diff options
Diffstat (limited to 'arch/arm64/kernel')
27 files changed, 410 insertions, 244 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 7c2bb4e72476..d95b3d6b471a 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -42,9 +42,9 @@ obj-$(CONFIG_COMPAT) += sigreturn32.o obj-$(CONFIG_COMPAT_ALIGNMENT_FIXUPS) += compat_alignment.o obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o -obj-$(CONFIG_MODULES) += module.o -obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o +obj-$(CONFIG_MODULES) += module.o module-plts.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o +obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o obj-$(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/alternative.c b/arch/arm64/kernel/alternative.c index d32d4ed5519b..8ff6610af496 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -24,8 +24,8 @@ #define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset) #define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset) -#define ALT_CAP(a) ((a)->cpufeature & ~ARM64_CB_BIT) -#define ALT_HAS_CB(a) ((a)->cpufeature & ARM64_CB_BIT) +#define ALT_CAP(a) ((a)->cpucap & ~ARM64_CB_BIT) +#define ALT_HAS_CB(a) ((a)->cpucap & ARM64_CB_BIT) /* Volatile, as we may be patching the guts of READ_ONCE() */ static volatile int all_alternatives_applied; @@ -37,12 +37,12 @@ struct alt_region { struct alt_instr *end; }; -bool alternative_is_applied(u16 cpufeature) +bool alternative_is_applied(u16 cpucap) { - if (WARN_ON(cpufeature >= ARM64_NCAPS)) + if (WARN_ON(cpucap >= ARM64_NCAPS)) return false; - return test_bit(cpufeature, applied_alternatives); + return test_bit(cpucap, applied_alternatives); } /* @@ -121,11 +121,11 @@ static noinstr void patch_alternative(struct alt_instr *alt, * accidentally call into the cache.S code, which is patched by us at * runtime. */ -static void clean_dcache_range_nopatch(u64 start, u64 end) +static noinstr void clean_dcache_range_nopatch(u64 start, u64 end) { u64 cur, d_size, ctr_el0; - ctr_el0 = read_sanitised_ftr_reg(SYS_CTR_EL0); + ctr_el0 = arm64_ftr_reg_ctrel0.sys_val; d_size = 4 << cpuid_feature_extract_unsigned_field(ctr_el0, CTR_EL0_DminLine_SHIFT); cur = start & ~(d_size - 1); @@ -141,7 +141,7 @@ static void clean_dcache_range_nopatch(u64 start, u64 end) static void __apply_alternatives(const struct alt_region *region, bool is_module, - unsigned long *feature_mask) + unsigned long *cpucap_mask) { struct alt_instr *alt; __le32 *origptr, *updptr; @@ -151,7 +151,7 @@ static void __apply_alternatives(const struct alt_region *region, int nr_inst; int cap = ALT_CAP(alt); - if (!test_bit(cap, feature_mask)) + if (!test_bit(cap, cpucap_mask)) continue; if (!cpus_have_cap(cap)) @@ -188,11 +188,10 @@ static void __apply_alternatives(const struct alt_region *region, icache_inval_all_pou(); isb(); - /* Ignore ARM64_CB bit from feature mask */ bitmap_or(applied_alternatives, applied_alternatives, - feature_mask, ARM64_NCAPS); + cpucap_mask, ARM64_NCAPS); bitmap_and(applied_alternatives, applied_alternatives, - cpu_hwcaps, ARM64_NCAPS); + system_cpucaps, ARM64_NCAPS); } } @@ -239,7 +238,7 @@ static int __init __apply_alternatives_multi_stop(void *unused) } else { DECLARE_BITMAP(remaining_capabilities, ARM64_NCAPS); - bitmap_complement(remaining_capabilities, boot_capabilities, + bitmap_complement(remaining_capabilities, boot_cpucaps, ARM64_NCAPS); BUG_ON(all_alternatives_applied); @@ -274,7 +273,7 @@ void __init apply_boot_alternatives(void) pr_info("applying boot alternatives\n"); __apply_alternatives(&kernel_alternatives, false, - &boot_capabilities[0]); + &boot_cpucaps[0]); } #ifdef CONFIG_MODULES diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 7d7128c65161..6ea7f23b1287 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -105,11 +105,11 @@ unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; #endif -DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); -EXPORT_SYMBOL(cpu_hwcaps); -static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS]; +DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS); +EXPORT_SYMBOL(system_cpucaps); +static struct arm64_cpu_capabilities const __ro_after_init *cpucap_ptrs[ARM64_NCAPS]; -DECLARE_BITMAP(boot_capabilities, ARM64_NCAPS); +DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS); bool arm64_use_ng_mappings = false; EXPORT_SYMBOL(arm64_use_ng_mappings); @@ -137,7 +137,7 @@ static cpumask_var_t cpu_32bit_el0_mask __cpumask_var_read_mostly; void dump_cpu_features(void) { /* file-wide pr_fmt adds "CPU features: " prefix */ - pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps); + pr_emerg("0x%*pb\n", ARM64_NCAPS, &system_cpucaps); } #define ARM64_CPUID_FIELDS(reg, field, min_value) \ @@ -223,6 +223,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), @@ -364,6 +365,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TIDCP1_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HCX_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_ETS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TWED_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_XNX_SHIFT, 4, 0), @@ -396,6 +398,12 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64mmfr3[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_S1PIE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR3_EL1_TCRX_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_ctr[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_EL0_DIC_SHIFT, 