,10 +40,6 @@ * the implementation assumes non-aliasing VIPT D-cache and (aliasing) * VIPT or ASID-tagged VIVT I-cache. * - * flush_cache_all() - * - * Unconditionally clean and invalidate the entire cache. - * * flush_cache_mm(mm) * * Clean and invalidate all user space cache entries @@ -69,7 +65,6 @@ * - kaddr - page address * - size - region size */ -extern void flush_cache_all(void); extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); @@ -120,6 +115,13 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); +static inline void __local_flush_icache_all(void) +{ + asm("ic iallu"); + dsb(nsh); + isb(); +} + static inline void __flush_icache_all(void) { asm("ic ialluis"); diff --git a/kernel/arch/arm64/include/asm/cachetype.h b/kernel/arch/arm64/include/asm/cachetype.h index da2fc9e3c..f5588692f 100644 --- a/kernel/arch/arm64/include/asm/cachetype.h +++ b/kernel/arch/arm64/include/asm/cachetype.h @@ -34,8 +34,8 @@ #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) -#define ICACHEF_ALIASING BIT(0) -#define ICACHEF_AIVIVT BIT(1) +#define ICACHEF_ALIASING 0 +#define ICACHEF_AIVIVT 1 extern unsigned long __icache_flags; diff --git a/kernel/arch/arm64/include/asm/cmpxchg.h b/kernel/arch/arm64/include/asm/cmpxchg.h index d8c25b7b1..9ea611ea6 100644 --- a/kernel/arch/arm64/include/asm/cmpxchg.h +++ b/kernel/arch/arm64/include/asm/cmpxchg.h @@ -21,231 +21,185 @@ #include #include +#include #include +#include -static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size) -{ - unsigned long ret, tmp; - - switch (size) { - case 1: - asm volatile("// __xchg1\n" - "1: ldxrb %w0, %2\n" - " stlxrb %w1, %w3, %2\n" - " cbnz %w1, 1b\n" - : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) - : "r" (x) - : "memory"); - break; - case 2: - asm volatile("// __xchg2\n" - "1: ldxrh %w0, %2\n" - " stlxrh %w1, %w3, %2\n" - " cbnz %w1, 1b\n" - : "=&r" (ret), "=&r" (tmp), "+Q" (*(u16 *)ptr) - : "r" (x) - : "memory"); - break; - case 4: - asm volatile("// __xchg4\n" - "1: ldxr %w0, %2\n" - " stlxr %w1, %w3, %2\n" - " cbnz %w1, 1b\n" - : "=&r" (ret), "=&r" (tmp), "+Q" (*(u32 *)ptr) - : "r" (x) - : "memory"); - break; - case 8: - asm volatile("// __xchg8\n" - "1: ldxr %0, %2\n" - " stlxr %w1, %3, %2\n" - " cbnz %w1, 1b\n" - : "=&r" (ret), "=&r" (tmp), "+Q" (*(u64 *)ptr) - : "r" (x) - : "memory"); - break; - default: - BUILD_BUG(); - } - - smp_mb(); - return ret; +/* + * We need separate acquire parameters for ll/sc and lse, since the full + * barrier case is generated as release+dmb for the former and + * acquire+release for the latter. + */ +#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl) \ +static inline unsigned long __xchg_case_##name(unsigned long x, \ + volatile void *ptr) \ +{ \ + unsigned long ret, tmp; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr" #sz "\t%" #w "0, %2\n" \ + " st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb, \ + /* LSE atomics */ \ + " nop\n" \ + " nop\n" \ + " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ + " nop\n" \ + " " #nop_lse) \ + : "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr) \ + : "r" (x) \ + : cl); \ + \ + return ret; \ } -#define xchg(ptr,x) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __xchg((unsigned long)(x), (ptr), sizeof(*(ptr))); \ - __ret; \ -}) - -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long oldval = 0, res; - - switch (size) { - case 1: - do { - asm volatile("// __cmpxchg1\n" - " ldxrb %w1, %2\n" - " mov %w0, #0\n" - " cmp %w1, %w3\n" - " b.ne 1f\n" - " stxrb %w0, %w4, %2\n" - "1:\n" - : "=&r" (res), "=&r" (oldval), "+Q" (*(u8 *)ptr) - : "Ir" (old), "r" (new) - : "cc"); - } while (res); - break; - - case 2: - do { - asm volatile("// __cmpxchg2\n" - " ldxrh %w1, %2\n" - " mov %w0, #0\n" - " cmp %w1, %w3\n" - " b.ne 1f\n" - " stxrh %w0, %w4, %2\n" - "1:\n" - : "=&r" (res), "=&r" (oldval), "+Q" (*(u16 *)ptr) - : "Ir" (old), "r" (new) - : "cc"); - } while (res); - break; - - case 4: - do { - asm volatile("// __cmpxchg4\n" - " ldxr %w1, %2\n" - " mov %w0, #0\n" - " cmp %w1, %w3\n" - " b.ne 1f\n" - " stxr %w0, %w4, %2\n" - "1:\n" - : "=&r" (res), "=&r" (oldval), "+Q" (*(u32 *)ptr) - : "Ir" (old), "r" (new) - : "cc"); - } while (res); - break; - - case 8: - do { - asm volatile("// __cmpxchg8\n" - " ldxr %1, %2\n" - " mov %w0, #0\n" - " cmp %1, %3\n" - " b.ne 1f\n" - " stxr %w0, %4, %2\n" - "1:\n" - : "=&r" (res), "=&r" (oldval), "+Q" (*(u64 *)ptr) - : "Ir" (old), "r" (new) - : "cc"); - } while (res); - break; - - default: - BUILD_BUG(); - } - - return oldval; +__XCHG_CASE(w, b, 1, , , , , , ) +__XCHG_CASE(w, h, 2, , , , , , ) +__XCHG_CASE(w, , 4, , , , , , ) +__XCHG_CASE( , , 8, , , , , , ) +__XCHG_CASE(w, b, acq_1, , , a, a, , "memory") +__XCHG_CASE(w, h, acq_2, , , a, a, , "memory") +__XCHG_CASE(w, , acq_4, , , a, a, , "memory") +__XCHG_CASE( , , acq_8, , , a, a, , "memory") +__XCHG_CASE(w, b, rel_1, , , , , l, "memory") +__XCHG_CASE(w, h, rel_2, , , , , l, "memory") +__XCHG_CASE(w, , rel_4, , , , , l, "memory") +__XCHG_CASE( , , rel_8, , , , , l, "memory") +__XCHG_CASE(w, b, mb_1, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, h, mb_2, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, , mb_4, dmb ish, nop, , a, l, "memory") +__XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory") + +#undef __XCHG_CASE + +#define __XCHG_GEN(sfx) \ +static inline unsigned long __xchg##sfx(unsigned long x, \ + volatile void *ptr, \ + int size) \ +{ \ + switch (size) { \ + case 1: \ + return __xchg_case##sfx##_1(x, ptr); \ + case 2: \ + return __xchg_case##sfx##_2(x, ptr); \ + case 4: \ + return __xchg_case##sfx##_4(x, ptr); \ + case 8: \ + return __xchg_case##sfx##_8(x, ptr); \ + default: \ + BUILD_BUG(); \ + } \ + \ + unreachable(); \ } -#define system_has_cmpxchg_double() 1 - -static inline int __cmpxchg_double(volatile void *ptr1, volatile void *ptr2, - unsigned long old1, unsigned long old2, - unsigned long new1, unsigned long new2, int size) -{ - unsigned long loop, lost; +__XCHG_GEN() +__XCHG_GEN(_acq) +__XCHG_GEN(_rel) +__XCHG_GEN(_mb) - switch (size) { - case 8: - VM_BUG_ON((unsigned long *)ptr2 - (unsigned long *)ptr1 != 1); - do { - asm volatile("// __cmpxchg_double8\n" - " ldxp %0, %1, %2\n" - " eor %0, %0, %3\n" - " eor %1, %1, %4\n" - " orr %1, %0, %1\n" - " mov %w0, #0\n" - " cbnz %1, 1f\n" - " stxp %w0, %5, %6, %2\n" - "1:\n" - : "=&r"(loop), "=&r"(lost), "+Q" (*(u64 *)ptr1) - : "r" (old1), "r"(old2), "r"(new1), "r"(new2)); - } while (loop); - break; - default: - BUILD_BUG(); - } +#undef __XCHG_GEN - return !lost; -} - -static inline int __cmpxchg_double_mb(volatile void *ptr1, volatile void *ptr2, - unsigned long old1, unsigned long old2, - unsigned long new1, unsigned long new2, int size) -{ - int ret; - - smp_mb(); - ret = __cmpxchg_double(ptr1, ptr2, old1, old2, new1, new2, size); - smp_mb(); +#define __xchg_wrapper(sfx, ptr, x) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \ + __ret; \ +}) - return ret; +/* xchg */ +#define xchg_relaxed(...) __xchg_wrapper( , __VA_ARGS__) +#define xchg_acquire(...) __xchg_wrapper(_acq, __VA_ARGS__) +#define xchg_release(...) __xchg_wrapper(_rel, __VA_ARGS__) +#define xchg(...) __xchg_wrapper( _mb, __VA_ARGS__) + +#define __CMPXCHG_GEN(sfx) \ +static inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ + unsigned long old, \ + unsigned long new, \ + int size) \ +{ \ + switch (size) { \ + case 1: \ + return __cmpxchg_case##sfx##_1(ptr, (u8)old, new); \ + case 2: \ + return __cmpxchg_case##sfx##_2(ptr, (u16)old, new); \ + case 4: \ + return __cmpxchg_case##sfx##_4(ptr, old, new); \ + case 8: \ + return __cmpxchg_case##sfx##_8(ptr, old, new); \ + default: \ + BUILD_BUG(); \ + } \ + \ + unreachable(); \ } -static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long ret; - - smp_mb(); - ret = __cmpxchg(ptr, old, new, size); - smp_mb(); +__CMPXCHG_GEN() +__CMPXCHG_GEN(_acq) +__CMPXCHG_GEN(_rel) +__CMPXCHG_GEN(_mb) - return ret; -} +#undef __CMPXCHG_GEN -#define cmpxchg(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __cmpxchg_mb((ptr), (unsigned long)(o), (unsigned long)(n), \ - sizeof(*(ptr))); \ - __ret; \ +#define __cmpxchg_wrapper(sfx, ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __ret = (__typeof__(*(ptr))) \ + __cmpxchg##sfx((ptr), (unsigned long)(o), \ + (unsigned long)(n), sizeof(*(ptr))); \ + __ret; \ }) -#define cmpxchg_local(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - __ret = (__typeof__(*(ptr))) \ - __cmpxchg((ptr), (unsigned long)(o), \ - (unsigned long)(n), sizeof(*(ptr))); \ - __ret; \ +/* cmpxchg */ +#define cmpxchg_relaxed(...) __cmpxchg_wrapper( , __VA_ARGS__) +#define cmpxchg_acquire(...) __cmpxchg_wrapper(_acq, __VA_ARGS__) +#define cmpxchg_release(...) __cmpxchg_wrapper(_rel, __VA_ARGS__) +#define cmpxchg(...) __cmpxchg_wrapper( _mb, __VA_ARGS__) +#define cmpxchg_local cmpxchg_relaxed + +/* cmpxchg64 */ +#define cmpxchg64_relaxed cmpxchg_relaxed +#define cmpxchg64_acquire cmpxchg_acquire +#define cmpxchg64_release cmpxchg_release +#define cmpxchg64 cmpxchg +#define cmpxchg64_local cmpxchg_local + +/* cmpxchg_double */ +#define system_has_cmpxchg_double() 1 + +#define __cmpxchg_double_check(ptr1, ptr2) \ +({ \ + if (sizeof(*(ptr1)) != 8) \ + BUILD_BUG(); \ + VM_BUG_ON((unsigned long *)(ptr2) - (unsigned long *)(ptr1) != 1); \ }) #define cmpxchg_double(ptr1, ptr2, o1, o2, n1, n2) \ ({\ int __ret;\ - __ret = __cmpxchg_double_mb((ptr1), (ptr2), (unsigned long)(o1), \ - (unsigned long)(o2), (unsigned long)(n1), \ - (unsigned long)(n2), sizeof(*(ptr1)));\ + __cmpxchg_double_check(ptr1, ptr2); \ + __ret = !__cmpxchg_double_mb((unsigned long)(o1), (unsigned long)(o2), \ + (unsigned long)(n1), (unsigned long)(n2), \ + ptr1); \ __ret; \ }) #define cmpxchg_double_local(ptr1, ptr2, o1, o2, n1, n2) \ ({\ int __ret;\ - __ret = __cmpxchg_double((ptr1), (ptr2), (unsigned long)(o1), \ - (unsigned long)(o2), (unsigned long)(n1), \ - (unsigned long)(n2), sizeof(*(ptr1)));\ + __cmpxchg_double_check(ptr1, ptr2); \ + __ret = !__cmpxchg_double((unsigned long)(o1), (unsigned long)(o2), \ + (unsigned long)(n1), (unsigned long)(n2), \ + ptr1); \ __ret; \ }) +/* this_cpu_cmpxchg */ #define _protect_cmpxchg_local(pcp, o, n) \ ({ \ typeof(*raw_cpu_ptr(&(pcp))) __ret; \ @@ -271,9 +225,4 @@ static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old, __ret; \ }) -#define cmpxchg64(ptr,o,n) cmpxchg((ptr),(o),(n)) -#define cmpxchg64_local(ptr,o,n) cmpxchg_local((ptr),(o),(n)) - -#define cmpxchg64_relaxed(ptr,o,n) cmpxchg_local((ptr),(o),(n)) - #endif /* __ASM_CMPXCHG_H */ diff --git a/kernel/arch/arm64/include/asm/compat.h b/kernel/arch/arm64/include/asm/compat.h index 7fbed6919..eb8432bb8 100644 --- a/kernel/arch/arm64/include/asm/compat.h +++ b/kernel/arch/arm64/include/asm/compat.h @@ -23,7 +23,6 @@ */ #include #include -#include #define COMPAT_USER_HZ 100 #ifdef __AARCH64EB__ @@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr) return (u32)(unsigned long)uptr; } -#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs())) +#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current))) static inline void __user *arch_compat_alloc_user_space(long len) { diff --git a/kernel/arch/arm64/include/asm/cpu.h b/kernel/arch/arm64/include/asm/cpu.h index 8e797b2fc..b5e9cee4b 100644 --- a/kernel/arch/arm64/include/asm/cpu.h +++ b/kernel/arch/arm64/include/asm/cpu.h @@ -63,4 +63,8 @@ DECLARE_PER_CPU(struct cpuinfo_arm64, cpu_data); void cpuinfo_store_cpu(void); void __init cpuinfo_store_boot_cpu(void); +void __init init_cpu_features(struct cpuinfo_arm64 *info); +void update_cpu_features(int cpu, struct cpuinfo_arm64 *info, + struct cpuinfo_arm64 *boot); + #endif /* __ASM_CPU_H */ diff --git a/kernel/arch/arm64/include/asm/cpu_ops.h b/kernel/arch/arm64/include/asm/cpu_ops.h index 5a31d6716..8f03446cf 100644 --- a/kernel/arch/arm64/include/asm/cpu_ops.h +++ b/kernel/arch/arm64/include/asm/cpu_ops.h @@ -19,15 +19,15 @@ #include #include -struct device_node; - /** * struct cpu_operations - Callback operations for hotplugging CPUs. * * @name: Name of the property as appears in a devicetree cpu node's - * enable-method property. - * @cpu_init: Reads any data necessary for a specific enable-method from the - * devicetree, for a given cpu node and proposed logical id. + * enable-method property. On systems booting with ACPI, @name + * identifies the struct cpu_operations entry corresponding to + * the boot protocol specified in the ACPI MADT table. + * @cpu_init: Reads any data necessary for a specific enable-method for a + * proposed logical id. * @cpu_prepare: Early one-time preparation step for a cpu. If there is a * mechanism for doing so, tests whether it is possible to boot * the given CPU. @@ -40,15 +40,15 @@ struct device_node; * @cpu_die: Makes a cpu leave the kernel. Must not fail. Called from the * cpu being killed. * @cpu_kill: Ensures a cpu has left the kernel. Called from another cpu. - * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from - * devicetree, for a given cpu node and proposed logical id. + * @cpu_init_idle: Reads any data necessary to initialize CPU idle states for + * a proposed logical id. * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing * to wrong parameters or error conditions. Called from the * CPU being suspended. Must be called with IRQs disabled. */ struct cpu_operations { const char *name; - int (*cpu_init)(struct device_node *, unsigned int); + int (*cpu_init)(unsigned int); int (*cpu_prepare)(unsigned int); int (*cpu_boot)(unsigned int); void (*cpu_postboot)(void); @@ -58,14 +58,17 @@ struct cpu_operations { int (*cpu_kill)(unsigned int cpu); #endif #ifdef CONFIG_CPU_IDLE - int (*cpu_init_idle)(struct device_node *, unsigned int); + int (*cpu_init_idle)(unsigned int); int (*cpu_suspend)(unsigned long); #endif }; extern const struct cpu_operations *cpu_ops[NR_CPUS]; -int __init cpu_read_ops(struct device_node *dn, int cpu); -void __init cpu_read_bootcpu_ops(void); -const struct cpu_operations *cpu_get_ops(const char *name); +int __init cpu_read_ops(int cpu); + +static inline void __init cpu_read_bootcpu_ops(void) +{ + cpu_read_ops(0); +} #endif /* ifndef __ASM_CPU_OPS_H */ diff --git a/kernel/arch/arm64/include/asm/cpufeature.h b/kernel/arch/arm64/include/asm/cpufeature.h index 82cb9f98b..8f271b83f 100644 --- a/kernel/arch/arm64/include/asm/cpufeature.h +++ b/kernel/arch/arm64/include/asm/cpufeature.h @@ -10,6 +10,7 @@ #define __ASM_CPUFEATURE_H #include +#include /* * In the arm64 world (as in the ARM world), elf_hwcap is used both internally @@ -24,20 +25,71 @@ #define ARM64_WORKAROUND_CLEAN_CACHE 0 #define ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE 1 #define ARM64_WORKAROUND_845719 2 +#define ARM64_HAS_SYSREG_GIC_CPUIF 3 +#define ARM64_HAS_PAN 4 +#define ARM64_HAS_LSE_ATOMICS 5 +#define ARM64_WORKAROUND_CAVIUM_23154 6 +#define ARM64_WORKAROUND_834220 7 -#define ARM64_NCAPS 3 +#define ARM64_NCAPS 8 #ifndef __ASSEMBLY__ +#include + +/* CPU feature register tracking */ +enum ftr_type { + FTR_EXACT, /* Use a predefined safe value */ + FTR_LOWER_SAFE, /* Smaller value is safe */ + FTR_HIGHER_SAFE,/* Bigger value is safe */ +}; + +#define FTR_STRICT true /* SANITY check strict matching required */ +#define FTR_NONSTRICT false /* SANITY check ignored */ + +#define FTR_SIGNED true /* Value should be treated as signed */ +#define FTR_UNSIGNED false /* Value should be treated as unsigned */ + +struct arm64_ftr_bits { + bool sign; /* Value is signed ? */ + bool strict; /* CPU Sanity check: strict matching required ? */ + enum ftr_type type; + u8 shift; + u8 width; + s64 safe_val; /* safe value for discrete features */ +}; + +/* + * @arm64_ftr_reg - Feature register + * @strict_mask Bits which should match across all CPUs for sanity. + * @sys_val Safe value across the CPUs (system view) + */ +struct arm64_ftr_reg { + u32 sys_id; + const char *name; + u64 strict_mask; + u64 sys_val; + struct arm64_ftr_bits *ftr_bits; +}; + struct arm64_cpu_capabilities { const char *desc; u16 capability; bool (*matches)(const struct arm64_cpu_capabilities *); + void (*enable)(void *); /* Called on all active CPUs */ union { struct { /* To be used for erratum handling only */ u32 midr_model; u32 midr_range_min, midr_range_max; }; + + struct { /* Feature register checking */ + u32 sys_reg; + int field_pos; + int min_field_value; + int hwcap_type; + unsigned long hwcap; + }; }; }; @@ -64,12 +116,73 @@ static inline void cpus_set_cap(unsigned int num) __set_bit(num, cpu_hwcaps); } -void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps, +static inline int __attribute_const__ +cpuid_feature_extract_field_width(u64 features, int field, int width) +{ + return (s64)(features << (64 - width - field)) >> (64 - width); +} + +static inline int __attribute_const__ +cpuid_feature_extract_field(u64 features, int field) +{ + return cpuid_feature_extract_field_width(features, field, 4); +} + +static inline unsigned int __attribute_const__ +cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) +{ + return (u64)(features << (64 - width - field)) >> (64 - width); +} + +static inline unsigned int __attribute_const__ +cpuid_feature_extract_unsigned_field(u64 features, int field) +{ + return cpuid_feature_extract_unsigned_field_width(features, field, 4); +} + +static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp) +{ + return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); +} + +static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val) +{ + return ftrp->sign ? + cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width) : + cpuid_feature_extract_unsigned_field_width(val, ftrp->shift, ftrp->width); +} + +static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) +{ + return cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_BIGENDEL_SHIFT) == 0x1 || + cpuid_feature_extract_field(mmfr0, ID_AA64MMFR0_BIGENDEL0_SHIFT) == 0x1; +} + +void __init setup_cpu_features(void); + +void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, const char *info); void check_local_cpu_errata(void); -void check_local_cpu_features(void); -bool cpu_supports_mixed_endian_el0(void); -bool system_supports_mixed_endian_el0(void); + +#ifdef CONFIG_HOTPLUG_CPU +void verify_local_cpu_capabilities(void); +#else +static inline void verify_local_cpu_capabilities(void) +{ +} +#endif + +u64 read_system_reg(u32 id); + +static inline bool cpu_supports_mixed_endian_el0(void) +{ + return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); +} + +static inline bool system_supports_mixed_endian_el0(void) +{ + return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1)); +} #endif /* __ASSEMBLY__ */ diff --git a/kernel/arch/arm64/include/asm/cpuidle.h b/kernel/arch/arm64/include/asm/cpuidle.h index 141b2fcab..0f74f05d6 100644 --- a/kernel/arch/arm64/include/asm/cpuidle.h +++ b/kernel/arch/arm64/include/asm/cpuidle.h @@ -5,20 +5,16 @@ #ifdef CONFIG_CPU_IDLE extern int arm_cpuidle_init(unsigned int cpu); -extern int cpu_suspend(unsigned long arg); +extern int arm_cpuidle_suspend(int index); #else static inline int arm_cpuidle_init(unsigned int cpu) { return -EOPNOTSUPP; } -static inline int cpu_suspend(unsigned long arg) +static inline int arm_cpuidle_suspend(int index) { return -EOPNOTSUPP; } #endif -static inline int arm_cpuidle_suspend(int index) -{ - return cpu_suspend(index); -} #endif diff --git a/kernel/arch/arm64/include/asm/cputype.h b/kernel/arch/arm64/include/asm/cputype.h index a84ec605b..1a5949364 100644 --- a/kernel/arch/arm64/include/asm/cputype.h +++ b/kernel/arch/arm64/include/asm/cputype.h @@ -62,27 +62,18 @@ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) -#define ARM_CPU_IMP_ARM 0x41 -#define ARM_CPU_IMP_APM 0x50 +#define ARM_CPU_IMP_ARM 0x41 +#define ARM_CPU_IMP_APM 0x50 +#define ARM_CPU_IMP_CAVIUM 0x43 -#define ARM_CPU_PART_AEM_V8 0xD0F -#define ARM_CPU_PART_FOUNDATION 0xD00 -#define ARM_CPU_PART_CORTEX_A57 0xD07 -#define ARM_CPU_PART_CORTEX_A53 0xD03 +#define ARM_CPU_PART_AEM_V8 0xD0F +#define ARM_CPU_PART_FOUNDATION 0xD00 +#define ARM_CPU_PART_CORTEX_A57 0xD07 +#define ARM_CPU_PART_CORTEX_A53 0xD03 -#define APM_CPU_PART_POTENZA 0x000 +#define APM_CPU_PART_POTENZA 0x000 -#define ID_AA64MMFR0_BIGENDEL0_SHIFT 16 -#define ID_AA64MMFR0_BIGENDEL0_MASK (0xf << ID_AA64MMFR0_BIGENDEL0_SHIFT) -#define ID_AA64MMFR0_BIGENDEL0(mmfr0) \ - (((mmfr0) & ID_AA64MMFR0_BIGENDEL0_MASK) >> ID_AA64MMFR0_BIGENDEL0_SHIFT) -#define ID_AA64MMFR0_BIGEND_SHIFT 8 -#define ID_AA64MMFR0_BIGEND_MASK (0xf << ID_AA64MMFR0_BIGEND_SHIFT) -#define ID_AA64MMFR0_BIGEND(mmfr0) \ - (((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT) - -#define SCTLR_EL1_CP15BEN (0x1 << 5) -#define SCTLR_EL1_SED (0x1 << 8) +#define CAVIUM_CPU_PART_THUNDERX 0x0A1 #ifndef __ASSEMBLY__ @@ -115,12 +106,6 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void) { return read_cpuid(CTR_EL0); } - -static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) -{ - return (ID_AA64MMFR0_BIGEND(mmfr0) == 0x1) || - (ID_AA64MMFR0_BIGENDEL0(mmfr0) == 0x1); -} #endif /* __ASSEMBLY__ */ #endif diff --git a/kernel/arch/arm64/include/asm/dcc.h b/kernel/arch/arm64/include/asm/dcc.h new file mode 100644 index 000000000..65e0190e9 --- /dev/null +++ b/kernel/arch/arm64/include/asm/dcc.h @@ -0,0 +1,55 @@ +/* Copyright (c) 2014-2015 The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * A call to __dcc_getchar() or __dcc_putchar() is typically followed by + * a call to __dcc_getstatus(). We want to make sure that the CPU does + * not speculative read the DCC status before executing the read or write + * instruction. That's what the ISBs are for. + * + * The 'volatile' ensures that the compiler does not cache the status bits, + * and instead reads the DCC register every time. + */ +#ifndef __ASM_DCC_H +#define __ASM_DCC_H + +#include + +static inline u32 __dcc_getstatus(void) +{ + u32 ret; + + asm volatile("mrs %0, mdccsr_el0" : "=r" (ret)); + + return ret; +} + +static inline char __dcc_getchar(void) +{ + char c; + + asm volatile("mrs %0, dbgdtrrx_el0" : "=r" (c)); + isb(); + + return c; +} + +static inline void __dcc_putchar(char c) +{ + /* + * The typecast is to make absolutely certain that 'c' is + * zero-extended. + */ + asm volatile("msr dbgdtrtx_el0, %0" + : : "r" ((unsigned long)(unsigned char)c)); + isb(); +} + +#endif diff --git a/kernel/arch/arm64/include/asm/debug-monitors.h b/kernel/arch/arm64/include/asm/debug-monitors.h index 40ec68aa6..279c85b5e 100644 --- a/kernel/arch/arm64/include/asm/debug-monitors.h +++ b/kernel/arch/arm64/include/asm/debug-monitors.h @@ -18,6 +18,12 @@ #ifdef __KERNEL__ +#include +#include +#include +#include +#include + /* Low-level stepping controls. */ #define DBG_MDSCR_SS (1 << 0) #define DBG_SPSR_SS (1 << 21) @@ -38,12 +44,7 @@ /* * Break point instruction encoding */ -#define BREAK_INSTR_SIZE 4 - -/* - * ESR values expected for dynamic and compile time BRK instruction - */ -#define DBG_ESR_VAL_BRK(x) (0xf2000000 | ((x) & 0xfffff)) +#define BREAK_INSTR_SIZE AARCH64_INSN_SIZE /* * #imm16 values used for BRK instruction generation @@ -51,10 +52,12 @@ * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction * 0x401: for compile time BRK instruction + * 0x800: kernel-mode BUG() and WARN() traps */ #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 +#define BUG_BRK_IMM 0x800 /* * BRK instruction encoding @@ -68,25 +71,10 @@ */ #define AARCH64_BREAK_FAULT (AARCH64_BREAK_MON | (FAULT_BRK_IMM << 5)) -/* - * Extract byte from BRK instruction - */ -#define KGDB_DYN_DBG_BRK_INS_BYTE(x) \ - ((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff) - -/* - * Extract byte from BRK #imm16 - */ -#define KGBD_DYN_DBG_BRK_IMM_BYTE(x) \ - (((((KGDB_DYN_DBG_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff) - -#define KGDB_DYN_DBG_BRK_BYTE(x) \ - (KGDB_DYN_DBG_BRK_INS_BYTE(x) | KGBD_DYN_DBG_BRK_IMM_BYTE(x)) - -#define KGDB_DYN_BRK_INS_BYTE0 KGDB_DYN_DBG_BRK_BYTE(0) -#define KGDB_DYN_BRK_INS_BYTE1 KGDB_DYN_DBG_BRK_BYTE(1) -#define KGDB_DYN_BRK_INS_BYTE2 KGDB_DYN_DBG_BRK_BYTE(2) -#define KGDB_DYN_BRK_INS_BYTE3 KGDB_DYN_DBG_BRK_BYTE(3) +#define AARCH64_BREAK_KGDB_DYN_DBG \ + (AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5)) +#define KGDB_DYN_BRK_INS_BYTE(x) \ + ((AARCH64_BREAK_KGDB_DYN_DBG >> (8 * (x))) & 0xff) #define CACHE_FLUSH_IS_SAFE 1 @@ -127,13 +115,13 @@ void unregister_break_hook(struct break_hook *hook); u8 debug_monitors_arch(void); -enum debug_el { +enum dbg_active_el { DBG_ACTIVE_EL0 = 0, DBG_ACTIVE_EL1, }; -void enable_debug_monitors(enum debug_el el); -void disable_debug_monitors(enum debug_el el); +void enable_debug_monitors(enum dbg_active_el el); +void disable_debug_monitors(enum dbg_active_el el); void user_rewind_single_step(struct task_struct *task); void user_fastforward_single_step(struct task_struct *task); diff --git a/kernel/arch/arm64/include/asm/dma-mapping.h b/kernel/arch/arm64/include/asm/dma-mapping.h index 9437e3dc5..61e08f360 100644 --- a/kernel/arch/arm64/include/asm/dma-mapping.h +++ b/kernel/arch/arm64/include/asm/dma-mapping.h @@ -21,20 +21,22 @@ #include #include -#include - #include #include #define DMA_ERROR_CODE (~(dma_addr_t)0) -extern struct dma_map_ops *dma_ops; +extern struct dma_map_ops dummy_dma_ops; static inline struct dma_map_ops *__generic_dma_ops(struct device *dev) { - if (unlikely(!dev) || !dev->archdata.dma_ops) - return dma_ops; - else + if (dev && dev->archdata.dma_ops) return dev->archdata.dma_ops; + + /* + * We expect no ISA devices, and all other DMA masters are expected to + * have someone call arch_setup_dma_ops at device creation time. + */ + return &dummy_dma_ops; } static inline struct dma_map_ops *get_dma_ops(struct device *dev) @@ -45,13 +47,15 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) return __generic_dma_ops(dev); } -static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - struct iommu_ops *iommu, bool coherent) -{ - dev->archdata.dma_coherent = coherent; -} +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu, bool coherent); #define arch_setup_dma_ops arch_setup_dma_ops +#ifdef CONFIG_IOMMU_DMA +void arch_teardown_dma_ops(struct device *dev); +#define arch_teardown_dma_ops arch_teardown_dma_ops +#endif + /* do not use this function in a driver */ static inline bool is_device_dma_coherent(struct device *dev) { @@ -72,28 +76,6 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dev_addr) return (phys_addr_t)dev_addr; } -static inline int dma_mapping_error(struct device *dev, dma_addr_t dev_addr) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - debug_dma_mapping_error(dev, dev_addr); - return ops->mapping_error(dev, dev_addr); -} - -static inline int dma_supported(struct device *dev, u64 mask) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - return ops->dma_supported(dev, mask); -} - -static inline 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; -} - static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { if (!dev->dma_mask) @@ -106,50 +88,5 @@ static inline void dma_mark_clean(void *addr, size_t size) { } -#define dma_alloc_coherent(d, s, h, f) dma_alloc_attrs(d, s, h, f, NULL) -#define dma_free_coherent(d, s, h, f) dma_free_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 flags, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - void *vaddr; - - if (dma_alloc_from_coherent(dev, size, dma_handle, &vaddr)) - return vaddr; - - vaddr = ops->alloc(dev, size, dma_handle, flags, attrs); - debug_dma_alloc_coherent(dev, size, *dma_handle, vaddr); - return vaddr; -} - -static inline void dma_free_attrs(struct device *dev, size_t size, - void *vaddr, dma_addr_t dev_addr, - struct dma_attrs *attrs) -{ - struct dma_map_ops *ops = get_dma_ops(dev); - - if (dma_release_from_coherent(dev, get_order(size), vaddr)) - return; - - debug_dma_free_coherent(dev, size, vaddr, dev_addr); - ops->free(dev, size, vaddr, dev_addr, attrs); -} - -/* - * There is no dma_cache_sync() implementation, so just return NULL here. - */ -static inline void *dma_alloc_noncoherent(struct device *dev, size_t size, - dma_addr_t *handle, gfp_t flags) -{ - return NULL; -} - -static inline void dma_free_noncoherent(struct device *dev, size_t size, - void *cpu_addr, dma_addr_t handle) -{ -} - #endif /* __KERNEL__ */ #endif /* __ASM_DMA_MAPPING_H */ diff --git a/kernel/arch/arm64/include/asm/esr.h b/kernel/arch/arm64/include/asm/esr.h index 70522450c..77eeb2cc6 100644 --- a/kernel/arch/arm64/include/asm/esr.h +++ b/kernel/arch/arm64/include/asm/esr.h @@ -18,6 +18,8 @@ #ifndef __ASM_ESR_H #define __ASM_ESR_H +#include + #define ESR_ELx_EC_UNKNOWN (0x00) #define ESR_ELx_EC_WFx (0x01) /* Unallocated EC: 0x02 */ @@ -99,6 +101,13 @@ #define ESR_ELx_WFx_ISS_WFE (UL(1) << 0) #define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1) +/* ESR value templates for specific events */ + +/* BRK instruction trap from AArch64 state */ +#define ESR_ELx_VAL_BRK64(imm) \ + ((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL | \ + ((imm) & 0xffff)) + #ifndef __ASSEMBLY__ #include diff --git a/kernel/arch/arm64/include/asm/exception.h b/kernel/arch/arm64/include/asm/exception.h index 0303705fc..6cb7e1a6b 100644 --- a/kernel/arch/arm64/include/asm/exception.h +++ b/kernel/arch/arm64/include/asm/exception.h @@ -18,7 +18,13 @@ #ifndef __ASM_EXCEPTION_H #define __ASM_EXCEPTION_H +#include + #define __exception __attribute__((section(".exception.text"))) +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#define __exception_irq_entry __irq_entry +#else #define __exception_irq_entry __exception +#endif #endif /* __ASM_EXCEPTION_H */ diff --git a/kernel/arch/arm64/include/asm/fixmap.h b/kernel/arch/arm64/include/asm/fixmap.h index 95e6b6dcb..309704544 100644 --- a/kernel/arch/arm64/include/asm/fixmap.h +++ b/kernel/arch/arm64/include/asm/fixmap.h @@ -8,7 +8,7 @@ * Copyright (C) 1998 Ingo Molnar * Copyright (C) 2013 Mark Salter * - * Adapted from arch/x86_64 version. + * Adapted from arch/x86 version. * */ @@ -17,6 +17,8 @@ #ifndef __ASSEMBLY__ #include +#include +#include #include /* @@ -32,6 +34,20 @@ */ enum fixed_addresses { FIX_HOLE, + + /* + * Reserve a virtual window for the FDT that is 2 MB larger than the + * maximum supported size, and put it at the top of the fixmap region. + * The additional space ensures that any FDT that does not exceed + * MAX_FDT_SIZE can be mapped regardless of whether it crosses any + * 2 MB alignment boundaries. + * + * Keep this at the top so it remains 2 MB aligned. + */ +#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M) + FIX_FDT_END, + FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1, + FIX_EARLYCON_MEM_BASE, FIX_TEXT_POKE0, __end_of_permanent_fixed_addresses, @@ -40,11 +56,7 @@ enum fixed_addresses { * Temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. */ -#ifdef CONFIG_ARM64_64K_PAGES -#define NR_FIX_BTMAPS 4 -#else -#define NR_FIX_BTMAPS 64 -#endif +#define NR_FIX_BTMAPS (SZ_256K / PAGE_SIZE) #define FIX_BTMAPS_SLOTS 7 #define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) diff --git a/kernel/arch/arm64/include/asm/futex.h b/kernel/arch/arm64/include/asm/futex.h index 74069b3bd..007a69fc4 100644 --- a/kernel/arch/arm64/include/asm/futex.h +++ b/kernel/arch/arm64/include/asm/futex.h @@ -20,10 +20,17 @@ #include #include + +#include +#include #include +#include #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \ asm volatile( \ + ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) \ +" prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ insn "\n" \ "2: stlxr %w3, %w0, %2\n" \ @@ -39,6 +46,8 @@ " .align 3\n" \ " .quad 1b, 4b, 2b, 4b\n" \ " .popsection\n" \ + ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) \ : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \ : "r" (oparg), "Ir" (-EFAULT) \ : "memory") @@ -112,6 +121,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, return -EFAULT; asm volatile("// futex_atomic_cmpxchg_inatomic\n" +" prfm pstl1strm, %2\n" "1: ldxr %w1, %2\n" " sub %w3, %w1, %w4\n" " cbnz %w3, 3f\n" diff --git a/kernel/arch/arm64/include/asm/hardirq.h b/kernel/arch/arm64/include/asm/hardirq.h index 6aae421f4..a57601f9d 100644 --- a/kernel/arch/arm64/include/asm/hardirq.h +++ b/kernel/arch/arm64/include/asm/hardirq.h @@ -24,9 +24,7 @@ typedef struct { unsigned int __softirq_pending; -#ifdef CONFIG_SMP unsigned int ipi_irqs[NR_IPI]; -#endif } ____cacheline_aligned irq_cpustat_t; #include /* Standard mappings for irq_cpustat_t above */ @@ -34,10 +32,8 @@ typedef struct { #define __inc_irq_stat(cpu, member) __IRQ_STAT(cpu, member)++ #define __get_irq_stat(cpu, member) __IRQ_STAT(cpu, member) -#ifdef CONFIG_SMP u64 smp_irq_stat_cpu(unsigned int cpu); #define arch_irq_stat_cpu smp_irq_stat_cpu -#endif #define __ARCH_IRQ_EXIT_IRQS_DISABLED 1 @@ -47,9 +43,4 @@ static inline void ack_bad_irq(unsigned int irq) irq_err_count++; } -/* - * No arch-specific IRQ flags. - */ -#define set_irq_flags(irq, flags) - #endif /* __ASM_HARDIRQ_H */ diff --git a/kernel/arch/arm64/include/asm/hugetlb.h b/kernel/arch/arm64/include/asm/hugetlb.h index 5b7ca8ace..bb4052e85 100644 --- a/kernel/arch/arm64/include/asm/hugetlb.h +++ b/kernel/arch/arm64/include/asm/hugetlb.h @@ -13,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __ASM_HUGETLB_H @@ -86,10 +82,6 @@ static inline int prepare_hugepage_range(struct file *file, return 0; } -static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) -{ -} - static inline int huge_pte_none(pte_t pte) { return pte_none(pte); @@ -100,15 +92,6 @@ static inline pte_t huge_pte_wrprotect(pte_t pte) return pte_wrprotect(pte); } -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) { clear_bit(PG_dcache_clean, &page->flags); diff --git a/kernel/arch/arm64/include/asm/hw_breakpoint.h b/kernel/arch/arm64/include/asm/hw_breakpoint.h index 52b484b6a..9732908bf 100644 --- a/kernel/arch/arm64/include/asm/hw_breakpoint.h +++ b/kernel/arch/arm64/include/asm/hw_breakpoint.h @@ -16,6 +16,9 @@ #ifndef __ASM_HW_BREAKPOINT_H #define __ASM_HW_BREAKPOINT_H +#include +#include + #ifdef __KERNEL__ struct arch_hw_breakpoint_ctrl { @@ -132,5 +135,23 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task) extern struct pmu perf_ops_bp; +/* Determine number of BRP registers available. */ +static inline int get_num_brps(void) +{ + u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1); + return 1 + + cpuid_feature_extract_unsigned_field(dfr0, + ID_AA64DFR0_BRPS_SHIFT); +} + +/* Determine number of WRP registers available. */ +static inline int get_num_wrps(void) +{ + u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1); + return 1 + + cpuid_feature_extract_unsigned_field(dfr0, + ID_AA64DFR0_WRPS_SHIFT); +} + #endif /* __KERNEL__ */ #endif /* __ASM_BREAKPOINT_H */ diff --git a/kernel/arch/arm64/include/asm/hwcap.h b/kernel/arch/arm64/include/asm/hwcap.h index 0ad735166..400b80b49 100644 --- a/kernel/arch/arm64/include/asm/hwcap.h +++ b/kernel/arch/arm64/include/asm/hwcap.h @@ -52,6 +52,14 @@ extern unsigned int compat_elf_hwcap, compat_elf_hwcap2; #endif +enum { + CAP_HWCAP = 1, +#ifdef CONFIG_COMPAT + CAP_COMPAT_HWCAP, + CAP_COMPAT_HWCAP2, +#endif +}; + extern unsigned long elf_hwcap; #endif #endif diff --git a/kernel/arch/arm64/include/asm/insn.h b/kernel/arch/arm64/include/asm/insn.h index f81b328d9..30e50eb54 100644 --- a/kernel/arch/arm64/include/asm/insn.h +++ b/kernel/arch/arm64/include/asm/insn.h @@ -281,6 +281,7 @@ __AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000) #undef __AARCH64_INSN_FUNCS bool aarch64_insn_is_nop(u32 insn); +bool aarch64_insn_is_branch_imm(u32 insn); int aarch64_insn_read(void *addr, u32 *insnp); int aarch64_insn_write(void *addr, u32 insn); @@ -351,6 +352,8 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +s32 aarch64_get_branch_offset(u32 insn); +u32 aarch64_set_branch_offset(u32 insn, s32 offset); bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn); diff --git a/kernel/arch/arm64/include/asm/io.h b/kernel/arch/arm64/include/asm/io.h index 540f7c0ae..44be1e03e 100644 --- a/kernel/arch/arm64/include/asm/io.h +++ b/kernel/arch/arm64/include/asm/io.h @@ -117,10 +117,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * ordering rules but do not guarantee any ordering relative to Normal memory * accesses. */ -#define readb_relaxed(c) ({ u8 __v = __raw_readb(c); __v; }) -#define readw_relaxed(c) ({ u16 __v = le16_to_cpu((__force __le16)__raw_readw(c)); __v; }) -#define readl_relaxed(c) ({ u32 __v = le32_to_cpu((__force __le32)__raw_readl(c)); __v; }) -#define readq_relaxed(c) ({ u64 __v = le64_to_cpu((__force __le64)__raw_readq(c)); __v; }) +#define readb_relaxed(c) ({ u8 __r = __raw_readb(c); __r; }) +#define readw_relaxed(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; }) +#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; }) +#define readq_relaxed(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; }) #define writeb_relaxed(v,c) ((void)__raw_writeb((v),(c))) #define writew_relaxed(v,c) ((void)__raw_writew((__force u16)cpu_to_le16(v),(c))) @@ -170,6 +170,7 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); #define ioremap(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_nocache(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_wc(addr, size) __ioremap((addr), (size), __pgprot(PROT_NORMAL_NC)) +#define ioremap_wt(addr, size) __ioremap((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define iounmap __iounmap /* diff --git a/kernel/arch/arm64/include/asm/irq.h b/kernel/arch/arm64/include/asm/irq.h index bbb251b14..8e8d30684 100644 --- a/kernel/arch/arm64/include/asm/irq.h +++ b/kernel/arch/arm64/include/asm/irq.h @@ -1,24 +1,15 @@ #ifndef __ASM_IRQ_H #define __ASM_IRQ_H -#include - #include struct pt_regs; -extern void migrate_irqs(void); extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); -static inline void acpi_irq_init(void) +static inline int nr_legacy_irqs(void) { - /* - * Hardcode ACPI IRQ chip initialization to GICv2 for now. - * Proper irqchip infrastructure will be implemented along with - * incoming GICv2m|GICv3|ITS bits. - */ - acpi_gic_init(); + return 0; } -#define acpi_irq_init acpi_irq_init #endif diff --git a/kernel/arch/arm64/include/asm/irq_work.h b/kernel/arch/arm64/include/asm/irq_work.h index b4f6b19a8..8e24ef3f7 100644 --- a/kernel/arch/arm64/include/asm/irq_work.h +++ b/kernel/arch/arm64/include/asm/irq_work.h @@ -1,8 +1,6 @@ #ifndef __ASM_IRQ_WORK_H #define __ASM_IRQ_WORK_H -#ifdef CONFIG_SMP - #include static inline bool arch_irq_work_has_interrupt(void) @@ -10,13 +8,4 @@ static inline bool arch_irq_work_has_interrupt(void) return !!__smp_cross_call; } -#else - -static inline bool arch_irq_work_has_interrupt(void) -{ - return false; -} - -#endif - #endif /* __ASM_IRQ_WORK_H */ diff --git a/kernel/arch/arm64/include/asm/jump_label.h b/kernel/arch/arm64/include/asm/jump_label.h index c0e5165c2..1b5e0e843 100644 --- a/kernel/arch/arm64/include/asm/jump_label.h +++ b/kernel/arch/arm64/include/asm/jump_label.h @@ -26,14 +26,28 @@ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE -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 goto("1: nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" ".popsection\n\t" - : : "i"(key) : : l_yes); + : : "i"(&((char *)key)[branch]) : : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) +{ + asm goto("1: b %l[l_yes]\n\t" + ".pushsection __jump_table, \"aw\"\n\t" + ".align 3\n\t" + ".quad 1b, %l[l_yes], %c0\n\t" + ".popsection\n\t" + : : "i"(&((char *)key)[branch]) : : l_yes); return false; l_yes: diff --git a/kernel/arch/arm64/include/asm/kasan.h b/kernel/arch/arm64/include/asm/kasan.h new file mode 100644 index 000000000..2774fa384 --- /dev/null +++ b/kernel/arch/arm64/include/asm/kasan.h @@ -0,0 +1,38 @@ +#ifndef __ASM_KASAN_H +#define __ASM_KASAN_H + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_KASAN + +#include +#include + +/* + * KASAN_SHADOW_START: beginning of the kernel virtual addresses. + * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/8 of kernel virtual addresses. + */ +#define KASAN_SHADOW_START (VA_START) +#define KASAN_SHADOW_END (KASAN_SHADOW_START + (1UL << (VA_BITS - 3))) + +/* + * This value is used to map an address to the corresponding shadow + * address by the following formula: + * shadow_addr = (address >> 3) + KASAN_SHADOW_OFFSET; + * + * (1 << 61) shadow addresses - [KASAN_SHADOW_OFFSET,KASAN_SHADOW_END] + * cover all 64-bits of virtual addresses. So KASAN_SHADOW_OFFSET + * should satisfy the following equation: + * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - (1ULL << 61) + */ +#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << (64 - 3))) + +void kasan_init(void); +asmlinkage void kasan_early_init(void); + +#else +static inline void kasan_init(void) { } +#endif + +#endif +#endif diff --git a/kernel/arch/arm64/include/asm/kernel-pgtable.h b/kernel/arch/arm64/include/asm/kernel-pgtable.h new file mode 100644 index 000000000..a459714ee --- /dev/null +++ b/kernel/arch/arm64/include/asm/kernel-pgtable.h @@ -0,0 +1,83 @@ +/* + * Kernel page table mapping + * + * Copyright (C) 2015 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#ifndef __ASM_KERNEL_PGTABLE_H +#define __ASM_KERNEL_PGTABLE_H + + +/* + * The linear mapping and the start of memory are both 2M aligned (per + * the arm64 booting.txt requirements). Hence we can use section mapping + * with 4K (section size = 2M) but not with 16K (section size = 32M) or + * 64K (section size = 512M). + */ +#ifdef CONFIG_ARM64_4K_PAGES +#define ARM64_SWAPPER_USES_SECTION_MAPS 1 +#else +#define ARM64_SWAPPER_USES_SECTION_MAPS 0 +#endif + +/* + * The idmap and swapper page tables need some space reserved in the kernel + * image. Both require pgd, pud (4 levels only) and pmd tables to (section) + * map the kernel. With the 64K page configuration, swapper and idmap need to + * map to pte level. The swapper also maps the FDT (see __create_page_tables + * for more information). Note that the number of ID map translation levels + * could be increased on the fly if system RAM is out of reach for the default + * VA range, so pages required to map highest possible PA are reserved in all + * cases. + */ +#if ARM64_SWAPPER_USES_SECTION_MAPS +#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) +#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT) - 1) +#else +#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) +#define IDMAP_PGTABLE_LEVELS (ARM64_HW_PGTABLE_LEVELS(PHYS_MASK_SHIFT)) +#endif + +#define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE) +#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE) + +/* Initial memory map size */ +#if ARM64_SWAPPER_USES_SECTION_MAPS +#define SWAPPER_BLOCK_SHIFT SECTION_SHIFT +#define SWAPPER_BLOCK_SIZE SECTION_SIZE +#define SWAPPER_TABLE_SHIFT PUD_SHIFT +#else +#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT +#define SWAPPER_BLOCK_SIZE PAGE_SIZE +#define SWAPPER_TABLE_SHIFT PMD_SHIFT +#endif + +/* The size of the initial kernel direct mapping */ +#define SWAPPER_INIT_MAP_SIZE (_AC(1, UL) << SWAPPER_TABLE_SHIFT) + +/* + * Initial memory map attributes. + */ +#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) +#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) + +#if ARM64_SWAPPER_USES_SECTION_MAPS +#define SWAPPER_MM_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS) +#else +#define SWAPPER_MM_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS) +#endif + + +#endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/kernel/arch/arm64/include/asm/kvm_arm.h b/kernel/arch/arm64/include/asm/kvm_arm.h index ac6fafb95..5e6857b6b 100644 --- a/kernel/arch/arm64/include/asm/kvm_arm.h +++ b/kernel/arch/arm64/include/asm/kvm_arm.h @@ -95,6 +95,7 @@ SCTLR_EL2_SA | SCTLR_EL2_I) /* TCR_EL2 Registers bits */ +#define TCR_EL2_RES1 ((1 << 31) | (1 << 23)) #define TCR_EL2_TBI (1 << 20) #define TCR_EL2_PS (7 << 16) #define TCR_EL2_PS_40B (2 << 16) @@ -106,9 +107,10 @@ #define TCR_EL2_MASK (TCR_EL2_TG0 | TCR_EL2_SH0 | \ TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ) -#define TCR_EL2_FLAGS (TCR_EL2_PS_40B) +#define TCR_EL2_FLAGS (TCR_EL2_RES1 | TCR_EL2_PS_40B) /* VTCR_EL2 Registers bits */ +#define VTCR_EL2_RES1 (1 << 31) #define VTCR_EL2_PS_MASK (7 << 16) #define VTCR_EL2_TG0_MASK (1 << 14) #define VTCR_EL2_TG0_4K (0 << 14) @@ -147,7 +149,8 @@ */ #define VTCR_EL2_FLAGS (VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \ - VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B) + VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \ + VTCR_EL2_RES1) #define VTTBR_X (38 - VTCR_EL2_T0SZ_40B) #else /* @@ -158,7 +161,8 @@ */ #define VTCR_EL2_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \ VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \ - VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B) + VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \ + VTCR_EL2_RES1) #define VTTBR_X (37 - VTCR_EL2_T0SZ_40B) #endif @@ -168,13 +172,15 @@ #define VTTBR_VMID_MASK (UL(0xFF) << VTTBR_VMID_SHIFT) /* Hyp System Trap Register */ -#define HSTR_EL2_TTEE (1 << 16) #define HSTR_EL2_T(x) (1 << x) +/* Hyp Coproccessor Trap Register Shifts */ +#define CPTR_EL2_TFP_SHIFT 10 + /* Hyp Coprocessor Trap Register */ #define CPTR_EL2_TCPAC (1 << 31) #define CPTR_EL2_TTA (1 << 20) -#define CPTR_EL2_TFP (1 << 10) +#define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT) /* Hyp Debug Configuration Register bits */ #define MDCR_EL2_TDRA (1 << 11) @@ -194,4 +200,20 @@ /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ #define HPFAR_MASK (~UL(0xf)) +#define kvm_arm_exception_type \ + {0, "IRQ" }, \ + {1, "TRAP" } + +#define ECN(x) { ESR_ELx_EC_##x, #x } + +#define kvm_arm_exception_class \ + ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \ + ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(CP14_64), ECN(SVC64), \ + ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(IMP_DEF), ECN(IABT_LOW), \ + ECN(IABT_CUR), ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \ + ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \ + ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \ + ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ + ECN(BKPT32), ECN(VECTOR32), ECN(BRK64) + #endif /* __ARM64_KVM_ARM_H__ */ diff --git a/kernel/arch/arm64/include/asm/kvm_asm.h b/kernel/arch/arm64/include/asm/kvm_asm.h index 4f7310fa7..5e377101f 100644 --- a/kernel/arch/arm64/include/asm/kvm_asm.h +++ b/kernel/arch/arm64/include/asm/kvm_asm.h @@ -27,7 +27,7 @@ #define MPIDR_EL1 1 /* MultiProcessor Affinity Register */ #define CSSELR_EL1 2 /* Cache Size Selection Register */ #define SCTLR_EL1 3 /* System Control Register */ -#define ACTLR_EL1 4 /* Auxilliary Control Register */ +#define ACTLR_EL1 4 /* Auxiliary Control Register */ #define CPACR_EL1 5 /* Coprocessor Access Control */ #define TTBR0_EL1 6 /* Translation Table Base Register 0 */ #define TTBR1_EL1 7 /* Translation Table Base Register 1 */ @@ -46,24 +46,14 @@ #define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */ #define PAR_EL1 21 /* Physical Address Register */ #define MDSCR_EL1 22 /* Monitor Debug System Control Register */ -#define DBGBCR0_EL1 23 /* Debug Breakpoint Control Registers (0-15) */ -#define DBGBCR15_EL1 38 -#define DBGBVR0_EL1 39 /* Debug Breakpoint Value Registers (0-15) */ -#define DBGBVR15_EL1 54 -#define DBGWCR0_EL1 55 /* Debug Watchpoint Control Registers (0-15) */ -#define DBGWCR15_EL1 70 -#define DBGWVR0_EL1 71 /* Debug Watchpoint Value Registers (0-15) */ -#define DBGWVR15_EL1 86 -#define MDCCINT_EL1 87 /* Monitor Debug Comms Channel Interrupt Enable Reg */ +#define MDCCINT_EL1 23 /* Monitor Debug Comms Channel Interrupt Enable Reg */ /* 32bit specific registers. Keep them at the end of the range */ -#define DACR32_EL2 88 /* Domain Access Control Register */ -#define IFSR32_EL2 89 /* Instruction Fault Status Register */ -#define FPEXC32_EL2 90 /* Floating-Point Exception Control Register */ -#define DBGVCR32_EL2 91 /* Debug Vector Catch Register */ -#define TEECR32_EL1 92 /* ThumbEE Configuration Register */ -#define TEEHBR32_EL1 93 /* ThumbEE Handler Base Register */ -#define NR_SYS_REGS 94 +#define DACR32_EL2 24 /* Domain Access Control Register */ +#define IFSR32_EL2 25 /* Instruction Fault Status Register */ +#define FPEXC32_EL2 26 /* Floating-Point Exception Control Register */ +#define DBGVCR32_EL2 27 /* Debug Vector Catch Register */ +#define NR_SYS_REGS 28 /* 32bit mapping */ #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ @@ -132,10 +122,7 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); extern u64 __vgic_v3_get_ich_vtr_el2(void); -extern char __save_vgic_v2_state[]; -extern char __restore_vgic_v2_state[]; -extern char __save_vgic_v3_state[]; -extern char __restore_vgic_v3_state[]; +extern u32 __kvm_get_mdcr_el2(void); #endif diff --git a/kernel/arch/arm64/include/asm/kvm_emulate.h b/kernel/arch/arm64/include/asm/kvm_emulate.h index 17e92f05b..25a40213b 100644 --- a/kernel/arch/arm64/include/asm/kvm_emulate.h +++ b/kernel/arch/arm64/include/asm/kvm_emulate.h @@ -99,12 +99,22 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) *vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT; } -static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num) +/* + * vcpu_get_reg and vcpu_set_reg should always be passed a register number + * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on + * AArch32 with banked registers. + */ +static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, + u8 reg_num) { - if (vcpu_mode_is_32bit(vcpu)) - return vcpu_reg32(vcpu, reg_num); + return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; +} - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num]; +static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, + unsigned long val) +{ + if (reg_num != 31) + vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val; } /* Get vcpu SPSR for current mode */ diff --git a/kernel/arch/arm64/include/asm/kvm_host.h b/kernel/arch/arm64/include/asm/kvm_host.h index f0f58c9be..a35ce7266 100644 --- a/kernel/arch/arm64/include/asm/kvm_host.h +++ b/kernel/arch/arm64/include/asm/kvm_host.h @@ -30,19 +30,16 @@ #define __KVM_HAVE_ARCH_INTC_INITIALIZED -#if defined(CONFIG_KVM_ARM_MAX_VCPUS) -#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS -#else -#define KVM_MAX_VCPUS 0 -#endif - #define KVM_USER_MEM_SLOTS 32 #define KVM_PRIVATE_MEM_SLOTS 4 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_HALT_POLL_NS_DEFAULT 500000 #include #include +#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS + #define KVM_VCPU_MAX_FEATURES 3 int __attribute_const__ kvm_target_cpu(void); @@ -103,15 +100,34 @@ struct kvm_vcpu_arch { /* HYP configuration */ u64 hcr_el2; + u32 mdcr_el2; /* Exception Information */ struct kvm_vcpu_fault_info fault; - /* Debug state */ + /* Guest debug state */ u64 debug_flags; + /* + * We maintain more than a single set of debug registers to support + * debugging the guest from the host and to maintain separate host and + * guest state during world switches. vcpu_debug_state are the debug + * registers of the vcpu as the guest sees them. host_debug_state are + * the host registers which are saved and restored during + * world switches. external_debug_state contains the debug + * values we want to debug the guest. This is set via the + * KVM_SET_GUEST_DEBUG ioctl. + * + * debug_ptr points to the set of debug registers that should be loaded + * onto the hardware when running the guest. + */ + struct kvm_guest_debug_arch *debug_ptr; + struct kvm_guest_debug_arch vcpu_debug_state; + struct kvm_guest_debug_arch external_debug_state; + /* Pointer to host CPU context */ kvm_cpu_context_t *host_cpu_context; + struct kvm_guest_debug_arch host_debug_state; /* VGIC state */ struct vgic_cpu vgic_cpu; @@ -122,7 +138,21 @@ struct kvm_vcpu_arch { * here. */ - /* Don't run the guest */ + /* + * Guest registers we preserve during guest debugging. + * + * These shadow registers are updated by the kvm_handle_sys_reg + * trap handler if the guest accesses or updates them while we + * are using guest debug. + */ + struct { + u32 mdscr_el1; + } guest_debug_preserved; + + /* vcpu power-off state */ + bool power_off; + + /* Don't run the guest (internal implementation need) */ bool pause; /* IO related fields */ @@ -165,6 +195,7 @@ struct kvm_vm_stat { struct kvm_vcpu_stat { u32 halt_successful_poll; + u32 halt_attempted_poll; u32 halt_wakeup; }; @@ -216,38 +247,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr, hyp_stack_ptr, vector_ptr); } -struct vgic_sr_vectors { - void *save_vgic; - void *restore_vgic; -}; - -static inline void vgic_arch_setup(const struct vgic_params *vgic) -{ - extern struct vgic_sr_vectors __vgic_sr_vectors; - - switch(vgic->type) - { - case VGIC_V2: - __vgic_sr_vectors.save_vgic = __save_vgic_v2_state; - __vgic_sr_vectors.restore_vgic = __restore_vgic_v2_state; - break; - -#ifdef CONFIG_ARM_GIC_V3 - case VGIC_V3: - __vgic_sr_vectors.save_vgic = __save_vgic_v3_state; - __vgic_sr_vectors.restore_vgic = __restore_vgic_v3_state; - break; -#endif - - default: - BUG(); - } -} - static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} +void kvm_arm_init_debug(void); +void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); +void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); +void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/kernel/arch/arm64/include/asm/lse.h b/kernel/arch/arm64/include/asm/lse.h new file mode 100644 index 000000000..3de42d686 --- /dev/null +++ b/kernel/arch/arm64/include/asm/lse.h @@ -0,0 +1,53 @@ +#ifndef __ASM_LSE_H +#define __ASM_LSE_H + +#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) + +#include +#include +#include + +#ifdef __ASSEMBLER__ + +.arch_extension lse + +.macro alt_lse, llsc, lse + alternative_insn "\llsc", "\lse", ARM64_HAS_LSE_ATOMICS +.endm + +#else /* __ASSEMBLER__ */ + +__asm__(".arch_extension lse"); + +/* Move the ll/sc atomics out-of-line */ +#define __LL_SC_INLINE +#define __LL_SC_PREFIX(x) __ll_sc_##x +#define __LL_SC_EXPORT(x) EXPORT_SYMBOL(__LL_SC_PREFIX(x)) + +/* Macro for constructing calls to out-of-line ll/sc atomics */ +#define __LL_SC_CALL(op) "bl\t" __stringify(__LL_SC_PREFIX(op)) "\n" + +/* In-line patching at runtime */ +#define ARM64_LSE_ATOMIC_INSN(llsc, lse) \ + ALTERNATIVE(llsc, lse, ARM64_HAS_LSE_ATOMICS) + +#endif /* __ASSEMBLER__ */ +#else /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ + +#ifdef __ASSEMBLER__ + +.macro alt_lse, llsc, lse + \llsc +.endm + +#else /* __ASSEMBLER__ */ + +#define __LL_SC_INLINE static inline +#define __LL_SC_PREFIX(x) x +#define __LL_SC_EXPORT(x) + +#define ARM64_LSE_ATOMIC_INSN(llsc, lse) llsc + +#endif /* __ASSEMBLER__ */ +#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ +#endif /* __ASM_LSE_H */ diff --git a/kernel/arch/arm64/include/asm/memory.h b/kernel/arch/arm64/include/asm/memory.h index 44a59c20e..853953cd1 100644 --- a/kernel/arch/arm64/include/asm/memory.h +++ b/kernel/arch/arm64/include/asm/memory.h @@ -42,12 +42,14 @@ * PAGE_OFFSET - the virtual address of the start of the kernel image (top * (VA_BITS - 1)) * VA_BITS - the maximum number of bits for virtual addresses. + * VA_START - the first kernel virtual address. * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. * The module space lives between the addresses given by TASK_SIZE * and PAGE_OFFSET - it must be within 128MB of the kernel text. */ #define VA_BITS (CONFIG_ARM64_VA_BITS) +#define VA_START (UL(0xffffffffffffffff) << VA_BITS) #define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1)) #define MODULES_END (PAGE_OFFSET) #define MODULES_VADDR (MODULES_END - SZ_64M) @@ -68,10 +70,6 @@ #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4)) -#if TASK_SIZE_64 > MODULES_VADDR -#error Top of 64-bit user space clashes with start of module space -#endif - /* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h @@ -80,12 +78,6 @@ #define __virt_to_phys(x) (((phys_addr_t)(x) - PAGE_OFFSET + PHYS_OFFSET)) #define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET + PAGE_OFFSET)) -/* - * Convert a physical address to a Page Frame Number and back - */ -#define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) -#define __pfn_to_phys(pfn) ((phys_addr_t)(pfn) << PAGE_SHIFT) - /* * Convert a page to/from a physical address */ @@ -100,6 +92,7 @@ #define MT_DEVICE_GRE 2 #define MT_NORMAL_NC 3 #define MT_NORMAL 4 +#define MT_NORMAL_WT 5 /* * Memory types for Stage-2 translation diff --git a/kernel/arch/arm64/include/asm/mmu.h b/kernel/arch/arm64/include/asm/mmu.h index 3d311761e..990124a67 100644 --- a/kernel/arch/arm64/include/asm/mmu.h +++ b/kernel/arch/arm64/include/asm/mmu.h @@ -17,22 +17,23 @@ #define __ASM_MMU_H typedef struct { - unsigned int id; - raw_spinlock_t id_lock; - void *vdso; + atomic64_t id; + void *vdso; } mm_context_t; -#define INIT_MM_CONTEXT(name) \ - .context.id_lock = __RAW_SPIN_LOCK_UNLOCKED(name.context.id_lock), - -#define ASID(mm) ((mm)->context.id & 0xffff) +/* + * This macro is only used by the TLBI code, which cannot race with an + * ASID change and therefore doesn't need to reload the counter using + * atomic64_read. + */ +#define ASID(mm) ((mm)->context.id.counter & 0xffff) extern void paging_init(void); -extern void setup_mm_for_reboot(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); +extern void *fixmap_remap_fdt(phys_addr_t dt_phys); #endif diff --git a/kernel/arch/arm64/include/asm/mmu_context.h b/kernel/arch/arm64/include/asm/mmu_context.h index 8ec41e5f5..24165784b 100644 --- a/kernel/arch/arm64/include/asm/mmu_context.h +++ b/kernel/arch/arm64/include/asm/mmu_context.h @@ -28,13 +28,6 @@ #include #include -#define MAX_ASID_BITS 16 - -extern unsigned int cpu_last_asid; - -void __init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void __new_context(struct mm_struct *mm); - #ifdef CONFIG_PID_IN_CONTEXTIDR static inline void contextidr_thread_switch(struct task_struct *next) { @@ -77,96 +70,38 @@ static inline bool __cpu_uses_extended_idmap(void) unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS))); } -static inline void __cpu_set_tcr_t0sz(u64 t0sz) -{ - unsigned long tcr; - - if (__cpu_uses_extended_idmap()) - asm volatile ( - " mrs %0, tcr_el1 ;" - " bfi %0, %1, %2, %3 ;" - " msr tcr_el1, %0 ;" - " isb" - : "=&r" (tcr) - : "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH)); -} - -/* - * Set TCR.T0SZ to the value appropriate for activating the identity map. - */ -static inline void cpu_set_idmap_tcr_t0sz(void) -{ - __cpu_set_tcr_t0sz(idmap_t0sz); -} - /* * Set TCR.T0SZ to its default value (based on VA_BITS) */ static inline void cpu_set_default_tcr_t0sz(void) { - __cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS)); -} - -static inline void switch_new_context(struct mm_struct *mm) -{ - unsigned long flags; - - __new_context(mm); + unsigned long tcr; - local_irq_save(flags); - cpu_switch_mm(mm->pgd, mm); - local_irq_restore(flags); -} + if (!