diff options
Diffstat (limited to 'arch/arm64/kernel')
27 files changed, 808 insertions, 431 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index fc6488660f64..4e5b8ee31442 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -21,7 +21,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ syscall.o -extra-$(CONFIG_EFI) := efi-entry.o +targets += efi-entry.o OBJCOPYFLAGS := --prefix-symbols=__efistub_ $(obj)/%.stub.o: $(obj)/%.o FORCE diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 7832b3216370..4cc581af2d96 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -630,7 +630,7 @@ static int __init armv8_deprecated_init(void) register_insn_emulation(&cp15_barrier_ops); if (IS_ENABLED(CONFIG_SETEND_EMULATION)) { - if(system_supports_mixed_endian_el0()) + if (system_supports_mixed_endian_el0()) register_insn_emulation(&setend_ops); else pr_info("setend instruction emulation is not supported on this system\n"); diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index a5bdce8af65b..9981a0a5a87f 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -40,6 +40,10 @@ int main(void) #endif BLANK(); DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context)); +#ifdef CONFIG_ARM64_PTR_AUTH + DEFINE(THREAD_KEYS_USER, offsetof(struct task_struct, thread.keys_user)); + DEFINE(THREAD_KEYS_KERNEL, offsetof(struct task_struct, thread.keys_kernel)); +#endif BLANK(); DEFINE(S_X0, offsetof(struct pt_regs, regs[0])); DEFINE(S_X2, offsetof(struct pt_regs, regs[2])); @@ -88,6 +92,9 @@ int main(void) BLANK(); DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); +#ifdef CONFIG_ARM64_PTR_AUTH + DEFINE(CPU_BOOT_PTRAUTH_KEY, offsetof(struct secondary_data, ptrauth_key)); +#endif BLANK(); #ifdef CONFIG_KVM_ARM_HOST DEFINE(VCPU_CONTEXT, offsetof(struct kvm_vcpu, arch.ctxt)); @@ -128,5 +135,14 @@ int main(void) DEFINE(SDEI_EVENT_INTREGS, offsetof(struct sdei_registered_event, interrupted_regs)); DEFINE(SDEI_EVENT_PRIORITY, offsetof(struct sdei_registered_event, priority)); #endif +#ifdef CONFIG_ARM64_PTR_AUTH + DEFINE(PTRAUTH_USER_KEY_APIA, offsetof(struct ptrauth_keys_user, apia)); + DEFINE(PTRAUTH_USER_KEY_APIB, offsetof(struct ptrauth_keys_user, apib)); + DEFINE(PTRAUTH_USER_KEY_APDA, offsetof(struct ptrauth_keys_user, apda)); + DEFINE(PTRAUTH_USER_KEY_APDB, offsetof(struct ptrauth_keys_user, apdb)); + DEFINE(PTRAUTH_USER_KEY_APGA, offsetof(struct ptrauth_keys_user, apga)); + DEFINE(PTRAUTH_KERNEL_KEY_APIA, offsetof(struct ptrauth_keys_kernel, apia)); + BLANK(); +#endif return 0; } diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 32c7bf858dd9..38087b4c0432 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -32,7 +32,7 @@ ENTRY(__cpu_soft_restart) /* Clear sctlr_el1 flags. */ mrs x12, sctlr_el1 - ldr x13, =SCTLR_ELx_FLAGS + mov_q x13, SCTLR_ELx_FLAGS bic x12, x12, x13 pre_disable_mmu_workaround msr sctlr_el1, x12 diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 703ad0a84f99..df56d2295d16 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/cpufeature.h> +#include <asm/kvm_asm.h> #include <asm/smp_plat.h> static bool __maybe_unused @@ -113,13 +114,10 @@ atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1); DEFINE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); #ifdef CONFIG_KVM_INDIRECT_VECTORS -extern char __smccc_workaround_1_smc_start[]; -extern char __smccc_workaround_1_smc_end[]; - static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start, const char *hyp_vecs_end) { - void *dst = lm_alias(__bp_harden_hyp_vecs_start + slot * SZ_2K); + void *dst = lm_alias(__bp_harden_hyp_vecs + slot * SZ_2K); int i; for (i = 0; i < SZ_2K; i += 0x80) @@ -163,9 +161,6 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, raw_spin_unlock(&bp_lock); } #else -#define __smccc_workaround_1_smc_start NULL -#define __smccc_workaround_1_smc_end NULL - static void install_bp_hardening_cb(bp_hardening_cb_t fn, const char *hyp_vecs_start, const char *hyp_vecs_end) @@ -176,7 +171,7 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, #include <linux/arm-smccc.h> -static void call_smc_arch_workaround_1(void) +static void __maybe_unused call_smc_arch_workaround_1(void) { arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } @@ -239,11 +234,14 @@ static int detect_harden_bp_fw(void) smccc_end = NULL; break; +#if IS_ENABLED(CONFIG_KVM_ARM_HOST) case SMCCC_CONDUIT_SMC: cb = call_smc_arch_workaround_1; - smccc_start = __smccc_workaround_1_smc_start; - smccc_end = __smccc_workaround_1_smc_end; + smccc_start = __smccc_workaround_1_smc; + smccc_end = __smccc_workaround_1_smc + + __SMCCC_WORKAROUND_1_SMC_SZ; break; +#endif default: return -1; diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c index 7e07072757af..e133011f64b5 100644 --- a/arch/arm64/kernel/cpu_ops.c +++ b/arch/arm64/kernel/cpu_ops.c @@ -15,10 +15,12 @@ #include <asm/smp_plat.h> extern const struct cpu_operations smp_spin_table_ops; +#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL extern const struct cpu_operations acpi_parking_protocol_ops; +#endif extern const struct cpu_operations cpu_psci_ops; -const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; +static const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; static const struct cpu_operations *const dt_supported_cpu_ops[] __initconst = { &smp_spin_table_ops, @@ -94,7 +96,7 @@ static const char *__init cpu_read_enable_method(int cpu) /* * Read a cpu's enable method and record it in cpu_ops. */ -int __init cpu_read_ops(int cpu) +int __init init_cpu_ops(int cpu) { const char *enable_method = cpu_read_enable_method(cpu); @@ -109,3 +111,8 @@ int __init cpu_read_ops(int cpu) return 0; } + +const struct cpu_operations *get_cpu_ops(int cpu) +{ + return cpu_ops[cpu]; +} diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0b6715625cf6..9fac745aa7bb 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -116,6 +116,8 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap); +static bool __system_matches_cap(unsigned int n); + /* * NOTE: Any changes to the visibility of features should be kept in * sync with the documentation of the CPU feature register ABI. @@ -163,6 +165,7 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0), @@ -551,7 +554,7 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) BUG_ON(!reg); - for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { + for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) { u64 ftr_mask = arm64_ftr_mask(ftrp); s64 ftr_new = arm64_ftr_value(ftrp, new); @@ -1222,6 +1225,57 @@ static bool has_hw_dbm(const struct arm64_cpu_capabilities *cap, #endif +#ifdef CONFIG_ARM64_AMU_EXTN + +/* + * The "amu_cpus" cpumask only signals that the CPU implementation for the + * flagged CPUs supports the Activity Monitors Unit (AMU) but does not provide + * information regarding all the events that it supports. When a CPU bit is + * set in the cpumask, the user of this feature can only rely on the presence + * of the 4 fixed counters for that CPU. But this does not guarantee that the + * counters are enabled or access to these counters is enabled by code + * executed at higher exception levels (firmware). + */ +static struct cpumask amu_cpus __read_mostly; + +bool cpu_has_amu_feat(int cpu) +{ + return cpumask_test_cpu(cpu, &amu_cpus); +} + +/* Initialize the use of AMU counters for frequency invariance */ +extern void init_cpu_freq_invariance_counters(void); + +static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) +{ + if (has_cpuid_feature(cap, SCOPE_LOCAL_CPU)) { + pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n", + smp_processor_id()); + cpumask_set_cpu(smp_processor_id(), &amu_cpus); + init_cpu_freq_invariance_counters(); + } +} + +static bool has_amu(const struct arm64_cpu_capabilities *cap, + int __unused) +{ + /* + * The AMU extension is a non-conflicting feature: the kernel can + * safely run a mix of CPUs with and without support for the + * activity monitors extension. Therefore, unconditionally enable + * the capability to allow any late CPU to use the feature. + * + * With this feature unconditionally enabled, the cpu_enable + * function will be called for all CPUs that match the criteria, + * including secondary and hotplugged, marking this feature as + * present on that respective CPU. The enable function will also + * print a detection message. + */ + + return true; +} +#endif + #ifdef CONFIG_ARM64_VHE static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused) { @@ -1316,10 +1370,18 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused) #endif /* CONFIG_ARM64_RAS_EXTN */ #ifdef CONFIG_ARM64_PTR_AUTH -static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap) +static bool has_address_auth(const struct arm64_cpu_capabilities *entry, + int __unused) { - sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | - SCTLR_ELx_ENDA | SCTLR_ELx_ENDB); + return __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) || + __system_matches_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF); +} + +static bool has_generic_auth(const struct arm64_cpu_capabilities *entry, + int __unused) +{ + return __system_matches_cap(ARM64_HAS_GENERIC_AUTH_ARCH) || + __system_matches_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF); } #endif /* CONFIG_ARM64_PTR_AUTH */ @@ -1347,6 +1409,25 @@ static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry, } #endif +/* Internal helper functions to match cpu capability type */ +static bool +cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU); +} + +static bool +cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); +} + +static bool +cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_PANIC_ON_CONFLICT); +} + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -1499,6 +1580,24 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_clear_disr, }, #endif /* CONFIG_ARM64_RAS_EXTN */ +#ifdef CONFIG_ARM64_AMU_EXTN + { + /* + * The feature is enabled by default if CONFIG_ARM64_AMU_EXTN=y. + * Therefore, don't provide .desc as we don't want the detection + * message to be shown until at least one CPU is detected to + * support the feature. + */ + .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_AMU_SHIFT, + .min_field_value = ID_AA64PFR0_AMU, + .cpu_enable = cpu_amu_enable, + }, +#endif /* CONFIG_ARM64_AMU_EXTN */ { .desc = "Data cache clean to the PoU not required for I/D coherence", .capability = ARM64_HAS_CACHE_IDC, @@ -1592,24 +1691,27 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "Address authentication (architected algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_ARCH, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_APA_SHIFT, .min_field_value = ID_AA64ISAR1_APA_ARCHITECTED, .matches = has_cpuid_feature, - .cpu_enable = cpu_enable_address_auth, }, { .desc = "Address authentication (IMP DEF algorithm)", .capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .sys_reg = SYS_ID_AA64ISAR1_EL1, .sign = FTR_UNSIGNED, .field_pos = ID_AA64ISAR1_API_SHIFT, .min_field_value = ID_AA64ISAR1_API_IMP_DEF, .matches = has_cpuid_feature, - .cpu_enable = cpu_enable_address_auth, + }, + { + .capability = ARM64_HAS_ADDRESS_AUTH, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_address_auth, }, { .desc = "Generic authentication (architected algorithm)", @@ -1631,6 +1733,11 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = ID_AA64ISAR1_GPI_IMP_DEF, .matches = has_cpuid_feature, }, + { + .capability = ARM64_HAS_GENERIC_AUTH, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_generic_auth, + }, #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_PSEUDO_NMI { @@ -1980,10 +2087,8 @@ static void __init enable_cpu_capabilities(u16 scope_mask) * Run through the list of capabilities to check for conflicts. * If the system has already detected a capability, take necessary * action on this CPU. - * - * Returns "false" on conflicts. */ -static bool verify_local_cpu_caps(u16 scope_mask) +static void verify_local_cpu_caps(u16 scope_mask) { int i; bool cpu_has_cap, system_has_cap; @@ -2028,10 +2133,12 @@ static bool verify_local_cpu_caps(u16 scope_mask) pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n", smp_processor_id(), caps->capability, caps->desc, system_has_cap, cpu_has_cap); - return false; - } - return true; + if (cpucap_panic_on_conflict(caps)) + cpu_panic_kernel(); + else + cpu_die_early(); + } } /* @@ -2041,12 +2148,8 @@ static bool verify_local_cpu_caps(u16 scope_mask) static void check_early_cpu_features(void) { verify_cpu_asid_bits(); - /* - * Early features are used by the kernel already. If there - * is a conflict, we cannot proceed further. - */ - if (!verify_local_cpu_caps(SCOPE_BOOT_CPU)) - cpu_panic_kernel(); + + verify_local_cpu_caps(SCOPE_BOOT_CPU); } static void @@ -2094,8 +2197,7 @@ static void verify_local_cpu_capabilities(void) * check_early_cpu_features(), as they need to be verified * on all secondary CPUs. */ - if (!verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU)) - cpu_die_early(); + verify_local_cpu_caps(SCOPE_ALL & ~SCOPE_BOOT_CPU); verify_local_elf_hwcaps(arm64_elf_hwcaps); @@ -2146,6 +2248,23 @@ bool this_cpu_has_cap(unsigned int n) return false; } +/* + * 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. + * In all other cases cpus_have_{const_}cap() should be used. + */ +static bool __system_matches_cap(unsigned int n) +{ + if (n < ARM64_NCAPS) { + const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n]; + + if (cap) + return cap->matches(cap, SCOPE_SYSTEM); + } + return false; +} + void cpu_set_feature(unsigned int num) { WARN_ON(num >= MAX_CPU_FEATURES); @@ -2218,7 +2337,7 @@ void __init setup_cpu_features(void) static bool __maybe_unused cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) { - return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO)); + return (__system_matches_cap(ARM64_HAS_PAN) && !__system_matches_cap(ARM64_HAS_UAO)); } static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap) diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index e4d6af2fdec7..b512b5503f6e 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -18,11 +18,11 @@ int arm_cpuidle_init(unsigned int cpu) { + const struct cpu_operations *ops = get_cpu_ops(cpu); int ret = -EOPNOTSUPP; - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_suspend && - cpu_ops[cpu]->cpu_init_idle) - ret = cpu_ops[cpu]->cpu_init_idle(cpu); + if (ops && ops->cpu_suspend && ops->cpu_init_idle) + ret = ops->cpu_init_idle(cpu); return ret; } @@ -37,8 +37,9 @@ int arm_cpuidle_init(unsigned int cpu) int arm_cpuidle_suspend(int index) { int cpu = smp_processor_id(); + const struct cpu_operations *ops = get_cpu_ops(cpu); - return cpu_ops[cpu]->cpu_suspend(index); + return ops->cpu_suspend(index); } #ifdef CONFIG_ACPI diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index fde59981445c..c839b5bf1904 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -175,7 +175,7 @@ NOKPROBE_SYMBOL(el0_pc); static void notrace el0_sp(struct pt_regs *regs, unsigned long esr) { user_exit_irqoff(); - local_daif_restore(DAIF_PROCCTX_NOIRQ); + local_daif_restore(DAIF_PROCCTX); do_sp_pc_abort(regs->sp, esr, regs); } NOKPROBE_SYMBOL(el0_sp); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 7d02f9966d34..833d48c9acb5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -75,27 +75,27 @@ add x29, sp, #S_STACKFRAME .endm -ENTRY(ftrace_regs_caller) +SYM_CODE_START(ftrace_regs_caller) ftrace_regs_entry 1 b ftrace_common -ENDPROC(ftrace_regs_caller) +SYM_CODE_END(ftrace_regs_caller) -ENTRY(ftrace_caller) +SYM_CODE_START(ftrace_caller) ftrace_regs_entry 0 b ftrace_common -ENDPROC(ftrace_caller) +SYM_CODE_END(ftrace_caller) -ENTRY(ftrace_common) +SYM_CODE_START(ftrace_common) sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) mov x1, x9 // parent_ip (callsite's LR) ldr_l x2, function_trace_op // op mov x3, sp // regs -GLOBAL(ftrace_call) +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) bl ftrace_stub #ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); nop // If enabled, this will be replaced // "b ftrace_graph_caller" #endif @@ -122,17 +122,17 @@ ftrace_common_return: add sp, sp, #S_FRAME_SIZE + 16 ret x9 -ENDPROC(ftrace_common) +SYM_CODE_END(ftrace_common) #ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) +SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return -ENDPROC(ftrace_graph_caller) +SYM_CODE_END(ftrace_graph_caller) #endif #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ @@ -218,7 +218,7 @@ ENDPROC(ftrace_graph_caller) * - tracer function to probe instrumented function's entry, * - ftrace_graph_caller to set up an exit hook */ -ENTRY(_mcount) +SYM_FUNC_START(_mcount) mcount_enter ldr_l x2, ftrace_trace_function @@ -242,7 +242,7 @@ skip_ftrace_call: // } b.ne ftrace_graph_caller // ftrace_graph_caller(); #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ mcount_exit -ENDPROC(_mcount) +SYM_FUNC_END(_mcount) EXPORT_SYMBOL(_mcount) NOKPROBE(_mcount) @@ -253,9 +253,9 @@ NOKPROBE(_mcount) * and later on, NOP to branch to ftrace_caller() when enabled or branch to * NOP when disabled per-function base. */ -ENTRY(_mcount) +SYM_FUNC_START(_mcount) ret -ENDPROC(_mcount) +SYM_FUNC_END(_mcount) EXPORT_SYMBOL(_mcount) NOKPROBE(_mcount) @@ -268,24 +268,24 @@ NOKPROBE(_mcount) * - tracer function to probe instrumented function's entry, * - ftrace_graph_caller to set up an exit hook */ -ENTRY(ftrace_caller) +SYM_FUNC_START(ftrace_caller) mcount_enter mcount_get_pc0 x0 // function's pc mcount_get_lr x1 // function's lr -GLOBAL(ftrace_call) // tracer(pc, lr); +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) // tracer(pc, lr); nop // This will be replaced with "bl xxx" // where xxx can be any kind of tracer. #ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); +SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); nop // If enabled, this will be replaced // "b ftrace_graph_caller" #endif mcount_exit -ENDPROC(ftrace_caller) +SYM_FUNC_END(ftrace_caller) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -298,20 +298,20 @@ ENDPROC(ftrace_caller) * the call stack in order to intercept instrumented function's return path * and run return_to_handler() later on its exit. */ -ENTRY(ftrace_graph_caller) +SYM_FUNC_START(ftrace_graph_caller) mcount_get_pc x0 // function's pc mcount_get_lr_addr x1 // pointer to function's saved lr mcount_get_parent_fp x2 // parent's fp bl prepare_ftrace_return // prepare_ftrace_return(pc, &lr, fp) mcount_exit -ENDPROC(ftrace_graph_caller) +SYM_FUNC_END(ftrace_graph_caller) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ -ENTRY(ftrace_stub) +SYM_FUNC_START(ftrace_stub) ret -ENDPROC(ftrace_stub) +SYM_FUNC_END(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -320,7 +320,7 @@ ENDPROC(ftrace_stub) * Run ftrace_return_to_handler() before going back to parent. * @fp is checked against the value passed by ftrace_graph_caller(). */ -ENTRY(return_to_handler) +SYM_CODE_START(return_to_handler) /* save return value regs */ sub sp, sp, #64 stp x0, x1, [sp] @@ -340,5 +340,5 @@ ENTRY(return_to_handler) add sp, sp, #64 ret -END(return_to_handler) +SYM_CODE_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 9461d812ae27..ddcde093c433 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -14,6 +14,7 @@ #include <asm/alternative.h> #include <asm/assembler.h> #include <asm/asm-offsets.h> +#include <asm/asm_pointer_auth.h> #include <asm/cpufeature.h> #include <asm/errno.h> #include <asm/esr.h> @@ -177,6 +178,7 @@ alternative_cb_end apply_ssbd 1, x22, x23 + ptrauth_keys_install_kernel tsk, 1, x20, x22, x23 .else add x21, sp, #S_FRAME_SIZE get_current_task tsk @@ -341,6 +343,9 @@ alternative_else_nop_endif msr cntkctl_el1, x1 4: #endif + /* No kernel C function calls after this as user keys are set. */ + ptrauth_keys_install_user tsk, x0, x1, x2 + apply_ssbd 0, x0, x1 .endif @@ -465,7 +470,7 @@ alternative_endif .pushsection ".entry.text", "ax" .align 11 -ENTRY(vectors) +SYM_CODE_START(vectors) kernel_ventry 1, sync_invalid // Synchronous EL1t kernel_ventry 1, irq_invalid // IRQ EL1t kernel_ventry 1, fiq_invalid // FIQ EL1t @@ -492,7 +497,7 @@ ENTRY(vectors) kernel_ventry 0, fiq_invalid, 32 // FIQ 32-bit EL0 kernel_ventry 0, error_invalid, 32 // Error 32-bit EL0 #endif -END(vectors) +SYM_CODE_END(vectors) #ifdef CONFIG_VMAP_STACK /* @@ -534,57 +539,57 @@ __bad_stack: ASM_BUG() .endm -el0_sync_invalid: +SYM_CODE_START_LOCAL(el0_sync_invalid) inv_entry 0, BAD_SYNC -ENDPROC(el0_sync_invalid) +SYM_CODE_END(el0_sync_invalid) -el0_irq_invalid: +SYM_CODE_START_LOCAL(el0_irq_invalid) inv_entry 0, BAD_IRQ -ENDPROC(el0_irq_invalid) +SYM_CODE_END(el0_irq_invalid) -el0_fiq_invalid: +SYM_CODE_START_LOCAL(el0_fiq_invalid) inv_entry 0, BAD_FIQ -ENDPROC(el0_fiq_invalid) +SYM_CODE_END(el0_fiq_invalid) -el0_error_invalid: +SYM_CODE_START_LOCAL(el0_error_invalid) inv_entry 0, BAD_ERROR -ENDPROC(el0_error_invalid) +SYM_CODE_END(el0_error_invalid) #ifdef CONFIG_COMPAT -el0_fiq_invalid_compat: +SYM_CODE_START_LOCAL(el0_fiq_invalid_compat) inv_entry 0, BAD_FIQ, 32 -ENDPROC(el0_fiq_invalid_compat) +SYM_CODE_END(el0_fiq_invalid_compat) #endif -el1_sync_invalid: +SYM_CODE_START_LOCAL(el1_sync_invalid) inv_entry 1, BAD_SYNC -ENDPROC(el1_sync_invalid) +SYM_CODE_END(el1_sync_invalid) -el1_irq_invalid: +SYM_CODE_START_LOCAL(el1_irq_invalid) inv_entry 1, BAD_IRQ -ENDPROC(el1_irq_invalid) +SYM_CODE_END(el1_irq_invalid) -el1_fiq_invalid: +SYM_CODE_START_LOCAL(el1_fiq_invalid) inv_entry 1, BAD_FIQ -ENDPROC(el1_fiq_invalid) +SYM_CODE_END(el1_fiq_invalid) -el1_error_invalid: +SYM_CODE_START_LOCAL(el1_error_invalid) inv_entry 1, BAD_ERROR -ENDPROC(el1_error_invalid) +SYM_CODE_END(el1_error_invalid) /* * EL1 mode handlers. */ .align 6 -el1_sync: +SYM_CODE_START_LOCAL_NOALIGN(el1_sync) kernel_entry 1 mov x0, sp bl el1_sync_handler kernel_exit 1 -ENDPROC(el1_sync) +SYM_CODE_END(el1_sync) .align 6 -el1_irq: +SYM_CODE_START_LOCAL_NOALIGN(el1_irq) kernel_entry 1 gic_prio_irq_setup pmr=x20, tmp=x1 enable_da_f @@ -639,42 +644,42 @@ alternative_else_nop_endif #endif kernel_exit 1 -ENDPROC(el1_irq) +SYM_CODE_END(el1_irq) /* * EL0 mode handlers. */ .align 6 -el0_sync: +SYM_CODE_START_LOCAL_NOALIGN(el0_sync) kernel_entry 0 mov x0, sp bl el0_sync_handler b ret_to_user -ENDPROC(el0_sync) +SYM_CODE_END(el0_sync) #ifdef CONFIG_COMPAT .align 6 -el0_sync_compat: +SYM_CODE_START_LOCAL_NOALIGN(el0_sync_compat) kernel_entry 0, 32 mov x0, sp bl el0_sync_compat_handler b ret_to_user -ENDPROC(el0_sync_compat) +SYM_CODE_END(el0_sync_compat) .align 6 -el0_irq_compat: +SYM_CODE_START_LOCAL_NOALIGN(el0_irq_compat) kernel_entry 0, 32 b el0_irq_naked -ENDPROC(el0_irq_compat) +SYM_CODE_END(el0_irq_compat) -el0_error_compat: +SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat) kernel_entry 0, 32 b el0_error_naked -ENDPROC(el0_error_compat) +SYM_CODE_END(el0_error_compat) #endif .align 6 -el0_irq: +SYM_CODE_START_LOCAL_NOALIGN(el0_irq) kernel_entry 0 el0_irq_naked: gic_prio_irq_setup pmr=x20, tmp=x0 @@ -696,9 +701,9 @@ el0_irq_naked: bl trace_hardirqs_on #endif b ret_to_user -ENDPROC(el0_irq) +SYM_CODE_END(el0_irq) -el1_error: +SYM_CODE_START_LOCAL(el1_error) kernel_entry 1 mrs x1, esr_el1 gic_prio_kentry_setup tmp=x2 @@ -706,9 +711,9 @@ el1_error: mov x0, sp bl do_serror kernel_exit 1 -ENDPROC(el1_error) +SYM_CODE_END(el1_error) -el0_error: +SYM_CODE_START_LOCAL(el0_error) kernel_entry 0 el0_error_naked: mrs x25, esr_el1 @@ -720,7 +725,7 @@ el0_error_naked: bl do_serror enable_da_f b ret_to_user -ENDPROC(el0_error) +SYM_CODE_END(el0_error) /* * Ok, we need to do extra processing, enter the slow path. @@ -832,7 +837,7 @@ alternative_else_nop_endif .endm .align 11 -ENTRY(tramp_vectors) +SYM_CODE_START_NOALIGN(tramp_vectors) .space 0x400 tramp_ventry @@ -844,24 +849,24 @@ ENTRY(tramp_vectors) tramp_ventry 32 tramp_ventry 32 tramp_ventry 32 -END(tramp_vectors) +SYM_CODE_END(tramp_vectors) -ENTRY(tramp_exit_native) +SYM_CODE_START(tramp_exit_native) tramp_exit -END(tramp_exit_native) +SYM_CODE_END(tramp_exit_native) -ENTRY(tramp_exit_compat) +SYM_CODE_START(tramp_exit_compat) tramp_exit 32 -END(tramp_exit_compat) +SYM_CODE_END(tramp_exit_compat) .ltorg .popsection // .entry.tramp.text #ifdef CONFIG_RANDOMIZE_BASE .pushsection ".rodata", "a" .align PAGE_SHIFT - .globl __entry_tramp_data_start -__entry_tramp_data_start: +SYM_DATA_START(__entry_tramp_data_start) .quad vectors +SYM_DATA_END(__entry_tramp_data_start) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ @@ -874,7 +879,7 @@ __entry_tramp_data_start: * Previous and next are guaranteed not to be the same. * */ -ENTRY(cpu_switch_to) +SYM_FUNC_START(cpu_switch_to) mov x10, #THREAD_CPU_CONTEXT add x8, x0, x10 mov x9, sp @@ -895,21 +900,22 @@ ENTRY(cpu_switch_to) ldr lr, [x8] mov sp, x9 msr sp_el0, x1 + ptrauth_keys_install_kernel x1, 1, x8, x9, x10 ret -ENDPROC(cpu_switch_to) +SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) /* * This is how we return from a fork. */ -ENTRY(ret_from_fork) +SYM_CODE_START(ret_from_fork) bl schedule_tail cbz x19, 1f // not a kernel thread mov x0, x20 blr x19 1: get_current_task tsk b ret_to_user -ENDPROC(ret_from_fork) +SYM_CODE_END(ret_from_fork) NOKPROBE(ret_from_fork) #ifdef CONFIG_ARM_SDE_INTERFACE @@ -938,7 +944,7 @@ NOKPROBE(ret_from_fork) */ .ltorg .pushsection ".entry.tramp.text", "ax" -ENTRY(__sdei_asm_entry_trampoline) +SYM_CODE_START(__sdei_asm_entry_trampoline) mrs x4, ttbr1_el1 tbz x4, #USER_ASID_BIT, 1f @@ -960,7 +966,7 @@ ENTRY(__sdei_asm_entry_trampoline) ldr x4, =__sdei_asm_handler #endif br x4 -ENDPROC(__sdei_asm_entry_trampoline) +SYM_CODE_END(__sdei_asm_entry_trampoline) NOKPROBE(__sdei_asm_entry_trampoline) /* @@ -970,21 +976,22 @@ NOKPROBE(__sdei_asm_entry_trampoline) * x2: exit_mode * x4: struct sdei_registered_event argument from registration time. */ -ENTRY(__sdei_asm_exit_trampoline) +SYM_CODE_START(__sdei_asm_exit_trampoline) ldr x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)] cbnz x4, 1f tramp_unmap_kernel tmp=x4 1: sdei_handler_exit exit_mode=x2 -ENDPROC(__sdei_asm_exit_trampoline) +SYM_CODE_END(__sdei_asm_exit_trampoline) NOKPROBE(__sdei_asm_exit_trampoline) .ltorg .popsection // .entry.tramp.text #ifdef CONFIG_RANDOMIZE_BASE .pushsection ".rodata", "a" -__sdei_asm_trampoline_next_handler: +SYM_DATA_START(__sdei_asm_trampoline_next_handler) .quad __sdei_asm_handler +SYM_DATA_END(__sdei_asm_trampoline_next_handler) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ @@ -1002,7 +1009,7 @@ __sdei_asm_trampoline_next_handler: * follow SMC-CC. We save (or retrieve) all the registers as the handler may * want them. */ -ENTRY(__sdei_asm_handler) +SYM_CODE_START(__sdei_asm_handler) stp x2, x3, [x1, #SDEI_EVENT_INTREGS + S_PC] stp x4, x5, [x1, #SDEI_EVENT_INTREGS + 16 * 2] stp x6, x7, [x1, #SDEI_EVENT_INTREGS + 16 * 3] @@ -1085,6 +1092,6 @@ alternative_else_nop_endif tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline br x5 #endif -ENDPROC(__sdei_asm_handler) +SYM_CODE_END(__sdei_asm_handler) NOKPROBE(__sdei_asm_handler) #endif /* CONFIG_ARM_SDE_INTERFACE */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 989b1944cb71..57a91032b4c2 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -105,7 +105,7 @@ pe_header: * x24 __primary_switch() .. relocate_kernel() * current RELR displacement */ -ENTRY(stext) +SYM_CODE_START(stext) bl preserve_boot_args bl el2_setup // Drop to EL1, w0=cpu_boot_mode adrp x23, __PHYS_OFFSET @@ -118,14 +118,15 @@ ENTRY(stext) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ + mov x0, #ARM64_CPU_BOOT_PRIMARY bl __cpu_setup // initialise processor b __primary_switch -ENDPROC(stext) +SYM_CODE_END(stext) /* * Preserve the arguments passed by the bootloader in x0 .. x3 */ -preserve_boot_args: +SYM_CODE_START_LOCAL(preserve_boot_args) mov x21, x0 // x21=FDT adr_l x0, boot_args // record the contents of @@ -137,7 +138,7 @@ preserve_boot_args: mov x1, #0x20 // 4 x 8 bytes b __inval_dcache_area // tail call -ENDPROC(preserve_boot_args) +SYM_CODE_END(preserve_boot_args) /* * Macro to create a table entry to the next page. @@ -275,7 +276,7 @@ ENDPROC(preserve_boot_args) * - first few MB of the kernel linear mapping to jump to once the MMU has * been enabled */ -__create_page_tables: +SYM_FUNC_START_LOCAL(__create_page_tables) mov x28, lr /* @@ -403,15 +404,14 @@ __create_page_tables: bl __inval_dcache_area ret x28 -ENDPROC(__create_page_tables) - .ltorg +SYM_FUNC_END(__create_page_tables) /* * The following fragment of code is executed with the MMU enabled. * * x0 = __PHYS_OFFSET */ -__primary_switched: +SYM_FUNC_START_LOCAL(__primary_switched) adrp x4, init_thread_union add sp, x4, #THREAD_SIZE adr_l x5, init_task @@ -456,7 +456,14 @@ __primary_switched: mov x29, #0 mov x30, #0 b start_kernel -ENDPROC(__primary_switched) +SYM_FUNC_END(__primary_switched) + + .pushsection ".rodata", "a" +SYM_DATA_START(kimage_vaddr) + .quad _text - TEXT_OFFSET +SYM_DATA_END(kimage_vaddr) +EXPORT_SYMBOL(kimage_vaddr) + .popsection /* * end early head section, begin head code that is also used for @@ -464,10 +471,6 @@ ENDPROC(__primary_switched) */ .section ".idmap.text","awx" -ENTRY(kimage_vaddr) - .quad _text - TEXT_OFFSET -EXPORT_SYMBOL(kimage_vaddr) - /* * If we're fortunate enough to boot at EL2, ensure that the world is * sane before dropping to EL1. @@ -475,7 +478,7 @@ EXPORT_SYMBOL(kimage_vaddr) * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in w0 if * booted in EL1 or EL2 respectively. */ -ENTRY(el2_setup) +SYM_FUNC_START(el2_setup) msr SPsel, #1 // We want to use SP_EL{1,2} mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 @@ -599,7 +602,7 @@ set_hcr: isb ret -install_el2_stub: +SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL) /* * When VHE is not in use, early init of EL2 and EL1 needs to be * done here. @@ -636,13 +639,13 @@ install_el2_stub: msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 eret -ENDPROC(el2_setup) +SYM_FUNC_END(el2_setup) /* * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed * in w0. See arch/arm64/include/asm/virt.h for more info. */ -set_cpu_boot_mode_flag: +SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag) adr_l x1, __boot_cpu_mode cmp w0, #BOOT_CPU_MODE_EL2 b.ne 1f @@ -651,7 +654,7 @@ set_cpu_boot_mode_flag: dmb sy dc ivac, x1 // Invalidate potentially stale cache line ret -ENDPROC(set_cpu_boot_mode_flag) +SYM_FUNC_END(set_cpu_boot_mode_flag) /* * These values are written with the MMU off, but read with the MMU on. @@ -667,15 +670,17 @@ ENDPROC(set_cpu_boot_mode_flag) * This is not in .bss, because we set it sufficiently early that the boot-time * zeroing of .bss would clobber it. */ -ENTRY(__boot_cpu_mode) +SYM_DATA_START(__boot_cpu_mode) .long BOOT_CPU_MODE_EL2 .long BOOT_CPU_MODE_EL1 +SYM_DATA_END(__boot_cpu_mode) /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. */ -ENTRY(__early_cpu_boot_status) +SYM_DATA_START(__early_cpu_boot_status) .quad 0 +SYM_DATA_END(__early_cpu_boot_status) .popsection @@ -683,7 +688,7 @@ ENTRY(__early_cpu_boot_status) * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise. */ -ENTRY(secondary_holding_pen) +SYM_FUNC_START(secondary_holding_pen) bl el2_setup // Drop to EL1, w0=cpu_boot_mode bl set_cpu_boot_mode_flag mrs x0, mpidr_el1 @@ -695,31 +700,32 @@ pen: ldr x4, [x3] b.eq secondary_startup wfe b pen -ENDPROC(secondary_holding_pen) +SYM_FUNC_END(secondary_holding_pen) /* * Secondary entry point that jumps straight into the kernel. Only to * be used where CPUs are brought online dynamically by the kernel. */ -ENTRY(secondary_entry) +SYM_FUNC_START(secondary_entry) bl el2_setup // Drop to EL1 bl set_cpu_boot_mode_flag b secondary_startup -ENDPROC(secondary_entry) +SYM_FUNC_END(secondary_entry) -secondary_startup: +SYM_FUNC_START_LOCAL(secondary_startup) /* * Common entry point for secondary CPUs. */ bl __cpu_secondary_check52bitva + mov x0, #ARM64_CPU_BOOT_SECONDARY bl __cpu_setup // initialise processor adrp x1, swapper_pg_dir bl __enable_mmu ldr x8, =__secondary_switched br x8 -ENDPROC(secondary_startup) +SYM_FUNC_END(secondary_startup) -__secondary_switched: +SYM_FUNC_START_LOCAL(__secondary_switched) adr_l x5, vectors msr vbar_el1, x5 isb @@ -734,13 +740,13 @@ __secondary_switched: mov x29, #0 mov x30, #0 b secondary_start_kernel -ENDPROC(__secondary_switched) +SYM_FUNC_END(__secondary_switched) -__secondary_too_slow: +SYM_FUNC_START_LOCAL(__secondary_too_slow) wfe wfi b __secondary_too_slow -ENDPROC(__secondary_too_slow) +SYM_FUNC_END(__secondary_too_slow) /* * The booting CPU updates the failed status @__early_cpu_boot_status, @@ -772,7 +778,7 @@ ENDPROC(__secondary_too_slow) * Checks if the selected granule size is supported by the CPU. * If it isn't, park the CPU */ -ENTRY(__enable_mmu) +SYM_FUNC_START(__enable_mmu) mrs x2, ID_AA64MMFR0_EL1 ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4 cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED @@ -796,9 +802,9 @@ ENTRY(__enable_mmu) dsb nsh isb ret -ENDPROC(__enable_mmu) +SYM_FUNC_END(__enable_mmu) -ENTRY(__cpu_secondary_check52bitva) +SYM_FUNC_START(__cpu_secondary_check52bitva) #ifdef CONFIG_ARM64_VA_BITS_52 ldr_l x0, vabits_actual cmp x0, #52 @@ -816,9 +822,9 @@ ENTRY(__cpu_secondary_check52bitva) #endif 2: ret -ENDPROC(__cpu_secondary_check52bitva) +SYM_FUNC_END(__cpu_secondary_check52bitva) -__no_granule_support: +SYM_FUNC_START_LOCAL(__no_granule_support) /* Indicate that this CPU can't boot and is stuck in the kernel */ update_early_cpu_boot_status \ CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_NO_GRAN, x1, x2 @@ -826,10 +832,10 @@ __no_granule_support: wfe wfi b 1b -ENDPROC(__no_granule_support) +SYM_FUNC_END(__no_granule_support) #ifdef CONFIG_RELOCATABLE -__relocate_kernel: +SYM_FUNC_START_LOCAL(__relocate_kernel) /* * Iterate over each entry in the relocation table, and apply the * relocations in place. @@ -931,10 +937,10 @@ __relocate_kernel: #endif ret -ENDPROC(__relocate_kernel) +SYM_FUNC_END(__relocate_kernel) #endif -__primary_switch: +SYM_FUNC_START_LOCAL(__primary_switch) #ifdef CONFIG_RANDOMIZE_BASE mov x19, x0 // preserve new SCTLR_EL1 value mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value @@ -977,4 +983,4 @@ __primary_switch: ldr x8, =__primary_switched adrp x0, __PHYS_OFFSET br x8 -ENDPROC(__primary_switch) +SYM_FUNC_END(__primary_switch) diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 38bcd4d4e43b..6532105b3e32 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -110,8 +110,6 @@ ENTRY(swsusp_arch_suspend_exit) cbz x24, 3f /* Do we need to re-initialise EL2? */ hvc #0 3: ret - - .ltorg ENDPROC(swsusp_arch_suspend_exit) /* diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 73d46070b315..e473ead806ed 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -63,7 +63,7 @@ el1_sync: beq 9f // Nothing to reset! /* Someone called kvm_call_hyp() against the hyp-stub... */ - ldr x0, =HVC_STUB_ERR + mov_q x0, HVC_STUB_ERR eret 9: mov x0, xzr diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index dd3ae8081b38..b40c3b0def92 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -121,7 +121,7 @@ static int setup_dtb(struct kimage *image, /* add kaslr-seed */ ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED); - if (ret == -FDT_ERR_NOTFOUND) + if (ret == -FDT_ERR_NOTFOUND) ret = 0; else if (ret) goto out; diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index e40b65645c86..4d7879484cec 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -285,6 +285,17 @@ static struct attribute_group armv8_pmuv3_format_attr_group = { #define ARMV8_IDX_COUNTER_LAST(cpu_pmu) \ (ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) + +/* + * 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_PMUVER_8_5); +} + /* * We must chain two programmable counters for 64 bit events, * except when we have allocated the 64bit cycle counter (for CPU @@ -294,9 +305,11 @@ static struct attribute_group armv8_pmuv3_format_attr_group = { 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 !WARN_ON(idx < 0) && armv8pmu_event_is_64bit(event) && + !armv8pmu_has_long_event(cpu_pmu) && (idx != ARMV8_IDX_CYCLE_COUNTER); } @@ -345,7 +358,7 @@ static inline void armv8pmu_select_counter(int idx) isb(); } -static inline u32 armv8pmu_read_evcntr(int idx) +static inline u64 armv8pmu_read_evcntr(int idx) { armv8pmu_select_counter(idx); return read_sysreg(pmxevcntr_el0); @@ -362,6 +375,44 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event) 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 arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); @@ -377,10 +428,10 @@ static u64 armv8pmu_read_counter(struct perf_event *event) else value = armv8pmu_read_hw_counter(event); - return value; + return armv8pmu_unbias_long_counter(event, value); } -static inline void armv8pmu_write_evcntr(int idx, u32 value) +static inline void armv8pmu_write_evcntr(int idx, u64 value) { armv8pmu_select_counter(idx); write_sysreg(value, pmxevcntr_el0); @@ -405,20 +456,14 @@ 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 (!armv8pmu_counter_valid(cpu_pmu, idx)) pr_err("CPU%u writing wrong counter %d\n", smp_processor_id(), idx); - else if (idx == ARMV8_IDX_CYCLE_COUNTER) { - /* - * The cycles counter is really a 64-bit counter. - * When treating it as a 32-bit counter, we only count - * the lower 32 bits, and set the upper 32-bits so that - * we get an interrupt upon 32-bit overflow. - */ - if (!armv8pmu_event_is_64bit(event)) - value |= 0xffffffff00000000ULL; + else if (idx == ARMV8_IDX_CYCLE_COUNTER) write_sysreg(value, pmccntr_el0); - } else + else armv8pmu_write_hw_counter(event, value); } @@ -450,86 +495,74 @@ static inline void armv8pmu_write_event_type(struct perf_event *event) } } -static inline int armv8pmu_enable_counter(int idx) +static u32 armv8pmu_event_cnten_mask(struct perf_event *event) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmcntenset_el0); - return idx; + 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) +{ + write_sysreg(mask, pmcntenset_el0); } static inline void armv8pmu_enable_event_counter(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; - int idx = event->hw.idx; - u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx)); + u32 mask = armv8pmu_event_cnten_mask(event); - if (armv8pmu_event_is_chained(event)) - counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1)); - - kvm_set_pmu_events(counter_bits, attr); + 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(idx); - if (armv8pmu_event_is_chained(event)) - armv8pmu_enable_counter(idx - 1); - } + if (!kvm_pmu_counter_deferred(attr)) + armv8pmu_enable_counter(mask); } -static inline int armv8pmu_disable_counter(int idx) +static inline void armv8pmu_disable_counter(u32 mask) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmcntenclr_el0); - return idx; + write_sysreg(mask, pmcntenclr_el0); } static inline void armv8pmu_disable_event_counter(struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; struct perf_event_attr *attr = &event->attr; - int idx = hwc->idx; - u32 counter_bits = BIT(ARMV8_IDX_TO_COUNTER(idx)); - - if (armv8pmu_event_is_chained(event)) - counter_bits |= BIT(ARMV8_IDX_TO_COUNTER(idx - 1)); + u32 mask = armv8pmu_event_cnten_mask(event); - kvm_clr_pmu_events(counter_bits); + kvm_clr_pmu_events(mask); /* We rely on the hypervisor switch code to disable guest counters */ - if (!kvm_pmu_counter_deferred(attr)) { - if (armv8pmu_event_is_chained(event)) - armv8pmu_disable_counter(idx - 1); - armv8pmu_disable_counter(idx); - } + if (!kvm_pmu_counter_deferred(attr)) + armv8pmu_disable_counter(mask); } -static inline int armv8pmu_enable_intens(int idx) +static inline void armv8pmu_enable_intens(u32 mask) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmintenset_el1); - return idx; + write_sysreg(mask, pmintenset_el1); } -static inline int armv8pmu_enable_event_irq(struct perf_event *event) +static inline void armv8pmu_enable_event_irq(struct perf_event *event) { - return armv8pmu_enable_intens(event->hw.idx); + u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); + armv8pmu_enable_intens(BIT(counter)); } -static inline int armv8pmu_disable_intens(int idx) +static inline void armv8pmu_disable_intens(u32 mask) { - u32 counter = ARMV8_IDX_TO_COUNTER(idx); - write_sysreg(BIT(counter), pmintenclr_el1); + write_sysreg(mask, pmintenclr_el1); isb(); /* Clear the overflow flag in case an interrupt is pending. */ - write_sysreg(BIT(counter), pmovsclr_el0); + write_sysreg(mask, pmovsclr_el0); isb(); - - return idx; } -static inline int armv8pmu_disable_event_irq(struct perf_event *event) +static inline void armv8pmu_disable_event_irq(struct perf_event *event) { - return armv8pmu_disable_intens(event->hw.idx); + u32 counter = ARMV8_IDX_TO_COUNTER(event->hw.idx); + armv8pmu_disable_intens(BIT(counter)); } static inline u32 armv8pmu_getreset_flags(void) @@ -743,7 +776,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc, /* * Otherwise use events counters */ - if (armv8pmu_event_is_64bit(event)) + if (armv8pmu_event_is_64bit(event) && + !armv8pmu_has_long_event(cpu_pmu)) return armv8pmu_get_chain_idx(cpuc, cpu_pmu); else return armv8pmu_get_single_idx(cpuc, cpu_pmu); @@ -815,13 +849,11 @@ static int armv8pmu_filter_match(struct perf_event *event) static void armv8pmu_reset(void *info) { struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; - u32 idx, nb_cnt = cpu_pmu->num_events; + u32 pmcr; /* The counter and interrupt enable registers are unknown at reset. */ - for (idx = ARMV8_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { - armv8pmu_disable_counter(idx); - armv8pmu_disable_intens(idx); - } + 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); @@ -830,8 +862,13 @@ static void armv8pmu_reset(void *info) * Initialize & Reset PMNC. Request overflow interrupt for * 64 bit cycle counter but cheat in armv8pmu_write_counter(). */ - armv8pmu_pmcr_write(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C | - ARMV8_PMU_PMCR_LC); + 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, @@ -914,6 +951,7 @@ static void __armv8pmu_probe_pmu(void *info) if (pmuver == 0xf || pmuver == 0) return; + cpu_pmu->pmuver = pmuver; probe->present = true; /* Read the nb of CNTx counters supported from PMNC */ @@ -953,7 +991,10 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu) return probe.present ? 