1, 1), @@ -722,6 +730,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1, &id_aa64mmfr1_override), ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), + ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3), /* Op1 = 0, CRn = 1, CRm = 2 */ ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr), @@ -954,24 +963,24 @@ extern const struct arm64_cpu_capabilities arm64_errata[]; static const struct arm64_cpu_capabilities arm64_features[]; static void __init -init_cpu_hwcaps_indirect_list_from_array(const struct arm64_cpu_capabilities *caps) +init_cpucap_indirect_list_from_array(const struct arm64_cpu_capabilities *caps) { for (; caps->matches; caps++) { if (WARN(caps->capability >= ARM64_NCAPS, "Invalid capability %d\n", caps->capability)) continue; - if (WARN(cpu_hwcaps_ptrs[caps->capability], + if (WARN(cpucap_ptrs[caps->capability], "Duplicate entry for capability %d\n", caps->capability)) continue; - cpu_hwcaps_ptrs[caps->capability] = caps; + cpucap_ptrs[caps->capability] = caps; } } -static void __init init_cpu_hwcaps_indirect_list(void) +static void __init init_cpucap_indirect_list(void) { - init_cpu_hwcaps_indirect_list_from_array(arm64_features); - init_cpu_hwcaps_indirect_list_from_array(arm64_errata); + init_cpucap_indirect_list_from_array(arm64_features); + init_cpucap_indirect_list_from_array(arm64_errata); } static void __init setup_boot_cpu_capabilities(void); @@ -1017,6 +1026,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2); + init_cpu_ftr_reg(SYS_ID_AA64MMFR3_EL1, info->reg_id_aa64mmfr3); init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); @@ -1049,10 +1059,10 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_GMID_EL1, info->reg_gmid); /* - * Initialize the indirect array of CPU hwcaps capabilities pointers - * before we handle the boot CPU below. + * Initialize the indirect array of CPU capabilities pointers before we + * handle the boot CPU below. */ - init_cpu_hwcaps_indirect_list(); + init_cpucap_indirect_list(); /* * Detect and enable early CPU capabilities based on the boot CPU, @@ -1262,6 +1272,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64mmfr1, boot->reg_id_aa64mmfr1); taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); + taint |= check_update_ftr_reg(SYS_ID_AA64MMFR3_EL1, cpu, + info->reg_id_aa64mmfr3, boot->reg_id_aa64mmfr3); taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); @@ -1391,6 +1403,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64MMFR0_EL1); read_sysreg_case(SYS_ID_AA64MMFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR2_EL1); + read_sysreg_case(SYS_ID_AA64MMFR3_EL1); read_sysreg_case(SYS_ID_AA64ISAR0_EL1); read_sysreg_case(SYS_ID_AA64ISAR1_EL1); read_sysreg_case(SYS_ID_AA64ISAR2_EL1); @@ -2048,9 +2061,9 @@ static bool has_address_auth_cpucap(const struct arm64_cpu_capabilities *entry, static bool has_address_auth_metacap(const struct arm64_cpu_capabilities *entry, int scope) { - bool api = has_address_auth_cpucap(cpu_hwcaps_ptrs[ARM64_HAS_ADDRESS_AUTH_IMP_DEF], scope); - bool apa = has_address_auth_cpucap(cpu_hwcaps_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA5], scope); - bool apa3 = has_address_auth_cpucap(cpu_hwcaps_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA3], scope); + bool api = has_address_auth_cpucap(cpucap_ptrs[ARM64_HAS_ADDRESS_AUTH_IMP_DEF], scope); + bool apa = has_address_auth_cpucap(cpucap_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA5], scope); + bool apa3 = has_address_auth_cpucap(cpucap_ptrs[ARM64_HAS_ADDRESS_AUTH_ARCH_QARMA3], scope); return apa || apa3 || api; } @@ -2186,6 +2199,11 @@ static void cpu_enable_dit(const struct arm64_cpu_capabilities *__unused) set_pstate_dit(1); } +static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) +{ + sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_MSCEn); +} + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -2235,11 +2253,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .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 = ID_AA64MMFR0_EL1_ECV_CNTPOFF, + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, ECV, CNTPOFF) }, #ifdef CONFIG_ARM64_PAN { @@ -2309,6 +2323,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = is_kvm_protected_mode, }, + { + .desc = "HCRX_EL2 register", + .capability = ARM64_HAS_HCX, + .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, + .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HCX, IMP) + }, #endif { .desc = "Kernel page table isolation (KPTI)", @@ -2641,6 +2662,27 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_enable_dit, ARM64_CPUID_FIELDS(ID_AA64PFR0_EL1, DIT, IMP) }, + { + .desc = "Memory Copy and Memory Set instructions", + .capability = ARM64_HAS_MOPS, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_mops, + ARM64_CPUID_FIELDS(ID_AA64ISAR2_EL1, MOPS, IMP) + }, + { + .capability = ARM64_HAS_TCR2, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, TCRX, IMP) + }, + { + .desc = "Stage-1 Permission Indirection Extension (S1PIE)", + .capability = ARM64_HAS_S1PIE, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_cpuid_feature, + ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1PIE, IMP) + }, {}, }; @@ -2769,6 +2811,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), + HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS), #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), @@ -2895,7 +2938,7 @@ static void update_cpu_capabilities(u16 scope_mask) scope_mask &= ARM64_CPUCAP_SCOPE_MASK; for (i = 0; i < ARM64_NCAPS; i++) { - caps = cpu_hwcaps_ptrs[i]; + caps = cpucap_ptrs[i]; if (!caps || !