diff options
Diffstat (limited to 'arch/arm64/kernel')
56 files changed, 1629 insertions, 1186 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 9e7dcb2c31c7..478491f07b4f 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -28,7 +28,10 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE $(call if_changed,objcopy) obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ - sigreturn32.o sys_compat.o + sys_compat.o +ifneq ($(CONFIG_COMPAT_VDSO), y) +obj-$(CONFIG_COMPAT) += sigreturn32.o +endif obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o @@ -62,6 +65,7 @@ obj-$(CONFIG_ARM64_SSBD) += ssbd.o obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-y += vdso/ probes/ +obj-$(CONFIG_COMPAT_VDSO) += vdso32/ head-y := head.o extra-y += $(head-y) vmlinux.lds diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 2804330c95dc..3a58e9db5cfe 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -152,10 +152,14 @@ static int __init acpi_fadt_sanity_check(void) */ if (table->revision < 5 || (table->revision == 5 && fadt->minor_revision < 1)) { - pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n", + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n", table->revision, fadt->minor_revision); - ret = -EINVAL; - goto out; + + if (!fadt->arm_boot_flags) { + ret = -EINVAL; + goto out; + } + pr_err("FADT has ARM boot flags set, assuming 5.1\n"); } if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 02f08768c298..214685760e1c 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -18,9 +18,9 @@ #include <asm/fixmap.h> #include <asm/thread_info.h> #include <asm/memory.h> +#include <asm/signal32.h> #include <asm/smp_plat.h> #include <asm/suspend.h> -#include <asm/vdso_datapage.h> #include <linux/kbuild.h> #include <linux/arm-smccc.h> @@ -66,6 +66,11 @@ int main(void) DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); BLANK(); +#ifdef CONFIG_COMPAT + DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); + DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0)); + BLANK(); +#endif DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); BLANK(); DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm)); @@ -80,33 +85,6 @@ int main(void) BLANK(); DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET); BLANK(); - DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); - DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); - DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW); - DEFINE(CLOCK_REALTIME_RES, offsetof(struct vdso_data, hrtimer_res)); - DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); - DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE); - DEFINE(CLOCK_COARSE_RES, LOW_RES_NSEC); - DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); - BLANK(); - DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last)); - DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec)); - DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec)); - DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec)); - DEFINE(VDSO_XTIME_CRS_NSEC, offsetof(struct vdso_data, xtime_coarse_nsec)); - DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec)); - DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count)); - DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult)); - DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift)); - DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest)); - DEFINE(VDSO_USE_SYSCALL, offsetof(struct vdso_data, use_syscall)); - BLANK(); - DEFINE(TVAL_TV_SEC, offsetof(struct timeval, tv_sec)); - DEFINE(TSPEC_TV_SEC, offsetof(struct timespec, tv_sec)); - BLANK(); - DEFINE(TZ_MINWEST, offsetof(struct timezone, tz_minuteswest)); - DEFINE(TZ_DSTTIME, offsetof(struct timezone, tz_dsttime)); - BLANK(); DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack)); DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task)); BLANK(); diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index 880d79904d36..7fa6828bb488 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -17,6 +17,15 @@ #define CLIDR_CTYPE(clidr, level) \ (((clidr) & CLIDR_CTYPE_MASK(level)) >> CLIDR_CTYPE_SHIFT(level)) +int cache_line_size(void) +{ + if (coherency_max_size != 0) + return coherency_max_size; + + return cache_line_size_of_cpu(); +} +EXPORT_SYMBOL_GPL(cache_line_size); + static inline enum cache_type get_cache_type(int level) { u64 clidr; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ca11ff7bf55e..1e43ba5c79b7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -554,6 +554,17 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) static bool __hardenbp_enab = true; static bool __spectrev2_safe = true; +int get_spectre_v2_workaround_state(void) +{ + if (__spectrev2_safe) + return ARM64_BP_HARDEN_NOT_REQUIRED; + + if (!