__cpu_uses_extended_idmap()) + return; -static inline void check_and_switch_context(struct mm_struct *mm, - struct task_struct *tsk) -{ - /* - * Required during context switch to avoid speculative page table - * walking with the wrong TTBR. - */ - cpu_set_reserved_ttbr0(); - - if (!((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) - /* - * The ASID is from the current generation, just switch to the - * new pgd. This condition is only true for calls from - * context_switch() and interrupts are already disabled. - */ - cpu_switch_mm(mm->pgd, mm); - else if (irqs_disabled()) - /* - * Defer the new ASID allocation until after the context - * switch critical region since __new_context() cannot be - * called with interrupts disabled. - */ - set_ti_thread_flag(task_thread_info(tsk), TIF_SWITCH_MM); - else - /* - * That is a direct call to switch_mm() or activate_mm() with - * interrupts enabled and a new context. - */ - switch_new_context(mm); + asm volatile ( + " mrs %0, tcr_el1 ;" + " bfi %0, %1, %2, %3 ;" + " msr tcr_el1, %0 ;" + " isb" + : "=&r" (tcr) + : "r"(TCR_T0SZ(VA_BITS)), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH)); } -#define init_new_context(tsk,mm) (__init_new_context(tsk,mm),0) +/* + * It would be nice to return ASIDs back to the allocator, but unfortunately + * that introduces a race with a generation rollover where we could erroneously + * free an ASID allocated in a future generation. We could workaround this by + * freeing the ASID from the context of the dying mm (e.g. in arch_exit_mmap), + * but we'd then need to make sure that we didn't dirty any TLBs afterwards. + * Setting a reserved TTBR0 or EPD0 would work, but it all gets ugly when you + * take CPU migration into account. + */ #define destroy_context(mm) do { } while(0) +void check_and_switch_context(struct mm_struct *mm, unsigned int cpu); -#define finish_arch_post_lock_switch \ - finish_arch_post_lock_switch -static inline void finish_arch_post_lock_switch(void) -{ - if (test_and_clear_thread_flag(TIF_SWITCH_MM)) { - struct mm_struct *mm = current->mm; - unsigned long flags; - - __new_context(mm); - - local_irq_save(flags); - cpu_switch_mm(mm->pgd, mm); - local_irq_restore(flags); - } -} +#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) /* * This is called when "tsk" is about to enter lazy TLB mode. @@ -194,6 +129,9 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, { unsigned int cpu = smp_processor_id(); + if (prev == next) + return; + /* * init_mm.pgd does not contain any user mappings and it is always * active for kernel addresses in TTBR1. Just set the reserved TTBR0. @@ -203,8 +141,7 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next, return; } - if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next) - check_and_switch_context(next, tsk); + check_and_switch_context(next, cpu); } #define deactivate_mm(tsk,mm) do { } while (0) diff --git a/kernel/arch/arm64/include/asm/page.h b/kernel/arch/arm64/include/asm/page.h index 7d9c7e4a4..9b2f5a9d0 100644 --- a/kernel/arch/arm64/include/asm/page.h +++ b/kernel/arch/arm64/include/asm/page.h @@ -20,31 +20,22 @@ #define __ASM_PAGE_H /* PAGE_SHIFT determines the page size */ +/* CONT_SHIFT determines the number of pages which can be tracked together */ #ifdef CONFIG_ARM64_64K_PAGES #define PAGE_SHIFT 16 +#define CONT_SHIFT 5 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define PAGE_SHIFT 14 +#define CONT_SHIFT 7 #else #define PAGE_SHIFT 12 +#define CONT_SHIFT 4 #endif -#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) +#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) -/* - * The idmap and swapper page tables need some space reserved in the kernel - * image. Both require pgd, pud (4 levels only) and pmd tables to (section) - * map the kernel. With the 64K page configuration, swapper and idmap need to - * map to pte level. The swapper also maps the FDT (see __create_page_tables - * for more information). Note that the number of ID map translation levels - * could be increased on the fly if system RAM is out of reach for the default - * VA range, so 3 pages are reserved in all cases. - */ -#ifdef CONFIG_ARM64_64K_PAGES -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) -#else -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) -#endif - -#define SWAPPER_DIR_SIZE (SWAPPER_PGTABLE_LEVELS * PAGE_SIZE) -#define IDMAP_DIR_SIZE (3 * PAGE_SIZE) +#define CONT_SIZE (_AC(1, UL) << (CONT_SHIFT + PAGE_SHIFT)) +#define CONT_MASK (~(CONT_SIZE-1)) #ifndef __ASSEMBLY__ diff --git a/kernel/arch/arm64/include/asm/percpu.h b/kernel/arch/arm64/include/asm/percpu.h index 4fde8c1df..0a456bef8 100644 --- a/kernel/arch/arm64/include/asm/percpu.h +++ b/kernel/arch/arm64/include/asm/percpu.h @@ -16,8 +16,6 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H -#ifdef CONFIG_SMP - static inline void set_my_cpu_offset(unsigned long off) { asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory"); @@ -38,12 +36,6 @@ static inline unsigned long __my_cpu_offset(void) } #define __my_cpu_offset __my_cpu_offset() -#else /* !CONFIG_SMP */ - -#define set_my_cpu_offset(x) do { } while (0) - -#endif /* CONFIG_SMP */ - #define PERCPU_OP(op, asm_op) \ static inline unsigned long __percpu_##op(void *ptr, \ unsigned long val, int size) \ diff --git a/kernel/arch/arm64/include/asm/perf_event.h b/kernel/arch/arm64/include/asm/perf_event.h index d26d1d53c..7bd3cdb53 100644 --- a/kernel/arch/arm64/include/asm/perf_event.h +++ b/kernel/arch/arm64/include/asm/perf_event.h @@ -17,11 +17,18 @@ #ifndef __ASM_PERF_EVENT_H #define __ASM_PERF_EVENT_H -#ifdef CONFIG_HW_PERF_EVENTS +#ifdef CONFIG_PERF_EVENTS struct pt_regs; extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) #endif +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->pc = (__ip); \ + (regs)->regs[29] = (unsigned long) __builtin_frame_address(0); \ + (regs)->sp = current_stack_pointer; \ + (regs)->pstate = PSR_MODE_EL1h; \ +} + #endif diff --git a/kernel/arch/arm64/include/asm/pgalloc.h b/kernel/arch/arm64/include/asm/pgalloc.h index 76420568d..c15053902 100644 --- a/kernel/arch/arm64/include/asm/pgalloc.h +++ b/kernel/arch/arm64/include/asm/pgalloc.h @@ -27,6 +27,7 @@ #define check_pgt_cache() do { } while (0) #define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) +#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 diff --git a/kernel/arch/arm64/include/asm/pgtable-hwdef.h b/kernel/arch/arm64/include/asm/pgtable-hwdef.h index 59bfae75d..d6739e836 100644 --- a/kernel/arch/arm64/include/asm/pgtable-hwdef.h +++ b/kernel/arch/arm64/include/asm/pgtable-hwdef.h @@ -16,13 +16,46 @@ #ifndef __ASM_PGTABLE_HWDEF_H #define __ASM_PGTABLE_HWDEF_H +/* + * Number of page-table levels required to address 'va_bits' wide + * address, without section mapping. We resolve the top (va_bits - PAGE_SHIFT) + * bits with (PAGE_SHIFT - 3) bits at each page table level. Hence: + * + * levels = DIV_ROUND_UP((va_bits - PAGE_SHIFT), (PAGE_SHIFT - 3)) + * + * where DIV_ROUND_UP(n, d) => (((n) + (d) - 1) / (d)) + * + * We cannot include linux/kernel.h which defines DIV_ROUND_UP here + * due to build issues. So we open code DIV_ROUND_UP here: + * + * ((((va_bits) - PAGE_SHIFT) + (PAGE_SHIFT - 3) - 1) / (PAGE_SHIFT - 3)) + * + * which gets simplified as : + */ +#define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3)) + +/* + * Size mapped by an entry at level n ( 0 <= n <= 3) + * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits + * in the final page. The maximum number of translation levels supported by + * the architecture is 4. Hence, starting at at level n, we have further + * ((4 - n) - 1) levels of translation excluding the offset within the page. + * So, the total number of bits mapped by an entry at level n is : + * + * ((4 - n) - 1) * (PAGE_SHIFT - 3) + PAGE_SHIFT + * + * Rearranging it a bit we get : + * (4 - n) * (PAGE_SHIFT - 3) + 3 + */ +#define ARM64_HW_PGTABLE_LEVEL_SHIFT(n) ((PAGE_SHIFT - 3) * (4 - (n)) + 3) + #define PTRS_PER_PTE (1 << (PAGE_SHIFT - 3)) /* * PMD_SHIFT determines the size a level 2 page table entry can map. */ #if CONFIG_PGTABLE_LEVELS > 2 -#define PMD_SHIFT ((PAGE_SHIFT - 3) * 2 + 3) +#define PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2) #define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) #define PTRS_PER_PMD PTRS_PER_PTE @@ -32,7 +65,7 @@ * PUD_SHIFT determines the size a level 1 page table entry can map. */ #if CONFIG_PGTABLE_LEVELS > 3 -#define PUD_SHIFT ((PAGE_SHIFT - 3) * 3 + 3) +#define PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1) #define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_MASK (~(PUD_SIZE-1)) #define PTRS_PER_PUD PTRS_PER_PTE @@ -42,7 +75,7 @@ * PGDIR_SHIFT determines the size a top-level page table entry can map * (depending on the configuration, this level can be 0, 1 or 2). */ -#define PGDIR_SHIFT ((PAGE_SHIFT - 3) * CONFIG_PGTABLE_LEVELS + 3) +#define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) #define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT)) @@ -54,6 +87,13 @@ #define SECTION_SIZE (_AC(1, UL) << SECTION_SHIFT) #define SECTION_MASK (~(SECTION_SIZE-1)) +/* + * Contiguous page definitions. + */ +#define CONT_PTES (_AC(1, UL) << CONT_SHIFT) +/* the the numerical offset of the PTE within a range of CONT_PTES */ +#define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1)) + /* * Hardware page table definitions. * @@ -83,6 +123,7 @@ #define PMD_SECT_S (_AT(pmdval_t, 3) << 8) #define PMD_SECT_AF (_AT(pmdval_t, 1) << 10) #define PMD_SECT_NG (_AT(pmdval_t, 1) << 11) +#define PMD_SECT_CONT (_AT(pmdval_t, 1) << 52) #define PMD_SECT_PXN (_AT(pmdval_t, 1) << 53) #define PMD_SECT_UXN (_AT(pmdval_t, 1) << 54) @@ -104,6 +145,8 @@ #define PTE_SHARED (_AT(pteval_t, 3) << 8) /* SH[1:0], inner shareable */ #define PTE_AF (_AT(pteval_t, 1) << 10) /* Access Flag */ #define PTE_NG (_AT(pteval_t, 1) << 11) /* nG */ +#define PTE_DBM (_AT(pteval_t, 1) << 51) /* Dirty Bit Management */ +#define PTE_CONT (_AT(pteval_t, 1) << 52) /* Contiguous range */ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ #define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */ @@ -168,5 +211,7 @@ #define TCR_TG1_64K (UL(3) << 30) #define TCR_ASID16 (UL(1) << 36) #define TCR_TBI0 (UL(1) << 37) +#define TCR_HA (UL(1) << 39) +#define TCR_HD (UL(1) << 40) #endif diff --git a/kernel/arch/arm64/include/asm/pgtable.h b/kernel/arch/arm64/include/asm/pgtable.h index 56283f8a6..eaa9cabf4 100644 --- a/kernel/arch/arm64/include/asm/pgtable.h +++ b/kernel/arch/arm64/include/asm/pgtable.h @@ -16,6 +16,7 @@ #ifndef __ASM_PGTABLE_H #define __ASM_PGTABLE_H +#include #include #include @@ -25,44 +26,53 @@ * Software defined PTE bits definition. */ #define PTE_VALID (_AT(pteval_t, 1) << 0) +#define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) -#define PTE_WRITE (_AT(pteval_t, 1) << 57) #define PTE_PROT_NONE (_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */ /* * VMALLOC and SPARSEMEM_VMEMMAP ranges. * - * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array + * VMEMAP_SIZE: allows the whole linear region to be covered by a struct page array * (rounded up to PUD_SIZE). * VMALLOC_START: beginning of the kernel VA space * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space, * fixed mappings and modules */ #define VMEMMAP_SIZE ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE) -#define VMALLOC_START (UL(0xffffffffffffffff) << VA_BITS) + +#ifndef CONFIG_KASAN +#define VMALLOC_START (VA_START) +#else +#include +#define VMALLOC_START (KASAN_SHADOW_END + SZ_64K) +#endif + #define VMALLOC_END (PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K) -#define vmemmap ((struct page *)(VMALLOC_END + SZ_64K)) +#define VMEMMAP_START (VMALLOC_END + SZ_64K) +#define vmemmap ((struct page *)VMEMMAP_START - \ + SECTION_ALIGN_DOWN(memstart_addr >> PAGE_SHIFT)) #define FIRST_USER_ADDRESS 0UL #ifndef __ASSEMBLY__ + +#include + extern void __pte_error(const char *file, int line, unsigned long val); extern void __pmd_error(const char *file, int line, unsigned long val); extern void __pud_error(const char *file, int line, unsigned long val); extern void __pgd_error(const char *file, int line, unsigned long val); -#ifdef CONFIG_SMP #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#else -#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF) -#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF) -#endif +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL_WT)) #define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) @@ -72,7 +82,10 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define _PAGE_DEFAULT (PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) #define PAGE_KERNEL __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_RO __pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY) +#define PAGE_KERNEL_ROX __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE) +#define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT) #define PAGE_HYP __pgprot(_PAGE_DEFAULT | PTE_HYP) #define PAGE_HYP_DEVICE __pgprot(PROT_DEVICE_nGnRE | PTE_HYP) @@ -80,7 +93,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val); #define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY) #define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN) -#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_TYPE_MASK) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) +#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN) #define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN) @@ -137,12 +150,21 @@ extern struct page *empty_zero_page; * The following only work if pte_present(). Undefined behaviour otherwise. */ #define pte_present(pte) (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))) -#define pte_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_exec(pte) (!(pte_val(pte) & PTE_UXN)) +#define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) +#ifdef CONFIG_ARM64_HW_AFDBM +#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY)) +#else +#define pte_hw_dirty(pte) (0) +#endif +#define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) +#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) + +#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_valid_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ @@ -195,6 +217,16 @@ static inline pte_t pte_mkspecial(pte_t pte) return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } +static inline pte_t pte_mkcont(pte_t pte) +{ + return set_pte_bit(pte, __pgprot(PTE_CONT)); +} + +static inline pte_t pte_mknoncont(pte_t pte) +{ + return clear_pte_bit(pte, __pgprot(PTE_CONT)); +} + static inline void set_pte(pte_t *ptep, pte_t pte) { *ptep = pte; @@ -209,20 +241,53 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } } +struct mm_struct; +struct vm_area_struct; + extern void __sync_icache_dcache(pte_t pteval, unsigned long addr); +/* + * PTE bits configuration in the presence of hardware Dirty Bit Management + * (PTE_WRITE == PTE_DBM): + * + * Dirty Writable | PTE_RDONLY PTE_WRITE PTE_DIRTY (sw) + * 0 0 | 1 0 0 + * 0 1 | 1 1 0 + * 1 0 | 1 0 1 + * 1 1 | 0 1 x + * + * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via + * the page fault mechanism. Checking the dirty status of a pte becomes: + * + * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) + */ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (pte_valid_user(pte)) { if (!pte_special(pte) && pte_exec(pte)) __sync_icache_dcache(pte, addr); - if (pte_dirty(pte) && pte_write(pte)) + if (pte_sw_dirty(pte) && pte_write(pte)) pte_val(pte) &= ~PTE_RDONLY; else pte_val(pte) |= PTE_RDONLY; } + /* + * If the existing pte is valid, check for potential race with + * hardware updates of the pte (ptep_set_access_flags safely changes + * valid ptes without going through an invalid entry). + */ + if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && + pte_valid(*ptep) && pte_valid(pte)) { + VM_WARN_ONCE(!pte_young(pte), + "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); + VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte), + "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", + __func__, pte_val(*ptep), pte_val(pte)); + } + set_pte(ptep, pte); } @@ -460,7 +525,10 @@ static inline pud_t *pud_offset(pgd_t *pgd, unsigned long addr) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | - PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK; + PTE_PROT_NONE | PTE_VALID | PTE_WRITE; + /* preserve the hardware dirty information */ + if (pte_hw_dirty(pte)) + pte = pte_mkdirty(pte); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); return pte; } @@ -470,6 +538,101 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); } +#ifdef CONFIG_ARM64_HW_AFDBM +/* + * Atomic pte/pmd modifications. + */ +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pte_t *ptep) +{ + pteval_t pteval; + unsigned int tmp, res; + + asm volatile("// ptep_test_and_clear_young\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " ubfx %w3, %w0, %5, #1 // extract PTE_AF (young)\n" + " and %0, %0, %4 // clear PTE_AF\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res) + : "L" (~PTE_AF), "I" (ilog2(PTE_AF))); + + return res; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + pteval_t old_pteval; + unsigned int tmp; + + asm volatile("// ptep_get_and_clear\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " stxr %w1, xzr, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))); + + return __pte(old_pteval); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_GET_AND_CLEAR +static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp)); +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +/* + * ptep_set_wrprotect - mark read-only while trasferring potential hardware + * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. + */ +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) +{ + pteval_t pteval; + unsigned long tmp; + + asm volatile("// ptep_set_wrprotect\n" + " prfm pstl1strm, %2\n" + "1: ldxr %0, %2\n" + " tst %0, %4 // check for hw dirty (!PTE_RDONLY)\n" + " csel %1, %3, xzr, eq // set PTE_DIRTY|PTE_RDONLY if dirty\n" + " orr %0, %0, %1 // if !dirty, PTE_RDONLY is already set\n" + " and %0, %0, %5 // clear PTE_WRITE/PTE_DBM\n" + " stxr %w1, %0, %2\n" + " cbnz %w1, 1b\n" + : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)) + : "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE) + : "cc"); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + ptep_set_wrprotect(mm, address, (pte_t *)pmdp); +} +#endif +#endif /* CONFIG_ARM64_HW_AFDBM */ + extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; @@ -505,6 +668,24 @@ extern int kern_addr_valid(unsigned long addr); #define pgtable_cache_init() do { } while (0) +/* + * On AArch64, the cache coherency is handled via the set_pte_at() function. + */ +static inline void update_mmu_cache(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + /* + * We don't do anything here, so there's a very small chance of + * us retaking a user fault which we just fixed up. The alternative + * is doing a dsb(ishst), but that penalises the fastpath. + */ +} + +#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) + +#define kc_vaddr_to_offset(v) ((v) & ~VA_START) +#define kc_offset_to_vaddr(o) ((o) | VA_START) + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/kernel/arch/arm64/include/asm/pmu.h b/kernel/arch/arm64/include/asm/pmu.h deleted file mode 100644 index b7710a596..000000000 --- a/kernel/arch/arm64/include/asm/pmu.h +++ /dev/null @@ -1,83 +0,0 @@ -/* - * Based on arch/arm/include/asm/pmu.h - * - * Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles - * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see . - */ -#ifndef __ASM_PMU_H -#define __ASM_PMU_H - -#ifdef CONFIG_HW_PERF_EVENTS - -/* The events for a given PMU register set. */ -struct pmu_hw_events { - /* - * The events that are active on the PMU for the given index. - */ - struct perf_event **events; - - /* - * A 1 bit for an index indicates that the counter is being used for - * an event. A 0 means that the counter can be used. - */ - unsigned long *used_mask; - - /* - * Hardware lock to serialize accesses to PMU registers. Needed for the - * read/modify/write sequences. - */ - raw_spinlock_t pmu_lock; -}; - -struct arm_pmu { - struct pmu pmu; - cpumask_t active_irqs; - int *irq_affinity; - const char *name; - irqreturn_t (*handle_irq)(int irq_num, void *dev); - void (*enable)(struct hw_perf_event *evt, int idx); - void (*disable)(struct hw_perf_event *evt, int idx); - int (*get_event_idx)(struct pmu_hw_events *hw_events, - struct hw_perf_event *hwc); - int (*set_event_filter)(struct hw_perf_event *evt, - struct perf_event_attr *attr); - u32 (*read_counter)(int idx); - void (*write_counter)(int idx, u32 val); - void (*start)(void); - void (*stop)(void); - void (*reset)(void *); - int (*map_event)(struct perf_event *event); - int num_events; - atomic_t active_events; - struct mutex reserve_mutex; - u64 max_period; - struct platform_device *plat_device; - struct pmu_hw_events *(*get_hw_events)(void); -}; - -#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) - -int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type); - -u64 armpmu_event_update(struct perf_event *event, - struct hw_perf_event *hwc, - int idx); - -int armpmu_event_set_period(struct perf_event *event, - struct hw_perf_event *hwc, - int idx); - -#endif /* CONFIG_HW_PERF_EVENTS */ -#endif /* __ASM_PMU_H */ diff --git a/kernel/arch/arm64/include/asm/proc-fns.h b/kernel/arch/arm64/include/asm/proc-fns.h index 220633b79..14ad6e4e8 100644 --- a/kernel/arch/arm64/include/asm/proc-fns.h +++ b/kernel/arch/arm64/include/asm/proc-fns.h @@ -28,12 +28,8 @@ struct mm_struct; struct cpu_suspend_ctx; -extern void cpu_cache_off(void); extern void cpu_do_idle(void); extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm); -extern void cpu_reset(unsigned long addr) __attribute__((noreturn)); -void cpu_soft_restart(phys_addr_t cpu_reset, - unsigned long addr) __attribute__((noreturn)); extern void cpu_do_suspend(struct cpu_suspend_ctx *ptr); extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr); diff --git a/kernel/arch/arm64/include/asm/processor.h b/kernel/arch/arm64/include/asm/processor.h index d2c37a1df..4acb7ca94 100644 --- a/kernel/arch/arm64/include/asm/processor.h +++ b/kernel/arch/arm64/include/asm/processor.h @@ -78,13 +78,30 @@ struct cpu_context { struct thread_struct { struct cpu_context cpu_context; /* cpu context */ - unsigned long tp_value; + unsigned long tp_value; /* TLS register */ +#ifdef CONFIG_COMPAT + unsigned long tp2_value; +#endif struct fpsimd_state fpsimd_state; unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ }; +#ifdef CONFIG_COMPAT +#define task_user_tls(t) \ +({ \ + unsigned long *__tls; \ + if (is_compat_thread(task_thread_info(t))) \ + __tls = &(t)->thread.tp2_value; \ + else \ + __tls = &(t)->thread.tp_value; \ + __tls; \ + }) +#else +#define task_user_tls(t) (&(t)->thread.tp_value) +#endif + #define INIT_THREAD { } static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) @@ -169,4 +186,6 @@ static inline void spin_lock_prefetch(const void *x) #endif +void cpu_enable_pan(void *__unused); + #endif /* __ASM_PROCESSOR_H */ diff --git a/kernel/arch/arm64/include/asm/psci.h b/kernel/arch/arm64/include/asm/psci.h deleted file mode 100644 index 2454bc59c..000000000 --- a/kernel/arch/arm64/include/asm/psci.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Copyright (C) 2013 ARM Limited - */ - -#ifndef __ASM_PSCI_H -#define __ASM_PSCI_H - -int psci_dt_init(void); -int psci_acpi_init(void); - -#endif /* __ASM_PSCI_H */ diff --git a/kernel/arch/arm64/include/asm/ptrace.h b/kernel/arch/arm64/include/asm/ptrace.h index d6dd9fdbc..e9e5467e0 100644 --- a/kernel/arch/arm64/include/asm/ptrace.h +++ b/kernel/arch/arm64/include/asm/ptrace.h @@ -83,14 +83,14 @@ #define compat_sp regs[13] #define compat_lr regs[14] #define compat_sp_hyp regs[15] -#define compat_sp_irq regs[16] -#define compat_lr_irq regs[17] -#define compat_sp_svc regs[18] -#define compat_lr_svc regs[19] -#define compat_sp_abt regs[20] -#define compat_lr_abt regs[21] -#define compat_sp_und regs[22] -#define compat_lr_und regs[23] +#define compat_lr_irq regs[16] +#define compat_sp_irq regs[17] +#define compat_lr_svc regs[18] +#define compat_sp_svc regs[19] +#define compat_lr_abt regs[20] +#define compat_sp_abt regs[21] +#define compat_lr_und regs[22] +#define compat_sp_und regs[23] #define compat_r8_fiq regs[24] #define compat_r9_fiq regs[25] #define compat_r10_fiq regs[26] @@ -183,11 +183,7 @@ static inline int valid_user_regs(struct user_pt_regs *regs) #define instruction_pointer(regs) ((unsigned long)(regs)->pc) -#ifdef CONFIG_SMP extern unsigned long profile_pc(struct pt_regs *regs); -#else -#define profile_pc(regs) instruction_pointer(regs) -#endif #endif /* __ASSEMBLY__ */ #endif diff --git a/kernel/arch/arm64/include/asm/smp.h b/kernel/arch/arm64/include/asm/smp.h index bf22650b1..d9c3d6a61 100644 --- a/kernel/arch/arm64/include/asm/smp.h +++ b/kernel/arch/arm64/include/asm/smp.h @@ -20,10 +20,6 @@ #include #include -#ifndef CONFIG_SMP -# error " included in non-SMP build" -#endif - #define raw_smp_processor_id() (current_thread_info()->cpu) struct seq_file; @@ -42,7 +38,7 @@ extern void handle_IPI(int ipinr, struct pt_regs *regs); * Discover the set of possible CPUs and determine their * SMP operations. */ -extern void of_smp_init_cpus(void); +extern void smp_init_cpus(void); /* * Provide a function to raise an IPI cross call on CPUs in callmap. diff --git a/kernel/arch/arm64/include/asm/smp_plat.h b/kernel/arch/arm64/include/asm/smp_plat.h index 8dcd61e32..af58dcdef 100644 --- a/kernel/arch/arm64/include/asm/smp_plat.h +++ b/kernel/arch/arm64/include/asm/smp_plat.h @@ -19,6 +19,8 @@ #ifndef __ASM_SMP_PLAT_H #define __ASM_SMP_PLAT_H +#include + #include struct mpidr_hash { @@ -39,7 +41,19 @@ static inline u32 mpidr_hash_size(void) */ extern u64 __cpu_logical_map[NR_CPUS]; #define cpu_logical_map(cpu) __cpu_logical_map[cpu] - -void __init do_post_cpus_up_work(void); +/* + * Retrieve logical cpu index corresponding to a given MPIDR.Aff* + * - mpidr: MPIDR.Aff* bits to be used for the look-up + * + * Returns the cpu logical index or -EINVAL on look-up error + */ +static inline int get_logical_index(u64 mpidr) +{ + int cpu; + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (cpu_logical_map(cpu) == mpidr) + return cpu; + return -EINVAL; +} #endif /* __ASM_SMP_PLAT_H */ diff --git a/kernel/arch/arm64/include/asm/spinlock.h b/kernel/arch/arm64/include/asm/spinlock.h index cee128732..c85e96d17 100644 --- a/kernel/arch/arm64/include/asm/spinlock.h +++ b/kernel/arch/arm64/include/asm/spinlock.h @@ -16,6 +16,7 @@ #ifndef __ASM_SPINLOCK_H #define __ASM_SPINLOCK_H +#include #include #include @@ -38,11 +39,21 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) asm volatile( /* Atomically increment the next ticket. */ + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ " prfm pstl1strm, %3\n" "1: ldaxr %w0, %3\n" " add %w1, %w0, %w5\n" " stxr %w2, %w1, %3\n" -" cbnz %w2, 1b\n" +" cbnz %w2, 1b\n", + /* LSE atomics */ +" mov %w2, %w5\n" +" ldadda %w2, %w0, %3\n" +" nop\n" +" nop\n" +" nop\n" + ) + /* Did we get the lock? */ " eor %w1, %w0, %w0, ror #16\n" " cbz %w1, 3f\n" @@ -67,15 +78,25 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) unsigned int tmp; arch_spinlock_t lockval; - asm volatile( -" prfm pstl1strm, %2\n" -"1: ldaxr %w0, %2\n" -" eor %w1, %w0, %w0, ror #16\n" -" cbnz %w1, 2f\n" -" add %w0, %w0, %3\n" -" stxr %w1, %w0, %2\n" -" cbnz %w1, 1b\n" -"2:" + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " prfm pstl1strm, %2\n" + "1: ldaxr %w0, %2\n" + " eor %w1, %w0, %w0, ror #16\n" + " cbnz %w1, 2f\n" + " add %w0, %w0, %3\n" + " stxr %w1, %w0, %2\n" + " cbnz %w1, 1b\n" + "2:", + /* LSE atomics */ + " ldr %w0, %2\n" + " eor %w1, %w0, %w0, ror #16\n" + " cbnz %w1, 1f\n" + " add %w1, %w0, %3\n" + " casa %w0, %w1, %2\n" + " and %w1, %w1, #0xffff\n" + " eor %w1, %w1, %w0, lsr #16\n" + "1:") : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) : "I" (1 << TICKET_SHIFT) : "memory"); @@ -85,10 +106,19 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock) static inline void arch_spin_unlock(arch_spinlock_t *lock) { - asm volatile( -" stlrh %w1, %0\n" - : "=Q" (lock->owner) - : "r" (lock->owner + 1) + unsigned long tmp; + + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " ldrh %w1, %0\n" + " add %w1, %w1, #1\n" + " stlrh %w1, %0", + /* LSE atomics */ + " mov %w1, #1\n" + " nop\n" + " staddlh %w1, %0") + : "=Q" (lock->owner), "=&r" (tmp) + : : "memory"); } @@ -123,13 +153,24 @@ static inline void arch_write_lock(arch_rwlock_t *rw) { unsigned int tmp; - asm volatile( + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ " sevl\n" "1: wfe\n" "2: ldaxr %w0, %1\n" " cbnz %w0, 1b\n" " stxr %w0, %w2, %1\n" " cbnz %w0, 2b\n" + " nop", + /* LSE atomics */ + "1: mov %w0, wzr\n" + "2: casa %w0, %w2, %1\n" + " cbz %w0, 3f\n" + " ldxr %w0, %1\n" + " cbz %w0, 2b\n" + " wfe\n" + " b 1b\n" + "3:") : "=&r" (tmp), "+Q" (rw->lock) : "r" (0x80000000) : "memory"); @@ -139,11 +180,18 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) { unsigned int tmp; - asm volatile( - " ldaxr %w0, %1\n" - " cbnz %w0, 1f\n" + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + "1: ldaxr %w0, %1\n" + " cbnz %w0, 2f\n" " stxr %w0, %w2, %1\n" - "1:\n" + " cbnz %w0, 1b\n" + "2:", + /* LSE atomics */ + " mov %w0, wzr\n" + " casa %w0, %w2, %1\n" + " nop\n" + " nop") : "=&r" (tmp), "+Q" (rw->lock) : "r" (0x80000000) : "memory"); @@ -153,9 +201,10 @@ static inline int arch_write_trylock(arch_rwlock_t *rw) static inline void arch_write_unlock(arch_rwlock_t *rw) { - asm volatile( - " stlr %w1, %0\n" - : "=Q" (rw->lock) : "r" (0) : "memory"); + asm volatile(ARM64_LSE_ATOMIC_INSN( + " stlr wzr, %0", + " swpl wzr, wzr, %0") + : "=Q" (rw->lock) :: "memory"); } /* write_can_lock - would write_trylock() succeed? */ @@ -172,6 +221,10 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) * * The memory barriers are implicit with the load-acquire and store-release * instructions. + * + * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC + * and LSE implementations may exhibit different behaviour (although this + * will have no effect on lockdep). */ static inline void arch_read_lock(arch_rwlock_t *rw) { @@ -179,26 +232,43 @@ static inline void arch_read_lock(arch_rwlock_t *rw) asm volatile( " sevl\n" + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ "1: wfe\n" "2: ldaxr %w0, %2\n" " add %w0, %w0, #1\n" " tbnz %w0, #31, 1b\n" " stxr %w1, %w0, %2\n" - " cbnz %w1, 2b\n" + " nop\n" + " cbnz %w1, 2b", + /* LSE atomics */ + "1: wfe\n" + "2: ldxr %w0, %2\n" + " adds %w1, %w0, #1\n" + " tbnz %w1, #31, 1b\n" + " casa %w0, %w1, %2\n" + " sbc %w0, %w1, %w0\n" + " cbnz %w0, 2b") : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : - : "memory"); + : "cc", "memory"); } static inline void arch_read_unlock(arch_rwlock_t *rw) { unsigned int tmp, tmp2; - asm volatile( + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ "1: ldxr %w0, %2\n" " sub %w0, %w0, #1\n" " stlxr %w1, %w0, %2\n" - " cbnz %w1, 1b\n" + " cbnz %w1, 1b", + /* LSE atomics */ + " movn %w0, #0\n" + " nop\n" + " nop\n" + " staddl %w0, %2") : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : : "memory"); @@ -206,17 +276,28 @@ static inline void arch_read_unlock(arch_rwlock_t *rw) static inline int arch_read_trylock(arch_rwlock_t *rw) { - unsigned int tmp, tmp2 = 1; + unsigned int tmp, tmp2; - asm volatile( - " ldaxr %w0, %2\n" + asm volatile(ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " mov %w1, #1\n" + "1: ldaxr %w0, %2\n" " add %w0, %w0, #1\n" - " tbnz %w0, #31, 1f\n" + " tbnz %w0, #31, 2f\n" " stxr %w1, %w0, %2\n" - "1:\n" - : "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock) + " cbnz %w1, 1b\n" + "2:", + /* LSE atomics */ + " ldr %w0, %2\n" + " adds %w1, %w0, #1\n" + " tbnz %w1, #31, 1f\n" + " casa %w0, %w1, %2\n" + " sbc %w1, %w1, %w0\n" + " nop\n" + "1:") + : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) : - : "memory"); + : "cc", "memory"); return !tmp2; } diff --git a/kernel/arch/arm64/include/asm/spinlock_types.h b/kernel/arch/arm64/include/asm/spinlock_types.h index b8d383665..55be59a35 100644 --- a/kernel/arch/arm64/include/asm/spinlock_types.h +++ b/kernel/arch/arm64/include/asm/spinlock_types.h @@ -20,6 +20,8 @@ # error "please don't include this file directly" #endif +#include + #define TICKET_SHIFT 16 typedef struct { diff --git a/kernel/arch/arm64/include/asm/string.h b/kernel/arch/arm64/include/asm/string.h index 64d2d4884..2eb714c46 100644 --- a/kernel/arch/arm64/include/asm/string.h +++ b/kernel/arch/arm64/include/asm/string.h @@ -36,17 +36,33 @@ extern __kernel_size_t strnlen(const char *, __kernel_size_t); #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *, const void *, __kernel_size_t); +extern void *__memcpy(void *, const void *, __kernel_size_t); #define __HAVE_ARCH_MEMMOVE extern void *memmove(void *, const void *, __kernel_size_t); +extern void *__memmove(void *, const void *, __kernel_size_t); #define __HAVE_ARCH_MEMCHR extern void *memchr(const void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, __kernel_size_t); +extern void *__memset(void *, int, __kernel_size_t); #define __HAVE_ARCH_MEMCMP extern int memcmp(const void *, const void *, size_t); + +#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) + +/* + * For files that are not instrumented (e.g. mm/slub.c) we + * should use not instrumented version of mem* functions. + */ + +#define memcpy(dst, src, len) __memcpy(dst, src, len) +#define memmove(dst, src, len) __memmove(dst, src, len) +#define memset(s, c, n) __memset(s, c, n) +#endif + #endif diff --git a/kernel/arch/arm64/include/asm/suspend.h b/kernel/arch/arm64/include/asm/suspend.h index 003802f58..59a5b0f1e 100644 --- a/kernel/arch/arm64/include/asm/suspend.h +++ b/kernel/arch/arm64/include/asm/suspend.h @@ -21,6 +21,6 @@ struct sleep_save_sp { phys_addr_t save_ptr_stash_phys; }; -extern int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)); +extern int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)); extern void cpu_resume(void); #endif diff --git a/kernel/arch/arm64/include/asm/sysreg.h b/kernel/arch/arm64/include/asm/sysreg.h index 5c89df0ac..d48ab5b41 100644 --- a/kernel/arch/arm64/include/asm/sysreg.h +++ b/kernel/arch/arm64/include/asm/sysreg.h @@ -20,8 +20,176 @@ #ifndef __ASM_SYSREG_H #define __ASM_SYSREG_H +#include + +/* + * ARMv8 ARM reserves the following encoding for system registers: + * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview", + * C5.2, version:ARM DDI 0487A.f) + * [20-19] : Op0 + * [18-16] : Op1 + * [15-12] : CRn + * [11-8] : CRm + * [7-5] : Op2 + */ #define sys_reg(op0, op1, crn, crm, op2) \ - ((((op0)-2)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5)) + ((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5)) + +#define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0) +#define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5) +#define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6) + +#define SYS_ID_PFR0_EL1 sys_reg(3, 0, 0, 1, 0) +#define SYS_ID_PFR1_EL1 sys_reg(3, 0, 0, 1, 1) +#define SYS_ID_DFR0_EL1 sys_reg(3, 0, 0, 1, 2) +#define SYS_ID_MMFR0_EL1 sys_reg(3, 0, 0, 1, 4) +#define SYS_ID_MMFR1_EL1 sys_reg(3, 0, 0, 1, 5) +#define SYS_ID_MMFR2_EL1 sys_reg(3, 0, 0, 1, 6) +#define SYS_ID_MMFR3_EL1 sys_reg(3, 0, 0, 1, 7) + +#define SYS_ID_ISAR0_EL1 sys_reg(3, 0, 0, 2, 0) +#define SYS_ID_ISAR1_EL1 sys_reg(3, 0, 0, 2, 1) +#define SYS_ID_ISAR2_EL1 sys_reg(3, 0, 0, 2, 2) +#define SYS_ID_ISAR3_EL1 sys_reg(3, 0, 0, 2, 3) +#define SYS_ID_ISAR4_EL1 sys_reg(3, 0, 0, 2, 4) +#define SYS_ID_ISAR5_EL1 sys_reg(3, 0, 0, 2, 5) +#define SYS_ID_MMFR4_EL1 sys_reg(3, 0, 0, 2, 6) + +#define SYS_MVFR0_EL1 sys_reg(3, 0, 0, 3, 0) +#define SYS_MVFR1_EL1 sys_reg(3, 0, 0, 3, 1) +#define SYS_MVFR2_EL1 sys_reg(3, 0, 0, 3, 2) + +#define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0) +#define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1) + +#define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0) +#define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1) + +#define SYS_ID_AA64ISAR0_EL1 sys_reg(3, 0, 0, 6, 0) +#define SYS_ID_AA64ISAR1_EL1 sys_reg(3, 0, 0, 6, 1) + +#define SYS_ID_AA64MMFR0_EL1 sys_reg(3, 0, 0, 7, 0) +#define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1) + +#define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0) +#define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1) +#define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7) + +#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4) + +#define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\ + (!!x)<<8 | 0x1f) + +/* SCTLR_EL1 */ +#define SCTLR_EL1_CP15BEN (0x1 << 5) +#define SCTLR_EL1_SED (0x1 << 8) +#define SCTLR_EL1_SPAN (0x1 << 23) + + +/* id_aa64isar0 */ +#define ID_AA64ISAR0_RDM_SHIFT 28 +#define ID_AA64ISAR0_ATOMICS_SHIFT 20 +#define ID_AA64ISAR0_CRC32_SHIFT 16 +#define ID_AA64ISAR0_SHA2_SHIFT 12 +#define ID_AA64ISAR0_SHA1_SHIFT 8 +#define ID_AA64ISAR0_AES_SHIFT 4 + +/* id_aa64pfr0 */ +#define ID_AA64PFR0_GIC_SHIFT 24 +#define ID_AA64PFR0_ASIMD_SHIFT 20 +#define ID_AA64PFR0_FP_SHIFT 16 +#define ID_AA64PFR0_EL3_SHIFT 12 +#define ID_AA64PFR0_EL2_SHIFT 8 +#define ID_AA64PFR0_EL1_SHIFT 4 +#define ID_AA64PFR0_EL0_SHIFT 0 + +#define ID_AA64PFR0_FP_NI 0xf +#define ID_AA64PFR0_FP_SUPPORTED 0x0 +#define ID_AA64PFR0_ASIMD_NI 0xf +#define ID_AA64PFR0_ASIMD_SUPPORTED 0x0 +#define ID_AA64PFR0_EL1_64BIT_ONLY 0x1 +#define ID_AA64PFR0_EL0_64BIT_ONLY 0x1 + +/* id_aa64mmfr0 */ +#define ID_AA64MMFR0_TGRAN4_SHIFT 28 +#define ID_AA64MMFR0_TGRAN64_SHIFT 24 +#define ID_AA64MMFR0_TGRAN16_SHIFT 20 +#define ID_AA64MMFR0_BIGENDEL0_SHIFT 16 +#define ID_AA64MMFR0_SNSMEM_SHIFT 12 +#define ID_AA64MMFR0_BIGENDEL_SHIFT 8 +#define ID_AA64MMFR0_ASID_SHIFT 4 +#define ID_AA64MMFR0_PARANGE_SHIFT 0 + +#define ID_AA64MMFR0_TGRAN4_NI 0xf +#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0 +#define ID_AA64MMFR0_TGRAN64_NI 0xf +#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0 +#define ID_AA64MMFR0_TGRAN16_NI 0x0 +#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1 + +/* id_aa64mmfr1 */ +#define ID_AA64MMFR1_PAN_SHIFT 20 +#define ID_AA64MMFR1_LOR_SHIFT 16 +#define ID_AA64MMFR1_HPD_SHIFT 12 +#define ID_AA64MMFR1_VHE_SHIFT 8 +#define ID_AA64MMFR1_VMIDBITS_SHIFT 4 +#define ID_AA64MMFR1_HADBS_SHIFT 0 + +/* id_aa64dfr0 */ +#define ID_AA64DFR0_CTX_CMPS_SHIFT 28 +#define ID_AA64DFR0_WRPS_SHIFT 20 +#define ID_AA64DFR0_BRPS_SHIFT 12 +#define ID_AA64DFR0_PMUVER_SHIFT 8 +#define ID_AA64DFR0_TRACEVER_SHIFT 4 +#define ID_AA64DFR0_DEBUGVER_SHIFT 0 + +#define ID_ISAR5_RDM_SHIFT 24 +#define ID_ISAR5_CRC32_SHIFT 16 +#define ID_ISAR5_SHA2_SHIFT 12 +#define ID_ISAR5_SHA1_SHIFT 8 +#define ID_ISAR5_AES_SHIFT 4 +#define ID_ISAR5_SEVL_SHIFT 0 + +#define MVFR0_FPROUND_SHIFT 28 +#define MVFR0_FPSHVEC_SHIFT 24 +#define MVFR0_FPSQRT_SHIFT 20 +#define MVFR0_FPDIVIDE_SHIFT 16 +#define MVFR0_FPTRAP_SHIFT 12 +#define MVFR0_FPDP_SHIFT 8 +#define MVFR0_FPSP_SHIFT 4 +#define MVFR0_SIMD_SHIFT 0 + +#define MVFR1_SIMDFMAC_SHIFT 28 +#define MVFR1_FPHP_SHIFT 24 +#define MVFR1_SIMDHP_SHIFT 20 +#define MVFR1_SIMDSP_SHIFT 16 +#define MVFR1_SIMDINT_SHIFT 12 +#define MVFR1_SIMDLS_SHIFT 8 +#define MVFR1_FPDNAN_SHIFT 4 +#define MVFR1_FPFTZ_SHIFT 0 + + +#define ID_AA64MMFR0_TGRAN4_SHIFT 28 +#define ID_AA64MMFR0_TGRAN64_SHIFT 24 +#define ID_AA64MMFR0_TGRAN16_SHIFT 20 + +#define ID_AA64MMFR0_TGRAN4_NI 0xf +#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0 +#define ID_AA64MMFR0_TGRAN64_NI 0xf +#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0 +#define ID_AA64MMFR0_TGRAN16_NI 0x0 +#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1 + +#if defined(CONFIG_ARM64_4K_PAGES) +#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT +#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN4_SUPPORTED +#elif defined(CONFIG_ARM64_16K_PAGES) +#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT +#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN16_SUPPORTED +#elif defined(CONFIG_ARM64_64K_PAGES) +#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT +#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED +#endif #ifdef __ASSEMBLY__ @@ -31,11 +199,11 @@ .equ __reg_num_xzr, 31 .macro mrs_s, rt, sreg - .inst 0xd5300000|(\sreg)|(__reg_num_\rt) + .inst 0xd5200000|(\sreg)|(__reg_num_\rt) .endm .macro msr_s, sreg, rt - .inst 0xd5100000|(\sreg)|(__reg_num_\rt) + .inst 0xd5000000|(\sreg)|(__reg_num_\rt) .endm #else @@ -47,14 +215,23 @@ asm( " .equ __reg_num_xzr, 31\n" "\n" " .macro mrs_s, rt, sreg\n" -" .inst 0xd5300000|(\\sreg)|(__reg_num_\\rt)\n" +" .inst 0xd5200000|(\\sreg)|(__reg_num_\\rt)\n" " .endm\n" "\n" " .macro msr_s, sreg, rt\n" -" .inst 0xd5100000|(\\sreg)|(__reg_num_\\rt)\n" +" .inst 0xd5000000|(\\sreg)|(__reg_num_\\rt)\n" " .endm\n" ); +static inline void config_sctlr_el1(u32 clear, u32 set) +{ + u32 val; + + asm volatile("mrs %0, sctlr_el1" : "=r" (val)); + val &= ~clear; + val |= set; + asm volatile("msr sctlr_el1, %0" : : "r" (val)); +} #endif #endif /* __ASM_SYSREG_H */ diff --git a/kernel/arch/arm64/include/asm/system_misc.h b/kernel/arch/arm64/include/asm/system_misc.h index 7a18fabbe..57f110bea 100644 --- a/kernel/arch/arm64/include/asm/system_misc.h +++ b/kernel/arch/arm64/include/asm/system_misc.h @@ -23,6 +23,8 @@ #include #include #include +#include +#include #include struct pt_regs; @@ -41,9 +43,19 @@ struct mm_struct; extern void show_pte(struct mm_struct *mm, unsigned long addr); extern void __show_regs(struct pt_regs *); -void soft_restart(unsigned long); extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); +#define show_unhandled_signals_ratelimited() \ +({ \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + bool __show_ratelimited = false; \ + if (show_unhandled_signals && __ratelimit(&_rs)) \ + __show_ratelimited = true; \ + __show_ratelimited; \ +}) + #define UDBG_UNDEFINED (1 << 0) #define UDBG_SYSCALL (1 << 1) #define UDBG_BADABORT (1 << 2) diff --git a/kernel/arch/arm64/include/asm/thread_info.h b/kernel/arch/arm64/include/asm/thread_info.h index 7d45b00db..5f4e89fbc 100644 --- a/kernel/arch/arm64/include/asm/thread_info.h +++ b/kernel/arch/arm64/include/asm/thread_info.h @@ -23,8 +23,10 @@ #include -#ifndef CONFIG_ARM64_64K_PAGES +#ifdef CONFIG_ARM64_4K_PAGES #define THREAD_SIZE_ORDER 2 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define THREAD_SIZE_ORDER 0 #endif #define THREAD_SIZE 16384 @@ -113,7 +115,6 @@ static inline struct thread_info *current_thread_info(void) #define TIF_RESTORE_SIGMASK 20 #define TIF_SINGLESTEP 21 #define TIF_32BIT 22 /* 32bit process */ -#define TIF_SWITCH_MM 23 /* deferred switch_mm */ #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) @@ -128,7 +129,8 @@ static inline struct thread_info *current_thread_info(void) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ - _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE) + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ + _TIF_NEED_RESCHED_LAZY) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ diff --git a/kernel/arch/arm64/include/asm/tlb.h b/kernel/arch/arm64/include/asm/tlb.h index 3a0242c7e..ffdaea795 100644 --- a/kernel/arch/arm64/include/asm/tlb.h +++ b/kernel/arch/arm64/include/asm/tlb.h @@ -37,12 +37,21 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - if (tlb->fullmm) { - flush_tlb_mm(tlb->mm); - } else { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; - flush_tlb_range(&vma, tlb->start, tlb->end); - } + struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + + /* + * The ASID allocator will either invalidate the ASID or mark + * it as used. + */ + if (tlb->fullmm) + return; + + /* + * The intermediate page table levels are already handled by + * the __(pte|pmd|pud)_free_tlb() functions, so last level + * TLBI is sufficient here. + */ + __flush_tlb_range(&vma, tlb->start, tlb->end, true); } static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, diff --git a/kernel/arch/arm64/include/asm/tlbflush.h b/kernel/arch/arm64/include/asm/tlbflush.h index c3bb05b98..b460ae28e 100644 --- a/kernel/arch/arm64/include/asm/tlbflush.h +++ b/kernel/arch/arm64/include/asm/tlbflush.h @@ -28,8 +28,6 @@ * TLB Management * ============== * - * The arch/arm64/mm/tlb.S files implement these methods. - * * The TLB specific code is expected to perform whatever tests it needs * to determine if it should invalidate the TLB for each call. Start * addresses are inclusive and end addresses are exclusive; it is safe to @@ -65,6 +63,14 @@ * only require the D-TLB to be invalidated. * - kaddr - Kernel virtual memory address */ +static inline void local_flush_tlb_all(void) +{ + dsb(nshst); + asm("tlbi vmalle1"); + dsb(nsh); + isb(); +} + static inline void flush_tlb_all(void) { dsb(ishst); @@ -75,7 +81,7 @@ static inline void flush_tlb_all(void) static inline void flush_tlb_mm(struct mm_struct *mm) { - unsigned long asid = (unsigned long)ASID(mm) << 48; + unsigned long asid = ASID(mm) << 48; dsb(ishst); asm("tlbi aside1is, %0" : : "r" (asid)); @@ -85,31 +91,59 @@ static inline void flush_tlb_mm(struct mm_struct *mm) static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { - unsigned long addr = uaddr >> 12 | - ((unsigned long)ASID(vma->vm_mm) << 48); + unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48); dsb(ishst); - asm("tlbi vae1is, %0" : : "r" (addr)); + asm("tlbi vale1is, %0" : : "r" (addr)); dsb(ish); } +/* + * This is meant to avoid soft lock-ups on large TLB flushing ranges and not + * necessarily a performance improvement. + */ +#define MAX_TLB_RANGE (1024UL << PAGE_SHIFT) + static inline void __flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, + bool last_level) { - unsigned long asid = (unsigned long)ASID(vma->vm_mm) << 48; + unsigned long asid = ASID(vma->vm_mm) << 48; unsigned long addr; + + if ((end - start) > MAX_TLB_RANGE) { + flush_tlb_mm(vma->vm_mm); + return; + } + start = asid | (start >> 12); end = asid | (end >> 12); dsb(ishst); - for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) - asm("tlbi vae1is, %0" : : "r"(addr)); + for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) { + if (last_level) + asm("tlbi vale1is, %0" : : "r"(addr)); + else + asm("tlbi vae1is, %0" : : "r"(addr)); + } dsb(ish); } -static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long end) +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + __flush_tlb_range(vma, start, end, false); +} + +static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) { unsigned long addr; + + if ((end - start) > MAX_TLB_RANGE) { + flush_tlb_all(); + return; + } + start >>= 12; end >>= 12; @@ -120,29 +154,6 @@ static inline void __flush_tlb_kernel_range(unsigned long start, unsigned long e isb(); } -/* - * This is meant to avoid soft lock-ups on large TLB flushing ranges and not - * necessarily a performance improvement. - */ -#define MAX_TLB_RANGE (1024UL << PAGE_SHIFT) - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if ((end - start) <= MAX_TLB_RANGE) - __flush_tlb_range(vma, start, end); - else - flush_tlb_mm(vma->vm_mm); -} - -static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end) -{ - if ((end - start) <= MAX_TLB_RANGE) - __flush_tlb_kernel_range(start, end); - else - flush_tlb_all(); -} - /* * Used to invalidate the TLB (walk caches) corresponding to intermediate page * table levels (pgd/pud/pmd). @@ -150,26 +161,11 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end static inline void __flush_tlb_pgtable(struct mm_struct *mm, unsigned long uaddr) { - unsigned long addr = uaddr >> 12 | ((unsigned long)ASID(mm) << 48); + unsigned long addr = uaddr >> 12 | (ASID(mm) << 48); - dsb(ishst); asm("tlbi vae1is, %0" : : "r" (addr)); dsb(ish); } -/* - * On AArch64, the cache coherency is handled via the set_pte_at() function. - */ -static inline void update_mmu_cache(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - /* - * set_pte() does not have a DSB for user mappings, so make sure that - * the page table write is visible. - */ - dsb(ishst); -} - -#define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #endif diff --git a/kernel/arch/arm64/include/asm/topology.h b/kernel/arch/arm64/include/asm/topology.h index 7ebcd31ce..a3e9d6fdb 100644 --- a/kernel/arch/arm64/include/asm/topology.h +++ b/kernel/arch/arm64/include/asm/topology.h @@ -1,8 +1,6 @@ #ifndef __ASM_TOPOLOGY_H #define __ASM_TOPOLOGY_H -#ifdef CONFIG_SMP - #include struct cpu_topology { @@ -18,19 +16,12 @@ extern struct cpu_topology cpu_topology[NR_CPUS]; #define topology_physical_package_id(cpu) (cpu_topology[cpu].cluster_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); -#else - -static inline void init_cpu_topology(void) { } -static inline void store_cpu_topology(unsigned int cpuid) { } - -#endif - #include #endif /* _ASM_ARM_TOPOLOGY_H */ diff --git a/kernel/arch/arm64/include/asm/traps.h b/kernel/arch/arm64/include/asm/traps.h index 232e4ba5d..0cc2f29bf 100644 --- a/kernel/arch/arm64/include/asm/traps.h +++ b/kernel/arch/arm64/include/asm/traps.h @@ -34,13 +34,32 @@ struct undef_hook { void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +static inline int __in_irqentry_text(unsigned long ptr) +{ + extern char __irqentry_text_start[]; + extern char __irqentry_text_end[]; + + return ptr >= (unsigned long)&__irqentry_text_start && + ptr < (unsigned long)&__irqentry_text_end; +} +#else +static inline int __in_irqentry_text(unsigned long ptr) +{ + return 0; +} +#endif + static inline int in_exception_text(unsigned long ptr) { extern char __exception_text_start[]; extern char __exception_text_end[]; + int in; + + in = ptr >= (unsigned long)&__exception_text_start && + ptr < (unsigned long)&__exception_text_end; - return ptr >= (unsigned long)&__exception_text_start && - ptr < (unsigned long)&__exception_text_end; + return in ? : __in_irqentry_text(ptr); } #endif diff --git a/kernel/arch/arm64/include/asm/uaccess.h b/kernel/arch/arm64/include/asm/uaccess.h index 07e1ba449..b2ede967f 100644 --- a/kernel/arch/arm64/include/asm/uaccess.h +++ b/kernel/arch/arm64/include/asm/uaccess.h @@ -24,7 +24,10 @@ #include #include +#include +#include #include +#include #include #include #include @@ -131,6 +134,8 @@ static inline void set_fs(mm_segment_t fs) do { \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN)); \ switch (sizeof(*(ptr))) { \ case 1: \ __get_user_asm("ldrb", "%w", __gu_val, (ptr), (err)); \ @@ -148,6 +153,8 @@ do { \ BUILD_BUG(); \ } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN)); \ } while (0) #define __get_user(x, ptr) \ @@ -194,6 +201,8 @@ do { \ do { \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN)); \ switch (sizeof(*(ptr))) { \ case 1: \ __put_user_asm("strb", "%w", __pu_val, (ptr), (err)); \ @@ -210,6 +219,8 @@ do { \ default: \ BUILD_BUG(); \ } \ + asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN)); \ } while (0) #define __put_user(x, ptr) \ diff --git a/kernel/arch/arm64/include/asm/unistd.h b/kernel/arch/arm64/include/asm/unistd.h index 3bc498c25..41e58fe3c 100644 --- a/kernel/arch/arm64/include/asm/unistd.h +++ b/kernel/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 388 +#define __NR_compat_syscalls 390 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/kernel/arch/arm64/include/asm/unistd32.h b/kernel/arch/arm64/include/asm/unistd32.h index cef934a90..5b925b761 100644 --- a/kernel/arch/arm64/include/asm/unistd32.h +++ b/kernel/arch/arm64/include/asm/unistd32.h @@ -797,3 +797,12 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 387 __SYSCALL(__NR_execveat, compat_sys_execveat) +#define __NR_userfaultfd 388 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 389 +__SYSCALL(__NR_membarrier, sys_membarrier) + +/* + * Please add new compat syscalls above this comment and update + * __NR_compat_syscalls in asm/unistd.h. + */ diff --git a/kernel/arch/arm64/include/asm/xen/events.h b/kernel/arch/arm64/include/asm/xen/events.h index 86553213c..4318866d0 100644 --- a/kernel/arch/arm64/include/asm/xen/events.h +++ b/kernel/arch/arm64/include/asm/xen/events.h @@ -18,4 +18,10 @@ static inline int xen_irqs_disabled(struct pt_regs *regs) #define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) +/* Rebind event channel is supported by default */ +static inline bool xen_support_evtchn_rebind(void) +{ + return true; +} + #endif /* _ASM_ARM64_XEN_EVENTS_H */ diff --git a/kernel/arch/arm64/include/uapi/asm/hwcap.h b/kernel/arch/arm64/include/uapi/asm/hwcap.h index 73cf0f54d..361c8a8ef 100644 --- a/kernel/arch/arm64/include/uapi/asm/hwcap.h +++ b/kernel/arch/arm64/include/uapi/asm/hwcap.h @@ -27,5 +27,6 @@ #define HWCAP_SHA1 (1 << 5) #define HWCAP_SHA2 (1 << 6) #define HWCAP_CRC32 (1 << 7) +#define HWCAP_ATOMICS (1 << 8) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/kernel/arch/arm64/include/uapi/asm/kvm.h b/kernel/arch/arm64/include/uapi/asm/kvm.h index d26832022..2d4ca4bb0 100644 --- a/kernel/arch/arm64/include/uapi/asm/kvm.h +++ b/kernel/arch/arm64/include/uapi/asm/kvm.h @@ -32,7 +32,7 @@ #ifndef __ASSEMBLY__ #include -#include +#include #include #define __KVM_HAVE_GUEST_DEBUG @@ -53,14 +53,20 @@ struct kvm_regs { struct user_fpsimd_state fp_regs; }; -/* Supported Processor Types */ +/* + * Supported CPU Targets - Adding a new target type is not recommended, + * unless there are some special registers not supported by the + * genericv8 syreg table. + */ #define KVM_ARM_TARGET_AEM_V8 0 #define KVM_ARM_TARGET_FOUNDATION_V8 1 #define KVM_ARM_TARGET_CORTEX_A57 2 #define KVM_ARM_TARGET_XGENE_POTENZA 3 #define KVM_ARM_TARGET_CORTEX_A53 4 +/* Generic ARM v8 target */ +#define KVM_ARM_TARGET_GENERIC_V8 5 -#define KVM_ARM_NUM_TARGETS 5 +#define KVM_ARM_NUM_TARGETS 6 /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 @@ -100,12 +106,39 @@ struct kvm_sregs { struct kvm_fpu { }; +/* + * See v8 ARM ARM D7.3: Debug Registers + * + * The architectural limit is 16 debug registers of each type although + * in practice there are usually less (see ID_AA64DFR0_EL1). + * + * Although the control registers are architecturally defined as 32 + * bits wide we use a 64 bit structure here to keep parity with + * KVM_GET/SET_ONE_REG behaviour which treats all system registers as + * 64 bit values. It also allows for the possibility of the + * architecture expanding the control registers without having to + * change the userspace ABI. + */ +#define KVM_ARM_MAX_DBG_REGS 16 struct kvm_guest_debug_arch { + __u64 dbg_bcr[KVM_ARM_MAX_DBG_REGS]; + __u64 dbg_bvr[KVM_ARM_MAX_DBG_REGS]; + __u64 dbg_wcr[KVM_ARM_MAX_DBG_REGS]; + __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS]; }; struct kvm_debug_exit_arch { + __u32 hsr; + __u64 far; /* used for watchpoints */ }; +/* + * Architecture specific defines for kvm_guest_debug->control + */ + +#define KVM_GUESTDBG_USE_SW_BP (1 << 16) +#define KVM_GUESTDBG_USE_HW (1 << 17) + struct kvm_sync_regs { }; diff --git a/kernel/arch/arm64/include/uapi/asm/ptrace.h b/kernel/arch/arm64/include/uapi/asm/ptrace.h index 6913643bb..208db3df1 100644 --- a/kernel/arch/arm64/include/uapi/asm/ptrace.h +++ b/kernel/arch/arm64/include/uapi/asm/ptrace.h @@ -44,6 +44,7 @@ #define PSR_I_BIT 0x00000080 #define PSR_A_BIT 0x00000100 #define PSR_D_BIT 0x00000200 +#define PSR_PAN_BIT 0x00400000 #define PSR_Q_BIT 0x08000000 #define PSR_V_BIT 0x10000000 #define PSR_C_BIT 0x20000000 diff --git a/kernel/arch/arm64/include/uapi/asm/signal.h b/kernel/arch/arm64/include/uapi/asm/signal.h index 8d1e72364..991bf5db2 100644 --- a/kernel/arch/arm64/include/uapi/asm/signal.h +++ b/kernel/arch/arm64/include/uapi/asm/signal.h @@ -19,6 +19,9 @@ /* Required for AArch32 compatibility. */ #define SA_RESTORER 0x04000000 +#define MINSIGSTKSZ 5120 +#define SIGSTKSZ 16384 + #include #endif diff --git a/kernel/arch/arm64/kernel/Makefile b/kernel/arch/arm64/kernel/Makefile index 426d0763c..474691f8b 100644 --- a/kernel/arch/arm64/kernel/Makefile +++ b/kernel/arch/arm64/kernel/Makefile @@ -4,7 +4,6 @@ CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET) AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) -CFLAGS_efi-stub.o := -DTEXT_OFFSET=$(TEXT_OFFSET) CFLAGS_armv8_deprecated.o := -I$(src) CFLAGS_REMOVE_ftrace.o = -pg @@ -17,22 +16,28 @@ arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ - cpufeature.o alternative.o cacheinfo.o + cpufeature.o alternative.o cacheinfo.o \ + smp.o smp_spin_table.o topology.o + +extra-$(CONFIG_EFI) := efi-entry.o + +OBJCOPYFLAGS := --prefix-symbols=__efistub_ +$(obj)/%.stub.o: $(obj)/%.o FORCE + $(call if_changed,objcopy) arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o entry32.o \ ../../arm/kernel/opcodes.