0 : -ENODEV; } -static int armv8_pmu_init(struct arm_pmu *cpu_pmu) +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) { int ret = armv8pmu_probe_pmu(cpu_pmu); if (ret) @@ -972,144 +1013,127 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->set_event_filter = armv8pmu_set_event_filter; cpu_pmu->filter_match = armv8pmu_filter_match; + 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; + return 0; } static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_pmuv3"; - cpu_pmu->map_event = armv8_pmuv3_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_pmuv3", + armv8_pmuv3_map_event, NULL, NULL); +} - return 0; +static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34", + armv8_pmuv3_map_event, NULL, NULL); } static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a35"; - cpu_pmu->map_event = armv8_a53_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; - - return 0; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35", + armv8_a53_map_event, NULL, NULL); } static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a53"; - cpu_pmu->map_event = armv8_a53_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53", + armv8_a53_map_event, NULL, NULL); +} - return 0; +static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55", + armv8_pmuv3_map_event, NULL, NULL); } static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a57"; - cpu_pmu->map_event = armv8_a57_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57", + armv8_a57_map_event, NULL, NULL); +} - return 0; +static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65", + armv8_pmuv3_map_event, NULL, NULL); } static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a72"; - cpu_pmu->map_event = armv8_a57_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; - - return 0; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72", + armv8_a57_map_event, NULL, NULL); } static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; - - cpu_pmu->name = "armv8_cortex_a73"; - cpu_pmu->map_event = armv8_a73_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73", + armv8_a73_map_event, NULL, NULL); +} - return 0; +static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75", + armv8_pmuv3_map_event, NULL, NULL); } -static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) +static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76", + armv8_pmuv3_map_event, NULL, NULL); +} - cpu_pmu->name = "armv8_cavium_thunder"; - cpu_pmu->map_event = armv8_thunder_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; +static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77", + armv8_pmuv3_map_event, NULL, NULL); +} - return 0; +static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1", + armv8_pmuv3_map_event, NULL, NULL); } -static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) +static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu) { - int ret = armv8_pmu_init(cpu_pmu); - if (ret) - return ret; + return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1", + armv8_pmuv3_map_event, NULL, NULL); +} - cpu_pmu->name = "armv8_brcm_vulcan"; - cpu_pmu->map_event = armv8_vulcan_map_event; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = - &armv8_pmuv3_events_attr_group; - cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = - &armv8_pmuv3_format_attr_group; +static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder", + armv8_thunder_map_event, NULL, NULL); +} - return 0; +static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu) +{ + return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan", + armv8_vulcan_map_event, NULL, NULL); } static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init}, + {.compatible = "arm,cortex-a34-pmu", .data = armv8_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_a55_pmu_init}, {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init}, + {.compatible = "arm,cortex-a65-pmu", .data = armv8_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_a75_pmu_init}, + {.compatible = "arm,cortex-a76-pmu", .data = armv8_a76_pmu_init}, + {.compatible = "arm,cortex-a77-pmu", .data = armv8_a77_pmu_init}, + {.compatible = "arm,neoverse-e1-pmu", .data = armv8_e1_pmu_init}, + {.compatible = "arm,neoverse-n1-pmu", .data = armv8_n1_pmu_init}, {.compatible = "cavium,thunder-pmu", .data = armv8_thunder_pmu_init}, {.compatible = "brcm,vulcan-pmu", .data = armv8_vulcan_pmu_init}, {}, diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c index c507b584259d..1e77736a4f66 100644 --- a/arch/arm64/kernel/pointer_auth.c +++ b/arch/arm64/kernel/pointer_auth.c @@ -9,7 +9,7 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) { - struct ptrauth_keys *keys = &tsk->thread.keys_user; + struct ptrauth_keys_user *keys = &tsk->thread.keys_user; unsigned long addr_key_mask = PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY; unsigned long key_mask = addr_key_mask | PR_PAC_APGAKEY; @@ -18,8 +18,7 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) return -EINVAL; if (!arg) { - ptrauth_keys_init(keys); - ptrauth_keys_switch(keys); + ptrauth_keys_init_user(keys); return 0; } @@ -41,7 +40,5 @@ int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) if (arg & PR_PAC_APGAKEY) get_random_bytes(&keys->apga, sizeof(keys->apga)); - ptrauth_keys_switch(keys); - return 0; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 3e5a6ad66cbe..56be4cbf771f 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -262,7 +262,7 @@ void __show_regs(struct pt_regs *regs) if (!user_mode(regs)) { printk("pc : %pS\n", (void *)regs->pc); - printk("lr : %pS\n", (void *)lr); + printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr)); } else { printk("pc : %016llx\n", regs->pc); printk("lr : %016llx\n", lr); @@ -376,6 +376,8 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start, */ fpsimd_flush_task_state(p); + ptrauth_thread_init_kernel(p); + if (likely(!(p->flags & PF_KTHREAD))) { *childregs = *current_pt_regs(); childregs->regs[0] = 0; @@ -512,7 +514,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, contextidr_thread_switch(next); entry_task_switch(next); uao_thread_switch(next); - ptrauth_thread_switch(next); ssbs_thread_switch(next); /* diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index cd6e5fa48b9c..b3d3005d9515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -999,7 +999,7 @@ static struct ptrauth_key pac_key_from_user(__uint128_t ukey) } static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, - const struct ptrauth_keys *keys) + const struct ptrauth_keys_user *keys) { ukeys->apiakey = pac_key_to_user(&keys->apia); ukeys->apibkey = pac_key_to_user(&keys->apib); @@ -1007,7 +1007,7 @@ static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, ukeys->apdbkey = pac_key_to_user(&keys->apdb); } -static void pac_address_keys_from_user(struct ptrauth_keys *keys, +static void pac_address_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_address_keys *ukeys) { keys->apia = pac_key_from_user(ukeys->apiakey); @@ -1021,7 +1021,7 @@ static int pac_address_keys_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; if (!system_supports_address_auth()) @@ -1038,7 +1038,7 @@ static int pac_address_keys_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; int ret; @@ -1056,12 +1056,12 @@ static int pac_address_keys_set(struct task_struct *target, } static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, - const struct ptrauth_keys *keys) + const struct ptrauth_keys_user *keys) { ukeys->apgakey = pac_key_to_user(&keys->apga); } -static void pac_generic_keys_from_user(struct ptrauth_keys *keys, +static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_generic_keys *ukeys) { keys->apga = pac_key_from_user(ukeys->apgakey); @@ -1072,7 +1072,7 @@ static int pac_generic_keys_get(struct task_struct *target, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; if (!system_supports_generic_auth()) @@ -1089,7 +1089,7 @@ static int pac_generic_keys_set(struct task_struct *target, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { - struct ptrauth_keys *keys = &target->thread.keys_user; + struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; int ret; diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index c1d7db71a726..c40ce496c78b 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -41,7 +41,7 @@ ENTRY(arm64_relocate_new_kernel) cmp x0, #CurrentEL_EL2 b.ne 1f mrs x0, sctlr_el2 - ldr x1, =SCTLR_ELx_FLAGS + mov_q x1, SCTLR_ELx_FLAGS bic x0, x0, x1 pre_disable_mmu_workaround msr sctlr_el2, x0 @@ -113,8 +113,6 @@ ENTRY(arm64_relocate_new_kernel) ENDPROC(arm64_relocate_new_kernel) -.ltorg - .align 3 /* To keep the 64-bit values below naturally aligned. */ .Lcopy_end: diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index a34890bf309f..3fd2c11c09fc 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -344,7 +344,7 @@ void __init setup_arch(char **cmdline_p) else psci_acpi_init(); - cpu_read_bootcpu_ops(); + init_bootcpu_ops(); smp_init_cpus(); smp_build_mpidr_hash(); @@ -371,8 +371,10 @@ void __init setup_arch(char **cmdline_p) static inline bool cpu_can_disable(unsigned int cpu) { #ifdef CONFIG_HOTPLUG_CPU - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_can_disable) - return cpu_ops[cpu]->cpu_can_disable(cpu); + const struct cpu_operations *ops = get_cpu_ops(cpu); + + if (ops && ops->cpu_can_disable) + return ops->cpu_can_disable(cpu); #endif return false; } diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index f5b04dd8a710..7b2f2e650c44 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/assembler.h> +#include <asm/smp.h> .text /* @@ -99,6 +100,7 @@ ENDPROC(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly + mov x0, #ARM64_CPU_RUNTIME bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ adrp x1, swapper_pg_dir diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 5407bf5d98ac..061f60fe452f 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -93,8 +93,10 @@ static inline int op_cpu_kill(unsigned int cpu) */ static int boot_secondary(unsigned int cpu, struct task_struct *idle) { - if (cpu_ops[cpu]->cpu_boot) - return cpu_ops[cpu]->cpu_boot(cpu); + const struct cpu_operations *ops = get_cpu_ops(cpu); + + if (ops->cpu_boot) + return ops->cpu_boot(cpu); return -EOPNOTSUPP; } @@ -112,63 +114,66 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) */ secondary_data.task = idle; secondary_data.stack = task_stack_page(idle) + THREAD_SIZE; +#if defined(CONFIG_ARM64_PTR_AUTH) + secondary_data.ptrauth_key.apia.lo = idle->thread.keys_kernel.apia.lo; + secondary_data.ptrauth_key.apia.hi = idle->thread.keys_kernel.apia.hi; +#endif update_cpu_boot_status(CPU_MMU_OFF); __flush_dcache_area(&secondary_data, sizeof(secondary_data)); - /* - * Now bring the CPU into our world. - */ + /* Now bring the CPU into our world */ ret = boot_secondary(cpu, idle); - if (ret == 0) { - /* - * CPU was successfully started, wait for it to come online or - * time out. - */ - wait_for_completion_timeout(&cpu_running, - msecs_to_jiffies(5000)); - - if (!cpu_online(cpu)) { - pr_crit("CPU%u: failed to come online\n", cpu); - ret = -EIO; - } - } else { + if (ret) { pr_err("CPU%u: failed to boot: %d\n", cpu, ret); return ret; } + /* + * CPU was successfully started, wait for it to come online or + * time out. + */ + wait_for_completion_timeout(&cpu_running, + msecs_to_jiffies(5000)); + if (cpu_online(cpu)) + return 0; + + pr_crit("CPU%u: failed to come online\n", cpu); secondary_data.task = NULL; secondary_data.stack = NULL; +#if defined(CONFIG_ARM64_PTR_AUTH) + secondary_data.ptrauth_key.apia.lo = 0; + secondary_data.ptrauth_key.apia.hi = 0; +#endif __flush_dcache_area(&secondary_data, sizeof(secondary_data)); status = READ_ONCE(secondary_data.status); - if (ret && status) { - - if (status == CPU_MMU_OFF) - status = READ_ONCE(__early_cpu_boot_status); + if (status == CPU_MMU_OFF) + status = READ_ONCE(__early_cpu_boot_status); - switch (status & CPU_BOOT_STATUS_MASK) { - default: - pr_err("CPU%u: failed in unknown state : 0x%lx\n", - cpu, status); - cpus_stuck_in_kernel++; - break; - case CPU_KILL_ME: - if (!op_cpu_kill(cpu)) { - pr_crit("CPU%u: died during early boot\n", cpu); - break; - } - pr_crit("CPU%u: may not have shut down cleanly\n", cpu); - /* Fall through */ - case CPU_STUCK_IN_KERNEL: - pr_crit("CPU%u: is stuck in kernel\n", cpu); - if (status & CPU_STUCK_REASON_52_BIT_VA) - pr_crit("CPU%u: does not support 52-bit VAs\n", cpu); - if (status & CPU_STUCK_REASON_NO_GRAN) - pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K); - cpus_stuck_in_kernel++; + switch (status & CPU_BOOT_STATUS_MASK) { + default: + pr_err("CPU%u: failed in unknown state : 0x%lx\n", + cpu, status); + cpus_stuck_in_kernel++; + break; + case CPU_KILL_ME: + if (!op_cpu_kill(cpu)) { + pr_crit("CPU%u: died during early boot\n", cpu); break; - case CPU_PANIC_KERNEL: - panic("CPU%u detected unsupported configuration\n", cpu); } + pr_crit("CPU%u: may not have shut down cleanly\n", cpu); + /* Fall through */ + case CPU_STUCK_IN_KERNEL: + pr_crit("CPU%u: is stuck in kernel\n", cpu); + if (status & CPU_STUCK_REASON_52_BIT_VA) + pr_crit("CPU%u: does not support 52-bit VAs\n", cpu); + if (status & CPU_STUCK_REASON_NO_GRAN) { + pr_crit("CPU%u: does not support %luK granule\n", + cpu, PAGE_SIZE / SZ_1K); + } + cpus_stuck_in_kernel++; + break; + case CPU_PANIC_KERNEL: + panic("CPU%u detected unsupported configuration\n", cpu); } return ret; @@ -196,6 +201,7 @@ asmlinkage notrace void secondary_start_kernel(void) { u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; struct mm_struct *mm = &init_mm; + const struct cpu_operations *ops; unsigned int cpu; cpu = task_cpu(current); @@ -227,8 +233,9 @@ asmlinkage notrace void secondary_start_kernel(void) */ check_local_cpu_capabilities(); - if (cpu_ops[cpu]->cpu_postboot) - cpu_ops[cpu]->cpu_postboot(); + ops = get_cpu_ops(cpu); + if (ops->cpu_postboot) + ops->cpu_postboot(); /* * Log the CPU info before it is marked online and might get read. @@ -266,19 +273,21 @@ asmlinkage notrace void secondary_start_kernel(void) #ifdef CONFIG_HOTPLUG_CPU static int op_cpu_disable(unsigned int cpu) { + const struct cpu_operations *ops = get_cpu_ops(cpu); + /* * If we don't have a cpu_die method, abort before we reach the point * of no return. CPU0 may not have an cpu_ops, so test for it. */ - if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die) + if (!ops || !ops->cpu_die) return -EOPNOTSUPP; /* * We may need to abort a hot unplug for some other mechanism-specific * reason. */ - if (cpu_ops[cpu]->cpu_disable) - return cpu_ops[cpu]->cpu_disable(cpu); + if (ops->cpu_disable) + return ops->cpu_disable(cpu); return 0; } @@ -314,15 +323,17 @@ int __cpu_disable(void) static int op_cpu_kill(unsigned int cpu) { + const struct cpu_operations *ops = get_cpu_ops(cpu); + /* * If we have no means of synchronising with the dying CPU, then assume * that it is really dead. We can only wait for an arbitrary length of * time and hope that it's dead, so let's skip the wait and just hope. */ - if (!cpu_ops[cpu]->cpu_kill) + if (!ops->cpu_kill) return 0; - return cpu_ops[cpu]->cpu_kill(cpu); + return ops->cpu_kill(cpu); } /* @@ -357,6 +368,7 @@ void __cpu_die(unsigned int cpu) void cpu_die(void) { unsigned int cpu = smp_processor_id(); + const struct cpu_operations *ops = get_cpu_ops(cpu); idle_task_exit(); @@ -370,12 +382,22 @@ void cpu_die(void) * mechanism must perform all required cache maintenance to ensure that * no dirty lines are lost in the process of shutting down the CPU. */ - cpu_ops[cpu]->cpu_die(cpu); + ops->cpu_die(cpu); BUG(); } #endif +static void __cpu_try_die(int cpu) +{ +#ifdef CONFIG_HOTPLUG_CPU + const struct cpu_operations *ops = get_cpu_ops(cpu); + + if (ops && ops->cpu_die) + ops->cpu_die(cpu); +#endif +} + /* * Kill the calling secondary CPU, early in bringup before it is turned * online. @@ -389,12 +411,11 @@ void cpu_die_early(void) /* Mark this CPU absent */ set_cpu_present(cpu, 0); -#ifdef CONFIG_HOTPLUG_CPU - update_cpu_boot_status(CPU_KILL_ME); - /* Check if we can park ourselves */ - if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die) - cpu_ops[cpu]->cpu_die(cpu); -#endif + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) { + update_cpu_boot_status(CPU_KILL_ME); + __cpu_try_die(cpu); + } + update_cpu_boot_status(CPU_STUCK_IN_KERNEL); cpu_park_loop(); @@ -488,10 +509,13 @@ static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid) */ static int __init smp_cpu_setup(int cpu) { - if (cpu_read_ops(cpu)) + const struct cpu_operations *ops; + + if (init_cpu_ops(cpu)) return -ENODEV; - if (cpu_ops[cpu]->cpu_init(cpu)) + ops = get_cpu_ops(cpu); + if (ops->cpu_init(cpu)) return -ENODEV; set_cpu_possible(cpu, true); @@ -714,6 +738,7 @@ void __init smp_init_cpus(void) void __init smp_prepare_cpus(unsigned int max_cpus) { + const struct cpu_operations *ops; int err; unsigned int cpu; unsigned int this_cpu; @@ -744,10 +769,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus) if (cpu == smp_processor_id()) continue; - if (!cpu_ops[cpu]) + ops = get_cpu_ops(cpu); + if (!ops) continue; - err = cpu_ops[cpu]->cpu_prepare(cpu); + err = ops->cpu_prepare(cpu); if (err) continue; @@ -863,10 +889,8 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) local_irq_disable(); sdei_mask_local_cpu(); -#ifdef CONFIG_HOTPLUG_CPU - if (cpu_ops[cpu]->cpu_die) - cpu_ops[cpu]->cpu_die(cpu); -#endif + if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) + __cpu_try_die(cpu); /* just in case */ cpu_park_loop(); @@ -1059,8 +1083,9 @@ static bool have_cpu_die(void) { #ifdef CONFIG_HOTPLUG_CPU int any_cpu = raw_smp_processor_id(); + const struct cpu_operations *ops = get_cpu_ops(any_cpu); - if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die) + if (ops && ops->cpu_die) return true; #endif return false; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index a336cb124320..139679c745bf 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -14,6 +14,7 @@ #include <linux/stacktrace.h> #include <asm/irq.h> +#include <asm/pointer_auth.