(caps->type & scope_mask) || cpus_have_cap(caps->capability) || !caps->matches(caps, cpucap_default_scope(caps))) @@ -2903,10 +2946,11 @@ static void update_cpu_capabilities(u16 scope_mask) if (caps->desc) pr_info("detected: %s\n", caps->desc); - cpus_set_cap(caps->capability); + + __set_bit(caps->capability, system_cpucaps); if ((scope_mask & SCOPE_BOOT_CPU) && (caps->type & SCOPE_BOOT_CPU)) - set_bit(caps->capability, boot_capabilities); + set_bit(caps->capability, boot_cpucaps); } } @@ -2920,7 +2964,7 @@ static int cpu_enable_non_boot_scope_capabilities(void *__unused) u16 non_boot_scope = SCOPE_ALL & ~SCOPE_BOOT_CPU; for_each_available_cap(i) { - const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[i]; + const struct arm64_cpu_capabilities *cap = cpucap_ptrs[i]; if (WARN_ON(!cap)) continue; @@ -2950,7 +2994,7 @@ static void __init enable_cpu_capabilities(u16 scope_mask) for (i = 0; i < ARM64_NCAPS; i++) { unsigned int num; - caps = cpu_hwcaps_ptrs[i]; + caps = cpucap_ptrs[i]; if (!caps || !(caps->type & scope_mask)) continue; num = caps->capability; @@ -2995,7 +3039,7 @@ static void verify_local_cpu_caps(u16 scope_mask) scope_mask &= ARM64_CPUCAP_SCOPE_MASK; for (i = 0; i < ARM64_NCAPS; i++) { - caps = cpu_hwcaps_ptrs[i]; + caps = cpucap_ptrs[i]; if (!caps || !(caps->type & scope_mask)) continue; @@ -3194,7 +3238,7 @@ static void __init setup_boot_cpu_capabilities(void) bool this_cpu_has_cap(unsigned int n) { if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) { - const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n]; + const struct arm64_cpu_capabilities *cap = cpucap_ptrs[n]; if (cap) return cap->matches(cap, SCOPE_LOCAL_CPU); @@ -3207,13 +3251,13 @@ EXPORT_SYMBOL_GPL(this_cpu_has_cap); /* * This helper function is used in a narrow window when, * - The system wide safe registers are set with all the SMP CPUs and, - * - The SYSTEM_FEATURE cpu_hwcaps may not have been set. + * - The SYSTEM_FEATURE system_cpucaps may not have been set. * In all other cases cpus_have_{const_}cap() should be used. */ static bool __maybe_unused __system_matches_cap(unsigned int n) { if (n < ARM64_NCAPS) { - const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n]; + const struct arm64_cpu_capabilities *cap = cpucap_ptrs[n]; if (cap) return cap->matches(cap, SCOPE_SYSTEM); diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index 42e19fff40ee..d1f68599c29f 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -13,7 +13,7 @@ #include <linux/of_device.h> #include <linux/psci.h> -#ifdef CONFIG_ACPI +#ifdef CONFIG_ACPI_PROCESSOR_IDLE #include <acpi/processor.h> diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index eb4378c23b3c..58622dc85917 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -125,6 +125,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_BI32I32] = "smebi32i32", [KERNEL_HWCAP_SME_B16B16] = "smeb16b16", [KERNEL_HWCAP_SME_F16F16] = "smef16f16", + [KERNEL_HWCAP_MOPS] = "mops", }; #ifdef CONFIG_COMPAT @@ -446,6 +447,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1); + info->reg_id_aa64mmfr3 = read_cpuid(ID_AA64MMFR3_EL1); info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 3af3c01c93a6..6b2e0c367702 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -126,7 +126,7 @@ static __always_inline void __exit_to_user_mode(void) lockdep_hardirqs_on(CALLER_ADDR0); } -static __always_inline void prepare_exit_to_user_mode(struct pt_regs *regs) +static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) { unsigned long flags; @@ -135,11 +135,13 @@ static __always_inline void prepare_exit_to_user_mode(struct pt_regs *regs) flags = read_thread_flags(); if (unlikely(flags & _TIF_WORK_MASK)) do_notify_resume(regs, flags); + + lockdep_sys_exit(); } static __always_inline void exit_to_user_mode(struct pt_regs *regs) { - prepare_exit_to_user_mode(regs); + exit_to_user_mode_prepare(regs); mte_check_tfsr_exit(); __exit_to_user_mode(); } @@ -611,6 +613,14 @@ static void noinstr el0_bti(struct pt_regs *regs) exit_to_user_mode(regs); } +static void noinstr el0_mops(struct pt_regs *regs, unsigned long esr) +{ + enter_from_user_mode(regs); + local_daif_restore(DAIF_PROCCTX); + do_el0_mops(regs, esr); + exit_to_user_mode(regs); +} + static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); @@ -688,6 +698,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_BTI: el0_bti(regs); break; + case ESR_ELx_EC_MOPS: + el0_mops(regs, esr); + break; case ESR_ELx_EC_BREAKPT_LOW: case ESR_ELx_EC_SOFTSTP_LOW: case ESR_ELx_EC_WATCHPT_LOW: diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index ab2a6e33c052..a40e5e50fa55 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -101,12 +101,11 @@ .org .Lventry_start\@ + 128 // Did we overflow the ventry slot? .endm - .macro tramp_alias, dst, sym, tmp - mov_q \dst, TRAMP_VALIAS - adr_l \tmp, \sym - add \dst, \dst, \tmp - adr_l \tmp, .entry.tramp.text - sub \dst, \dst, \tmp + .macro tramp_alias, dst, sym + .set .Lalias\@, TRAMP_VALIAS + \sym - .entry.tramp.text + movz \dst, :abs_g2_s:.Lalias\@ + movk \dst, :abs_g1_nc:.Lalias\@ + movk \dst, :abs_g0_nc:.Lalias\@ .endm /* @@ -435,13 +434,14 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 eret alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - bne 