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o -arm64-obj-$(CONFIG_SMP) += smp.o smp_spin_table.o topology.o -arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o +arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o arm64-obj-$(CONFIG_CPU_PM) += sleep.o suspend.o arm64-obj-$(CONFIG_CPU_IDLE) += cpuidle.o arm64-obj-$(CONFIG_JUMP_LABEL) += jump_label.o arm64-obj-$(CONFIG_KGDB) += kgdb.o -arm64-obj-$(CONFIG_EFI) += efi.o efi-stub.o efi-entry.o +arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o arm64-obj-$(CONFIG_PCI) += pci.o arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o arm64-obj-$(CONFIG_ACPI) += acpi.o @@ -40,7 +45,7 @@ arm64-obj-$(CONFIG_ACPI) += acpi.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) head-y := head.o -extra-y := $(head-y) vmlinux.lds +extra-y += $(head-y) vmlinux.lds # vDSO - this must be built first to generate the symbol offsets $(call objectify,$(arm64-obj-y)): $(obj)/vdso/vdso-offsets.h diff --git a/kernel/arch/arm64/kernel/acpi.c b/kernel/arch/arm64/kernel/acpi.c index 8b8395588..d1ce8e2f9 100644 --- a/kernel/arch/arm64/kernel/acpi.c +++ b/kernel/arch/arm64/kernel/acpi.c @@ -29,6 +29,11 @@ #include #include +#ifdef CONFIG_ACPI_APEI +# include +# include +#endif + int acpi_noirq = 1; /* skip ACPI IRQ initialization */ int acpi_disabled = 1; EXPORT_SYMBOL(acpi_disabled); @@ -36,12 +41,6 @@ EXPORT_SYMBOL(acpi_disabled); int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */ EXPORT_SYMBOL(acpi_pci_disabled); -/* Processors with enabled flag and sane MPIDR */ -static int enabled_cpus; - -/* Boot CPU is valid or not in MADT */ -static bool bootcpu_valid __initdata; - static bool param_acpi_off __initdata; static bool param_acpi_force __initdata; @@ -95,122 +94,15 @@ void __init __acpi_unmap_table(char *map, unsigned long size) early_memunmap(map, size); } -/** - * acpi_map_gic_cpu_interface - generates a logical cpu number - * and map to MPIDR represented by GICC structure - */ -static void __init -acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) +bool __init acpi_psci_present(void) { - int i; - u64 mpidr = processor->arm_mpidr & MPIDR_HWID_BITMASK; - bool enabled = !!(processor->flags & ACPI_MADT_ENABLED); - - if (mpidr == INVALID_HWID) { - pr_info("Skip MADT cpu entry with invalid MPIDR\n"); - return; - } - - total_cpus++; - if (!enabled) - return; - - if (enabled_cpus >= NR_CPUS) { - pr_warn("NR_CPUS limit of %d reached, Processor %d/0x%llx ignored.\n", - NR_CPUS, total_cpus, mpidr); - return; - } - - /* Check if GICC structure of boot CPU is available in the MADT */ - if (cpu_logical_map(0) == mpidr) { - if (bootcpu_valid) { - pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n", - mpidr); - return; - } - - bootcpu_valid = true; - } - - /* - * Duplicate MPIDRs are a recipe for disaster. Scan - * all initialized entries and check for - * duplicates. If any is found just ignore the CPU. - */ - for (i = 1; i < enabled_cpus; i++) { - if (cpu_logical_map(i) == mpidr) { - pr_err("Firmware bug, duplicate CPU MPIDR: 0x%llx in MADT\n", - mpidr); - return; - } - } - - if (!acpi_psci_present()) - return; - - cpu_ops[enabled_cpus] = cpu_get_ops("psci"); - /* CPU 0 was already initialized */ - if (enabled_cpus) { - if (!cpu_ops[enabled_cpus]) - return; - - if (cpu_ops[enabled_cpus]->cpu_init(NULL, enabled_cpus)) - return; - - /* map the logical cpu id to cpu MPIDR */ - cpu_logical_map(enabled_cpus) = mpidr; - } - - enabled_cpus++; + return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_COMPLIANT; } -static int __init -acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, - const unsigned long end) +/* Whether HVC must be used instead of SMC as the PSCI conduit */ +bool __init acpi_psci_use_hvc(void) { - struct acpi_madt_generic_interrupt *processor; - - processor = (struct acpi_madt_generic_interrupt *)header; - - if (BAD_MADT_ENTRY(processor, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - acpi_map_gic_cpu_interface(processor); - return 0; -} - -/* Parse GIC cpu interface entries in MADT for SMP init */ -void __init acpi_init_cpus(void) -{ - int count, i; - - /* - * do a partial walk of MADT to determine how many CPUs - * we have including disabled CPUs, and get information - * we need for SMP init - */ - count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, - acpi_parse_gic_cpu_interface, 0); - - if (!count) { - pr_err("No GIC CPU interface entries present\n"); - return; - } else if (count < 0) { - pr_err("Error parsing GIC CPU interface entry\n"); - return; - } - - if (!bootcpu_valid) { - pr_err("MADT missing boot CPU MPIDR, not enabling secondaries\n"); - return; - } - - for (i = 0; i < enabled_cpus; i++) - set_cpu_possible(i, true); - - /* Make boot-up look pretty */ - pr_info("%d CPUs enabled, %d CPUs total\n", enabled_cpus, total_cpus); + return acpi_gbl_FADT.arm_boot_flags & ACPI_FADT_PSCI_USE_HVC; } /* @@ -319,27 +211,26 @@ void __init acpi_boot_table_init(void) } } -void __init acpi_gic_init(void) +#ifdef CONFIG_ACPI_APEI +pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { - struct acpi_table_header *table; - acpi_status status; - acpi_size tbl_size; - int err; - - if (acpi_disabled) - return; - - status = acpi_get_table_with_size(ACPI_SIG_MADT, 0, &table, &tbl_size); - if (ACPI_FAILURE(status)) { - const char *msg = acpi_format_exception(status); - - pr_err("Failed to get MADT table, %s\n", msg); - return; - } + /* + * According to "Table 8 Map: EFI memory types to AArch64 memory + * types" of UEFI 2.5 section 2.3.6.1, each EFI memory type is + * mapped to a corresponding MAIR attribute encoding. + * The EFI memory attribute advises all possible capabilities + * of a memory region. We use the most efficient capability. + */ - err = gic_v2_acpi_init(table); - if (err) - pr_err("Failed to initialize GIC IRQ controller"); + u64 attr; - early_acpi_os_unmap_memory((char *)table, tbl_size); + attr = efi_mem_attributes(addr); + if (attr & EFI_MEMORY_WB) + return PAGE_KERNEL; + if (attr & EFI_MEMORY_WT) + return __pgprot(PROT_NORMAL_WT); + if (attr & EFI_MEMORY_WC) + return __pgprot(PROT_NORMAL_NC); + return __pgprot(PROT_DEVICE_nGnRnE); } +#endif diff --git a/kernel/arch/arm64/kernel/alternative.c b/kernel/arch/arm64/kernel/alternative.c index 28f8365ed..ab9db0e98 100644 --- a/kernel/arch/arm64/kernel/alternative.c +++ b/kernel/arch/arm64/kernel/alternative.c @@ -24,8 +24,13 @@ #include #include #include +#include #include +#define __ALT_PTR(a,f) (u32 *)((void *)&(a)->f + (a)->f) +#define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset) +#define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset) + extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; struct alt_region { @@ -33,13 +38,63 @@ struct alt_region { struct alt_instr *end; }; -static int __apply_alternatives(void *alt_region) +/* + * Check if the target PC is within an alternative block. + */ +static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc) +{ + unsigned long replptr; + + if (kernel_text_address(pc)) + return 1; + + replptr = (unsigned long)ALT_REPL_PTR(alt); + if (pc >= replptr && pc <= (replptr + alt->alt_len)) + return 0; + + /* + * Branching into *another* alternate sequence is doomed, and + * we're not even trying to fix it up. + */ + BUG(); +} + +static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr) +{ + u32 insn; + + insn = le32_to_cpu(*altinsnptr); + + if (aarch64_insn_is_branch_imm(insn)) { + s32 offset = aarch64_get_branch_offset(insn); + unsigned long target; + + target = (unsigned long)altinsnptr + offset; + + /* + * If we're branching inside the alternate sequence, + * do not rewrite the instruction, as it is already + * correct. Otherwise, generate the new instruction. + */ + if (branch_insn_requires_update(alt, target)) { + offset = target - (unsigned long)insnptr; + insn = aarch64_set_branch_offset(insn, offset); + } + } + + return insn; +} + +static void __apply_alternatives(void *alt_region) { struct alt_instr *alt; struct alt_region *region = alt_region; - u8 *origptr, *replptr; + u32 *origptr, *replptr; for (alt = region->begin; alt < region->end; alt++) { + u32 insn; + int i, nr_inst; + if (!cpus_have_cap(alt->cpufeature)) continue; @@ -47,25 +102,51 @@ static int __apply_alternatives(void *alt_region) pr_info_once("patching kernel code\n"); - origptr = (u8 *)&alt->orig_offset + alt->orig_offset; - replptr = (u8 *)&alt->alt_offset + alt->alt_offset; - memcpy(origptr, replptr, alt->alt_len); + origptr = ALT_ORIG_PTR(alt); + replptr = ALT_REPL_PTR(alt); + nr_inst = alt->alt_len / sizeof(insn); + + for (i = 0; i < nr_inst; i++) { + insn = get_alt_insn(alt, origptr + i, replptr + i); + *(origptr + i) = cpu_to_le32(insn); + } + flush_icache_range((uintptr_t)origptr, - (uintptr_t)(origptr + alt->alt_len)); + (uintptr_t)(origptr + nr_inst)); } - - return 0; } -void apply_alternatives_all(void) +/* + * We might be patching the stop_machine state machine, so implement a + * really simple polling protocol here. + */ +static int __apply_alternatives_multi_stop(void *unused) { + static int patched = 0; struct alt_region region = { .begin = __alt_instructions, .end = __alt_instructions_end, }; + /* We always have a CPU 0 at this point (__init) */ + if (smp_processor_id()) { + while (!READ_ONCE(patched)) + cpu_relax(); + isb(); + } else { + BUG_ON(patched); + __apply_alternatives(®ion); + /* Barriers provided by the cache flushing */ + WRITE_ONCE(patched, 1); + } + + return 0; +} + +void __init apply_alternatives_all(void) +{ /* better not try code patching on a live SMP system */ - stop_machine(__apply_alternatives, ®ion, NULL); + stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask); } void apply_alternatives(void *start, size_t length) diff --git a/kernel/arch/arm64/kernel/arm64ksyms.c b/kernel/arch/arm64/kernel/arm64ksyms.c index a85843ddb..3b6d8cc9d 100644 --- a/kernel/arch/arm64/kernel/arm64ksyms.c +++ b/kernel/arch/arm64/kernel/arm64ksyms.c @@ -51,6 +51,9 @@ EXPORT_SYMBOL(strnlen); EXPORT_SYMBOL(memset); EXPORT_SYMBOL(memcpy); EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(__memset); +EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(__memmove); EXPORT_SYMBOL(memchr); EXPORT_SYMBOL(memcmp); diff --git a/kernel/arch/arm64/kernel/armv8_deprecated.c b/kernel/arch/arm64/kernel/armv8_deprecated.c index 7922c2e71..937f5e58a 100644 --- a/kernel/arch/arm64/kernel/armv8_deprecated.c +++ b/kernel/arch/arm64/kernel/armv8_deprecated.c @@ -14,8 +14,11 @@ #include #include +#include +#include #include #include +#include #include #include #include @@ -279,22 +282,28 @@ static void register_insn_emulation_sysctl(struct ctl_table *table) */ #define __user_swpX_asm(data, addr, res, temp, B) \ __asm__ __volatile__( \ - " mov %w2, %w1\n" \ - "0: ldxr"B" %w1, [%3]\n" \ - "1: stxr"B" %w0, %w2, [%3]\n" \ + ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) \ + "0: ldxr"B" %w2, [%3]\n" \ + "1: stxr"B" %w0, %w1, [%3]\n" \ " cbz %w0, 2f\n" \ " mov %w0, %w4\n" \ + " b 3f\n" \ "2:\n" \ + " mov %w1, %w2\n" \ + "3:\n" \ " .pushsection .fixup,\"ax\"\n" \ " .align 2\n" \ - "3: mov %w0, %w5\n" \ - " b 2b\n" \ + "4: mov %w0, %w5\n" \ + " b 3b\n" \ " .popsection" \ " .pushsection __ex_table,\"a\"\n" \ " .align 3\n" \ - " .quad 0b, 3b\n" \ - " .quad 1b, 3b\n" \ - " .popsection" \ + " .quad 0b, 4b\n" \ + " .quad 1b, 4b\n" \ + " .popsection\n" \ + ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) \ : "=&r" (res), "+r" (data), "=&r" (temp) \ : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \ : "memory") @@ -504,16 +513,6 @@ ret: return 0; } -static inline void config_sctlr_el1(u32 clear, u32 set) -{ - u32 val; - - asm volatile("mrs %0, sctlr_el1" : "=r" (val)); - val &= ~clear; - val |= set; - asm volatile("msr sctlr_el1, %0" : : "r" (val)); -} - static int cp15_barrier_set_hw_mode(bool enable) { if (enable) diff --git a/kernel/arch/arm64/kernel/asm-offsets.c b/kernel/arch/arm64/kernel/asm-offsets.c index c73e2aea4..c5038409e 100644 --- a/kernel/arch/arm64/kernel/asm-offsets.c +++ b/kernel/arch/arm64/kernel/asm-offsets.c @@ -61,7 +61,7 @@ int main(void) DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); - DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id)); + DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); BLANK(); DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm)); DEFINE(VMA_VM_FLAGS, offsetof(struct vm_area_struct, vm_flags)); @@ -117,18 +117,22 @@ int main(void) DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2)); DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2)); DEFINE(VCPU_DEBUG_FLAGS, offsetof(struct kvm_vcpu, arch.debug_flags)); + DEFINE(VCPU_DEBUG_PTR, offsetof(struct kvm_vcpu, arch.debug_ptr)); + DEFINE(DEBUG_BCR, offsetof(struct kvm_guest_debug_arch, dbg_bcr)); + DEFINE(DEBUG_BVR, offsetof(struct kvm_guest_debug_arch, dbg_bvr)); + DEFINE(DEBUG_WCR, offsetof(struct kvm_guest_debug_arch, dbg_wcr)); + DEFINE(DEBUG_WVR, offsetof(struct kvm_guest_debug_arch, dbg_wvr)); DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2)); + DEFINE(VCPU_MDCR_EL2, offsetof(struct kvm_vcpu, arch.mdcr_el2)); DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context)); + DEFINE(VCPU_HOST_DEBUG_STATE, offsetof(struct kvm_vcpu, arch.host_debug_state)); DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval)); DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff)); DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled)); DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); - DEFINE(VGIC_SAVE_FN, offsetof(struct vgic_sr_vectors, save_vgic)); - DEFINE(VGIC_RESTORE_FN, offsetof(struct vgic_sr_vectors, restore_vgic)); - DEFINE(VGIC_SR_VECTOR_SZ, sizeof(struct vgic_sr_vectors)); DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr)); DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr)); DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr)); diff --git a/kernel/arch/arm64/kernel/cpu_errata.c b/kernel/arch/arm64/kernel/cpu_errata.c index 6ffd91438..feb6b4efa 100644 --- a/kernel/arch/arm64/kernel/cpu_errata.c +++ b/kernel/arch/arm64/kernel/cpu_errata.c @@ -23,6 +23,7 @@ #define MIDR_CORTEX_A53 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_PART(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) +#define MIDR_THUNDERX MIDR_CPU_PART(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define CPU_MODEL_MASK (MIDR_IMPLEMENTOR_MASK | MIDR_PARTNUM_MASK | \ MIDR_ARCHITECTURE_MASK) @@ -74,6 +75,15 @@ const struct arm64_cpu_capabilities arm64_errata[] = { (1 << MIDR_VARIANT_SHIFT) | 2), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_834220 + { + /* Cortex-A57 r0p0 - r1p2 */ + .desc = "ARM erratum 834220", + .capability = ARM64_WORKAROUND_834220, + MIDR_RANGE(MIDR_CORTEX_A57, 0x00, + (1 << MIDR_VARIANT_SHIFT) | 2), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_845719 { /* Cortex-A53 r0p[01234] */ @@ -81,6 +91,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .capability = ARM64_WORKAROUND_845719, MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x04), }, +#endif +#ifdef CONFIG_CAVIUM_ERRATUM_23154 + { + /* Cavium ThunderX, pass 1.x */ + .desc = "Cavium erratum 23154", + .capability = ARM64_WORKAROUND_CAVIUM_23154, + MIDR_RANGE(MIDR_THUNDERX, 0x00, 0x01), + }, #endif { } @@ -88,5 +106,5 @@ const struct arm64_cpu_capabilities arm64_errata[] = { void check_local_cpu_errata(void) { - check_cpu_capabilities(arm64_errata, "enabling workaround for"); + update_cpu_capabilities(arm64_errata, "enabling workaround for"); } diff --git a/kernel/arch/arm64/kernel/cpu_ops.c b/kernel/arch/arm64/kernel/cpu_ops.c index fb8ff9ba4..b6bd7d447 100644 --- a/kernel/arch/arm64/kernel/cpu_ops.c +++ b/kernel/arch/arm64/kernel/cpu_ops.c @@ -16,11 +16,13 @@ * along with this program. If not, see . */ -#include -#include +#include #include #include #include +#include +#include +#include extern const struct cpu_operations smp_spin_table_ops; extern const struct cpu_operations cpu_psci_ops; @@ -28,14 +30,12 @@ extern const struct cpu_operations cpu_psci_ops; const struct cpu_operations *cpu_ops[NR_CPUS]; static const struct cpu_operations *supported_cpu_ops[] __initconst = { -#ifdef CONFIG_SMP &smp_spin_table_ops, -#endif &cpu_psci_ops, NULL, }; -const struct cpu_operations * __init cpu_get_ops(const char *name) +static const struct cpu_operations * __init cpu_get_ops(const char *name) { const struct cpu_operations **ops = supported_cpu_ops; @@ -49,39 +49,53 @@ const struct cpu_operations * __init cpu_get_ops(const char *name) return NULL; } +static const char *__init cpu_read_enable_method(int cpu) +{ + const char *enable_method; + + if (acpi_disabled) { + struct device_node *dn = of_get_cpu_node(cpu, NULL); + + if (!dn) { + if (!cpu) + pr_err("Failed to find device node for boot cpu\n"); + return NULL; + } + + enable_method = of_get_property(dn, "enable-method", NULL); + if (!enable_method) { + /* + * The boot CPU may not have an enable method (e.g. + * when spin-table is used for secondaries). + * Don't warn spuriously. + */ + if (cpu != 0) + pr_err("%s: missing enable-method property\n", + dn->full_name); + } + } else { + enable_method = acpi_get_enable_method(cpu); + if (!enable_method) + pr_err("Unsupported ACPI enable-method\n"); + } + + return enable_method; +} /* - * Read a cpu's enable method from the device tree and record it in cpu_ops. + * Read a cpu's enable method and record it in cpu_ops. */ -int __init cpu_read_ops(struct device_node *dn, int cpu) +int __init cpu_read_ops(int cpu) { - const char *enable_method = of_get_property(dn, "enable-method", NULL); - if (!enable_method) { - /* - * The boot CPU may not have an enable method (e.g. when - * spin-table is used for secondaries). Don't warn spuriously. - */ - if (cpu != 0) - pr_err("%s: missing enable-method property\n", - dn->full_name); - return -ENOENT; - } + const char *enable_method = cpu_read_enable_method(cpu); + + if (!enable_method) + return -ENODEV; cpu_ops[cpu] = cpu_get_ops(enable_method); if (!cpu_ops[cpu]) { - pr_warn("%s: unsupported enable-method property: %s\n", - dn->full_name, enable_method); + pr_warn("Unsupported enable-method: %s\n", enable_method); return -EOPNOTSUPP; } return 0; } - -void __init cpu_read_bootcpu_ops(void) -{ - struct device_node *dn = of_get_cpu_node(0, NULL); - if (!dn) { - pr_err("Failed to find device node for boot cpu\n"); - return; - } - cpu_read_ops(dn, 0); -} diff --git a/kernel/arch/arm64/kernel/cpufeature.c b/kernel/arch/arm64/kernel/cpufeature.c index 3d9967e43..0669c6328 100644 --- a/kernel/arch/arm64/kernel/cpufeature.c +++ b/kernel/arch/arm64/kernel/cpufeature.c @@ -16,17 +16,730 @@ * along with this program. If not, see . */ -#define pr_fmt(fmt) "alternatives: " fmt +#define pr_fmt(fmt) "CPU features: " fmt +#include +#include #include #include #include +#include +#include +#include + +unsigned long elf_hwcap __read_mostly; +EXPORT_SYMBOL_GPL(elf_hwcap); + +#ifdef CONFIG_COMPAT +#define COMPAT_ELF_HWCAP_DEFAULT \ + (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\ + COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ + COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ + COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ + COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ + COMPAT_HWCAP_LPAE) +unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; +unsigned int compat_elf_hwcap2 __read_mostly; +#endif + +DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); + +#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + { \ + .sign = SIGNED, \ + .strict = STRICT, \ + .type = TYPE, \ + .shift = SHIFT, \ + .width = WIDTH, \ + .safe_val = SAFE_VAL, \ + } + +/* Define a feature with signed values */ +#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + __ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) + +/* Define a feature with unsigned value */ +#define U_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ + __ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) + +#define ARM64_FTR_END \ + { \ + .width = 0, \ + } + +static struct arm64_ftr_bits ftr_id_aa64isar0[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_ATOMICS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */ + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_aa64pfr0[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), + /* Linux doesn't care about the EL3 */ + ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64PFR0_EL3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), + /* Linux shouldn't care about secure memory */ + ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_ASID_SHIFT, 4, 0), + /* + * Differing PARange is fine as long as all peripherals and memory are mapped + * within the minimum PARange of all CPUs + */ + U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HPD_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VHE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_HADBS_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_ctr[] = { + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RAO */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0), /* CWG */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), /* ERG */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1), /* DminLine */ + /* + * Linux can handle differing I-cache policies. Userspace JITs will + * make use of *minLine + */ + U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0), /* L1Ip */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0), /* RAZ */ + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */ + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_mmfr0[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0), /* InnerShr */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0), /* FCSE */ + ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0), /* AuxReg */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 4, 0), /* TCM */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* ShareLvl */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* OuterShr */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* PMSA */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* VMSA */ + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_aa64dfr0[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), + U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_mvfr2[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* FPMisc */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* SIMDMisc */ + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_dczid[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 5, 27, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 1, 1), /* DZP */ + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* BS */ + ARM64_FTR_END, +}; + + +static struct arm64_ftr_bits ftr_id_isar5[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 20, 4, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_SEVL_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_mmfr4[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* ac2 */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* RAZ */ + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_id_pfr0[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 16, 0), /* RAZ */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0), /* State3 */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0), /* State2 */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0), /* State1 */ + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0), /* State0 */ + ARM64_FTR_END, +}; + +/* + * Common ftr bits for a 32bit register with all hidden, strict + * attributes, with 4bit feature fields and a default safe value of + * 0. Covers the following 32bit registers: + * id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] + */ +static struct arm64_ftr_bits ftr_generic_32bits[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 4, 4, 0), + ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_generic[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_generic32[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0), + ARM64_FTR_END, +}; + +static struct arm64_ftr_bits ftr_aa64raz[] = { + ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0), + ARM64_FTR_END, +}; + +#define ARM64_FTR_REG(id, table) \ + { \ + .sys_id = id, \ + .name = #id, \ + .ftr_bits = &((table)[0]), \ + } + +static struct arm64_ftr_reg arm64_ftr_regs[] = { + + /* Op1 = 0, CRn = 0, CRm = 1 */ + ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0), + ARM64_FTR_REG(SYS_ID_PFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_DFR0_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_MMFR0_EL1, ftr_id_mmfr0), + ARM64_FTR_REG(SYS_ID_MMFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_MMFR2_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_MMFR3_EL1, ftr_generic_32bits), + + /* Op1 = 0, CRn = 0, CRm = 2 */ + ARM64_FTR_REG(SYS_ID_ISAR0_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_ISAR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_ISAR2_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_ISAR3_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_ID_ISAR5_EL1, ftr_id_isar5), + ARM64_FTR_REG(SYS_ID_MMFR4_EL1, ftr_id_mmfr4), + + /* Op1 = 0, CRn = 0, CRm = 3 */ + ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2), + + /* Op1 = 0, CRn = 0, CRm = 4 */ + ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0), + ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_aa64raz), + + /* Op1 = 0, CRn = 0, CRm = 5 */ + ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), + ARM64_FTR_REG(SYS_ID_AA64DFR1_EL1, ftr_generic), + + /* Op1 = 0, CRn = 0, CRm = 6 */ + ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0), + ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_aa64raz), + + /* Op1 = 0, CRn = 0, CRm = 7 */ + ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), + ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1), + + /* Op1 = 3, CRn = 0, CRm = 0 */ + ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr), + ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid), + + /* Op1 = 3, CRn = 14, CRm = 0 */ + ARM64_FTR_REG(SYS_CNTFRQ_EL0, ftr_generic32), +}; + +static int search_cmp_ftr_reg(const void *id, const void *regp) +{ + return (int)(unsigned long)id - (int)((const struct arm64_ftr_reg *)regp)->sys_id; +} + +/* + * get_arm64_ftr_reg - Lookup a feature register entry using its + * sys_reg() encoding. With the array arm64_ftr_regs sorted in the + * ascending order of sys_id , we use binary search to find a matching + * entry. + * + * returns - Upon success, matching ftr_reg entry for id. + * - NULL on failure. It is upto the caller to decide + * the impact of a failure. + */ +static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id) +{ + return bsearch((const void *)(unsigned long)sys_id, + arm64_ftr_regs, + ARRAY_SIZE(arm64_ftr_regs), + sizeof(arm64_ftr_regs[0]), + search_cmp_ftr_reg); +} + +static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val) +{ + u64 mask = arm64_ftr_mask(ftrp); + + reg &= ~mask; + reg |= (ftr_val << ftrp->shift) & mask; + return reg; +} + +static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur) +{ + s64 ret = 0; + + switch (ftrp->type) { + case FTR_EXACT: + ret = ftrp->safe_val; + break; + case FTR_LOWER_SAFE: + ret = new < cur ? new : cur; + break; + case FTR_HIGHER_SAFE: + ret = new > cur ? new : cur; + break; + default: + BUG(); + } + + return ret; +} + +static int __init sort_cmp_ftr_regs(const void *a, const void *b) +{ + return ((const struct arm64_ftr_reg *)a)->sys_id - + ((const struct arm64_ftr_reg *)b)->sys_id; +} + +static void __init swap_ftr_regs(void *a, void *b, int size) +{ + struct arm64_ftr_reg tmp = *(struct arm64_ftr_reg *)a; + *(struct arm64_ftr_reg *)a = *(struct arm64_ftr_reg *)b; + *(struct arm64_ftr_reg *)b = tmp; +} + +static void __init sort_ftr_regs(void) +{ + /* Keep the array sorted so that we can do the binary search */ + sort(arm64_ftr_regs, + ARRAY_SIZE(arm64_ftr_regs), + sizeof(arm64_ftr_regs[0]), + sort_cmp_ftr_regs, + swap_ftr_regs); +} + +/* + * Initialise the CPU feature register from Boot CPU values. + * Also initiliases the strict_mask for the register. + */ +static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) +{ + u64 val = 0; + u64 strict_mask = ~0x0ULL; + struct arm64_ftr_bits *ftrp; + struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg); + + BUG_ON(!reg); + + for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { + s64 ftr_new = arm64_ftr_value(ftrp, new); + + val = arm64_ftr_set_value(ftrp, val, ftr_new); + if (!ftrp->strict) + strict_mask &= ~arm64_ftr_mask(ftrp); + } + reg->sys_val = val; + reg->strict_mask = strict_mask; +} + +void __init init_cpu_features(struct cpuinfo_arm64 *info) +{ + /* Before we start using the tables, make sure it is sorted */ + sort_ftr_regs(); + + init_cpu_ftr_reg(SYS_CTR_EL0, info->reg_ctr); + init_cpu_ftr_reg(SYS_DCZID_EL0, info->reg_dczid); + init_cpu_ftr_reg(SYS_CNTFRQ_EL0, info->reg_cntfrq); + init_cpu_ftr_reg(SYS_ID_AA64DFR0_EL1, info->reg_id_aa64dfr0); + init_cpu_ftr_reg(SYS_ID_AA64DFR1_EL1, info->reg_id_aa64dfr1); + init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0); + init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1); + init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); + init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); + init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); + init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); + init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0); + init_cpu_ftr_reg(SYS_ID_ISAR0_EL1, info->reg_id_isar0); + init_cpu_ftr_reg(SYS_ID_ISAR1_EL1, info->reg_id_isar1); + init_cpu_ftr_reg(SYS_ID_ISAR2_EL1, info->reg_id_isar2); + init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3); + init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4); + init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5); + init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0); + init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1); + init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2); + init_cpu_ftr_reg(SYS_ID_MMFR3_EL1, info->reg_id_mmfr3); + init_cpu_ftr_reg(SYS_ID_PFR0_EL1, info->reg_id_pfr0); + init_cpu_ftr_reg(SYS_ID_PFR1_EL1, info->reg_id_pfr1); + init_cpu_ftr_reg(SYS_MVFR0_EL1, info->reg_mvfr0); + init_cpu_ftr_reg(SYS_MVFR1_EL1, info->reg_mvfr1); + init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2); +} + +static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new) +{ + struct arm64_ftr_bits *ftrp; + + for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { + s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val); + s64 ftr_new = arm64_ftr_value(ftrp, new); + + if (ftr_cur == ftr_new) + continue; + /* Find a safe value */ + ftr_new = arm64_ftr_safe_value(ftrp, ftr_new, ftr_cur); + reg->sys_val = arm64_ftr_set_value(ftrp, reg->sys_val, ftr_new); + } + +} + +static int check_update_ftr_reg(u32 sys_id, int cpu, u64 val, u64 boot) +{ + struct arm64_ftr_reg *regp = get_arm64_ftr_reg(sys_id); + + BUG_ON(!regp); + update_cpu_ftr_reg(regp, val); + if ((boot & regp->strict_mask) == (val & regp->strict_mask)) + return 0; + pr_warn("SANITY CHECK: Unexpected variation in %s. Boot CPU: %#016llx, CPU%d: %#016llx\n", + regp->name, boot, cpu, val); + return 1; +} + +/* + * Update system wide CPU feature registers with the values from a + * non-boot CPU. Also performs SANITY checks to make sure that there + * aren't any insane variations from that of the boot CPU. + */ +void update_cpu_features(int cpu, + struct cpuinfo_arm64 *info, + struct cpuinfo_arm64 *boot) +{ + int taint = 0; + + /* + * The kernel can handle differing I-cache policies, but otherwise + * caches should look identical. Userspace JITs will make use of + * *minLine. + */ + taint |= check_update_ftr_reg(SYS_CTR_EL0, cpu, + info->reg_ctr, boot->reg_ctr); + + /* + * Userspace may perform DC ZVA instructions. Mismatched block sizes + * could result in too much or too little memory being zeroed if a + * process is preempted and migrated between CPUs. + */ + taint |= check_update_ftr_reg(SYS_DCZID_EL0, cpu, + info->reg_dczid, boot->reg_dczid); + + /* If different, timekeeping will be broken (especially with KVM) */ + taint |= check_update_ftr_reg(SYS_CNTFRQ_EL0, cpu, + info->reg_cntfrq, boot->reg_cntfrq); + + /* + * The kernel uses self-hosted debug features and expects CPUs to + * support identical debug features. We presently need CTX_CMPs, WRPs, + * and BRPs to be identical. + * ID_AA64DFR1 is currently RES0. + */ + taint |= check_update_ftr_reg(SYS_ID_AA64DFR0_EL1, cpu, + info->reg_id_aa64dfr0, boot->reg_id_aa64dfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64DFR1_EL1, cpu, + info->reg_id_aa64dfr1, boot->reg_id_aa64dfr1); + /* + * Even in big.LITTLE, processors should be identical instruction-set + * wise. + */ + taint |= check_update_ftr_reg(SYS_ID_AA64ISAR0_EL1, cpu, + info->reg_id_aa64isar0, boot->reg_id_aa64isar0); + taint |= check_update_ftr_reg(SYS_ID_AA64ISAR1_EL1, cpu, + info->reg_id_aa64isar1, boot->reg_id_aa64isar1); + + /* + * Differing PARange support is fine as long as all peripherals and + * memory are mapped within the minimum PARange of all CPUs. + * Linux should not care about secure memory. + */ + taint |= check_update_ftr_reg(SYS_ID_AA64MMFR0_EL1, cpu, + info->reg_id_aa64mmfr0, boot->reg_id_aa64mmfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64MMFR1_EL1, cpu, + info->reg_id_aa64mmfr1, boot->reg_id_aa64mmfr1); + + /* + * EL3 is not our concern. + * ID_AA64PFR1 is currently RES0. + */ + taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, + info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, + info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1); + + /* + * If we have AArch32, we care about 32-bit features for compat. These + * registers should be RES0 otherwise. + */ + taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu, + info->reg_id_dfr0, boot->reg_id_dfr0); + taint |= check_update_ftr_reg(SYS_ID_ISAR0_EL1, cpu, + info->reg_id_isar0, boot->reg_id_isar0); + taint |= check_update_ftr_reg(SYS_ID_ISAR1_EL1, cpu, + info->reg_id_isar1, boot->reg_id_isar1); + taint |= check_update_ftr_reg(SYS_ID_ISAR2_EL1, cpu, + info->reg_id_isar2, boot->reg_id_isar2); + taint |= check_update_ftr_reg(SYS_ID_ISAR3_EL1, cpu, + info->reg_id_isar3, boot->reg_id_isar3); + taint |= check_update_ftr_reg(SYS_ID_ISAR4_EL1, cpu, + info->reg_id_isar4, boot->reg_id_isar4); + taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu, + info->reg_id_isar5, boot->reg_id_isar5); + + /* + * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and + * ACTLR formats could differ across CPUs and therefore would have to + * be trapped for virtualization anyway. + */ + taint |= check_update_ftr_reg(SYS_ID_MMFR0_EL1, cpu, + info->reg_id_mmfr0, boot->reg_id_mmfr0); + taint |= check_update_ftr_reg(SYS_ID_MMFR1_EL1, cpu, + info->reg_id_mmfr1, boot->reg_id_mmfr1); + taint |= check_update_ftr_reg(SYS_ID_MMFR2_EL1, cpu, + info->reg_id_mmfr2, boot->reg_id_mmfr2); + taint |= check_update_ftr_reg(SYS_ID_MMFR3_EL1, cpu, + info->reg_id_mmfr3, boot->reg_id_mmfr3); + taint |= check_update_ftr_reg(SYS_ID_PFR0_EL1, cpu, + info->reg_id_pfr0, boot->reg_id_pfr0); + taint |= check_update_ftr_reg(SYS_ID_PFR1_EL1, cpu, + info->reg_id_pfr1, boot->reg_id_pfr1); + taint |= check_update_ftr_reg(SYS_MVFR0_EL1, cpu, + info->reg_mvfr0, boot->reg_mvfr0); + taint |= check_update_ftr_reg(SYS_MVFR1_EL1, cpu, + info->reg_mvfr1, boot->reg_mvfr1); + taint |= check_update_ftr_reg(SYS_MVFR2_EL1, cpu, + info->reg_mvfr2, boot->reg_mvfr2); + + /* + * Mismatched CPU features are a recipe for disaster. Don't even + * pretend to support them. + */ + WARN_TAINT_ONCE(taint, TAINT_CPU_OUT_OF_SPEC, + "Unsupported CPU feature variation.\n"); +} + +u64 read_system_reg(u32 id) +{ + struct arm64_ftr_reg *regp = get_arm64_ftr_reg(id); + + /* We shouldn't get a request for an unsupported register */ + BUG_ON(!regp); + return regp->sys_val; +} + +#include + +static bool +feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) +{ + int val = cpuid_feature_extract_field(reg, entry->field_pos); + + return val >= entry->min_field_value; +} + +static bool +has_cpuid_feature(const struct arm64_cpu_capabilities *entry) +{ + u64 val; + + val = read_system_reg(entry->sys_reg); + return feature_matches(val, entry); +} + +static bool has_useable_gicv3_cpuif(const struct arm64_cpu_capabilities *entry) +{ + bool has_sre; + + if (!has_cpuid_feature(entry)) + return false; + + has_sre = gic_enable_sre(); + if (!has_sre) + pr_warn_once("%s present but disabled by higher exception level\n", + entry->desc); + + return has_sre; +} static const struct arm64_cpu_capabilities arm64_features[] = { + { + .desc = "GIC system register CPU interface", + .capability = ARM64_HAS_SYSREG_GIC_CPUIF, + .matches = has_useable_gicv3_cpuif, + .sys_reg = SYS_ID_AA64PFR0_EL1, + .field_pos = ID_AA64PFR0_GIC_SHIFT, + .min_field_value = 1, + }, +#ifdef CONFIG_ARM64_PAN + { + .desc = "Privileged Access Never", + .capability = ARM64_HAS_PAN, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64MMFR1_EL1, + .field_pos = ID_AA64MMFR1_PAN_SHIFT, + .min_field_value = 1, + .enable = cpu_enable_pan, + }, +#endif /* CONFIG_ARM64_PAN */ +#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) + { + .desc = "LSE atomic instructions", + .capability = ARM64_HAS_LSE_ATOMICS, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64ISAR0_EL1, + .field_pos = ID_AA64ISAR0_ATOMICS_SHIFT, + .min_field_value = 2, + }, +#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ {}, }; -void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps, +#define HWCAP_CAP(reg, field, min_value, type, cap) \ + { \ + .desc = #cap, \ + .matches = has_cpuid_feature, \ + .sys_reg = reg, \ + .field_pos = field, \ + .min_field_value = min_value, \ + .hwcap_type = type, \ + .hwcap = cap, \ + } + +static const struct arm64_cpu_capabilities arm64_hwcaps[] = { + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 2, CAP_HWCAP, HWCAP_PMULL), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, 1, CAP_HWCAP, HWCAP_AES), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, 1, CAP_HWCAP, HWCAP_SHA1), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, 1, CAP_HWCAP, HWCAP_SHA2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, 1, CAP_HWCAP, HWCAP_CRC32), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, 2, CAP_HWCAP, HWCAP_ATOMICS), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 0, CAP_HWCAP, HWCAP_FP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 0, CAP_HWCAP, HWCAP_ASIMD), +#ifdef CONFIG_COMPAT + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA2_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2), + HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_CRC32_SHIFT, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32), +#endif + {}, +}; + +static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap) +{ + switch (cap->hwcap_type) { + case CAP_HWCAP: + elf_hwcap |= cap->hwcap; + break; +#ifdef CONFIG_COMPAT + case CAP_COMPAT_HWCAP: + compat_elf_hwcap |= (u32)cap->hwcap; + break; + case CAP_COMPAT_HWCAP2: + compat_elf_hwcap2 |= (u32)cap->hwcap; + break; +#endif + default: + WARN_ON(1); + break; + } +} + +/* Check if we have a particular HWCAP enabled */ +static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities *cap) +{ + bool rc; + + switch (cap->hwcap_type) { + case CAP_HWCAP: + rc = (elf_hwcap & cap->hwcap) != 0; + break; +#ifdef CONFIG_COMPAT + case CAP_COMPAT_HWCAP: + rc = (compat_elf_hwcap & (u32)cap->hwcap) != 0; + break; + case CAP_COMPAT_HWCAP2: + rc = (compat_elf_hwcap2 & (u32)cap->hwcap) != 0; + break; +#endif + default: + WARN_ON(1); + rc = false; + } + + return rc; +} + +static void setup_cpu_hwcaps(void) +{ + int i; + const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps; + + for (i = 0; hwcaps[i].desc; i++) + if (hwcaps[i].matches(&hwcaps[i])) + cap_set_hwcap(&hwcaps[i]); +} + +void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, const char *info) { int i; @@ -41,7 +754,176 @@ void check_cpu_capabilities(const struct arm64_cpu_capabilities *caps, } } -void check_local_cpu_features(void) +/* + * Run through the enabled capabilities and enable() it on all active + * CPUs + */ +static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +{ + int i; + + for (i = 0; caps[i].desc; i++) + if (caps[i].enable && cpus_have_cap(caps[i].capability)) + on_each_cpu(caps[i].enable, NULL, true); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Flag to indicate if we have computed the system wide + * capabilities based on the boot time active CPUs. This + * will be used to determine if a new booting CPU should + * go through the verification process to make sure that it + * supports the system capabilities, without using a hotplug + * notifier. + */ +static bool sys_caps_initialised; + +static inline void set_sys_caps_initialised(void) +{ + sys_caps_initialised = true; +} + +/* + * __raw_read_system_reg() - Used by a STARTING cpu before cpuinfo is populated. + */ +static u64 __raw_read_system_reg(u32 sys_id) +{ + switch (sys_id) { + case SYS_ID_PFR0_EL1: return (u64)read_cpuid(ID_PFR0_EL1); + case SYS_ID_PFR1_EL1: return (u64)read_cpuid(ID_PFR1_EL1); + case SYS_ID_DFR0_EL1: return (u64)read_cpuid(ID_DFR0_EL1); + case SYS_ID_MMFR0_EL1: return (u64)read_cpuid(ID_MMFR0_EL1); + case SYS_ID_MMFR1_EL1: return (u64)read_cpuid(ID_MMFR1_EL1); + case SYS_ID_MMFR2_EL1: return (u64)read_cpuid(ID_MMFR2_EL1); + case SYS_ID_MMFR3_EL1: return (u64)read_cpuid(ID_MMFR3_EL1); + case SYS_ID_ISAR0_EL1: return (u64)read_cpuid(ID_ISAR0_EL1); + case SYS_ID_ISAR1_EL1: return (u64)read_cpuid(ID_ISAR1_EL1); + case SYS_ID_ISAR2_EL1: return (u64)read_cpuid(ID_ISAR2_EL1); + case SYS_ID_ISAR3_EL1: return (u64)read_cpuid(ID_ISAR3_EL1); + case SYS_ID_ISAR4_EL1: return (u64)read_cpuid(ID_ISAR4_EL1); + case SYS_ID_ISAR5_EL1: return (u64)read_cpuid(ID_ISAR4_EL1); + case SYS_MVFR0_EL1: return (u64)read_cpuid(MVFR0_EL1); + case SYS_MVFR1_EL1: return (u64)read_cpuid(MVFR1_EL1); + case SYS_MVFR2_EL1: return (u64)read_cpuid(MVFR2_EL1); + + case SYS_ID_AA64PFR0_EL1: return (u64)read_cpuid(ID_AA64PFR0_EL1); + case SYS_ID_AA64PFR1_EL1: return (u64)read_cpuid(ID_AA64PFR0_EL1); + case SYS_ID_AA64DFR0_EL1: return (u64)read_cpuid(ID_AA64DFR0_EL1); + case SYS_ID_AA64DFR1_EL1: return (u64)read_cpuid(ID_AA64DFR0_EL1); + case SYS_ID_AA64MMFR0_EL1: return (u64)read_cpuid(ID_AA64MMFR0_EL1); + case SYS_ID_AA64MMFR1_EL1: return (u64)read_cpuid(ID_AA64MMFR1_EL1); + case SYS_ID_AA64ISAR0_EL1: return (u64)read_cpuid(ID_AA64ISAR0_EL1); + case SYS_ID_AA64ISAR1_EL1: return (u64)read_cpuid(ID_AA64ISAR1_EL1); + + case SYS_CNTFRQ_EL0: return (u64)read_cpuid(CNTFRQ_EL0); + case SYS_CTR_EL0: return (u64)read_cpuid(CTR_EL0); + case SYS_DCZID_EL0: return (u64)read_cpuid(DCZID_EL0); + default: + BUG(); + return 0; + } +} + +/* + * Park the CPU which doesn't have the capability as advertised + * by the system. + */ +static void fail_incapable_cpu(char *cap_type, + const struct arm64_cpu_capabilities *cap) +{ + int cpu = smp_processor_id(); + + pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc); + /* Mark this CPU absent */ + set_cpu_present(cpu, 0); + + /* Check if we can park ourselves */ + if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) + cpu_ops[cpu]->cpu_die(cpu); + asm( + "1: wfe\n" + " wfi\n" + " b 1b"); +} + +/* + * Run through the enabled system capabilities and enable() it on this CPU. + * The capabilities were decided based on the available CPUs at the boot time. + * Any new CPU should match the system wide status of the capability. If the + * new CPU doesn't have a capability which the system now has enabled, we + * cannot do anything to fix it up and could cause unexpected failures. So + * we park the CPU. + */ +void verify_local_cpu_capabilities(void) { - check_cpu_capabilities(arm64_features, "detected feature"); + int i; + const struct arm64_cpu_capabilities *caps; + + /* + * If we haven't computed the system capabilities, there is nothing + * to verify. + */ + if (!sys_caps_initialised) + return; + + caps = arm64_features; + for (i = 0; caps[i].desc; i++) { + if (!cpus_have_cap(caps[i].capability) || !caps[i].sys_reg) + continue; + /* + * If the new CPU misses an advertised feature, we cannot proceed + * further, park the cpu. + */ + if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) + fail_incapable_cpu("arm64_features", &caps[i]); + if (caps[i].enable) + caps[i].enable(NULL); + } + + for (i = 0, caps = arm64_hwcaps; caps[i].desc; i++) { + if (!cpus_have_hwcap(&caps[i])) + continue; + if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) + fail_incapable_cpu("arm64_hwcaps", &caps[i]); + } +} + +#else /* !CONFIG_HOTPLUG_CPU */ + +static inline void set_sys_caps_initialised(void) +{ +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +static void setup_feature_capabilities(void) +{ + update_cpu_capabilities(arm64_features, "detected feature:"); + enable_cpu_capabilities(arm64_features); +} + +void __init setup_cpu_features(void) +{ + u32 cwg; + int cls; + + /* Set the CPU feature capabilies */ + setup_feature_capabilities(); + setup_cpu_hwcaps(); + + /* Advertise that we have computed the system capabilities */ + set_sys_caps_initialised(); + + /* + * Check for sane CTR_EL0.CWG value. + */ + cwg = cache_type_cwg(); + cls = cache_line_size(); + if (!cwg) + pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n", + cls); + if (L1_CACHE_BYTES < cls) + pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n", + L1_CACHE_BYTES, cls); } diff --git a/kernel/arch/arm64/kernel/cpuidle.c b/kernel/arch/arm64/kernel/cpuidle.c index a78143a5c..9047cab68 100644 --- a/kernel/arch/arm64/kernel/cpuidle.c +++ b/kernel/arch/arm64/kernel/cpuidle.c @@ -15,18 +15,13 @@ #include #include -int arm_cpuidle_init(unsigned int cpu) +int __init arm_cpuidle_init(unsigned int cpu) { int ret = -EOPNOTSUPP; - struct device_node *cpu_node = of_cpu_device_node_get(cpu); - - if (!cpu_node) - return -ENODEV; if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_init_idle) - ret = cpu_ops[cpu]->cpu_init_idle(cpu_node, cpu); + ret = cpu_ops[cpu]->cpu_init_idle(cpu); - of_node_put(cpu_node); return ret; } @@ -37,7 +32,7 @@ int arm_cpuidle_init(unsigned int cpu) * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU * operations back-end error code otherwise. */ -int cpu_suspend(unsigned long arg) +int arm_cpuidle_suspend(int index) { int cpu = smp_processor_id(); @@ -47,5 +42,5 @@ int cpu_suspend(unsigned long arg) */ if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_suspend) return -EOPNOTSUPP; - return cpu_ops[cpu]->cpu_suspend(arg); + return cpu_ops[cpu]->cpu_suspend(index); } diff --git a/kernel/arch/arm64/kernel/cpuinfo.c b/kernel/arch/arm64/kernel/cpuinfo.c index 75d5a867e..212ae6361 100644 --- a/kernel/arch/arm64/kernel/cpuinfo.c +++ b/kernel/arch/arm64/kernel/cpuinfo.c @@ -24,9 +24,13 @@ #include #include #include +#include #include #include +#include +#include #include +#include /* * In case the boot CPU is hotpluggable, we record its initial state and @@ -35,7 +39,6 @@ */ DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data); static struct cpuinfo_arm64 boot_cpu_data; -static bool mixed_endian_el0 = true; static char *icache_policy_str[] = { [ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN", @@ -46,157 +49,152 @@ static char *icache_policy_str[] = { unsigned long __icache_flags; -static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) +static const char *const hwcap_str[] = { + "fp", + "asimd", + "evtstrm", + "aes", + "pmull", + "sha1", + "sha2", + "crc32", + "atomics", + NULL +}; + +#ifdef CONFIG_COMPAT +static const char *const compat_hwcap_str[] = { + "swp", + "half", + "thumb", + "26bit", + "fastmult", + "fpa", + "vfp", + "edsp", + "java", + "iwmmxt", + "crunch", + "thumbee", + "neon", + "vfpv3", + "vfpv3d16", + "tls", + "vfpv4", + "idiva", + "idivt", + "vfpd32", + "lpae", + "evtstrm" +}; + +static const char *const compat_hwcap2_str[] = { + "aes", + "pmull", + "sha1", + "sha2", + "crc32", + NULL +}; +#endif /* CONFIG_COMPAT */ + +static int c_show(struct seq_file *m, void *v) { - unsigned int cpu = smp_processor_id(); - u32 l1ip = CTR_L1IP(info->reg_ctr); + int i, j; + + for_each_online_cpu(i) { + struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); + u32 midr = cpuinfo->reg_midr; - if (l1ip != ICACHE_POLICY_PIPT) { /* - * VIPT caches are non-aliasing if the VA always equals the PA - * in all bit positions that are covered by the index. This is - * the case if the size of a way (# of sets * line size) does - * not exceed PAGE_SIZE. + * glibc reads /proc/cpuinfo to determine the number of + * online processors, looking for lines beginning with + * "processor". Give glibc what it expects. */ - u32 waysize = icache_get_numsets() * icache_get_linesize(); + seq_printf(m, "processor\t: %d\n", i); - if (l1ip != ICACHE_POLICY_VIPT || waysize > PAGE_SIZE) - set_bit(ICACHEF_ALIASING, &__icache_flags); + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000UL/HZ), + loops_per_jiffy / (5000UL/HZ) % 100); + + /* + * Dump out the common processor features in a single line. + * Userspace should read the hwcaps with getauxval(AT_HWCAP) + * rather than attempting to parse this, but there's a body of + * software which does already (at least for 32-bit). + */ + seq_puts(m, "Features\t:"); + if (personality(current->personality) == PER_LINUX32) { +#ifdef CONFIG_COMPAT + for (j = 0; compat_hwcap_str[j]; j++) + if (compat_elf_hwcap & (1 << j)) + seq_printf(m, " %s", compat_hwcap_str[j]); + + for (j = 0; compat_hwcap2_str[j]; j++) + if (compat_elf_hwcap2 & (1 << j)) + seq_printf(m, " %s", compat_hwcap2_str[j]); +#endif /* CONFIG_COMPAT */ + } else { + for (j = 0; hwcap_str[j]; j++) + if (elf_hwcap & (1 << j)) + seq_printf(m, " %s", hwcap_str[j]); + } + seq_puts(m, "\n"); + + seq_printf(m, "CPU implementer\t: 0x%02x\n", + MIDR_IMPLEMENTOR(midr)); + seq_printf(m, "CPU architecture: 8\n"); + seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr)); + seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr)); + seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr)); } - if (l1ip == ICACHE_POLICY_AIVIVT) - set_bit(ICACHEF_AIVIVT, &__icache_flags); - pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu); + return 0; } -bool cpu_supports_mixed_endian_el0(void) +static void *c_start(struct seq_file *m, loff_t *pos) { - return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); + return *pos < 1 ? (void *)1 : NULL; } -bool system_supports_mixed_endian_el0(void) +static void *c_next(struct seq_file *m, void *v, loff_t *pos) { - return mixed_endian_el0; + ++*pos; + return NULL; } -static void update_mixed_endian_el0_support(struct cpuinfo_arm64 *info) +static void c_stop(struct seq_file *m, void *v) { - mixed_endian_el0 &= id_aa64mmfr0_mixed_endian_el0(info->reg_id_aa64mmfr0); } -static void update_cpu_features(struct cpuinfo_arm64 *info) -{ - update_mixed_endian_el0_support(info); -} +const struct seq_operations cpuinfo_op = { + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = c_show +}; -static int check_reg_mask(char *name, u64 mask, u64 boot, u64 cur, int cpu) +static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) { - if ((boot & mask) == (cur & mask)) - return 0; - - pr_warn("SANITY CHECK: Unexpected variation in %s. Boot CPU: %#016lx, CPU%d: %#016lx\n", - name, (unsigned long)boot, cpu, (unsigned long)cur); - - return 1; -} + unsigned int cpu = smp_processor_id(); + u32 l1ip = CTR_L1IP(info->reg_ctr); -#define CHECK_MASK(field, mask, boot, cur, cpu) \ - check_reg_mask(#field, mask, (boot)->reg_ ## field, (cur)->reg_ ## field, cpu) + if (l1ip != ICACHE_POLICY_PIPT) { + /* + * VIPT caches are non-aliasing if the VA always equals the PA + * in all bit positions that are covered by the index. This is + * the case if the size of a way (# of sets * line size) does + * not exceed PAGE_SIZE. + */ + u32 waysize = icache_get_numsets() * icache_get_linesize(); -#define CHECK(field, boot, cur, cpu) \ - CHECK_MASK(field, ~0ULL, boot, cur, cpu) + if (l1ip != ICACHE_POLICY_VIPT || waysize > PAGE_SIZE) + set_bit(ICACHEF_ALIASING, &__icache_flags); + } + if (l1ip == ICACHE_POLICY_AIVIVT) + set_bit(ICACHEF_AIVIVT, &__icache_flags); -/* - * Verify that CPUs don't have unexpected differences that will cause problems. - */ -static void cpuinfo_sanity_check(struct cpuinfo_arm64 *cur) -{ - unsigned int cpu = smp_processor_id(); - struct cpuinfo_arm64 *boot = &boot_cpu_data; - unsigned int diff = 0; - - /* - * The kernel can handle differing I-cache policies, but otherwise - * caches should look identical. Userspace JITs will make use of - * *minLine. - */ - diff |= CHECK_MASK(ctr, 0xffff3fff, boot, cur, cpu); - - /* - * Userspace may perform DC ZVA instructions. Mismatched block sizes - * could result in too much or too little memory being zeroed if a - * process is preempted and migrated between CPUs. - */ - diff |= CHECK(dczid, boot, cur, cpu); - - /* If different, timekeeping will be broken (especially with KVM) */ - diff |= CHECK(cntfrq, boot, cur, cpu); - - /* - * The kernel uses self-hosted debug features and expects CPUs to - * support identical debug features. We presently need CTX_CMPs, WRPs, - * and BRPs to be identical. - * ID_AA64DFR1 is currently RES0. - */ - diff |= CHECK(id_aa64dfr0, boot, cur, cpu); - diff |= CHECK(id_aa64dfr1, boot, cur, cpu); - - /* - * Even in big.LITTLE, processors should be identical instruction-set - * wise. - */ - diff |= CHECK(id_aa64isar0, boot, cur, cpu); - diff |= CHECK(id_aa64isar1, boot, cur, cpu); - - /* - * Differing PARange support is fine as long as all peripherals and - * memory are mapped within the minimum PARange of all CPUs. - * Linux should not care about secure memory. - * ID_AA64MMFR1 is currently RES0. - */ - diff |= CHECK_MASK(id_aa64mmfr0, 0xffffffffffff0ff0, boot, cur, cpu); - diff |= CHECK(id_aa64mmfr1, boot, cur, cpu); - - /* - * EL3 is not our concern. - * ID_AA64PFR1 is currently RES0. - */ - diff |= CHECK_MASK(id_aa64pfr0, 0xffffffffffff0fff, boot, cur, cpu); - diff |= CHECK(id_aa64pfr1, boot, cur, cpu); - - /* - * If we have AArch32, we care about 32-bit features for compat. These - * registers should be RES0 otherwise. - */ - diff |= CHECK(id_dfr0, boot, cur, cpu); - diff |= CHECK(id_isar0, boot, cur, cpu); - diff |= CHECK(id_isar1, boot, cur, cpu); - diff |= CHECK(id_isar2, boot, cur, cpu); - diff |= CHECK(id_isar3, boot, cur, cpu); - diff |= CHECK(id_isar4, boot, cur, cpu); - diff |= CHECK(id_isar5, boot, cur, cpu); - /* - * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and - * ACTLR formats could differ across CPUs and therefore would have to - * be trapped for virtualization anyway. - */ - diff |= CHECK_MASK(id_mmfr0, 0xff0fffff, boot, cur, cpu); - diff |= CHECK(id_mmfr1, boot, cur, cpu); - diff |= CHECK(id_mmfr2, boot, cur, cpu); - diff |= CHECK(id_mmfr3, boot, cur, cpu); - diff |= CHECK(id_pfr0, boot, cur, cpu); - diff |= CHECK(id_pfr1, boot, cur, cpu); - - diff |= CHECK(mvfr0, boot, cur, cpu); - diff |= CHECK(mvfr1, boot, cur, cpu); - diff |= CHECK(mvfr2, boot, cur, cpu); - - /* - * Mismatched CPU features are a recipe for disaster. Don't even - * pretend to support them. - */ - WARN_TAINT_ONCE(diff, TAINT_CPU_OUT_OF_SPEC, - "Unsupported CPU feature variation.