diff options
Diffstat (limited to 'arch/arm64/kernel')
32 files changed, 409 insertions, 1892 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index ceba6792f5b3..7c2bb4e72476 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o -obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_CPU_PM) += sleep.o suspend.o obj-$(CONFIG_CPU_IDLE) += cpuidle.o diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 8a9052cf3013..1febd412b4d2 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -420,14 +420,14 @@ static DEFINE_MUTEX(insn_emulation_mutex); static void enable_insn_hw_mode(void *data) { - struct insn_emulation *insn = (struct insn_emulation *)data; + struct insn_emulation *insn = data; if (insn->set_hw_mode) insn->set_hw_mode(true); } static void disable_insn_hw_mode(void *data) { - struct insn_emulation *insn = (struct insn_emulation *)data; + struct insn_emulation *insn = data; if (insn->set_hw_mode) insn->set_hw_mode(false); } diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index ae345b06e9f7..0996094b0d22 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -93,6 +93,9 @@ int main(void) DEFINE(FREGS_LR, offsetof(struct ftrace_regs, lr)); DEFINE(FREGS_SP, offsetof(struct ftrace_regs, sp)); DEFINE(FREGS_PC, offsetof(struct ftrace_regs, pc)); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + DEFINE(FREGS_DIRECT_TRAMP, offsetof(struct ftrace_regs, direct_tramp)); +#endif DEFINE(FREGS_SIZE, sizeof(struct ftrace_regs)); BLANK(); #endif @@ -197,6 +200,9 @@ int main(void) #endif #ifdef CONFIG_FUNCTION_TRACER DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); +#endif #endif return 0; } diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index c307f69e9b55..d9c9218fa1fd 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -38,11 +38,9 @@ static void ci_leaf_init(struct cacheinfo *this_leaf, this_leaf->type = type; } -int init_cache_level(unsigned int cpu) +static void detect_cache_level(unsigned int *level_p, unsigned int *leaves_p) { unsigned int ctype, level, leaves; - int fw_level, ret; - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); for (level = 1, leaves = 0; level <= MAX_CACHE_LEVEL; level++) { ctype = get_cache_type(level); @@ -54,6 +52,27 @@ int init_cache_level(unsigned int cpu) leaves += (ctype == CACHE_TYPE_SEPARATE) ? 2 : 1; } + *level_p = level; + *leaves_p = leaves; +} + +int early_cache_level(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + + detect_cache_level(&this_cpu_ci->num_levels, &this_cpu_ci->num_leaves); + + return 0; +} + +int init_cache_level(unsigned int cpu) +{ + unsigned int level, leaves; + int fw_level, ret; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + + detect_cache_level(&level, &leaves); + if (acpi_disabled) { fw_level = of_find_last_cache_level(cpu); } else { diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c index 5edec2f49ec9..deff21bfa680 100644 --- a/arch/arm64/kernel/compat_alignment.c +++ b/arch/arm64/kernel/compat_alignment.c @@ -314,36 +314,32 @@ int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs) int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs); unsigned int type; u32 instr = 0; - u16 tinstr = 0; int isize = 4; int thumb2_32b = 0; - int fault; instrptr = instruction_pointer(regs); if (compat_thumb_mode(regs)) { __le16 __user *ptr = (__le16 __user *)(instrptr & ~1); + u16 tinstr, tinst2; - fault = alignment_get_thumb(regs, ptr, &tinstr); - if (!fault) { - if (IS_T32(tinstr)) { - /* Thumb-2 32-bit */ - u16 tinst2; - fault = alignment_get_thumb(regs, ptr + 1, &tinst2); - instr = ((u32)tinstr << 16) | tinst2; - thumb2_32b = 1; - } else { - isize = 2; - instr = thumb2arm(tinstr); - } + if (alignment_get_thumb(regs, ptr, &tinstr)) + return 1; + + if (IS_T32(tinstr)) { /* Thumb-2 32-bit */ + if (alignment_get_thumb(regs, ptr + 1, &tinst2)) + return 1; + instr = ((u32)tinstr << 16) | tinst2; + thumb2_32b = 1; + } else { + isize = 2; + instr = thumb2arm(tinstr); } } else { - fault = alignment_get_arm(regs, (__le32 __user *)instrptr, &instr); + if (alignment_get_arm(regs, (__le32 __user *)instrptr, &instr)) + return 1; } - if (fault) - return 1; - switch (CODING_BITS(instr)) { case 0x00000000: /* 3.13.4 load/store instruction extensions */ if (LDSTHD_I_BIT(instr)) diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 6b752fe89745..c87445dde674 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -14,7 +14,7 @@ #include <asm/virt.h> .text -.pushsection .idmap.text, "awx" +.pushsection .idmap.text, "a" /* * cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 2e3e55139777..7d7128c65161 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -140,6 +140,13 @@ void dump_cpu_features(void) pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps); } +#define ARM64_CPUID_FIELDS(reg, field, min_value) \ + .sys_reg = SYS_##reg, \ + .field_pos = reg##_##field##_SHIFT, \ + .field_width = reg##_##field##_WIDTH, \ + .sign = reg##_##field##_SIGNED, \ + .min_field_value = reg##_##field##_##min_value, + #define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ .sign = SIGNED, \ @@ -1490,10 +1497,18 @@ static const DEVICE_ATTR_RO(aarch32_el0); static int __init aarch32_el0_sysfs_init(void) { + struct device *dev_root; + int ret = 0; + if (!allow_mismatched_32bit_el0) return 0; - return device_create_file(cpu_subsys.dev_root, &dev_attr_aarch32_el0); + dev_root = bus_get_dev_root(&cpu_subsys); + if (dev_root) { + ret = device_create_file(dev_root, &dev_attr_aarch32_el0); + put_device(dev_root); + } + return ret; } device_initcall(aarch32_el0_sysfs_init); @@ -2206,22 +2221,25 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_GIC_CPUIF_SYSREGS, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_useable_gicv3_cpuif, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .field_pos = ID_AA64PFR0_EL1_GIC_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 1, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, GIC, IMP) }, { .desc = "Enhanced Counter Virtualization", .capability = ARM64_HAS_ECV, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, ECV, IMP) + }, + { + .desc = "Enhanced Counter Virtualization (CNTPOFF)", + .capability = ARM64_HAS_ECV_CNTPOFF, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR0_EL1, .field_pos = ID_AA64MMFR0_EL1_ECV_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, - .min_field_value = 1, + .min_field_value = ID_AA64MMFR0_EL1_ECV_CNTPOFF, }, #ifdef CONFIG_ARM64_PAN { @@ -2229,12 +2247,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_PAN, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64MMFR1_EL1, - .field_pos = ID_AA64MMFR1_EL1_PAN_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 1, .cpu_enable = cpu_enable_pan, + ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, PAN, IMP) }, #endif /* CONFIG_ARM64_PAN */ #ifdef CONFIG_ARM64_EPAN @@ -2243,11 +2257,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_EPAN, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64MMFR1_EL1, - .field_pos = ID_AA64MMFR1_EL1_PAN_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 3, + ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, PAN, PAN3) }, #endif /* CONFIG_ARM64_EPAN */ #ifdef CONFIG_ARM64_LSE_ATOMICS @@ -2256,11 +2266,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_LSE_ATOMICS, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_EL1_ATOMIC_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 2, + ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, ATOMIC, IMP) }, #endif /* CONFIG_ARM64_LSE_ATOMICS */ { @@ -2281,21 +2287,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_NESTED_VIRT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_nested_virt_support, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_EL1_NV_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64MMFR2_EL1_NV_IMP, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, NV, IMP) }, { .capability = ARM64_HAS_32BIT_EL0_DO_NOT_USE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_32bit_el0, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_EL0_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR0_EL1_ELx_32BIT_64BIT, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, EL0, AARCH32) }, #ifdef CONFIG_KVM { @@ -2303,11 +2301,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_32BIT_EL1, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_EL1_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR0_EL1_ELx_32BIT_64BIT, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, EL1, AARCH32) }, { .desc = "Protected KVM", @@ -2320,17 +2314,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Kernel page table isolation (KPTI)", .capability = ARM64_UNMAP_KERNEL_AT_EL0, .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, + .cpu_enable = kpti_install_ng_mappings, + .matches = unmap_kernel_at_el0, /* * The ID feature fields below are used to indicate that * the CPU doesn't need KPTI. See unmap_kernel_at_el0 for * more details. */ - .sys_reg = SYS_ID_AA64PFR0_EL1, - .field_pos = ID_AA64PFR0_EL1_CSV3_SHIFT, - .field_width = 4, - .min_field_value = 1, - .matches = unmap_kernel_at_el0, - .cpu_enable = kpti_install_ng_mappings, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, CSV3, IMP) }, { /* FP/SIMD is not implemented */ @@ -2345,21 +2336,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_DCPOP, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .field_pos = ID_AA64ISAR1_EL1_DPB_SHIFT, - .field_width = 4, - .min_field_value = 1, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, DPB, IMP) }, { .desc = "Data cache clean to Point of Deep Persistence", .capability = ARM64_HAS_DCPODP, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR1_EL1_DPB_SHIFT, - .field_width = 4, - .min_field_value = 2, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, DPB, DPB2) }, #endif #ifdef CONFIG_ARM64_SVE @@ -2367,13 +2351,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Scalable Vector Extension", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SVE, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_SVE_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR0_EL1_SVE_IMP, - .matches = has_cpuid_feature, .cpu_enable = sve_kernel_enable, + .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, SVE, IMP) }, #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_RAS_EXTN @@ -2382,12 +2362,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_RAS_EXTN, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_RAS_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR0_EL1_RAS_IMP, .cpu_enable = cpu_clear_disr, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, RAS, IMP) }, #endif /* CONFIG_ARM64_RAS_EXTN */ #ifdef CONFIG_ARM64_AMU_EXTN @@ -2401,12 +2377,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_AMU_EXTN, .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .matches = has_amu, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_AMU_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR0_EL1_AMU_IMP, .cpu_enable = cpu_amu_enable, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, AMU, IMP) }, #endif /* CONFIG_ARM64_AMU_EXTN */ { @@ -2426,34 +2398,22 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Stage-2 Force Write-Back", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAS_STAGE2_FWB, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_EL1_FWB_SHIFT, - .field_width = 4, - .min_field_value = 1, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, FWB, IMP) }, { .desc = "ARMv8.4 Translation Table Level", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_HAS_ARMv8_4_TTL, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_EL1_TTL_SHIFT, - .field_width = 4, - .min_field_value = 1, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, TTL, IMP) }, { .desc = "TLB range maintenance instructions", .capability = ARM64_HAS_TLB_RANGE, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_EL1_TLB_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = ID_AA64ISAR0_EL1_TLB_RANGE, + ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, TLB, RANGE) }, #ifdef CONFIG_ARM64_HW_AFDBM { @@ -2467,13 +2427,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { */ .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .capability = ARM64_HW_DBM, - .sys_reg = SYS_ID_AA64MMFR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR1_EL1_HAFDBS_SHIFT, - .field_width = 4, - .min_field_value = 2, .matches = has_hw_dbm, .cpu_enable = cpu_enable_hw_dbm, + ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, DBM) }, #endif { @@ -2481,21 +2437,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_CRC32, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_EL1_CRC32_SHIFT, - .field_width = 4, - .min_field_value = 1, + ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, CRC32, IMP) }, { .desc = "Speculative Store Bypassing Safe (SSBS)", .capability = ARM64_SSBS, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_EL1_SSBS_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = ID_AA64PFR1_EL1_SSBS_IMP, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SSBS, IMP) }, #ifdef CONFIG_ARM64_CNP { @@ -2503,12 +2452,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_CNP, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_useable_cnp, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_EL1_CnP_SHIFT, - .field_width = 4, - .min_field_value = 1, .cpu_enable = cpu_enable_cnp, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, CnP, IMP) }, #endif { @@ -2516,45 +2461,29 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_SB, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .field_pos = ID_AA64ISAR1_EL1_SB_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 1, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, SB, IMP) }, #ifdef CONFIG_ARM64_PTR_AUTH { .desc = "Address authentication (architected QARMA5 algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA5, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR1_EL1_APA_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64ISAR1_EL1_APA_PAuth, .matches = has_address_auth_cpucap, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, APA, PAuth) }, { .desc = "Address authentication (architected QARMA3 algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA3, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, - .sys_reg = SYS_ID_AA64ISAR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR2_EL1_APA3_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64ISAR2_EL1_APA3_PAuth, .matches = has_address_auth_cpucap, + ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, APA3, PAuth) }, { .desc = "Address authentication (IMP DEF algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR1_EL1_API_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64ISAR1_EL1_API_PAuth, .matches = has_address_auth_cpucap, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, API, PAuth) }, { .capability = ARM64_HAS_ADDRESS_AUTH, @@ -2565,34 +2494,22 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "Generic authentication (architected QARMA5 algorithm)", .capability = ARM64_HAS_GENERIC_AUTH_ARCH_QARMA5, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR1_EL1_GPA_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64ISAR1_EL1_GPA_IMP, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, GPA, IMP) }, { .desc = "Generic authentication (architected QARMA3 algorithm)", .capability = ARM64_HAS_GENERIC_AUTH_ARCH_QARMA3, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64ISAR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR2_EL1_GPA3_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64ISAR2_EL1_GPA3_IMP, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, GPA3, IMP) }, { .desc = "Generic authentication (IMP DEF algorithm)", .capability = ARM64_HAS_GENERIC_AUTH_IMP_DEF, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR1_EL1_GPI_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64ISAR1_EL1_GPI_IMP, .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, GPI, IMP) }, { .capability = ARM64_HAS_GENERIC_AUTH, @@ -2624,13 +2541,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .desc = "E0PD", .capability = ARM64_HAS_E0PD, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, - .field_width = 4, - .field_pos = ID_AA64MMFR2_EL1_E0PD_SHIFT, - .matches = has_cpuid_feature, - .min_field_value = 1, .cpu_enable = cpu_enable_e0pd, + .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, E0PD, IMP) }, #endif { @@ -2638,11 +2551,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_RNG, .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64ISAR0_EL1, - .field_pos = ID_AA64ISAR0_EL1_RNDR_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 1, + ARM64_CPUID_FIELDS(ID_AA64ISAR0_EL1, RNDR, IMP) }, #ifdef CONFIG_ARM64_BTI { @@ -2655,11 +2564,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { #endif .matches = has_cpuid_feature, .cpu_enable = bti_enable, - .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_EL1_BT_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR1_EL1_BT_IMP, - .sign = FTR_UNSIGNED, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, BT, IMP) }, #endif #ifdef CONFIG_ARM64_MTE @@ -2668,120 +2573,80 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_MTE, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_EL1_MTE_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR1_EL1_MTE_MTE2, - .sign = FTR_UNSIGNED, .cpu_enable = cpu_enable_mte, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, MTE, MTE2) }, { .desc = "Asymmetric MTE Tag Check Fault", .capability = ARM64_MTE_ASYMM, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_EL1_MTE_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR1_EL1_MTE_MTE3, - .sign = FTR_UNSIGNED, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, MTE, MTE3) }, #endif /* CONFIG_ARM64_MTE */ { .desc = "RCpc load-acquire (LDAPR)", .capability = ARM64_HAS_LDAPR, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64ISAR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR1_EL1_LRCPC_SHIFT, - .field_width = 4, .matches = has_cpuid_feature, - .min_field_value = 1, + ARM64_CPUID_FIELDS(ID_AA64ISAR1_EL1, LRCPC, IMP) }, #ifdef CONFIG_ARM64_SME { .desc = "Scalable Matrix Extension", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME, - .sys_reg = SYS_ID_AA64PFR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR1_EL1_SME_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR1_EL1_SME_IMP, .matches = has_cpuid_feature, .cpu_enable = sme_kernel_enable, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SME, IMP) }, /* FA64 should be sorted after the base SME capability */ { .desc = "FA64", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME_FA64, - .sys_reg = SYS_ID_AA64SMFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64SMFR0_EL1_FA64_SHIFT, - .field_width = 1, - .min_field_value = ID_AA64SMFR0_EL1_FA64_IMP, .matches = has_cpuid_feature, .cpu_enable = fa64_kernel_enable, + ARM64_CPUID_FIELDS(ID_AA64SMFR0_EL1, FA64, IMP) }, { .desc = "SME2", .type = ARM64_CPUCAP_SYSTEM_FEATURE, .capability = ARM64_SME2, - .sys_reg = SYS_ID_AA64PFR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR1_EL1_SME_SHIFT, - .field_width = ID_AA64PFR1_EL1_SME_WIDTH, - .min_field_value = ID_AA64PFR1_EL1_SME_SME2, .matches = has_cpuid_feature, .cpu_enable = sme2_kernel_enable, + ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, SME, SME2) }, #endif /* CONFIG_ARM64_SME */ { .desc = "WFx with timeout", .capability = ARM64_HAS_WFXT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64ISAR2_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64ISAR2_EL1_WFxT_SHIFT, - .field_width = 4, .matches = has_cpuid_feature, - .min_field_value = ID_AA64ISAR2_EL1_WFxT_IMP, + ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, WFxT, IMP) }, { .desc = "Trap EL0 IMPLEMENTATION DEFINED functionality", .capability = ARM64_HAS_TIDCP1, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64MMFR1_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR1_EL1_TIDCP1_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64MMFR1_EL1_TIDCP1_IMP, .matches = has_cpuid_feature, .cpu_enable = cpu_trap_el0_impdef, + ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, TIDCP1, IMP) }, { .desc = "Data independent timing control (DIT)", .capability = ARM64_HAS_DIT, .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_DIT_SHIFT, - .field_width = 4, - .min_field_value = ID_AA64PFR0_EL1_DIT_IMP, .matches = has_cpuid_feature, .cpu_enable = cpu_enable_dit, + ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, DIT, IMP) }, {}, }; #define HWCAP_CPUID_MATCH(reg, field, min_value) \ - .matches = has_user_cpuid_feature, \ - .sys_reg = SYS_##reg, \ - .field_pos = reg##_##field##_SHIFT, \ - .field_width = reg##_##field##_WIDTH, \ - .sign = reg##_##field##_SIGNED, \ - .min_field_value = reg##_##field##_##min_value, + .matches = has_user_cpuid_feature, \ + ARM64_CPUID_FIELDS(reg, field, min_value) #define __HWCAP_CAP(name, cap_type, cap) \ .desc = name, \ diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c index 2b65aae332ce..66cde752cd74 100644 --- a/arch/arm64/kernel/crash_core.c +++ b/arch/arm64/kernel/crash_core.c @@ -8,6 +8,7 @@ #include <asm/cpufeature.h> #include <asm/memory.h> #include <asm/pgtable-hwdef.h> +#include <asm/pointer_auth.h> static inline u64 get_tcr_el1_t1sz(void); diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 3da09778267e..64f2ecbdfe5c 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -438,6 +438,11 @@ int kernel_active_single_step(void) } NOKPROBE_SYMBOL(kernel_active_single_step); +void kernel_rewind_single_step(struct pt_regs *regs) +{ + set_regs_spsr_ss(regs); +} + /* ptrace API */ void user_enable_single_step(struct task_struct *task) { diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S index d731b4655df8..11d7f7de202d 100644 --- a/arch/arm64/kernel/efi-header.S +++ b/arch/arm64/kernel/efi-header.S @@ -81,9 +81,47 @@ .quad 0 // CertificationTable .quad 0 // BaseRelocationTable -#ifdef CONFIG_DEBUG_EFI +#if defined(CONFIG_DEBUG_EFI) || defined(CONFIG_ARM64_BTI_KERNEL) .long .Lefi_debug_table - .L_head // DebugTable .long .Lefi_debug_table_size + + /* + * The debug table is referenced via its Relative Virtual Address (RVA), + * which is only defined for those parts of the image that are covered + * by a section declaration. Since this header is not covered by any + * section, the debug table must be emitted elsewhere. So stick it in + * the .init.rodata section instead. + * + * Note that the payloads themselves are permitted to have zero RVAs, + * which means we can simply put those right after the section headers. + */ + __INITRODATA + + .align 2 +.Lefi_debug_table: +#ifdef CONFIG_DEBUG_EFI + // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long IMAGE_DEBUG_TYPE_CODEVIEW // Type + .long .Lefi_debug_entry_size // SizeOfData + .long 0 // RVA + .long .Lefi_debug_entry - .L_head // FileOffset +#endif +#ifdef CONFIG_ARM64_BTI_KERNEL + .long 0 // Characteristics + .long 0 // TimeDateStamp + .short 0 // MajorVersion + .short 0 // MinorVersion + .long IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS // Type + .long 4 // SizeOfData + .long 0 // RVA + .long .Lefi_dll_characteristics_ex - .L_head // FileOffset +#endif + .set .Lefi_debug_table_size, . - .Lefi_debug_table + .previous #endif // Section table @@ -119,33 +157,6 @@ .set .Lsection_count, (. - .Lsection_table) / 40 #ifdef CONFIG_DEBUG_EFI - /* - * The debug table is referenced via its Relative Virtual Address (RVA), - * which is only defined for those parts of the image that are covered - * by a section declaration. Since this header is not covered by any - * section, the debug table must be emitted elsewhere. So stick it in - * the .init.rodata section instead. - * - * Note that the EFI debug entry itself may legally have a zero RVA, - * which means we can simply put it right after the section headers. - */ - __INITRODATA - - .align 2 -.Lefi_debug_table: - // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY - .long 0 // Characteristics - .long 0 // TimeDateStamp - .short 0 // MajorVersion - .short 0 // MinorVersion - .long IMAGE_DEBUG_TYPE_CODEVIEW // Type - .long .Lefi_debug_entry_size // SizeOfData - .long 0 // RVA - .long .Lefi_debug_entry - .L_head // FileOffset - - .set .Lefi_debug_table_size, . - .Lefi_debug_table - .previous - .Lefi_debug_entry: // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY .ascii "NB10" // Signature @@ -157,6 +168,10 @@ .set .Lefi_debug_entry_size, . - .Lefi_debug_entry #endif +#ifdef CONFIG_ARM64_BTI_KERNEL +.Lefi_dll_characteristics_ex: + .long IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT +#endif .balign SEGMENT_ALIGN .Lefi_header_end: diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index cce1167199e3..3af3c01c93a6 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -840,7 +840,7 @@ UNHANDLED(el0t, 32, error) #endif /* CONFIG_COMPAT */ #ifdef CONFIG_VMAP_STACK -asmlinkage void noinstr handle_bad_stack(struct pt_regs *regs) +asmlinkage void noinstr __noreturn handle_bad_stack(struct pt_regs *regs) { unsigned long esr = read_sysreg(esr_el1); unsigned long far = read_sysreg(far_el1); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 350ed81324ac..1c38a60575aa 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -36,6 +36,31 @@ SYM_CODE_START(ftrace_caller) bti c +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * The literal pointer to the ops is at an 8-byte aligned boundary + * which is either 12 or 16 bytes before the BL instruction in the call + * site. See ftrace_call_adjust() for details. + * + * Therefore here the LR points at `literal + 16` or `literal + 20`, + * and we can find the address of the literal in either case by + * aligning to an 8-byte boundary and subtracting 16. We do the + * alignment first as this allows us to fold the subtraction into the + * LDR. + */ + bic x11, x30, 0x7 + ldr x11, [x11, #-(4 * AARCH64_INSN_SIZE)] // op + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + ldr x17, [x11, #FTRACE_OPS_DIRECT_CALL] // op->direct_call + cbnz x17, ftrace_caller_direct +#endif +#endif + /* Save original SP */ mov x10, sp @@ -49,6 +74,10 @@ SYM_CODE_START(ftrace_caller) stp x6, x7, [sp, #FREGS_X6] str x8, [sp, #FREGS_X8] +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + str xzr, [sp, #FREGS_DIRECT_TRAMP] +#endif + /* Save the callsite's FP, LR, SP */ str x29, [sp, #FREGS_FP] str x9, [sp, #FREGS_LR] @@ -71,20 +100,7 @@ SYM_CODE_START(ftrace_caller) mov x3, sp // regs #ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS - /* - * The literal pointer to the ops is at an 8-byte aligned boundary - * which is either 12 or 16 bytes before the BL instruction in the call - * site. See ftrace_call_adjust() for details. - * - * Therefore here the LR points at `literal + 16` or `literal + 20`, - * and we can find the address of the literal in either case by - * aligning to an 8-byte boundary and subtracting 16. We do the - * alignment first as this allows us to fold the subtraction into the - * LDR. - */ - bic x2, x30, 0x7 - ldr x2, [x2, #-16] // op - + mov x2, x11 // op ldr x4, [x2, #FTRACE_OPS_FUNC] // op->func blr x4 // op->func(ip, parent_ip, op, regs) @@ -107,8 +123,15 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) ldp x6, x7, [sp, #FREGS_X6] ldr x8, [sp, #FREGS_X8] - /* Restore the callsite's FP, LR, PC */ + /* Restore the callsite's FP */ ldr x29, [sp, #FREGS_FP] + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + ldr x17, [sp, #FREGS_DIRECT_TRAMP] + cbnz x17, ftrace_caller_direct_late +#endif + + /* Restore the callsite's LR and PC */ ldr x30, [sp, #FREGS_LR] ldr x9, [sp, #FREGS_PC] @@ -116,8 +139,45 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) add sp, sp, #FREGS_SIZE + 32 ret x9 + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct_late, SYM_L_LOCAL) + /* + * Head to a direct trampoline in x17 after having run other tracers. + * The ftrace_regs are live, and x0-x8 and FP have been restored. The + * LR, PC, and SP have not been restored. + */ + + /* + * Restore the callsite's LR and PC matching the trampoline calling + * convention. + */ + ldr x9, [sp, #FREGS_LR] + ldr x30, [sp, #FREGS_PC] + + /* Restore the callsite's SP */ + add sp, sp, #FREGS_SIZE + 32 + +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) + /* + * Head to a direct trampoline in x17. + * + * We use `BR X17` as this can safely land on a `BTI C` or `PACIASP` in + * the trampoline, and will not unbalance any return stack. + */ + br x17 +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ SYM_CODE_END(ftrace_caller) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + bti c + mov x10, x30 + mov x30, x9 + ret x10 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ /* diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 9e7e50a0fd76..2fbafa5cc7ac 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, /* * TIF_SME controls whether a task can use SME without trapping while * in userspace, when TIF_SME is set then we must have storage - * alocated in sve_state and sme_state to store the contents of both ZA + * allocated in sve_state and sme_state to store the contents of both ZA * and the SVE registers for both streaming and non-streaming modes. * * If both SVCR.ZA and SVCR.SM are disabled then at any point we @@ -1477,7 +1477,7 @@ void do_sve_acc(unsigned long esr, struct pt_regs *regs) * * TIF_SME should be clear on entry: otherwise, fpsimd_restore_current_state() * would have disabled the SME access trap for userspace during - * ret_to_user, making an SVE access trap impossible in that case. + * ret_to_user, making an SME access trap impossible in that case. */ void do_sme_acc(unsigned long esr, struct pt_regs *regs) { diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 5545fe1a9012..432626c866a8 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -195,15 +195,22 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } -static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) +static struct plt_entry *get_ftrace_plt(struct module *mod) { #ifdef CONFIG_ARM64_MODULE_PLTS struct plt_entry *plt = mod->arch.ftrace_trampolines; - if (addr == FTRACE_ADDR) - return &plt[FTRACE_PLT_IDX]; -#endif + return &plt[FTRACE_PLT_IDX]; +#else return NULL; +#endif +} + +static bool reachable_by_bl(unsigned long addr, unsigned long pc) +{ + long offset = (long)addr - (long)pc; + + return offset >= -SZ_128M && offset < SZ_128M; } /* @@ -220,14 +227,21 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, unsigned long *addr) { unsigned long pc = rec->ip; - long offset = (long)*addr - (long)pc; struct plt_entry *plt; /* + * If a custom trampoline is unreachable, rely on the ftrace_caller + * trampoline which knows how to indirectly reach that trampoline + * through ops->direct_call. + */ + if (*addr != FTRACE_ADDR && !reachable_by_bl(*addr, pc)) + *addr = FTRACE_ADDR; + + /* * When the target is within range of the 'BL' instruction, use 'addr' * as-is and branch to that directly. */ - if (offset >= -SZ_128M && offset < SZ_128M) + if (reachable_by_bl(*addr, pc)) return true; /* @@ -256,7 +270,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, if (WARN_ON(!mod)) return false; - plt = get_ftrace_plt(mod, *addr); + plt = get_ftrace_plt(mod); if (!plt) { pr_err("ftrace: no module PLT for %ps\n", (void *)*addr); return false; @@ -330,12 +344,24 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { - if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller)) + unsigned long pc = rec->ip; + u32 old, new; + int ret; + + ret = ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec)); + if (ret) + return ret; + + if (!ftrace_find_callable_addr(rec, NULL, &old_addr)) return -EINVAL; - if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller)) + if (!ftrace_find_callable_addr(rec, NULL, &addr)) return -EINVAL; - return ftrace_rec_update_ops(rec); + old = aarch64_insn_gen_branch_imm(pc, old_addr, + AARCH64_INSN_BRANCH_LINK); + new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); + + return ftrace_modify_code(pc, old, new, true); } #endif diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b98970907226..e92caebff46a 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -150,8 +150,8 @@ CPU_BE( tbz x19, #SCTLR_ELx_EE_SHIFT, 1f ) pre_disable_mmu_workaround msr sctlr_el2, x19 b 3f - pre_disable_mmu_workaround -2: msr sctlr_el1, x19 +2: pre_disable_mmu_workaround + msr sctlr_el1, x19 3: isb mov x19, xzr ret diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index d833d78a7f31..370ab84fd06e 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -167,7 +167,7 @@ static const struct { } aliases[] __initconst = { { "kvm-arm.mode=nvhe", "id_aa64mmfr1.vh=0" }, { "kvm-arm.mode=protected", "id_aa64mmfr1.vh=0" }, - { "arm64.nosve", "id_aa64pfr0.sve=0 id_aa64pfr1.sme=0" }, + { "arm64.nosve", "id_aa64pfr0.sve=0" }, { "arm64.nosme", "id_aa64pfr1.sme=0" }, { "arm64.nobti", "id_aa64pfr1.bt=0" }, { "arm64.nopauth", @@ -178,6 +178,13 @@ static const struct { { "nokaslr", "kaslr.disabled=1" }, }; +static int __init parse_nokaslr(char *unused) +{ + /* nokaslr param handling is done by early cpufeature code */ + return 0; +} +early_param("nokaslr", parse_nokaslr); + static int __init find_field(const char *cmdline, const struct ftr_set_desc *reg, int f, u64 *v) { diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 8309197c0ebd..35f3c7959513 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -108,4 +108,8 @@ KVM_NVHE_ALIAS(kvm_protected_mode_initialized); #endif /* CONFIG_KVM */ +#ifdef CONFIG_EFI_ZBOOT +_kernel_codesize = ABSOLUTE(__inittext_end - _text); +#endif + #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index cda9c1e9864f..4e1f983df3d1 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -224,6 +224,8 @@ int kgdb_arch_handle_exception(int exception_vector, int signo, */ if (!kernel_active_single_step()) kernel_enable_single_step(linux_regs); + else + kernel_rewind_single_step(linux_regs); err = 0; break; default: diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index ce3d40120f72..078910db77a4 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/kexec.h> #include <linux/page-flags.h> +#include <linux/reboot.h> #include <linux/set_memory.h> #include <linux/smp.h> @@ -102,7 +103,7 @@ static void kexec_segment_flush(const struct kimage *kimage) /* Allocates pages for kexec page table */ static void *kexec_page_alloc(void *arg) { - struct kimage *kimage = (struct kimage *)arg; + struct kimage *kimage = arg; struct page *page = kimage_alloc_control_pages(kimage, 0); void *vaddr = NULL; @@ -268,26 +269,6 @@ void machine_crash_shutdown(struct pt_regs *regs) pr_info("Starting crashdump kernel...