4f msr far_el1, x29 - tramp_alias x30, tramp_exit_native, x29 - br x30 -4: - tramp_alias x30, tramp_exit_compat, x29 - br x30 + + ldr_this_cpu x30, this_cpu_vector, x29 + tramp_alias x29, tramp_exit + msr vbar_el1, x30 // install vector table + ldr lr, [sp, #S_LR] // restore x30 + add sp, sp, #PT_REGS_SIZE // restore sp + br x29 #endif .else ldr lr, [sp, #S_LR] @@ -732,22 +732,6 @@ alternative_else_nop_endif .org 1b + 128 // Did we overflow the ventry slot? .endm - .macro tramp_exit, regsize = 64 - tramp_data_read_var x30, this_cpu_vector - get_this_cpu_offset x29 - ldr x30, [x30, x29] - - msr vbar_el1, x30 - ldr lr, [sp, #S_LR] - tramp_unmap_kernel x29 - .if \regsize == 64 - mrs x29, far_el1 - .endif - add sp, sp, #PT_REGS_SIZE // restore sp - eret - sb - .endm - .macro generate_tramp_vector, kpti, bhb .Lvector_start\@: .space 0x400 @@ -768,7 +752,7 @@ alternative_else_nop_endif */ .pushsection ".entry.tramp.text", "ax" .align 11 -SYM_CODE_START_NOALIGN(tramp_vectors) +SYM_CODE_START_LOCAL_NOALIGN(tramp_vectors) #ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_LOOP generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_FW @@ -777,13 +761,12 @@ SYM_CODE_START_NOALIGN(tramp_vectors) generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_NONE SYM_CODE_END(tramp_vectors) -SYM_CODE_START(tramp_exit_native) - tramp_exit -SYM_CODE_END(tramp_exit_native) - -SYM_CODE_START(tramp_exit_compat) - tramp_exit 32 -SYM_CODE_END(tramp_exit_compat) +SYM_CODE_START_LOCAL(tramp_exit) + tramp_unmap_kernel x29 + mrs x29, far_el1 // restore x29 + eret + sb +SYM_CODE_END(tramp_exit) .popsection // .entry.tramp.text #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ @@ -1077,7 +1060,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3 + tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline br x5 #endif SYM_CODE_END(__sdei_asm_handler) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 2fbafa5cc7ac..7a1aeb95d7c3 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1649,6 +1649,7 @@ void fpsimd_flush_thread(void) fpsimd_flush_thread_vl(ARM64_VEC_SME); current->thread.svcr = 0; + sme_smstop(); } current->thread.fp_type = FP_STATE_FPSIMD; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 432626c866a8..a650f5e11fc5 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -197,7 +197,7 @@ int ftrace_update_ftrace_func(ftrace_func_t func) static struct plt_entry *get_ftrace_plt(struct module *mod) { -#ifdef CONFIG_ARM64_MODULE_PLTS +#ifdef CONFIG_MODULES struct plt_entry *plt = mod->arch.ftrace_trampolines; return &plt[FTRACE_PLT_IDX]; @@ -249,7 +249,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, * must use a PLT to reach it. We can only place PLTs for modules, and * only when module PLT support is built-in. */ - if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) + if (!IS_ENABLED(CONFIG_MODULES)) return false; /* @@ -431,10 +431,8 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, * * Note: 'mod' is only set at module load time. */ - if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) && - IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) { + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) && mod) return aarch64_insn_patch_text_nosync((void *)pc, new); - } if (!ftrace_find_callable_addr(rec, mod, &addr)) return -EINVAL; diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index e92caebff46a..0f5a30f109d9 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -382,7 +382,7 @@ SYM_FUNC_START_LOCAL(create_idmap) adrp x0, init_idmap_pg_dir adrp x3, _text adrp x6, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - mov x7, SWAPPER_RX_MMUFLAGS + mov_q x7, SWAPPER_RX_MMUFLAGS map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT @@ -391,7 +391,7 @@ SYM_FUNC_START_LOCAL(create_idmap) adrp x2, init_pg_dir adrp x3, init_pg_end bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 - mov x5, SWAPPER_RW_MMUFLAGS + mov_q x5, SWAPPER_RW_MMUFLAGS mov x6, #SWAPPER_BLOCK_SHIFT bl remap_region @@ -402,7 +402,7 @@ SYM_FUNC_START_LOCAL(create_idmap) bfi x22, x21, #0, #SWAPPER_BLOCK_SHIFT // remapped FDT address add x3, x2, #MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE bic x4, x21, #SWAPPER_BLOCK_SIZE - 1 - mov x5, SWAPPER_RW_MMUFLAGS + mov_q x5, SWAPPER_RW_MMUFLAGS mov x6, #SWAPPER_BLOCK_SHIFT bl remap_region @@ -430,7 +430,7 @@ SYM_FUNC_START_LOCAL(create_kernel_mapping) adrp x3, _text // runtime __pa(_text) sub x6, x6, x3 // _end - _text add x6, x6, x5 // runtime __va(_end) - mov x7, SWAPPER_RW_MMUFLAGS + mov_q x7, SWAPPER_RW_MMUFLAGS map_memory x0, x1, x5, x6, x7, x3, (VA_BITS - PGDIR_SHIFT), x10, x11, x12, x13, x14 diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 788597a6b6a2..02870beb271e 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -99,7 +99,6 @@ int pfn_is_nosave(unsigned long pfn) void notrace save_processor_state(void) { - WARN_ON(num_online_cpus() != 1); } void notrace restore_processor_state(void) diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index b29a311bb055..db2a1861bb97 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -973,14 +973,6 @@ static int hw_breakpoint_reset(unsigned int cpu) return 0; } -#ifdef CONFIG_CPU_PM -extern void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int)); -#else -static inline void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int)) -{ -} -#endif - /* * One-time initialisation. */ diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 9439240c3fcf..d63de1973ddb 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -119,6 +119,24 @@ SYM_CODE_START_LOCAL(__finalise_el2) msr ttbr1_el1, x0 mrs_s x0, SYS_MAIR_EL12 msr mair_el1, x0 + mrs x1, REG_ID_AA64MMFR3_EL1 + ubfx x1, x1, #ID_AA64MMFR3_EL1_TCRX_SHIFT, #4 + cbz x1, .Lskip_tcr2 + mrs x0, REG_TCR2_EL12 + msr REG_TCR2_EL1, x0 + + // Transfer permission indirection state + mrs x1, REG_ID_AA64MMFR3_EL1 + ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4 + cbz x1, .Lskip_indirection + mrs x0, REG_PIRE0_EL12 + msr REG_PIRE0_EL1, x0 + mrs x0, REG_PIR_EL12 + msr REG_PIR_EL1, x0 + +.Lskip_indirection: +.Lskip_tcr2: + isb // Hack the exception return to stay at EL2 diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 370ab84fd06e..8439248c21d3 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -123,6 +123,7 @@ static const struct ftr_set_desc isar2 __initconst = { .fields = { FIELD("gpa3", ID_AA64ISAR2_EL1_GPA3_SHIFT, NULL), FIELD("apa3", ID_AA64ISAR2_EL1_APA3_SHIFT, NULL), + FIELD("mops", ID_AA64ISAR2_EL1_MOPS_SHIFT, NULL), {} }, }; @@ -174,6 +175,7 @@ static const struct { "id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 " "id_aa64isar1.api=0 id_aa64isar1.apa=0 " "id_aa64isar2.gpa3=0 id_aa64isar2.apa3=0" }, + { "arm64.nomops", "id_aa64isar2.mops=0" }, { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "kaslr.disabled=1" }, }; diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index e7477f21a4c9..17f96a19781d 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -4,90 +4,35 @@ */ #include <linux/cache.h> -#include <linux/crc32.h> #include <linux/init.h> -#include <linux/libfdt.h> -#include <linux/mm_types.h> -#include <linux/sched.h> -#include <linux/types.h> -#include <linux/pgtable.h> -#include <linux/random.h> +#include <linux/printk.h> -#include <asm/fixmap.h> -#include <asm/kernel-pgtable.h> +#include <asm/cpufeature.h> #include <asm/memory.h> -#include <asm/mmu.h> -#include <asm/sections.h> -#include <asm/setup.h> -u64 __ro_after_init module_alloc_base; u16 __initdata memstart_offset_seed; struct arm64_ftr_override kaslr_feature_override __initdata; -static int __init kaslr_init(void) -{ - u64 module_range; - u32 seed; - - /* - * Set a reasonable default for module_alloc_base in case - * we end up running with module randomization disabled. - */ - module_alloc_base = (u64)_etext - MODULES_VSIZE; +bool __ro_after_init __kaslr_is_enabled = false; +void __init kaslr_init(void) +{ if (kaslr_feature_override.val & kaslr_feature_override.mask & 0xf) { pr_info("KASLR disabled on command line\n"); - return 0; - } - - if (!kaslr_enabled()) { - pr_warn("KASLR disabled due to lack of seed\n"); - return 0; + return; } - pr_info("KASLR enabled\n"); - /* - * KASAN without KASAN_VMALLOC does not expect the module region to - * intersect the vmalloc region, since shadow memory is allocated for - * each module at load time, whereas the vmalloc region will already be - * shadowed by KASAN zero pages. + * The KASLR offset modulo MIN_KIMG_ALIGN is taken from the physical + * placement of the image rather than from the seed, so a displacement + * of less than MIN_KIMG_ALIGN means that no seed was provided. */ - BUILD_BUG_ON((IS_ENABLED(CONFIG_KASAN_GENERIC) || - IS_ENABLED(CONFIG_KASAN_SW_TAGS)) && - !IS_ENABLED(CONFIG_KASAN_VMALLOC)); - - seed = get_random_u32(); - - if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { - /* - * Randomize the module region over a 2 GB window covering the - * kernel. This reduces the risk of modules leaking information - * about the address of the kernel itself, but results in - * branches between modules and the core kernel that are - * resolved via PLTs. (Branches between modules will be - * resolved normally.) - */ - module_range = SZ_2G - (u64)(_end - _stext); - module_alloc_base = max((u64)_end - SZ_2G, (u64)MODULES_VADDR); - } else { - /* - * Randomize the module region by setting module_alloc_base to - * a PAGE_SIZE multiple in the range [_etext - MODULES_VSIZE, - * _stext) . This guarantees that the resulting region still - * covers [_stext, _etext], and that all relative branches can - * be resolved without veneers unless this region is exhausted - * and we fall back to a larger 2GB window in module_alloc() - * when ARM64_MODULE_PLTS is enabled. - */ - module_range = MODULES_VSIZE - (u64)(_etext - _stext); + if (kaslr_offset() < MIN_KIMG_ALIGN) { + pr_warn("KASLR disabled due to lack of seed\n"); + return; } - /* use the lower 21 bits to randomize the base of the module region */ - module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21; - module_alloc_base &= PAGE_MASK; - - return 0; + pr_info("KASLR enabled\n"); + __kaslr_is_enabled = true; } -subsys_initcall(kaslr_init) diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 5ed6a585f21f..636be6715155 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -48,7 +48,7 @@ static void *image_load(struct kimage *image, /* * We require a kernel with an unambiguous Image header. Per - * Documentation/arm64/booting.rst, this is the case when image_size + * Documentation/arch/arm64/booting.rst, this is the case when image_size * is non-zero (practically speaking, since v3.17). */ h = (struct arm64_image_header *)kernel; diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S index 692e9d2e31e5..af046ceac22d 100644 --- a/arch/arm64/kernel/kuser32.S +++ b/arch/arm64/kernel/kuser32.S @@ -10,7 +10,7 @@ * aarch32_setup_additional_pages() and are provided for compatibility * reasons with 32 bit (aarch32) applications that need them. * - * See Documentation/arm/kernel_user_helpers.rst for formal definitions. + * See Documentation/arch/arm/kernel_user_helpers.rst for formal definitions. */ #include <asm/unistd.h> diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 543493bf924d..ad02058756b5 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -7,6 +7,7 @@ #include <linux/ftrace.