\n"); + pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu); } static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) @@ -236,15 +234,13 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) cpuinfo_detect_icache_policy(info); check_local_cpu_errata(); - check_local_cpu_features(); - update_cpu_features(info); } void cpuinfo_store_cpu(void) { struct cpuinfo_arm64 *info = this_cpu_ptr(&cpu_data); __cpuinfo_store_cpu(info); - cpuinfo_sanity_check(info); + update_cpu_features(smp_processor_id(), info, &boot_cpu_data); } void __init cpuinfo_store_boot_cpu(void) @@ -253,4 +249,5 @@ void __init cpuinfo_store_boot_cpu(void) __cpuinfo_store_cpu(info); boot_cpu_data = *info; + init_cpu_features(&boot_cpu_data); } diff --git a/kernel/arch/arm64/kernel/debug-monitors.c b/kernel/arch/arm64/kernel/debug-monitors.c index 70654d843..c1492ba1f 100644 --- a/kernel/arch/arm64/kernel/debug-monitors.c +++ b/kernel/arch/arm64/kernel/debug-monitors.c @@ -26,14 +26,16 @@ #include #include -#include +#include #include +#include #include /* Determine debug architecture. */ u8 debug_monitors_arch(void) { - return read_cpuid(ID_AA64DFR0_EL1) & 0xf; + return cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1), + ID_AA64DFR0_DEBUGVER_SHIFT); } /* @@ -58,7 +60,7 @@ static u32 mdscr_read(void) * Allow root to disable self-hosted debug from userspace. * This is useful if you want to connect an external JTAG debugger. */ -static u32 debug_enabled = 1; +static bool debug_enabled = true; static int create_debug_debugfs_entry(void) { @@ -69,7 +71,7 @@ fs_initcall(create_debug_debugfs_entry); static int __init early_debug_disable(char *buf) { - debug_enabled = 0; + debug_enabled = false; return 0; } @@ -82,7 +84,7 @@ early_param("nodebugmon", early_debug_disable); static DEFINE_PER_CPU(int, mde_ref_count); static DEFINE_PER_CPU(int, kde_ref_count); -void enable_debug_monitors(enum debug_el el) +void enable_debug_monitors(enum dbg_active_el el) { u32 mdscr, enable = 0; @@ -102,7 +104,7 @@ void enable_debug_monitors(enum debug_el el) } } -void disable_debug_monitors(enum debug_el el) +void disable_debug_monitors(enum dbg_active_el el) { u32 mdscr, disable = 0; @@ -134,7 +136,7 @@ static int os_lock_notify(struct notifier_block *self, unsigned long action, void *data) { int cpu = (unsigned long)data; - if (action == CPU_ONLINE) + if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) smp_call_function_single(cpu, clear_os_lock, NULL, 1); return NOTIFY_OK; } @@ -184,24 +186,25 @@ static void clear_regs_spsr_ss(struct pt_regs *regs) /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); -static DEFINE_RWLOCK(step_hook_lock); +static DEFINE_SPINLOCK(step_hook_lock); void register_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_add(&hook->node, &step_hook); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_add_rcu(&hook->node, &step_hook); + spin_unlock(&step_hook_lock); } void unregister_step_hook(struct step_hook *hook) { - write_lock(&step_hook_lock); - list_del(&hook->node); - write_unlock(&step_hook_lock); + spin_lock(&step_hook_lock); + list_del_rcu(&hook->node); + spin_unlock(&step_hook_lock); + synchronize_rcu(); } /* - * Call registered single step handers + * Call registered single step handlers * There is no Syndrome info to check for determining the handler. * So we call all the registered handlers, until the right handler is * found which returns zero. @@ -211,15 +214,15 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) struct step_hook *hook; int retval = DBG_HOOK_ERROR; - read_lock(&step_hook_lock); + rcu_read_lock(); - list_for_each_entry(hook, &step_hook, node) { + list_for_each_entry_rcu(hook, &step_hook, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - read_unlock(&step_hook_lock); + rcu_read_unlock(); return retval; } diff --git a/kernel/arch/arm64/kernel/efi-entry.S b/kernel/arch/arm64/kernel/efi-entry.S index 8ce9b0577..a773db929 100644 --- a/kernel/arch/arm64/kernel/efi-entry.S +++ b/kernel/arch/arm64/kernel/efi-entry.S @@ -29,7 +29,7 @@ * we want to be. The kernel image wants to be placed at TEXT_OFFSET * from start of RAM. */ -ENTRY(efi_stub_entry) +ENTRY(entry) /* * Create a stack frame to save FP/LR with extra space * for image_addr variable passed to efi_entry(). @@ -86,8 +86,8 @@ ENTRY(efi_stub_entry) * entries for the VA range of the current image, so no maintenance is * necessary. */ - adr x0, efi_stub_entry - adr x1, efi_stub_entry_end + adr x0, entry + adr x1, entry_end sub x1, x1, x0 bl __flush_dcache_area @@ -120,5 +120,5 @@ efi_load_fail: ldp x29, x30, [sp], #32 ret -efi_stub_entry_end: -ENDPROC(efi_stub_entry) +entry_end: +ENDPROC(entry) diff --git a/kernel/arch/arm64/kernel/efi-stub.c b/kernel/arch/arm64/kernel/efi-stub.c deleted file mode 100644 index f5374065a..000000000 --- a/kernel/arch/arm64/kernel/efi-stub.c +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Copyright (C) 2013, 2014 Linaro Ltd; - * - * This file implements the EFI boot stub for the arm64 kernel. - * Adapted from ARM version by Mark Salter - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ -#include -#include -#include - -efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table, - unsigned long *image_addr, - unsigned long *image_size, - unsigned long *reserve_addr, - unsigned long *reserve_size, - unsigned long dram_base, - efi_loaded_image_t *image) -{ - efi_status_t status; - unsigned long kernel_size, kernel_memsize = 0; - - /* Relocate the image, if required. */ - kernel_size = _edata - _text; - if (*image_addr != (dram_base + TEXT_OFFSET)) { - kernel_memsize = kernel_size + (_end - _edata); - status = efi_low_alloc(sys_table, kernel_memsize + TEXT_OFFSET, - SZ_2M, reserve_addr); - if (status != EFI_SUCCESS) { - pr_efi_err(sys_table, "Failed to relocate kernel\n"); - return status; - } - memcpy((void *)*reserve_addr + TEXT_OFFSET, (void *)*image_addr, - kernel_size); - *image_addr = *reserve_addr + TEXT_OFFSET; - *reserve_size = kernel_memsize + TEXT_OFFSET; - } - - - return EFI_SUCCESS; -} diff --git a/kernel/arch/arm64/kernel/efi.c b/kernel/arch/arm64/kernel/efi.c index 352962bc2..4eeb17198 100644 --- a/kernel/arch/arm64/kernel/efi.c +++ b/kernel/arch/arm64/kernel/efi.c @@ -48,18 +48,8 @@ static struct mm_struct efi_mm = { .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), - INIT_MM_CONTEXT(efi_mm) }; -static int uefi_debug __initdata; -static int __init uefi_debug_setup(char *str) -{ - uefi_debug = 1; - - return 0; -} -early_param("uefi_debug", uefi_debug_setup); - static int __init is_normal_ram(efi_memory_desc_t *md) { if (md->attribute & EFI_MEMORY_WB) @@ -137,7 +127,11 @@ static int __init uefi_init(void) table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables; config_tables = early_memremap(efi_to_phys(efi.systab->tables), table_size); - + if (config_tables == NULL) { + pr_warn("Unable to map EFI config table array.\n"); + retval = -ENOMEM; + goto out; + } retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables, sizeof(efi_config_table_64_t), NULL); @@ -158,6 +152,7 @@ static __init int is_reserve_region(efi_memory_desc_t *md) case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: return 0; default: break; @@ -170,14 +165,14 @@ static __init void reserve_regions(void) efi_memory_desc_t *md; u64 paddr, npages, size; - if (uefi_debug) + if (efi_enabled(EFI_DBG)) pr_info("Processing EFI memory map:\n"); for_each_efi_memory_desc(&memmap, md) { paddr = md->phys_addr; npages = md->num_pages; - if (uefi_debug) { + if (efi_enabled(EFI_DBG)) { char buf[64]; pr_info(" 0x%012llx-0x%012llx %s", @@ -193,11 +188,11 @@ static __init void reserve_regions(void) if (is_reserve_region(md)) { memblock_reserve(paddr, size); - if (uefi_debug) + if (efi_enabled(EFI_DBG)) pr_cont("*"); } - if (uefi_debug) + if (efi_enabled(EFI_DBG)) pr_cont("\n"); } @@ -209,15 +204,23 @@ void __init efi_init(void) struct efi_fdt_params params; /* Grab UEFI information placed in FDT by stub */ - if (!efi_get_fdt_params(¶ms, uefi_debug)) + if (!efi_get_fdt_params(¶ms)) return; efi_system_table = params.system_table; memblock_reserve(params.mmap & PAGE_MASK, PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK))); - memmap.phys_map = (void *)params.mmap; + memmap.phys_map = params.mmap; memmap.map = early_memremap(params.mmap, params.mmap_size); + if (memmap.map == NULL) { + /* + * If we are booting via UEFI, the UEFI memory map is the only + * description of memory we have, so there is little point in + * proceeding if we cannot access it. + */ + panic("Unable to map EFI memory map.\n"); + } memmap.map_end = memmap.map + params.mmap_size; memmap.desc_size = params.desc_size; memmap.desc_version = params.desc_ver; @@ -233,8 +236,9 @@ static bool __init efi_virtmap_init(void) { efi_memory_desc_t *md; + init_new_context(NULL, &efi_mm); + for_each_efi_memory_desc(&memmap, md) { - u64 paddr, npages, size; pgprot_t prot; if (!(md->attribute & EFI_MEMORY_RUNTIME)) @@ -242,11 +246,6 @@ static bool __init efi_virtmap_init(void) if (md->virt_addr == 0) return false; - paddr = md->phys_addr; - npages = md->num_pages; - memrange_efi_to_native(&paddr, &npages); - size = npages << PAGE_SHIFT; - pr_info(" EFI remap 0x%016llx => %p\n", md->phys_addr, (void *)md->virt_addr); @@ -257,12 +256,15 @@ static bool __init efi_virtmap_init(void) */ if (!is_normal_ram(md)) prot = __pgprot(PROT_DEVICE_nGnRE); - else if (md->type == EFI_RUNTIME_SERVICES_CODE) + else if (md->type == EFI_RUNTIME_SERVICES_CODE || + !PAGE_ALIGNED(md->phys_addr)) prot = PAGE_KERNEL_EXEC; else prot = PAGE_KERNEL; - create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot); + create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + __pgprot(pgprot_val(prot) | PTE_NG)); } return true; } @@ -278,22 +280,22 @@ static int __init arm64_enable_runtime_services(void) if (!efi_enabled(EFI_BOOT)) { pr_info("EFI services will not be available.\n"); - return -1; + return 0; } if (efi_runtime_disabled()) { pr_info("EFI runtime services will be disabled.\n"); - return -1; + return 0; } pr_info("Remapping and enabling EFI services.\n"); mapsize = memmap.map_end - memmap.map; - memmap.map = (__force void *)ioremap_cache((phys_addr_t)memmap.phys_map, + memmap.map = (__force void *)ioremap_cache(memmap.phys_map, mapsize); if (!memmap.map) { pr_err("Failed to remap EFI memory map\n"); - return -1; + return -ENOMEM; } memmap.map_end = memmap.map + mapsize; efi.memmap = &memmap; @@ -302,13 +304,13 @@ static int __init arm64_enable_runtime_services(void) sizeof(efi_system_table_t)); if (!efi.systab) { pr_err("Failed to remap EFI System Table\n"); - return -1; + return -ENOMEM; } set_bit(EFI_SYSTEM_TABLES, &efi.flags); if (!efi_virtmap_init()) { pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n"); - return -1; + return -ENOMEM; } /* Set up runtime services function pointers */ @@ -337,14 +339,7 @@ core_initcall(arm64_dmi_init); static void efi_set_pgd(struct mm_struct *mm) { - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); - - flush_tlb_all(); - if (icache_is_aivivt()) - __flush_icache_all(); + switch_mm(NULL, mm, NULL); } void efi_virtmap_load(void) diff --git a/kernel/arch/arm64/kernel/entry-ftrace.S b/kernel/arch/arm64/kernel/entry-ftrace.S index 08cafc518..0f03a8fe2 100644 --- a/kernel/arch/arm64/kernel/entry-ftrace.S +++ b/kernel/arch/arm64/kernel/entry-ftrace.S @@ -178,6 +178,24 @@ ENTRY(ftrace_stub) ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* save return value regs*/ + .macro save_return_regs + sub sp, sp, #64 + stp x0, x1, [sp] + stp x2, x3, [sp, #16] + stp x4, x5, [sp, #32] + stp x6, x7, [sp, #48] + .endm + + /* restore return value regs*/ + .macro restore_return_regs + ldp x0, x1, [sp] + ldp x2, x3, [sp, #16] + ldp x4, x5, [sp, #32] + ldp x6, x7, [sp, #48] + add sp, sp, #64 + .endm + /* * void ftrace_graph_caller(void) * @@ -204,11 +222,11 @@ ENDPROC(ftrace_graph_caller) * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled. */ ENTRY(return_to_handler) - str x0, [sp, #-16]! + save_return_regs mov x0, x29 // parent's fp bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); mov x30, x0 // restore the original return address - ldr x0, [sp], #16 + restore_return_regs ret END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/kernel/arch/arm64/kernel/entry.S b/kernel/arch/arm64/kernel/entry.S index 6515be375..dd8fd31f8 100644 --- a/kernel/arch/arm64/kernel/entry.S +++ b/kernel/arch/arm64/kernel/entry.S @@ -21,7 +21,7 @@ #include #include -#include +#include #include #include #include @@ -116,38 +116,34 @@ */ .endm - .macro kernel_exit, el, ret = 0 + .macro kernel_exit, el ldp x21, x22, [sp, #S_PC] // load ELR, SPSR .if \el == 0 ct_user_enter ldr x23, [sp, #S_SP] // load return stack pointer msr sp_el0, x23 - #ifdef CONFIG_ARM64_ERRATUM_845719 - alternative_insn \ - "nop", \ - "tbz x22, #4, 1f", \ - ARM64_WORKAROUND_845719 +alternative_if_not ARM64_WORKAROUND_845719 + nop + nop +#ifdef CONFIG_PID_IN_CONTEXTIDR + nop +#endif +alternative_else + tbz x22, #4, 1f #ifdef CONFIG_PID_IN_CONTEXTIDR - alternative_insn \ - "nop; nop", \ - "mrs x29, contextidr_el1; msr contextidr_el1, x29; 1:", \ - ARM64_WORKAROUND_845719 + mrs x29, contextidr_el1 + msr contextidr_el1, x29 #else - alternative_insn \ - "nop", \ - "msr contextidr_el1, xzr; 1:", \ - ARM64_WORKAROUND_845719 + msr contextidr_el1, xzr #endif +1: +alternative_endif #endif .endif msr elr_el1, x21 // set up the return data msr spsr_el1, x22 - .if \ret - ldr x1, [sp, #S_X1] // preserve x0 (syscall return) - .else ldp x0, x1, [sp, #16 * 0] - .endif ldp x2, x3, [sp, #16 * 1] ldp x4, x5, [sp, #16 * 2] ldp x6, x7, [sp, #16 * 3] @@ -349,8 +345,8 @@ el1_inv: // TODO: add support for undefined instructions in kernel mode enable_dbg mov x0, sp + mov x2, x1 mov x1, #BAD_SYNC - mrs x2, esr_el1 b bad_mode ENDPROC(el1_sync) @@ -440,6 +436,8 @@ el0_sync_compat: b.eq el0_fpsimd_acc cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception b.eq el0_fpsimd_exc + cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception + b.eq el0_sp_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap @@ -556,7 +554,7 @@ el0_inv: ct_user_exit mov x0, sp mov x1, #BAD_SYNC - mrs x2, esr_el1 + mov x2, x25 bl bad_mode b ret_to_user ENDPROC(el0_sync) @@ -588,7 +586,8 @@ ENDPROC(el0_irq) * */ ENTRY(cpu_switch_to) - add x8, x0, #THREAD_CPU_CONTEXT + mov x10, #THREAD_CPU_CONTEXT + add x8, x0, x10 mov x9, sp stp x19, x20, [x8], #16 // store callee-saved registers stp x21, x22, [x8], #16 @@ -597,7 +596,7 @@ ENTRY(cpu_switch_to) stp x27, x28, [x8], #16 stp x29, x9, [x8], #16 str lr, [x8] - add x8, x1, #THREAD_CPU_CONTEXT + add x8, x1, x10 ldp x19, x20, [x8], #16 // restore callee-saved registers ldp x21, x22, [x8], #16 ldp x23, x24, [x8], #16 @@ -615,17 +614,21 @@ ENDPROC(cpu_switch_to) */ ret_fast_syscall: disable_irq // disable interrupts - ldr x1, [tsk, #TI_FLAGS] + str x0, [sp, #S_X0] // returned x0 + ldr x1, [tsk, #TI_FLAGS] // re-check for syscall tracing + and x2, x1, #_TIF_SYSCALL_WORK + cbnz x2, ret_fast_syscall_trace and x2, x1, #_TIF_WORK_MASK - cbnz x2, fast_work_pending + cbnz x2, work_pending enable_step_tsk x1, x2 - kernel_exit 0, ret = 1 + kernel_exit 0 +ret_fast_syscall_trace: + enable_irq // enable interrupts + b __sys_trace_return_skipped // we already saved x0 /* * Ok, we need to do extra processing, enter the slow path. */ -fast_work_pending: - str x0, [sp, #S_X0] // returned x0 work_pending: tbnz x1, #TIF_NEED_RESCHED, work_resched tbnz x1, #TIF_NEED_RESCHED_LAZY, work_resched @@ -650,7 +653,7 @@ ret_to_user: cbnz x2, work_pending enable_step_tsk x1, x2 no_work_pending: - kernel_exit 0, ret = 0 + kernel_exit 0 ENDPROC(ret_to_user) /* diff --git a/kernel/arch/arm64/kernel/entry32.S b/kernel/arch/arm64/kernel/entry32.S index bd9bfaa92..f332d5d1f 100644 --- a/kernel/arch/arm64/kernel/entry32.S +++ b/kernel/arch/arm64/kernel/entry32.S @@ -32,13 +32,11 @@ ENTRY(compat_sys_sigreturn_wrapper) mov x0, sp - mov x27, #0 // prevent syscall restart handling (why) b compat_sys_sigreturn ENDPROC(compat_sys_sigreturn_wrapper) ENTRY(compat_sys_rt_sigreturn_wrapper) mov x0, sp - mov x27, #0 // prevent syscall restart handling (why) b compat_sys_rt_sigreturn ENDPROC(compat_sys_rt_sigreturn_wrapper) diff --git a/kernel/arch/arm64/kernel/fpsimd.c b/kernel/arch/arm64/kernel/fpsimd.c index c31e59fe2..4c46c54a3 100644 --- a/kernel/arch/arm64/kernel/fpsimd.c +++ b/kernel/arch/arm64/kernel/fpsimd.c @@ -17,6 +17,7 @@ * along with this program. If not, see . */ +#include #include #include #include @@ -297,25 +298,49 @@ static void fpsimd_pm_init(void) static inline void fpsimd_pm_init(void) { } #endif /* CONFIG_CPU_PM */ +#ifdef CONFIG_HOTPLUG_CPU +static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action) { + case CPU_DEAD: + case CPU_DEAD_FROZEN: + per_cpu(fpsimd_last_state, cpu) = NULL; + break; + } + return NOTIFY_OK; +} + +static struct notifier_block fpsimd_cpu_hotplug_notifier_block = { + .notifier_call = fpsimd_cpu_hotplug_notifier, +}; + +static inline void fpsimd_hotplug_init(void) +{ + register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block); +} + +#else +static inline void fpsimd_hotplug_init(void) { } +#endif + /* * FP/SIMD support code initialisation. */ static int __init fpsimd_init(void) { - u64 pfr = read_cpuid(ID_AA64PFR0_EL1); - - if (pfr & (0xf << 16)) { + if (elf_hwcap & HWCAP_FP) { + fpsimd_pm_init(); + fpsimd_hotplug_init(); + } else { pr_notice("Floating-point is not implemented\n"); - return 0; } - elf_hwcap |= HWCAP_FP; - if (pfr & (0xf << 20)) + if (!(elf_hwcap & HWCAP_ASIMD)) pr_notice("Advanced SIMD is not implemented\n"); - else - elf_hwcap |= HWCAP_ASIMD; - - fpsimd_pm_init(); return 0; } diff --git a/kernel/arch/arm64/kernel/head.S b/kernel/arch/arm64/kernel/head.S index 36aa31ff2..b68525792 100644 --- a/kernel/arch/arm64/kernel/head.S +++ b/kernel/arch/arm64/kernel/head.S @@ -29,11 +29,13 @@ #include #include #include +#include #include -#include #include #include #include +#include +#include #include #define __PHYS_OFFSET (KERNEL_START - TEXT_OFFSET) @@ -46,36 +48,9 @@ #error TEXT_OFFSET must be less than 2MB #endif -#ifdef CONFIG_ARM64_64K_PAGES -#define BLOCK_SHIFT PAGE_SHIFT -#define BLOCK_SIZE PAGE_SIZE -#define TABLE_SHIFT PMD_SHIFT -#else -#define BLOCK_SHIFT SECTION_SHIFT -#define BLOCK_SIZE SECTION_SIZE -#define TABLE_SHIFT PUD_SHIFT -#endif - #define KERNEL_START _text #define KERNEL_END _end -/* - * Initial memory map attributes. - */ -#ifndef CONFIG_SMP -#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF -#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF -#else -#define PTE_FLAGS PTE_TYPE_PAGE | PTE_AF | PTE_SHARED -#define PMD_FLAGS PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S -#endif - -#ifdef CONFIG_ARM64_64K_PAGES -#define MM_MMUFLAGS PTE_ATTRINDX(MT_NORMAL) | PTE_FLAGS -#else -#define MM_MMUFLAGS PMD_ATTRINDX(MT_NORMAL) | PMD_FLAGS -#endif - /* * Kernel startup entry point. * --------------------------- @@ -125,8 +100,8 @@ efi_head: #endif #ifdef CONFIG_EFI - .globl stext_offset - .set stext_offset, stext - efi_head + .globl __efistub_stext_offset + .set __efistub_stext_offset, stext - efi_head .align 3 pe_header: .ascii "PE" @@ -149,8 +124,8 @@ optional_header: .long _end - stext // SizeOfCode .long 0 // SizeOfInitializedData .long 0 // SizeOfUninitializedData - .long efi_stub_entry - efi_head // AddressOfEntryPoint - .long stext_offset // BaseOfCode + .long __efistub_entry - efi_head // AddressOfEntryPoint + .long __efistub_stext_offset // BaseOfCode extra_header_fields: .quad 0 // ImageBase @@ -167,7 +142,7 @@ extra_header_fields: .long _end - efi_head // SizeOfImage // Everything before the kernel image is considered part of the header - .long stext_offset // SizeOfHeaders + .long __efistub_stext_offset // SizeOfHeaders .long 0 // CheckSum .short 0xa // Subsystem (EFI application) .short 0 // DllCharacteristics @@ -212,9 +187,9 @@ section_table: .byte 0 .byte 0 // end of 0 padding of section name .long _end - stext // VirtualSize - .long stext_offset // VirtualAddress + .long __efistub_stext_offset // VirtualAddress .long _edata - stext // SizeOfRawData - .long stext_offset // PointerToRawData + .long __efistub_stext_offset // PointerToRawData .long 0 // PointerToRelocations (0 for executables) .long 0 // PointerToLineNumbers (0 for executables) @@ -237,8 +212,6 @@ ENTRY(stext) bl el2_setup // Drop to EL1, w20=cpu_boot_mode adrp x24, __PHYS_OFFSET bl set_cpu_boot_mode_flag - - bl __vet_fdt bl __create_page_tables // x25=TTBR0, x26=TTBR1 /* * The following calls CPU setup code, see arch/arm64/mm/proc.S for @@ -269,24 +242,6 @@ preserve_boot_args: b __inval_cache_range // tail call ENDPROC(preserve_boot_args) -/* - * Determine validity of the x21 FDT pointer. - * The dtb must be 8-byte aligned and live in the first 512M of memory. - */ -__vet_fdt: - tst x21, #0x7 - b.ne 1f - cmp x21, x24 - b.lt 1f - mov x0, #(1 << 29) - add x0, x0, x24 - cmp x21, x0 - b.ge 1f - ret -1: - mov x21, #0 - ret -ENDPROC(__vet_fdt) /* * Macro to create a table entry to the next page. * @@ -317,8 +272,11 @@ ENDPROC(__vet_fdt) */ .macro create_pgd_entry, tbl, virt, tmp1, tmp2 create_table_entry \tbl, \virt, PGDIR_SHIFT, PTRS_PER_PGD, \tmp1, \tmp2 -#if SWAPPER_PGTABLE_LEVELS == 3 - create_table_entry \tbl, \virt, TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2 +#if SWAPPER_PGTABLE_LEVELS > 3 + create_table_entry \tbl, \virt, PUD_SHIFT, PTRS_PER_PUD, \tmp1, \tmp2 +#endif +#if SWAPPER_PGTABLE_LEVELS > 2 + create_table_entry \tbl, \virt, SWAPPER_TABLE_SHIFT, PTRS_PER_PTE, \tmp1, \tmp2 #endif .endm @@ -330,15 +288,15 @@ ENDPROC(__vet_fdt) * Corrupts: phys, start, end, pstate */ .macro create_block_map, tbl, flags, phys, start, end - lsr \phys, \phys, #BLOCK_SHIFT - lsr \start, \start, #BLOCK_SHIFT + lsr \phys, \phys, #SWAPPER_BLOCK_SHIFT + lsr \start, \start, #SWAPPER_BLOCK_SHIFT and \start, \start, #PTRS_PER_PTE - 1 // table index - orr \phys, \flags, \phys, lsl #BLOCK_SHIFT // table entry - lsr \end, \end, #BLOCK_SHIFT + orr \phys, \flags, \phys, lsl #SWAPPER_BLOCK_SHIFT // table entry + lsr \end, \end, #SWAPPER_BLOCK_SHIFT and \end, \end, #PTRS_PER_PTE - 1 // table end index 9999: str \phys, [\tbl, \start, lsl #3] // store the entry add \start, \start, #1 // next entry - add \phys, \phys, #BLOCK_SIZE // next block + add \phys, \phys, #SWAPPER_BLOCK_SIZE // next block cmp \start, \end b.ls 9999b .endm @@ -348,8 +306,7 @@ ENDPROC(__vet_fdt) * required to get the kernel running. The following sections are required: * - identity mapping to enable the MMU (low address, TTBR0) * - first few MB of the kernel linear mapping to jump to once the MMU has - * been enabled, including the FDT blob (TTBR1) - * - pgd entry for fixed mappings (TTBR1) + * been enabled */ __create_page_tables: adrp x25, idmap_pg_dir @@ -376,13 +333,13 @@ __create_page_tables: cmp x0, x6 b.lo 1b - ldr x7, =MM_MMUFLAGS + ldr x7, =SWAPPER_MM_MMUFLAGS /* * Create the identity mapping. */ mov x0, x25 // idmap_pg_dir - adrp x3, KERNEL_START // __pa(KERNEL_START) + adrp x3, __idmap_text_start // __pa(__idmap_text_start) #ifndef CONFIG_ARM64_VA_BITS_48 #define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) @@ -405,11 +362,11 @@ __create_page_tables: /* * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the - * entire kernel image can be ID mapped. As T0SZ == (64 - #bits used), + * entire ID map region can be mapped. As T0SZ == (64 - #bits used), * this number conveniently equals the number of leading zeroes in - * the physical address of KERNEL_END. + * the physical address of __idmap_text_end. */ - adrp x5, KERNEL_END + adrp x5, __idmap_text_end clz x5, x5 cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough? b.ge 1f // .. then skip additional level @@ -424,8 +381,8 @@ __create_page_tables: #endif create_pgd_entry x0, x3, x5, x6 - mov x5, x3 // __pa(KERNEL_START) - adr_l x6, KERNEL_END // __pa(KERNEL_END) + mov x5, x3 // __pa(__idmap_text_start) + adr_l x6, __idmap_text_end // __pa(__idmap_text_end) create_block_map x0, x7, x3, x5, x6 /* @@ -438,22 +395,6 @@ __create_page_tables: mov x3, x24 // phys offset create_block_map x0, x7, x3, x5, x6 - /* - * Map the FDT blob (maximum 2MB; must be within 512MB of - * PHYS_OFFSET). - */ - mov x3, x21 // FDT phys address - and x3, x3, #~((1 << 21) - 1) // 2MB aligned - mov x6, #PAGE_OFFSET - sub x5, x3, x24 // subtract PHYS_OFFSET - tst x5, #~((1 << 29) - 1) // within 512MB? - csel x21, xzr, x21, ne // zero the FDT pointer - b.ne 1f - add x5, x5, x6 // __va(FDT blob) - add x6, x5, #1 << 21 // 2MB for the FDT blob - sub x6, x6, #1 // inclusive range - create_block_map x0, x7, x3, x5, x6 -1: /* * Since the page tables have been populated with non-cacheable * accesses (MMU disabled), invalidate the idmap and swapper page @@ -486,6 +427,9 @@ __mmap_switched: str_l x21, __fdt_pointer, x5 // Save FDT pointer str_l x24, memstart_addr, x6 // Save PHYS_OFFSET mov x29, #0 +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif b start_kernel ENDPROC(__mmap_switched) @@ -540,6 +484,8 @@ CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1 orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1 msr_s ICC_SRE_EL2, x0 isb // Make sure SRE is now set + mrs_s x0, ICC_SRE_EL2 // Read SRE back, + tbz x0, #0, 3f // and check that it sticks msr_s ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults 3: @@ -566,9 +512,14 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems #endif /* EL2 debug */ + mrs x0, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx x0, x0, #8, #4 + cmp x0, #1 + b.lt 4f // Skip if no PMU present mrs x0, pmcr_el0 // Disable debug access traps ubfx x0, x0, #11, #5 // to EL2 and allow access to msr mdcr_el2, x0 // all PMU counters from EL1 +4: /* Stage-2 translation */ msr vttbr_el2, xzr @@ -616,7 +567,6 @@ ENTRY(__boot_cpu_mode) .long BOOT_CPU_MODE_EL1 .popsection -#ifdef CONFIG_SMP /* * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise. @@ -664,7 +614,6 @@ ENTRY(__secondary_switched) mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) -#endif /* CONFIG_SMP */ /* * Enable the MMU. @@ -672,9 +621,17 @@ ENDPROC(__secondary_switched) * x0 = SCTLR_EL1 value for turning on the MMU. * x27 = *virtual* address to jump to upon completion * - * other registers depend on the function called upon completion + * Other registers depend on the function called upon completion. + * + * Checks if the selected granule size is supported by the CPU. + * If it isn't, park the CPU */ + .section ".idmap.text", "ax" __enable_mmu: + mrs x1, ID_AA64MMFR0_EL1 + ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4 + cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED + b.ne __no_granule_support ldr x5, =vectors msr vbar_el1, x5 msr ttbr0_el1, x25 // load TTBR0 @@ -682,5 +639,18 @@ __enable_mmu: isb msr sctlr_el1, x0 isb + /* + * Invalidate the local I-cache so that any instructions fetched + * speculatively from the PoC are discarded, since they may have + * been dynamically patched at the PoU. + */ + ic iallu + dsb nsh + isb br x27 ENDPROC(__enable_mmu) + +__no_granule_support: + wfe + b __no_granule_support +ENDPROC(__no_granule_support) diff --git a/kernel/arch/arm64/kernel/hw_breakpoint.c b/kernel/arch/arm64/kernel/hw_breakpoint.c index e7d934d3a..b45c95d34 100644 --- a/kernel/arch/arm64/kernel/hw_breakpoint.c +++ b/kernel/arch/arm64/kernel/hw_breakpoint.c @@ -28,10 +28,10 @@ #include #include +#include #include #include #include -#include #include #include #include @@ -49,18 +49,6 @@ static DEFINE_PER_CPU(int, stepping_kernel_bp); static int core_num_brps; static int core_num_wrps; -/* Determine number of BRP registers available. */ -static int get_num_brps(void) -{ - return ((read_cpuid(ID_AA64DFR0_EL1) >> 12) & 0xf) + 1; -} - -/* Determine number of WRP registers available. */ -static int get_num_wrps(void) -{ - return ((read_cpuid(ID_AA64DFR0_EL1) >> 20) & 0xf) + 1; -} - int hw_breakpoint_slots(int type) { /* @@ -157,7 +145,7 @@ static void write_wb_reg(int reg, int n, u64 val) * Convert a breakpoint privilege level to the corresponding exception * level. */ -static enum debug_el debug_exception_level(int privilege) +static enum dbg_active_el debug_exception_level(int privilege) { switch (privilege) { case AARCH64_BREAKPOINT_EL0: @@ -176,6 +164,20 @@ enum hw_breakpoint_ops { HW_BREAKPOINT_RESTORE }; +static int is_compat_bp(struct perf_event *bp) +{ + struct task_struct *tsk = bp->hw.target; + + /* + * tsk can be NULL for per-cpu (non-ptrace) breakpoints. + * In this case, use the native interface, since we don't have + * the notion of a "compat CPU" and could end up relying on + * deprecated behaviour if we use unaligned watchpoints in + * AArch64 state. + */ + return tsk && is_compat_thread(task_thread_info(tsk)); +} + /** * hw_breakpoint_slot_setup - Find and setup a perf slot according to * operations @@ -231,7 +233,7 @@ static int hw_breakpoint_control(struct perf_event *bp, struct perf_event **slots; struct debug_info *debug_info = ¤t->thread.debug; int i, max_slots, ctrl_reg, val_reg, reg_enable; - enum debug_el dbg_el = debug_exception_level(info->ctrl.privilege); + enum dbg_active_el dbg_el = debug_exception_level(info->ctrl.privilege); u32 ctrl; if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { @@ -433,7 +435,7 @@ static int arch_build_bp_info(struct perf_event *bp) * Watchpoints can be of length 1, 2, 4 or 8 bytes. */ if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { - if (is_compat_task()) { + if (is_compat_bp(bp)) { if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 && info->ctrl.len != ARM_BREAKPOINT_LEN_4) return -EINVAL; @@ -490,7 +492,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * AArch32 tasks expect some simple alignment fixups, so emulate * that here. */ - if (is_compat_task()) { + if (is_compat_bp(bp)) { if (info->ctrl.len == ARM_BREAKPOINT_LEN_8) alignment_mask = 0x7; else @@ -538,7 +540,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp) * exception level at the register level. * This is used when single-stepping after a breakpoint exception. */ -static void toggle_bp_registers(int reg, enum debug_el el, int enable) +static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable) { int i, max_slots, privilege; u32 ctrl; @@ -885,7 +887,7 @@ static int hw_breakpoint_reset_notify(struct notifier_block *self, void *hcpu) { int cpu = (long)hcpu; - if (action == CPU_ONLINE) + if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1); return NOTIFY_OK; } diff --git a/kernel/arch/arm64/kernel/image.h b/kernel/arch/arm64/kernel/image.h index 8fae0756e..bc2abb8b1 100644 --- a/kernel/arch/arm64/kernel/image.h +++ b/kernel/arch/arm64/kernel/image.h @@ -47,7 +47,10 @@ #define __HEAD_FLAG_BE 0 #endif -#define __HEAD_FLAGS (__HEAD_FLAG_BE << 0) +#define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2) + +#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \ + (__HEAD_FLAG_PAGE_SIZE << 1)) /* * These will output as part of the Image header, which should be little-endian @@ -59,4 +62,37 @@ _kernel_offset_le = DATA_LE64(TEXT_OFFSET); \ _kernel_flags_le = DATA_LE64(__HEAD_FLAGS); +#ifdef CONFIG_EFI + +/* + * The EFI stub has its own symbol namespace prefixed by __efistub_, to + * isolate it from the kernel proper. The following symbols are legally + * accessed by the stub, so provide some aliases to make them accessible. + * Only include data symbols here, or text symbols of functions that are + * guaranteed to be safe when executed at another offset than they were + * linked at. The routines below are all implemented in assembler in a + * position independent manner + */ +__efistub_memcmp = __pi_memcmp; +__efistub_memchr = __pi_memchr; +__efistub_memcpy = __pi_memcpy; +__efistub_memmove = __pi_memmove; +__efistub_memset = __pi_memset; +__efistub_strlen = __pi_strlen; +__efistub_strcmp = __pi_strcmp; +__efistub_strncmp = __pi_strncmp; +__efistub___flush_dcache_area = __pi___flush_dcache_area; + +#ifdef CONFIG_KASAN +__efistub___memcpy = __pi_memcpy; +__efistub___memmove = __pi_memmove; +__efistub___memset = __pi_memset; +#endif + +__efistub__text = _text; +__efistub__end = _end; +__efistub__edata = _edata; + +#endif + #endif /* __ASM_IMAGE_H */ diff --git a/kernel/arch/arm64/kernel/insn.c b/kernel/arch/arm64/kernel/insn.c index 30eb88e5b..c08b9ad6f 100644 --- a/kernel/arch/arm64/kernel/insn.c +++ b/kernel/arch/arm64/kernel/insn.c @@ -77,6 +77,14 @@ bool __kprobes aarch64_insn_is_nop(u32 insn) } } +bool aarch64_insn_is_branch_imm(u32 insn) +{ + return (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) || + aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) || + aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_bcond(insn)); +} + static DEFINE_RAW_SPINLOCK(patch_lock); static void __kprobes *patch_map(void *addr, int fixmap) @@ -93,9 +101,8 @@ static void __kprobes *patch_map(void *addr, int fixmap) return addr; BUG_ON(!page); - set_fixmap(fixmap, page_to_phys(page)); - - return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); + return (void *)set_fixmap_offset(fixmap, page_to_phys(page) + + (uintaddr & ~PAGE_MASK)); } static void __kprobes patch_unmap(int fixmap) @@ -1057,6 +1064,58 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +/* + * Decode the imm field of a branch, and return the byte offset as a + * signed value (so it can be used when computing a new branch + * target). + */ +s32 aarch64_get_branch_offset(u32 insn) +{ + s32 imm; + + if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) { + imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn); + return (imm << 6) >> 4; + } + + if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_bcond(insn)) { + imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_19, insn); + return (imm << 13) >> 11; + } + + if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) { + imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_14, insn); + return (imm << 18) >> 16; + } + + /* Unhandled instruction */ + BUG(); +} + +/* + * Encode the displacement of a branch in the imm field and return the + * updated instruction. + */ +u32 aarch64_set_branch_offset(u32 insn, s32 offset) +{ + if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) + return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_26, insn, + offset >> 2); + + if (aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_bcond(insn)) + return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_19, insn, + offset >> 2); + + if (aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn)) + return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_14, insn, + offset >> 2); + + /* Unhandled instruction */ + BUG(); +} + bool aarch32_insn_is_wide(u32 insn) { return insn >= 0xe800; diff --git a/kernel/arch/arm64/kernel/irq.c b/kernel/arch/arm64/kernel/irq.c index 240b75c0e..9f17ec071 100644 --- a/kernel/arch/arm64/kernel/irq.c +++ b/kernel/arch/arm64/kernel/irq.c @@ -27,15 +27,12 @@ #include #include #include -#include unsigned long irq_err_count; int arch_show_interrupts(struct seq_file *p, int prec) { -#ifdef CONFIG_SMP show_ipi_list(p, prec); -#endif seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count); return 0; } @@ -56,64 +53,3 @@ void __init init_IRQ(void) if (!handle_arch_irq) panic("No interrupt controller found."); } - -#ifdef CONFIG_HOTPLUG_CPU -static bool migrate_one_irq(struct irq_desc *desc) -{ - struct irq_data *d = irq_desc_get_irq_data(desc); - const struct cpumask *affinity = d->affinity; - struct irq_chip *c; - bool ret = false; - - /* - * If this is a per-CPU interrupt, or the affinity does not - * include this CPU, then we have nothing to do. - */ - if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) - return false; - - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - affinity = cpu_online_mask; - ret = true; - } - - c = irq_data_get_irq_chip(d); - if (!c->irq_set_affinity) - pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) - cpumask_copy(d->affinity, affinity); - - return ret; -} - -/* - * The current CPU has been marked offline. Migrate IRQs off this CPU. - * If the affinity settings do not allow other CPUs, force them onto any - * available CPU. - * - * Note: we must iterate over all IRQs, whether they have an attached - * action structure or not, as we need to get chained interrupts too. - */ -void migrate_irqs(void) -{ - unsigned int i; - struct irq_desc *desc; - unsigned long flags; - - local_irq_save(flags); - - for_each_irq_desc(i, desc) { - bool affinity_broken; - - raw_spin_lock(&desc->lock); - affinity_broken = migrate_one_irq(desc); - raw_spin_unlock(&desc->lock); - - if (affinity_broken) - pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", - i, smp_processor_id()); - } - - local_irq_restore(flags); -} -#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/arch/arm64/kernel/jump_label.c b/kernel/arch/arm64/kernel/jump_label.c index 4f1fec7a4..c2dd1ad3e 100644 --- a/kernel/arch/arm64/kernel/jump_label.c +++ b/kernel/arch/arm64/kernel/jump_label.c @@ -28,7 +28,7 @@ void arch_jump_label_transform(struct jump_entry *entry, void *addr = (void *)entry->code; u32 insn; - if (type == JUMP_LABEL_ENABLE) { + if (type == JUMP_LABEL_JMP) { insn = aarch64_insn_gen_branch_imm(entry->code, entry->target, AARCH64_INSN_BRANCH_NOLINK); diff --git a/kernel/arch/arm64/kernel/kgdb.c b/kernel/arch/arm64/kernel/kgdb.c index a0d10c55f..bcac81e60 100644 --- a/kernel/arch/arm64/kernel/kgdb.c +++ b/kernel/arch/arm64/kernel/kgdb.c @@ -235,13 +235,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) static struct break_hook kgdb_brkpt_hook = { .esr_mask = 0xffffffff, - .esr_val = DBG_ESR_VAL_BRK(KGDB_DYN_DBG_BRK_IMM), + .esr_val = (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM), .fn = kgdb_brk_fn }; static struct break_hook kgdb_compiled_brkpt_hook = { .esr_mask = 0xffffffff, - .esr_val = DBG_ESR_VAL_BRK(KGDB_COMPILED_DBG_BRK_IMM), + .esr_val = (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM), .fn = kgdb_compiled_brk_fn }; @@ -328,9 +328,9 @@ void kgdb_arch_exit(void) */ struct kgdb_arch arch_kgdb_ops = { .gdb_bpt_instr = { - KGDB_DYN_BRK_INS_BYTE0, - KGDB_DYN_BRK_INS_BYTE1, - KGDB_DYN_BRK_INS_BYTE2, - KGDB_DYN_BRK_INS_BYTE3, + KGDB_DYN_BRK_INS_BYTE(0), + KGDB_DYN_BRK_INS_BYTE(1), + KGDB_DYN_BRK_INS_BYTE(2), + KGDB_DYN_BRK_INS_BYTE(3), } }; diff --git a/kernel/arch/arm64/kernel/module.c b/kernel/arch/arm64/kernel/module.c index 876eb8df5..f4bc779e6 100644 --- a/kernel/arch/arm64/kernel/module.c +++ b/kernel/arch/arm64/kernel/module.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -34,9 +35,18 @@ void *module_alloc(unsigned long size) { - return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, 0, - NUMA_NO_NODE, __builtin_return_address(0)); + void *p; + + p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, 0, + NUMA_NO_NODE, __builtin_return_address(0)); + + if (p && (kasan_module_alloc(p, size) < 0)) { + vfree(p); + return NULL; + } + + return p; } enum aarch64_reloc_op { diff --git a/kernel/arch/arm64/kernel/pci.c b/kernel/arch/arm64/kernel/pci.c index 4095379dc..b3d098bd3 100644 --- a/kernel/arch/arm64/kernel/pci.c +++ b/kernel/arch/arm64/kernel/pci.c @@ -38,6 +38,19 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, return res->start; } +/** + * pcibios_enable_device - Enable I/O and memory. + * @dev: PCI device to be enabled + * @mask: bitmask of BARs to enable + */ +int pcibios_enable_device(struct pci_dev *dev, int mask) +{ + if (pci_has_flag(PCI_PROBE_ONLY)) + return 0; + + return pci_enable_resources(dev, mask); +} + /* * Try to assign the IRQ number from DT when adding a new device */ diff --git a/kernel/arch/arm64/kernel/perf_callchain.c b/kernel/arch/arm64/kernel/perf_callchain.c new file mode 100644 index 000000000..3aa74830c --- /dev/null +++ b/kernel/arch/arm64/kernel/perf_callchain.c @@ -0,0 +1,196 @@ +/* + * arm64 callchain support + * + * Copyright (C) 2015 ARM Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#include +#include + +#include + +struct frame_tail { + struct frame_tail __user *fp; + unsigned long lr; +} __attribute__((packed)); + +/* + * Get the return address for a single stackframe and return a pointer to the + * next frame tail. + */ +static struct frame_tail __user * +user_backtrace(struct frame_tail __user *tail, + struct perf_callchain_entry *entry) +{ + struct frame_tail buftail; + unsigned long err; + + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) + return NULL; + + pagefault_disable(); + err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); + pagefault_enable(); + + if (err) + return NULL; + + perf_callchain_store(entry, buftail.lr); + + /* + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ + if (tail >= buftail.fp) + return NULL; + + return buftail.fp; +} + +#ifdef CONFIG_COMPAT +/* + * The registers we're interested in are at the end of the variable + * length saved register structure. The fp points at the end of this + * structure so the address of this struct is: + * (struct compat_frame_tail *)(xxx->fp)-1 + * + * This code has been adapted from the ARM OProfile support. + */ +struct compat_frame_tail { + compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */ + u32 sp; + u32 lr; +} __attribute__((packed)); + +static struct compat_frame_tail __user * +compat_user_backtrace(struct compat_frame_tail __user *tail, + struct perf_callchain_entry *entry) +{ + struct compat_frame_tail buftail; + unsigned long err; + + /* Also check accessibility of one struct frame_tail beyond */ + if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) + return NULL; + + pagefault_disable(); + err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); + pagefault_enable(); + + if (err) + return NULL; + + perf_callchain_store(entry, buftail.lr); + + /* + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ + if (tail + 1 >= (struct compat_frame_tail __user *) + compat_ptr(buftail.fp)) + return NULL; + + return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1; +} +#endif /* CONFIG_COMPAT */ + +void perf_callchain_user(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* We don't support guest os callchain now */ + return; + } + + perf_callchain_store(entry, regs->pc); + + if (!compat_user_mode(regs)) { + /* AARCH64 mode */ + struct frame_tail __user *tail; + + tail = (struct frame_tail __user *)regs->regs[29]; + + while (entry->nr < PERF_MAX_STACK_DEPTH && + tail && !((unsigned long)tail & 0xf)) + tail = user_backtrace(tail, entry); + } else { +#ifdef CONFIG_COMPAT + /* AARCH32 compat mode */ + struct compat_frame_tail __user *tail; + + tail = (struct compat_frame_tail __user *)regs->compat_fp - 1; + + while ((entry->nr < PERF_MAX_STACK_DEPTH) && + tail && !((unsigned long)tail & 0x3)) + tail = compat_user_backtrace(tail, entry); +#endif + } +} + +/* + * Gets called by walk_stackframe() for every stackframe. This will be called + * whist unwinding the stackframe and is like a subroutine return so we use + * the PC. + */ +static int callchain_trace(struct stackframe *frame, void *data) +{ + struct perf_callchain_entry *entry = data; + perf_callchain_store(entry, frame->pc); + return 0; +} + +void perf_callchain_kernel(struct perf_callchain_entry *entry, + struct pt_regs *regs) +{ + struct stackframe frame; + + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + /* We don't support guest os callchain now */ + return; + } + + frame.fp = regs->regs[29]; + frame.sp = regs->sp; + frame.pc = regs->pc; + + walk_stackframe(&frame, callchain_trace, entry); +} + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + return perf_guest_cbs->get_guest_ip(); + + return instruction_pointer(regs); +} + +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + int misc = 0; + + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (perf_guest_cbs->is_user_mode()) + misc |= PERF_RECORD_MISC_GUEST_USER; + else + misc |= PERF_RECORD_MISC_GUEST_KERNEL; + } else { + if (user_mode(regs)) + misc |= PERF_RECORD_MISC_USER; + else + misc |= PERF_RECORD_MISC_KERNEL; + } + + return misc; +} diff --git a/kernel/arch/arm64/kernel/perf_event.c b/kernel/arch/arm64/kernel/perf_event.c index fd26e57e7..62d3dc60c 100644 --- a/kernel/arch/arm64/kernel/perf_event.c +++ b/kernel/arch/arm64/kernel/perf_event.c @@ -18,644 +18,12 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see . */ -#define pr_fmt(fmt) "hw perfevents: " fmt -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include #include -#include -#include - -/* - * ARMv8 supports a maximum of 32 events. - * The cycle counter is included in this total. - */ -#define ARMPMU_MAX_HWEVENTS 32 - -static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events); -static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask); -static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events); - -#define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) - -/* Set at runtime when we know what CPU type we are. */ -static struct arm_pmu *cpu_pmu; - -int -armpmu_get_max_events(void) -{ - int max_events = 0; - - if (cpu_pmu != NULL) - max_events = cpu_pmu->num_events; - - return max_events; -} -EXPORT_SYMBOL_GPL(armpmu_get_max_events); - -int perf_num_counters(void) -{ - return armpmu_get_max_events(); -} -EXPORT_SYMBOL_GPL(perf_num_counters); - -#define HW_OP_UNSUPPORTED 0xFFFF - -#define C(_x) \ - PERF_COUNT_HW_CACHE_##_x - -#define CACHE_OP_UNSUPPORTED 0xFFFF - -static int -armpmu_map_cache_event(const unsigned (*cache_map) - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX], - u64 config) -{ - unsigned int cache_type, cache_op, cache_result, ret; - - cache_type = (config >> 0) & 0xff; - if (cache_type >= PERF_COUNT_HW_CACHE_MAX) - return -EINVAL; - - cache_op = (config >> 8) & 0xff; - if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) - return -EINVAL; - - cache_result = (config >> 16) & 0xff; - if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) - return -EINVAL; - - ret = (int)(*cache_map)[cache_type][cache_op][cache_result]; - - if (ret == CACHE_OP_UNSUPPORTED) - return -ENOENT; - - return ret; -} - -static int -armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) -{ - int mapping; - - if (config >= PERF_COUNT_HW_MAX) - return -EINVAL; - - mapping = (*event_map)[config]; - return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; -} - -static int -armpmu_map_raw_event(u32 raw_event_mask, u64 config) -{ - return (int)(config & raw_event_mask); -} - -static int map_cpu_event(struct perf_event *event, - const unsigned (*event_map)[PERF_COUNT_HW_MAX], - const unsigned (*cache_map) - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX], - u32 raw_event_mask) -{ - u64 config = event->attr.config; - - switch (event->attr.type) { - case PERF_TYPE_HARDWARE: - return armpmu_map_event(event_map, config); - case PERF_TYPE_HW_CACHE: - return armpmu_map_cache_event(cache_map, config); - case PERF_TYPE_RAW: - return armpmu_map_raw_event(raw_event_mask, config); - } - - return -ENOENT; -} - -int -armpmu_event_set_period(struct perf_event *event, - struct hw_perf_event *hwc, - int idx) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - s64 left = local64_read(&hwc->period_left); - s64 period = hwc->sample_period; - int ret = 0; - - if (unlikely(left <= -period)) { - left = period; - local64_set(&hwc->period_left, left); - hwc->last_period = period; - ret = 1; - } - - if (unlikely(left <= 0)) { - left += period; - local64_set(&hwc->period_left, left); - hwc->last_period = period; - ret = 1; - } - - /* - * Limit the maximum period to prevent the counter value - * from overtaking the one we are about to program. In - * effect we are reducing max_period to account for - * interrupt latency (and we are being very conservative). - */ - if (left > (armpmu->max_period >> 1)) - left = armpmu->max_period >> 1; - - local64_set(&hwc->prev_count, (u64)-left); - - armpmu->write_counter(idx, (u64)(-left) & 0xffffffff); - - perf_event_update_userpage(event); - - return ret; -} - -u64 -armpmu_event_update(struct perf_event *event, - struct hw_perf_event *hwc, - int idx) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - u64 delta, prev_raw_count, new_raw_count; - -again: - prev_raw_count = local64_read(&hwc->prev_count); - new_raw_count = armpmu->read_counter(idx); - - if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count) != prev_raw_count) - goto again; - - delta = (new_raw_count - prev_raw_count) & armpmu->max_period; - - local64_add(delta, &event->count); - local64_sub(delta, &hwc->period_left); - - return new_raw_count; -} - -static void -armpmu_read(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - - /* Don't read disabled counters! */ - if (hwc->idx < 0) - return; - - armpmu_event_update(event, hwc, hwc->idx); -} - -static void -armpmu_stop(struct perf_event *event, int flags) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct hw_perf_event *hwc = &event->hw; - - /* - * ARM pmu always has to update the counter, so ignore - * PERF_EF_UPDATE, see comments in armpmu_start(). - */ - if (!