\n"); } -void arch_kexec_protect_crashkres(void) -{ - int i; - - for (i = 0; i < kexec_crash_image->nr_segments; i++) - set_memory_valid( - __phys_to_virt(kexec_crash_image->segment[i].mem), - kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0); -} - -void arch_kexec_unprotect_crashkres(void) -{ - int i; - - for (i = 0; i < kexec_crash_image->nr_segments; i++) - set_memory_valid( - __phys_to_virt(kexec_crash_image->segment[i].mem), - kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1); -} - #ifdef CONFIG_HIBERNATION /* * To preserve the crash dump kernel image, the relevant memory segments diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 5a0a8f552a61..543493bf924d 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -65,17 +65,12 @@ static bool plt_entries_equal(const struct plt_entry *a, (q + aarch64_insn_adrp_get_offset(le32_to_cpu(b->adrp))); } -static bool in_init(const struct module *mod, void *loc) -{ - return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size; -} - u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, void *loc, const Elf64_Rela *rela, Elf64_Sym *sym) { - struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : - &mod->arch.init; + struct mod_plt_sec *pltsec = !within_module_init((unsigned long)loc, mod) ? + &mod->arch.core : &mod->arch.init; struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr; int i = pltsec->plt_num_entries; int j = i - 1; @@ -105,8 +100,8 @@ u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs, void *loc, u64 val) { - struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : - &mod->arch.init; + struct mod_plt_sec *pltsec = !within_module_init((unsigned long)loc, mod) ? + &mod->arch.core : &mod->arch.init; struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr; int i = pltsec->plt_num_entries++; u32 br; diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 65b196e3ca6c..6d157f32187b 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -38,7 +38,7 @@ user_backtrace(struct frame_tail __user *tail, if (err) return NULL; - lr = ptrauth_strip_insn_pac(buftail.lr); + lr = ptrauth_strip_user_insn_pac(buftail.lr); perf_callchain_store(entry, lr); diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c deleted file mode 100644 index dde06c0f97f3..000000000000 --- a/arch/arm64/kernel/perf_event.c +++ /dev/null @@ -1,1467 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * ARMv8 PMUv3 Performance Events handling code. - * - * Copyright (C) 2012 ARM Limited - * Author: Will Deacon <will.deacon@arm.com> - * - * This code is based heavily on the ARMv7 perf event code. - */ - -#include <asm/irq_regs.h> -#include <asm/perf_event.h> -#include <asm/sysreg.h> -#include <asm/virt.h> - -#include <clocksource/arm_arch_timer.h> - -#include <linux/acpi.h> -#include <linux/clocksource.h> -#include <linux/kvm_host.h> -#include <linux/of.h> -#include <linux/perf/arm_pmu.h> -#include <linux/platform_device.h> -#include <linux/sched_clock.h> -#include <linux/smp.h> - -/* ARMv8 Cortex-A53 specific event types. */ -#define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 - -/* ARMv8 Cavium ThunderX specific event types. */ -#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST 0xE9 -#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS 0xEA -#define ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS 0xEB -#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS 0xEC -#define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS 0xED - -/* - * ARMv8 Architectural defined events, not all of these may - * be supported on any given implementation. Unsupported events will - * be disabled at run-time based on the PMCEID registers. - */ -static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { - PERF_MAP_ALL_UNSUPPORTED, - [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES, - [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED, - [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, - [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, - [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED, - [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, - [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, - [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND, - [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND, -}; - -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] = { - PERF_CACHE_MAP_ALL_UNSUPPORTED, - - [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, - [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, - - [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE, - [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL, - - [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL, - [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB, - - [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL, - [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB, - - [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD, - [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_LL_CACHE_RD, - - [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED, - [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_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_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREF_LINEFILL, - - [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD, - [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR, -}; - -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_IMPDEF_PERFCTR_L1D_CACHE_RD, - [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD, - [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, - [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR, - - [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD, - [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR, - - [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD, - [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR, -}; - -static const unsigned armv8_a73_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_IMPDEF_PERFCTR_L1D_CACHE_RD, - [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, -}; - -static const unsigned armv8_thunder_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_IMPDEF_PERFCTR_L1D_CACHE_RD, - [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD, - [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, - [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_MISS_ST, - [C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS, - [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS, - - [C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS, - [C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS, - - [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD, - [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD, - [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR, - [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR, -}; - -static const unsigned armv8_vulcan_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_IMPDEF_PERFCTR_L1D_CACHE_RD, - [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD, - [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR, - [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR, - - [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD, - [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR, - [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD, - [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR, - - [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD, - [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR, -}; - -static ssize_t -armv8pmu_events_sysfs_show(struct device *dev, - struct device_attribute *attr, char *page) -{ - struct perf_pmu_events_attr *pmu_attr; - - pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr); - - return sprintf(page, "event=0x%04llx\n", pmu_attr->id); -} - -#define ARMV8_EVENT_ATTR(name, config) \ - PMU_EVENT_ATTR_ID(name, armv8pmu_events_sysfs_show, config) - -static struct attribute *armv8_pmuv3_event_attrs[] = { - ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), - ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), - ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), - ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL), - ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1D_CACHE), - ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL), - ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_LD_RETIRED), - ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_ST_RETIRED), - ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INST_RETIRED), - ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN), - ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_RETURN), - ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED), - ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED), - ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED), - ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED), - ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED), - ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED), - ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CPU_CYCLES), - ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_BR_PRED), - ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS), - ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1I_CACHE), - ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB), - ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2D_CACHE), - ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL), - ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB), - ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS), - ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEMORY_ERROR), - ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_INST_SPEC), - ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED), - ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES), - /* Don't expose the chain event in /sys, since it's useless in isolation */ - ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE), - ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE), - ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED), - ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED), - ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND), - ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND), - ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB), - ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB), - ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE), - ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL), - ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE), - ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL), - ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE), - ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB), - ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL), - ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL), - ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB), - ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB), - ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS), - ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE), - ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS), - ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK), - ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK), - ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD), - ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD), - ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD), - ARMV8_EVENT_ATTR(l1d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD), - ARMV8_EVENT_ATTR(op_retired, ARMV8_PMUV3_PERFCTR_OP_RETIRED), - ARMV8_EVENT_ATTR(op_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC), - ARMV8_EVENT_ATTR(stall, ARMV8_PMUV3_PERFCTR_STALL), - ARMV8_EVENT_ATTR(stall_slot_backend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND), - ARMV8_EVENT_ATTR(stall_slot_frontend, ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND), - ARMV8_EVENT_ATTR(stall_slot, ARMV8_PMUV3_PERFCTR_STALL_SLOT), - ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP), - ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED), - ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE), - ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION), - ARMV8_EVENT_ATTR(cnt_cycles, ARMV8_AMU_PERFCTR_CNT_CYCLES), - ARMV8_EVENT_ATTR(stall_backend_mem, ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM), - ARMV8_EVENT_ATTR(l1i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS), - ARMV8_EVENT_ATTR(l2d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD), - ARMV8_EVENT_ATTR(l2i_cache_lmiss, ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS), - ARMV8_EVENT_ATTR(l3d_cache_lmiss_rd, ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD), - ARMV8_EVENT_ATTR(trb_wrap, ARMV8_PMUV3_PERFCTR_TRB_WRAP), - ARMV8_EVENT_ATTR(trb_trig, ARMV8_PMUV3_PERFCTR_TRB_TRIG), - ARMV8_EVENT_ATTR(trcextout0, ARMV8_PMUV3_PERFCTR_TRCEXTOUT0), - ARMV8_EVENT_ATTR(trcextout1, ARMV8_PMUV3_PERFCTR_TRCEXTOUT1), - ARMV8_EVENT_ATTR(trcextout2, ARMV8_PMUV3_PERFCTR_TRCEXTOUT2), - ARMV8_EVENT_ATTR(trcextout3, ARMV8_PMUV3_PERFCTR_TRCEXTOUT3), - ARMV8_EVENT_ATTR(cti_trigout4, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4), - ARMV8_EVENT_ATTR(cti_trigout5, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5), - ARMV8_EVENT_ATTR(cti_trigout6, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6), - ARMV8_EVENT_ATTR(cti_trigout7, ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7), - ARMV8_EVENT_ATTR(ldst_align_lat, ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT), - ARMV8_EVENT_ATTR(ld_align_lat, ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT), - ARMV8_EVENT_ATTR(st_align_lat, ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT), - ARMV8_EVENT_ATTR(mem_access_checked, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED), - ARMV8_EVENT_ATTR(mem_access_checked_rd, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD), - ARMV8_EVENT_ATTR(mem_access_checked_wr, ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR), - NULL, -}; - -static umode_t -armv8pmu_event_attr_is_visible(struct kobject *kobj, - struct attribute *attr, int unused) -{ - struct device *dev = kobj_to_dev(kobj); - struct pmu *pmu = dev_get_drvdata(dev); - struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - struct perf_pmu_events_attr *pmu_attr; - - pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); - - if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS && - test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap)) - return attr->mode; - - if (pmu_attr->id >= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE) { - u64 id = pmu_attr->id - ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; - - if (id < ARMV8_PMUV3_MAX_COMMON_EVENTS && - test_bit(id, cpu_pmu->pmceid_ext_bitmap)) - return attr->mode; - } - - return 0; -} - -static const struct attribute_group armv8_pmuv3_events_attr_group = { - .name = "events", - .attrs = armv8_pmuv3_event_attrs, - .is_visible = armv8pmu_event_attr_is_visible, -}; - -PMU_FORMAT_ATTR(event, "config:0-15"); -PMU_FORMAT_ATTR(long, "config1:0"); -PMU_FORMAT_ATTR(rdpmc, "config1:1"); - -static int sysctl_perf_user_access __read_mostly; - -static inline bool armv8pmu_event_is_64bit(struct perf_event *event) -{ - return event->attr.config1 & 0x1; -} - -static inline bool armv8pmu_event_want_user_access(struct perf_event *event) -{ - return event->attr.config1 & 0x2; -} - -static struct attribute *armv8_pmuv3_format_attrs[] = { - &format_attr_event.attr, - &format_attr_long.attr, - &format_attr_rdpmc.attr, - NULL, -}; - -static const struct attribute_group armv8_pmuv3_format_attr_group = { - .name = "format", - .attrs = armv8_pmuv3_format_attrs, -}; - -static ssize_t slots_show(struct device *dev, struct device_attribute *attr, - char *page) -{ - struct pmu *pmu = dev_get_drvdata(dev); - struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK; - - return sysfs_emit(page, "0x%08x\n", slots); -} - -static DEVICE_ATTR_RO(slots); - -static ssize_t bus_slots_show(struct device *dev, struct device_attribute *attr, - char *page) -{ - struct pmu *pmu = dev_get_drvdata(dev); - struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - u32 bus_slots = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_SLOTS_SHIFT) - & ARMV8_PMU_BUS_SLOTS_MASK; - - return sysfs_emit(page, "0x%08x\n", bus_slots); -} - -static DEVICE_ATTR_RO(bus_slots); - -static ssize_t bus_width_show(struct device *dev, struct device_attribute *attr, - char *page) -{ - struct pmu *pmu = dev_get_drvdata(dev); - struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu); - u32 bus_width = (cpu_pmu->reg_pmmir >> ARMV8_PMU_BUS_WIDTH_SHIFT) - & ARMV8_PMU_BUS_WIDTH_MASK; - u32 val = 0; - - /* Encoded as Log2(number of bytes), plus one */ - if (bus_width > 2 && bus_width < 13) - val = 1 << (bus_width - 1); - - return sysfs_emit(page, "0x%08x\n", val); -} - -static DEVICE_ATTR_RO(bus_width); - -static struct attribute *armv8_pmuv3_caps_attrs[] = { - &dev_attr_slots.attr, - &dev_attr_bus_slots.attr, - &dev_attr_bus_width.attr, - NULL, -}; - -static const struct attribute_group armv8_pmuv3_caps_attr_group = { - .name = "caps", - .attrs = armv8_pmuv3_caps_attrs, -}; - -/* - * Perf Events' indices - */ -#define ARMV8_IDX_CYCLE_COUNTER 0 -#define ARMV8_IDX_COUNTER0 1 -#define ARMV8_IDX_CYCLE_COUNTER_USER 32 - -/* - * We unconditionally enable ARMv8.5-PMU long event counter support - * (64-bit events) where supported. Indicate if this arm_pmu has long - * event counter support. - */ -static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu) -{ - return (cpu_pmu->pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P5); -} - -static inline bool armv8pmu_event_has_user_read(struct perf_event *event) -{ - return event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT; -} - -/* - * We must chain two programmable counters for 64 bit events, - * except when we have allocated the 64bit cycle counter (for CPU - * cycles event) or when user space counter access is enabled. - */ -static inline bool armv8pmu_event_is_chained(struct perf_event *event) -{ - int idx = event->hw.idx; - struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); - - return !armv8pmu_event_has_user_read(event) && - armv8pmu_event_is_64bit(event) && - !armv8pmu_has_long_event(cpu_pmu) && - (idx != ARMV8_IDX_CYCLE_COUNTER); -} - -/* - * ARMv8 low level PMU access - */ - -/* - * Perf Event to low level counters mapping - */ -#define ARMV8_IDX_TO_COUNTER(x) \ - (((x) - ARMV8_IDX_COUNTER0) & ARMV8_PMU_COUNTER_MASK) - -/* - * This code is really good - */ - -#define PMEVN_CASE(n, case_macro) \ - case n: case_macro(n); break - -#define PMEVN_SWITCH(x, case_macro) \ - do { \ - switch (x) { \ - PMEVN_CASE(0, case_macro); \ - PMEVN_CASE(1, case_macro); \ - PMEVN_CASE(2, case_macro); \ - PMEVN_CASE(3, case_macro); \ - PMEVN_CASE(4, case_macro); \ - PMEVN_CASE(5, case_macro); \ - PMEVN_CASE(6, case_macro); \ - PMEVN_CASE(7, case_macro); \ - PMEVN_CASE(8, case_macro); \ - PMEVN_CASE(9, case_macro); \ - PMEVN_CASE(10, case_macro); \ - PMEVN_CASE(11, case_macro); \ - PMEVN_CASE(12, case_macro); \ - PMEVN_CASE(13, case_macro); \ - PMEVN_CASE(14, case_macro); \ - PMEVN_CASE(15, case_macro); \ - PMEVN_CASE(16, case_macro); \ - PMEVN_CASE(17, case_macro); \ - PMEVN_CASE(18, case_macro); \ - PMEVN_CASE(19, case_macro); \ - PMEVN_CASE(20, case_macro); \ - PMEVN_CASE(21, case_macro); \ - PMEVN_CASE(22, case_macro); \ - PMEVN_CASE(23, case_macro); \ - PMEVN_CASE(24, case_macro); \ - PMEVN_CASE(25, case_macro); \ - PMEVN_CASE(26, case_macro); \ - PMEVN_CASE(27, case_macro); \ - PMEVN_CASE(28, case_macro); \ - PMEVN_CASE(29, case_macro); \ - PMEVN_CASE(30, case_macro); \ - default: WARN(1, "Invalid PMEV* index\n"); \ - } \ - } while (0) - -#define RETURN_READ_PMEVCNTRN(n) \ - return read_sysreg(pmevcntr##n##_el0) -static unsigned long read_pmevcntrn(int n) -{ - PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN); - return 0; -} - -#define WRITE_PMEVCNTRN(n) \ - write_sysreg(val, pmevcntr##n##_el0) -static void write_pmevcntrn(int n, unsigned long val) -{ - PMEVN_SWITCH(n, WRITE_PMEVCNTRN); -} - -#define WRITE_PMEVTYPERN(n) \ - write_sysreg(val, pmevtyper##n##_el0) -static void write_pmevtypern(int n, unsigned long val) -{ - PMEVN_SWITCH(n, WRITE_PMEVTYPERN); -} - -static inline u32 armv8pmu_pmcr_read(void) -{ - return read_sysreg(pmcr_el0); -} - -static inline void armv8pmu_pmcr_write(u32 val) -{ - val &= ARMV8_PMU_PMCR_MASK; - isb(); - write_sysreg(val, pmcr_el0); -} - -static inline int armv8pmu_has_overflowed(u32 pmovsr) -{ - return pmovsr & ARMV8_PMU_OVERFLOWED_MASK; -} - -static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx) -{ - return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx)); -} - -static inline u64 armv8pmu_read_evcntr(int idx) -{ - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - - return read_pmevcntrn(counter); -} - -static inline u64 armv8pmu_read_hw_counter(struct perf_event *event) -{ - int idx = event->hw.idx; - u64 val = armv8pmu_read_evcntr(idx); - - if (armv8pmu_event_is_chained(event)) - val = (val << 32) | armv8pmu_read_evcntr(idx - 1); - return val; -} - -/* - * The cycle counter is always a 64-bit counter. When ARMV8_PMU_PMCR_LP - * is set the event counters also become 64-bit counters. Unless the - * user has requested a long counter (attr.config1) then we want to - * interrupt upon 32-bit overflow - we achieve this by applying a bias. - */ -static bool armv8pmu_event_needs_bias(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; - - if (armv8pmu_event_is_64bit(event)) - return false; - - if (armv8pmu_has_long_event(cpu_pmu) || - idx == ARMV8_IDX_CYCLE_COUNTER) - return true; - - return false; -} - -static u64 armv8pmu_bias_long_counter(struct perf_event *event, u64 value) -{ - if (armv8pmu_event_needs_bias(event)) - value |= GENMASK(63, 32); - - return value; -} - -static u64 armv8pmu_unbias_long_counter(struct perf_event *event, u64 value) -{ - if (armv8pmu_event_needs_bias(event)) - value &= ~GENMASK(63, 32); - - return value; -} - -static u64 armv8pmu_read_counter(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - u64 value; - - if (idx == ARMV8_IDX_CYCLE_COUNTER) - value = read_sysreg(pmccntr_el0); - else - value = armv8pmu_read_hw_counter(event); - - return armv8pmu_unbias_long_counter(event, value); -} - -static inline void armv8pmu_write_evcntr(int idx, u64 value) -{ - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - - write_pmevcntrn(counter, value); -} - -static inline void armv8pmu_write_hw_counter(struct perf_event *event, - u64 value) -{ - int idx = event->hw.idx; - - if (armv8pmu_event_is_chained(event)) { - armv8pmu_write_evcntr(idx, upper_32_bits(value)); - armv8pmu_write_evcntr(idx - 1, lower_32_bits(value)); - } else { - armv8pmu_write_evcntr(idx, value); - } -} - -static void armv8pmu_write_counter(struct perf_event *event, u64 value) -{ - struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - - value = armv8pmu_bias_long_counter(event, value); - - if (idx == ARMV8_IDX_CYCLE_COUNTER) - write_sysreg(value, pmccntr_el0); - else - armv8pmu_write_hw_counter(event, value); -} - -static inline void armv8pmu_write_evtype(int idx, u32 val) -{ - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - - val &= ARMV8_PMU_EVTYPE_MASK; - write_pmevtypern(counter, val); -} - -static inline void armv8pmu_write_event_type(struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - int idx = hwc->idx; - - /* - * For chained events, the low counter is programmed to count - * the event of interest and the high counter is programmed - * with CHAIN event code with filters set to count at all ELs. - */ - if (armv8pmu_event_is_chained(event)) { - u32 chain_evt = ARMV8_PMUV3_PERFCTR_CHAIN | - ARMV8_PMU_INCLUDE_EL2; - - armv8pmu_write_evtype(idx - 1, hwc->config_base); - armv8pmu_write_evtype(idx, chain_evt); - } else { - if (idx == ARMV8_IDX_CYCLE_COUNTER) - write_sysreg(hwc->config_base, pmccfiltr_el0); - else - armv8pmu_write_evtype(idx, hwc->config_base); - } -} - -static u32 armv8pmu_event_cnten_mask(struct perf_event *event) -{ - int counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); - u32 mask = BIT(counter); - - if (armv8pmu_event_is_chained(event)) - mask |= BIT(counter - 1); - return mask; -} - -static inline void armv8pmu_enable_counter(u32 mask) -{ - /* - * Make sure event configuration register writes are visible before we - * enable the counter. - * */ - isb(); - write_sysreg(mask, pmcntenset_el0); -} - -static inline void armv8pmu_enable_event_counter(struct perf_event *event) -{ - struct perf_event_attr *attr = &event->attr; - u32 mask = armv8pmu_event_cnten_mask(event); - - kvm_set_pmu_events(mask, attr); - - /* We rely on the hypervisor switch code to enable guest counters */ - if (!kvm_pmu_counter_deferred(attr)) - armv8pmu_enable_counter(mask); -} - -static inline void armv8pmu_disable_counter(u32 mask) -{ - write_sysreg(mask, pmcntenclr_el0); - /* - * Make sure the effects of disabling the counter are visible before we - * start configuring the event. - */ - isb(); -} - -static inline void armv8pmu_disable_event_counter(struct perf_event *event) -{ - struct perf_event_attr *attr = &event->attr; - u32 mask = armv8pmu_event_cnten_mask(event); - - kvm_clr_pmu_events(mask); - - /* We rely on the hypervisor switch code to disable guest counters */ - if (!kvm_pmu_counter_deferred(attr)) - armv8pmu_disable_counter(mask); -} - -static inline void armv8pmu_enable_intens(u32 mask) -{ - write_sysreg(mask, pmintenset_el1); -} - -static inline void armv8pmu_enable_event_irq(struct perf_event *event) -{ - u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); - armv8pmu_enable_intens(BIT(counter)); -} - -static inline void armv8pmu_disable_intens(u32 mask) -{ - write_sysreg(mask, pmintenclr_el1); - isb(); - /* Clear the overflow flag in case an interrupt is pending. */ - write_sysreg(mask, pmovsclr_el0); - isb(); -} - -static inline void armv8pmu_disable_event_irq(struct perf_event *event) -{ - u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); - armv8pmu_disable_intens(BIT(counter)); -} - -static inline u32 armv8pmu_getreset_flags(void) -{ - u32 value; - - /* Read */ - value = read_sysreg(pmovsclr_el0); - - /* Write to clear flags */ - value &= ARMV8_PMU_OVSR_MASK; - write_sysreg(value, pmovsclr_el0); - - return value; -} - -static void armv8pmu_disable_user_access(void) -{ - write_sysreg(0, pmuserenr_el0); -} - -static void armv8pmu_enable_user_access(struct arm_pmu *cpu_pmu) -{ - int i; - struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); - - /* Clear any unused counters to avoid leaking their contents */ - for_each_clear_bit(i, cpuc->used_mask, cpu_pmu->num_events) { - if (i == ARMV8_IDX_CYCLE_COUNTER) - write_sysreg(0, pmccntr_el0); - else - armv8pmu_write_evcntr(i, 0); - } - - write_sysreg(0, pmuserenr_el0); - write_sysreg(ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_CR, pmuserenr_el0); -} - -static void armv8pmu_enable_event(struct perf_event *event) -{ - /* - * Enable counter and interrupt, and set the counter to count - * the event that we're interested in. - */ - - /* - * Disable counter - */ - armv8pmu_disable_event_counter(event); - - /* - * Set event. - */ - armv8pmu_write_event_type(event); - - /* - * Enable interrupt for this counter - */ - armv8pmu_enable_event_irq(event); - - /* - * Enable counter - */ - armv8pmu_enable_event_counter(event); -} - -static void armv8pmu_disable_event(struct perf_event *event) -{ - /* - * Disable counter - */ - armv8pmu_disable_event_counter(event); - - /* - * Disable interrupt for this counter - */ - armv8pmu_disable_event_irq(event); -} - -static void armv8pmu_start(struct arm_pmu *cpu_pmu) -{ - struct perf_event_context *ctx; - int nr_user = 0; - - ctx = perf_cpu_task_ctx(); - if (ctx) - nr_user = ctx->nr_user; - - if (sysctl_perf_user_access && nr_user) - armv8pmu_enable_user_access(cpu_pmu); - else - armv8pmu_disable_user_access(); - - /* Enable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E); -} - -static void armv8pmu_stop(struct arm_pmu *cpu_pmu) -{ - /* Disable all counters */ - armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E); -} - -static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu) -{ - u32 pmovsr; - struct perf_sample_data data; - struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); - struct pt_regs *regs; - int idx; - - /* - * Get and reset the IRQ flags - */ - pmovsr = armv8pmu_getreset_flags(); - - /* - * Did an overflow occur? - */ - if (!armv8pmu_has_overflowed(pmovsr)) - return IRQ_NONE; - - /* - * Handle the counter(s) overflow(s) - */ - regs = get_irq_regs(); - - /* - * Stop the PMU while processing the counter overflows - * to prevent skews in group events. - */ - armv8pmu_stop(cpu_pmu); - for (idx = 0; idx < cpu_pmu->num_events; ++idx) { - struct perf_event *event = cpuc->events[idx]; - struct hw_perf_event *hwc; - - /* Ignore if we don't have an event. */ - if (!event) - continue; - - /* - * We have a single interrupt for all counters. Check that - * each counter has overflowed before we process it. - */ - if (!armv8pmu_counter_has_overflowed(pmovsr, idx)) - continue; - - hwc = &event->hw; - armpmu_event_update(event); - perf_sample_data_init(&data, 0, hwc->last_period); - if (!armpmu_event_set_period(event)) - continue; - - /* - * Perf event overflow will queue the processing of the event as - * an irq_work which will be taken care of in the handling of - * IPI_IRQ_WORK. - */ - if (perf_event_overflow(event, &data, regs)) - cpu_pmu->disable(event); - } - armv8pmu_start(cpu_pmu); - - return IRQ_HANDLED; -} - -static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc, - struct arm_pmu *cpu_pmu) -{ - int idx; - - for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx++) { - if (!test_and_set_bit(idx, cpuc->used_mask)) - return idx; - } - return -EAGAIN; -} - -static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc, - struct arm_pmu *cpu_pmu) -{ - int idx; - - /* - * Chaining requires two consecutive event counters, where - * the lower idx must be even. - */ - for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) { - if (!test_and_set_bit(idx, cpuc->used_mask)) { - /* Check if the preceding even counter is available */ - if (!test_and_set_bit(idx - 1, cpuc->used_mask)) - return idx; - /* Release the Odd counter */ - clear_bit(idx, cpuc->used_mask); - } - } - return -EAGAIN; -} - -static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, - struct perf_event *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_PMU_EVTYPE_EVENT; - - /* Always prefer to place a cycle counter into the cycle counter. */ - if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) { - if (!test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask)) - return ARMV8_IDX_CYCLE_COUNTER; - else if (armv8pmu_event_is_64bit(event) && - armv8pmu_event_want_user_access(event) && - !armv8pmu_has_long_event(cpu_pmu)) - return -EAGAIN; - } - - /* - * Otherwise use events counters - */ - if (armv8pmu_event_is_chained(event)) - return armv8pmu_get_chain_idx(cpuc, cpu_pmu); - else - return armv8pmu_get_single_idx(cpuc, cpu_pmu); -} - -static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc, - struct perf_event *event) -{ - int idx = event->hw.idx; - - clear_bit(idx, cpuc->used_mask); - if (armv8pmu_event_is_chained(event)) - clear_bit(idx - 1, cpuc->used_mask); -} - -static int armv8pmu_user_event_idx(struct perf_event *event) -{ - if (!sysctl_perf_user_access || !armv8pmu_event_has_user_read(event)) - return 0; - - /* - * We remap the cycle counter index to 32 to - * match the offset applied to the rest of - * the counter indices. - */ - if (event->hw.idx == ARMV8_IDX_CYCLE_COUNTER) - return ARMV8_IDX_CYCLE_COUNTER_USER; - - return event->hw.idx; -} - -/* - * Add an event filter to a given event. - */ -static int armv8pmu_set_event_filter(struct hw_perf_event *event, - struct perf_event_attr *attr) -{ - unsigned long config_base = 0; - - if (attr->exclude_idle) - return -EPERM; - - /* - * If we're running in hyp mode, then we *are* the hypervisor. - * Therefore we ignore exclude_hv in this configuration, since - * there's no hypervisor to sample anyway. This is consistent - * with other architectures (x86 and Power). - */ - if (is_kernel_in_hyp_mode()) { - if (!attr->exclude_kernel && !attr->exclude_host) - config_base |= ARMV8_PMU_INCLUDE_EL2; - if (attr->exclude_guest) - config_base |= ARMV8_PMU_EXCLUDE_EL1; - if (attr->exclude_host) - config_base |= ARMV8_PMU_EXCLUDE_EL0; - } else { - if (!attr->exclude_hv && !attr->exclude_host) - config_base |= ARMV8_PMU_INCLUDE_EL2; - } - - /* - * Filter out !VHE kernels and guest kernels - */ - if (attr->exclude_kernel) - config_base |= ARMV8_PMU_EXCLUDE_EL1; - - if (attr->exclude_user) - config_base |= ARMV8_PMU_EXCLUDE_EL0; - - /* - * Install the filter into config_base as this is used to - * construct the event type. - */ - event->config_base = config_base; - - return 0; -} - -static void armv8pmu_reset(void *info) -{ - struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; - u32 pmcr; - - /* The counter and interrupt enable registers are unknown at reset. */ - armv8pmu_disable_counter(U32_MAX); - armv8pmu_disable_intens(U32_MAX); - - /* Clear the counters we flip at guest entry/exit */ - kvm_clr_pmu_events(U32_MAX); - - /* - * Initialize & Reset PMNC. Request overflow interrupt for - * 64 bit cycle counter but cheat in armv8pmu_write_counter(). - */ - pmcr = ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_LC; - - /* Enable long event counter support where available */ - if (armv8pmu_has_long_event(cpu_pmu)) - pmcr |= ARMV8_PMU_PMCR_LP; - - armv8pmu_pmcr_write(pmcr); -} - -static int __armv8_pmuv3_map_event(struct perf_event *event, - const unsigned (*extra_event_map) - [PERF_COUNT_HW_MAX], - const unsigned (*extra_cache_map) - [PERF_COUNT_HW_CACHE_MAX] - [PERF_COUNT_HW_CACHE_OP_MAX] - [PERF_COUNT_HW_CACHE_RESULT_MAX]) -{ - int hw_event_id; - struct arm_pmu *armpmu = to_arm_pmu(event->pmu); - - hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map, - &armv8_pmuv3_perf_cache_map, - ARMV8_PMU_EVTYPE_EVENT); - - /* - * CHAIN events only work when paired with an adjacent counter, and it - * never makes sense for a user to open one in isolation, as they'll be - * rotated arbitrarily. - */ - if (hw_event_id == ARMV8_PMUV3_PERFCTR_CHAIN) - return -EINVAL; - - if (armv8pmu_event_is_64bit(event)) - event->hw.flags |= ARMPMU_EVT_64BIT; - - /* - * User events must be allocated into a single counter, and so - * must not be chained. - * - * Most 64-bit events require long counter support, but 64-bit - * CPU_CYCLES events can be placed into the dedicated cycle - * counter when this is free. - */ - if (armv8pmu_event_want_user_access(event)) { - if (!