__hardenbp_enab) + return ARM64_BP_HARDEN_UNKNOWN; + + return ARM64_BP_HARDEN_WA_NEEDED; +} + /* * List of CPUs that do not need any Spectre-v2 mitigation at all. */ @@ -854,13 +865,15 @@ ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { - if (__spectrev2_safe) + switch (get_spectre_v2_workaround_state()) { + case ARM64_BP_HARDEN_NOT_REQUIRED: return sprintf(buf, "Not affected\n"); - - if (__hardenbp_enab) + case ARM64_BP_HARDEN_WA_NEEDED: return sprintf(buf, "Mitigation: Branch predictor hardening\n"); - - return sprintf(buf, "Vulnerable\n"); + case ARM64_BP_HARDEN_UNKNOWN: + default: + return sprintf(buf, "Vulnerable\n"); + } } ssize_t cpu_show_spec_store_bypass(struct device *dev, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index aabdabf52fdb..9323bcc40a58 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -184,9 +184,17 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + /* + * We already refuse to boot CPUs that don't support our configured + * page size, so we can only detect mismatches for a page size other + * than the one we're currently using. Unfortunately, SoCs like this + * exist in the wild so, even though we don't like it, we'll have to go + * along with it and treat them as non-strict. + */ + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), /* Linux shouldn't care about secure memory */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), @@ -225,8 +233,8 @@ 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_DIC_SHIFT, 1, 1), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_CWG_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_OR_ZERO_SAFE, CTR_ERG_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1), /* * Linux can handle differing I-cache policies. Userspace JITs will @@ -468,6 +476,10 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, case FTR_LOWER_SAFE: ret = new < cur ? new : cur; break; + case FTR_HIGHER_OR_ZERO_SAFE: + if (!cur || !new) + break; + /* Fallthrough */ case FTR_HIGHER_SAFE: ret = new > cur ? new : cur; break; @@ -882,7 +894,7 @@ static bool has_no_hw_prefetch(const struct arm64_cpu_capabilities *entry, int _ u32 midr = read_cpuid_id(); /* Cavium ThunderX pass 1.x and 2.x */ - return MIDR_IS_CPU_MODEL_RANGE(midr, MIDR_THUNDERX, + return midr_is_cpu_model_range(midr, MIDR_THUNDERX, MIDR_CPU_VAR_REV(0, 0), MIDR_CPU_VAR_REV(1, MIDR_REVISION_MASK)); } @@ -1184,14 +1196,14 @@ static struct undef_hook ssbs_emulation_hook = { static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused) { static bool undef_hook_registered = false; - static DEFINE_SPINLOCK(hook_lock); + static DEFINE_RAW_SPINLOCK(hook_lock); - spin_lock(&hook_lock); + raw_spin_lock(&hook_lock); if (!undef_hook_registered) { register_undef_hook(&ssbs_emulation_hook); undef_hook_registered = true; } - spin_unlock(&hook_lock); + raw_spin_unlock(&hook_lock); if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) { sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS); @@ -1618,6 +1630,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -1629,6 +1642,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB), HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index d1048173fd8a..e4d6af2fdec7 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -11,6 +11,7 @@ #include <linux/cpu_pm.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/psci.h> #include <asm/cpuidle.h> #include <asm/cpu_ops.h> @@ -46,17 +47,58 @@ int arm_cpuidle_suspend(int index) #define ARM64_LPI_IS_RETENTION_STATE(arch_flags) (!(arch_flags)) +static int psci_acpi_cpu_init_idle(unsigned int cpu) +{ + int i, count; + struct acpi_lpi_state *lpi; + struct acpi_processor *pr = per_cpu(processors, cpu); + + /* + * If the PSCI cpu_suspend function hook has not been initialized + * idle states must not be enabled, so bail out + */ + if (!psci_ops.cpu_suspend) + return -EOPNOTSUPP; + + if (unlikely(!pr || !pr->flags.has_lpi)) + return -EINVAL; + + count = pr->power.count - 1; + if (count <= 0) + return -ENODEV; + + for (i = 0; i < count; i++) { + u32 state; + + lpi = &pr->power.lpi_states[i + 1]; + /* + * Only bits[31:0] represent a PSCI power_state while + * bits[63:32] must be 0x0 as per ARM ACPI FFH Specification + */ + state = lpi->address; + if (!psci_power_state_is_valid(state)) { + pr_warn("Invalid PSCI power state %#x\n", state); + return -EINVAL; + } + } + + return 0; +} + int acpi_processor_ffh_lpi_probe(unsigned int cpu) { - return arm_cpuidle_init(cpu); + return psci_acpi_cpu_init_idle(cpu); } int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) { + u32 state = lpi->address; + if (ARM64_LPI_IS_RETENTION_STATE(lpi->arch_flags)) - return CPU_PM_CPU_IDLE_ENTER_RETENTION(arm_cpuidle_suspend, - lpi->index); + return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(psci_cpu_suspend_enter, + lpi->index, state); else - return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index); + return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, + lpi->index, state); } #endif diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 0593665fc7b4..05933c065732 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -33,7 +33,7 @@ DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data); static struct cpuinfo_arm64 boot_cpu_data; -static char *icache_policy_str[] = { +static const char *icache_policy_str[] = { [0 ... ICACHE_POLICY_PIPT] = "RESERVED/UNKNOWN", [ICACHE_POLICY_VIPT] = "VIPT", [ICACHE_POLICY_PIPT] = "PIPT", @@ -82,6 +82,8 @@ static const char *const hwcap_str[] = { "svebitperm", "svesha3", "svesm4", + "flagm2", + "frint", NULL }; diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index f8719bd30850..48222a4760c2 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -207,16 +207,16 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_step_hook : &kernel_step_hook; - rcu_read_lock(); - + /* + * Since single-step exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { retval = hook->fn(regs, esr); if (retval == DBG_HOOK_HANDLED) break; } - rcu_read_unlock(); - return retval; } NOKPROBE_SYMBOL(call_step_hook); @@ -305,14 +305,16 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) list = user_mode(regs) ? &user_break_hook : &kernel_break_hook; - rcu_read_lock(); + /* + * Since brk exception disables interrupt, this function is + * entirely not preemptible, and we can use rcu list safely here. + */ list_for_each_entry_rcu(hook, list, node) { unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK; if ((comment & ~hook->mask) == hook->imm) fn = hook->fn; } - rcu_read_unlock(); return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 3c33d0dd8e0e..d0cf596db82c 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -82,8 +82,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) return 0; } -static int __init set_permissions(pte_t *ptep, pgtable_t token, - unsigned long addr, void *data) +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) { efi_memory_desc_t *md = data; pte_t pte = READ_ONCE(*ptep); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2df8d0a1d980..84a822748c84 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -30,9 +30,9 @@ * Context tracking subsystem. Used to instrument transitions * between user and kernel mode. */ - .macro ct_user_exit + .macro ct_user_exit_irqoff #ifdef CONFIG_CONTEXT_TRACKING - bl context_tracking_user_exit + bl enter_from_user_mode #endif .endm @@ -247,6 +247,7 @@ alternative_else_nop_endif /* * Registers that may be useful after this macro is invoked: * + * x20 - ICC_PMR_EL1 * x21 - aborted SP * x22 - aborted PC * x23 - aborted PSTATE @@ -424,6 +425,38 @@ tsk .req x28 // current thread_info irq_stack_exit .endm +#ifdef CONFIG_ARM64_PSEUDO_NMI + /* + * Set res to 0 if irqs were unmasked in interrupted context. + * Otherwise set res to non-0 value. + */ + .macro test_irqs_unmasked res:req, pmr:req +alternative_if ARM64_HAS_IRQ_PRIO_MASKING + sub \res, \pmr, #GIC_PRIO_IRQON +alternative_else + mov \res, xzr +alternative_endif + .endm +#endif + + .macro gic_prio_kentry_setup, tmp:req +#ifdef CONFIG_ARM64_PSEUDO_NMI + alternative_if ARM64_HAS_IRQ_PRIO_MASKING + mov \tmp, #(GIC_PRIO_PSR_I_SET | GIC_PRIO_IRQON) + msr_s SYS_ICC_PMR_EL1, \tmp + alternative_else_nop_endif +#endif + .endm + + .macro gic_prio_irq_setup, pmr:req, tmp:req +#ifdef CONFIG_ARM64_PSEUDO_NMI + alternative_if ARM64_HAS_IRQ_PRIO_MASKING + orr \tmp, \pmr, #GIC_PRIO_PSR_I_SET + msr_s SYS_ICC_PMR_EL1, \tmp + alternative_else_nop_endif +#endif + .endm + .text /* @@ -553,10 +586,8 @@ el1_sync: b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef - cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el1_sp_pc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el1_sp_pc + b.eq el1_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL1 b.eq el1_undef cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 @@ -578,9 +609,11 @@ el1_da: bl do_mem_abort kernel_exit 1 -el1_sp_pc: +el1_pc: /* - * Stack or PC alignment exception handling + * PC alignment exception handling. We don't handle SP alignment faults, + * since we will have hit a recursive exception when trying to push the + * initial pt_regs. */ mrs x0, far_el1 inherit_daif pstate=x23, tmp=x2 @@ -602,6 +635,7 @@ el1_dbg: cmp x24, #ESR_ELx_EC_BRK64 // if BRK64 cinc x24, x24, eq // set bit '0' tbz x24, #0, el1_inv // EL1 only + gic_prio_kentry_setup tmp=x3 mrs x0, far_el1 mov x2, sp // struct pt_regs bl do_debug_exception @@ -619,20 +653,18 @@ ENDPROC(el1_sync) .align 6 el1_irq: kernel_entry 1 + gic_prio_irq_setup pmr=x20, tmp=x1 enable_da_f -#ifdef CONFIG_TRACE_IRQFLAGS + #ifdef CONFIG_ARM64_PSEUDO_NMI -alternative_if ARM64_HAS_IRQ_PRIO_MASKING - ldr x20, [sp, #S_PMR_SAVE] -alternative_else - mov x20, #GIC_PRIO_IRQON -alternative_endif - cmp x20, #GIC_PRIO_IRQOFF - /* Irqs were disabled, don't trace */ - b.ls 1f + test_irqs_unmasked res=x0, pmr=x20 + cbz x0, 1f + bl asm_nmi_enter +1: #endif + +#ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off -1: #endif irq_handler @@ -651,14 +683,23 @@ alternative_else_nop_endif bl preempt_schedule_irq // irq en/disable is done inside 1: #endif -#ifdef CONFIG_TRACE_IRQFLAGS + #ifdef CONFIG_ARM64_PSEUDO_NMI /* - * if IRQs were disabled when we received the interrupt, we have an NMI - * and we are not re-enabling interrupt upon eret. Skip tracing. + * When using IRQ priority masking, we can get spurious interrupts while + * PMR is set to GIC_PRIO_IRQOFF. An NMI might also have occurred in a + * section with interrupts disabled. Skip tracing in those cases. */ - cmp x20, #GIC_PRIO_IRQOFF - b.ls 1f + test_irqs_unmasked res=x0, pmr=x20 + cbz x0, 1f + bl asm_nmi_exit +1: +#endif + +#ifdef CONFIG_TRACE_IRQFLAGS +#ifdef CONFIG_ARM64_PSEUDO_NMI + test_irqs_unmasked res=x0, pmr=x20 + cbnz x0, 1f #endif bl trace_hardirqs_on 1: @@ -691,9 +732,9 @@ el0_sync: ccmp x24, #ESR_ELx_EC_WFx, #4, ne b.eq el0_sys cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception - b.eq el0_sp_pc + b.eq el0_sp cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_sp_pc + b.eq el0_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_BREAKPT_LOW // debug exception in EL0 @@ -717,7 +758,7 @@ el0_sync_compat: cmp x24, #ESR_ELx_EC_FP_EXC32 // FP/ASIMD exception b.eq el0_fpsimd_exc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception - b.eq el0_sp_pc + b.eq el0_pc cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0 b.eq el0_undef cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap @@ -751,8 +792,8 @@ el0_cp15: /* * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions */ + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, x25 mov x1, sp bl