(hwc->state & PERF_HES_STOPPED)) { - armpmu->disable(hwc, hwc->idx); - barrier(); /* why? */ - armpmu_event_update(event, hwc, hwc->idx); - hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; - } -} - -static void -armpmu_start(struct perf_event *event, int flags) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct hw_perf_event *hwc = &event->hw; - - /* - * ARM pmu always has to reprogram the period, so ignore - * PERF_EF_RELOAD, see the comment below. - */ - if (flags & PERF_EF_RELOAD) - WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); - - hwc->state = 0; - /* - * Set the period again. Some counters can't be stopped, so when we - * were stopped we simply disabled the IRQ source and the counter - * may have been left counting. If we don't do this step then we may - * get an interrupt too soon or *way* too late if the overflow has - * happened since disabling. - */ - armpmu_event_set_period(event, hwc, hwc->idx); - armpmu->enable(hwc, hwc->idx); -} - -static void -armpmu_del(struct perf_event *event, int flags) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct pmu_hw_events *hw_events = armpmu->get_hw_events(); - struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - - WARN_ON(idx < 0); - - armpmu_stop(event, PERF_EF_UPDATE); - hw_events->events[idx] = NULL; - clear_bit(idx, hw_events->used_mask); - - perf_event_update_userpage(event); -} - -static int -armpmu_add(struct perf_event *event, int flags) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct pmu_hw_events *hw_events = armpmu->get_hw_events(); - struct hw_perf_event *hwc = &event->hw; - int idx; - int err = 0; - - perf_pmu_disable(event->pmu); - - /* If we don't have a space for the counter then finish early. */ - idx = armpmu->get_event_idx(hw_events, hwc); - if (idx < 0) { - err = idx; - goto out; - } - - /* - * If there is an event in the counter we are going to use then make - * sure it is disabled. - */ - event->hw.idx = idx; - armpmu->disable(hwc, idx); - hw_events->events[idx] = event; - - hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; - if (flags & PERF_EF_START) - armpmu_start(event, PERF_EF_RELOAD); - - /* Propagate our changes to the userspace mapping. */ - perf_event_update_userpage(event); - -out: - perf_pmu_enable(event->pmu); - return err; -} - -static int -validate_event(struct pmu *pmu, struct pmu_hw_events *hw_events, - struct perf_event *event) -{ - struct arm_pmu *armpmu; - struct hw_perf_event fake_event = event->hw; - struct pmu *leader_pmu = event->group_leader->pmu; - - if (is_software_event(event)) - return 1; - - /* - * Reject groups spanning multiple HW PMUs (e.g. CPU + CCI). The - * core perf code won't check that the pmu->ctx == leader->ctx - * until after pmu->event_init(event). - */ - if (event->pmu != pmu) - return 0; - - if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF) - return 1; - - if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec) - return 1; - - armpmu = to_arm_pmu(event->pmu); - return armpmu->get_event_idx(hw_events, &fake_event) >= 0; -} - -static int -validate_group(struct perf_event *event) -{ - struct perf_event *sibling, *leader = event->group_leader; - struct pmu_hw_events fake_pmu; - DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS); - - /* - * Initialise the fake PMU. We only need to populate the - * used_mask for the purposes of validation. - */ - memset(fake_used_mask, 0, sizeof(fake_used_mask)); - fake_pmu.used_mask = fake_used_mask; - - if (!validate_event(event->pmu, &fake_pmu, leader)) - return -EINVAL; - - list_for_each_entry(sibling, &leader->sibling_list, group_entry) { - if (!validate_event(event->pmu, &fake_pmu, sibling)) - return -EINVAL; - } - - if (!validate_event(event->pmu, &fake_pmu, event)) - return -EINVAL; - - return 0; -} - -static void -armpmu_disable_percpu_irq(void *data) -{ - unsigned int irq = *(unsigned int *)data; - disable_percpu_irq(irq); -} - -static void -armpmu_release_hardware(struct arm_pmu *armpmu) -{ - int irq; - unsigned int i, irqs; - struct platform_device *pmu_device = armpmu->plat_device; - - irqs = min(pmu_device->num_resources, num_possible_cpus()); - if (!irqs) - return; - - irq = platform_get_irq(pmu_device, 0); - if (irq <= 0) - return; - - if (irq_is_percpu(irq)) { - on_each_cpu(armpmu_disable_percpu_irq, &irq, 1); - free_percpu_irq(irq, &cpu_hw_events); - } else { - for (i = 0; i < irqs; ++i) { - int cpu = i; - - if (armpmu->irq_affinity) - cpu = armpmu->irq_affinity[i]; - - if (!cpumask_test_and_clear_cpu(cpu, &armpmu->active_irqs)) - continue; - irq = platform_get_irq(pmu_device, i); - if (irq > 0) - free_irq(irq, armpmu); - } - } -} - -static void -armpmu_enable_percpu_irq(void *data) -{ - unsigned int irq = *(unsigned int *)data; - enable_percpu_irq(irq, IRQ_TYPE_NONE); -} - -static int -armpmu_reserve_hardware(struct arm_pmu *armpmu) -{ - int err, irq; - unsigned int i, irqs; - struct platform_device *pmu_device = armpmu->plat_device; - - if (!pmu_device) { - pr_err("no PMU device registered\n"); - return -ENODEV; - } - - irqs = min(pmu_device->num_resources, num_possible_cpus()); - if (!irqs) { - pr_err("no irqs for PMUs defined\n"); - return -ENODEV; - } - - irq = platform_get_irq(pmu_device, 0); - if (irq <= 0) { - pr_err("failed to get valid irq for PMU device\n"); - return -ENODEV; - } - - if (irq_is_percpu(irq)) { - err = request_percpu_irq(irq, armpmu->handle_irq, - "arm-pmu", &cpu_hw_events); - - if (err) { - pr_err("unable to request percpu IRQ%d for ARM PMU counters\n", - irq); - armpmu_release_hardware(armpmu); - return err; - } - - on_each_cpu(armpmu_enable_percpu_irq, &irq, 1); - } else { - for (i = 0; i < irqs; ++i) { - int cpu = i; - - err = 0; - irq = platform_get_irq(pmu_device, i); - if (irq <= 0) - continue; - - if (armpmu->irq_affinity) - cpu = armpmu->irq_affinity[i]; - - /* - * If we have a single PMU interrupt that we can't shift, - * assume that we're running on a uniprocessor machine and - * continue. Otherwise, continue without this interrupt. - */ - if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) { - pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n", - irq, cpu); - continue; - } - - err = request_irq(irq, armpmu->handle_irq, - IRQF_NOBALANCING | IRQF_NO_THREAD, - "arm-pmu", armpmu); - if (err) { - pr_err("unable to request IRQ%d for ARM PMU counters\n", - irq); - armpmu_release_hardware(armpmu); - return err; - } - - cpumask_set_cpu(cpu, &armpmu->active_irqs); - } - } - - return 0; -} - -static void -hw_perf_event_destroy(struct perf_event *event) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - atomic_t *active_events = &armpmu->active_events; - struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex; - - if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) { - armpmu_release_hardware(armpmu); - mutex_unlock(pmu_reserve_mutex); - } -} - -static int -event_requires_mode_exclusion(struct perf_event_attr *attr) -{ - return attr->exclude_idle || attr->exclude_user || - attr->exclude_kernel || attr->exclude_hv; -} - -static int -__hw_perf_event_init(struct perf_event *event) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - struct hw_perf_event *hwc = &event->hw; - int mapping, err; - - mapping = armpmu->map_event(event); - - if (mapping < 0) { - pr_debug("event %x:%llx not supported\n", event->attr.type, - event->attr.config); - return mapping; - } - - /* - * We don't assign an index until we actually place the event onto - * hardware. Use -1 to signify that we haven't decided where to put it - * yet. For SMP systems, each core has it's own PMU so we can't do any - * clever allocation or constraints checking at this point. - */ - hwc->idx = -1; - hwc->config_base = 0; - hwc->config = 0; - hwc->event_base = 0; - - /* - * Check whether we need to exclude the counter from certain modes. - */ - if ((!armpmu->set_event_filter || - armpmu->set_event_filter(hwc, &event->attr)) && - event_requires_mode_exclusion(&event->attr)) { - pr_debug("ARM performance counters do not support mode exclusion\n"); - return -EPERM; - } - - /* - * Store the event encoding into the config_base field. - */ - hwc->config_base |= (unsigned long)mapping; - - if (!hwc->sample_period) { - /* - * For non-sampling runs, limit the sample_period to half - * of the counter width. That way, the new counter value - * is far less likely to overtake the previous one unless - * you have some serious IRQ latency issues. - */ - hwc->sample_period = armpmu->max_period >> 1; - hwc->last_period = hwc->sample_period; - local64_set(&hwc->period_left, hwc->sample_period); - } - - err = 0; - if (event->group_leader != event) { - err = validate_group(event); - if (err) - return -EINVAL; - } - - return err; -} - -static int armpmu_event_init(struct perf_event *event) -{ - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - int err = 0; - atomic_t *active_events = &armpmu->active_events; - - if (armpmu->map_event(event) == -ENOENT) - return -ENOENT; - event->destroy = hw_perf_event_destroy; - - if (!atomic_inc_not_zero(active_events)) { - mutex_lock(&armpmu->reserve_mutex); - if (atomic_read(active_events) == 0) - err = armpmu_reserve_hardware(armpmu); - - if (!err) - atomic_inc(active_events); - mutex_unlock(&armpmu->reserve_mutex); - } - - if (err) - return err; - - err = __hw_perf_event_init(event); - if (err) - hw_perf_event_destroy(event); - - return err; -} - -static void armpmu_enable(struct pmu *pmu) -{ - struct arm_pmu *armpmu = to_arm_pmu(pmu); - struct pmu_hw_events *hw_events = armpmu->get_hw_events(); - int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events); - - if (enabled) - armpmu->start(); -} - -static void armpmu_disable(struct pmu *pmu) -{ - struct arm_pmu *armpmu = to_arm_pmu(pmu); - armpmu->stop(); -} - -static void __init armpmu_init(struct arm_pmu *armpmu) -{ - atomic_set(&armpmu->active_events, 0); - mutex_init(&armpmu->reserve_mutex); - - armpmu->pmu = (struct pmu) { - .pmu_enable = armpmu_enable, - .pmu_disable = armpmu_disable, - .event_init = armpmu_event_init, - .add = armpmu_add, - .del = armpmu_del, - .start = armpmu_start, - .stop = armpmu_stop, - .read = armpmu_read, - }; -} - -int __init armpmu_register(struct arm_pmu *armpmu, char *name, int type) -{ - armpmu_init(armpmu); - return perf_pmu_register(&armpmu->pmu, name, type); -} +#include +#include +#include /* * ARMv8 PMUv3 Performance Events handling code. @@ -701,128 +69,123 @@ enum armv8_pmuv3_perf_types { ARMV8_PMUV3_PERFCTR_BUS_CYCLES = 0x1D, }; +/* ARMv8 Cortex-A53 specific event types. */ +enum armv8_a53_pmu_perf_types { + ARMV8_A53_PERFCTR_PREFETCH_LINEFILL = 0xC2, +}; + +/* ARMv8 Cortex-A57 specific event types. */ +enum armv8_a57_perf_types { + ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD = 0x40, + ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST = 0x41, + ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD = 0x42, + ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST = 0x43, + ARMV8_A57_PERFCTR_DTLB_REFILL_LD = 0x4c, + ARMV8_A57_PERFCTR_DTLB_REFILL_ST = 0x4d, +}; + /* PMUv3 HW events mapping. */ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* ARM Cortex-A53 HW events mapping. */ +static const unsigned armv8_a53_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, +}; + +static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES, [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED, [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED, [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, - [PERF_COUNT_HW_BUS_CYCLES] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = HW_OP_UNSUPPORTED, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = HW_OP_UNSUPPORTED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, }; static const unsigned armv8_pmuv3_perf_cache_map[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)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, - [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(L1I)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(LL)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(DTLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(ITLB)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(BPU)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, - [C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, - [C(NODE)] = { - [C(OP_READ)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_WRITE)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - [C(OP_PREFETCH)] = { - [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED, - [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED, - }, - }, + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREFETCH_LINEFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_DTLB_REFILL_LD, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_A57_PERFCTR_DTLB_REFILL_ST, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, }; + /* * Perf Events' indices */ #define ARMV8_IDX_CYCLE_COUNTER 0 #define ARMV8_IDX_COUNTER0 1 -#define ARMV8_IDX_COUNTER_LAST (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) +#define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \ + (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) #define ARMV8_MAX_COUNTERS 32 #define ARMV8_COUNTER_MASK (ARMV8_MAX_COUNTERS - 1) @@ -888,49 +251,34 @@ static inline int armv8pmu_has_overflowed(u32 pmovsr) return pmovsr & ARMV8_OVERFLOWED_MASK; } -static inline int armv8pmu_counter_valid(int idx) +static inline int armv8pmu_counter_valid(struct arm_pmu *cpu_pmu, int idx) { - return idx >= ARMV8_IDX_CYCLE_COUNTER && idx <= ARMV8_IDX_COUNTER_LAST; + return idx >= ARMV8_IDX_CYCLE_COUNTER && + idx <= ARMV8_IDX_COUNTER_LAST(cpu_pmu); } static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx) { - int ret = 0; - u32 counter; - - if (!armv8pmu_counter_valid(idx)) { - pr_err("CPU%u checking wrong counter %d overflow status\n", - smp_processor_id(), idx); - } else { - counter = ARMV8_IDX_TO_COUNTER(idx); - ret = pmnc & BIT(counter); - } - - return ret; + return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx)); } static inline int armv8pmu_select_counter(int idx) { - u32 counter; - - if (!armv8pmu_counter_valid(idx)) { - pr_err("CPU%u selecting wrong PMNC counter %d\n", - smp_processor_id(), idx); - return -EINVAL; - } - - counter = ARMV8_IDX_TO_COUNTER(idx); + u32 counter = ARMV8_IDX_TO_COUNTER(idx); asm volatile("msr pmselr_el0, %0" :: "r" (counter)); isb(); return idx; } -static inline u32 armv8pmu_read_counter(int idx) +static inline u32 armv8pmu_read_counter(struct perf_event *event) { + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; u32 value = 0; - if (!armv8pmu_counter_valid(idx)) + if (!armv8pmu_counter_valid(cpu_pmu, idx)) pr_err("CPU%u reading wrong counter %d\n", smp_processor_id(), idx); else if (idx == ARMV8_IDX_CYCLE_COUNTER) @@ -941,9 +289,13 @@ static inline u32 armv8pmu_read_counter(int idx) return value; } -static inline void armv8pmu_write_counter(int idx, u32 value) +static inline void armv8pmu_write_counter(struct perf_event *event, u32 value) { - if (!armv8pmu_counter_valid(idx)) + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (!armv8pmu_counter_valid(cpu_pmu, idx)) pr_err("CPU%u writing wrong counter %d\n", smp_processor_id(), idx); else if (idx == ARMV8_IDX_CYCLE_COUNTER) @@ -962,65 +314,34 @@ static inline void armv8pmu_write_evtype(int idx, u32 val) static inline int armv8pmu_enable_counter(int idx) { - u32 counter; - - if (!armv8pmu_counter_valid(idx)) { - pr_err("CPU%u enabling wrong PMNC counter %d\n", - smp_processor_id(), idx); - return -EINVAL; - } - - counter = ARMV8_IDX_TO_COUNTER(idx); + u32 counter = ARMV8_IDX_TO_COUNTER(idx); asm volatile("msr pmcntenset_el0, %0" :: "r" (BIT(counter))); return idx; } static inline int armv8pmu_disable_counter(int idx) { - u32 counter; - - if (!armv8pmu_counter_valid(idx)) { - pr_err("CPU%u disabling wrong PMNC counter %d\n", - smp_processor_id(), idx); - return -EINVAL; - } - - counter = ARMV8_IDX_TO_COUNTER(idx); + u32 counter = ARMV8_IDX_TO_COUNTER(idx); asm volatile("msr pmcntenclr_el0, %0" :: "r" (BIT(counter))); return idx; } static inline int armv8pmu_enable_intens(int idx) { - u32 counter; - - if (!armv8pmu_counter_valid(idx)) { - pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n", - smp_processor_id(), idx); - return -EINVAL; - } - - counter = ARMV8_IDX_TO_COUNTER(idx); + u32 counter = ARMV8_IDX_TO_COUNTER(idx); asm volatile("msr pmintenset_el1, %0" :: "r" (BIT(counter))); return idx; } static inline int armv8pmu_disable_intens(int idx) { - u32 counter; - - if (!armv8pmu_counter_valid(idx)) { - pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n", - smp_processor_id(), idx); - return -EINVAL; - } - - counter = ARMV8_IDX_TO_COUNTER(idx); + u32 counter = ARMV8_IDX_TO_COUNTER(idx); asm volatile("msr pmintenclr_el1, %0" :: "r" (BIT(counter))); isb(); /* Clear the overflow flag in case an interrupt is pending. */ asm volatile("msr pmovsclr_el0, %0" :: "r" (BIT(counter))); isb(); + return idx; } @@ -1038,10 +359,13 @@ static inline u32 armv8pmu_getreset_flags(void) return value; } -static void armv8pmu_enable_event(struct hw_perf_event *hwc, int idx) +static void armv8pmu_enable_event(struct perf_event *event) { unsigned long flags; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct hw_perf_event *hwc = &event->hw; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; /* * Enable counter and interrupt, and set the counter to count @@ -1072,10 +396,13 @@ static void armv8pmu_enable_event(struct hw_perf_event *hwc, int idx) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static void armv8pmu_disable_event(struct hw_perf_event *hwc, int idx) +static void armv8pmu_disable_event(struct perf_event *event) { unsigned long flags; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct hw_perf_event *hwc = &event->hw; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; /* * Disable counter and interrupt @@ -1099,7 +426,8 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) { u32 pmovsr; struct perf_sample_data data; - struct pmu_hw_events *cpuc; + struct arm_pmu *cpu_pmu = (struct arm_pmu *)dev; + struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); struct pt_regs *regs; int idx; @@ -1119,7 +447,6 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) */ regs = get_irq_regs(); - cpuc = this_cpu_ptr(&cpu_hw_events); for (idx = 0; idx < cpu_pmu->num_events; ++idx) { struct perf_event *event = cpuc->events[idx]; struct hw_perf_event *hwc; @@ -1136,13 +463,13 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) continue; hwc = &event->hw; - armpmu_event_update(event, hwc, idx); + armpmu_event_update(event); perf_sample_data_init(&data, 0, hwc->last_period); - if (!armpmu_event_set_period(event, hwc, idx)) + if (!armpmu_event_set_period(event)) continue; if (perf_event_overflow(event, &data, regs)) - cpu_pmu->disable(hwc, idx); + cpu_pmu->disable(event); } /* @@ -1157,10 +484,10 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev) return IRQ_HANDLED; } -static void armv8pmu_start(void) +static void armv8pmu_start(struct arm_pmu *cpu_pmu) { unsigned long flags; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Enable all counters */ @@ -1168,10 +495,10 @@ static void armv8pmu_start(void) raw_spin_unlock_irqrestore(&events->pmu_lock, flags); } -static void armv8pmu_stop(void) +static void armv8pmu_stop(struct arm_pmu *cpu_pmu) { unsigned long flags; - struct pmu_hw_events *events = cpu_pmu->get_hw_events(); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); raw_spin_lock_irqsave(&events->pmu_lock, flags); /* Disable all counters */ @@ -1180,10 +507,12 @@ static void armv8pmu_stop(void) } static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, - struct hw_perf_event *event) + struct perf_event *event) { int idx; - unsigned long evtype = event->config_base & ARMV8_EVTYPE_EVENT; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long evtype = hwc->config_base & ARMV8_EVTYPE_EVENT; /* Always place a cycle counter into the cycle counter. */ if (evtype == ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES) { @@ -1234,360 +563,119 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event, static void armv8pmu_reset(void *info) { + struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; u32 idx, nb_cnt = cpu_pmu->num_events; /* The counter and interrupt enable registers are unknown at reset. */ - for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) - armv8pmu_disable_event(NULL, idx); + for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + armv8pmu_disable_counter(idx); + armv8pmu_disable_intens(idx); + } /* Initialize & Reset PMNC: C and P bits. */ armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); - - /* Disable access from userspace. */ - asm volatile("msr pmuserenr_el0, %0" :: "r" (0)); } static int armv8_pmuv3_map_event(struct perf_event *event) { - return map_cpu_event(event, &armv8_pmuv3_perf_map, + return armpmu_map_event(event, &armv8_pmuv3_perf_map, &armv8_pmuv3_perf_cache_map, ARMV8_EVTYPE_EVENT); } -static struct arm_pmu armv8pmu = { - .handle_irq = armv8pmu_handle_irq, - .enable = armv8pmu_enable_event, - .disable = armv8pmu_disable_event, - .read_counter = armv8pmu_read_counter, - .write_counter = armv8pmu_write_counter, - .get_event_idx = armv8pmu_get_event_idx, - .start = armv8pmu_start, - .stop = armv8pmu_stop, - .reset = armv8pmu_reset, - .max_period = (1LLU << 32) - 1, -}; - -static u32 __init armv8pmu_read_num_pmnc_events(void) -{ - u32 nb_cnt; - - /* Read the nb of CNTx counters supported from PMNC */ - nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK; - - /* Add the CPU cycles counter and return */ - return nb_cnt + 1; -} - -static struct arm_pmu *__init armv8_pmuv3_pmu_init(void) +static int armv8_a53_map_event(struct perf_event *event) { - armv8pmu.name = "arm/armv8-pmuv3"; - armv8pmu.map_event = armv8_pmuv3_map_event; - armv8pmu.num_events = armv8pmu_read_num_pmnc_events(); - armv8pmu.set_event_filter = armv8pmu_set_event_filter; - return &armv8pmu; + return armpmu_map_event(event, &armv8_a53_perf_map, + &armv8_a53_perf_cache_map, + ARMV8_EVTYPE_EVENT); } -/* - * Ensure the PMU has sane values out of reset. - * This requires SMP to be available, so exists as a separate initcall. - */ -static int __init -cpu_pmu_reset(void) +static int armv8_a57_map_event(struct perf_event *event) { - if (cpu_pmu && cpu_pmu->reset) - return on_each_cpu(cpu_pmu->reset, NULL, 1); - return 0; + return armpmu_map_event(event, &armv8_a57_perf_map, + &armv8_a57_perf_cache_map, + ARMV8_EVTYPE_EVENT); } -arch_initcall(cpu_pmu_reset); -/* - * PMU platform driver and devicetree bindings. - */ -static const struct of_device_id armpmu_of_device_ids[] = { - {.compatible = "arm,armv8-pmuv3"}, - {}, -}; - -static int armpmu_device_probe(struct platform_device *pdev) +static void armv8pmu_read_num_pmnc_events(void *info) { - int i, irq, *irqs; - - if (!cpu_pmu) - return -ENODEV; - - /* Don't bother with PPIs; they're already affine */ - irq = platform_get_irq(pdev, 0); - if (irq >= 0 && irq_is_percpu(irq)) - goto out; - - irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); - if (!irqs) - return -ENOMEM; - - for (i = 0; i < pdev->num_resources; ++i) { - struct device_node *dn; - int cpu; - - dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity", - i); - if (!dn) { - pr_warn("Failed to parse %s/interrupt-affinity[%d]\n", - of_node_full_name(pdev->dev.of_node), i); - break; - } - - for_each_possible_cpu(cpu) - if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL)) - break; - - of_node_put(dn); - if (cpu >= nr_cpu_ids) { - pr_warn("Failed to find logical CPU for %s\n", - dn->name); - break; - } - - irqs[i] = cpu; - } + int *nb_cnt = info; - if (i == pdev->num_resources) - cpu_pmu->irq_affinity = irqs; - else - kfree(irqs); - -out: - cpu_pmu->plat_device = pdev; - return 0; -} - -static struct platform_driver armpmu_driver = { - .driver = { - .name = "arm-pmu", - .of_match_table = armpmu_of_device_ids, - }, - .probe = armpmu_device_probe, -}; + /* Read the nb of CNTx counters supported from PMNC */ + *nb_cnt = (armv8pmu_pmcr_read() >> ARMV8_PMCR_N_SHIFT) & ARMV8_PMCR_N_MASK; -static int __init register_pmu_driver(void) -{ - return platform_driver_register(&armpmu_driver); + /* Add the CPU cycles counter */ + *nb_cnt += 1; } -device_initcall(register_pmu_driver); -static struct pmu_hw_events *armpmu_get_cpu_events(void) +static int armv8pmu_probe_num_events(struct arm_pmu *arm_pmu) { - return this_cpu_ptr(&cpu_hw_events); + return smp_call_function_any(&arm_pmu->supported_cpus, + armv8pmu_read_num_pmnc_events, + &arm_pmu->num_events, 1); } -static void __init cpu_pmu_init(struct arm_pmu *armpmu) +static void armv8_pmu_init(struct arm_pmu *cpu_pmu) { - int cpu; - for_each_possible_cpu(cpu) { - struct pmu_hw_events *events = &per_cpu(cpu_hw_events, cpu); - events->events = per_cpu(hw_events, cpu); - events->used_mask = per_cpu(used_mask, cpu); - raw_spin_lock_init(&events->pmu_lock); - } - armpmu->get_hw_events = armpmu_get_cpu_events; + cpu_pmu->handle_irq = armv8pmu_handle_irq, + cpu_pmu->enable = armv8pmu_enable_event, + cpu_pmu->disable = armv8pmu_disable_event, + cpu_pmu->read_counter = armv8pmu_read_counter, + cpu_pmu->write_counter = armv8pmu_write_counter, + cpu_pmu->get_event_idx = armv8pmu_get_event_idx, + cpu_pmu->start = armv8pmu_start, + cpu_pmu->stop = armv8pmu_stop, + cpu_pmu->reset = armv8pmu_reset, + cpu_pmu->max_period = (1LLU << 32) - 1, + cpu_pmu->set_event_filter = armv8pmu_set_event_filter; } -static int __init init_hw_perf_events(void) -{ - u64 dfr = read_cpuid(ID_AA64DFR0_EL1); - - switch ((dfr >> 8) & 0xf) { - case 0x1: /* PMUv3 */ - cpu_pmu = armv8_pmuv3_pmu_init(); - break; - } - - if (cpu_pmu) { - pr_info("enabled with %s PMU driver, %d counters available\n", - cpu_pmu->name, cpu_pmu->num_events); - cpu_pmu_init(cpu_pmu); - armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW); - } else { - pr_info("no hardware support available\n"); - } - - return 0; -} -early_initcall(init_hw_perf_events); - -/* - * Callchain handling code. - */ -struct frame_tail { - struct frame_tail __user *fp; - unsigned long lr; -} __attribute__((packed)); - -/* - * Get the return address for a single stackframe and return a pointer to the - * next frame tail. - */ -static struct frame_tail __user * -user_backtrace(struct frame_tail __user *tail, - struct perf_callchain_entry *entry) +static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu) { - struct frame_tail buftail; - unsigned long err; - - /* Also check accessibility of one struct frame_tail beyond */ - if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) - return NULL; - - pagefault_disable(); - err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); - pagefault_enable(); - - if (err) - return NULL; - - perf_callchain_store(entry, buftail.lr); - - /* - * Frame pointers should strictly progress back up the stack - * (towards higher addresses). - */ - if (tail >= buftail.fp) - return NULL; - - return buftail.fp; + armv8_pmu_init(cpu_pmu); + cpu_pmu->name = "armv8_pmuv3"; + cpu_pmu->map_event = armv8_pmuv3_map_event; + return armv8pmu_probe_num_events(cpu_pmu); } -#ifdef CONFIG_COMPAT -/* - * The registers we're interested in are at the end of the variable - * length saved register structure. The fp points at the end of this - * structure so the address of this struct is: - * (struct compat_frame_tail *)(xxx->fp)-1 - * - * This code has been adapted from the ARM OProfile support. - */ -struct compat_frame_tail { - compat_uptr_t fp; /* a (struct compat_frame_tail *) in compat mode */ - u32 sp; - u32 lr; -} __attribute__((packed)); - -static struct compat_frame_tail __user * -compat_user_backtrace(struct compat_frame_tail __user *tail, - struct perf_callchain_entry *entry) +static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) { - struct compat_frame_tail buftail; - unsigned long err; - - /* Also check accessibility of one struct frame_tail beyond */ - if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) - return NULL; - - pagefault_disable(); - err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); - pagefault_enable(); - - if (err) - return NULL; - - perf_callchain_store(entry, buftail.lr); - - /* - * Frame pointers should strictly progress back up the stack - * (towards higher addresses). - */ - if (tail + 1 >= (struct compat_frame_tail __user *) - compat_ptr(buftail.fp)) - return NULL; - - return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1; + armv8_pmu_init(cpu_pmu); + cpu_pmu->name = "armv8_cortex_a53"; + cpu_pmu->map_event = armv8_a53_map_event; + return armv8pmu_probe_num_events(cpu_pmu); } -#endif /* CONFIG_COMPAT */ -void perf_callchain_user(struct perf_callchain_entry *entry, - struct pt_regs *regs) +static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) { - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - /* We don't support guest os callchain now */ - return; - } - - perf_callchain_store(entry, regs->pc); - - if (!compat_user_mode(regs)) { - /* AARCH64 mode */ - struct frame_tail __user *tail; - - tail = (struct frame_tail __user *)regs->regs[29]; - - while (entry->nr < PERF_MAX_STACK_DEPTH && - tail && !((unsigned long)tail & 0xf)) - tail = user_backtrace(tail, entry); - } else { -#ifdef CONFIG_COMPAT - /* AARCH32 compat mode */ - struct compat_frame_tail __user *tail; - - tail = (struct compat_frame_tail __user *)regs->compat_fp - 1; - - while ((entry->nr < PERF_MAX_STACK_DEPTH) && - tail && !((unsigned long)tail & 0x3)) - tail = compat_user_backtrace(tail, entry); -#endif - } + armv8_pmu_init(cpu_pmu); + cpu_pmu->name = "armv8_cortex_a57"; + cpu_pmu->map_event = armv8_a57_map_event; + return armv8pmu_probe_num_events(cpu_pmu); } -/* - * Gets called by walk_stackframe() for every stackframe. This will be called - * whist unwinding the stackframe and is like a subroutine return so we use - * the PC. - */ -static int callchain_trace(struct stackframe *frame, void *data) -{ - struct perf_callchain_entry *entry = data; - perf_callchain_store(entry, frame->pc); - return 0; -} +static const struct of_device_id armv8_pmu_of_device_ids[] = { + {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init}, + {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init}, + {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init}, + {}, +}; -void perf_callchain_kernel(struct perf_callchain_entry *entry, - struct pt_regs *regs) +static int armv8_pmu_device_probe(struct platform_device *pdev) { - struct stackframe frame; - - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - /* We don't support guest os callchain now */ - return; - } - - frame.fp = regs->regs[29]; - frame.sp = regs->sp; - frame.pc = regs->pc; - - walk_stackframe(&frame, callchain_trace, entry); + return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL); } -unsigned long perf_instruction_pointer(struct pt_regs *regs) -{ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - return perf_guest_cbs->get_guest_ip(); - - return instruction_pointer(regs); -} +static struct platform_driver armv8_pmu_driver = { + .driver = { + .name = "armv8-pmu", + .of_match_table = armv8_pmu_of_device_ids, + }, + .probe = armv8_pmu_device_probe, +}; -unsigned long perf_misc_flags(struct pt_regs *regs) +static int __init register_armv8_pmu_driver(void) { - int misc = 0; - - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - if (perf_guest_cbs->is_user_mode()) - misc |= PERF_RECORD_MISC_GUEST_USER; - else - misc |= PERF_RECORD_MISC_GUEST_KERNEL; - } else { - if (user_mode(regs)) - misc |= PERF_RECORD_MISC_USER; - else - misc |= PERF_RECORD_MISC_KERNEL; - } - - return misc; + return platform_driver_register(&armv8_pmu_driver); } +device_initcall(register_armv8_pmu_driver); diff --git a/kernel/arch/arm64/kernel/process.c b/kernel/arch/arm64/kernel/process.c index c6b1f3b96..f75b540bc 100644 --- a/kernel/arch/arm64/kernel/process.c +++ b/kernel/arch/arm64/kernel/process.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -58,14 +59,6 @@ unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); #endif -void soft_restart(unsigned long addr) -{ - setup_mm_for_reboot(); - cpu_soft_restart(virt_to_phys(cpu_reset), addr); - /* Should never get here */ - BUG(); -} - /* * Function pointers to optional machine specific functions */ @@ -83,8 +76,10 @@ void arch_cpu_idle(void) * This should do all the clock switching and wait for interrupt * tricks */ + trace_cpu_idle_rcuidle(1, smp_processor_id()); cpu_do_idle(); local_irq_enable(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_HOTPLUG_CPU @@ -136,9 +131,7 @@ void machine_power_off(void) /* * Restart requires that the secondary CPUs stop performing any activity - * while the primary CPU resets the system. Systems with a single CPU can - * use soft_restart() as their machine descriptor's .restart hook, since that - * will cause the only available CPU to reset. Systems with multiple CPUs must + * while the primary CPU resets the system. Systems with multiple CPUs must * provide a HW restart implementation, to ensure that all CPUs reset at once. * This is required so that any code running after reset on the primary CPU * doesn't have to co-ordinate with other CPUs to ensure they aren't still @@ -243,7 +236,8 @@ void release_thread(struct task_struct *dead_task) int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - fpsimd_preserve_current_state(); + if (current->mm) + fpsimd_preserve_current_state(); *dst = *src; return 0; } @@ -254,35 +248,35 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, unsigned long stk_sz, struct task_struct *p) { struct pt_regs *childregs = task_pt_regs(p); - unsigned long tls = p->thread.tp_value; memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context)); if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; - if (is_compat_thread(task_thread_info(p))) { - if (stack_start) + + /* + * Read the current TLS pointer from tpidr_el0 as it may be + * out-of-sync with the saved value. + */ + asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p))); + + if (stack_start) { + if (is_compat_thread(task_thread_info(p))) childregs->compat_sp = stack_start; - } else { - /* - * Read the current TLS pointer from tpidr_el0 as it may be - * out-of-sync with the saved value. - */ - asm("mrs %0, tpidr_el0" : "=r" (tls)); - if (stack_start) { - /* 16-byte aligned stack mandatory on AArch64 */ - if (stack_start & 15) - return -EINVAL; + /* 16-byte aligned stack mandatory on AArch64 */ + else if (stack_start & 15) + return -EINVAL; + else childregs->sp = stack_start; - } } + /* * If a TLS pointer was passed to clone (4th argument), use it * for the new thread. */ if (clone_flags & CLONE_SETTLS) - tls = childregs->regs[3]; + p->thread.tp_value = childregs->regs[3]; } else { memset(childregs, 0, sizeof(struct pt_regs)); childregs->pstate = PSR_MODE_EL1h; @@ -291,7 +285,6 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, } p->thread.cpu_context.pc = (unsigned long)ret_from_fork; p->thread.cpu_context.sp = (unsigned long)childregs; - p->thread.tp_value = tls; ptrace_hw_copy_thread(p); @@ -302,18 +295,12 @@ static void tls_thread_switch(struct task_struct *next) { unsigned long tpidr, tpidrro; - if (!is_compat_task()) { - asm("mrs %0, tpidr_el0" : "=r" (tpidr)); - current->thread.tp_value = tpidr; - } + asm("mrs %0, tpidr_el0" : "=r" (tpidr)); + *task_user_tls(current) = tpidr; - if (is_compat_thread(task_thread_info(next))) { - tpidr = 0; - tpidrro = next->thread.tp_value; - } else { - tpidr = next->thread.tp_value; - tpidrro = 0; - } + tpidr = *task_user_tls(next); + tpidrro = is_compat_thread(task_thread_info(next)) ? + next->thread.tp_value : 0; asm( " msr tpidr_el0, %0\n" diff --git a/kernel/arch/arm64/kernel/psci.c b/kernel/arch/arm64/kernel/psci.c index ea18cb539..f67f35b6e 100644 --- a/kernel/arch/arm64/kernel/psci.c +++ b/kernel/arch/arm64/kernel/psci.c @@ -15,183 +15,32 @@ #define pr_fmt(fmt) "psci: " fmt -#include #include #include #include -#include -#include #include +#include #include + #include -#include #include #include #include -#include #include #include -#include - -#define PSCI_POWER_STATE_TYPE_STANDBY 0 -#define PSCI_POWER_STATE_TYPE_POWER_DOWN 1 - -struct psci_power_state { - u16 id; - u8 type; - u8 affinity_level; -}; - -struct psci_operations { - int (*cpu_suspend)(struct psci_power_state state, - unsigned long entry_point); - int (*cpu_off)(struct psci_power_state state); - int (*cpu_on)(unsigned long cpuid, unsigned long entry_point); - int (*migrate)(unsigned long cpuid); - int (*affinity_info)(unsigned long target_affinity, - unsigned long lowest_affinity_level); - int (*migrate_info_type)(void); -}; - -static struct psci_operations psci_ops; - -static int (*invoke_psci_fn)(u64, u64, u64, u64); -typedef int (*psci_initcall_t)(const struct device_node *); - -asmlinkage int __invoke_psci_fn_hvc(u64, u64, u64, u64); -asmlinkage int __invoke_psci_fn_smc(u64, u64, u64, u64); - -enum psci_function { - PSCI_FN_CPU_SUSPEND, - PSCI_FN_CPU_ON, - PSCI_FN_CPU_OFF, - PSCI_FN_MIGRATE, - PSCI_FN_AFFINITY_INFO, - PSCI_FN_MIGRATE_INFO_TYPE, - PSCI_FN_MAX, -}; - -static DEFINE_PER_CPU_READ_MOSTLY(struct psci_power_state *, psci_power_state); - -static u32 psci_function_id[PSCI_FN_MAX]; - -static int psci_to_linux_errno(int errno) -{ - switch (errno) { - case PSCI_RET_SUCCESS: - return 0; - case PSCI_RET_NOT_SUPPORTED: - return -EOPNOTSUPP; - case PSCI_RET_INVALID_PARAMS: - return -EINVAL; - case PSCI_RET_DENIED: - return -EPERM; - }; - - return -EINVAL; -} - -static u32 psci_power_state_pack(struct psci_power_state state) -{ - return ((state.id << PSCI_0_2_POWER_STATE_ID_SHIFT) - & PSCI_0_2_POWER_STATE_ID_MASK) | - ((state.type << PSCI_0_2_POWER_STATE_TYPE_SHIFT) - & PSCI_0_2_POWER_STATE_TYPE_MASK) | - ((state.affinity_level << PSCI_0_2_POWER_STATE_AFFL_SHIFT) - & PSCI_0_2_POWER_STATE_AFFL_MASK); -} - -static void psci_power_state_unpack(u32 power_state, - struct psci_power_state *state) -{ - state->id = (power_state & PSCI_0_2_POWER_STATE_ID_MASK) >> - PSCI_0_2_POWER_STATE_ID_SHIFT; - state->type = (power_state & PSCI_0_2_POWER_STATE_TYPE_MASK) >> - PSCI_0_2_POWER_STATE_TYPE_SHIFT; - state->affinity_level = - (power_state & PSCI_0_2_POWER_STATE_AFFL_MASK) >> - PSCI_0_2_POWER_STATE_AFFL_SHIFT; -} - -static int psci_get_version(void) -{ - int err; - - err = invoke_psci_fn(PSCI_0_2_FN_PSCI_VERSION, 0, 0, 0); - return err; -} - -static int psci_cpu_suspend(struct psci_power_state state, - unsigned long entry_point) -{ - int err; - u32 fn, power_state; - - fn = psci_function_id[PSCI_FN_CPU_SUSPEND]; - power_state = psci_power_state_pack(state); - err = invoke_psci_fn(fn, power_state, entry_point, 0); - return psci_to_linux_errno(err); -} -static int psci_cpu_off(struct psci_power_state state) -{ - int err; - u32 fn, power_state; +static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state); - fn = psci_function_id[PSCI_FN_CPU_OFF]; - power_state = psci_power_state_pack(state); - err = invoke_psci_fn(fn, power_state, 0, 0); - return psci_to_linux_errno(err); -} - -static int psci_cpu_on(unsigned long cpuid, unsigned long entry_point) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_CPU_ON]; - err = invoke_psci_fn(fn, cpuid, entry_point, 0); - return psci_to_linux_errno(err); -} - -static int psci_migrate(unsigned long cpuid) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_MIGRATE]; - err = invoke_psci_fn(fn, cpuid, 0, 0); - return psci_to_linux_errno(err); -} - -static int psci_affinity_info(unsigned long target_affinity, - unsigned long lowest_affinity_level) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_AFFINITY_INFO]; - err = invoke_psci_fn(fn, target_affinity, lowest_affinity_level, 0); - return err; -} - -static int psci_migrate_info_type(void) -{ - int err; - u32 fn; - - fn = psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE]; - err = invoke_psci_fn(fn, 0, 0, 0); - return err; -} - -static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, - unsigned int cpu) +static int __maybe_unused cpu_psci_cpu_init_idle(unsigned int cpu) { int i, ret, count = 0; - struct psci_power_state *psci_states; - struct device_node *state_node; + u32 *psci_states; + struct device_node *state_node, *cpu_node; + + cpu_node = of_get_cpu_node(cpu, NULL); + if (!cpu_node) + return -ENODEV; /* * If the PSCI cpu_suspend function hook has not been initialized @@ -215,13 +64,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, return -ENOMEM; for (i = 0; i < count; i++) { - u32 psci_power_state; + u32 state; state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i); ret = of_property_read_u32(state_node, "arm,psci-suspend-param", - &psci_power_state); + &state); if (ret) { pr_warn(" * %s missing arm,psci-suspend-param property\n", state_node->full_name); @@ -230,9 +79,13 @@ static int __maybe_unused cpu_psci_cpu_init_idle(struct device_node *cpu_node, } of_node_put(state_node); - pr_debug("psci-power-state %#x index %d\n", psci_power_state, - i); - psci_power_state_unpack(psci_power_state, &psci_states[i]); + pr_debug("psci-power-state %#x index %d\n", state, i); + if (!psci_power_state_is_valid(state)) { + pr_warn("Invalid PSCI power state %#x\n", state); + ret = -EINVAL; + goto free_mem; + } + psci_states[i] = state; } /* Idle states parsed correctly, initialize per-cpu pointer */ per_cpu(psci_power_state, cpu) = psci_states; @@ -243,208 +96,7 @@ free_mem: return ret; } -static int get_set_conduit_method(struct device_node *np) -{ - const char *method; - - pr_info("probing for conduit method from DT.\n"); - - if (of_property_read_string(np, "method", &method)) { - pr_warn("missing \"method\" property\n"); - return -ENXIO; - } - - if (!strcmp("hvc", method)) { - invoke_psci_fn = __invoke_psci_fn_hvc; - } else if (!strcmp("smc", method)) { - invoke_psci_fn = __invoke_psci_fn_smc; - } else { - pr_warn("invalid \"method\" property: %s\n", method); - return -EINVAL; - } - return 0; -} - -static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd) -{ - invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0); -} - -static void psci_sys_poweroff(void) -{ - invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0); -} - -static void __init psci_0_2_set_functions(void) -{ - pr_info("Using standard PSCI v0.2 function IDs\n"); - psci_function_id[PSCI_FN_CPU_SUSPEND] = PSCI_0_2_FN64_CPU_SUSPEND; - psci_ops.cpu_suspend = psci_cpu_suspend; - - psci_function_id[PSCI_FN_CPU_OFF] = PSCI_0_2_FN_CPU_OFF; - psci_ops.cpu_off = psci_cpu_off; - - psci_function_id[PSCI_FN_CPU_ON] = PSCI_0_2_FN64_CPU_ON; - psci_ops.cpu_on = psci_cpu_on; - - psci_function_id[PSCI_FN_MIGRATE] = PSCI_0_2_FN64_MIGRATE; - psci_ops.migrate = psci_migrate; - - psci_function_id[PSCI_FN_AFFINITY_INFO] = PSCI_0_2_FN64_AFFINITY_INFO; - psci_ops.affinity_info = psci_affinity_info; - - psci_function_id[PSCI_FN_MIGRATE_INFO_TYPE] = - PSCI_0_2_FN_MIGRATE_INFO_TYPE; - psci_ops.migrate_info_type = psci_migrate_info_type; - - arm_pm_restart = psci_sys_reset; - - pm_power_off = psci_sys_poweroff; -} - -/* - * Probe function for PSCI firmware versions >= 0.2 - */ -static int __init psci_probe(void) -{ - int ver = psci_get_version(); - - if (ver == PSCI_RET_NOT_SUPPORTED) { - /* - * PSCI versions >=0.2 mandates implementation of - * PSCI_VERSION. - */ - pr_err("PSCI firmware does not comply with the v0.2 spec.\n"); - return -EOPNOTSUPP; - } else { - pr_info("PSCIv%d.%d detected in firmware.\n", - PSCI_VERSION_MAJOR(ver), - PSCI_VERSION_MINOR(ver)); - - if (PSCI_VERSION_MAJOR(ver) == 0 && - PSCI_VERSION_MINOR(ver) < 2) { - pr_err("Conflicting PSCI version detected.\n"); - return -EINVAL; - } - } - - psci_0_2_set_functions(); - - return 0; -} - -/* - * PSCI init function for PSCI versions >=0.2 - * - * Probe based on PSCI PSCI_VERSION function - */ -static int __init psci_0_2_init(struct device_node *np) -{ - int err; - - err = get_set_conduit_method(np); - - if (err) - goto out_put_node; - /* - * Starting with v0.2, the PSCI specification introduced a call - * (PSCI_VERSION) that allows probing the firmware version, so - * that PSCI function IDs and version specific initialization - * can be carried out according to the specific version reported - * by firmware - */ - err = psci_probe(); - -out_put_node: - of_node_put(np); - return err; -} - -/* - * PSCI < v0.2 get PSCI Function IDs via DT. - */ -static int __init psci_0_1_init(struct device_node *np) -{ - u32 id; - int err; - - err = get_set_conduit_method(np); - - if (err) - goto out_put_node; - - pr_info("Using PSCI v0.1 Function IDs from DT\n"); - - if (!of_property_read_u32(np, "cpu_suspend", &id)) { - psci_function_id[PSCI_FN_CPU_SUSPEND] = id; - psci_ops.cpu_suspend = psci_cpu_suspend; - } - - if (!of_property_read_u32(np, "cpu_off", &id)) { - psci_function_id[PSCI_FN_CPU_OFF] = id; - psci_ops.cpu_off = psci_cpu_off; - } - - if (!of_property_read_u32(np, "cpu_on", &id)) { - psci_function_id[PSCI_FN_CPU_ON] = id; - psci_ops.cpu_on = psci_cpu_on; - } - - if (!of_property_read_u32(np, "migrate", &id)) { - psci_function_id[PSCI_FN_MIGRATE] = id; - psci_ops.migrate = psci_migrate; - } - -out_put_node: - of_node_put(np); - return err; -} - -static const struct of_device_id psci_of_match[] __initconst = { - { .compatible = "arm,psci", .data = psci_0_1_init}, - { .compatible = "arm,psci-0.2", .data = psci_0_2_init}, - {}, -}; - -int __init psci_dt_init(void) -{ - struct device_node *np; - const struct of_device_id *matched_np; - psci_initcall_t init_fn; - - np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np); - - if (!np) - return -ENODEV; - - init_fn = (psci_initcall_t)matched_np->data; - return init_fn(np); -} - -/* - * We use PSCI 0.2+ when ACPI is deployed on ARM64 and it's - * explicitly clarified in SBBR - */ -int __init psci_acpi_init(void) -{ - if (!acpi_psci_present()) { - pr_info("is not implemented in ACPI.\n"); - return -EOPNOTSUPP; - } - - pr_info("probing for conduit method from ACPI.\n"); - - if (acpi_psci_use_hvc()) - invoke_psci_fn = __invoke_psci_fn_hvc; - else - invoke_psci_fn = __invoke_psci_fn_smc; - - return psci_probe(); -} - -#ifdef CONFIG_SMP - -static int __init cpu_psci_cpu_init(struct device_node *dn, unsigned int cpu) +static int __init cpu_psci_cpu_init(unsigned int cpu) { return 0; } @@ -474,6 +126,11 @@ static int cpu_psci_cpu_disable(unsigned int cpu) /* Fail early if we don't have CPU_OFF support */ if (!psci_ops.cpu_off) return -EOPNOTSUPP; + + /* Trusted OS will deny CPU_OFF */ + if (psci_tos_resident_on(cpu)) + return -EPERM; + return 0; } @@ -484,9 +141,8 @@ static void cpu_psci_cpu_die(unsigned int cpu) * There are no known implementations of PSCI actually using the * power state field, pass a sensible default for now. */ - struct psci_power_state state = { - .type = PSCI_POWER_STATE_TYPE_POWER_DOWN, - }; + u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << + PSCI_0_2_POWER_STATE_TYPE_SHIFT; ret = psci_ops.cpu_off(state); @@ -498,7 +154,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu) int err, i; if (!psci_ops.affinity_info) - return 1; + return 0; /* * cpu_kill could race with cpu_die and we can * potentially end up declaring this cpu undead @@ -509,7 +165,7 @@ static int cpu_psci_cpu_kill(unsigned int cpu) err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { pr_info("CPU%d killed.\n", cpu); - return 1; + return 0; } msleep(10); @@ -518,15 +174,13 @@ static int cpu_psci_cpu_kill(unsigned int cpu) pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", cpu, err); - /* Make op_cpu_kill() fail. */ - return 0; + return -ETIMEDOUT; } #endif -#endif static int psci_suspend_finisher(unsigned long index) { - struct psci_power_state *state = __this_cpu_read(psci_power_state); + u32 *state = __this_cpu_read(psci_power_state); return psci_ops.cpu_suspend(state[index - 1], virt_to_phys(cpu_resume)); @@ -535,7 +189,7 @@ static int psci_suspend_finisher(unsigned long index) static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index) { int ret; - struct psci_power_state *state = __this_cpu_read(psci_power_state); + u32 *state = __this_cpu_read(psci_power_state); /* * idle state index 0 corresponds to wfi, should never be called * from the cpu_suspend operations @@ -543,10 +197,10 @@ static int __maybe_unused cpu_psci_cpu_suspend(unsigned long index) if (WARN_ON_ONCE(!index)) return -EINVAL; - if (state[index - 1].type == PSCI_POWER_STATE_TYPE_STANDBY) + if (!psci_power_state_loses_context(state[index - 1])) ret = psci_ops.cpu_suspend(state[index - 1], 0); else - ret = __cpu_suspend(index, psci_suspend_finisher); + ret = cpu_suspend(index, psci_suspend_finisher); return ret; } @@ -557,7 +211,6 @@ const struct cpu_operations cpu_psci_ops = { .cpu_init_idle = cpu_psci_cpu_init_idle, .cpu_suspend = cpu_psci_cpu_suspend, #endif -#ifdef CONFIG_SMP .cpu_init = cpu_psci_cpu_init, .cpu_prepare = cpu_psci_cpu_prepare, .cpu_boot = cpu_psci_cpu_boot, @@ -566,6 +219,5 @@ const struct cpu_operations cpu_psci_ops = { .cpu_die = cpu_psci_cpu_die, .cpu_kill = cpu_psci_cpu_kill, #endif -#endif }; diff --git a/kernel/arch/arm64/kernel/ptrace.c b/kernel/arch/arm64/kernel/ptrace.c index d882b833d..ff7f13239 100644 --- a/kernel/arch/arm64/kernel/ptrace.c +++ b/kernel/arch/arm64/kernel/ptrace.c @@ -58,6 +58,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT @@ -826,6 +832,30 @@ static int compat_vfp_set(struct task_struct *target, return ret; } +static int compat_tls_get(struct task_struct *target, + const struct user_regset *regset, unsigned int pos, + unsigned int count, void *kbuf, void __user *ubuf) +{ + compat_ulong_t tls = (compat_ulong_t)target->thread.tp_value; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); +} + +static int compat_tls_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; + compat_ulong_t tls; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); + if (ret) + return ret; + + target->thread.tp_value = tls; + return ret; +} + static const struct user_regset aarch32_regsets[] = { [REGSET_COMPAT_GPR] = { .core_note_type = NT_PRSTATUS, @@ -850,6 +880,64 @@ static const struct user_regset_view user_aarch32_view = { .regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets) }; +static const struct user_regset aarch32_ptrace_regsets[] = { + [REGSET_GPR] = { + .core_note_type = NT_PRSTATUS, + .n = COMPAT_ELF_NGREG, + .size = sizeof(compat_elf_greg_t), + .align = sizeof(compat_elf_greg_t), + .get = compat_gpr_get, + .set = compat_gpr_set + }, + [REGSET_FPR] = { + .core_note_type = NT_ARM_VFP, + .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), + .size = sizeof(compat_ulong_t), + .align = sizeof(compat_ulong_t), + .get = compat_vfp_get, + .set = compat_vfp_set + }, + [REGSET_TLS] = { + .core_note_type = NT_ARM_TLS, + .n = 1, + .size = sizeof(compat_ulong_t), + .align = sizeof(compat_ulong_t), + .get = compat_tls_get, + .set = compat_tls_set, + }, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + [REGSET_HW_BREAK] = { + .core_note_type = NT_ARM_HW_BREAK, + .n = sizeof(struct user_hwdebug_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .get = hw_break_get, + .set = hw_break_set, + }, + [REGSET_HW_WATCH] = { + .core_note_type = NT_ARM_HW_WATCH, + .n = sizeof(struct user_hwdebug_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .get = hw_break_get, + .set = hw_break_set, + }, +#endif + [REGSET_SYSTEM_CALL] = { + .core_note_type = NT_ARM_SYSTEM_CALL, + .n = 1, + .size = sizeof(int), + .align = sizeof(int), + .get = system_call_get, + .set = system_call_set, + }, +}; + +static const struct user_regset_view user_aarch32_ptrace_view = { + .name = "aarch32", .e_machine = EM_ARM, + .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) +}; + static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { @@ -1109,8 +1197,16 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, const struct user_regset_view *task_user_regset_view(struct task_struct *task) { #ifdef CONFIG_COMPAT - if (is_compat_thread(task_thread_info(task))) + /* + * Core dumping of 32-bit tasks or compat ptrace requests must use the + * user_aarch32_view compatible with arm32. Native ptrace requests on + * 32-bit children use an extended user_aarch32_ptrace_view to allow + * access to the TLS register. + */ + if (is_compat_task()) return &user_aarch32_view; + else if (is_compat_thread(task_thread_info(task))) + return &user_aarch32_ptrace_view; #endif return &user_aarch64_view; } diff --git a/kernel/arch/arm64/kernel/setup.c b/kernel/arch/arm64/kernel/setup.c index 74753132c..811947914 100644 --- a/kernel/arch/arm64/kernel/setup.c +++ b/kernel/arch/arm64/kernel/setup.c @@ -28,13 +28,11 @@ #include #include #include -#include #include #include #include #include #include -#include #include #include #include @@ -45,7 +43,7 @@ #include #include #include -#include +#include #include #include @@ -54,6 +52,7 @@ #include #include #include +#include #include #include #include @@ -61,26 +60,8 @@ #include #include #include -#include #include -#include - -unsigned long elf_hwcap __read_mostly; -EXPORT_SYMBOL_GPL(elf_hwcap); - -#ifdef CONFIG_COMPAT -#define COMPAT_ELF_HWCAP_DEFAULT \ - (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\ - COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ - COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ - COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ - COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ - COMPAT_HWCAP_LPAE) -unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; -unsigned int compat_elf_hwcap2 __read_mostly; -#endif - -DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); +#include phys_addr_t __fdt_pointer __initdata; @@ -105,18 +86,6 @@ static struct resource mem_res[] = { #define kernel_code mem_res[0] #define kernel_data mem_res[1] -void __init early_print(const char *str, ...) -{ - char buf[256]; - va_list ap; - - va_start(ap, str); - vsnprintf(buf, sizeof(buf), str, ap); - va_end(ap); - - printk("%s", buf); -} - /* * The recorded values of x0 .. x3 upon kernel entry. */ @@ -142,7 +111,6 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id) } struct mpidr_hash mpidr_hash; -#ifdef CONFIG_SMP /** * smp_build_mpidr_hash - Pre-compute shifts required at each affinity * level in order to build a linear index from an @@ -208,130 +176,17 @@ static void __init smp_build_mpidr_hash(void) pr_warn("Large number of MPIDR hash buckets detected\n"); __flush_dcache_area(&mpidr_hash, sizeof(struct mpidr_hash)); } -#endif - -static void __init hyp_mode_check(void) -{ - if (is_hyp_mode_available()) - pr_info("CPU: All CPU(s) started at EL2\n"); - else if (is_hyp_mode_mismatched()) - WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC, - "CPU: CPUs started in inconsistent modes"); - else - pr_info("CPU: All CPU(s) started at EL1\n"); -} - -void __init do_post_cpus_up_work(void) -{ - hyp_mode_check(); - apply_alternatives_all(); -} - -#ifdef CONFIG_UP_LATE_INIT -void __init up_late_init(void) -{ - do_post_cpus_up_work(); -} -#endif /* CONFIG_UP_LATE_INIT */ - -static void __init setup_processor(void) -{ - u64 features, block; - u32 cwg; - int cls; - - printk("CPU: AArch64 Processor [%08x] revision %d\n", - read_cpuid_id(), read_cpuid_id() & 15); - - sprintf(init_utsname()->machine, ELF_PLATFORM); - elf_hwcap = 0; - - cpuinfo_store_boot_cpu(); - - /* - * Check for sane CTR_EL0.CWG value. - */ - cwg = cache_type_cwg(); - cls = cache_line_size(); - if (!cwg) - pr_warn("No Cache Writeback Granule information, assuming cache line size %d\n", - cls); - if (L1_CACHE_BYTES < cls) - pr_warn("L1_CACHE_BYTES smaller than the Cache Writeback Granule (%d < %d)\n", - L1_CACHE_BYTES, cls); - - /* - * ID_AA64ISAR0_EL1 contains 4-bit wide signed feature blocks. - * The blocks we test below represent incremental functionality - * for non-negative values. Negative values are reserved. - */ - features = read_cpuid(ID_AA64ISAR0_EL1); - block = (features >> 4) & 0xf; - if (!(block & 0x8)) { - switch (block) { - default: - case 2: - elf_hwcap |= HWCAP_PMULL; - case 1: - elf_hwcap |= HWCAP_AES; - case 0: - break; - } - } - - block = (features >> 8) & 0xf; - if (block && !(block & 0x8)) - elf_hwcap |= HWCAP_SHA1; - - block = (features >> 12) & 0xf; - if (block && !(block & 0x8)) - elf_hwcap |= HWCAP_SHA2; - - block = (features >> 16) & 0xf; - if (block && !(block & 0x8)) - elf_hwcap |= HWCAP_CRC32; - -#ifdef CONFIG_COMPAT - /* - * ID_ISAR5_EL1 carries similar information as above, but pertaining to - * the Aarch32 32-bit execution state. - */ - features = read_cpuid(ID_ISAR5_EL1); - block = (features >> 4) & 0xf; - if (!(block & 0x8)) { - switch (block) { - default: - case 2: - compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL; - case 1: - compat_elf_hwcap2 |= COMPAT_HWCAP2_AES; - case 0: - break; - } - } - - block = (features >> 8) & 0xf; - if (block && !(block & 0x8)) - compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1; - - block = (features >> 12) & 0xf; - if (block && !(block & 0x8)) - compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2; - - block = (features >> 16) & 0xf; - if (block && !(block & 0x8)) - compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32; -#endif -} static void __init setup_machine_fdt(phys_addr_t dt_phys) { - if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) { - early_print("\n" - "Error: invalid device tree blob at physical address 0x%p (virtual address 0x%p)\n" - "The dtb must be 8-byte aligned and passed in the first 512MB of memory\n" - "\nPlease check your bootloader.