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -86,7 +87,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && - (frame->pc == (unsigned long)return_to_handler)) { + (ptrauth_strip_insn_pac(frame->pc) == (unsigned long)return_to_handler)) { struct ftrace_ret_stack *ret_stack; /* * This is a case where function graph tracer has @@ -101,6 +102,8 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + frame->pc = ptrauth_strip_insn_pac(frame->pc); + /* * Frames created upon entry from EL0 have NULL FP and PC values, so * don't bother reporting these. Frames created by __noreturn functions diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index fa9528dfd0ce..0801a0f3c156 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -14,6 +14,7 @@ #include <linux/acpi.h> #include <linux/arch_topology.h> #include <linux/cacheinfo.h> +#include <linux/cpufreq.h> #include <linux/init.h> #include <linux/percpu.h> @@ -120,4 +121,183 @@ int __init parse_acpi_topology(void) } #endif +#ifdef CONFIG_ARM64_AMU_EXTN +#undef pr_fmt +#define pr_fmt(fmt) "AMU: " fmt + +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale); +static DEFINE_PER_CPU(u64, arch_const_cycles_prev); +static DEFINE_PER_CPU(u64, arch_core_cycles_prev); +static cpumask_var_t amu_fie_cpus; + +/* Initialize counter reference per-cpu variables for the current CPU */ +void init_cpu_freq_invariance_counters(void) +{ + this_cpu_write(arch_core_cycles_prev, + read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0)); + this_cpu_write(arch_const_cycles_prev, + read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0)); +} + +static int validate_cpu_freq_invariance_counters(int cpu) +{ + u64 max_freq_hz, ratio; + + if (!cpu_has_amu_feat(cpu)) { + pr_debug("CPU%d: counters are not supported.\n", cpu); + return -EINVAL; + } + + if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) || + !per_cpu(arch_core_cycles_prev, cpu))) { + pr_debug("CPU%d: cycle counters are not enabled.\n", cpu); + return -EINVAL; + } + + /* Convert maximum frequency from KHz to Hz and validate */ + max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000; + if (unlikely(!max_freq_hz)) { + pr_debug("CPU%d: invalid maximum frequency.\n", cpu); + return -EINVAL; + } + + /* + * Pre-compute the fixed ratio between the frequency of the constant + * counter and the maximum frequency of the CPU. + * + * const_freq + * arch_max_freq_scale = ---------------- * SCHED_CAPACITY_SCALE² + * cpuinfo_max_freq + * + * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE² + * in order to ensure a good resolution for arch_max_freq_scale for + * very low arch timer frequencies (down to the KHz range which should + * be unlikely). + */ + ratio = (u64)arch_timer_get_rate() << (2 * SCHED_CAPACITY_SHIFT); + ratio = div64_u64(ratio, max_freq_hz); + if (!ratio) { + WARN_ONCE(1, "System timer frequency too low.\n"); + return -EINVAL; + } + + per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio; + + return 0; +} + +static inline bool +enable_policy_freq_counters(int cpu, cpumask_var_t valid_cpus) +{ + struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + + if (!policy) { + pr_debug("CPU%d: No cpufreq policy found.\n", cpu); + return false; + } + + if (cpumask_subset(policy->related_cpus, valid_cpus)) + cpumask_or(amu_fie_cpus, policy->related_cpus, + amu_fie_cpus); + + cpufreq_cpu_put(policy); + + return true; +} + +static DEFINE_STATIC_KEY_FALSE(amu_fie_key); +#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key) + +static int __init init_amu_fie(void) +{ + cpumask_var_t valid_cpus; + bool have_policy = false; + int ret = 0; + int cpu; + + if (!zalloc_cpumask_var(&valid_cpus, GFP_KERNEL)) + return -ENOMEM; + + if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) { + ret = -ENOMEM; + goto free_valid_mask; + } + + for_each_present_cpu(cpu) { + if (validate_cpu_freq_invariance_counters(cpu)) + continue; + cpumask_set_cpu(cpu, valid_cpus); + have_policy |= enable_policy_freq_counters(cpu, valid_cpus); + } + + /* + * If we are not restricted by cpufreq policies, we only enable + * the use of the AMU feature for FIE if all CPUs support AMU. + * Otherwise, enable_policy_freq_counters has already enabled + * policy cpus. + */ + if (!have_policy && cpumask_equal(valid_cpus, cpu_present_mask)) + cpumask_or(amu_fie_cpus, amu_fie_cpus, valid_cpus); + + if (!cpumask_empty(amu_fie_cpus)) { + pr_info("CPUs[%*pbl]: counters will be used for FIE.", + cpumask_pr_args(amu_fie_cpus)); + static_branch_enable(&amu_fie_key); + } + +free_valid_mask: + free_cpumask_var(valid_cpus); + + return ret; +} +late_initcall_sync(init_amu_fie); + +bool arch_freq_counters_available(struct cpumask *cpus) +{ + return amu_freq_invariant() && + cpumask_subset(cpus, amu_fie_cpus); +} + +void topology_scale_freq_tick(void) +{ + u64 prev_core_cnt, prev_const_cnt; + u64 core_cnt, const_cnt, scale; + int cpu = smp_processor_id(); + + if (!amu_freq_invariant()) + return; + + if (!cpumask_test_cpu(cpu, amu_fie_cpus)) + return; + + const_cnt = read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0); + core_cnt = read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0); + prev_const_cnt = this_cpu_read(arch_const_cycles_prev); + prev_core_cnt = this_cpu_read(arch_core_cycles_prev); + + if (unlikely(core_cnt <= prev_core_cnt || + const_cnt <= prev_const_cnt)) + goto store_and_exit; + + /* + * /\core arch_max_freq_scale + * scale = ------- * -------------------- + * /\const SCHED_CAPACITY_SCALE + * + * See validate_cpu_freq_invariance_counters() for details on + * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. + */ + scale = core_cnt - prev_core_cnt; + scale *= this_cpu_read(arch_max_freq_scale); + scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, + const_cnt - prev_const_cnt); + + scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); + this_cpu_write(freq_scale, (unsigned long)scale); + +store_and_exit: + this_cpu_write(arch_core_cycles_prev, core_cnt); + this_cpu_write(arch_const_cycles_prev, const_cnt); +} +#endif /* CONFIG_ARM64_AMU_EXTN */ diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S index 0723aa398d6e..12324863d5c2 100644 --- a/arch/arm64/kernel/vdso/sigreturn.S +++ b/arch/arm64/kernel/vdso/sigreturn.S @@ -14,7 +14,7 @@ .text nop -ENTRY(__kernel_rt_sigreturn) +SYM_FUNC_START(__kernel_rt_sigreturn) .cfi_startproc .cfi_signal_frame .cfi_def_cfa x29, 0 @@ -23,4 +23,4 @@ ENTRY(__kernel_rt_sigreturn) mov x8, #__NR_rt_sigreturn svc #0 .cfi_endproc -ENDPROC(__kernel_rt_sigreturn) +SYM_FUNC_END(__kernel_rt_sigreturn) diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S index 1a81277c2d09..620524969696 100644 --- a/arch/arm64/kernel/vdso32/sigreturn.S +++ b/arch/arm64/kernel/vdso32/sigreturn.S @@ -10,13 +10,6 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> -#define ARM_ENTRY(name) \ - ENTRY(name) - -#define ARM_ENDPROC(name) \ - .type name, %function; \ - END(name) - .text .arm @@ -24,39 +17,39 @@ .save {r0-r15} .pad #COMPAT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_sigreturn_arm) +SYM_FUNC_START(__kernel_sigreturn_arm) mov r7, #__NR_compat_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_sigreturn_arm) +SYM_FUNC_END(__kernel_sigreturn_arm) .fnstart .save {r0-r15} .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_rt_sigreturn_arm) +SYM_FUNC_START(__kernel_rt_sigreturn_arm) mov r7, #__NR_compat_rt_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_rt_sigreturn_arm) +SYM_FUNC_END(__kernel_rt_sigreturn_arm) .thumb .fnstart .save {r0-r15} .pad #COMPAT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_sigreturn_thumb) +SYM_FUNC_START(__kernel_sigreturn_thumb) mov r7, #__NR_compat_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_sigreturn_thumb) +SYM_FUNC_END(__kernel_sigreturn_thumb) .fnstart .save {r0-r15} .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET nop -ARM_ENTRY(__kernel_rt_sigreturn_thumb) +SYM_FUNC_START(__kernel_rt_sigreturn_thumb) mov r7, #__NR_compat_rt_sigreturn svc #0 .fnend -ARM_ENDPROC(__kernel_rt_sigreturn_thumb) +SYM_FUNC_END(__kernel_rt_sigreturn_thumb) |