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/moduleloader.h> #include <linux/sort.h> static struct plt_entry __get_adrp_add_pair(u64 dst, u64 pc, diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 5af4975caeb5..dd851297596e 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -7,6 +7,8 @@ * Author: Will Deacon <will.deacon@arm.com> */ +#define pr_fmt(fmt) "Modules: " fmt + #include <linux/bitops.h> #include <linux/elf.h> #include <linux/ftrace.h> @@ -15,52 +17,131 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/moduleloader.h> +#include <linux/random.h> #include <linux/scs.h> #include <linux/vmalloc.h> + #include <asm/alternative.h> #include <asm/insn.h> #include <asm/scs.h> #include <asm/sections.h> +static u64 module_direct_base __ro_after_init = 0; +static u64 module_plt_base __ro_after_init = 0; + +/* + * Choose a random page-aligned base address for a window of 'size' bytes which + * entirely contains the interval [start, end - 1]. + */ +static u64 __init random_bounding_box(u64 size, u64 start, u64 end) +{ + u64 max_pgoff, pgoff; + + if ((end - start) >= size) + return 0; + + max_pgoff = (size - (end - start)) / PAGE_SIZE; + pgoff = get_random_u32_inclusive(0, max_pgoff); + + return start - pgoff * PAGE_SIZE; +} + +/* + * Modules may directly reference data and text anywhere within the kernel + * image and other modules. References using PREL32 relocations have a +/-2G + * range, and so we need to ensure that the entire kernel image and all modules + * fall within a 2G window such that these are always within range. + * + * Modules may directly branch to functions and code within the kernel text, + * and to functions and code within other modules. These branches will use + * CALL26/JUMP26 relocations with a +/-128M range. Without PLTs, we must ensure + * that the entire kernel text and all module text falls within a 128M window + * such that these are always within range. With PLTs, we can expand this to a + * 2G window. + * + * We chose the 128M region to surround the entire kernel image (rather than + * just the text) as using the same bounds for the 128M and 2G regions ensures + * by construction that we never select a 128M region that is not a subset of + * the 2G region. For very large and unusual kernel configurations this means + * we may fall back to PLTs where they could have been avoided, but this keeps + * the logic significantly simpler. + */ +static int __init module_init_limits(void) +{ + u64 kernel_end = (u64)_end; + u64 kernel_start = (u64)_text; + u64 kernel_size = kernel_end - kernel_start; + + /* + * The default modules region is placed immediately below the kernel + * image, and is large enough to use the full 2G relocation range. + */ + BUILD_BUG_ON(KIMAGE_VADDR != MODULES_END); + BUILD_BUG_ON(MODULES_VSIZE < SZ_2G); + + if (!kaslr_enabled()) { + if (kernel_size < SZ_128M) + module_direct_base = kernel_end - SZ_128M; + if (kernel_size < SZ_2G) + module_plt_base = kernel_end - SZ_2G; + } else { + u64 min = kernel_start; + u64 max = kernel_end; + + if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { + pr_info("2G module region forced by RANDOMIZE_MODULE_REGION_FULL\n"); + } else { + module_direct_base = random_bounding_box(SZ_128M, min, max); + if (module_direct_base) { + min = module_direct_base; + max = module_direct_base + SZ_128M; + } + } + + module_plt_base = random_bounding_box(SZ_2G, min, max); + } + + pr_info("%llu pages in range for non-PLT usage", + module_direct_base ? (SZ_128M - kernel_size) / PAGE_SIZE : 0); + pr_info("%llu pages in range for PLT usage", + module_plt_base ? (SZ_2G - kernel_size) / PAGE_SIZE : 0); + + return 0; +} +subsys_initcall(module_init_limits); + void *module_alloc(unsigned long size) { - u64 module_alloc_end = module_alloc_base + MODULES_VSIZE; - gfp_t gfp_mask = GFP_KERNEL; - void *p; - - /* Silence the initial allocation */ - if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS)) - gfp_mask |= __GFP_NOWARN; - - if (IS_ENABLED(CONFIG_KASAN_GENERIC) || - IS_ENABLED(CONFIG_KASAN_SW_TAGS)) - /* don't exceed the static module region - see below */ - module_alloc_end = MODULES_END; - - p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_end, gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK, - NUMA_NO_NODE, __builtin_return_address(0)); - - if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && - (IS_ENABLED(CONFIG_KASAN_VMALLOC) || - (!IS_ENABLED(CONFIG_KASAN_GENERIC) && - !IS_ENABLED(CONFIG_KASAN_SW_TAGS)))) - /* - * KASAN without KASAN_VMALLOC can only deal with module - * allocations being served from the reserved module region, - * since the remainder of the vmalloc region is already - * backed by zero shadow pages, and punching holes into it - * is non-trivial. Since the module region is not randomized - * when KASAN is enabled without KASAN_VMALLOC, it is even - * less