\n", - dt_phys, phys_to_virt(dt_phys)); + void *dt_virt = fixmap_remap_fdt(dt_phys); + + if (!dt_virt || !early_init_dt_scan(dt_virt)) { + pr_crit("\n" + "Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n" + "The dtb must be 8-byte aligned and must not exceed 2 MB in size\n" + "\nPlease check your bootloader.", + &dt_phys, dt_virt); while (true) cpu_relax(); @@ -368,14 +223,76 @@ static void __init request_standard_resources(void) } } +#ifdef CONFIG_BLK_DEV_INITRD +/* + * Relocate initrd if it is not completely within the linear mapping. + * This would be the case if mem= cuts out all or part of it. + */ +static void __init relocate_initrd(void) +{ + phys_addr_t orig_start = __virt_to_phys(initrd_start); + phys_addr_t orig_end = __virt_to_phys(initrd_end); + phys_addr_t ram_end = memblock_end_of_DRAM(); + phys_addr_t new_start; + unsigned long size, to_free = 0; + void *dest; + + if (orig_end <= ram_end) + return; + + /* + * Any of the original initrd which overlaps the linear map should + * be freed after relocating. + */ + if (orig_start < ram_end) + to_free = ram_end - orig_start; + + size = orig_end - orig_start; + if (!size) + return; + + /* initrd needs to be relocated completely inside linear mapping */ + new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn), + size, PAGE_SIZE); + if (!new_start) + panic("Cannot relocate initrd of size %ld\n", size); + memblock_reserve(new_start, size); + + initrd_start = __phys_to_virt(new_start); + initrd_end = initrd_start + size; + + pr_info("Moving initrd from [%llx-%llx] to [%llx-%llx]\n", + orig_start, orig_start + size - 1, + new_start, new_start + size - 1); + + dest = (void *)initrd_start; + + if (to_free) { + memcpy(dest, (void *)__phys_to_virt(orig_start), to_free); + dest += to_free; + } + + copy_from_early_mem(dest, orig_start + to_free, size - to_free); + + if (to_free) { + pr_info("Freeing original RAMDISK from [%llx-%llx]\n", + orig_start, orig_start + to_free - 1); + memblock_free(orig_start, to_free); + } +} +#else +static inline void __init relocate_initrd(void) +{ +} +#endif + u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; void __init setup_arch(char **cmdline_p) { - setup_processor(); - - setup_machine_fdt(__fdt_pointer); + pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id()); + sprintf(init_utsname()->machine, ELF_PLATFORM); init_mm.start_code = (unsigned long) _text; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; @@ -386,6 +303,8 @@ void __init setup_arch(char **cmdline_p) early_fixmap_init(); early_ioremap_init(); + setup_machine_fdt(__fdt_pointer); + parse_early_param(); /* @@ -401,6 +320,10 @@ void __init setup_arch(char **cmdline_p) acpi_boot_table_init(); paging_init(); + relocate_initrd(); + + kasan_init(); + request_standard_resources(); early_ioremap_reset(); @@ -408,18 +331,14 @@ void __init setup_arch(char **cmdline_p) if (acpi_disabled) { unflatten_device_tree(); psci_dt_init(); - cpu_read_bootcpu_ops(); -#ifdef CONFIG_SMP - of_smp_init_cpus(); -#endif } else { psci_acpi_init(); - acpi_init_cpus(); } + xen_early_init(); -#ifdef CONFIG_SMP + cpu_read_bootcpu_ops(); + smp_init_cpus(); smp_build_mpidr_hash(); -#endif #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) @@ -438,8 +357,13 @@ void __init setup_arch(char **cmdline_p) static int __init arm64_device_init(void) { - of_iommu_init(); - of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL); + if (of_have_populated_dt()) { + of_iommu_init(); + of_platform_populate(NULL, of_default_bus_match_table, + NULL, NULL); + } else if (acpi_disabled) { + pr_crit("Device tree not populated\n"); + } return 0; } arch_initcall_sync(arm64_device_init); @@ -457,125 +381,3 @@ static int __init topology_init(void) return 0; } subsys_initcall(topology_init); - -static const char *hwcap_str[] = { - "fp", - "asimd", - "evtstrm", - "aes", - "pmull", - "sha1", - "sha2", - "crc32", - NULL -}; - -#ifdef CONFIG_COMPAT -static const char *compat_hwcap_str[] = { - "swp", - "half", - "thumb", - "26bit", - "fastmult", - "fpa", - "vfp", - "edsp", - "java", - "iwmmxt", - "crunch", - "thumbee", - "neon", - "vfpv3", - "vfpv3d16", - "tls", - "vfpv4", - "idiva", - "idivt", - "vfpd32", - "lpae", - "evtstrm" -}; - -static const char *compat_hwcap2_str[] = { - "aes", - "pmull", - "sha1", - "sha2", - "crc32", - NULL -}; -#endif /* CONFIG_COMPAT */ - -static int c_show(struct seq_file *m, void *v) -{ - int i, j; - - for_each_online_cpu(i) { - struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); - u32 midr = cpuinfo->reg_midr; - - /* - * glibc reads /proc/cpuinfo to determine the number of - * online processors, looking for lines beginning with - * "processor". Give glibc what it expects. - */ -#ifdef CONFIG_SMP - seq_printf(m, "processor\t: %d\n", i); -#endif - - /* - * Dump out the common processor features in a single line. - * Userspace should read the hwcaps with getauxval(AT_HWCAP) - * rather than attempting to parse this, but there's a body of - * software which does already (at least for 32-bit). - */ - seq_puts(m, "Features\t:"); - if (personality(current->personality) == PER_LINUX32) { -#ifdef CONFIG_COMPAT - for (j = 0; compat_hwcap_str[j]; j++) - if (compat_elf_hwcap & (1 << j)) - seq_printf(m, " %s", compat_hwcap_str[j]); - - for (j = 0; compat_hwcap2_str[j]; j++) - if (compat_elf_hwcap2 & (1 << j)) - seq_printf(m, " %s", compat_hwcap2_str[j]); -#endif /* CONFIG_COMPAT */ - } else { - for (j = 0; hwcap_str[j]; j++) - if (elf_hwcap & (1 << j)) - seq_printf(m, " %s", hwcap_str[j]); - } - seq_puts(m, "\n"); - - seq_printf(m, "CPU implementer\t: 0x%02x\n", - MIDR_IMPLEMENTOR(midr)); - seq_printf(m, "CPU architecture: 8\n"); - seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr)); - seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr)); - seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr)); - } - - return 0; -} - -static void *c_start(struct seq_file *m, loff_t *pos) -{ - return *pos < 1 ? (void *)1 : NULL; -} - -static void *c_next(struct seq_file *m, void *v, loff_t *pos) -{ - ++*pos; - return NULL; -} - -static void c_stop(struct seq_file *m, void *v) -{ -} - -const struct seq_operations cpuinfo_op = { - .start = c_start, - .next = c_next, - .stop = c_stop, - .show = c_show -}; diff --git a/kernel/arch/arm64/kernel/signal32.c b/kernel/arch/arm64/kernel/signal32.c index c58aee062..71ef6dc89 100644 --- a/kernel/arch/arm64/kernel/signal32.c +++ b/kernel/arch/arm64/kernel/signal32.c @@ -394,7 +394,7 @@ badframe: if (show_unhandled_signals) pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n", current->comm, task_pid_nr(current), __func__, - regs->pc, regs->sp); + regs->pc, regs->compat_sp); force_sig(SIGSEGV, current); return 0; } @@ -431,7 +431,7 @@ badframe: if (show_unhandled_signals) pr_info_ratelimited("%s[%d]: bad frame in %s: pc=%08llx sp=%08llx\n", current->comm, task_pid_nr(current), __func__, - regs->pc, regs->sp); + regs->pc, regs->compat_sp); force_sig(SIGSEGV, current); return 0; } diff --git a/kernel/arch/arm64/kernel/sleep.S b/kernel/arch/arm64/kernel/sleep.S index ede186cdd..f586f7c87 100644 --- a/kernel/arch/arm64/kernel/sleep.S +++ b/kernel/arch/arm64/kernel/sleep.S @@ -82,7 +82,6 @@ ENTRY(__cpu_suspend_enter) str x2, [x0, #CPU_CTX_SP] ldr x1, =sleep_save_sp ldr x1, [x1, #SLEEP_SAVE_SP_VIRT] -#ifdef CONFIG_SMP mrs x7, mpidr_el1 ldr x9, =mpidr_hash ldr x10, [x9, #MPIDR_HASH_MASK] @@ -94,7 +93,6 @@ ENTRY(__cpu_suspend_enter) ldp w5, w6, [x9, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x8, x3, x4, x5, x6, x7, x10 add x1, x1, x8, lsl #3 -#endif bl __cpu_suspend_save /* * Grab suspend finisher in x20 and its argument in x19 @@ -130,12 +128,22 @@ ENDPROC(__cpu_suspend_enter) /* * x0 must contain the sctlr value retrieved from restored context */ + .pushsection ".idmap.text", "ax" ENTRY(cpu_resume_mmu) ldr x3, =cpu_resume_after_mmu msr sctlr_el1, x0 // restore sctlr_el1 isb + /* + * Invalidate the local I-cache so that any instructions fetched + * speculatively from the PoC are discarded, since they may have + * been dynamically patched at the PoU. + */ + ic iallu + dsb nsh + isb br x3 // global jump to virtual address ENDPROC(cpu_resume_mmu) + .popsection cpu_resume_after_mmu: mov x0, #0 // return zero on success ldp x19, x20, [sp, #16] @@ -149,7 +157,6 @@ ENDPROC(cpu_resume_after_mmu) ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly -#ifdef CONFIG_SMP mrs x1, mpidr_el1 adrp x8, mpidr_hash add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address @@ -159,18 +166,12 @@ ENTRY(cpu_resume) ldp w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)] compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2 /* x7 contains hash index, let's use it to grab context pointer */ -#else - mov x7, xzr -#endif - adrp x0, sleep_save_sp - add x0, x0, #:lo12:sleep_save_sp - ldr x0, [x0, #SLEEP_SAVE_SP_PHYS] + ldr_l x0, sleep_save_sp + SLEEP_SAVE_SP_PHYS ldr x0, [x0, x7, lsl #3] /* load sp from context */ ldr x2, [x0, #CPU_CTX_SP] - adrp x1, sleep_idmap_phys /* load physical address of identity map page table in x1 */ - ldr x1, [x1, #:lo12:sleep_idmap_phys] + adrp x1, idmap_pg_dir mov sp, x2 /* * cpu_do_resume expects x0 to contain context physical address diff --git a/kernel/arch/arm64/kernel/smp.c b/kernel/arch/arm64/kernel/smp.c index d3a202b85..b1adc51b2 100644 --- a/kernel/arch/arm64/kernel/smp.c +++ b/kernel/arch/arm64/kernel/smp.c @@ -17,6 +17,7 @@ * along with this program. If not, see . */ +#include #include #include #include @@ -51,6 +52,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -140,22 +142,27 @@ asmlinkage void secondary_start_kernel(void) */ atomic_inc(&mm->mm_count); current->active_mm = mm; - cpumask_set_cpu(cpu, mm_cpumask(mm)); set_my_cpu_offset(per_cpu_offset(smp_processor_id())); - printk("CPU%u: Booted secondary processor\n", cpu); /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. */ cpu_set_reserved_ttbr0(); - flush_tlb_all(); + local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); preempt_disable(); trace_hardirqs_off(); + /* + * If the system has established the capabilities, make sure + * this CPU ticks all of those. If it doesn't, the CPU will + * fail to come online. + */ + verify_local_cpu_capabilities(); + if (cpu_ops[cpu]->cpu_postboot) cpu_ops[cpu]->cpu_postboot(); @@ -176,6 +183,8 @@ asmlinkage void secondary_start_kernel(void) * the CPU migration code to notice that the CPU is online * before we continue. */ + pr_info("CPU%u: Booted secondary processor [%08x]\n", + cpu, read_cpuid_id()); set_cpu_online(cpu, true); complete(&cpu_running); @@ -230,12 +239,7 @@ int __cpu_disable(void) /* * OK - migrate IRQs away from this CPU */ - migrate_irqs(); - - /* - * Remove this CPU from the vm mask set of all processes. - */ - clear_tasks_mm_cpumask(cpu); + irq_migrate_all_off_this_cpu(); return 0; } @@ -248,20 +252,20 @@ static int op_cpu_kill(unsigned int cpu) * time and hope that it's dead, so let's skip the wait and just hope. */ if (!cpu_ops[cpu]->cpu_kill) - return 1; + return 0; return cpu_ops[cpu]->cpu_kill(cpu); } -static DECLARE_COMPLETION(cpu_died); - /* * called on the thread which is asking for a CPU to be shutdown - * waits until shutdown has completed, or it is timed out. */ void __cpu_die(unsigned int cpu) { - if (!wait_for_completion_timeout(&cpu_died, msecs_to_jiffies(5000))) { + int err; + + if (!cpu_wait_death(cpu, 5)) { pr_crit("CPU%u: cpu didn't die\n", cpu); return; } @@ -273,8 +277,10 @@ void __cpu_die(unsigned int cpu) * verify that it has really left the kernel before we consider * clobbering anything it might still be using. */ - if (!op_cpu_kill(cpu)) - pr_warn("CPU%d may not have shut down cleanly\n", cpu); + err = op_cpu_kill(cpu); + if (err) + pr_warn("CPU%d may not have shut down cleanly: %d\n", + cpu, err); } /* @@ -294,7 +300,7 @@ void cpu_die(void) local_irq_disable(); /* Tell __cpu_die() that this CPU is now safe to dispose of */ - complete(&cpu_died); + (void)cpu_report_death(); /* * Actually shutdown the CPU. This must never fail. The specific hotplug @@ -307,67 +313,182 @@ void cpu_die(void) } #endif +static void __init hyp_mode_check(void) +{ + if (is_hyp_mode_available()) + pr_info("CPU: All CPU(s) started at EL2\n"); + else if (is_hyp_mode_mismatched()) + WARN_TAINT(1, TAINT_CPU_OUT_OF_SPEC, + "CPU: CPUs started in inconsistent modes"); + else + pr_info("CPU: All CPU(s) started at EL1\n"); +} + void __init smp_cpus_done(unsigned int max_cpus) { pr_info("SMP: Total of %d processors activated.\n", num_online_cpus()); - do_post_cpus_up_work(); + setup_cpu_features(); + hyp_mode_check(); + apply_alternatives_all(); } void __init smp_prepare_boot_cpu(void) { + cpuinfo_store_boot_cpu(); set_my_cpu_offset(per_cpu_offset(smp_processor_id())); } +static u64 __init of_get_cpu_mpidr(struct device_node *dn) +{ + const __be32 *cell; + u64 hwid; + + /* + * A cpu node with missing "reg" property is + * considered invalid to build a cpu_logical_map + * entry. + */ + cell = of_get_property(dn, "reg", NULL); + if (!cell) { + pr_err("%s: missing reg property\n", dn->full_name); + return INVALID_HWID; + } + + hwid = of_read_number(cell, of_n_addr_cells(dn)); + /* + * Non affinity bits must be set to 0 in the DT + */ + if (hwid & ~MPIDR_HWID_BITMASK) { + pr_err("%s: invalid reg property\n", dn->full_name); + return INVALID_HWID; + } + return hwid; +} + +/* + * Duplicate MPIDRs are a recipe for disaster. Scan all initialized + * entries and check for duplicates. If any is found just ignore the + * cpu. cpu_logical_map was initialized to INVALID_HWID to avoid + * matching valid MPIDR values. + */ +static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid) +{ + unsigned int i; + + for (i = 1; (i < cpu) && (i < NR_CPUS); i++) + if (cpu_logical_map(i) == hwid) + return true; + return false; +} + +/* + * Initialize cpu operations for a logical cpu and + * set it in the possible mask on success + */ +static int __init smp_cpu_setup(int cpu) +{ + if (cpu_read_ops(cpu)) + return -ENODEV; + + if (cpu_ops[cpu]->cpu_init(cpu)) + return -ENODEV; + + set_cpu_possible(cpu, true); + + return 0; +} + +static bool bootcpu_valid __initdata; +static unsigned int cpu_count = 1; + +#ifdef CONFIG_ACPI +/* + * acpi_map_gic_cpu_interface - parse processor MADT entry + * + * Carry out sanity checks on MADT processor entry and initialize + * cpu_logical_map on success + */ +static void __init +acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) +{ + u64 hwid = processor->arm_mpidr; + + if (!(processor->flags & ACPI_MADT_ENABLED)) { + pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid); + return; + } + + if (hwid & ~MPIDR_HWID_BITMASK || hwid == INVALID_HWID) { + pr_err("skipping CPU entry with invalid MPIDR 0x%llx\n", hwid); + return; + } + + if (is_mpidr_duplicate(cpu_count, hwid)) { + pr_err("duplicate CPU MPIDR 0x%llx in MADT\n", hwid); + return; + } + + /* Check if GICC structure of boot CPU is available in the MADT */ + if (cpu_logical_map(0) == hwid) { + if (bootcpu_valid) { + pr_err("duplicate boot CPU MPIDR: 0x%llx in MADT\n", + hwid); + return; + } + bootcpu_valid = true; + return; + } + + if (cpu_count >= NR_CPUS) + return; + + /* map the logical cpu id to cpu MPIDR */ + cpu_logical_map(cpu_count) = hwid; + + cpu_count++; +} + +static int __init +acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_generic_interrupt *processor; + + processor = (struct acpi_madt_generic_interrupt *)header; + if (BAD_MADT_GICC_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + acpi_map_gic_cpu_interface(processor); + + return 0; +} +#else +#define acpi_table_parse_madt(...) do { } while (0) +#endif + /* * Enumerate the possible CPU set from the device tree and build the * cpu logical map array containing MPIDR values related to logical * cpus. Assumes that cpu_logical_map(0) has already been initialized. */ -void __init of_smp_init_cpus(void) +static void __init of_parse_and_init_cpus(void) { struct device_node *dn = NULL; - unsigned int i, cpu = 1; - bool bootcpu_valid = false; while ((dn = of_find_node_by_type(dn, "cpu"))) { - const u32 *cell; - u64 hwid; + u64 hwid = of_get_cpu_mpidr(dn); - /* - * A cpu node with missing "reg" property is - * considered invalid to build a cpu_logical_map - * entry. - */ - cell = of_get_property(dn, "reg", NULL); - if (!cell) { - pr_err("%s: missing reg property\n", dn->full_name); + if (hwid == INVALID_HWID) goto next; - } - hwid = of_read_number(cell, of_n_addr_cells(dn)); - /* - * Non affinity bits must be set to 0 in the DT - */ - if (hwid & ~MPIDR_HWID_BITMASK) { - pr_err("%s: invalid reg property\n", dn->full_name); + if (is_mpidr_duplicate(cpu_count, hwid)) { + pr_err("%s: duplicate cpu reg properties in the DT\n", + dn->full_name); goto next; } - /* - * Duplicate MPIDRs are a recipe for disaster. Scan - * all initialized entries and check for - * duplicates. If any is found just ignore the cpu. - * cpu_logical_map was initialized to INVALID_HWID to - * avoid matching valid MPIDR values. - */ - for (i = 1; (i < cpu) && (i < NR_CPUS); i++) { - if (cpu_logical_map(i) == hwid) { - pr_err("%s: duplicate cpu reg properties in the DT\n", - dn->full_name); - goto next; - } - } - /* * The numbering scheme requires that the boot CPU * must be assigned logical id 0. Record it so that @@ -392,38 +513,58 @@ void __init of_smp_init_cpus(void) continue; } - if (cpu >= NR_CPUS) - goto next; - - if (cpu_read_ops(dn, cpu) != 0) - goto next; - - if (cpu_ops[cpu]->cpu_init(dn, cpu)) + if (cpu_count >= NR_CPUS) goto next; pr_debug("cpu logical map 0x%llx\n", hwid); - cpu_logical_map(cpu) = hwid; + cpu_logical_map(cpu_count) = hwid; next: - cpu++; + cpu_count++; } +} - /* sanity check */ - if (cpu > NR_CPUS) - pr_warning("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu, NR_CPUS); +/* + * Enumerate the possible CPU set from the device tree or ACPI and build the + * cpu logical map array containing MPIDR values related to logical + * cpus. Assumes that cpu_logical_map(0) has already been initialized. + */ +void __init smp_init_cpus(void) +{ + int i; + + if (acpi_disabled) + of_parse_and_init_cpus(); + else + /* + * do a walk of MADT to determine how many CPUs + * we have including disabled CPUs, and get information + * we need for SMP init + */ + acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, + acpi_parse_gic_cpu_interface, 0); + + if (cpu_count > NR_CPUS) + pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", + cpu_count, NR_CPUS); if (!bootcpu_valid) { - pr_err("DT missing boot CPU MPIDR, not enabling secondaries\n"); + pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); return; } /* - * All the cpus that made it to the cpu_logical_map have been - * validated so set them as possible cpus. + * We need to set the cpu_logical_map entries before enabling + * the cpus so that cpu processor description entries (DT cpu nodes + * and ACPI MADT entries) can be retrieved by matching the cpu hwid + * with entries in cpu_logical_map while initializing the cpus. + * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 0; i < NR_CPUS; i++) - if (cpu_logical_map(i) != INVALID_HWID) - set_cpu_possible(i, true); + for (i = 1; i < NR_CPUS; i++) { + if (cpu_logical_map(i) != INVALID_HWID) { + if (smp_cpu_setup(i)) + cpu_logical_map(i) = INVALID_HWID; + } + } } void __init smp_prepare_cpus(unsigned int max_cpus) diff --git a/kernel/arch/arm64/kernel/smp_spin_table.c b/kernel/arch/arm64/kernel/smp_spin_table.c index 14944e5b2..aef3605a8 100644 --- a/kernel/arch/arm64/kernel/smp_spin_table.c +++ b/kernel/arch/arm64/kernel/smp_spin_table.c @@ -49,8 +49,14 @@ static void write_pen_release(u64 val) } -static int smp_spin_table_cpu_init(struct device_node *dn, unsigned int cpu) +static int smp_spin_table_cpu_init(unsigned int cpu) { + struct device_node *dn; + + dn = of_get_cpu_node(cpu, NULL); + if (!dn) + return -ENODEV; + /* * Determine the address from which the CPU is polling. */ diff --git a/kernel/arch/arm64/kernel/stacktrace.c b/kernel/arch/arm64/kernel/stacktrace.c index 407991bf7..ccb6078ed 100644 --- a/kernel/arch/arm64/kernel/stacktrace.c +++ b/kernel/arch/arm64/kernel/stacktrace.c @@ -48,11 +48,7 @@ int notrace unwind_frame(struct stackframe *frame) frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); - /* - * -4 here because we care about the PC at time of bl, - * not where the return will go. - */ - frame->pc = *(unsigned long *)(fp + 8) - 4; + frame->pc = *(unsigned long *)(fp + 8); return 0; } diff --git a/kernel/arch/arm64/kernel/suspend.c b/kernel/arch/arm64/kernel/suspend.c index d7daf45ae..1095aa483 100644 --- a/kernel/arch/arm64/kernel/suspend.c +++ b/kernel/arch/arm64/kernel/suspend.c @@ -1,3 +1,4 @@ +#include #include #include #include @@ -41,7 +42,7 @@ void notrace __cpu_suspend_save(struct cpu_suspend_ctx *ptr, * time the notifier runs debug exceptions might have been enabled already, * with HW breakpoints registers content still in an unknown state. */ -void (*hw_breakpoint_restore)(void *); +static void (*hw_breakpoint_restore)(void *); void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) { /* Prevent multiple restore hook initializations */ @@ -51,13 +52,13 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *)) } /* - * __cpu_suspend + * cpu_suspend * * arg: argument to pass to the finisher function * fn: finisher function pointer * */ -int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) { struct mm_struct *mm = current->active_mm; int ret; @@ -70,6 +71,13 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) */ local_dbg_save(flags); + /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + /* * mm context saved on the stack, it will be restored when * the cpu comes out of reset through the identity mapped @@ -80,17 +88,21 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) if (ret == 0) { /* * We are resuming from reset with TTBR0_EL1 set to the - * idmap to enable the MMU; restore the active_mm mappings in - * TTBR0_EL1 unless the active_mm == &init_mm, in which case - * the thread entered __cpu_suspend with TTBR0_EL1 set to - * reserved TTBR0 page tables and should be restored as such. + * idmap to enable the MMU; set the TTBR0 to the reserved + * page tables to prevent speculative TLB allocations, flush + * the local tlb and set the default tcr_el1.t0sz so that + * the TTBR0 address space set-up is properly restored. + * If the current active_mm != &init_mm we entered cpu_suspend + * with mappings in TTBR0 that must be restored, so we switch + * them back to complete the address space configuration + * restoration before returning. */ - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + cpu_set_default_tcr_t0sz(); - flush_tlb_all(); + if (mm != &init_mm) + cpu_switch_mm(mm->pgd, mm); /* * Restore per-cpu offset before any kernel @@ -107,6 +119,8 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) hw_breakpoint_restore(NULL); } + unpause_graph_tracing(); + /* * Restore pstate flags. OS lock and mdscr have been already * restored, so from this point onwards, debugging is fully @@ -118,7 +132,6 @@ int __cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) } struct sleep_save_sp sleep_save_sp; -phys_addr_t sleep_idmap_phys; static int __init cpu_suspend_init(void) { @@ -132,9 +145,7 @@ static int __init cpu_suspend_init(void) sleep_save_sp.save_ptr_stash = ctx_ptr; sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr); - sleep_idmap_phys = virt_to_phys(idmap_pg_dir); __flush_dcache_area(&sleep_save_sp, sizeof(struct sleep_save_sp)); - __flush_dcache_area(&sleep_idmap_phys, sizeof(sleep_idmap_phys)); return 0; } diff --git a/kernel/arch/arm64/kernel/time.c b/kernel/arch/arm64/kernel/time.c index 42f9195cf..13339b6ff 100644 --- a/kernel/arch/arm64/kernel/time.c +++ b/kernel/arch/arm64/kernel/time.c @@ -42,7 +42,6 @@ #include #include -#ifdef CONFIG_SMP unsigned long profile_pc(struct pt_regs *regs) { struct stackframe frame; @@ -62,23 +61,16 @@ unsigned long profile_pc(struct pt_regs *regs) return frame.pc; } EXPORT_SYMBOL(profile_pc); -#endif void __init time_init(void) { u32 arch_timer_rate; of_clk_init(NULL); - clocksource_of_init(); + clocksource_probe(); tick_setup_hrtimer_broadcast(); - /* - * Since ACPI or FDT will only one be available in the system, - * we can use acpi_generic_timer_init() here safely - */ - acpi_generic_timer_init(); - arch_timer_rate = arch_timer_get_rate(); if (!arch_timer_rate) panic("Unable to initialise architected timer.\n"); diff --git a/kernel/arch/arm64/kernel/topology.c b/kernel/arch/arm64/kernel/topology.c index fcb8f7b42..694f6deed 100644 --- a/kernel/arch/arm64/kernel/topology.c +++ b/kernel/arch/arm64/kernel/topology.c @@ -300,6 +300,6 @@ void __init init_cpu_topology(void) * Discard anything that was parsed if we hit an error so we * don't use partial information. */ - if (parse_dt_topology()) + if (of_have_populated_dt() && parse_dt_topology()) reset_cpu_topology(); } diff --git a/kernel/arch/arm64/kernel/traps.c b/kernel/arch/arm64/kernel/traps.c index 1ef2940df..e9b9b5364 100644 --- a/kernel/arch/arm64/kernel/traps.c +++ b/kernel/arch/arm64/kernel/traps.c @@ -17,6 +17,7 @@ * along with this program. If not, see . */ +#include #include #include #include @@ -32,8 +33,10 @@ #include #include +#include #include #include +#include #include #include #include @@ -52,11 +55,12 @@ int show_unhandled_signals = 1; * Dump out the contents of some memory nicely... */ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, - unsigned long top) + unsigned long top, bool compat) { unsigned long first; mm_segment_t fs; int i; + unsigned int width = compat ? 4 : 8; /* * We need to switch to kernel mode so that we can use __get_user @@ -75,13 +79,22 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, memset(str, ' ', sizeof(str)); str[sizeof(str) - 1] = '\0'; - for (p = first, i = 0; i < 8 && p < top; i++, p += 4) { + for (p = first, i = 0; i < (32 / width) + && p < top; i++, p += width) { if (p >= bottom && p < top) { - unsigned int val; - if (__get_user(val, (unsigned int *)p) == 0) - sprintf(str + i * 9, " %08x", val); - else - sprintf(str + i * 9, " ????????"); + unsigned long val; + + if (width == 8) { + if (__get_user(val, (unsigned long *)p) == 0) + sprintf(str + i * 17, " %016lx", val); + else + sprintf(str + i * 17, " ????????????????"); + } else { + if (__get_user(val, (unsigned int *)p) == 0) + sprintf(str + i * 9, " %08lx", val); + else + sprintf(str + i * 9, " ????????"); + } } } printk("%s%04lx:%s\n", lvl, first & 0xffff, str); @@ -90,12 +103,12 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, set_fs(fs); } -static void dump_backtrace_entry(unsigned long where, unsigned long stack) +static void dump_backtrace_entry(unsigned long where) { + /* + * Note that 'where' can have a physical address, but it's not handled. + */ print_ip_sym(where); - if (in_exception_text(where)) - dump_mem("", "Exception stack", stack, - stack + sizeof(struct pt_regs)); } static void dump_instr(const char *lvl, struct pt_regs *regs) @@ -159,12 +172,17 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) pr_emerg("Call trace:\n"); while (1) { unsigned long where = frame.pc; + unsigned long stack; int ret; + dump_backtrace_entry(where); ret = unwind_frame(&frame); if (ret < 0) break; - dump_backtrace_entry(where, frame.sp); + stack = frame.sp; + if (in_exception_text(where)) + dump_mem("", "Exception stack", stack, + stack + sizeof(struct pt_regs), false); } } @@ -179,11 +197,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) #else #define S_PREEMPT "" #endif -#ifdef CONFIG_SMP #define S_SMP " SMP" -#else -#define S_SMP "" -#endif static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs) @@ -207,7 +221,8 @@ static int __die(const char *str, int err, struct thread_info *thread, if (!user_mode(regs) || in_interrupt()) { dump_mem(KERN_EMERG, "Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_stack_page(tsk)); + THREAD_SIZE + (unsigned long)task_stack_page(tsk), + compat_user_mode(regs)); dump_backtrace(regs, tsk); dump_instr(KERN_EMERG, regs); } @@ -335,8 +350,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (call_undef_hook(regs) == 0) return; - if (show_unhandled_signals && unhandled_signal(current, SIGILL) && - printk_ratelimit()) { + if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) { pr_info("%s[%d]: undefined instruction: pc=%p\n", current->comm, task_pid_nr(current), pc); dump_instr(KERN_INFO, regs); @@ -363,7 +377,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs) } #endif - if (show_unhandled_signals && printk_ratelimit()) { + if (show_unhandled_signals_ratelimited()) { pr_info("%s[%d]: syscall %d\n", current->comm, task_pid_nr(current), (int)regs->syscallno); dump_instr("", regs); @@ -460,7 +474,63 @@ void __pgd_error(const char *file, int line, unsigned long val) pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val); } +/* GENERIC_BUG traps */ + +int is_valid_bugaddr(unsigned long addr) +{ + /* + * bug_handler() only called for BRK #BUG_BRK_IMM. + * So the answer is trivial -- any spurious instances with no + * bug table entry will be rejected by report_bug() and passed + * back to the debug-monitors code and handled as a fatal + * unexpected debug exception. + */ + return 1; +} + +static int bug_handler(struct pt_regs *regs, unsigned int esr) +{ + if (user_mode(regs)) + return DBG_HOOK_ERROR; + + switch (report_bug(regs->pc, regs)) { + case BUG_TRAP_TYPE_BUG: + die("Oops - BUG", regs, 0); + break; + + case BUG_TRAP_TYPE_WARN: + /* Ideally, report_bug() should backtrace for us... but no. */ + dump_backtrace(regs, NULL); + break; + + default: + /* unknown/unrecognised bug trap type */ + return DBG_HOOK_ERROR; + } + + /* If thread survives, skip over the BUG instruction and continue: */ + regs->pc += AARCH64_INSN_SIZE; /* skip BRK and resume */ + return DBG_HOOK_HANDLED; +} + +static struct break_hook bug_break_hook = { + .esr_val = 0xf2000000 | BUG_BRK_IMM, + .esr_mask = 0xffffffff, + .fn = bug_handler, +}; + +/* + * Initial handler for AArch64 BRK exceptions + * This handler only used until debug_traps_init(). + */ +int __init early_brk64(unsigned long addr, unsigned int esr, + struct pt_regs *regs) +{ + return bug_handler(regs, esr) != DBG_HOOK_HANDLED; +} + +/* This registration must happen early, before debug_traps_init(). */ void __init trap_init(void) { - return; + register_break_hook(&bug_break_hook); } diff --git a/kernel/arch/arm64/kernel/vdso.c b/kernel/arch/arm64/kernel/vdso.c index ec37ab3f5..97bc68f4c 100644 --- a/kernel/arch/arm64/kernel/vdso.c +++ b/kernel/arch/arm64/kernel/vdso.c @@ -199,16 +199,15 @@ up_fail: */ void update_vsyscall(struct timekeeper *tk) { - struct timespec xtime_coarse; u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter"); ++vdso_data->tb_seq_count; smp_wmb(); - xtime_coarse = __current_kernel_time(); vdso_data->use_syscall = use_syscall; - vdso_data->xtime_coarse_sec = xtime_coarse.tv_sec; - vdso_data->xtime_coarse_nsec = xtime_coarse.tv_nsec; + vdso_data->xtime_coarse_sec = tk->xtime_sec; + vdso_data->xtime_coarse_nsec = tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift; vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; diff --git a/kernel/arch/arm64/kernel/vdso/Makefile b/kernel/arch/arm64/kernel/vdso/Makefile index f6fe17d88..b467fd0a3 100644 --- a/kernel/arch/arm64/kernel/vdso/Makefile +++ b/kernel/arch/arm64/kernel/vdso/Makefile @@ -15,6 +15,9 @@ ccflags-y := -shared -fno-common -fno-builtin ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \ $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) +# Disable gcov profiling for VDSO code +GCOV_PROFILE := n + # Workaround for bare-metal (ELF) toolchains that neglect to pass -shared # down to collect2, resulting in silent corruption of the vDSO image. ccflags-y += -Wl,-shared diff --git a/kernel/arch/arm64/kernel/vmlinux.lds.S b/kernel/arch/arm64/kernel/vmlinux.lds.S index a2c29865c..71426a78d 100644 --- a/kernel/arch/arm64/kernel/vmlinux.lds.S +++ b/kernel/arch/arm64/kernel/vmlinux.lds.S @@ -5,6 +5,8 @@ */ #include +#include +#include #include #include #include @@ -38,6 +40,12 @@ jiffies = jiffies_64; *(.hyp.text) \ VMLINUX_SYMBOL(__hyp_text_end) = .; +#define IDMAP_TEXT \ + . = ALIGN(SZ_4K); \ + VMLINUX_SYMBOL(__idmap_text_start) = .; \ + *(.idmap.text) \ + VMLINUX_SYMBOL(__idmap_text_end) = .; + /* * The size of the PE/COFF section that covers the kernel image, which * runs from stext to _edata, must be a round multiple of the PE/COFF @@ -54,9 +62,12 @@ PECOFF_FILE_ALIGNMENT = 0x200; #define PECOFF_EDATA_PADDING #endif -#ifdef CONFIG_DEBUG_ALIGN_RODATA +#if defined(CONFIG_DEBUG_ALIGN_RODATA) #define ALIGN_DEBUG_RO . = ALIGN(1<phys conversions will fail. diff --git a/kernel/arch/arm64/kvm/Kconfig b/kernel/arch/arm64/kvm/Kconfig index 5105e297e..a5272c07d 100644 --- a/kernel/arch/arm64/kvm/Kconfig +++ b/kernel/arch/arm64/kvm/Kconfig @@ -16,9 +16,13 @@ menuconfig VIRTUALIZATION if VIRTUALIZATION +config KVM_ARM_VGIC_V3 + bool + config KVM bool "Kernel-based Virtual Machine (KVM) support" depends on OF + depends on !ARM64_16K_PAGES select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES @@ -28,10 +32,14 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD + select KVM_ARM_VGIC_V3 ---help--- Support hosting virtualized guest machines. + We don't support KVM with 16K page tables yet, due to the multiple + levels of fake page tables. If unsure, say N. @@ -40,15 +48,6 @@ config KVM_ARM_HOST ---help--- Provides host support for ARM processors. -config KVM_ARM_MAX_VCPUS - int "Number maximum supported virtual CPUs per VM" - depends on KVM_ARM_HOST - default 4 - help - Static number of max supported virtual CPUs per VM. - - If you choose a high number, the vcpu structures will be quite - large, so only choose a reasonable number that you expect to - actually use. +source drivers/vhost/Kconfig endif # VIRTUALIZATION diff --git a/kernel/arch/arm64/kvm/Makefile b/kernel/arch/arm64/kvm/Makefile index d5904f876..1949fe5f5 100644 --- a/kernel/arch/arm64/kvm/Makefile +++ b/kernel/arch/arm64/kvm/Makefile @@ -11,13 +11,13 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o kvm-$(CONFIG_KVM_ARM_HOST) += emulate.o inject_fault.o regmap.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o -kvm-$(CONFIG_KVM_ARM_HOST) += guest.o reset.o sys_regs.o sys_regs_generic_v8.o +kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o diff --git a/kernel/arch/arm64/kvm/debug.c b/kernel/arch/arm64/kvm/debug.c new file mode 100644 index 000000000..47e5f0fea --- /dev/null +++ b/kernel/arch/arm64/kvm/debug.c @@ -0,0 +1,217 @@ +/* + * Debug and Guest Debug support + * + * Copyright (C) 2015 - Linaro Ltd + * Author: Alex Bennée + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + +#include +#include + +#include +#include +#include +#include + +#include "trace.h" + +/* These are the bits of MDSCR_EL1 we may manipulate */ +#define MDSCR_EL1_DEBUG_MASK (DBG_MDSCR_SS | \ + DBG_MDSCR_KDE | \ + DBG_MDSCR_MDE) + +static DEFINE_PER_CPU(u32, mdcr_el2); + +/** + * save/restore_guest_debug_regs + * + * For some debug operations we need to tweak some guest registers. As + * a result we need to save the state of those registers before we + * make those modifications. + * + * Guest access to MDSCR_EL1 is trapped by the hypervisor and handled + * after we have restored the preserved value to the main context. + */ +static void save_guest_debug_regs(struct kvm_vcpu *vcpu) +{ + vcpu->arch.guest_debug_preserved.mdscr_el1 = vcpu_sys_reg(vcpu, MDSCR_EL1); + + trace_kvm_arm_set_dreg32("Saved MDSCR_EL1", + vcpu->arch.guest_debug_preserved.mdscr_el1); +} + +static void restore_guest_debug_regs(struct kvm_vcpu *vcpu) +{ + vcpu_sys_reg(vcpu, MDSCR_EL1) = vcpu->arch.guest_debug_preserved.mdscr_el1; + + trace_kvm_arm_set_dreg32("Restored MDSCR_EL1", + vcpu_sys_reg(vcpu, MDSCR_EL1)); +} + +/** + * kvm_arm_init_debug - grab what we need for debug + * + * Currently the sole task of this function is to retrieve the initial + * value of mdcr_el2 so we can preserve MDCR_EL2.HPMN which has + * presumably been set-up by some knowledgeable bootcode. + * + * It is called once per-cpu during CPU hyp initialisation. + */ + +void kvm_arm_init_debug(void) +{ + __this_cpu_write(mdcr_el2, kvm_call_hyp(__kvm_get_mdcr_el2)); +} + +/** + * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state + */ + +void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.debug_ptr = &vcpu->arch.vcpu_debug_state; +} + +/** + * kvm_arm_setup_debug - set up debug related stuff + * + * @vcpu: the vcpu pointer + * + * This is called before each entry into the hypervisor to setup any + * debug related registers. Currently this just ensures we will trap + * access to: + * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) + * - Debug ROM Address (MDCR_EL2_TDRA) + * - OS related registers (MDCR_EL2_TDOSA) + * + * Additionally, KVM only traps guest accesses to the debug registers if + * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY + * flag on vcpu->arch.debug_flags). Since the guest must not interfere + * with the hardware state when debugging the guest, we must ensure that + * trapping is enabled whenever we are debugging the guest using the + * debug registers. + */ + +void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) +{ + bool trap_debug = !(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY); + + trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); + + vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; + vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | + MDCR_EL2_TPMCR | + MDCR_EL2_TDRA | + MDCR_EL2_TDOSA); + + /* Is Guest debugging in effect? */ + if (vcpu->guest_debug) { + /* Route all software debug exceptions to EL2 */ + vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; + + /* Save guest debug state */ + save_guest_debug_regs(vcpu); + + /* + * Single Step (ARM ARM D2.12.3 The software step state + * machine) + * + * If we are doing Single Step we need to manipulate + * the guest's MDSCR_EL1.SS and PSTATE.SS. Once the + * step has occurred the hypervisor will trap the + * debug exception and we return to userspace. + * + * If the guest attempts to single step its userspace + * we would have to deal with a trapped exception + * while in the guest kernel. Because this would be + * hard to unwind we suppress the guest's ability to + * do so by masking MDSCR_EL.SS. + * + * This confuses guest debuggers which use + * single-step behind the scenes but everything + * returns to normal once the host is no longer + * debugging the system. + */ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + *vcpu_cpsr(vcpu) |= DBG_SPSR_SS; + vcpu_sys_reg(vcpu, MDSCR_EL1) |= DBG_MDSCR_SS; + } else { + vcpu_sys_reg(vcpu, MDSCR_EL1) &= ~DBG_MDSCR_SS; + } + + trace_kvm_arm_set_dreg32("SPSR_EL2", *vcpu_cpsr(vcpu)); + + /* + * HW Breakpoints and watchpoints + * + * We simply switch the debug_ptr to point to our new + * external_debug_state which has been populated by the + * debug ioctl. The existing KVM_ARM64_DEBUG_DIRTY + * mechanism ensures the registers are updated on the + * world switch. + */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { + /* Enable breakpoints/watchpoints */ + vcpu_sys_reg(vcpu, MDSCR_EL1) |= DBG_MDSCR_MDE; + + vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + trap_debug = true; + + trace_kvm_arm_set_regset("BKPTS", get_num_brps(), + &vcpu->arch.debug_ptr->dbg_bcr[0], + &vcpu->arch.debug_ptr->dbg_bvr[0]); + + trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), + &vcpu->arch.debug_ptr->dbg_wcr[0], + &vcpu->arch.debug_ptr->dbg_wvr[0]); + } + } + + BUG_ON(!vcpu->guest_debug && + vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state); + + /* Trap debug register access */ + if (trap_debug) + vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; + + trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); + trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_sys_reg(vcpu, MDSCR_EL1)); +} + +void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) +{ + trace_kvm_arm_clear_debug(vcpu->guest_debug); + + if (vcpu->guest_debug) { + restore_guest_debug_regs(vcpu); + + /* + * If we were using HW debug we need to restore the + * debug_ptr to the guest debug state. + */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { + kvm_arm_reset_debug_ptr(vcpu); + + trace_kvm_arm_set_regset("BKPTS", get_num_brps(), + &vcpu->arch.debug_ptr->dbg_bcr[0], + &vcpu->arch.debug_ptr->dbg_bvr[0]); + + trace_kvm_arm_set_regset("WAPTS", get_num_wrps(), + &vcpu->arch.debug_ptr->dbg_wcr[0], + &vcpu->arch.debug_ptr->dbg_wvr[0]); + } + } +} diff --git a/kernel/arch/arm64/kvm/guest.c b/kernel/arch/arm64/kvm/guest.c index 9535bd555..3039f080e 100644 --- a/kernel/arch/arm64/kvm/guest.c +++ b/kernel/arch/arm64/kvm/guest.c @@ -32,6 +32,8 @@ #include #include +#include "trace.h" + struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; @@ -184,7 +186,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) u64 val; val = kvm_arm_timer_get_reg(vcpu, reg->id); - return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)); + return copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id)) ? -EFAULT : 0; } /** @@ -293,7 +295,8 @@ int __attribute_const__ kvm_target_cpu(void) break; }; - return -EINVAL; + /* Return a default generic target */ + return KVM_ARM_TARGET_GENERIC_V8; } int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init) @@ -331,3 +334,41 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, { return -EINVAL; } + +#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ + KVM_GUESTDBG_USE_SW_BP | \ + KVM_GUESTDBG_USE_HW | \ + KVM_GUESTDBG_SINGLESTEP) + +/** + * kvm_arch_vcpu_ioctl_set_guest_debug - set up guest debugging + * @kvm: pointer to the KVM struct + * @kvm_guest_debug: the ioctl data buffer + * + * This sets up and enables the VM for guest debugging. Userspace + * passes in a control flag to enable different debug types and + * potentially other architecture specific information in the rest of + * the structure. + */ +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + trace_kvm_set_guest_debug(vcpu, dbg->control); + + if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) + return -EINVAL; + + if (dbg->control & KVM_GUESTDBG_ENABLE) { + vcpu->guest_debug = dbg->control; + + /* Hardware assisted Break and Watch points */ + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW) { + vcpu->arch.external_debug_state = dbg->arch; + } + + } else { + /* If not enabled clear all flags */ + vcpu->guest_debug = 0; + } + return 0; +} diff --git a/kernel/arch/arm64/kvm/handle_exit.c b/kernel/arch/arm64/kvm/handle_exit.c index 524fa2567..15f0477b0 100644 --- a/kernel/arch/arm64/kvm/handle_exit.c +++ b/kernel/arch/arm64/kvm/handle_exit.c @@ -37,7 +37,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret; - trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), + trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0), kvm_vcpu_hvc_get_imm(vcpu)); ret = kvm_psci_call(vcpu); @@ -82,6 +82,45 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) return 1; } +/** + * kvm_handle_guest_debug - handle a debug exception instruction + * + * @vcpu: the vcpu pointer + * @run: access to the kvm_run structure for results + * + * We route all debug exceptions through the same handler. If both the + * guest and host are using the same debug facilities it will be up to + * userspace to re-inject the correct exception for guest delivery. + * + * @return: 0 (while setting run->exit_reason), -1 for error + */ +static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + u32 hsr = kvm_vcpu_get_hsr(vcpu); + int ret = 0; + + run->exit_reason = KVM_EXIT_DEBUG; + run->debug.arch.hsr = hsr; + + switch (hsr >> ESR_ELx_EC_SHIFT) { + case ESR_ELx_EC_WATCHPT_LOW: + run->debug.arch.far = vcpu->arch.fault.far_el2; + /* fall through */ + case ESR_ELx_EC_SOFTSTP_LOW: + case ESR_ELx_EC_BREAKPT_LOW: + case ESR_ELx_EC_BKPT32: + case ESR_ELx_EC_BRK64: + break; + default: + kvm_err("%s: un-handled case hsr: %#08x\n", + __func__, (unsigned int) hsr); + ret = -1; + break; + } + + return ret; +} + static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_WFx] = kvm_handle_wfx, [ESR_ELx_EC_CP15_32] = kvm_handle_cp15_32, @@ -96,6 +135,11 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_SYS64] = kvm_handle_sys_reg, [ESR_ELx_EC_IABT_LOW] = kvm_handle_guest_abort, [ESR_ELx_EC_DABT_LOW] = kvm_handle_guest_abort, + [ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug, + [ESR_ELx_EC_WATCHPT_LOW]= kvm_handle_guest_debug, + [ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug, + [ESR_ELx_EC_BKPT32] = kvm_handle_guest_debug, + [ESR_ELx_EC_BRK64] = kvm_handle_guest_debug, }; static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) diff --git a/kernel/arch/arm64/kvm/hyp.S b/kernel/arch/arm64/kvm/hyp.S index 64f9e60b3..86c289832 100644 --- a/kernel/arch/arm64/kvm/hyp.S +++ b/kernel/arch/arm64/kvm/hyp.S @@ -17,8 +17,10 @@ #include +#include #include #include +#include #include #include #include @@ -50,8 +52,8 @@ stp x29, lr, [x3, #80] mrs x19, sp_el0 - mrs x20, elr_el2 // EL1 PC - mrs x21, spsr_el2 // EL1 pstate + mrs x20, elr_el2 // pc before entering el2 + mrs x21, spsr_el2 // pstate before entering el2 stp x19, x20, [x3, #96] str x21, [x3, #112] @@ -82,8 +84,8 @@ ldr x21, [x3, #16] msr sp_el0, x19 - msr elr_el2, x20 // EL1 PC - msr spsr_el2, x21 // EL1 pstate + msr elr_el2, x20 // pc on return from el2 + msr spsr_el2, x21 // pstate on return from el2 add x3, x2, #CPU_XREG_OFFSET(19) ldp x19, x20, [x3] @@ -228,199 +230,52 @@ stp x24, x25, [x3, #160] .endm -.macro save_debug - // x2: base address for cpu context - // x3: tmp register - - mrs x26, id_aa64dfr0_el1 - ubfx x24, x26, #12, #4 // Extract BRPs - ubfx x25, x26, #20, #4 // Extract WRPs - mov w26, #15 - sub w24, w26, w24 // How many BPs to skip - sub w25, w26, w25 // How many WPs to skip - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - mrs x20, dbgbcr15_el1 - mrs x19, dbgbcr14_el1 - mrs x18, dbgbcr13_el1 - mrs x17, dbgbcr12_el1 - mrs x16, dbgbcr11_el1 - mrs x15, dbgbcr10_el1 - mrs x14, dbgbcr9_el1 - mrs x13, dbgbcr8_el1 - mrs x12, dbgbcr7_el1 - mrs x11, dbgbcr6_el1 - mrs x10, dbgbcr5_el1 - mrs x9, dbgbcr4_el1 - mrs x8, dbgbcr3_el1 - mrs x7, dbgbcr2_el1 - mrs x6, dbgbcr1_el1 - mrs x5, dbgbcr0_el1 - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 - -1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - mrs x20, dbgbvr15_el1 - mrs x19, dbgbvr14_el1 - mrs x18, dbgbvr13_el1 - mrs x17, dbgbvr12_el1 - mrs x16, dbgbvr11_el1 - mrs x15, dbgbvr10_el1 - mrs x14, dbgbvr9_el1 - mrs x13, dbgbvr8_el1 - mrs x12, dbgbvr7_el1 - mrs x11, dbgbvr6_el1 - mrs x10, dbgbvr5_el1 - mrs x9, dbgbvr4_el1 - mrs x8, dbgbvr3_el1 - mrs x7, dbgbvr2_el1 - mrs x6, dbgbvr1_el1 - mrs x5, dbgbvr0_el1 - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 - -1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - mrs x20, dbgwcr15_el1 - mrs x19, dbgwcr14_el1 - mrs x18, dbgwcr13_el1 - mrs x17, dbgwcr12_el1 - mrs x16, dbgwcr11_el1 - mrs x15, dbgwcr10_el1 - mrs x14, dbgwcr9_el1 - mrs x13, dbgwcr8_el1 - mrs x12, dbgwcr7_el1 - mrs x11, dbgwcr6_el1 - mrs x10, dbgwcr5_el1 - mrs x9, dbgwcr4_el1 - mrs x8, dbgwcr3_el1 - mrs x7, dbgwcr2_el1 - mrs x6, dbgwcr1_el1 - mrs x5, dbgwcr0_el1 - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 +.macro save_debug type + // x4: pointer to register set + // x5: number of registers to skip + // x6..x22 trashed + adr x22, 1f + add x22, x22, x5, lsl #2 + br x22 1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - mrs x20, dbgwvr15_el1 - mrs x19, dbgwvr14_el1 - mrs x18, dbgwvr13_el1 - mrs x17, dbgwvr12_el1 - mrs x16, dbgwvr11_el1 - mrs x15, dbgwvr10_el1 - mrs x14, dbgwvr9_el1 - mrs x13, dbgwvr8_el1 - mrs x12, dbgwvr7_el1 - mrs x11, dbgwvr6_el1 - mrs x10, dbgwvr5_el1 - mrs x9, dbgwvr4_el1 - mrs x8, dbgwvr3_el1 - mrs x7, dbgwvr2_el1 - mrs x6, dbgwvr1_el1 - mrs x5, dbgwvr0_el1 - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 - + mrs x21, \type\()15_el1 + mrs x20, \type\()14_el1 + mrs x19, \type\()13_el1 + mrs x18, \type\()12_el1 + mrs x17, \type\()11_el1 + mrs x16, \type\()10_el1 + mrs x15, \type\()9_el1 + mrs x14, \type\()8_el1 + mrs x13, \type\()7_el1 + mrs x12, \type\()6_el1 + mrs x11, \type\()5_el1 + mrs x10, \type\()4_el1 + mrs x9, \type\()3_el1 + mrs x8, \type\()2_el1 + mrs x7, \type\()1_el1 + mrs x6, \type\()0_el1 + + adr x22, 1f + add x22, x22, x5, lsl #2 + br x22 1: - str x20, [x3, #(15 * 8)] - str x19, [x3, #(14 * 8)] - str x18, [x3, #(13 * 8)] - str x17, [x3, #(12 * 8)] - str x16, [x3, #(11 * 8)] - str x15, [x3, #(10 * 8)] - str x14, [x3, #(9 * 8)] - str x13, [x3, #(8 * 8)] - str x12, [x3, #(7 * 8)] - str x11, [x3, #(6 * 8)] - str x10, [x3, #(5 * 8)] - str x9, [x3, #(4 * 8)] - str x8, [x3, #(3 * 8)] - str x7, [x3, #(2 * 8)] - str x6, [x3, #(1 * 8)] - str x5, [x3, #(0 * 8)] - - mrs x21, mdccint_el1 - str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] + str x21, [x4, #(15 * 8)] + str x20, [x4, #(14 * 8)] + str x19, [x4, #(13 * 8)] + str x18, [x4, #(12 * 8)] + str x17, [x4, #(11 * 8)] + str x16, [x4, #(10 * 8)] + str x15, [x4, #(9 * 8)] + str x14, [x4, #(8 * 8)] + str x13, [x4, #(7 * 8)] + str x12, [x4, #(6 * 8)] + str x11, [x4, #(5 * 8)] + str x10, [x4, #(4 * 8)] + str x9, [x4, #(3 * 8)] + str x8, [x4, #(2 * 8)] + str x7, [x4, #(1 * 8)] + str x6, [x4, #(0 * 8)] .endm .macro restore_sysregs @@ -465,195 +320,52 @@ msr mdscr_el1, x25 .endm -.macro restore_debug - // x2: base address for cpu context - // x3: tmp register - - mrs x26, id_aa64dfr0_el1 - ubfx x24, x26, #12, #4 // Extract BRPs - ubfx x25, x26, #20, #4 // Extract WRPs - mov w26, #15 - sub w24, w26, w24 // How many BPs to skip - sub w25, w26, w25 // How many WPs to skip +.macro restore_debug type + // x4: pointer to register set + // x5: number of registers to skip + // x6..x22 trashed - add x3, x2, #CPU_SYSREG_OFFSET(DBGBCR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - msr dbgbcr15_el1, x20 - msr dbgbcr14_el1, x19 - msr dbgbcr13_el1, x18 - msr dbgbcr12_el1, x17 - msr dbgbcr11_el1, x16 - msr dbgbcr10_el1, x15 - msr dbgbcr9_el1, x14 - msr dbgbcr8_el1, x13 - msr dbgbcr7_el1, x12 - msr dbgbcr6_el1, x11 - msr dbgbcr5_el1, x10 - msr dbgbcr4_el1, x9 - msr dbgbcr3_el1, x8 - msr dbgbcr2_el1, x7 - msr dbgbcr1_el1, x6 - msr dbgbcr0_el1, x5 - - add x3, x2, #CPU_SYSREG_OFFSET(DBGBVR0_EL1) - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x24, lsl #2 - br x26 + adr x22, 1f + add x22, x22, x5, lsl #2 + br x22 1: - msr dbgbvr15_el1, x20 - msr dbgbvr14_el1, x19 - msr dbgbvr13_el1, x18 - msr dbgbvr12_el1, x17 - msr dbgbvr11_el1, x16 - msr dbgbvr10_el1, x15 - msr dbgbvr9_el1, x14 - msr dbgbvr8_el1, x13 - msr dbgbvr7_el1, x12 - msr dbgbvr6_el1, x11 - msr dbgbvr5_el1, x10 - msr dbgbvr4_el1, x9 - msr dbgbvr3_el1, x8 - msr dbgbvr2_el1, x7 - msr dbgbvr1_el1, x6 - msr dbgbvr0_el1, x5 - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWCR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 + ldr x21, [x4, #(15 * 8)] + ldr x20, [x4, #(14 * 8)] + ldr x19, [x4, #(13 * 8)] + ldr x18, [x4, #(12 * 8)] + ldr x17, [x4, #(11 * 8)] + ldr x16, [x4, #(10 * 8)] + ldr x15, [x4, #(9 * 8)] + ldr x14, [x4, #(8 * 8)] + ldr x13, [x4, #(7 * 8)] + ldr x12, [x4, #(6 * 8)] + ldr x11, [x4, #(5 * 8)] + ldr x10, [x4, #(4 * 8)] + ldr x9, [x4, #(3 * 8)] + ldr x8, [x4, #(2 * 8)] + ldr x7, [x4, #(1 * 8)] + ldr x6, [x4, #(0 * 8)] + + adr x22, 1f + add x22, x22, x5, lsl #2 + br x22 1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - msr dbgwcr15_el1, x20 - msr dbgwcr14_el1, x19 - msr dbgwcr13_el1, x18 - msr dbgwcr12_el1, x17 - msr dbgwcr11_el1, x16 - msr dbgwcr10_el1, x15 - msr dbgwcr9_el1, x14 - msr dbgwcr8_el1, x13 - msr dbgwcr7_el1, x12 - msr dbgwcr6_el1, x11 - msr dbgwcr5_el1, x10 - msr dbgwcr4_el1, x9 - msr dbgwcr3_el1, x8 - msr dbgwcr2_el1, x7 - msr dbgwcr1_el1, x6 - msr dbgwcr0_el1, x5 - - add x3, x2, #CPU_SYSREG_OFFSET(DBGWVR0_EL1) - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - ldr x20, [x3, #(15 * 8)] - ldr x19, [x3, #(14 * 8)] - ldr x18, [x3, #(13 * 8)] - ldr x17, [x3, #(12 * 8)] - ldr x16, [x3, #(11 * 8)] - ldr x15, [x3, #(10 * 8)] - ldr x14, [x3, #(9 * 8)] - ldr x13, [x3, #(8 * 8)] - ldr x12, [x3, #(7 * 8)] - ldr x11, [x3, #(6 * 8)] - ldr x10, [x3, #(5 * 8)] - ldr x9, [x3, #(4 * 8)] - ldr x8, [x3, #(3 * 8)] - ldr x7, [x3, #(2 * 8)] - ldr x6, [x3, #(1 * 8)] - ldr x5, [x3, #(0 * 8)] - - adr x26, 1f - add x26, x26, x25, lsl #2 - br x26 -1: - msr dbgwvr15_el1, x20 - msr dbgwvr14_el1, x19 - msr dbgwvr13_el1, x18 - msr dbgwvr12_el1, x17 - msr dbgwvr11_el1, x16 - msr dbgwvr10_el1, x15 - msr dbgwvr9_el1, x14 - msr dbgwvr8_el1, x13 - msr dbgwvr7_el1, x12 - msr dbgwvr6_el1, x11 - msr dbgwvr5_el1, x10 - msr dbgwvr4_el1, x9 - msr dbgwvr3_el1, x8 - msr dbgwvr2_el1, x7 - msr dbgwvr1_el1, x6 - msr dbgwvr0_el1, x5 - - ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] - msr mdccint_el1, x21 + msr \type\()15_el1, x21 + msr \type\()14_el1, x20 + msr \type\()13_el1, x19 + msr \type\()12_el1, x18 + msr \type\()11_el1, x17 + msr \type\()10_el1, x16 + msr \type\()9_el1, x15 + msr \type\()8_el1, x14 + msr \type\()7_el1, x13 + msr \type\()6_el1, x12 + msr \type\()5_el1, x11 + msr \type\()4_el1, x10 + msr \type\()3_el1, x9 + msr \type\()2_el1, x8 + msr \type\()1_el1, x7 + msr \type\()0_el1, x6 .endm .macro skip_32bit_state tmp, target @@ -673,6 +385,14 @@ tbz \tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target .endm +/* + * Branch to target if CPTR_EL2.TFP bit is set (VFP/SIMD trapping enabled) + */ +.macro skip_fpsimd_state tmp, target + mrs \tmp, cptr_el2 + tbnz \tmp, #CPTR_EL2_TFP_SHIFT, \target +.endm + .macro compute_debug_state target // Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY // is set, we do a full save/restore cycle and disable trapping. @@ -711,20 +431,15 @@ add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2) mrs x4, dacr32_el2 mrs x5, ifsr32_el2 - mrs x6, fpexc32_el2 stp x4, x5, [x3] - str x6, [x3, #16] - skip_debug_state x8, 2f + skip_fpsimd_state x8, 2f + mrs x6, fpexc32_el2 + str x6, [x3, #16] +2: + skip_debug_state x8, 1f mrs x7, dbgvcr32_el2 str x7, [x3, #24] -2: - skip_tee_state x8, 1f - - add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1) - mrs x4, teecr32_el1 - mrs x5, teehbr32_el1 - stp x4, x5, [x3] 1: .endm @@ -741,51 +456,46 @@ add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2) ldp x4, x5, [x3] - ldr x6, [x3, #16] msr dacr32_el2, x4 msr ifsr32_el2, x5 - msr fpexc32_el2, x6 - skip_debug_state x8, 2f + skip_debug_state x8, 1f ldr x7, [x3, #24] msr dbgvcr32_el2, x7 -2: - skip_tee_state x8, 1f - - add x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1) - ldp x4, x5, [x3] - msr teecr32_el1, x4 - msr teehbr32_el1, x5 1: .endm .macro activate_traps ldr x2, [x0, #VCPU_HCR_EL2] + + /* + * We are about to set CPTR_EL2.TFP to trap all floating point + * register accesses to EL2, however, the ARM ARM clearly states that + * traps are only taken to EL2 if the operation would not otherwise + * trap to EL1. Therefore, always make sure that for 32-bit guests, + * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit. + */ + tbnz x2, #HCR_RW_SHIFT, 99f // open code skip_32bit_state + mov x3, #(1 << 30) + msr fpexc32_el2, x3 + isb +99: msr hcr_el2, x2 mov x2, #CPTR_EL2_TTA + orr x2, x2, #CPTR_EL2_TFP msr cptr_el2, x2 mov x2, #(1 << 15) // Trap CP15 Cr=15 msr hstr_el2, x2 - mrs x2, mdcr_el2 - and x2, x2, #MDCR_EL2_HPMN_MASK - orr x2, x2, #(MDCR_EL2_TPM | MDCR_EL2_TPMCR) - orr x2, x2, #(MDCR_EL2_TDRA | MDCR_EL2_TDOSA) - - // Check for KVM_ARM64_DEBUG_DIRTY, and set debug to trap - // if not dirty. - ldr x3, [x0, #VCPU_DEBUG_FLAGS] - tbnz x3, #KVM_ARM64_DEBUG_DIRTY_SHIFT, 1f - orr x2, x2, #MDCR_EL2_TDA -1: + // Monitor Debug Config - see kvm_arm_setup_debug() + ldr x2, [x0, #VCPU_MDCR_EL2] msr mdcr_el2, x2 .endm .macro deactivate_traps mov x2, #HCR_RW msr hcr_el2, x2 - msr cptr_el2, xzr msr hstr_el2, xzr mrs x2, mdcr_el2 @@ -808,10 +518,11 @@ * Call into the vgic backend for state saving */ .macro save_vgic_state - adr x24, __vgic_sr_vectors - ldr x24, [x24, VGIC_SAVE_FN] - kern_hyp_va x24 - blr x24 +alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF + bl __save_vgic_v2_state +alternative_else + bl __save_vgic_v3_state +alternative_endif mrs x24, hcr_el2 mov x25, #HCR_INT_OVERRIDE neg x25, x25 @@ -828,10 +539,11 @@ orr x24, x24, #HCR_INT_OVERRIDE orr x24, x24, x25 msr hcr_el2, x24 - adr x24, __vgic_sr_vectors - ldr x24, [x24, #VGIC_RESTORE_FN] - kern_hyp_va x24 - blr x24 +alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF + bl __restore_vgic_v2_state +alternative_else + bl __restore_vgic_v3_state +alternative_endif .endm .macro save_timer_state @@ -897,21 +609,101 @@ __restore_sysregs: restore_sysregs ret +/* Save debug state */ __save_debug: - save_debug + // x2: ptr to CPU context + // x3: ptr to debug reg struct + // x4/x5/x6-22/x24-26: trashed + + mrs x26, id_aa64dfr0_el1 + ubfx x24, x26, #12, #4 // Extract BRPs + ubfx x25, x26, #20, #4 // Extract WRPs + mov w26, #15 + sub w24, w26, w24 // How many BPs to skip + sub w25, w26, w25 // How many WPs to skip + + mov x5, x24 + add x4, x3, #DEBUG_BCR + save_debug dbgbcr + add x4, x3, #DEBUG_BVR + save_debug dbgbvr + + mov x5, x25 + add x4, x3, #DEBUG_WCR + save_debug dbgwcr + add x4, x3, #DEBUG_WVR + save_debug dbgwvr + + mrs x21, mdccint_el1 + str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] ret +/* Restore debug state */ __restore_debug: - restore_debug + // x2: ptr to CPU context + // x3: ptr to debug reg struct + // x4/x5/x6-22/x24-26: trashed + + mrs x26, id_aa64dfr0_el1 + ubfx x24, x26, #12, #4 // Extract BRPs + ubfx x25, x26, #20, #4 // Extract WRPs + mov w26, #15 + sub w24, w26, w24 // How many BPs to skip + sub w25, w26, w25 // How many WPs to skip + + mov x5, x24 + add x4, x3, #DEBUG_BCR + restore_debug dbgbcr + add x4, x3, #DEBUG_BVR + restore_debug dbgbvr + + mov x5, x25 + add x4, x3, #DEBUG_WCR + restore_debug dbgwcr + add x4, x3, #DEBUG_WVR + restore_debug dbgwvr + + ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] + msr mdccint_el1, x21 + ret __save_fpsimd: + skip_fpsimd_state x3, 1f save_fpsimd - ret +1: ret __restore_fpsimd: + skip_fpsimd_state x3, 1f restore_fpsimd - ret +1: ret + +switch_to_guest_fpsimd: + push x4, lr + + mrs x2, cptr_el2 + bic x2, x2, #CPTR_EL2_TFP + msr cptr_el2, x2 + isb + + mrs x0, tpidr_el2 + + ldr x2, [x0, #VCPU_HOST_CONTEXT] + kern_hyp_va x2 + bl __save_fpsimd + + add x2, x0, #VCPU_CONTEXT + bl __restore_fpsimd + + skip_32bit_state x3, 1f + ldr x4, [x2, #CPU_SYSREG_OFFSET(FPEXC32_EL2)] + msr fpexc32_el2, x4 +1: + pop x4, lr + pop x2, x3 + pop x0, x1 + + eret /* * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu); @@ -933,10 +725,10 @@ ENTRY(__kvm_vcpu_run) kern_hyp_va x2 save_host_regs - bl __save_fpsimd bl __save_sysregs compute_debug_state 1f + add x3, x0, #VCPU_HOST_DEBUG_STATE bl __save_debug 1: activate_traps @@ -952,9 +744,10 @@ ENTRY(__kvm_vcpu_run) // to Cortex-A57 erratum #852523. restore_guest_32bit_state bl __restore_sysregs - bl __restore_fpsimd skip_debug_state x3, 1f + ldr x3, [x0, #VCPU_DEBUG_PTR] + kern_hyp_va x3 bl __restore_debug 1: restore_guest_regs @@ -974,6 +767,8 @@ __kvm_vcpu_return: bl __save_sysregs skip_debug_state x3, 1f + ldr x3, [x0, #VCPU_DEBUG_PTR] + kern_hyp_va x3 bl __save_debug 1: save_guest_32bit_state @@ -990,12 +785,15 @@ __kvm_vcpu_return: bl __restore_sysregs bl __restore_fpsimd + /* Clear FPSIMD and Trace trapping */ + msr cptr_el2, xzr skip_debug_state x3, 1f // Clear the dirty flag for the next run, as all the state has // already been saved. Note that we nuke the whole 64bit word. // If we ever add more flags, we'll have to be more careful... str xzr, [x0, #VCPU_DEBUG_FLAGS] + add x3, x0, #VCPU_HOST_DEBUG_STATE bl __restore_debug 1: restore_host_regs @@ -1065,13 +863,11 @@ ENTRY(__kvm_flush_vm_context) ret ENDPROC(__kvm_flush_vm_context) - // struct vgic_sr_vectors __vgi_sr_vectors; - .align 3 -ENTRY(__vgic_sr_vectors) - .skip VGIC_SR_VECTOR_SZ -ENDPROC(__vgic_sr_vectors) - __kvm_hyp_panic: + // Stash PAR_EL1 before corrupting it in __restore_sysregs + mrs x0, par_el1 + push x0, xzr + // Guess the context by looking at VTTBR: // If zero, then we're already a host. // Otherwise restore a minimal host context before panicing. @@ -1088,6 +884,14 @@ __kvm_hyp_panic: bl __restore_sysregs + /* + * Make sure we have a valid host stack, and don't leave junk in the + * frame pointer that will give us a misleading host stack unwinding. + */ + ldr x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)] + msr sp_el1, x22 + mov x29, xzr + 1: adr x0, __hyp_panic_str adr x1, 2f ldp x2, x3, [x1] @@ -1098,7 +902,7 @@ __kvm_hyp_panic: mrs x3, esr_el2 mrs x4, far_el2 mrs x5, hpfar_el2 - mrs x6, par_el1 + pop x6, xzr // active context PAR_EL1 mrs x7, tpidr_el2 mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ @@ -1114,7 +918,7 @@ __kvm_hyp_panic: ENDPROC(__kvm_hyp_panic) __hyp_panic_str: - .ascii "HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0" + .ascii "HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0" .align 2 @@ -1204,15 +1008,26 @@ el1_trap: * x1: ESR * x2: ESR_EC */ + + /* Guest accessed VFP/SIMD registers, save host, restore Guest */ + cmp x2, #ESR_ELx_EC_FP_ASIMD + b.eq switch_to_guest_fpsimd + cmp x2, #ESR_ELx_EC_DABT_LOW mov x0, #ESR_ELx_EC_IABT_LOW ccmp x2, x0, #4, ne b.ne 1f // Not an abort we care about /* This is an abort. Check for permission fault */ +alternative_if_not ARM64_WORKAROUND_834220 and x2, x1, #ESR_ELx_FSC_TYPE cmp x2, #FSC_PERM b.ne 1f // Not a permission fault +alternative_else + nop // Use the permission fault path to + nop // check for a valid S1 translation, + nop // regardless of the ESR value. +alternative_endif /* * Check for Stage-1 page table walk, which is guaranteed @@ -1298,4 +1113,10 @@ ENTRY(__kvm_hyp_vector) ventry el1_error_invalid // Error 32-bit EL1 ENDPROC(__kvm_hyp_vector) + +ENTRY(__kvm_get_mdcr_el2) + mrs x0, mdcr_el2 + ret +ENDPROC(__kvm_get_mdcr_el2) + .popsection diff --git a/kernel/arch/arm64/kvm/inject_fault.c b/kernel/arch/arm64/kvm/inject_fault.c index 85c57158d..648112e90 100644 --- a/kernel/arch/arm64/kvm/inject_fault.c +++ b/kernel/arch/arm64/kvm/inject_fault.c @@ -48,7 +48,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) /* Note: These now point to the banked copies */ *vcpu_spsr(vcpu) = new_spsr_value; - *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; + *vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; /* Branch to exception vector */ if (sctlr & (1 << 13)) diff --git a/kernel/arch/arm64/kvm/reset.c b/kernel/arch/arm64/kvm/reset.c index 0b4326578..f34745cb3 100644 --- a/kernel/arch/arm64/kvm/reset.c +++ b/kernel/arch/arm64/kvm/reset.