do_cp15instr @@ -764,8 +805,8 @@ el0_da: * Data abort handling */ mrs x26, far_el1 + ct_user_exit_irqoff enable_daif - ct_user_exit clear_address_tag x0, x26 mov x1, x25 mov x2, sp @@ -776,11 +817,12 @@ el0_ia: * Instruction abort handling */ mrs x26, far_el1 + gic_prio_kentry_setup tmp=x0 + ct_user_exit_irqoff enable_da_f #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif - ct_user_exit mov x0, x26 mov x1, x25 mov x2, sp @@ -790,8 +832,8 @@ el0_fpsimd_acc: /* * Floating Point or Advanced SIMD access */ + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, x25 mov x1, sp bl do_fpsimd_acc @@ -800,8 +842,8 @@ el0_sve_acc: /* * Scalable Vector Extension access */ + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, x25 mov x1, sp bl do_sve_acc @@ -810,22 +852,27 @@ el0_fpsimd_exc: /* * Floating Point, Advanced SIMD or SVE exception */ + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, x25 mov x1, sp bl do_fpsimd_exc b ret_to_user +el0_sp: + ldr x26, [sp, #S_SP] + b el0_sp_pc +el0_pc: + mrs x26, far_el1 el0_sp_pc: /* * Stack or PC alignment exception handling */ - mrs x26, far_el1 + gic_prio_kentry_setup tmp=x0 + ct_user_exit_irqoff enable_da_f #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif - ct_user_exit mov x0, x26 mov x1, x25 mov x2, sp @@ -835,8 +882,8 @@ el0_undef: /* * Undefined instruction */ + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, sp bl do_undefinstr b ret_to_user @@ -844,8 +891,8 @@ el0_sys: /* * System instructions, for trapped cache maintenance instructions */ + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, x25 mov x1, sp bl do_sysinstr @@ -855,16 +902,18 @@ el0_dbg: * Debug exception handling */ tbnz x24, #0, el0_inv // EL0 only - mrs x0, far_el1 + mrs x24, far_el1 + gic_prio_kentry_setup tmp=x3 + ct_user_exit_irqoff + mov x0, x24 mov x1, x25 mov x2, sp bl do_debug_exception - enable_daif - ct_user_exit + enable_da_f b ret_to_user el0_inv: + ct_user_exit_irqoff enable_daif - ct_user_exit mov x0, sp mov x1, #BAD_SYNC mov x2, x25 @@ -876,12 +925,14 @@ ENDPROC(el0_sync) el0_irq: kernel_entry 0 el0_irq_naked: + gic_prio_irq_setup pmr=x20, tmp=x0 + ct_user_exit_irqoff enable_da_f + #ifdef CONFIG_TRACE_IRQFLAGS bl trace_hardirqs_off #endif - ct_user_exit #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR tbz x22, #55, 1f bl do_el0_irq_bp_hardening @@ -898,6 +949,7 @@ ENDPROC(el0_irq) el1_error: kernel_entry 1 mrs x1, esr_el1 + gic_prio_kentry_setup tmp=x2 enable_dbg mov x0, sp bl do_serror @@ -907,12 +959,14 @@ ENDPROC(el1_error) el0_error: kernel_entry 0 el0_error_naked: - mrs x1, esr_el1 + mrs x25, esr_el1 + gic_prio_kentry_setup tmp=x2 + ct_user_exit_irqoff enable_dbg mov x0, sp + mov x1, x25 bl do_serror - enable_daif - ct_user_exit + enable_da_f b ret_to_user ENDPROC(el0_error) @@ -932,6 +986,7 @@ work_pending: */ ret_to_user: disable_daif + gic_prio_kentry_setup tmp=x3 ldr x1, [tsk, #TSK_TI_FLAGS] and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending @@ -948,6 +1003,7 @@ ENDPROC(ret_to_user) */ .align 6 el0_svc: + gic_prio_kentry_setup tmp=x1 mov x0, sp bl el0_svc_handler b ret_to_user diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 0cfcf5c237c5..37d3912cfe06 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -82,7 +82,8 @@ * To prevent this from racing with the manipulation of the task's FPSIMD state * from task context and thereby corrupting the state, it is necessary to * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE - * flag with local_bh_disable() unless softirqs are already masked. + * flag with {, __}get_cpu_fpsimd_context(). This will still allow softirqs to + * run but prevent them to use FPSIMD. * * For a certain task, the sequence may look something like this: * - the task gets scheduled in; if both the task's fpsimd_cpu field @@ -145,6 +146,56 @@ extern void __percpu *efi_sve_state; #endif /* ! CONFIG_ARM64_SVE */ +DEFINE_PER_CPU(bool, fpsimd_context_busy); +EXPORT_PER_CPU_SYMBOL(fpsimd_context_busy); + +static void __get_cpu_fpsimd_context(void) +{ + bool busy = __this_cpu_xchg(fpsimd_context_busy, true); + + WARN_ON(busy); +} + +/* + * Claim ownership of the CPU FPSIMD context for use by the calling context. + * + * The caller may freely manipulate the FPSIMD context metadata until + * put_cpu_fpsimd_context() is called. + * + * The double-underscore version must only be called if you know the task + * can't be preempted. + */ +static void get_cpu_fpsimd_context(void) +{ + preempt_disable(); + __get_cpu_fpsimd_context(); +} + +static void __put_cpu_fpsimd_context(void) +{ + bool busy = __this_cpu_xchg(fpsimd_context_busy, false); + + WARN_ON(!busy); /* No matching get_cpu_fpsimd_context()? */ +} + +/* + * Release the CPU FPSIMD context. + * + * Must be called from a context in which get_cpu_fpsimd_context() was + * previously called, with no call to put_cpu_fpsimd_context() in the + * meantime. + */ +static void put_cpu_fpsimd_context(void) +{ + __put_cpu_fpsimd_context(); + preempt_enable(); +} + +static bool have_cpu_fpsimd_context(void) +{ + return !preemptible() && __this_cpu_read(fpsimd_context_busy); +} + /* * Call __sve_free() directly only if you know task can't be scheduled * or preempted. @@ -215,12 +266,10 @@ static void sve_free(struct task_struct *task) * This function should be called only when the FPSIMD/SVE state in * thread_struct is known to be up to date, when preparing to enter * userspace. - * - * Softirqs (and preemption) must