(event->attach_state & PERF_ATTACH_TASK)) - return -EINVAL; - if (armv8pmu_event_is_64bit(event) && - (hw_event_id != ARMV8_PMUV3_PERFCTR_CPU_CYCLES) && - !armv8pmu_has_long_event(armpmu)) - return -EOPNOTSUPP; - - event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; - } - - /* Only expose micro/arch events supported by this PMU */ - if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) - && test_bit(hw_event_id, armpmu->pmceid_bitmap)) { - return hw_event_id; - } - - return armpmu_map_event(event, extra_event_map, extra_cache_map, - ARMV8_PMU_EVTYPE_EVENT); -} - -static int armv8_pmuv3_map_event(struct perf_event *event) -{ - return __armv8_pmuv3_map_event(event, NULL, NULL); -} - -static int armv8_a53_map_event(struct perf_event *event) -{ - return __armv8_pmuv3_map_event(event, NULL, &armv8_a53_perf_cache_map); -} - -static int armv8_a57_map_event(struct perf_event *event) -{ - return __armv8_pmuv3_map_event(event, NULL, &armv8_a57_perf_cache_map); -} - -static int armv8_a73_map_event(struct perf_event *event) -{ - return __armv8_pmuv3_map_event(event, NULL, &armv8_a73_perf_cache_map); -} - -static int armv8_thunder_map_event(struct perf_event *event) -{ - return __armv8_pmuv3_map_event(event, NULL, - &armv8_thunder_perf_cache_map); -} - -static int armv8_vulcan_map_event(struct perf_event *event) -{ - return __armv8_pmuv3_map_event(event, NULL, - &armv8_vulcan_perf_cache_map); -} - -struct armv8pmu_probe_info { - struct arm_pmu *pmu; - bool present; -}; - -static void __armv8pmu_probe_pmu(void *info) -{ - struct armv8pmu_probe_info *probe = info; - struct arm_pmu *cpu_pmu = probe->pmu; - u64 dfr0; - u64 pmceid_raw[2]; - u32 pmceid[2]; - int pmuver; - - dfr0 = read_sysreg(id_aa64dfr0_el1); - pmuver = cpuid_feature_extract_unsigned_field(dfr0, - ID_AA64DFR0_EL1_PMUVer_SHIFT); - if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || - pmuver == ID_AA64DFR0_EL1_PMUVer_NI) - return; - - cpu_pmu->pmuver = pmuver; - probe->present = true; - - /* Read the nb of CNTx counters supported from PMNC */ - cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT) - & ARMV8_PMU_PMCR_N_MASK; - - /* Add the CPU cycles counter */ - cpu_pmu->num_events += 1; - - pmceid[0] = pmceid_raw[0] = read_sysreg(pmceid0_el0); - pmceid[1] = pmceid_raw[1] = read_sysreg(pmceid1_el0); - - bitmap_from_arr32(cpu_pmu->pmceid_bitmap, - pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); - - pmceid[0] = pmceid_raw[0] >> 32; - pmceid[1] = pmceid_raw[1] >> 32; - - bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap, - pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); - - /* store PMMIR_EL1 register for sysfs */ - if (pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P4 && (pmceid_raw[1] & BIT(31))) - cpu_pmu->reg_pmmir = read_cpuid(PMMIR_EL1); - else - cpu_pmu->reg_pmmir = 0; -} - -static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu) -{ - struct armv8pmu_probe_info probe = { - .pmu = cpu_pmu, - .present = false, - }; - int ret; - - ret = smp_call_function_any(&cpu_pmu->supported_cpus, - __armv8pmu_probe_pmu, - &probe, 1); - if (ret) - return ret; - - return probe.present ? 0 : -ENODEV; -} - -static void armv8pmu_disable_user_access_ipi(void *unused) -{ - armv8pmu_disable_user_access(); -} - -static int armv8pmu_proc_user_access_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (ret || !write || sysctl_perf_user_access) - return ret; - - on_each_cpu(armv8pmu_disable_user_access_ipi, NULL, 1); - return 0; -} - -static struct ctl_table armv8_pmu_sysctl_table[] = { - { - .procname = "perf_user_access", - .data = &sysctl_perf_user_access, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = armv8pmu_proc_user_access_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { } -}; - -static void armv8_pmu_register_sysctl_table(void) -{ - static u32 tbl_registered = 0; - - if (!cmpxchg_relaxed(&tbl_registered, 0, 1)) - register_sysctl("kernel", armv8_pmu_sysctl_table); -} - -static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name, - int (*map_event)(struct perf_event *event), - const struct attribute_group *events, - const struct attribute_group *format, - const struct attribute_group *caps) -{ - int ret = armv8pmu_probe_pmu(cpu_pmu); - if (ret) - return ret; - - 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->clear_event_idx = armv8pmu_clear_event_idx; - cpu_pmu->start = armv8pmu_start; - cpu_pmu->stop = armv8pmu_stop; - cpu_pmu->reset = armv8pmu_reset; - cpu_pmu->set_event_filter = armv8pmu_set_event_filter; - - cpu_pmu->pmu.event_idx = armv8pmu_user_event_idx; - - cpu_pmu->name = name; - cpu_pmu->map_event = map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = events ? - events : &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ? - format : &armv8_pmuv3_format_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ? - caps : &armv8_pmuv3_caps_attr_group; - - armv8_pmu_register_sysctl_table(); - return 0; -} - -static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name, - int (*map_event)(struct perf_event *event)) -{ - return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL); -} - -#define PMUV3_INIT_SIMPLE(name) \ -static int name##_pmu_init(struct arm_pmu *cpu_pmu) \ -{ \ - return armv8_pmu_init_nogroups(cpu_pmu, #name, armv8_pmuv3_map_event);\ -} - -PMUV3_INIT_SIMPLE(armv8_pmuv3) - -PMUV3_INIT_SIMPLE(armv8_cortex_a34) -PMUV3_INIT_SIMPLE(armv8_cortex_a55) -PMUV3_INIT_SIMPLE(armv8_cortex_a65) -PMUV3_INIT_SIMPLE(armv8_cortex_a75) -PMUV3_INIT_SIMPLE(armv8_cortex_a76) -PMUV3_INIT_SIMPLE(armv8_cortex_a77) -PMUV3_INIT_SIMPLE(armv8_cortex_a78) -PMUV3_INIT_SIMPLE(armv9_cortex_a510) -PMUV3_INIT_SIMPLE(armv9_cortex_a710) -PMUV3_INIT_SIMPLE(armv8_cortex_x1) -PMUV3_INIT_SIMPLE(armv9_cortex_x2) -PMUV3_INIT_SIMPLE(armv8_neoverse_e1) -PMUV3_INIT_SIMPLE(armv8_neoverse_n1) -PMUV3_INIT_SIMPLE(armv9_neoverse_n2) -PMUV3_INIT_SIMPLE(armv8_neoverse_v1) - -PMUV3_INIT_SIMPLE(armv8_nvidia_carmel) -PMUV3_INIT_SIMPLE(armv8_nvidia_denver) - -static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35", - armv8_a53_map_event); -} - -static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53", - armv8_a53_map_event); -} - -static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57", - armv8_a57_map_event); -} - -static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72", - armv8_a57_map_event); -} - -static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73", - armv8_a73_map_event); -} - -static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder", - armv8_thunder_map_event); -} - -static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) -{ - return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan", - armv8_vulcan_map_event); -} - -static const struct of_device_id armv8_pmu_of_device_ids[] = { - {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_pmu_init}, - {.compatible = "arm,cortex-a34-pmu", .data = armv8_cortex_a34_pmu_init}, - {.compatible = "arm,cortex-a35-pmu", .data = armv8_a35_pmu_init}, - {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init}, - {.compatible = "arm,cortex-a55-pmu", .data = armv8_cortex_a55_pmu_init}, - {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init}, - {.compatible = "arm,cortex-a65-pmu", .data = armv8_cortex_a65_pmu_init}, - {.compatible = "arm,cortex-a72-pmu", .data = armv8_a72_pmu_init}, - {.compatible = "arm,cortex-a73-pmu", .data = armv8_a73_pmu_init}, - {.compatible = "arm,cortex-a75-pmu", .data = armv8_cortex_a75_pmu_init}, - {.compatible = "arm,cortex-a76-pmu", .data = armv8_cortex_a76_pmu_init}, - {.compatible = "arm,cortex-a77-pmu", .data = armv8_cortex_a77_pmu_init}, - {.compatible = "arm,cortex-a78-pmu", .data = armv8_cortex_a78_pmu_init}, - {.compatible = "arm,cortex-a510-pmu", .data = armv9_cortex_a510_pmu_init}, - {.compatible = "arm,cortex-a710-pmu", .data = armv9_cortex_a710_pmu_init}, - {.compatible = "arm,cortex-x1-pmu", .data = armv8_cortex_x1_pmu_init}, - {.compatible = "arm,cortex-x2-pmu", .data = armv9_cortex_x2_pmu_init}, - {.compatible = "arm,neoverse-e1-pmu", .data = armv8_neoverse_e1_pmu_init}, - {.compatible = "arm,neoverse-n1-pmu", .data = armv8_neoverse_n1_pmu_init}, - {.compatible = "arm,neoverse-n2-pmu", .data = armv9_neoverse_n2_pmu_init}, - {.compatible = "arm,neoverse-v1-pmu", .data = armv8_neoverse_v1_pmu_init}, - {.compatible = "cavium,thunder-pmu", .data = armv8_thunder_pmu_init}, - {.compatible = "brcm,vulcan-pmu", .data = armv8_vulcan_pmu_init}, - {.compatible = "nvidia,carmel-pmu", .data = armv8_nvidia_carmel_pmu_init}, - {.compatible = "nvidia,denver-pmu", .data = armv8_nvidia_denver_pmu_init}, - {}, -}; - -static int armv8_pmu_device_probe(struct platform_device *pdev) -{ - return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL); -} - -static struct platform_driver armv8_pmu_driver = { - .driver = { - .name = ARMV8_PMU_PDEV_NAME, - .of_match_table = armv8_pmu_of_device_ids, - .suppress_bind_attrs = true, - }, - .probe = armv8_pmu_device_probe, -}; - -static int __init armv8_pmu_driver_init(void) -{ - if (acpi_disabled) - return platform_driver_register(&armv8_pmu_driver); - else - return arm_pmu_acpi_probe(armv8_pmuv3_pmu_init); -} -device_initcall(armv8_pmu_driver_init) - -void arch_perf_update_userpage(struct perf_event *event, - struct perf_event_mmap_page *userpg, u64 now) -{ - struct clock_read_data *rd; - unsigned int seq; - u64 ns; - - userpg->cap_user_time = 0; - userpg->cap_user_time_zero = 0; - userpg->cap_user_time_short = 0; - userpg->cap_user_rdpmc = armv8pmu_event_has_user_read(event); - - if (userpg->cap_user_rdpmc) { - if (event->hw.flags & ARMPMU_EVT_64BIT) - userpg->pmc_width = 64; - else - userpg->pmc_width = 32; - } - - do { - rd = sched_clock_read_begin(&seq); - - if (rd->read_sched_clock != arch_timer_read_counter) - return; - - userpg->time_mult = rd->mult; - userpg->time_shift = rd->shift; - userpg->time_zero = rd->epoch_ns; - userpg->time_cycles = rd->epoch_cyc; - userpg->time_mask = rd->sched_clock_mask; - - /* - * Subtract the cycle base, such that software that - * doesn't know about cap_user_time_short still 'works' - * assuming no wraps. - */ - ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift); - userpg->time_zero -= ns; - - } while (sched_clock_read_retry(seq)); - - userpg->time_offset = userpg->time_zero - now; - - /* - * time_shift is not expected to be greater than 31 due to - * the original published conversion algorithm shifting a - * 32-bit value (now specifies a 64-bit value) - refer - * perf_event_mmap_page documentation in perf_event.h. - */ - if (userpg->time_shift == 32) { - userpg->time_shift = 31; - userpg->time_mult >>= 1; - } - - /* - * Internal timekeeping for enabled/running/stopped times - * is always computed with the sched_clock. - */ - userpg->cap_user_time = 1; - userpg->cap_user_time_zero = 1; - userpg->cap_user_time_short = 1; -} diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 71d59b5abede..0fcc4eb1a7ab 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -69,7 +69,7 @@ void (*pm_power_off)(void); EXPORT_SYMBOL_GPL(pm_power_off); #ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) +void __noreturn arch_cpu_idle_dead(void) { cpu_die(); } @@ -217,7 +217,7 @@ void __show_regs(struct pt_regs *regs) if (!user_mode(regs)) { printk("pc : %pS\n", (void *)regs->pc); - printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr)); + printk("lr : %pS\n", (void *)ptrauth_strip_kernel_insn_pac(lr)); } else { printk("pc : %016llx\n", regs->pc); printk("lr : %016llx\n", lr); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index fca9cc6f5581..05f40c4e18fd 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -966,9 +966,6 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) { const char *v = arm64_get_bp_hardening_vector(slot); - if (slot < 0) - return; - __this_cpu_write(this_cpu_vector, v); /* diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 06a02707f488..2cfc810d0a5b 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -651,7 +651,7 @@ static int parse_user_sigframe(struct user_ctxs *user, break; case TPIDR2_MAGIC: - if (!system_supports_sme()) + if (!system_supports_tpidr2()) goto invalid; if (user->tpidr2) @@ -802,7 +802,7 @@ static int restore_sigframe(struct pt_regs *regs, err = restore_fpsimd_context(&user); } - if (err == 0 && system_supports_sme() && user.tpidr2) + if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user); if (err == 0 && system_supports_sme() && user.za) @@ -893,6 +893,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } + if (system_supports_tpidr2()) { + err = sigframe_alloc(user, &user->tpidr2_offset, + sizeof(struct tpidr2_context)); + if (err) + return err; + } + if (system_supports_sme()) { unsigned int vl; unsigned int vq = 0; @@ -902,11 +909,6 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, else vl = task_get_sme_vl(current); - err = sigframe_alloc(user, &user->tpidr2_offset, - sizeof(struct tpidr2_context)); - if (err) - return err; - if (thread_za_enabled(¤t->thread)) vq = sve_vq_from_vl(vl); @@ -974,7 +976,7 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, } /* TPIDR2 if supported */ - if (system_supports_sme() && err == 0) { + if (system_supports_tpidr2() && err == 0) { struct tpidr2_context __user *tpidr2_ctx = apply_user_offset(user, user->tpidr2_offset); err |= preserve_tpidr2_context(tpidr2_ctx); diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 2ae7cff1953a..2aa5129d8253 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -97,7 +97,7 @@ SYM_FUNC_START(__cpu_suspend_enter) ret SYM_FUNC_END(__cpu_suspend_enter) - .pushsection ".idmap.text", "awx" + .pushsection ".idmap.text", "a" SYM_CODE_START(cpu_resume) mov x0, xzr bl init_kernel_el diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 4e8327264255..d00d4cbb31b1 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -51,7 +51,6 @@ #include <asm/ptrace.h> #include <asm/virt.h> -#define CREATE_TRACE_POINTS #include <trace/events/ipi.h> DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number); @@ -361,7 +360,7 @@ void __cpu_die(unsigned int cpu) * Called from the idle thread for the CPU which has been shutdown. * */ -void cpu_die(void) +void __noreturn cpu_die(void) { unsigned int cpu = smp_processor_id(); const struct cpu_operations *ops = get_cpu_ops(cpu); @@ -398,7 +397,7 @@ static void __cpu_try_die(int cpu) * Kill the calling secondary CPU, early in bringup before it is turned * online. */ -void cpu_die_early(void) +void __noreturn cpu_die_early(void) { int cpu = smp_processor_id(); @@ -816,7 +815,7 @@ void arch_irq_work_raise(void) } #endif -static void local_cpu_stop(void) +static void __noreturn local_cpu_stop(void) { set_cpu_online(smp_processor_id(), false); @@ -830,7 +829,7 @@ static void local_cpu_stop(void) * that cpu_online_mask gets correctly updated and smp_send_stop() can skip * CPUs that have already stopped themselves. */ -void panic_smp_self_stop(void) +void __noreturn panic_smp_self_stop(void) { local_cpu_stop(); } @@ -839,7 +838,7 @@ void panic_smp_self_stop(void) static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); #endif -static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) { #ifdef CONFIG_KEXEC_CORE crash_save_cpu(regs, cpu); @@ -854,6 +853,8 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) /* just in case */ cpu_park_loop(); +#else + BUG(); #endif } @@ -977,7 +978,7 @@ void __init set_smp_ipi_range(int ipi_base, int n) ipi_setup(smp_processor_id()); } -void smp_send_reschedule(int cpu) +void arch_smp_send_reschedule(int cpu) { smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); } diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 83154303e682..17f66a74c745 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -25,8 +25,9 @@ * * The regs must be on a stack currently owned by the calling task. */ -static __always_inline void unwind_init_from_regs(struct unwind_state *state, - struct pt_regs *regs) +static __always_inline void +unwind_init_from_regs(struct unwind_state *state, + struct pt_regs *regs) { unwind_init_common(state, current); @@ -42,7 +43,8 @@ static __always_inline void unwind_init_from_regs(struct unwind_state *state, * * The function which invokes this must be noinline. */ -static __always_inline void unwind_init_from_caller(struct unwind_state *state) +static __always_inline void +unwind_init_from_caller(struct unwind_state *state) { unwind_init_common(state, current); @@ -60,8 +62,9 @@ static __always_inline void unwind_init_from_caller(struct unwind_state *state) * duration of the unwind, or the unwind will be bogus. It is never valid to * call this for the current task. */ -static __always_inline void unwind_init_from_task(struct unwind_state *state, - struct task_struct *task) +static __always_inline void +unwind_init_from_task(struct unwind_state *state, + struct task_struct *task) { unwind_init_common(state, task); @@ -69,6 +72,32 @@ static __always_inline void unwind_init_from_task(struct unwind_state *state, state->pc = thread_saved_pc(task); } +static __always_inline int +unwind_recover_return_address(struct unwind_state *state) +{ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (state->task->ret_stack && + (state->pc == (unsigned long)return_to_handler)) { + unsigned long orig_pc; + orig_pc = ftrace_graph_ret_addr(state->task, NULL, state->pc, + (void *)state->fp); + if (WARN_ON_ONCE(state->pc == orig_pc)) + return -EINVAL; + state->pc = orig_pc; + } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_KRETPROBES + if (is_kretprobe_trampoline(state->pc)) { + state->pc = kretprobe_find_ret_addr(state->task, + (void *)state->fp, + &state->kr_cur); + } +#endif /* CONFIG_KRETPROBES */ + + return 0; +} + /* * Unwind from one frame record (A) to the next frame record (B). * @@ -76,7 +105,8 @@ static __always_inline void unwind_init_from_task(struct unwind_state *state, * records (e.g. a cycle), determined based on the location and fp value of A * and the location (but not the fp value) of B. */ -static int notrace unwind_next(struct unwind_state *state) +static __always_inline int +unwind_next(struct unwind_state *state) { struct task_struct *tsk = state->task; unsigned long fp = state->fp; @@ -90,37 +120,18 @@ static int notrace unwind_next(struct unwind_state *state) if (err) return err; - state->pc = ptrauth_strip_insn_pac(state->pc); - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (tsk->ret_stack && - (state->pc == (unsigned long)return_to_handler)) { - unsigned long orig_pc; - /* - * This is a case where function graph tracer has - * modified a return address (LR) in a stack frame - * to hook a function return. - * So replace it to an original value. - */ - orig_pc = ftrace_graph_ret_addr(tsk, NULL, state->pc, - (void *)state->fp); - if (WARN_ON_ONCE(state->pc == orig_pc)) - return -EINVAL; - state->pc = orig_pc; - } -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#ifdef CONFIG_KRETPROBES - if (is_kretprobe_trampoline(state->pc)) - state->pc = kretprobe_find_ret_addr(tsk, (void *)state->fp, &state->kr_cur); -#endif + state->pc = ptrauth_strip_kernel_insn_pac(state->pc); - return 0; + return unwind_recover_return_address(state); } -NOKPROBE_SYMBOL(unwind_next); -static void notrace unwind(struct unwind_state *state, - stack_trace_consume_fn consume_entry, void *cookie) +static __always_inline void +unwind(struct unwind_state *state, stack_trace_consume_fn consume_entry, + void *cookie) { + if (unwind_recover_return_address(state)) + return; + while (1) { int ret; @@ -131,40 +142,6 @@ static void notrace unwind(struct unwind_state *state, break; } } -NOKPROBE_SYMBOL(unwind); - -static bool dump_backtrace_entry(void *arg, unsigned long where) -{ - char *loglvl = arg; - printk("%s %pSb\n", loglvl, (void *)where); - return true; -} - -void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, - const char *loglvl) -{ - pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); - - if (regs && user_mode(regs)) - return; - - if (!tsk) - tsk = current; - - if (!try_get_task_stack(tsk)) - return; - - printk("%sCall trace:\n", loglvl); - arch_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs); - - put_task_stack(tsk); -} - -void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) -{ - dump_backtrace(NULL, tsk, loglvl); - barrier(); -} /* * Per-cpu stacks are only accessible when unwinding the current task in a @@ -230,3 +207,36 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, unwind(&state, consume_entry, cookie); } + +static bool dump_backtrace_entry(void *arg, unsigned long where) +{ + char *loglvl = arg; + printk("%s %pSb\n", loglvl, (void *)where); + return true; +} + +void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, + const char *loglvl) +{ + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + + if (regs && user_mode(regs)) + return; + + if (!tsk) + tsk = current; + + if (!try_get_task_stack(tsk)) + return; + + printk("%sCall trace:\n", loglvl); + arch_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs); + + put_task_stack(tsk); +} + +void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) +{ + dump_backtrace(NULL, tsk, loglvl); + barrier(); +} diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 4a79ba100799..4bb1b8f47298 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -863,7 +863,7 @@ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned long esr) DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) __aligned(16); -void panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) +void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr); @@ -905,7 +905,6 @@ void __noreturn arm64_serror_panic(struct pt_regs *regs, unsigned long esr) nmi_panic(regs, "Asynchronous SError Interrupt"); cpu_park_loop(); - unreachable(); } bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned long esr) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index beaf9586338f..fe7a53c6781f 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -6,9 +6,7 @@ # Heavily based on the vDSO Makefiles for other archs. # -# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before -# the inclusion of generic Makefile. -ARCH_REL_TYPE_ABS := R_AARCH64_JUMP_SLOT|R_AARCH64_GLOB_DAT|R_AARCH64_ABS64 +# Include the generic Makefile to check the built vdso. include $(srctree)/lib/vdso/Makefile obj-vdso := vgettimeofday.o note.o sigreturn.o diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index f59bd1a4ead6..d014162c5c71 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -3,9 +3,6 @@ # Makefile for vdso32 # -# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before -# the inclusion of generic Makefile. -ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32 include $(srctree)/lib/vdso/Makefile # Same as cc-*option, but using CC_COMPAT instead of CC diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index b9202c2ee18e..3cd7e76cc562 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -181,18 +181,8 @@ SECTIONS KPROBES_TEXT HYPERVISOR_TEXT *(.gnu.warning) - . = ALIGN(16); - *(.got) /* Global offset table */ } - /* - * Make sure that the .got.plt is either completely empty or it - * contains only the lazy dispatch entries. - */ - .got.plt : { *(.got.plt) } - ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, - "Unexpected GOT/PLT entries detected!") - . = ALIGN(SEGMENT_ALIGN); _etext = .; /* End of text section */ @@ -201,6 +191,15 @@ SECTIONS HYPERVISOR_DATA_SECTIONS + .got : { *(.got) } + /* + * Make sure that the .got.plt is either completely empty or it + * contains only the lazy dispatch entries. + */ + .got.plt : { *(.got.plt) } + ASSERT(SIZEOF(.got.plt) == 0 || SIZEOF(.got.plt) == 0x18, + "Unexpected GOT/PLT entries detected!") + /* code sections that are never executed via the kernel mapping */ .rodata.text : { TRAMP_TEXT |