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -52,10 +53,16 @@ static bool cpu_has_32bit_el1(void) { u64 pfr0; - pfr0 = read_cpuid(ID_AA64PFR0_EL1); + pfr0 = read_system_reg(SYS_ID_AA64PFR0_EL1); return !!(pfr0 & 0x20); } +/** + * kvm_arch_dev_ioctl_check_extension + * + * We currently assume that the number of HW registers is uniform + * across all CPUs (see cpuinfo_sanity_check). + */ int kvm_arch_dev_ioctl_check_extension(long ext) { int r; @@ -64,6 +71,15 @@ int kvm_arch_dev_ioctl_check_extension(long ext) case KVM_CAP_ARM_EL1_32BIT: r = cpu_has_32bit_el1(); break; + case KVM_CAP_GUEST_DEBUG_HW_BPS: + r = get_num_brps(); + break; + case KVM_CAP_GUEST_DEBUG_HW_WPS: + r = get_num_wrps(); + break; + case KVM_CAP_SET_GUEST_DEBUG: + r = 1; + break; default: r = 0; } @@ -105,7 +121,5 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) kvm_reset_sys_regs(vcpu); /* Reset timer */ - kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq); - - return 0; + return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq); } diff --git a/kernel/arch/arm64/kvm/sys_regs.c b/kernel/arch/arm64/kvm/sys_regs.c index c370b4014..d2650e84f 100644 --- a/kernel/arch/arm64/kvm/sys_regs.c +++ b/kernel/arch/arm64/kvm/sys_regs.c @@ -38,6 +38,8 @@ #include "sys_regs.h" +#include "trace.h" + /* * All of this file is extremly similar to the ARM coproc.c, but the * types are different. My gut feeling is that it should be pretty @@ -76,7 +78,7 @@ static u32 get_ccsidr(u32 csselr) * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized). */ static bool access_dcsw(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (!p->is_write) @@ -92,21 +94,19 @@ static bool access_dcsw(struct kvm_vcpu *vcpu, * sys_regs and leave it in complete control of the caches. */ static bool access_vm_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { - unsigned long val; bool was_enabled = vcpu_has_cache_enabled(vcpu); BUG_ON(!p->is_write); - val = *vcpu_reg(vcpu, p->Rt); if (!p->is_aarch32) { - vcpu_sys_reg(vcpu, r->reg) = val; + vcpu_sys_reg(vcpu, r->reg) = p->regval; } else { if (!p->is_32bit) - vcpu_cp15_64_high(vcpu, r->reg) = val >> 32; - vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL; + vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval); + vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval); } kvm_toggle_cache(vcpu, was_enabled); @@ -120,22 +120,19 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, * for both AArch64 and AArch32 accesses. */ static bool access_gic_sgi(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { - u64 val; - if (!p->is_write) return read_from_write_only(vcpu, p); - val = *vcpu_reg(vcpu, p->Rt); - vgic_v3_dispatch_sgi(vcpu, val); + vgic_v3_dispatch_sgi(vcpu, p->regval); return true; } static bool trap_raz_wi(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) @@ -145,19 +142,19 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { return ignore_write(vcpu, p); } else { - *vcpu_reg(vcpu, p->Rt) = (1 << 3); + p->regval = (1 << 3); return true; } } static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { @@ -165,7 +162,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, } else { u32 val; asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val)); - *vcpu_reg(vcpu, p->Rt) = val; + p->regval = val; return true; } } @@ -198,19 +195,224 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu, * now use the debug registers. */ static bool trap_debug_regs(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { - vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt); + vcpu_sys_reg(vcpu, r->reg) = p->regval; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg); + p->regval = vcpu_sys_reg(vcpu, r->reg); + } + + trace_trap_reg(__func__, r->reg, p->is_write, p->regval); + + return true; +} + +/* + * reg_to_dbg/dbg_to_reg + * + * A 32 bit write to a debug register leave top bits alone + * A 32 bit read from a debug register only returns the bottom bits + * + * All writes will set the KVM_ARM64_DEBUG_DIRTY flag to ensure the + * hyp.S code switches between host and guest values in future. + */ +static inline void reg_to_dbg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + u64 *dbg_reg) +{ + u64 val = p->regval; + + if (p->is_32bit) { + val &= 0xffffffffUL; + val |= ((*dbg_reg >> 32) << 32); } + *dbg_reg = val; + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; +} + +static inline void dbg_to_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + u64 *dbg_reg) +{ + p->regval = *dbg_reg; + if (p->is_32bit) + p->regval &= 0xffffffffUL; +} + +static inline bool trap_bvr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) +{ + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + + if (p->is_write) + reg_to_dbg(vcpu, p, dbg_reg); + else + dbg_to_reg(vcpu, p, dbg_reg); + + trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + + return true; +} + +static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + + if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static inline void reset_bvr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; +} + +static inline bool trap_bcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) +{ + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + + if (p->is_write) + reg_to_dbg(vcpu, p, dbg_reg); + else + dbg_to_reg(vcpu, p, dbg_reg); + + trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + + return true; +} + +static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + + return 0; +} + +static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + + if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static inline void reset_bcr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; +} + +static inline bool trap_wvr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) +{ + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + + if (p->is_write) + reg_to_dbg(vcpu, p, dbg_reg); + else + dbg_to_reg(vcpu, p, dbg_reg); + + trace_trap_reg(__func__, rd->reg, p->is_write, + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); + return true; } +static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + + if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static inline void reset_wvr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; +} + +static inline bool trap_wcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) +{ + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + + if (p->is_write) + reg_to_dbg(vcpu, p, dbg_reg); + else + dbg_to_reg(vcpu, p, dbg_reg); + + trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + + return true; +} + +static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + + if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr) +{ + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + + if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) + return -EFAULT; + return 0; +} + +static inline void reset_wcr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) +{ + vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; +} + static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 amair; @@ -240,16 +442,16 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ /* DBGBVRn_EL1 */ \ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \ - trap_debug_regs, reset_val, (DBGBVR0_EL1 + (n)), 0 }, \ + trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \ /* DBGBCRn_EL1 */ \ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \ - trap_debug_regs, reset_val, (DBGBCR0_EL1 + (n)), 0 }, \ + trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \ /* DBGWVRn_EL1 */ \ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \ - trap_debug_regs, reset_val, (DBGWVR0_EL1 + (n)), 0 }, \ + trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \ /* DBGWCRn_EL1 */ \ { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \ - trap_debug_regs, reset_val, (DBGWCR0_EL1 + (n)), 0 } + trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr } /* * Architected system registers. @@ -329,13 +531,6 @@ static const struct sys_reg_desc sys_reg_descs[] = { { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110), trap_dbgauthstatus_el1 }, - /* TEECR32_EL1 */ - { Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000), - NULL, reset_val, TEECR32_EL1, 0 }, - /* TEEHBR32_EL1 */ - { Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000), - NULL, reset_val, TEEHBR32_EL1, 0 }, - /* MDCCSR_EL1 */ { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000), trap_raz_wi }, @@ -484,60 +679,89 @@ static const struct sys_reg_desc sys_reg_descs[] = { }; static bool trap_dbgidr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { return ignore_write(vcpu, p); } else { - u64 dfr = read_cpuid(ID_AA64DFR0_EL1); - u64 pfr = read_cpuid(ID_AA64PFR0_EL1); - u32 el3 = !!((pfr >> 12) & 0xf); - - *vcpu_reg(vcpu, p->Rt) = ((((dfr >> 20) & 0xf) << 28) | - (((dfr >> 12) & 0xf) << 24) | - (((dfr >> 28) & 0xf) << 20) | - (6 << 16) | (el3 << 14) | (el3 << 12)); + u64 dfr = read_system_reg(SYS_ID_AA64DFR0_EL1); + u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1); + u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT); + + p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) | + (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) | + (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) + | (6 << 16) | (el3 << 14) | (el3 << 12)); return true; } } static bool trap_debug32(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) { - vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt); + vcpu_cp14(vcpu, r->reg) = p->regval; vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } else { - *vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg); + p->regval = vcpu_cp14(vcpu, r->reg); } return true; } -#define DBG_BCR_BVR_WCR_WVR(n) \ - /* DBGBVRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_debug32, \ - NULL, (cp14_DBGBVR0 + (n) * 2) }, \ - /* DBGBCRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_debug32, \ - NULL, (cp14_DBGBCR0 + (n) * 2) }, \ - /* DBGWVRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_debug32, \ - NULL, (cp14_DBGWVR0 + (n) * 2) }, \ - /* DBGWCRn */ \ - { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_debug32, \ - NULL, (cp14_DBGWCR0 + (n) * 2) } - -#define DBGBXVR(n) \ - { Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_debug32, \ - NULL, cp14_DBGBXVR0 + n * 2 } +/* AArch32 debug register mappings + * + * AArch32 DBGBVRn is mapped to DBGBVRn_EL1[31:0] + * AArch32 DBGBXVRn is mapped to DBGBVRn_EL1[63:32] + * + * All control registers and watchpoint value registers are mapped to + * the lower 32 bits of their AArch64 equivalents. We share the trap + * handlers with the above AArch64 code which checks what mode the + * system is in. + */ + +static inline bool trap_xvr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) +{ + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + + if (p->is_write) { + u64 val = *dbg_reg; + + val &= 0xffffffffUL; + val |= p->regval << 32; + *dbg_reg = val; + + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + } else { + p->regval = *dbg_reg >> 32; + } + + trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + + return true; +} + +#define DBG_BCR_BVR_WCR_WVR(n) \ + /* DBGBVRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 4), trap_bvr, NULL, n }, \ + /* DBGBCRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 5), trap_bcr, NULL, n }, \ + /* DBGWVRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 6), trap_wvr, NULL, n }, \ + /* DBGWCRn */ \ + { Op1( 0), CRn( 0), CRm((n)), Op2( 7), trap_wcr, NULL, n } + +#define DBGBXVR(n) \ + { Op1( 0), CRn( 1), CRm((n)), Op2( 1), trap_xvr, NULL, n } /* * Trapped cp14 registers. We generally ignore most of the external * debug, on the principle that they don't really make sense to a - * guest. Revisit this one day, whould this principle change. + * guest. Revisit this one day, would this principle change. */ static const struct sys_reg_desc cp14_regs[] = { /* DBGIDR */ @@ -759,7 +983,7 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run) * Return 0 if the access has been handled, and -1 if not. */ static int emulate_cp(struct kvm_vcpu *vcpu, - const struct sys_reg_params *params, + struct sys_reg_params *params, const struct sys_reg_desc *table, size_t num) { @@ -830,12 +1054,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + int Rt = (hsr >> 5) & 0xf; int Rt2 = (hsr >> 10) & 0xf; params.is_aarch32 = true; params.is_32bit = false; params.CRm = (hsr >> 1) & 0xf; - params.Rt = (hsr >> 5) & 0xf; params.is_write = ((hsr & 1) == 0); params.Op0 = 0; @@ -844,15 +1068,12 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, params.CRn = 0; /* - * Massive hack here. Store Rt2 in the top 32bits so we only - * have one register to deal with. As we use the same trap + * Make a 64-bit value out of Rt and Rt2. As we use the same trap * backends between AArch32 and AArch64, we get away with it. */ if (params.is_write) { - u64 val = *vcpu_reg(vcpu, params.Rt); - val &= 0xffffffff; - val |= *vcpu_reg(vcpu, Rt2) << 32; - *vcpu_reg(vcpu, params.Rt) = val; + params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff; + params.regval |= vcpu_get_reg(vcpu, Rt2) << 32; } if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific)) @@ -863,11 +1084,10 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, unhandled_cp_access(vcpu, ¶ms); out: - /* Do the opposite hack for the read side */ + /* Split up the value between registers for the read side */ if (!params.is_write) { - u64 val = *vcpu_reg(vcpu, params.Rt); - val >>= 32; - *vcpu_reg(vcpu, Rt2) = val; + vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); + vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval)); } return 1; @@ -886,21 +1106,24 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, { struct sys_reg_params params; u32 hsr = kvm_vcpu_get_hsr(vcpu); + int Rt = (hsr >> 5) & 0xf; params.is_aarch32 = true; params.is_32bit = true; params.CRm = (hsr >> 1) & 0xf; - params.Rt = (hsr >> 5) & 0xf; + params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = ((hsr & 1) == 0); params.CRn = (hsr >> 10) & 0xf; params.Op0 = 0; params.Op1 = (hsr >> 14) & 0x7; params.Op2 = (hsr >> 17) & 0x7; - if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific)) - return 1; - if (!emulate_cp(vcpu, ¶ms, global, nr_global)) + if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific) || + !emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); return 1; + } unhandled_cp_access(vcpu, ¶ms); return 1; @@ -943,7 +1166,7 @@ int kvm_handle_cp14_32(struct kvm_vcpu *vcpu, struct kvm_run *run) } static int emulate_sys_reg(struct kvm_vcpu *vcpu, - const struct sys_reg_params *params) + struct sys_reg_params *params) { size_t num; const struct sys_reg_desc *table, *r; @@ -998,6 +1221,10 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) { struct sys_reg_params params; unsigned long esr = kvm_vcpu_get_hsr(vcpu); + int Rt = (esr >> 5) & 0x1f; + int ret; + + trace_kvm_handle_sys_reg(esr); params.is_aarch32 = false; params.is_32bit = false; @@ -1006,10 +1233,14 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run) params.CRn = (esr >> 10) & 0xf; params.CRm = (esr >> 1) & 0xf; params.Op2 = (esr >> 17) & 0x7; - params.Rt = (esr >> 5) & 0x1f; + params.regval = vcpu_get_reg(vcpu, Rt); params.is_write = !(esr & 1); - return emulate_sys_reg(vcpu, ¶ms); + ret = emulate_sys_reg(vcpu, ¶ms); + + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); + return ret; } /****************************************************************************** @@ -1303,6 +1534,9 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg if (!r) return get_invariant_sys_reg(reg->id, uaddr); + if (r->get_user) + return (r->get_user)(vcpu, r, reg, uaddr); + return reg_to_user(uaddr, &vcpu_sys_reg(vcpu, r->reg), reg->id); } @@ -1321,6 +1555,9 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg if (!r) return set_invariant_sys_reg(reg->id, uaddr); + if (r->set_user) + return (r->set_user)(vcpu, r, reg, uaddr); + return reg_from_user(&vcpu_sys_reg(vcpu, r->reg), uaddr, reg->id); } diff --git a/kernel/arch/arm64/kvm/sys_regs.h b/kernel/arch/arm64/kvm/sys_regs.h index d411e2514..dbbb01cfb 100644 --- a/kernel/arch/arm64/kvm/sys_regs.h +++ b/kernel/arch/arm64/kvm/sys_regs.h @@ -28,7 +28,7 @@ struct sys_reg_params { u8 CRn; u8 CRm; u8 Op2; - u8 Rt; + u64 regval; bool is_write; bool is_aarch32; bool is_32bit; /* Only valid if is_aarch32 is true */ @@ -44,7 +44,7 @@ struct sys_reg_desc { /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, - const struct sys_reg_params *, + struct sys_reg_params *, const struct sys_reg_desc *); /* Initialization for vcpu. */ @@ -55,6 +55,12 @@ struct sys_reg_desc { /* Value (usually reset value) */ u64 val; + + /* Custom get/set_user functions, fallback to generic if NULL */ + int (*get_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr); + int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, + const struct kvm_one_reg *reg, void __user *uaddr); }; static inline void print_sys_reg_instr(const struct sys_reg_params *p) @@ -71,9 +77,9 @@ static inline bool ignore_write(struct kvm_vcpu *vcpu, } static inline bool read_zero(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p) + struct sys_reg_params *p) { - *vcpu_reg(vcpu, p->Rt) = 0; + p->regval = 0; return true; } diff --git a/kernel/arch/arm64/kvm/sys_regs_generic_v8.c b/kernel/arch/arm64/kvm/sys_regs_generic_v8.c index 475fd2929..ed90578fa 100644 --- a/kernel/arch/arm64/kvm/sys_regs_generic_v8.c +++ b/kernel/arch/arm64/kvm/sys_regs_generic_v8.c @@ -31,13 +31,13 @@ #include "sys_regs.h" static bool access_actlr(struct kvm_vcpu *vcpu, - const struct sys_reg_params *p, + struct sys_reg_params *p, const struct sys_reg_desc *r) { if (p->is_write) return ignore_write(vcpu, p); - *vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1); + p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1); return true; } @@ -94,6 +94,8 @@ static int __init sys_reg_genericv8_init(void) &genericv8_target_table); kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA, &genericv8_target_table); + kvm_register_target_sys_reg_table(KVM_ARM_TARGET_GENERIC_V8, + &genericv8_target_table); return 0; } diff --git a/kernel/arch/arm64/kvm/trace.h b/kernel/arch/arm64/kvm/trace.h index 157416e96..7fb0008c4 100644 --- a/kernel/arch/arm64/kvm/trace.h +++ b/kernel/arch/arm64/kvm/trace.h @@ -44,6 +44,129 @@ TRACE_EVENT(kvm_hvc_arm64, __entry->vcpu_pc, __entry->r0, __entry->imm) ); +TRACE_EVENT(kvm_arm_setup_debug, + TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), + TP_ARGS(vcpu, guest_debug), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(__u32, guest_debug) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->guest_debug = guest_debug; + ), + + TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) +); + +TRACE_EVENT(kvm_arm_clear_debug, + TP_PROTO(__u32 guest_debug), + TP_ARGS(guest_debug), + + TP_STRUCT__entry( + __field(__u32, guest_debug) + ), + + TP_fast_assign( + __entry->guest_debug = guest_debug; + ), + + TP_printk("flags: 0x%08x", __entry->guest_debug) +); + +TRACE_EVENT(kvm_arm_set_dreg32, + TP_PROTO(const char *name, __u32 value), + TP_ARGS(name, value), + + TP_STRUCT__entry( + __field(const char *, name) + __field(__u32, value) + ), + + TP_fast_assign( + __entry->name = name; + __entry->value = value; + ), + + TP_printk("%s: 0x%08x", __entry->name, __entry->value) +); + +TRACE_EVENT(kvm_arm_set_regset, + TP_PROTO(const char *type, int len, __u64 *control, __u64 *value), + TP_ARGS(type, len, control, value), + TP_STRUCT__entry( + __field(const char *, name) + __field(int, len) + __array(u64, ctrls, 16) + __array(u64, values, 16) + ), + TP_fast_assign( + __entry->name = type; + __entry->len = len; + memcpy(__entry->ctrls, control, len << 3); + memcpy(__entry->values, value, len << 3); + ), + TP_printk("%d %s CTRL:%s VALUE:%s", __entry->len, __entry->name, + __print_array(__entry->ctrls, __entry->len, sizeof(__u64)), + __print_array(__entry->values, __entry->len, sizeof(__u64))) +); + +TRACE_EVENT(trap_reg, + TP_PROTO(const char *fn, int reg, bool is_write, u64 write_value), + TP_ARGS(fn, reg, is_write, write_value), + + TP_STRUCT__entry( + __field(const char *, fn) + __field(int, reg) + __field(bool, is_write) + __field(u64, write_value) + ), + + TP_fast_assign( + __entry->fn = fn; + __entry->reg = reg; + __entry->is_write = is_write; + __entry->write_value = write_value; + ), + + TP_printk("%s %s reg %d (0x%08llx)", __entry->fn, __entry->is_write?"write to":"read from", __entry->reg, __entry->write_value) +); + +TRACE_EVENT(kvm_handle_sys_reg, + TP_PROTO(unsigned long hsr), + TP_ARGS(hsr), + + TP_STRUCT__entry( + __field(unsigned long, hsr) + ), + + TP_fast_assign( + __entry->hsr = hsr; + ), + + TP_printk("HSR 0x%08lx", __entry->hsr) +); + +TRACE_EVENT(kvm_set_guest_debug, + TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), + TP_ARGS(vcpu, guest_debug), + + TP_STRUCT__entry( + __field(struct kvm_vcpu *, vcpu) + __field(__u32, guest_debug) + ), + + TP_fast_assign( + __entry->vcpu = vcpu; + __entry->guest_debug = guest_debug; + ), + + TP_printk("vcpu: %p, flags: 0x%08x", __entry->vcpu, __entry->guest_debug) +); + + #endif /* _TRACE_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/kernel/arch/arm64/kvm/vgic-v2-switch.S b/kernel/arch/arm64/kvm/vgic-v2-switch.S index f002fe1c3..3f000712a 100644 --- a/kernel/arch/arm64/kvm/vgic-v2-switch.S +++ b/kernel/arch/arm64/kvm/vgic-v2-switch.S @@ -47,7 +47,6 @@ __save_vgic_v2_state: add x3, x0, #VCPU_VGIC_CPU /* Save all interesting registers */ - ldr w4, [x2, #GICH_HCR] ldr w5, [x2, #GICH_VMCR] ldr w6, [x2, #GICH_MISR] ldr w7, [x2, #GICH_EISR0] @@ -55,7 +54,6 @@ __save_vgic_v2_state: ldr w9, [x2, #GICH_ELRSR0] ldr w10, [x2, #GICH_ELRSR1] ldr w11, [x2, #GICH_APR] -CPU_BE( rev w4, w4 ) CPU_BE( rev w5, w5 ) CPU_BE( rev w6, w6 ) CPU_BE( rev w7, w7 ) @@ -64,7 +62,6 @@ CPU_BE( rev w9, w9 ) CPU_BE( rev w10, w10 ) CPU_BE( rev w11, w11 ) - str w4, [x3, #VGIC_V2_CPU_HCR] str w5, [x3, #VGIC_V2_CPU_VMCR] str w6, [x3, #VGIC_V2_CPU_MISR] CPU_LE( str w7, [x3, #VGIC_V2_CPU_EISR] ) diff --git a/kernel/arch/arm64/kvm/vgic-v3-switch.S b/kernel/arch/arm64/kvm/vgic-v3-switch.S index 617a012a0..3c20730dd 100644 --- a/kernel/arch/arm64/kvm/vgic-v3-switch.S +++ b/kernel/arch/arm64/kvm/vgic-v3-switch.S @@ -48,13 +48,11 @@ dsb st // Save all interesting registers - mrs_s x4, ICH_HCR_EL2 mrs_s x5, ICH_VMCR_EL2 mrs_s x6, ICH_MISR_EL2 mrs_s x7, ICH_EISR_EL2 mrs_s x8, ICH_ELSR_EL2 - str w4, [x3, #VGIC_V3_CPU_HCR] str w5, [x3, #VGIC_V3_CPU_VMCR] str w6, [x3, #VGIC_V3_CPU_MISR] str w7, [x3, #VGIC_V3_CPU_EISR] diff --git a/kernel/arch/arm64/lib/Makefile b/kernel/arch/arm64/lib/Makefile index d98d3e398..1a811ecf7 100644 --- a/kernel/arch/arm64/lib/Makefile +++ b/kernel/arch/arm64/lib/Makefile @@ -3,3 +3,16 @@ lib-y := bitops.o clear_user.o delay.o copy_from_user.o \ clear_page.o memchr.o memcpy.o memmove.o memset.o \ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ strchr.o strrchr.o + +# Tell the compiler to treat all general purpose registers as +# callee-saved, which allows for efficient runtime patching of the bl +# instruction in the caller with an atomic instruction when supported by +# the CPU. Result and argument registers are handled correctly, based on +# the function prototype. +lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o +CFLAGS_atomic_ll_sc.o := -fcall-used-x0 -ffixed-x1 -ffixed-x2 \ + -ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6 \ + -ffixed-x7 -fcall-saved-x8 -fcall-saved-x9 \ + -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \ + -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \ + -fcall-saved-x16 -fcall-saved-x17 -fcall-saved-x18 diff --git a/kernel/arch/arm64/lib/atomic_ll_sc.c b/kernel/arch/arm64/lib/atomic_ll_sc.c new file mode 100644 index 000000000..b0c538b0d --- /dev/null +++ b/kernel/arch/arm64/lib/atomic_ll_sc.c @@ -0,0 +1,3 @@ +#include +#define __ARM64_IN_ATOMIC_IMPL +#include diff --git a/kernel/arch/arm64/lib/bitops.S b/kernel/arch/arm64/lib/bitops.S index 7dac371cc..43ac736ba 100644 --- a/kernel/arch/arm64/lib/bitops.S +++ b/kernel/arch/arm64/lib/bitops.S @@ -18,52 +18,59 @@ #include #include +#include /* * x0: bits 5:0 bit offset * bits 31:6 word offset * x1: address */ - .macro bitop, name, instr + .macro bitop, name, llsc, lse ENTRY( \name ) and w3, w0, #63 // Get bit offset eor w0, w0, w3 // Clear low bits mov x2, #1 add x1, x1, x0, lsr #3 // Get word offset +alt_lse " prfm pstl1strm, [x1]", "nop" lsl x3, x2, x3 // Create mask -1: ldxr x2, [x1] - \instr x2, x2, x3 - stxr w0, x2, [x1] - cbnz w0, 1b + +alt_lse "1: ldxr x2, [x1]", "\lse x3, [x1]" +alt_lse " \llsc x2, x2, x3", "nop" +alt_lse " stxr w0, x2, [x1]", "nop" +alt_lse " cbnz w0, 1b", "nop" + ret ENDPROC(\name ) .endm - .macro testop, name, instr + .macro testop, name, llsc, lse ENTRY( \name ) and w3, w0, #63 // Get bit offset eor w0, w0, w3 // Clear low bits mov x2, #1 add x1, x1, x0, lsr #3 // Get word offset +alt_lse " prfm pstl1strm, [x1]", "nop" lsl x4, x2, x3 // Create mask -1: ldxr x2, [x1] - lsr x0, x2, x3 // Save old value of bit - \instr x2, x2, x4 // toggle bit - stlxr w5, x2, [x1] - cbnz w5, 1b - dmb ish + +alt_lse "1: ldxr x2, [x1]", "\lse x4, x2, [x1]" + lsr x0, x2, x3 +alt_lse " \llsc x2, x2, x4", "nop" +alt_lse " stlxr w5, x2, [x1]", "nop" +alt_lse " cbnz w5, 1b", "nop" +alt_lse " dmb ish", "nop" + and x0, x0, #1 -3: ret + ret ENDPROC(\name ) .endm /* * Atomic bit operations. */ - bitop change_bit, eor - bitop clear_bit, bic - bitop set_bit, orr + bitop change_bit, eor, steor + bitop clear_bit, bic, stclr + bitop set_bit, orr, stset - testop test_and_change_bit, eor - testop test_and_clear_bit, bic - testop test_and_set_bit, orr + testop test_and_change_bit, eor, ldeoral + testop test_and_clear_bit, bic, ldclral + testop test_and_set_bit, orr, ldsetal diff --git a/kernel/arch/arm64/lib/clear_user.S b/kernel/arch/arm64/lib/clear_user.S index c17967fdf..a9723c71c 100644 --- a/kernel/arch/arm64/lib/clear_user.S +++ b/kernel/arch/arm64/lib/clear_user.S @@ -16,7 +16,11 @@ * along with this program. If not, see . */ #include + +#include #include +#include +#include .text @@ -29,6 +33,8 @@ * Alignment fixed up by hardware. */ ENTRY(__clear_user) +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) mov x2, x1 // save the size for fixup return subs x1, x1, #8 b.mi 2f @@ -48,6 +54,8 @@ USER(9f, strh wzr, [x0], #2 ) b.mi 5f USER(9f, strb wzr, [x0] ) 5: mov x0, #0 +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) ret ENDPROC(__clear_user) diff --git a/kernel/arch/arm64/lib/copy_from_user.S b/kernel/arch/arm64/lib/copy_from_user.S index 5e27add9d..4699cd74f 100644 --- a/kernel/arch/arm64/lib/copy_from_user.S +++ b/kernel/arch/arm64/lib/copy_from_user.S @@ -15,7 +15,12 @@ */ #include + +#include #include +#include +#include +#include /* * Copy from user space to a kernel buffer (alignment handled by the hardware) @@ -27,40 +32,58 @@ * Returns: * x0 - bytes not copied */ + + .macro ldrb1 ptr, regB, val + USER(9998f, ldrb \ptr, [\regB], \val) + .endm + + .macro strb1 ptr, regB, val + strb \ptr, [\regB], \val + .endm + + .macro ldrh1 ptr, regB, val + USER(9998f, ldrh \ptr, [\regB], \val) + .endm + + .macro strh1 ptr, regB, val + strh \ptr, [\regB], \val + .endm + + .macro ldr1 ptr, regB, val + USER(9998f, ldr \ptr, [\regB], \val) + .endm + + .macro str1 ptr, regB, val + str \ptr, [\regB], \val + .endm + + .macro ldp1 ptr, regB, regC, val + USER(9998f, ldp \ptr, \regB, [\regC], \val) + .endm + + .macro stp1 ptr, regB, regC, val + stp \ptr, \regB, [\regC], \val + .endm + +end .req x5 ENTRY(__copy_from_user) - add x4, x1, x2 // upper user buffer boundary - subs x2, x2, #8 - b.mi 2f -1: -USER(9f, ldr x3, [x1], #8 ) - subs x2, x2, #8 - str x3, [x0], #8 - b.pl 1b -2: adds x2, x2, #4 - b.mi 3f -USER(9f, ldr w3, [x1], #4 ) - sub x2, x2, #4 - str w3, [x0], #4 -3: adds x2, x2, #2 - b.mi 4f -USER(9f, ldrh w3, [x1], #2 ) - sub x2, x2, #2 - strh w3, [x0], #2 -4: adds x2, x2, #1 - b.mi 5f -USER(9f, ldrb w3, [x1] ) - strb w3, [x0] -5: mov x0, #0 +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) + add end, x0, x2 +#include "copy_template.S" +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) + mov x0, #0 // Nothing to copy ret ENDPROC(__copy_from_user) .section .fixup,"ax" .align 2 -9: sub x2, x4, x1 - mov x3, x2 -10: strb wzr, [x0], #1 // zero remaining buffer space - subs x3, x3, #1 - b.ne 10b - mov x0, x2 // bytes not copied +9998: + sub x0, end, dst +9999: + strb wzr, [dst], #1 // zero remaining buffer space + cmp dst, end + b.lo 9999b ret .previous diff --git a/kernel/arch/arm64/lib/copy_in_user.S b/kernel/arch/arm64/lib/copy_in_user.S index 84b6c9bb9..81c8fc93c 100644 --- a/kernel/arch/arm64/lib/copy_in_user.S +++ b/kernel/arch/arm64/lib/copy_in_user.S @@ -17,7 +17,12 @@ */ #include + +#include #include +#include +#include +#include /* * Copy from user space to user space (alignment handled by the hardware) @@ -29,35 +34,52 @@ * Returns: * x0 - bytes not copied */ + .macro ldrb1 ptr, regB, val + USER(9998f, ldrb \ptr, [\regB], \val) + .endm + + .macro strb1 ptr, regB, val + USER(9998f, strb \ptr, [\regB], \val) + .endm + + .macro ldrh1 ptr, regB, val + USER(9998f, ldrh \ptr, [\regB], \val) + .endm + + .macro strh1 ptr, regB, val + USER(9998f, strh \ptr, [\regB], \val) + .endm + + .macro ldr1 ptr, regB, val + USER(9998f, ldr \ptr, [\regB], \val) + .endm + + .macro str1 ptr, regB, val + USER(9998f, str \ptr, [\regB], \val) + .endm + + .macro ldp1 ptr, regB, regC, val + USER(9998f, ldp \ptr, \regB, [\regC], \val) + .endm + + .macro stp1 ptr, regB, regC, val + USER(9998f, stp \ptr, \regB, [\regC], \val) + .endm + +end .req x5 ENTRY(__copy_in_user) - add x4, x0, x2 // upper user buffer boundary - subs x2, x2, #8 - b.mi 2f -1: -USER(9f, ldr x3, [x1], #8 ) - subs x2, x2, #8 -USER(9f, str x3, [x0], #8 ) - b.pl 1b -2: adds x2, x2, #4 - b.mi 3f -USER(9f, ldr w3, [x1], #4 ) - sub x2, x2, #4 -USER(9f, str w3, [x0], #4 ) -3: adds x2, x2, #2 - b.mi 4f -USER(9f, ldrh w3, [x1], #2 ) - sub x2, x2, #2 -USER(9f, strh w3, [x0], #2 ) -4: adds x2, x2, #1 - b.mi 5f -USER(9f, ldrb w3, [x1] ) -USER(9f, strb w3, [x0] ) -5: mov x0, #0 +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) + add end, x0, x2 +#include "copy_template.S" +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) + mov x0, #0 ret ENDPROC(__copy_in_user) .section .fixup,"ax" .align 2 -9: sub x0, x4, x0 // bytes not copied +9998: sub x0, end, dst // bytes not copied ret .previous diff --git a/kernel/arch/arm64/lib/copy_template.S b/kernel/arch/arm64/lib/copy_template.S new file mode 100644 index 000000000..410fbdb81 --- /dev/null +++ b/kernel/arch/arm64/lib/copy_template.S @@ -0,0 +1,193 @@ +/* + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2013 Linaro. + * + * This code is based on glibc cortex strings work originally authored by Linaro + * and re-licensed under GPLv2 for the Linux kernel. The original code can + * be found @ + * + * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/ + * files/head:/src/aarch64/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ + + +/* + * Copy a buffer from src to dest (alignment handled by the hardware) + * + * Parameters: + * x0 - dest + * x1 - src + * x2 - n + * Returns: + * x0 - dest + */ +dstin .req x0 +src .req x1 +count .req x2 +tmp1 .req x3 +tmp1w .req w3 +tmp2 .req x4 +tmp2w .req w4 +dst .req x6 + +A_l .req x7 +A_h .req x8 +B_l .req x9 +B_h .req x10 +C_l .req x11 +C_h .req x12 +D_l .req x13 +D_h .req x14 + + mov dst, dstin + cmp count, #16 + /*When memory length is less than 16, the accessed are not aligned.*/ + b.lo .Ltiny15 + + neg tmp2, src + ands tmp2, tmp2, #15/* Bytes to reach alignment. */ + b.eq .LSrcAligned + sub count, count, tmp2 + /* + * Copy the leading memory data from src to dst in an increasing + * address order.By this way,the risk of overwritting the source + * memory data is eliminated when the distance between src and + * dst is less than 16. The memory accesses here are alignment. + */ + tbz tmp2, #0, 1f + ldrb1 tmp1w, src, #1 + strb1 tmp1w, dst, #1 +1: + tbz tmp2, #1, 2f + ldrh1 tmp1w, src, #2 + strh1 tmp1w, dst, #2 +2: + tbz tmp2, #2, 3f + ldr1 tmp1w, src, #4 + str1 tmp1w, dst, #4 +3: + tbz tmp2, #3, .LSrcAligned + ldr1 tmp1, src, #8 + str1 tmp1, dst, #8 + +.LSrcAligned: + cmp count, #64 + b.ge .Lcpy_over64 + /* + * Deal with small copies quickly by dropping straight into the + * exit block. + */ +.Ltail63: + /* + * Copy up to 48 bytes of data. At this point we only need the + * bottom 6 bits of count to be accurate. + */ + ands tmp1, count, #0x30 + b.eq .Ltiny15 + cmp tmp1w, #0x20 + b.eq 1f + b.lt 2f + ldp1 A_l, A_h, src, #16 + stp1 A_l, A_h, dst, #16 +1: + ldp1 A_l, A_h, src, #16 + stp1 A_l, A_h, dst, #16 +2: + ldp1 A_l, A_h, src, #16 + stp1 A_l, A_h, dst, #16 +.Ltiny15: + /* + * Prefer to break one ldp/stp into several load/store to access + * memory in an increasing address order,rather than to load/store 16 + * bytes from (src-16) to (dst-16) and to backward the src to aligned + * address,which way is used in original cortex memcpy. If keeping + * the original memcpy process here, memmove need to satisfy the + * precondition that src address is at least 16 bytes bigger than dst + * address,otherwise some source data will be overwritten when memove + * call memcpy directly. To make memmove simpler and decouple the + * memcpy's dependency on memmove, withdrew the original process. + */ + tbz count, #3, 1f + ldr1 tmp1, src, #8 + str1 tmp1, dst, #8 +1: + tbz count, #2, 2f + ldr1 tmp1w, src, #4 + str1 tmp1w, dst, #4 +2: + tbz count, #1, 3f + ldrh1 tmp1w, src, #2 + strh1 tmp1w, dst, #2 +3: + tbz count, #0, .Lexitfunc + ldrb1 tmp1w, src, #1 + strb1 tmp1w, dst, #1 + + b .Lexitfunc + +.Lcpy_over64: + subs count, count, #128 + b.ge .Lcpy_body_large + /* + * Less than 128 bytes to copy, so handle 64 here and then jump + * to the tail. + */ + ldp1 A_l, A_h, src, #16 + stp1 A_l, A_h, dst, #16 + ldp1 B_l, B_h, src, #16 + ldp1 C_l, C_h, src, #16 + stp1 B_l, B_h, dst, #16 + stp1 C_l, C_h, dst, #16 + ldp1 D_l, D_h, src, #16 + stp1 D_l, D_h, dst, #16 + + tst count, #0x3f + b.ne .Ltail63 + b .Lexitfunc + + /* + * Critical loop. Start at a new cache line boundary. Assuming + * 64 bytes per line this ensures the entire loop is in one line. + */ + .p2align L1_CACHE_SHIFT +.Lcpy_body_large: + /* pre-get 64 bytes data. */ + ldp1 A_l, A_h, src, #16 + ldp1 B_l, B_h, src, #16 + ldp1 C_l, C_h, src, #16 + ldp1 D_l, D_h, src, #16 +1: + /* + * interlace the load of next 64 bytes data block with store of the last + * loaded 64 bytes data. + */ + stp1 A_l, A_h, dst, #16 + ldp1 A_l, A_h, src, #16 + stp1 B_l, B_h, dst, #16 + ldp1 B_l, B_h, src, #16 + stp1 C_l, C_h, dst, #16 + ldp1 C_l, C_h, src, #16 + stp1 D_l, D_h, dst, #16 + ldp1 D_l, D_h, src, #16 + subs count, count, #64 + b.ge 1b + stp1 A_l, A_h, dst, #16 + stp1 B_l, B_h, dst, #16 + stp1 C_l, C_h, dst, #16 + stp1 D_l, D_h, dst, #16 + + tst count, #0x3f + b.ne .Ltail63 +.Lexitfunc: diff --git a/kernel/arch/arm64/lib/copy_to_user.S b/kernel/arch/arm64/lib/copy_to_user.S index a0aeeb9b7..7512bbbc0 100644 --- a/kernel/arch/arm64/lib/copy_to_user.S +++ b/kernel/arch/arm64/lib/copy_to_user.S @@ -15,7 +15,12 @@ */ #include + +#include #include +#include +#include +#include /* * Copy to user space from a kernel buffer (alignment handled by the hardware) @@ -27,35 +32,52 @@ * Returns: * x0 - bytes not copied */ + .macro ldrb1 ptr, regB, val + ldrb \ptr, [\regB], \val + .endm + + .macro strb1 ptr, regB, val + USER(9998f, strb \ptr, [\regB], \val) + .endm + + .macro ldrh1 ptr, regB, val + ldrh \ptr, [\regB], \val + .endm + + .macro strh1 ptr, regB, val + USER(9998f, strh \ptr, [\regB], \val) + .endm + + .macro ldr1 ptr, regB, val + ldr \ptr, [\regB], \val + .endm + + .macro str1 ptr, regB, val + USER(9998f, str \ptr, [\regB], \val) + .endm + + .macro ldp1 ptr, regB, regC, val + ldp \ptr, \regB, [\regC], \val + .endm + + .macro stp1 ptr, regB, regC, val + USER(9998f, stp \ptr, \regB, [\regC], \val) + .endm + +end .req x5 ENTRY(__copy_to_user) - add x4, x0, x2 // upper user buffer boundary - subs x2, x2, #8 - b.mi 2f -1: - ldr x3, [x1], #8 - subs x2, x2, #8 -USER(9f, str x3, [x0], #8 ) - b.pl 1b -2: adds x2, x2, #4 - b.mi 3f - ldr w3, [x1], #4 - sub x2, x2, #4 -USER(9f, str w3, [x0], #4 ) -3: adds x2, x2, #2 - b.mi 4f - ldrh w3, [x1], #2 - sub x2, x2, #2 -USER(9f, strh w3, [x0], #2 ) -4: adds x2, x2, #1 - b.mi 5f - ldrb w3, [x1] -USER(9f, strb w3, [x0] ) -5: mov x0, #0 +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) + add end, x0, x2 +#include "copy_template.S" +ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_HAS_PAN, \ + CONFIG_ARM64_PAN) + mov x0, #0 ret ENDPROC(__copy_to_user) .section .fixup,"ax" .align 2 -9: sub x0, x4, x0 // bytes not copied +9998: sub x0, end, dst // bytes not copied ret .previous diff --git a/kernel/arch/arm64/lib/memchr.S b/kernel/arch/arm64/lib/memchr.S index 8636b7549..4444c1d25 100644 --- a/kernel/arch/arm64/lib/memchr.S +++ b/kernel/arch/arm64/lib/memchr.S @@ -41,4 +41,4 @@ ENTRY(memchr) ret 2: mov x0, #0 ret -ENDPROC(memchr) +ENDPIPROC(memchr) diff --git a/kernel/arch/arm64/lib/memcmp.S b/kernel/arch/arm64/lib/memcmp.S index 6ea0776ba..ffbdec003 100644 --- a/kernel/arch/arm64/lib/memcmp.S +++ b/kernel/arch/arm64/lib/memcmp.S @@ -255,4 +255,4 @@ CPU_LE( rev data2, data2 ) .Lret0: mov result, #0 ret -ENDPROC(memcmp) +ENDPIPROC(memcmp) diff --git a/kernel/arch/arm64/lib/memcpy.S b/kernel/arch/arm64/lib/memcpy.S index 8a9a96d3d..676139377 100644 --- a/kernel/arch/arm64/lib/memcpy.S +++ b/kernel/arch/arm64/lib/memcpy.S @@ -36,166 +36,42 @@ * Returns: * x0 - dest */ -dstin .req x0 -src .req x1 -count .req x2 -tmp1 .req x3 -tmp1w .req w3 -tmp2 .req x4 -tmp2w .req w4 -tmp3 .req x5 -tmp3w .req w5 -dst .req x6 + .macro ldrb1 ptr, regB, val + ldrb \ptr, [\regB], \val + .endm -A_l .req x7 -A_h .req x8 -B_l .req x9 -B_h .req x10 -C_l .req x11 -C_h .req x12 -D_l .req x13 -D_h .req x14 + .macro strb1 ptr, regB, val + strb \ptr, [\regB], \val + .endm -ENTRY(memcpy) - mov dst, dstin - cmp count, #16 - /*When memory length is less than 16, the accessed are not aligned.*/ - b.lo .Ltiny15 + .macro ldrh1 ptr, regB, val + ldrh \ptr, [\regB], \val + .endm - neg tmp2, src - ands tmp2, tmp2, #15/* Bytes to reach alignment. */ - b.eq .LSrcAligned - sub count, count, tmp2 - /* - * Copy the leading memory data from src to dst in an increasing - * address order.By this way,the risk of overwritting the source - * memory data is eliminated when the distance between src and - * dst is less than 16. The memory accesses here are alignment. - */ - tbz tmp2, #0, 1f - ldrb tmp1w, [src], #1 - strb tmp1w, [dst], #1 -1: - tbz tmp2, #1, 2f - ldrh tmp1w, [src], #2 - strh tmp1w, [dst], #2 -2: - tbz tmp2, #2, 3f - ldr tmp1w, [src], #4 - str tmp1w, [dst], #4 -3: - tbz tmp2, #3, .LSrcAligned - ldr tmp1, [src],#8 - str tmp1, [dst],#8 + .macro strh1 ptr, regB, val + strh \ptr, [\regB], \val + .endm -.LSrcAligned: - cmp count, #64 - b.ge .Lcpy_over64 - /* - * Deal with small copies quickly by dropping straight into the - * exit block. - */ -.Ltail63: - /* - * Copy up to 48 bytes of data. At this point we only need the - * bottom 6 bits of count to be accurate. - */ - ands tmp1, count, #0x30 - b.eq .Ltiny15 - cmp tmp1w, #0x20 - b.eq 1f - b.lt 2f - ldp A_l, A_h, [src], #16 - stp A_l, A_h, [dst], #16 -1: - ldp A_l, A_h, [src], #16 - stp A_l, A_h, [dst], #16 -2: - ldp A_l, A_h, [src], #16 - stp A_l, A_h, [dst], #16 -.Ltiny15: - /* - * Prefer to break one ldp/stp into several load/store to access - * memory in an increasing address order,rather than to load/store 16 - * bytes from (src-16) to (dst-16) and to backward the src to aligned - * address,which way is used in original cortex memcpy. If keeping - * the original memcpy process here, memmove need to satisfy the - * precondition that src address is at least 16 bytes bigger than dst - * address,otherwise some source data will be overwritten when memove - * call memcpy directly. To make memmove simpler and decouple the - * memcpy's dependency on memmove, withdrew the original process. - */ - tbz count, #3, 1f - ldr tmp1, [src], #8 - str tmp1, [dst], #8 -1: - tbz count, #2, 2f - ldr tmp1w, [src], #4 - str tmp1w, [dst], #4 -2: - tbz count, #1, 3f - ldrh tmp1w, [src], #2 - strh tmp1w, [dst], #2 -3: - tbz count, #0, .Lexitfunc - ldrb tmp1w, [src] - strb tmp1w, [dst] + .macro ldr1 ptr, regB, val + ldr \ptr, [\regB], \val + .endm -.Lexitfunc: - ret + .macro str1 ptr, regB, val + str \ptr, [\regB], \val + .endm -.Lcpy_over64: - subs count, count, #128 - b.ge .Lcpy_body_large - /* - * Less than 128 bytes to copy, so handle 64 here and then jump - * to the tail. - */ - ldp A_l, A_h, [src],#16 - stp A_l, A_h, [dst],#16 - ldp B_l, B_h, [src],#16 - ldp C_l, C_h, [src],#16 - stp B_l, B_h, [dst],#16 - stp C_l, C_h, [dst],#16 - ldp D_l, D_h, [src],#16 - stp D_l, D_h, [dst],#16 + .macro ldp1 ptr, regB, regC, val + ldp \ptr, \regB, [\regC], \val + .endm - tst count, #0x3f - b.ne .Ltail63 - ret + .macro stp1 ptr, regB, regC, val + stp \ptr, \regB, [\regC], \val + .endm - /* - * Critical loop. Start at a new cache line boundary. Assuming - * 64 bytes per line this ensures the entire loop is in one line. - */ - .p2align L1_CACHE_SHIFT -.Lcpy_body_large: - /* pre-get 64 bytes data. */ - ldp A_l, A_h, [src],#16 - ldp B_l, B_h, [src],#16 - ldp C_l, C_h, [src],#16 - ldp D_l, D_h, [src],#16 -1: - /* - * interlace the load of next 64 bytes data block with store of the last - * loaded 64 bytes data. - */ - stp A_l, A_h, [dst],#16 - ldp A_l, A_h, [src],#16 - stp B_l, B_h, [dst],#16 - ldp B_l, B_h, [src],#16 - stp C_l, C_h, [dst],#16 - ldp C_l, C_h, [src],#16 - stp D_l, D_h, [dst],#16 - ldp D_l, D_h, [src],#16 - subs count, count, #64 - b.ge 1b - stp A_l, A_h, [dst],#16 - stp B_l, B_h, [dst],#16 - stp C_l, C_h, [dst],#16 - stp D_l, D_h, [dst],#16 - - tst count, #0x3f - b.ne .Ltail63 + .weak memcpy +ENTRY(__memcpy) +ENTRY(memcpy) +#include "copy_template.S" ret -ENDPROC(memcpy) +ENDPIPROC(memcpy) +ENDPROC(__memcpy) diff --git a/kernel/arch/arm64/lib/memmove.S b/kernel/arch/arm64/lib/memmove.S index 57b19ea2d..a5a445901 100644 --- a/kernel/arch/arm64/lib/memmove.S +++ b/kernel/arch/arm64/lib/memmove.S @@ -57,12 +57,14 @@ C_h .req x12 D_l .req x13 D_h .req x14 + .weak memmove +ENTRY(__memmove) ENTRY(memmove) cmp dstin, src - b.lo memcpy + b.lo __memcpy add tmp1, src, count cmp dstin, tmp1 - b.hs memcpy /* No overlap. */ + b.hs __memcpy /* No overlap. */ add dst, dstin, count add src, src, count @@ -194,4 +196,5 @@ ENTRY(memmove) tst count, #0x3f b.ne .Ltail63 ret -ENDPROC(memmove) +ENDPIPROC(memmove) +ENDPROC(__memmove) diff --git a/kernel/arch/arm64/lib/memset.S b/kernel/arch/arm64/lib/memset.S index 7c72dfd36..f2670a9f2 100644 --- a/kernel/arch/arm64/lib/memset.S +++ b/kernel/arch/arm64/lib/memset.S @@ -54,6 +54,8 @@ dst .req x8 tmp3w .req w9 tmp3 .req x9 + .weak memset +ENTRY(__memset) ENTRY(memset) mov dst, dstin /* Preserve return value. */ and A_lw, val, #255 @@ -213,4 +215,5 @@ ENTRY(memset) ands count, count, zva_bits_x b.ne .Ltail_maybe_long ret -ENDPROC(memset) +ENDPIPROC(memset) +ENDPROC(__memset) diff --git a/kernel/arch/arm64/lib/strcmp.S b/kernel/arch/arm64/lib/strcmp.S index 42f828b06..471fe6176 100644 --- a/kernel/arch/arm64/lib/strcmp.S +++ b/kernel/arch/arm64/lib/strcmp.S @@ -231,4 +231,4 @@ CPU_BE( orr syndrome, diff, has_nul ) lsr data1, data1, #56 sub result, data1, data2, lsr #56 ret -ENDPROC(strcmp) +ENDPIPROC(strcmp) diff --git a/kernel/arch/arm64/lib/strlen.S b/kernel/arch/arm64/lib/strlen.S index 987b68b9c..55ccc8e24 100644 --- a/kernel/arch/arm64/lib/strlen.S +++ b/kernel/arch/arm64/lib/strlen.S @@ -123,4 +123,4 @@ CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ csinv data1, data1, xzr, le csel data2, data2, data2a, le b .Lrealigned -ENDPROC(strlen) +ENDPIPROC(strlen) diff --git a/kernel/arch/arm64/lib/strncmp.S b/kernel/arch/arm64/lib/strncmp.S index 0224cf5a5..e26704476 100644 --- a/kernel/arch/arm64/lib/strncmp.S +++ b/kernel/arch/arm64/lib/strncmp.S @@ -307,4 +307,4 @@ CPU_BE( orr syndrome, diff, has_nul ) .Lret0: mov result, #0 ret -ENDPROC(strncmp) +ENDPIPROC(strncmp) diff --git a/kernel/arch/arm64/mm/Makefile b/kernel/arch/arm64/mm/Makefile index 773d37a14..57f57fde5 100644 --- a/kernel/arch/arm64/mm/Makefile +++ b/kernel/arch/arm64/mm/Makefile @@ -4,3 +4,6 @@ obj-y := dma-mapping.o extable.o fault.o init.o \ context.o proc.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_ARM64_PTDUMP) += dump.o + +obj-$(CONFIG_KASAN) += kasan_init.o +KASAN_SANITIZE_kasan_init.o := n diff --git a/kernel/arch/arm64/mm/cache.S b/kernel/arch/arm64/mm/cache.S index 2560e1e15..cfa44a6ad 100644 --- a/kernel/arch/arm64/mm/cache.S +++ b/kernel/arch/arm64/mm/cache.S @@ -22,83 +22,10 @@ #include #include #include -#include +#include #include "proc-macros.S" -/* - * __flush_dcache_all() - * - * Flush the whole D-cache. - * - * Corrupted registers: x0-x7, x9-x11 - */ -__flush_dcache_all: - dmb sy // ensure ordering with previous memory accesses - mrs x0, clidr_el1 // read clidr - and x3, x0, #0x7000000 // extract loc from clidr - lsr x3, x3, #23 // left align loc bit field - cbz x3, finished // if loc is 0, then no need to clean - mov x10, #0 // start clean at cache level 0 -loop1: - add x2, x10, x10, lsr #1 // work out 3x current cache level - lsr x1, x0, x2 // extract cache type bits from clidr - and x1, x1, #7 // mask of the bits for current cache only - cmp x1, #2 // see what cache we have at this level - b.lt skip // skip if no cache, or just i-cache - save_and_disable_irqs x9 // make CSSELR and CCSIDR access atomic - msr csselr_el1, x10 // select current cache level in csselr - isb // isb to sych the new cssr&csidr - mrs x1, ccsidr_el1 // read the new ccsidr - restore_irqs x9 - and x2, x1, #7 // extract the length of the cache lines - add x2, x2, #4 // add 4 (line length offset) - mov x4, #0x3ff - and x4, x4, x1, lsr #3 // find maximum number on the way size - clz w5, w4 // find bit position of way size increment - mov x7, #0x7fff - and x7, x7, x1, lsr #13 // extract max number of the index size -loop2: - mov x9, x4 // create working copy of max way size -loop3: - lsl x6, x9, x5 - orr x11, x10, x6 // factor way and cache number into x11 - lsl x6, x7, x2 - orr x11, x11, x6 // factor index number into x11 - dc cisw, x11 // clean & invalidate by set/way - subs x9, x9, #1 // decrement the way - b.ge loop3 - subs x7, x7, #1 // decrement the index - b.ge loop2 -skip: - add x10, x10, #2 // increment cache number - cmp x3, x10 - b.gt loop1 -finished: - mov x10, #0 // swith back to cache level 0 - msr csselr_el1, x10 // select current cache level in csselr - dsb sy - isb - ret -ENDPROC(__flush_dcache_all) - -/* - * flush_cache_all() - * - * Flush the entire cache system. The data cache flush is now achieved - * using atomic clean / invalidates working outwards from L1 cache. This - * is done using Set/Way based cache maintainance instructions. The - * instruction cache can still be invalidated back to the point of - * unification in a single instruction. - */ -ENTRY(flush_cache_all) - mov x12, lr - bl __flush_dcache_all - mov x0, #0 - ic ialluis // I+BTB cache invalidate - ret x12 -ENDPROC(flush_cache_all) - /* * flush_icache_range(start,end) * @@ -171,7 +98,7 @@ ENTRY(__flush_dcache_area) b.lo 1b dsb sy ret -ENDPROC(__flush_dcache_area) +ENDPIPROC(__flush_dcache_area) /* * __inval_cache_range(start, end) @@ -204,7 +131,7 @@ __dma_inv_range: b.lo 2b dsb sy ret -ENDPROC(__inval_cache_range) +ENDPIPROC(__inval_cache_range) ENDPROC(__dma_inv_range) /* @@ -216,7 +143,12 @@ __dma_clean_range: dcache_line_size x2, x3 sub x3, x2, #1 bic x0, x0, x3 -1: alternative_insn "dc cvac, x0", "dc civac, x0", ARM64_WORKAROUND_CLEAN_CACHE +1: +alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE + dc cvac, x0 +alternative_else + dc civac, x0 +alternative_endif add x0, x0, x2 cmp x0, x1 b.lo 1b @@ -239,7 +171,7 @@ ENTRY(__dma_flush_range) b.lo 1b dsb sy ret -ENDPROC(__dma_flush_range) +ENDPIPROC(__dma_flush_range) /* * __dma_map_area(start, size, dir) @@ -252,7 +184,7 @@ ENTRY(__dma_map_area) cmp w2, #DMA_FROM_DEVICE b.eq __dma_inv_range b __dma_clean_range -ENDPROC(__dma_map_area) +ENDPIPROC(__dma_map_area) /* * __dma_unmap_area(start, size, dir) @@ -265,4 +197,4 @@ ENTRY(__dma_unmap_area) cmp w2, #DMA_TO_DEVICE b.ne __dma_inv_range ret -ENDPROC(__dma_unmap_area) +ENDPIPROC(__dma_unmap_area) diff --git a/kernel/arch/arm64/mm/context.c b/kernel/arch/arm64/mm/context.c index 76c1e6cd3..e87f53ff5 100644 --- a/kernel/arch/arm64/mm/context.c +++ b/kernel/arch/arm64/mm/context.c @@ -17,151 +17,199 @@ * along with this program. If not, see . */ -#include +#include #include +#include #include -#include -#include +#include #include #include -#include - -#define asid_bits(reg) \ - (((read_cpuid(ID_AA64MMFR0_EL1) & 0xf0) >> 2) + 8) - -#define ASID_FIRST_VERSION (1 << MAX_ASID_BITS) +static u32 asid_bits; static DEFINE_RAW_SPINLOCK(cpu_asid_lock); -unsigned int cpu_last_asid = ASID_FIRST_VERSION; -/* - * We fork()ed a process, and we need a new context for the child to run in. - */ -void __init_new_context(struct task_struct *tsk, struct mm_struct *mm) -{ - mm->context.id = 0; - raw_spin_lock_init(&mm->context.id_lock); -} +static atomic64_t asid_generation; +static unsigned long *asid_map; -static void flush_context(void) -{ - /* set the reserved TTBR0 before flushing the TLB */ - cpu_set_reserved_ttbr0(); - flush_tlb_all(); - if (icache_is_aivivt()) - __flush_icache_all(); -} +static DEFINE_PER_CPU(atomic64_t, active_asids); +static DEFINE_PER_CPU(u64, reserved_asids); +static cpumask_t tlb_flush_pending; -#ifdef CONFIG_SMP +#define ASID_MASK (~GENMASK(asid_bits - 1, 0)) +#define ASID_FIRST_VERSION (1UL << asid_bits) +#define NUM_USER_ASIDS ASID_FIRST_VERSION -static void set_mm_context(struct mm_struct *mm, unsigned int asid) +static void flush_context(unsigned int cpu) { - unsigned long flags; + int i; + u64 asid; + + /* Update the list of reserved ASIDs and the ASID bitmap. */ + bitmap_clear(asid_map, 0, NUM_USER_ASIDS); /* - * Locking needed for multi-threaded applications where the same - * mm->context.id could be set from different CPUs during the - * broadcast. This function is also called via IPI so the - * mm->context.id_lock has to be IRQ-safe. + * Ensure the generation bump is observed before we xchg the + * active_asids. */ - raw_spin_lock_irqsave(&mm->context.id_lock, flags); - if (likely((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) { + smp_wmb(); + + for_each_possible_cpu(i) { + asid = atomic64_xchg_relaxed(&per_cpu(active_asids, i), 0); /* - * Old version of ASID found. Set the new one and reset - * mm_cpumask(mm). + * If this CPU has already been through a + * rollover, but hasn't run another task in + * the meantime, we must preserve its reserved + * ASID, as this is the only trace we have of + * the process it is still running. */ - mm->context.id = asid; - cpumask_clear(mm_cpumask(mm)); + if (asid == 0) + asid = per_cpu(reserved_asids, i); + __set_bit(asid & ~ASID_MASK, asid_map); + per_cpu(reserved_asids, i) = asid; } - raw_spin_unlock_irqrestore(&mm->context.id_lock, flags); - /* - * Set the mm_cpumask(mm) bit for the current CPU. - */ - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); + /* Queue a TLB invalidate and flush the I-cache if necessary. */ + cpumask_setall(&tlb_flush_pending); + + if (icache_is_aivivt()) + __flush_icache_all(); } -/* - * Reset the ASID on the current CPU. This function call is broadcast from the - * CPU handling the ASID rollover and holding cpu_asid_lock. - */ -static void reset_context(void *info) +static bool check_update_reserved_asid(u64 asid, u64 newasid) { - unsigned int asid; - unsigned int cpu = smp_processor_id(); - struct mm_struct *mm = current->active_mm; + int cpu; + bool hit = false; /* - * current->active_mm could be init_mm for the idle thread immediately - * after secondary CPU boot or hotplug. TTBR0_EL1 is already set to - * the reserved value, so no need to reset any context. + * Iterate over the set of reserved ASIDs looking for a match. + * If we find one, then we can update our mm to use newasid + * (i.e. the same ASID in the current generation) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old ASID are updated to reflect the mm. Failure to do + * so could result in us missing the reserved ASID in a future + * generation. */ - if (mm == &init_mm) - return; - - smp_rmb(); - asid = cpu_last_asid + cpu; - - flush_context(); - set_mm_context(mm, asid); + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_asids, cpu) == asid) { + hit = true; + per_cpu(reserved_asids, cpu) = newasid; + } + } - /* set the new ASID */ - cpu_switch_mm(mm->pgd, mm); + return hit; } -#else - -static inline void set_mm_context(struct mm_struct *mm, unsigned int asid) +static u64 new_context(struct mm_struct *mm, unsigned int cpu) { - mm->context.id = asid; - cpumask_copy(mm_cpumask(mm), cpumask_of(smp_processor_id())); -} + static u32 cur_idx = 1; + u64 asid = atomic64_read(&mm->context.id); + u64 generation = atomic64_read(&asid_generation); -#endif + if (asid != 0) { + u64 newasid = generation | (asid & ~ASID_MASK); -void __new_context(struct mm_struct *mm) -{ - unsigned int asid; - unsigned int bits = asid_bits(); + /* + * If our current ASID was active during a rollover, we + * can continue to use it and this was just a false alarm. + */ + if (check_update_reserved_asid(asid, newasid)) + return newasid; - raw_spin_lock(&cpu_asid_lock); -#ifdef CONFIG_SMP - /* - * Check the ASID again, in case the change was broadcast from another - * CPU before we acquired the lock. - */ - if (!unlikely((mm->context.id ^ cpu_last_asid) >> MAX_ASID_BITS)) { - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - raw_spin_unlock(&cpu_asid_lock); - return; + /* + * We had a valid ASID in a previous life, so try to re-use + * it if possible. + */ + asid &= ~ASID_MASK; + if (!