be disabled. */ static void task_fpsimd_load(void) { - WARN_ON(!in_softirq() && !irqs_disabled()); + WARN_ON(!have_cpu_fpsimd_context()); if (system_supports_sve() && test_thread_flag(TIF_SVE)) sve_load_state(sve_pffr(¤t->thread), @@ -233,16 +282,14 @@ static void task_fpsimd_load(void) /* * Ensure FPSIMD/SVE storage in memory for the loaded context is up to * date with respect to the CPU registers. - * - * Softirqs (and preemption) must be disabled. */ -void fpsimd_save(void) +static void fpsimd_save(void) { struct fpsimd_last_state_struct const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ - WARN_ON(!in_softirq() && !irqs_disabled()); + WARN_ON(!have_cpu_fpsimd_context()); if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { if (system_supports_sve() && test_thread_flag(TIF_SVE)) { @@ -359,12 +406,25 @@ static __uint128_t arm64_cpu_to_le128(__uint128_t x) #define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) +static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst, + unsigned int vq) +{ + unsigned int i; + __uint128_t *p; + + for (i = 0; i < SVE_NUM_ZREGS; ++i) { + p = (__uint128_t *)ZREG(sst, vq, i); + *p = arm64_cpu_to_le128(fst->vregs[i]); + } +} + /* * Transfer the FPSIMD state in task->thread.uw.fpsimd_state to * task->thread.sve_state. * * Task can be a non-runnable task, or current. In the latter case, - * softirqs (and preemption) must be disabled. + * the caller must have ownership of the cpu FPSIMD context before calling + * this function. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.uw.fpsimd_state must be up to date before calling this @@ -375,17 +435,12 @@ static void fpsimd_to_sve(struct task_struct *task) unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - unsigned int i; - __uint128_t *p; if (!system_supports_sve()) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) { - p = (__uint128_t *)ZREG(sst, vq, i); - *p = arm64_cpu_to_le128(fst->vregs[i]); - } + __fpsimd_to_sve(sst, fst, vq); } /* @@ -393,7 +448,8 @@ static void fpsimd_to_sve(struct task_struct *task) * task->thread.uw.fpsimd_state. * * Task can be a non-runnable task, or current. In the latter case, - * softirqs (and preemption) must be disabled. + * the caller must have ownership of the cpu FPSIMD context before calling + * this function. * task->thread.sve_state must point to at least sve_state_size(task) * bytes of allocated kernel memory. * task->thread.sve_state must be up to date before calling this function. @@ -410,7 +466,7 @@ static void sve_to_fpsimd(struct task_struct *task) return; vq = sve_vq_from_vl(task->thread.sve_vl); - for (i = 0; i < 32; ++i) { + for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); } @@ -501,8 +557,6 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) unsigned int vq; void *sst = task->thread.sve_state; struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state; - unsigned int i; - __uint128_t *p; if (!test_tsk_thread_flag(task, TIF_SVE)) return; @@ -510,11 +564,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) vq = sve_vq_from_vl(task->thread.sve_vl); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); - - for (i = 0; i < 32; ++i) { - p = (__uint128_t *)ZREG(sst, vq, i); - *p = arm64_cpu_to_le128(fst->vregs[i]); - } + __fpsimd_to_sve(sst, fst, vq); } int sve_set_vector_length(struct task_struct *task, @@ -557,7 +607,7 @@ int sve_set_vector_length(struct task_struct *task, * non-SVE thread. */ if (task == current) { - local_bh_disable(); + get_cpu_fpsimd_context(); fpsimd_save(); } @@ -567,7 +617,7 @@ int sve_set_vector_length(struct task_struct *task, sve_to_fpsimd(task); if (task == current) - local_bh_enable(); + put_cpu_fpsimd_context(); /* * Force reallocation of task SVE state to the correct size @@ -880,7 +930,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) sve_alloc(current); - local_bh_disable(); + get_cpu_fpsimd_context(); fpsimd_save(); @@ -891,7 +941,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) if (test_and_set_thread_flag(TIF_SVE)) WARN_ON(1); /* SVE access shouldn't have trapped */ - local_bh_enable(); + put_cpu_fpsimd_context(); } /* @@ -935,6 +985,8 @@ void fpsimd_thread_switch(struct task_struct *next) if (!system_supports_fpsimd()) return; + __get_cpu_fpsimd_context(); + /* Save unsaved fpsimd state, if any: */ fpsimd_save(); @@ -949,6 +1001,8 @@ void fpsimd_thread_switch(struct task_struct *next) update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, wrong_task || wrong_cpu); + + __put_cpu_fpsimd_context(); } void fpsimd_flush_thread(void) @@ -958,7 +1012,7 @@ void fpsimd_flush_thread(void) if (!system_supports_fpsimd()) return; - local_bh_disable(); + get_cpu_fpsimd_context(); fpsimd_flush_task_state(current); memset(¤t->thread.uw.fpsimd_state, 0, @@ -999,7 +1053,7 @@ void fpsimd_flush_thread(void) current->thread.sve_vl_onexec = 0; } - local_bh_enable(); + put_cpu_fpsimd_context(); } /* @@ -1011,9 +1065,9 @@ void fpsimd_preserve_current_state(void) if (!system_supports_fpsimd()) return; - local_bh_disable(); + get_cpu_fpsimd_context(); fpsimd_save(); - local_bh_enable(); + put_cpu_fpsimd_context(); } /* @@ -1030,7 +1084,8 @@ void fpsimd_signal_preserve_current_state(void) /* * Associate current's FPSIMD context with this cpu - * Preemption must be disabled when calling this function. + * The caller must have ownership of the cpu FPSIMD context before calling + * this function. */ void fpsimd_bind_task_to_cpu(void) { @@ -1076,14 +1131,14 @@ void fpsimd_restore_current_state(void) if (!system_supports_fpsimd()) return; - local_bh_disable(); + get_cpu_fpsimd_context(); if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { task_fpsimd_load(); fpsimd_bind_task_to_cpu(); } - local_bh_enable(); + put_cpu_fpsimd_context(); } /* @@ -1096,7 +1151,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) if (!system_supports_fpsimd()) return; - local_bh_disable(); + get_cpu_fpsimd_context(); current->thread.uw.fpsimd_state = *state; if (system_supports_sve() && test_thread_flag(TIF_SVE)) @@ -1107,7 +1162,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) clear_thread_flag(TIF_FOREIGN_FPSTATE); - local_bh_enable(); + put_cpu_fpsimd_context(); } /* @@ -1133,18 +1188,29 @@ void fpsimd_flush_task_state(struct task_struct *t) /* * Invalidate any task's FPSIMD state that is present on this cpu. - * This function must be called with softirqs disabled. + * The FPSIMD context should be acquired with get_cpu_fpsimd_context() + * before calling this function. */ -void fpsimd_flush_cpu_state(void) +static void fpsimd_flush_cpu_state(void) { __this_cpu_write(fpsimd_last_state.st, NULL); set_thread_flag(TIF_FOREIGN_FPSTATE); } -#ifdef CONFIG_KERNEL_MODE_NEON +/* + * Save the FPSIMD state to memory and invalidate cpu view. + * This function must be called with preemption disabled. + */ +void fpsimd_save_and_flush_cpu_state(void) +{ + WARN_ON(preemptible()); + __get_cpu_fpsimd_context(); + fpsimd_save(); + fpsimd_flush_cpu_state(); + __put_cpu_fpsimd_context(); +} -DEFINE_PER_CPU(bool, kernel_neon_busy); -EXPORT_PER_CPU_SYMBOL(kernel_neon_busy); +#ifdef CONFIG_KERNEL_MODE_NEON /* * Kernel-side NEON support functions @@ -1170,19 +1236,13 @@ void kernel_neon_begin(void) BUG_ON(!may_use_simd()); - local_bh_disable(); - - __this_cpu_write(kernel_neon_busy, true); + get_cpu_fpsimd_context(); /* Save unsaved fpsimd state, if any: */ fpsimd_save(); /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); - - preempt_disable(); - - local_bh_enable(); } EXPORT_SYMBOL(kernel_neon_begin); @@ -1197,15 +1257,10 @@ EXPORT_SYMBOL(kernel_neon_begin); */ void kernel_neon_end(void) { - bool busy; - if (!system_supports_fpsimd()) return; - busy = __this_cpu_xchg(kernel_neon_busy, false); - WARN_ON(!busy); /* No matching kernel_neon_begin()? */ - - preempt_enable(); + put_cpu_fpsimd_context(); } EXPORT_SYMBOL(kernel_neon_end); @@ -1297,8 +1352,7 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self, { switch (cmd) { case CPU_PM_ENTER: - fpsimd_save(); - fpsimd_flush_cpu_state(); + fpsimd_save_and_flush_cpu_state(); break; case CPU_PM_EXIT: break; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 1285c7b2947f..171773257974 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -73,7 +73,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (offset < -SZ_128M || offset >= SZ_128M) { #ifdef CONFIG_ARM64_MODULE_PLTS - struct plt_entry trampoline; + struct plt_entry trampoline, *dst; struct module *mod; /* @@ -106,23 +106,27 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * to check if the actual opcodes are in fact identical, * regardless of the offset in memory so use memcmp() instead. */ - trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline); - if (memcmp(mod->arch.ftrace_trampoline, &trampoline, - sizeof(trampoline))) { - if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) { + dst = mod->arch.ftrace_trampoline; + trampoline = get_plt_entry(addr, dst); + if (memcmp(dst, &trampoline, sizeof(trampoline))) { + if (plt_entry_is_initialized(dst)) { pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n"); return -EINVAL; } /* point the trampoline to our ftrace entry point */ module_disable_ro(mod); - *mod->arch.ftrace_trampoline = trampoline; + *dst = trampoline; module_enable_ro(mod, true); - /* update trampoline before patching in the branch */ - smp_wmb(); + /* + * Ensure updated trampoline is visible to instruction + * fetch before we patch in the branch. + */ + __flush_icache_range((unsigned long)&dst[0], + (unsigned long)&dst[1]); } - addr = (unsigned long)(void *)mod->arch.ftrace_trampoline; + addr = (unsigned long)dst; #else /* CONFIG_ARM64_MODULE_PLTS */ return -EINVAL; #endif /* CONFIG_ARM64_MODULE_PLTS */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 2cdacd1c141b..989b1944cb71 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -102,6 +102,8 @@ pe_header: * x23 stext() .. start_kernel() physical misalignment/KASLR offset * x28 __create_page_tables() callee preserved temp register * x19/x20 __primary_switch() callee preserved temp registers + * x24 __primary_switch() .. relocate_kernel() + * current RELR displacement */ ENTRY(stext) bl preserve_boot_args @@ -308,15 +310,15 @@ __create_page_tables: adrp x0, idmap_pg_dir adrp x3, __idmap_text_start // __pa(__idmap_text_start) -#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#ifdef CONFIG_ARM64_VA_BITS_52 mrs_s x6, SYS_ID_AA64MMFR2_EL1 and x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT) mov x5, #52 cbnz x6, 1f #endif - mov x5, #VA_BITS + mov x5, #VA_BITS_MIN 1: - adr_l x6, vabits_user + adr_l x6, vabits_actual str x5, [x6] dmb sy dc ivac, x6 // Invalidate potentially stale cache line @@ -724,14 +726,22 @@ __secondary_switched: adr_l x0, secondary_data ldr x1, [x0, #CPU_BOOT_STACK] // get secondary_data.stack + cbz x1, __secondary_too_slow mov sp, x1 ldr x2, [x0, #CPU_BOOT_TASK] + cbz x2, __secondary_too_slow