likely that the module region gets exhausted, so we - * can simply omit this fallback in that case. - */ - p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_base + SZ_2G, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, - __builtin_return_address(0)); + void *p = NULL; + + /* + * Where possible, prefer to allocate within direct branch range of the + * kernel such that no PLTs are necessary. + */ + if (module_direct_base) { + p = __vmalloc_node_range(size, MODULE_ALIGN, + module_direct_base, + module_direct_base + SZ_128M, + GFP_KERNEL | __GFP_NOWARN, + PAGE_KERNEL, 0, NUMA_NO_NODE, + __builtin_return_address(0)); + } - if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { + if (!p && module_plt_base) { + p = __vmalloc_node_range(size, MODULE_ALIGN, + module_plt_base, + module_plt_base + SZ_2G, + GFP_KERNEL | __GFP_NOWARN, + PAGE_KERNEL, 0, NUMA_NO_NODE, + __builtin_return_address(0)); + } + + if (!p) { + pr_warn_ratelimited("%s: unable to allocate memory\n", + __func__); + } + + if (p && (kasan_alloc_module_shadow(p, size, GFP_KERNEL) < 0)) { vfree(p); return NULL; } @@ -448,9 +529,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_CALL26: ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, 26, AARCH64_INSN_IMM_26); - - if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && - ovf == -ERANGE) { + if (ovf == -ERANGE) { val = module_emit_plt_entry(me, sechdrs, loc, &rel[i], sym); if (!val) return -ENOEXEC; @@ -487,7 +566,7 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { -#if defined(CONFIG_ARM64_MODULE_PLTS) && defined(CONFIG_DYNAMIC_FTRACE) +#if defined(CONFIG_DYNAMIC_FTRACE) const Elf_Shdr *s; struct plt_entry *plts; diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index f5bcb0dc6267..4c5ef9b20065 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -66,13 +66,10 @@ void mte_sync_tags(pte_t old_pte, pte_t pte) return; /* if PG_mte_tagged is set, tags have already been initialised */ - for (i = 0; i < nr_pages; i++, page++) { - if (!page_mte_tagged(page)) { + for (i = 0; i < nr_pages; i++, page++) + if (!page_mte_tagged(page)) mte_sync_page_tags(page, old_pte, check_swap, pte_is_tagged); - set_page_mte_tagged(page); - } - } /* ensure the tags are visible before the PTE is set */ smp_wmb(); @@ -419,10 +416,9 @@ long get_mte_ctrl(struct task_struct *task) static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, struct iovec *kiov, unsigned int gup_flags) { - struct vm_area_struct *vma; void __user *buf = kiov->iov_base; size_t len = kiov->iov_len; - int ret; + int err = 0; int write = gup_flags & FOLL_WRITE; if (!access_ok(buf, len)) @@ -432,14 +428,16 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, return -EIO; while (len) { + struct vm_area_struct *vma; unsigned long tags, offset; void *maddr; - struct page *page = NULL; + struct page *page = get_user_page_vma_remote(mm, addr, + gup_flags, &vma); - ret = get_user_pages_remote(mm, addr, 1, gup_flags, &page, - &vma, NULL); - if (ret <= 0) + if (IS_ERR_OR_NULL(page)) { + err = page == NULL ? -EIO : PTR_ERR(page); break; + } /* * Only copy tags if the page has been mapped as PROT_MTE @@ -449,7 +447,7 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, * was never mapped with PROT_MTE. */ if (!(vma->vm_flags & VM_MTE)) { - ret = -EOPNOTSUPP; + err = -EOPNOTSUPP; put_page(page); break; } @@ -482,7 +480,7 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, kiov->iov_len = buf - kiov->iov_base; if (!kiov->iov_len) { /* check for error accessing the tracee's address space */ - if (ret <= 0) + if (err) return -EIO; else return -EFAULT; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index b8ec7b3ac9cb..417a8a86b2db 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -296,6 +296,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; + kaslr_init(); + /* * If know now we are going to need KPTI then use non-global * mappings from the start, avoiding the cost of rewriting diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 2cfc810d0a5b..e304f7ebec2a 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -23,6 +23,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/elf.h> +#include <asm/exception.h> #include <asm/cacheflush.h> #include <asm/ucontext.h> #include <asm/unistd.h> @@ -398,7 +399,7 @@ static int restore_tpidr2_context(struct user_ctxs *user) __get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err); if (!err) - current->thread.tpidr2_el0 = tpidr2_el0; + write_sysreg_s(tpidr2_el0, SYS_TPIDR2_EL0); return err; } diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index d00d4cbb31b1..edd63894d61e 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -332,17 +332,13 @@ static int op_cpu_kill(unsigned int cpu) } /* - * called on the thread which is asking for a CPU to be shutdown - - * waits until shutdown has completed, or it is timed out. + * Called on the thread which is asking for a CPU to be shutdown after the + * shutdown completed. */ -void __cpu_die(unsigned int cpu) +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { int err; - if (!cpu_wait_death(cpu, 5)) { - pr_crit("CPU%u: cpu didn't die\n", cpu); - return; - } pr_debug("CPU%u: shutdown\n", cpu); /* @@ -369,8 +365,8 @@ void __noreturn cpu_die(void) local_daif_mask(); - /* Tell __cpu_die() that this CPU is now safe to dispose of */ - (void)cpu_report_death(); + /* Tell cpuhp_bp_sync_dead() that this CPU is now safe to dispose of */ + cpuhp_ap_report_dead(); /* * Actually shutdown the CPU. This must never fail. The specific hotplug diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index da84cf855c44..5a668d7f3c1f 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -147,11 +147,9 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, * exit regardless, as the old entry assembly did. */ if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { - local_daif_mask(); flags = read_thread_flags(); if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; - local_daif_restore(DAIF_PROCCTX); } trace_exit: diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 4bb1b8f47298..8b70759cdbb9 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -514,6 +514,63 @@ void do_el1_fpac(struct pt_regs *regs, unsigned long esr) die("Oops - FPAC", regs, esr); } +void do_el0_mops(struct pt_regs *regs, unsigned long esr) +{ + bool wrong_option = esr & ESR_ELx_MOPS_ISS_WRONG_OPTION; + bool option_a = esr & ESR_ELx_MOPS_ISS_OPTION_A; + int dstreg = ESR_ELx_MOPS_ISS_DESTREG(esr); + int srcreg = ESR_ELx_MOPS_ISS_SRCREG(esr); + int sizereg = ESR_ELx_MOPS_ISS_SIZEREG(esr); + unsigned long dst, src, size; + + dst = pt_regs_read_reg(regs, dstreg); + src = pt_regs_read_reg(regs, srcreg); + size = pt_regs_read_reg(regs, sizereg); + + /* + * Put the registers back in the original format suitable for a + * prologue instruction, using the generic return routine from the + * Arm ARM (DDI 0487I.a) rules CNTMJ and MWFQH. + */ + if (esr & ESR_ELx_MOPS_ISS_MEM_INST) { + /* SET* instruction */ + if (option_a ^ wrong_option) { + /* Format is from Option A; forward set */ + pt_regs_write_reg(regs, dstreg, dst + size); + pt_regs_write_reg(regs, sizereg, -size); + } + } else { + /* CPY* instruction */ + if (!(option_a ^ wrong_option)) { + /* Format is from Option B */ + if (regs->pstate & PSR_N_BIT) { + /* Backward copy */ + pt_regs_write_reg(regs, dstreg, dst - size); + pt_regs_write_reg(regs, srcreg, src - size); + } + } else { + /* Format is from Option A */ + if (size & BIT(63)) { + /* Forward copy */ + pt_regs_write_reg(regs, dstreg, dst + size); + pt_regs_write_reg(regs, srcreg, src + size); + pt_regs_write_reg(regs, sizereg, -size); + } + } + } + + if (esr & ESR_ELx_MOPS_ISS_FROM_EPILOGUE) + regs->pc -= 8; + else + regs->pc -= 4; + + /* + * If single stepping then finish the step before executing the + * prologue instruction. + */ + user_fastforward_single_step(current); +} + #define __user_cache_maint(insn, address, res) \ if (address >= TASK_SIZE_MAX) { \ res = -EFAULT; \ @@ -824,6 +881,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_DABT_LOW] = "DABT (lower EL)", [ESR_ELx_EC_DABT_CUR] = "DABT (current EL)", [ESR_ELx_EC_SP_ALIGN] = "SP Alignment", + [ESR_ELx_EC_MOPS] = "MOPS", [ESR_ELx_EC_FP_EXC32] = "FP (AArch32)", [ESR_ELx_EC_FP_EXC64] = "FP (AArch64)", [ESR_ELx_EC_SERROR] = "SError", @@ -947,7 +1005,7 @@ void do_serror(struct pt_regs *regs, unsigned long esr) } /* GENERIC_BUG traps */ - +#ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long addr) { /* @@ -959,6 +1017,7 @@ int is_valid_bugaddr(unsigned long addr) */ return 1; } +#endif static int bug_handler(struct pt_regs *regs, unsigned long esr) { @@ -1044,7 +1103,7 @@ static int kasan_handler(struct pt_regs *regs, unsigned long esr) bool recover = esr & KASAN_ESR_RECOVER; bool write = esr & KASAN_ESR_WRITE; size_t size = KASAN_ESR_SIZE(esr); - u64 addr = regs->regs[0]; + void *addr = (void *)regs->regs[0]; u64 pc = regs->pc; kasan_report(addr, size, write, pc); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 0119dc91abb5..d9e1355730ef 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -288,7 +288,7 @@ static int aarch32_alloc_kuser_vdso_page(void) memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start, kuser_sz); - aarch32_vectors_page = virt_to_page(vdso_page); + aarch32_vectors_page = virt_to_page((void *)vdso_page); return 0; } diff --git a/arch/arm64/kernel/watchdog_hld.c b/arch/arm64/kernel/watchdog_hld.c new file mode 100644 index 000000000000..dcd25322127c --- /dev/null +++ b/arch/arm64/kernel/watchdog_hld.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/nmi.h> +#include <linux/cpufreq.h> +#include <linux/perf/arm_pmu.h> + +/* + * Safe maximum CPU frequency in case a particular platform doesn't implement + * cpufreq driver. Although, architecture doesn't put any restrictions on + * maximum frequency but 5 GHz seems to be safe maximum given the available + * Arm CPUs in the market which are clocked much less than 5 GHz. On the other + * hand, we can't make it much higher as it would lead to a large hard-lockup + * detection timeout on parts which are running slower (eg. 1GHz on + * Developerbox) and doesn't possess a cpufreq driver. + */ +#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz +u64 hw_nmi_get_sample_period(int watchdog_thresh) +{ + unsigned int cpu = smp_processor_id(); + unsigned long max_cpu_freq; + + max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; + if (!max_cpu_freq) + max_cpu_freq = SAFE_MAX_CPU_FREQ; + + return (u64)max_cpu_freq * watchdog_thresh; +} + +bool __init arch_perf_nmi_is_available(void) +{ + /* + * hardlockup_detector_perf_init() will success even if Pseudo-NMI turns off, + * however, the pmu interrupts will act like a normal interrupt instead of + * NMI and the hardlockup detector would be broken. + */ + return arm_pmu_irq_is_nmi(); +} |