__test_and_set_bit(asid, asid_map)) + return newasid; } -#endif + /* - * At this point, it is guaranteed that the current mm (with an old - * ASID) isn't active on any other CPU since the ASIDs are changed - * simultaneously via IPI. + * Allocate a free ASID. If we can't find one, take a note of the + * currently active ASIDs and mark the TLBs as requiring flushes. + * We always count from ASID #1, as we use ASID #0 when setting a + * reserved TTBR0 for the init_mm. */ - asid = ++cpu_last_asid; + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, cur_idx); + if (asid != NUM_USER_ASIDS) + goto set_asid; + + /* We're out of ASIDs, so increment the global generation count */ + generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION, + &asid_generation); + flush_context(cpu); + + /* We have at least 1 ASID per CPU, so this will always succeed */ + asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1); + +set_asid: + __set_bit(asid, asid_map); + cur_idx = asid; + return asid | generation; +} + +void check_and_switch_context(struct mm_struct *mm, unsigned int cpu) +{ + unsigned long flags; + u64 asid; + + asid = atomic64_read(&mm->context.id); /* - * If we've used up all our ASIDs, we need to start a new version and - * flush the TLB. + * The memory ordering here is subtle. We rely on the control + * dependency between the generation read and the update of + * active_asids to ensure that we are synchronised with a + * parallel rollover (i.e. this pairs with the smp_wmb() in + * flush_context). */ - if (unlikely((asid & ((1 << bits) - 1)) == 0)) { - /* increment the ASID version */ - cpu_last_asid += (1 << MAX_ASID_BITS) - (1 << bits); - if (cpu_last_asid == 0) - cpu_last_asid = ASID_FIRST_VERSION; - asid = cpu_last_asid + smp_processor_id(); - flush_context(); -#ifdef CONFIG_SMP - smp_wmb(); - smp_call_function(reset_context, NULL, 1); -#endif - cpu_last_asid += NR_CPUS - 1; + if (!((asid ^ atomic64_read(&asid_generation)) >> asid_bits) + && atomic64_xchg_relaxed(&per_cpu(active_asids, cpu), asid)) + goto switch_mm_fastpath; + + raw_spin_lock_irqsave(&cpu_asid_lock, flags); + /* Check that our ASID belongs to the current generation. */ + asid = atomic64_read(&mm->context.id); + if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) { + asid = new_context(mm, cpu); + atomic64_set(&mm->context.id, asid); + } + + if (cpumask_test_and_clear_cpu(cpu, &tlb_flush_pending)) + local_flush_tlb_all(); + + atomic64_set(&per_cpu(active_asids, cpu), asid); + raw_spin_unlock_irqrestore(&cpu_asid_lock, flags); + +switch_mm_fastpath: + cpu_switch_mm(mm->pgd, mm); +} + +static int asids_init(void) +{ + int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4); + + switch (fld) { + default: + pr_warn("Unknown ASID size (%d); assuming 8-bit\n", fld); + /* Fallthrough */ + case 0: + asid_bits = 8; + break; + case 2: + asid_bits = 16; } - set_mm_context(mm, asid); - raw_spin_unlock(&cpu_asid_lock); + /* If we end up with more CPUs than ASIDs, expect things to crash */ + WARN_ON(NUM_USER_ASIDS < num_possible_cpus()); + atomic64_set(&asid_generation, ASID_FIRST_VERSION); + asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map), + GFP_KERNEL); + if (!asid_map) + panic("Failed to allocate bitmap for %lu ASIDs\n", + NUM_USER_ASIDS); + + pr_info("ASID allocator initialised with %lu entries\n", NUM_USER_ASIDS); + return 0; } +early_initcall(asids_init); diff --git a/kernel/arch/arm64/mm/dma-mapping.c b/kernel/arch/arm64/mm/dma-mapping.c index b0bd4e5fd..354144e33 100644 --- a/kernel/arch/arm64/mm/dma-mapping.c +++ b/kernel/arch/arm64/mm/dma-mapping.c @@ -18,6 +18,7 @@ */ #include +#include #include #include #include @@ -28,9 +29,6 @@ #include -struct dma_map_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, bool coherent) { @@ -100,7 +98,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) { + if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) { struct page *page; void *addr; @@ -144,10 +142,11 @@ static void *__dma_alloc(struct device *dev, size_t size, struct page *page; void *ptr, *coherent_ptr; bool coherent = is_device_dma_coherent(dev); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false); size = PAGE_ALIGN(size); - if (!coherent && !(flags & __GFP_WAIT)) { + if (!coherent && !gfpflags_allow_blocking(flags)) { struct page *page = NULL; void *addr = __alloc_from_pool(size, &page, flags); @@ -171,9 +170,7 @@ static void *__dma_alloc(struct device *dev, size_t size, /* create a coherent mapping */ page = virt_to_page(ptr); coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - __get_dma_pgprot(attrs, - __pgprot(PROT_NORMAL_NC), false), - NULL); + prot, NULL); if (!coherent_ptr) goto no_map; @@ -303,9 +300,10 @@ static void __swiotlb_sync_sg_for_device(struct device *dev, sg->length, dir); } -/* vma->vm_page_prot must be set appropriately before calling this function */ -static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) +static int __swiotlb_mmap(struct device *dev, + struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) { int ret = -ENXIO; unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> @@ -314,6 +312,9 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, + is_device_dma_coherent(dev)); + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) return ret; @@ -327,20 +328,24 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } -static int __swiotlb_mmap(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) +static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t handle, size_t size, + struct dma_attrs *attrs) { - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, - is_device_dma_coherent(dev)); - return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); + int ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + + if (!ret) + sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)), + PAGE_ALIGN(size), 0); + + return ret; } static struct dma_map_ops swiotlb_dma_ops = { .alloc = __dma_alloc, .free = __dma_free, .mmap = __swiotlb_mmap, + .get_sgtable = __swiotlb_get_sgtable, .map_page = __swiotlb_map_page, .unmap_page = __swiotlb_unmap_page, .map_sg = __swiotlb_map_sg_attrs, @@ -414,15 +419,101 @@ out: return -ENOMEM; } -static int __init arm64_dma_init(void) +/******************************************** + * The following APIs are for dummy DMA ops * + ********************************************/ + +static void *__dummy_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) { - int ret; + return NULL; +} - dma_ops = &swiotlb_dma_ops; +static void __dummy_free(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ +} - ret = atomic_pool_init(); +static int __dummy_mmap(struct device *dev, + struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) +{ + return -ENXIO; +} - return ret; +static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return DMA_ERROR_CODE; +} + +static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ +} + +static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return 0; +} + +static void __dummy_unmap_sg(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ +} + +static void __dummy_sync_single(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ +} + +static void __dummy_sync_sg(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ +} + +static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr) +{ + return 1; +} + +static int __dummy_dma_supported(struct device *hwdev, u64 mask) +{ + return 0; +} + +struct dma_map_ops dummy_dma_ops = { + .alloc = __dummy_alloc, + .free = __dummy_free, + .mmap = __dummy_mmap, + .map_page = __dummy_map_page, + .unmap_page = __dummy_unmap_page, + .map_sg = __dummy_map_sg, + .unmap_sg = __dummy_unmap_sg, + .sync_single_for_cpu = __dummy_sync_single, + .sync_single_for_device = __dummy_sync_single, + .sync_sg_for_cpu = __dummy_sync_sg, + .sync_sg_for_device = __dummy_sync_sg, + .mapping_error = __dummy_mapping_error, + .dma_supported = __dummy_dma_supported, +}; +EXPORT_SYMBOL(dummy_dma_ops); + +static int __init arm64_dma_init(void) +{ + return atomic_pool_init(); } arch_initcall(arm64_dma_init); @@ -434,3 +525,471 @@ static int __init dma_debug_do_init(void) return 0; } fs_initcall(dma_debug_do_init); + + +#ifdef CONFIG_IOMMU_DMA +#include +#include +#include + +/* Thankfully, all cache ops are by VA so we can ignore phys here */ +static void flush_page(struct device *dev, const void *virt, phys_addr_t phys) +{ + __dma_flush_range(virt, virt + PAGE_SIZE); +} + +static void *__iommu_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, + struct dma_attrs *attrs) +{ + bool coherent = is_device_dma_coherent(dev); + int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent); + size_t iosize = size; + void *addr; + + if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) + return NULL; + + size = PAGE_ALIGN(size); + + /* + * Some drivers rely on this, and we probably don't want the + * possibility of stale kernel data being read by devices anyway. + */ + gfp |= __GFP_ZERO; + + if (gfpflags_allow_blocking(gfp)) { + struct page **pages; + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); + + pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle, + flush_page); + if (!pages) + return NULL; + + addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, + __builtin_return_address(0)); + if (!addr) + iommu_dma_free(dev, pages, iosize, handle); + } else { + struct page *page; + /* + * In atomic context we can't remap anything, so we'll only + * get the virtually contiguous buffer we need by way of a + * physically contiguous allocation. + */ + if (coherent) { + page = alloc_pages(gfp, get_order(size)); + addr = page ? page_address(page) : NULL; + } else { + addr = __alloc_from_pool(size, &page, gfp); + } + if (!addr) + return NULL; + + *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); + if (iommu_dma_mapping_error(dev, *handle)) { + if (coherent) + __free_pages(page, get_order(size)); + else + __free_from_pool(addr, size); + addr = NULL; + } + } + return addr; +} + +static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) +{ + size_t iosize = size; + + size = PAGE_ALIGN(size); + /* + * @cpu_addr will be one of 3 things depending on how it was allocated: + * - A remapped array of pages from iommu_dma_alloc(), for all + * non-atomic allocations. + * - A non-cacheable alias from the atomic pool, for atomic + * allocations by non-coherent devices. + * - A normal lowmem address, for atomic allocations by + * coherent devices. + * Hence how dodgy the below logic looks... + */ + if (__in_atomic_pool(cpu_addr, size)) { + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); + __free_from_pool(cpu_addr, size); + } else if (is_vmalloc_addr(cpu_addr)){ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (WARN_ON(!area || !area->pages)) + return; + iommu_dma_free(dev, area->pages, iosize, &handle); + dma_common_free_remap(cpu_addr, size, VM_USERMAP); + } else { + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); + __free_pages(virt_to_page(cpu_addr), get_order(size)); + } +} + +static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) +{ + struct vm_struct *area; + int ret; + + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, + is_device_dma_coherent(dev)); + + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + area = find_vm_area(cpu_addr); + if (WARN_ON(!area || !area->pages)) + return -ENXIO; + + return iommu_dma_mmap(area->pages, size, vma); +} + +static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size, struct dma_attrs *attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct vm_struct *area = find_vm_area(cpu_addr); + + if (WARN_ON(!area || !area->pages)) + return -ENXIO; + + return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size, + GFP_KERNEL); +} + +static void __iommu_sync_single_for_cpu(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ + phys_addr_t phys; + + if (is_device_dma_coherent(dev)) + return; + + phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr); + __dma_unmap_area(phys_to_virt(phys), size, dir); +} + +static void __iommu_sync_single_for_device(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ + phys_addr_t phys; + + if (is_device_dma_coherent(dev)) + return; + + phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr); + __dma_map_area(phys_to_virt(phys), size, dir); +} + +static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + bool coherent = is_device_dma_coherent(dev); + int prot = dma_direction_to_prot(dir, coherent); + dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); + + if (!iommu_dma_mapping_error(dev, dev_addr) && + !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_single_for_device(dev, dev_addr, size, dir); + + return dev_addr; +} + +static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_single_for_cpu(dev, dev_addr, size, dir); + + iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs); +} + +static void __iommu_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + if (is_device_dma_coherent(dev)) + return; + + for_each_sg(sgl, sg, nelems, i) + __dma_unmap_area(sg_virt(sg), sg->length, dir); +} + +static void __iommu_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + if (is_device_dma_coherent(dev)) + return; + + for_each_sg(sgl, sg, nelems, i) + __dma_map_area(sg_virt(sg), sg->length, dir); +} + +static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + bool coherent = is_device_dma_coherent(dev); + + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_sg_for_device(dev, sgl, nelems, dir); + + return iommu_dma_map_sg(dev, sgl, nelems, + dma_direction_to_prot(dir, coherent)); +} + +static void __iommu_unmap_sg_attrs(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir); + + iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs); +} + +static struct dma_map_ops iommu_dma_ops = { + .alloc = __iommu_alloc_attrs, + .free = __iommu_free_attrs, + .mmap = __iommu_mmap_attrs, + .get_sgtable = __iommu_get_sgtable, + .map_page = __iommu_map_page, + .unmap_page = __iommu_unmap_page, + .map_sg = __iommu_map_sg_attrs, + .unmap_sg = __iommu_unmap_sg_attrs, + .sync_single_for_cpu = __iommu_sync_single_for_cpu, + .sync_single_for_device = __iommu_sync_single_for_device, + .sync_sg_for_cpu = __iommu_sync_sg_for_cpu, + .sync_sg_for_device = __iommu_sync_sg_for_device, + .dma_supported = iommu_dma_supported, + .mapping_error = iommu_dma_mapping_error, +}; + +/* + * TODO: Right now __iommu_setup_dma_ops() gets called too early to do + * everything it needs to - the device is only partially created and the + * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we + * need this delayed attachment dance. Once IOMMU probe ordering is sorted + * to move the arch_setup_dma_ops() call later, all the notifier bits below + * become unnecessary, and will go away. + */ +struct iommu_dma_notifier_data { + struct list_head list; + struct device *dev; + const struct iommu_ops *ops; + u64 dma_base; + u64 size; +}; +static LIST_HEAD(iommu_dma_masters); +static DEFINE_MUTEX(iommu_dma_notifier_lock); + +/* + * Temporarily "borrow" a domain feature flag to to tell if we had to resort + * to creating our own domain here, in case we need to clean it up again. + */ +#define __IOMMU_DOMAIN_FAKE_DEFAULT (1U << 31) + +static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops, + u64 dma_base, u64 size) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + + /* + * Best case: The device is either part of a group which was + * already attached to a domain in a previous call, or it's + * been put in a default DMA domain by the IOMMU core. + */ + if (!domain) { + /* + * Urgh. The IOMMU core isn't going to do default domains + * for non-PCI devices anyway, until it has some means of + * abstracting the entirely implementation-specific + * sideband data/SoC topology/unicorn dust that may or + * may not differentiate upstream masters. + * So until then, HORRIBLE HACKS! + */ + domain = ops->domain_alloc(IOMMU_DOMAIN_DMA); + if (!domain) + goto out_no_domain; + + domain->ops = ops; + domain->type = IOMMU_DOMAIN_DMA | __IOMMU_DOMAIN_FAKE_DEFAULT; + + if (iommu_attach_device(domain, dev)) + goto out_put_domain; + } + + if (iommu_dma_init_domain(domain, dma_base, size)) + goto out_detach; + + dev->archdata.dma_ops = &iommu_dma_ops; + return true; + +out_detach: + iommu_detach_device(domain, dev); +out_put_domain: + if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT) + iommu_domain_free(domain); +out_no_domain: + pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", + dev_name(dev)); + return false; +} + +static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops, + u64 dma_base, u64 size) +{ + struct iommu_dma_notifier_data *iommudata; + + iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL); + if (!iommudata) + return; + + iommudata->dev = dev; + iommudata->ops = ops; + iommudata->dma_base = dma_base; + iommudata->size = size; + + mutex_lock(&iommu_dma_notifier_lock); + list_add(&iommudata->list, &iommu_dma_masters); + mutex_unlock(&iommu_dma_notifier_lock); +} + +static int __iommu_attach_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct iommu_dma_notifier_data *master, *tmp; + + if (action != BUS_NOTIFY_ADD_DEVICE) + return 0; + + mutex_lock(&iommu_dma_notifier_lock); + list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) { + if (do_iommu_attach(master->dev, master->ops, + master->dma_base, master->size)) { + list_del(&master->list); + kfree(master); + } + } + mutex_unlock(&iommu_dma_notifier_lock); + return 0; +} + +static int register_iommu_dma_ops_notifier(struct bus_type *bus) +{ + struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL); + int ret; + + if (!nb) + return -ENOMEM; + /* + * The device must be attached to a domain before the driver probe + * routine gets a chance to start allocating DMA buffers. However, + * the IOMMU driver also needs a chance to configure the iommu_group + * via its add_device callback first, so we need to make the attach + * happen between those two points. Since the IOMMU core uses a bus + * notifier with default priority for add_device, do the same but + * with a lower priority to ensure the appropriate ordering. + */ + nb->notifier_call = __iommu_attach_notifier; + nb->priority = -100; + + ret = bus_register_notifier(bus, nb); + if (ret) { + pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n", + bus->name); + kfree(nb); + } + return ret; +} + +static int __init __iommu_dma_init(void) +{ + int ret; + + ret = iommu_dma_init(); + if (!ret) + ret = register_iommu_dma_ops_notifier(&platform_bus_type); + if (!ret) + ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); + return ret; +} +arch_initcall(__iommu_dma_init); + +static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *ops) +{ + struct iommu_group *group; + + if (!ops) + return; + /* + * TODO: As a concession to the future, we're ready to handle being + * called both early and late (i.e. after bus_add_device). Once all + * the platform bus code is reworked to call us late and the notifier + * junk above goes away, move the body of do_iommu_attach here. + */ + group = iommu_group_get(dev); + if (group) { + do_iommu_attach(dev, ops, dma_base, size); + iommu_group_put(group); + } else { + queue_iommu_attach(dev, ops, dma_base, size); + } +} + +void arch_teardown_dma_ops(struct device *dev) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + + if (domain) { + iommu_detach_device(domain, dev); + if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT) + iommu_domain_free(domain); + } + + dev->archdata.dma_ops = NULL; +} + +#else + +static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu) +{ } + +#endif /* CONFIG_IOMMU_DMA */ + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu, bool coherent) +{ + if (!dev->archdata.dma_ops) + dev->archdata.dma_ops = &swiotlb_dma_ops; + + dev->archdata.dma_coherent = coherent; + __iommu_setup_dma_ops(dev, dma_base, size, iommu); +} diff --git a/kernel/arch/arm64/mm/dump.c b/kernel/arch/arm64/mm/dump.c index f3d6221cd..5a22a119a 100644 --- a/kernel/arch/arm64/mm/dump.c +++ b/kernel/arch/arm64/mm/dump.c @@ -67,6 +67,12 @@ static struct addr_marker address_markers[] = { { -1, NULL }, }; +/* + * The page dumper groups page table entries of the same type into a single + * description. It uses pg_state to track the range information while + * iterating over the pte entries. When the continuity is broken it then + * dumps out a description of the range. + */ struct pg_state { struct seq_file *seq; const struct addr_marker *marker; @@ -113,6 +119,16 @@ static const struct prot_bits pte_bits[] = { .val = PTE_NG, .set = "NG", .clear = " ", + }, { + .mask = PTE_CONT, + .val = PTE_CONT, + .set = "CON", + .clear = " ", + }, { + .mask = PTE_TABLE_BIT, + .val = PTE_TABLE_BIT, + .set = " ", + .clear = "BLK", }, { .mask = PTE_UXN, .val = PTE_UXN, @@ -198,7 +214,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, unsigned long delta; if (st->current_prot) { - seq_printf(st->seq, "0x%16lx-0x%16lx ", + seq_printf(st->seq, "0x%016lx-0x%016lx ", st->start_address, addr); delta = (addr - st->start_address) >> 10; diff --git a/kernel/arch/arm64/mm/fault.c b/kernel/arch/arm64/mm/fault.c index 0948d327d..92ddac1e8 100644 --- a/kernel/arch/arm64/mm/fault.c +++ b/kernel/arch/arm64/mm/fault.c @@ -30,9 +30,11 @@ #include #include +#include #include #include #include +#include #include #include #include @@ -115,8 +117,7 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr, { struct siginfo si; - if (show_unhandled_signals && unhandled_signal(tsk, sig) && - printk_ratelimit()) { + if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) { pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n", tsk->comm, task_pid_nr(tsk), fault_name(esr), sig, addr, esr); @@ -224,6 +225,13 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } + /* + * PAN bit set implies the fault happened in kernel space, but not + * in the arch's user access functions. + */ + if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT)) + goto no_context; + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -279,6 +287,7 @@ retry: * starvation. */ mm_flags &= ~FAULT_FLAG_ALLOW_RETRY; + mm_flags |= FAULT_FLAG_TRIED; goto retry; } } @@ -384,16 +393,16 @@ static struct fault_info { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, - { do_bad, SIGBUS, 0, "reserved access flag fault" }, + { do_bad, SIGBUS, 0, "unknown 8" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, - { do_bad, SIGBUS, 0, "reserved permission fault" }, + { do_bad, SIGBUS, 0, "unknown 12" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_bad, SIGBUS, 0, "synchronous external abort" }, - { do_bad, SIGBUS, 0, "asynchronous external abort" }, + { do_bad, SIGBUS, 0, "unknown 17" }, { do_bad, SIGBUS, 0, "unknown 18" }, { do_bad, SIGBUS, 0, "unknown 19" }, { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, @@ -401,16 +410,16 @@ static struct fault_info { { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, { do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" }, { do_bad, SIGBUS, 0, "synchronous parity error" }, - { do_bad, SIGBUS, 0, "asynchronous parity error" }, + { do_bad, SIGBUS, 0, "unknown 25" }, { do_bad, SIGBUS, 0, "unknown 26" }, { do_bad, SIGBUS, 0, "unknown 27" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, - { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, + { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, { do_bad, SIGBUS, 0, "unknown 32" }, { do_bad, SIGBUS, BUS_ADRALN, "alignment fault" }, - { do_bad, SIGBUS, 0, "debug event" }, + { do_bad, SIGBUS, 0, "unknown 34" }, { do_bad, SIGBUS, 0, "unknown 35" }, { do_bad, SIGBUS, 0, "unknown 36" }, { do_bad, SIGBUS, 0, "unknown 37" }, @@ -424,21 +433,21 @@ static struct fault_info { { do_bad, SIGBUS, 0, "unknown 45" }, { do_bad, SIGBUS, 0, "unknown 46" }, { do_bad, SIGBUS, 0, "unknown 47" }, - { do_bad, SIGBUS, 0, "unknown 48" }, + { do_bad, SIGBUS, 0, "TLB conflict abort" }, { do_bad, SIGBUS, 0, "unknown 49" }, { do_bad, SIGBUS, 0, "unknown 50" }, { do_bad, SIGBUS, 0, "unknown 51" }, { do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" }, - { do_bad, SIGBUS, 0, "unknown 53" }, + { do_bad, SIGBUS, 0, "implementation fault (unsupported exclusive)" }, { do_bad, SIGBUS, 0, "unknown 54" }, { do_bad, SIGBUS, 0, "unknown 55" }, { do_bad, SIGBUS, 0, "unknown 56" }, { do_bad, SIGBUS, 0, "unknown 57" }, - { do_bad, SIGBUS, 0, "implementation fault (coprocessor abort)" }, + { do_bad, SIGBUS, 0, "unknown 58" }, { do_bad, SIGBUS, 0, "unknown 59" }, { do_bad, SIGBUS, 0, "unknown 60" }, - { do_bad, SIGBUS, 0, "unknown 61" }, - { do_bad, SIGBUS, 0, "unknown 62" }, + { do_bad, SIGBUS, 0, "section domain fault" }, + { do_bad, SIGBUS, 0, "page domain fault" }, { do_bad, SIGBUS, 0, "unknown 63" }, }; @@ -478,22 +487,37 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr, struct pt_regs *regs) { struct siginfo info; + struct task_struct *tsk = current; + + if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS)) + pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n", + tsk->comm, task_pid_nr(tsk), + esr_get_class_string(esr), (void *)regs->pc, + (void *)regs->sp); info.si_signo = SIGBUS; info.si_errno = 0; info.si_code = BUS_ADRALN; info.si_addr = (void __user *)addr; - arm64_notify_die("", regs, &info, esr); + arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr); } -static struct fault_info debug_fault_info[] = { +int __init early_brk64(unsigned long addr, unsigned int esr, + struct pt_regs *regs); + +/* + * __refdata because early_brk64 is __init, but the reference to it is + * clobbered at arch_initcall time. + * See traps.c and debug-monitors.c:debug_traps_init(). + */ +static struct fault_info __refdata debug_fault_info[] = { { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" }, { do_bad, SIGBUS, 0, "unknown 3" }, { do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" }, { do_bad, SIGTRAP, 0, "aarch32 vector catch" }, - { do_bad, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" }, + { early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" }, { do_bad, SIGBUS, 0, "unknown 7" }, }; @@ -530,3 +554,10 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, return 0; } + +#ifdef CONFIG_ARM64_PAN +void cpu_enable_pan(void *__unused) +{ + config_sctlr_el1(SCTLR_EL1_SPAN, 0); +} +#endif /* CONFIG_ARM64_PAN */ diff --git a/kernel/arch/arm64/mm/flush.c b/kernel/arch/arm64/mm/flush.c index b6f14e8d2..c26b80401 100644 --- a/kernel/arch/arm64/mm/flush.c +++ b/kernel/arch/arm64/mm/flush.c @@ -60,14 +60,10 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { -#ifdef CONFIG_SMP preempt_disable(); -#endif memcpy(dst, src, len); flush_ptrace_access(vma, page, uaddr, dst, len); -#ifdef CONFIG_SMP preempt_enable(); -#endif } void __sync_icache_dcache(pte_t pte, unsigned long addr) @@ -102,7 +98,6 @@ EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ -EXPORT_SYMBOL(flush_cache_all); EXPORT_SYMBOL(flush_icache_range); #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/kernel/arch/arm64/mm/hugetlbpage.c b/kernel/arch/arm64/mm/hugetlbpage.c index 0eeb4f093..383b03ff3 100644 --- a/kernel/arch/arm64/mm/hugetlbpage.c +++ b/kernel/arch/arm64/mm/hugetlbpage.c @@ -13,10 +13,6 @@ * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include @@ -31,13 +27,6 @@ #include #include -#ifndef CONFIG_ARCH_WANT_HUGE_PMD_SHARE -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) -{ - return 0; -} -#endif - int pmd_huge(pmd_t pmd) { return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); diff --git a/kernel/arch/arm64/mm/init.c b/kernel/arch/arm64/mm/init.c index ad87ce826..4cb98aa8c 100644 --- a/kernel/arch/arm64/mm/init.c +++ b/kernel/arch/arm64/mm/init.c @@ -86,10 +86,10 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) memset(zone_size, 0, sizeof(zone_size)); /* 4GB maximum for 32-bit only capable devices */ - if (IS_ENABLED(CONFIG_ZONE_DMA)) { - max_dma = PFN_DOWN(arm64_dma_phys_limit); - zone_size[ZONE_DMA] = max_dma - min; - } +#ifdef CONFIG_ZONE_DMA + max_dma = PFN_DOWN(arm64_dma_phys_limit); + zone_size[ZONE_DMA] = max_dma - min; +#endif zone_size[ZONE_NORMAL] = max - max_dma; memcpy(zhole_size, zone_size, sizeof(zhole_size)); @@ -101,11 +101,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) if (start >= max) continue; - if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) { +#ifdef CONFIG_ZONE_DMA + if (start < max_dma) { unsigned long dma_end = min(end, max_dma); zhole_size[ZONE_DMA] -= dma_end - start; } - +#endif if (end > max_dma) { unsigned long normal_end = min(end, max); unsigned long normal_start = max(start, max_dma); @@ -298,6 +299,9 @@ void __init mem_init(void) #define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K) pr_notice("Virtual kernel memory layout:\n" +#ifdef CONFIG_KASAN + " kasan : 0x%16lx - 0x%16lx (%6ld GB)\n" +#endif " vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n" #ifdef CONFIG_SPARSEMEM_VMEMMAP " vmemmap : 0x%16lx - 0x%16lx (%6ld GB maximum)\n" @@ -310,10 +314,13 @@ void __init mem_init(void) " .init : 0x%p" " - 0x%p" " (%6ld KB)\n" " .text : 0x%p" " - 0x%p" " (%6ld KB)\n" " .data : 0x%p" " - 0x%p" " (%6ld KB)\n", +#ifdef CONFIG_KASAN + MLG(KASAN_SHADOW_START, KASAN_SHADOW_END), +#endif MLG(VMALLOC_START, VMALLOC_END), #ifdef CONFIG_SPARSEMEM_VMEMMAP - MLG((unsigned long)vmemmap, - (unsigned long)vmemmap + VMEMMAP_SIZE), + MLG(VMEMMAP_START, + VMEMMAP_START + VMEMMAP_SIZE), MLM((unsigned long)virt_to_page(PAGE_OFFSET), (unsigned long)virt_to_page(high_memory)), #endif @@ -358,9 +365,9 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD -static int keep_initrd; +static int keep_initrd __initdata; -void free_initrd_mem(unsigned long start, unsigned long end) +void __init free_initrd_mem(unsigned long start, unsigned long end) { if (!keep_initrd) free_reserved_area((void *)start, (void *)end, 0, "initrd"); diff --git a/kernel/arch/arm64/mm/kasan_init.c b/kernel/arch/arm64/mm/kasan_init.c new file mode 100644 index 000000000..cf038c7d9 --- /dev/null +++ b/kernel/arch/arm64/mm/kasan_init.c @@ -0,0 +1,165 @@ +/* + * This file contains kasan initialization code for ARM64. + * + * Copyright (c) 2015 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin + * + * 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. + * + */ + +#define pr_fmt(fmt) "kasan: " fmt +#include +#include +#include +#include + +#include +#include +#include +#include + +static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); + +static void __init kasan_early_pte_populate(pmd_t *pmd, unsigned long addr, + unsigned long end) +{ + pte_t *pte; + unsigned long next; + + if (pmd_none(*pmd)) + pmd_populate_kernel(&init_mm, pmd, kasan_zero_pte); + + pte = pte_offset_kernel(pmd, addr); + do { + next = addr + PAGE_SIZE; + set_pte(pte, pfn_pte(virt_to_pfn(kasan_zero_page), + PAGE_KERNEL)); + } while (pte++, addr = next, addr != end && pte_none(*pte)); +} + +static void __init kasan_early_pmd_populate(pud_t *pud, + unsigned long addr, + unsigned long end) +{ + pmd_t *pmd; + unsigned long next; + + if (pud_none(*pud)) + pud_populate(&init_mm, pud, kasan_zero_pmd); + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + kasan_early_pte_populate(pmd, addr, next); + } while (pmd++, addr = next, addr != end && pmd_none(*pmd)); +} + +static void __init kasan_early_pud_populate(pgd_t *pgd, + unsigned long addr, + unsigned long end) +{ + pud_t *pud; + unsigned long next; + + if (pgd_none(*pgd)) + pgd_populate(&init_mm, pgd, kasan_zero_pud); + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + kasan_early_pmd_populate(pud, addr, next); + } while (pud++, addr = next, addr != end && pud_none(*pud)); +} + +static void __init kasan_map_early_shadow(void) +{ + unsigned long addr = KASAN_SHADOW_START; + unsigned long end = KASAN_SHADOW_END; + unsigned long next; + pgd_t *pgd; + + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + kasan_early_pud_populate(pgd, addr, next); + } while (pgd++, addr = next, addr != end); +} + +asmlinkage void __init kasan_early_init(void) +{ + BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << 61)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_START, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + kasan_map_early_shadow(); +} + +static void __init clear_pgds(unsigned long start, + unsigned long end) +{ + /* + * Remove references to kasan page tables from + * swapper_pg_dir. pgd_clear() can't be used + * here because it's nop on 2,3-level pagetable setups + */ + for (; start < end; start += PGDIR_SIZE) + set_pgd(pgd_offset_k(start), __pgd(0)); +} + +static void __init cpu_set_ttbr1(unsigned long ttbr1) +{ + asm( + " msr ttbr1_el1, %0\n" + " isb" + : + : "r" (ttbr1)); +} + +void __init kasan_init(void) +{ + struct memblock_region *reg; + + /* + * We are going to perform proper setup of shadow memory. + * At first we should unmap early shadow (clear_pgds() call bellow). + * However, instrumented code couldn't execute without shadow memory. + * tmp_pg_dir used to keep early shadow mapped until full shadow + * setup will be finished. + */ + memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); + cpu_set_ttbr1(__pa(tmp_pg_dir)); + flush_tlb_all(); + + clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + + kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, + kasan_mem_to_shadow((void *)MODULES_VADDR)); + + for_each_memblock(memory, reg) { + void *start = (void *)__phys_to_virt(reg->base); + void *end = (void *)__phys_to_virt(reg->base + reg->size); + + if (start >= end) + break; + + /* + * end + 1 here is intentional. We check several shadow bytes in + * advance to slightly speed up fastpath. In some rare cases + * we could cross boundary of mapped shadow, so we just map + * some more here. + */ + vmemmap_populate((unsigned long)kasan_mem_to_shadow(start), + (unsigned long)kasan_mem_to_shadow(end) + 1, + pfn_to_nid(virt_to_pfn(start))); + } + + memset(kasan_zero_page, 0, PAGE_SIZE); + cpu_set_ttbr1(__pa(swapper_pg_dir)); + flush_tlb_all(); + + /* At this point kasan is fully initialized. Enable error messages */ + init_task.kasan_depth = 0; + pr_info("KernelAddressSanitizer initialized\n"); +} diff --git a/kernel/arch/arm64/mm/mmu.c b/kernel/arch/arm64/mm/mmu.c index 5b8b66442..116ad654d 100644 --- a/kernel/arch/arm64/mm/mmu.c +++ b/kernel/arch/arm64/mm/mmu.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -31,6 +32,7 @@ #include #include +#include #include #include #include @@ -62,8 +64,12 @@ EXPORT_SYMBOL(phys_mem_access_prot); static void __init *early_alloc(unsigned long sz) { - void *ptr = __va(memblock_alloc(sz, sz)); - BUG_ON(!ptr); + phys_addr_t phys; + void *ptr; + + phys = memblock_alloc(sz, sz); + BUG_ON(!phys); + ptr = __va(phys); memset(ptr, 0, sz); return ptr; } @@ -109,14 +115,14 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, } while (pte++, addr += PAGE_SIZE, addr != end); } -void split_pud(pud_t *old_pud, pmd_t *pmd) +static void split_pud(pud_t *old_pud, pmd_t *pmd) { unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT; pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr); int i = 0; do { - set_pmd(pmd, __pmd(addr | prot)); + set_pmd(pmd, __pmd(addr | pgprot_val(prot))); addr += PMD_SIZE; } while (pmd++, i++, i < PTRS_PER_PMD); } @@ -266,7 +272,7 @@ static void *late_alloc(unsigned long size) return ptr; } -static void __ref create_mapping(phys_addr_t phys, unsigned long virt, +static void __init create_mapping(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot) { if (virt < VMALLOC_START) { @@ -307,8 +313,8 @@ static void __init __map_memblock(phys_addr_t start, phys_addr_t end) * for now. This will get more fine grained later once all memory * is mapped */ - unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE); - unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); + unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE); + unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE); if (end < kernel_x_start) { create_mapping(start, __phys_to_virt(start), @@ -352,14 +358,11 @@ static void __init map_mem(void) * memory addressable from the initial direct kernel mapping. * * The initial direct kernel mapping, located at swapper_pg_dir, gives - * us PUD_SIZE (4K pages) or PMD_SIZE (64K pages) memory starting from - * PHYS_OFFSET (which must be aligned to 2MB as per - * Documentation/arm64/booting.txt). + * us PUD_SIZE (with SECTION maps) or PMD_SIZE (without SECTION maps, + * memory starting from PHYS_OFFSET (which must be aligned to 2MB as + * per Documentation/arm64/booting.txt). */ - if (IS_ENABLED(CONFIG_ARM64_64K_PAGES)) - limit = PHYS_OFFSET + PMD_SIZE; - else - limit = PHYS_OFFSET + PUD_SIZE; + limit = PHYS_OFFSET + SWAPPER_INIT_MAP_SIZE; memblock_set_current_limit(limit); /* map all the memory banks */ @@ -370,21 +373,24 @@ static void __init map_mem(void) if (start >= end) break; -#ifndef CONFIG_ARM64_64K_PAGES - /* - * For the first memory bank align the start address and - * current memblock limit to prevent create_mapping() from - * allocating pte page tables from unmapped memory. - * When 64K pages are enabled, the pte page table for the - * first PGDIR_SIZE is already present in swapper_pg_dir. - */ - if (start < limit) - start = ALIGN(start, PMD_SIZE); - if (end < limit) { - limit = end & PMD_MASK; - memblock_set_current_limit(limit); + if (ARM64_SWAPPER_USES_SECTION_MAPS) { + /* + * For the first memory bank align the start address and + * current memblock limit to prevent create_mapping() from + * allocating pte page tables from unmapped memory. With + * the section maps, if the first block doesn't end on section + * size boundary, create_mapping() will try to allocate a pte + * page, which may be returned from an unmapped area. + * When section maps are not used, the pte page table for the + * current limit is already present in swapper_pg_dir. + */ + if (start < limit) + start = ALIGN(start, SECTION_SIZE); + if (end < limit) { + limit = end & SECTION_MASK; + memblock_set_current_limit(limit); + } } -#endif __map_memblock(start, end); } @@ -392,22 +398,22 @@ static void __init map_mem(void) memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); } -void __init fixup_executable(void) +static void __init fixup_executable(void) { #ifdef CONFIG_DEBUG_RODATA /* now that we are actually fully mapped, make the start/end more fine grained */ - if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_start = round_down(__pa(_stext), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(aligned_start, __phys_to_virt(aligned_start), __pa(_stext) - aligned_start, PAGE_KERNEL); } - if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) { + if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) { unsigned long aligned_end = round_up(__pa(__init_end), - SECTION_SIZE); + SWAPPER_BLOCK_SIZE); create_mapping(__pa(__init_end), (unsigned long)__init_end, aligned_end - __pa(__init_end), PAGE_KERNEL); @@ -420,7 +426,7 @@ void mark_rodata_ro(void) { create_mapping_late(__pa(_stext), (unsigned long)_stext, (unsigned long)_etext - (unsigned long)_stext, - PAGE_KERNEL_EXEC | PTE_RDONLY); + PAGE_KERNEL_ROX); } #endif @@ -450,26 +456,18 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. */ cpu_set_reserved_ttbr0(); - flush_tlb_all(); + local_flush_tlb_all(); cpu_set_default_tcr_t0sz(); } -/* - * Enable the identity mapping to allow the MMU disabling. - */ -void setup_mm_for_reboot(void) -{ - cpu_set_reserved_ttbr0(); - flush_tlb_all(); - cpu_set_idmap_tcr_t0sz(); - cpu_switch_mm(idmap_pg_dir, &init_mm); -} - /* * Check whether a kernel address is valid (derived from arch/x86/). */ @@ -508,12 +506,12 @@ int kern_addr_valid(unsigned long addr) return pfn_valid(pte_pfn(*pte)); } #ifdef CONFIG_SPARSEMEM_VMEMMAP -#ifdef CONFIG_ARM64_64K_PAGES +#if !ARM64_SWAPPER_USES_SECTION_MAPS int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { return vmemmap_populate_basepages(start, end, node); } -#else /* !CONFIG_ARM64_64K_PAGES */ +#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) { unsigned long addr = start; @@ -643,3 +641,59 @@ void __set_fixmap(enum fixed_addresses idx, flush_tlb_kernel_range(addr, addr+PAGE_SIZE); } } + +void *__init fixmap_remap_fdt(phys_addr_t dt_phys) +{ + const u64 dt_virt_base = __fix_to_virt(FIX_FDT); + pgprot_t prot = PAGE_KERNEL_RO; + int size, offset; + void *dt_virt; + + /* + * Check whether the physical FDT address is set and meets the minimum + * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be + * at least 8 bytes so that we can always access the size field of the + * FDT header after mapping the first chunk, double check here if that + * is indeed the case. + */ + BUILD_BUG_ON(MIN_FDT_ALIGN < 8); + if (!dt_phys || dt_phys % MIN_FDT_ALIGN) + return NULL; + + /* + * Make sure that the FDT region can be mapped without the need to + * allocate additional translation table pages, so that it is safe + * to call create_mapping() this early. + * + * On 64k pages, the FDT will be mapped using PTEs, so we need to + * be in the same PMD as the rest of the fixmap. + * On 4k pages, we'll use section mappings for the FDT so we only + * have to be in the same PUD. + */ + BUILD_BUG_ON(dt_virt_base % SZ_2M); + + BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT != + __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT); + + offset = dt_phys % SWAPPER_BLOCK_SIZE; + dt_virt = (void *)dt_virt_base + offset; + + /* map the first chunk so we can read the size from the header */ + create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + SWAPPER_BLOCK_SIZE, prot); + + if (fdt_check_header(dt_virt) != 0) + return NULL; + + size = fdt_totalsize(dt_virt); + if (size > MAX_FDT_SIZE) + return NULL; + + if (offset + size > SWAPPER_BLOCK_SIZE) + create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base, + round_up(offset + size, SWAPPER_BLOCK_SIZE), prot); + + memblock_reserve(dt_phys, size); + + return dt_virt; +} diff --git a/kernel/arch/arm64/mm/pageattr.c b/kernel/arch/arm64/mm/pageattr.c index e47ed1c5d..cf6240741 100644 --- a/kernel/arch/arm64/mm/pageattr.c +++ b/kernel/arch/arm64/mm/pageattr.c @@ -45,7 +45,7 @@ static int change_memory_common(unsigned long addr, int numpages, int ret; struct page_change_data data; - if (!IS_ALIGNED(addr, PAGE_SIZE)) { + if (!PAGE_ALIGNED(addr)) { start &= PAGE_MASK; end = start + size; WARN_ON_ONCE(1); @@ -57,6 +57,9 @@ static int change_memory_common(unsigned long addr, int numpages, if (end < MODULES_VADDR || end >= MODULES_END) return -EINVAL; + if (!numpages) + return 0; + data.set_mask = set_mask; data.clear_mask = clear_mask; diff --git a/kernel/arch/arm64/mm/pgd.c b/kernel/arch/arm64/mm/pgd.c index 71ca104f9..cb3ba1b81 100644 --- a/kernel/arch/arm64/mm/pgd.c +++ b/kernel/arch/arm64/mm/pgd.c @@ -28,8 +28,6 @@ #include "mm.h" -#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) - static struct kmem_cache *pgd_cache; pgd_t *pgd_alloc(struct mm_struct *mm) diff --git a/kernel/arch/arm64/mm/proc-macros.S b/kernel/arch/arm64/mm/proc-macros.S index 4c4d93c4b..d69dffffa 100644 --- a/kernel/arch/arm64/mm/proc-macros.S +++ b/kernel/arch/arm64/mm/proc-macros.S @@ -62,3 +62,15 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present + */ + .macro reset_pmuserenr_el0, tmpreg + mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer + sbfx \tmpreg, \tmpreg, #8, #4 + cmp \tmpreg, #1 // Skip if no PMU present + b.lt 9000f + msr pmuserenr_el0, xzr // Disable PMU access from EL0 +9000: + .endm diff --git a/kernel/arch/arm64/mm/proc.S b/kernel/arch/arm64/mm/proc.S index cdd754e19..b8f04b3f2 100644 --- a/kernel/arch/arm64/mm/proc.S +++ b/kernel/arch/arm64/mm/proc.S @@ -30,67 +30,19 @@ #ifdef CONFIG_ARM64_64K_PAGES #define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K -#else +#elif defined(CONFIG_ARM64_16K_PAGES) +#define TCR_TG_FLAGS TCR_TG0_16K | TCR_TG1_16K +#else /* CONFIG_ARM64_4K_PAGES */ #define TCR_TG_FLAGS TCR_TG0_4K | TCR_TG1_4K #endif -#ifdef CONFIG_SMP #define TCR_SMP_FLAGS TCR_SHARED -#else -#define TCR_SMP_FLAGS 0 -#endif /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA #define MAIR(attr, mt) ((attr) << ((mt) * 8)) -/* - * cpu_cache_off() - * - * Turn the CPU D-cache off. - */ -ENTRY(cpu_cache_off) - mrs x0, sctlr_el1 - bic x0, x0, #1 << 2 // clear SCTLR.C - msr sctlr_el1, x0 - isb - ret -ENDPROC(cpu_cache_off) - -/* - * cpu_reset(loc) - * - * Perform a soft reset of the system. Put the CPU into the same state - * as it would be if it had been reset, and branch to what would be the - * reset vector. It must be executed with the flat identity mapping. - * - * - loc - location to jump to for soft reset - */ - .align 5 -ENTRY(cpu_reset) - mrs x1, sctlr_el1 - bic x1, x1, #1 - msr sctlr_el1, x1 // disable the MMU - isb - ret x0 -ENDPROC(cpu_reset) - -ENTRY(cpu_soft_restart) - /* Save address of cpu_reset() and reset address */ - mov x19, x0 - mov x20, x1 - - /* Turn D-cache off */ - bl cpu_cache_off - - /* Push out all dirty data, and ensure cache is empty */ - bl flush_cache_all - - mov x0, x20 - ret x19 -ENDPROC(cpu_soft_restart) - /* * cpu_do_idle() * @@ -165,6 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -180,7 +133,7 @@ ENDPROC(cpu_do_resume) * - pgd_phys - physical address of new TTB */ ENTRY(cpu_do_switch_mm) - mmid w1, x1 // get mm->context.id + mmid x1, x1 // get mm->context.id bfi x0, x1, #48, #16 // set the ASID msr ttbr0_el1, x0 // set TTBR0 isb @@ -196,13 +149,14 @@ ENDPROC(cpu_do_switch_mm) * value of the SCTLR_EL1 register. */ ENTRY(__cpu_setup) - ic iallu // I+BTB cache invalidate - tlbi vmalle1is // invalidate I + D TLBs - dsb ish + tlbi vmalle1 // Invalidate local TLB + dsb nsh mov x0, #3 << 20 msr cpacr_el1, x0 // Enable FP/ASIMD - msr mdscr_el1, xzr // Reset mdscr_el1 + mov x0, #1 << 12 // Reset mdscr_el1 and disable + msr mdscr_el1, x0 // access to the DCC from EL0 + reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * @@ -213,12 +167,14 @@ ENTRY(__cpu_setup) * DEVICE_GRE 010 00001100 * NORMAL_NC 011 01000100 * NORMAL 100 11111111 + * NORMAL_WT 101 10111011 */ ldr x5, =MAIR(0x00, MT_DEVICE_nGnRnE) | \ MAIR(0x04, MT_DEVICE_nGnRE) | \ MAIR(0x0c, MT_DEVICE_GRE) | \ MAIR(0x44, MT_NORMAL_NC) | \ - MAIR(0xff, MT_NORMAL) + MAIR(0xff, MT_NORMAL) | \ + MAIR(0xbb, MT_NORMAL_WT) msr mair_el1, x5 /* * Prepare SCTLR @@ -242,6 +198,19 @@ ENTRY(__cpu_setup) */ mrs x9, ID_AA64MMFR0_EL1 bfi x10, x9, #32, #3 +#ifdef CONFIG_ARM64_HW_AFDBM + /* + * Hardware update of the Access and Dirty bits. + */ + mrs x9, ID_AA64MMFR1_EL1 + and x9, x9, #0xf + cbz x9, 2f + cmp x9, #2 + b.lt 1f + orr x10, x10, #TCR_HD // hardware Dirty flag update +1: orr x10, x10, #TCR_HA // hardware Access flag update +2: +#endif /* CONFIG_ARM64_HW_AFDBM */ msr tcr_el1, x10 ret // return to head.S ENDPROC(__cpu_setup) diff --git a/kernel/arch/arm64/net/bpf_jit.h b/kernel/arch/arm64/net/bpf_jit.h index 98a26ce82..aee5637ea 100644 --- a/kernel/arch/arm64/net/bpf_jit.h +++ b/kernel/arch/arm64/net/bpf_jit.h @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014 Zi Shen Lim + * Copyright (C) 2014-2015 Zi Shen Lim * * 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 @@ -35,6 +35,7 @@ aarch64_insn_gen_comp_branch_imm(0, offset, Rt, A64_VARIANT(sf), \ AARCH64_INSN_BRANCH_COMP_##type) #define A64_CBZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, ZERO) +#define A64_CBNZ(sf, Rt, imm19) A64_COMP_BRANCH(sf, Rt, (imm19) << 2, NONZERO) /* Conditional branch (immediate) */ #define A64_COND_BRANCH(cond, offset) \ diff --git a/kernel/arch/arm64/net/bpf_jit_comp.c b/kernel/arch/arm64/net/bpf_jit_comp.c index c047598b0..b162ad70e 100644 --- a/kernel/arch/arm64/net/bpf_jit_comp.c +++ b/kernel/arch/arm64/net/bpf_jit_comp.c @@ -1,7 +1,7 @@ /* * BPF JIT compiler for ARM64 * - * Copyright (C) 2014 Zi Shen Lim + * Copyright (C) 2014-2015 Zi Shen Lim * * 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 @@ -50,7 +50,7 @@ static const int bpf2a64[] = { [BPF_REG_8] = A64_R(21), [BPF_REG_9] = A64_R(22), /* read-only frame pointer to access stack */ - [BPF_REG_FP] = A64_FP, + [BPF_REG_FP] = A64_R(25), /* temporary register for internal BPF JIT */ [TMP_REG_1] = A64_R(23), [TMP_REG_2] = A64_R(24), @@ -139,6 +139,12 @@ static inline int epilogue_offset(const struct jit_ctx *ctx) /* Stack must be multiples of 16B */ #define STACK_ALIGN(sz) (((sz) + 15) & ~15) +#define _STACK_SIZE \ + (MAX_BPF_STACK \ + + 4 /* extra for skb_copy_bits buffer */) + +#define STACK_SIZE STACK_ALIGN(_STACK_SIZE) + static void build_prologue(struct jit_ctx *ctx) { const u8 r6 = bpf2a64[BPF_REG_6]; @@ -150,10 +156,35 @@ static void build_prologue(struct jit_ctx *ctx) const u8 rx = bpf2a64[BPF_REG_X]; const u8 tmp1 = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; - int stack_size = MAX_BPF_STACK; - stack_size += 4; /* extra for skb_copy_bits buffer */ - stack_size = STACK_ALIGN(stack_size); + /* + * BPF prog stack layout + * + * high + * original A64_SP => 0:+-----+ BPF prologue + * |FP/LR| + * current A64_FP => -16:+-----+ + * | ... | callee saved registers + * +-----+ + * | | x25/x26 + * BPF fp register => -80:+-----+ <= (BPF_FP) + * | | + * | ... | BPF prog stack + * | | + * +-----+ <= (BPF_FP - MAX_BPF_STACK) + * |RSVD | JIT scratchpad + * current A64_SP => +-----+ <= (BPF_FP - STACK_SIZE) + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + * + */ + + /* Save FP and LR registers to stay align with ARM64 AAPCS */ + emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); + emit(A64_MOV(1, A64_FP, A64_SP), ctx); /* Save callee-saved register */ emit(A64_PUSH(r6, r7, A64_SP), ctx); @@ -161,12 +192,15 @@ static void build_prologue(struct jit_ctx *ctx) if (ctx->tmp_used) emit(A64_PUSH(tmp1, tmp2, A64_SP), ctx); - /* Set up BPF stack */ - emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx); + /* Save fp (x25) and x26. SP requires 16 bytes alignment */ + emit(A64_PUSH(fp, A64_R(26), A64_SP), ctx); - /* Set up frame pointer */ + /* Set up BPF prog stack base register (x25) */ emit(A64_MOV(1, fp, A64_SP), ctx); + /* Set up function call stack */ + emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); + /* Clear registers A and X */ emit_a64_mov_i64(ra, 0, ctx); emit_a64_mov_i64(rx, 0, ctx); @@ -182,13 +216,12 @@ static void build_epilogue(struct jit_ctx *ctx) const u8 fp = bpf2a64[BPF_REG_FP]; const u8 tmp1 = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; - int stack_size = MAX_BPF_STACK; - - stack_size += 4; /* extra for skb_copy_bits buffer */ - stack_size = STACK_ALIGN(stack_size); /* We're done with BPF stack */ - emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx); + emit(A64_ADD_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); + + /* Restore fs (x25) and x26 */ + emit(A64_POP(fp, A64_R(26), A64_SP), ctx); /* Restore callee-saved register */ if (ctx->tmp_used) @@ -196,8 +229,8 @@ static void build_epilogue(struct jit_ctx *ctx) emit(A64_POP(r8, r9, A64_SP), ctx); emit(A64_POP(r6, r7, A64_SP), ctx); - /* Restore frame pointer */ - emit(A64_MOV(1, fp, A64_SP), ctx); + /* Restore FP/LR registers */ + emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); /* Set return value */ emit(A64_MOV(1, A64_R(0), r0), ctx); @@ -225,6 +258,17 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) u8 jmp_cond; s32 jmp_offset; +#define check_imm(bits, imm) do { \ + if ((((imm) > 0) && ((imm) >> (bits))) || \ + (((imm) < 0) && (~(imm) >> (bits)))) { \ + pr_info("[%2d] imm=%d(0x%x) out of range\n", \ + i, imm, imm); \ + return -EINVAL; \ + } \ +} while (0) +#define check_imm19(imm) check_imm(19, imm) +#define check_imm26(imm) check_imm(26, imm) + switch (code) { /* dst = src */ case BPF_ALU | BPF_MOV | BPF_X: @@ -258,15 +302,33 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU64 | BPF_DIV | BPF_X: - emit(A64_UDIV(is64, dst, dst, src), ctx); - break; case BPF_ALU | BPF_MOD | BPF_X: case BPF_ALU64 | BPF_MOD | BPF_X: - ctx->tmp_used = 1; - emit(A64_UDIV(is64, tmp, dst, src), ctx); - emit(A64_MUL(is64, tmp, tmp, src), ctx); - emit(A64_SUB(is64, dst, dst, tmp), ctx); + { + const u8 r0 = bpf2a64[BPF_REG_0]; + + /* if (src == 0) return 0 */ + jmp_offset = 3; /* skip ahead to else path */ + check_imm19(jmp_offset); + emit(A64_CBNZ(is64, src, jmp_offset), ctx); + emit(A64_MOVZ(1, r0, 0, 0), ctx); + jmp_offset = epilogue_offset(ctx); + check_imm26(jmp_offset); + emit(A64_B(jmp_offset), ctx); + /* else */ + switch (BPF_OP(code)) { + case BPF_DIV: + emit(A64_UDIV(is64, dst, dst, src), ctx); + break; + case BPF_MOD: + ctx->tmp_used = 1; + emit(A64_UDIV(is64, tmp, dst, src), ctx); + emit(A64_MUL(is64, tmp, tmp, src), ctx); + emit(A64_SUB(is64, dst, dst, tmp), ctx); + break; + } break; + } case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_LSH | BPF_X: emit(A64_LSLV(is64, dst, dst, src), ctx); @@ -393,17 +455,6 @@ emit_bswap_uxt: emit(A64_ASR(is64, dst, dst, imm), ctx); break; -#define check_imm(bits, imm) do { \ - if ((((imm) > 0) && ((imm) >> (bits))) || \ - (((imm) < 0) && (~(imm) >> (bits)))) { \ - pr_info("[%2d] imm=%d(0x%x) out of range\n", \ - i, imm, imm); \ - return -EINVAL; \ - } \ -} while (0) -#define check_imm19(imm) check_imm(19, imm) -#define check_imm26(imm) check_imm(26, imm) - /* JUMP off */ case BPF_JMP | BPF_JA: jmp_offset = bpf2a64_offset(i + off, i, ctx); @@ -539,7 +590,25 @@ emit_cond_jmp: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_DW: - goto notyet; + /* Load imm to a register then store it */ + ctx->tmp_used = 1; + emit_a64_mov_i(1, tmp2, off, ctx); + emit_a64_mov_i(1, tmp, imm, ctx); + switch (BPF_SIZE(code)) { + case BPF_W: + emit(A64_STR32(tmp, dst, tmp2), ctx); + break; + case BPF_H: + emit(A64_STRH(tmp, dst, tmp2), ctx); + break; + case BPF_B: + emit(A64_STRB(tmp, dst, tmp2), ctx); + break; + case BPF_DW: + emit(A64_STR64(tmp, dst, tmp2), ctx); + break; + } + break; /* STX: *(size *)(dst + off) = src */ case BPF_STX | BPF_MEM | BPF_W: @@ -606,7 +675,7 @@ emit_cond_jmp: return -EINVAL; } emit_a64_mov_i64(r3, size, ctx); - emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx); + emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx); emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx); emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx); emit(A64_MOV(1, A64_FP, A64_SP), ctx); @@ -740,11 +809,11 @@ void bpf_int_jit_compile(struct bpf_prog *prog) if (bpf_jit_enable > 1) bpf_jit_dump(prog->len, image_size, 2, ctx.image); - bpf_flush_icache(ctx.image, ctx.image + ctx.idx); + bpf_flush_icache(header, ctx.image + ctx.idx); set_memory_ro((unsigned long)header, header->pages); prog->bpf_func = (void *)ctx.image; - prog->jited = true; + prog->jited = 1; out: kfree(ctx.offset); } -- cgit 1.2.3-korg