msr sp_el0, x2 mov x29, #0 mov x30, #0 b secondary_start_kernel ENDPROC(__secondary_switched) +__secondary_too_slow: + wfe + wfi + b __secondary_too_slow +ENDPROC(__secondary_too_slow) + /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. @@ -772,7 +782,7 @@ ENTRY(__enable_mmu) phys_to_ttbr x1, x1 phys_to_ttbr x2, x2 msr ttbr0_el1, x2 // load TTBR0 - offset_ttbr1 x1 + offset_ttbr1 x1, x3 msr ttbr1_el1, x1 // load TTBR1 isb msr sctlr_el1, x0 @@ -789,8 +799,8 @@ ENTRY(__enable_mmu) ENDPROC(__enable_mmu) ENTRY(__cpu_secondary_check52bitva) -#ifdef CONFIG_ARM64_USER_VA_BITS_52 - ldr_l x0, vabits_user +#ifdef CONFIG_ARM64_VA_BITS_52 + ldr_l x0, vabits_actual cmp x0, #52 b.ne 2f @@ -834,14 +844,93 @@ __relocate_kernel: 0: cmp x9, x10 b.hs 1f - ldp x11, x12, [x9], #24 - ldr x13, [x9, #-8] - cmp w12, #R_AARCH64_RELATIVE + ldp x12, x13, [x9], #24 + ldr x14, [x9, #-8] + cmp w13, #R_AARCH64_RELATIVE b.ne 0b - add x13, x13, x23 // relocate - str x13, [x11, x23] + add x14, x14, x23 // relocate + str x14, [x12, x23] b 0b -1: ret + +1: +#ifdef CONFIG_RELR + /* + * Apply RELR relocations. + * + * RELR is a compressed format for storing relative relocations. The + * encoded sequence of entries looks like: + * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] + * + * i.e. start with an address, followed by any number of bitmaps. The + * address entry encodes 1 relocation. The subsequent bitmap entries + * encode up to 63 relocations each, at subsequent offsets following + * the last address entry. + * + * The bitmap entries must have 1 in the least significant bit. The + * assumption here is that an address cannot have 1 in lsb. Odd + * addresses are not supported. Any odd addresses are stored in the RELA + * section, which is handled above. + * + * Excluding the least significant bit in the bitmap, each non-zero + * bit in the bitmap represents a relocation to be applied to + * a corresponding machine word that follows the base address + * word. The second least significant bit represents the machine + * word immediately following the initial address, and each bit + * that follows represents the next word, in linear order. As such, + * a single bitmap can encode up to 63 relocations in a 64-bit object. + * + * In this implementation we store the address of the next RELR table + * entry in x9, the address being relocated by the current address or + * bitmap entry in x13 and the address being relocated by the current + * bit in x14. + * + * Because addends are stored in place in the binary, RELR relocations + * cannot be applied idempotently. We use x24 to keep track of the + * currently applied displacement so that we can correctly relocate if + * __relocate_kernel is called twice with non-zero displacements (i.e. + * if there is both a physical misalignment and a KASLR displacement). + */ + ldr w9, =__relr_offset // offset to reloc table + ldr w10, =__relr_size // size of reloc table + add x9, x9, x11 // __va(.relr) + add x10, x9, x10 // __va(.relr) + sizeof(.relr) + + sub x15, x23, x24 // delta from previous offset + cbz x15, 7f // nothing to do if unchanged + mov x24, x23 // save new offset + +2: cmp x9, x10 + b.hs 7f + ldr x11, [x9], #8 + tbnz x11, #0, 3f // branch to handle bitmaps + add x13, x11, x23 + ldr x12, [x13] // relocate address entry + add x12, x12, x15 + str x12, [x13], #8 // adjust to start of bitmap + b 2b + +3: mov x14, x13 +4: lsr x11, x11, #1 + cbz x11, 6f + tbz x11, #0, 5f // skip bit if not set + ldr x12, [x14] // relocate bit + add x12, x12, x15 + str x12, [x14] + +5: add x14, x14, #8 // move to next bit's address + b 4b + +6: /* + * Move to the next bitmap's address. 8 is the word size, and 63 is the + * number of significant bits in a bitmap entry. + */ + add x13, x13, #(8 * 63) + b 2b + +7: +#endif + ret + ENDPROC(__relocate_kernel) #endif @@ -854,6 +943,9 @@ __primary_switch: adrp x1, init_pg_dir bl __enable_mmu #ifdef CONFIG_RELOCATABLE +#ifdef CONFIG_RELR + mov x24, #0 // no RELR displacement yet +#endif bl __relocate_kernel #ifdef CONFIG_RANDOMIZE_BASE ldr x8, =__primary_switched diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index 2f4a2ce7264b..38bcd4d4e43b 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -22,14 +22,14 @@ * Even switching to our copied tables will cause a changed output address at * each stage of the walk. */ -.macro break_before_make_ttbr_switch zero_page, page_table, tmp +.macro break_before_make_ttbr_switch zero_page, page_table, tmp, tmp2 phys_to_ttbr \tmp, \zero_page msr ttbr1_el1, \tmp isb tlbi vmalle1 dsb nsh phys_to_ttbr \tmp, \page_table - offset_ttbr1 \tmp + offset_ttbr1 \tmp, \tmp2 msr ttbr1_el1, \tmp isb .endm @@ -70,7 +70,7 @@ ENTRY(swsusp_arch_suspend_exit) * We execute from ttbr0, change ttbr1 to our copied linear map tables * with a break-before-make via the zero page */ - break_before_make_ttbr_switch x5, x0, x6 + break_before_make_ttbr_switch x5, x0, x6, x8 mov x21, x1 mov x30, x2 @@ -101,7 +101,7 @@ ENTRY(swsusp_arch_suspend_exit) dsb ish /* wait for PoU cleaning to finish */ /* switch to the restored kernels page tables */ - break_before_make_ttbr_switch x25, x21, x6 + break_before_make_ttbr_switch x25, x21, x6, x8 ic ialluis dsb ish diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 9341fcc6e809..e0a7fce0e01c 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -496,7 +496,7 @@ int swsusp_arch_resume(void) rc = -ENOMEM; goto out; } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END); if (rc) goto out; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index dceb84520948..38ee1514cd9c 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -536,13 +536,18 @@ int hw_breakpoint_arch_parse(struct perf_event *bp, /* Aligned */ break; case 1: - /* Allow single byte watchpoint. */ - if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) - break; case 2: /* Allow halfword watchpoints and breakpoints. */ if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) break; + + /* Fallthrough */ + case 3: + /* Allow single byte watchpoint. */ + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) + break; + + /* Fallthrough */ default: return -EINVAL; } diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h new file mode 100644 index 000000000000..25a2a9b479c2 --- /dev/null +++ b/arch/arm64/kernel/image-vars.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Linker script variables to be set after section resolution, as + * ld.lld does not like variables assigned before SECTIONS is processed. + */ +#ifndef __ARM64_KERNEL_IMAGE_VARS_H +#define __ARM64_KERNEL_IMAGE_VARS_H + +#ifndef LINKER_SCRIPT +#error This file should only be included in vmlinux.lds.S +#endif + +#ifdef CONFIG_EFI + +__efistub_stext_offset = stext - _text; + +/* + * The EFI stub has its own symbol namespace prefixed by __efistub_, to + * isolate it from the kernel proper. The following symbols are legally + * accessed by the stub, so provide some aliases to make them accessible. + * Only include data symbols here, or text symbols of functions that are + * guaranteed to be safe when executed at another offset than they were + * linked at. The routines below are all implemented in assembler in a + * position independent manner + */ +__efistub_memcmp = __pi_memcmp; +__efistub_memchr = __pi_memchr; +__efistub_memcpy = __pi_memcpy; +__efistub_memmove = __pi_memmove; +__efistub_memset = __pi_memset; +__efistub_strlen = __pi_strlen; +__efistub_strnlen = __pi_strnlen; +__efistub_strcmp = __pi_strcmp; +__efistub_strncmp = __pi_strncmp; +__efistub_strrchr = __pi_strrchr; +__efistub___flush_dcache_area = __pi___flush_dcache_area; + +#ifdef CONFIG_KASAN +__efistub___memcpy = __pi_memcpy; +__efistub___memmove = __pi_memmove; +__efistub___memset = __pi_memset; +#endif + +__efistub__text = _text; +__efistub__end = _end; +__efistub__edata = _edata; +__efistub_screen_info = screen_info; + +#endif + +#endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index 2b85c0d6fa3d..c7d38c660372 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -65,46 +65,4 @@ DEFINE_IMAGE_LE64(_kernel_offset_le, TEXT_OFFSET); \ DEFINE_IMAGE_LE64(_kernel_flags_le, __HEAD_FLAGS); -#ifdef CONFIG_EFI - -/* - * Use ABSOLUTE() to avoid ld.lld treating this as a relative symbol: - * https://github.com/ClangBuiltLinux/linux/issues/561 - */ -__efistub_stext_offset = ABSOLUTE(stext - _text); - -/* - * The EFI stub has its own symbol namespace prefixed by __efistub_, to - * isolate it from the kernel proper. The following symbols are legally - * accessed by the stub, so provide some aliases to make them accessible. - * Only include data symbols here, or text symbols of functions that are - * guaranteed to be safe when executed at another offset than they were - * linked at. The routines below are all implemented in assembler in a - * position independent manner - */ -__efistub_memcmp = __pi_memcmp; -__efistub_memchr = __pi_memchr; -__efistub_memcpy = __pi_memcpy; -__efistub_memmove = __pi_memmove; -__efistub_memset = __pi_memset; -__efistub_strlen = __pi_strlen; -__efistub_strnlen = __pi_strnlen; -__efistub_strcmp = __pi_strcmp; -__efistub_strncmp = __pi_strncmp; -__efistub_strrchr = __pi_strrchr; -__efistub___flush_dcache_area = __pi___flush_dcache_area; - -#ifdef CONFIG_KASAN -__efistub___memcpy = __pi_memcpy; -__efistub___memmove = __pi_memmove; -__efistub___memset = __pi_memset; -#endif - -__efistub__text = _text; -__efistub__end = _end; -__efistub__edata = _edata; -__efistub_screen_info = screen_info; - -#endif - #endif /* __ARM64_KERNEL_IMAGE_H */ diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 84b059ed04fc..d801a7094076 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -26,7 +26,7 @@ #define AARCH64_INSN_N_BIT BIT(22) #define AARCH64_INSN_LSL_12 BIT(22) -static int aarch64_insn_encoding_class[] = { +static const int aarch64_insn_encoding_class[] = { AARCH64_INSN_CLS_UNKNOWN, AARCH64_INSN_CLS_UNKNOWN, AARCH64_INSN_CLS_UNKNOWN, diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index c70034fbd4ce..04a327ccf84d 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -16,8 +16,10 @@ #include <linux/smp.h> #include <linux/init.h> #include <linux/irqchip.h> +#include <linux/kprobes.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> +#include <asm/daifflags.h> #include <asm/vmap_stack.h> unsigned long irq_err_count; @@ -64,4 +66,28 @@ void __init init_IRQ(void) irqchip_init(); if (!handle_arch_irq) panic("No interrupt controller found."); + + if (system_uses_irq_prio_masking()) { + /* + * Now that we have a stack for our IRQ handler, set + * the PMR/PSR pair to a consistent state. + */ + WARN_ON(read_sysreg(daif) & PSR_A_BIT); + local_daif_restore(DAIF_PROCCTX_NOIRQ); + } +} + +/* + * Stubs to make nmi_enter/exit() code callable from ASM + */ +asmlinkage void notrace asm_nmi_enter(void) +{ + nmi_enter(); +} +NOKPROBE_SYMBOL(asm_nmi_enter); + +asmlinkage void notrace asm_nmi_exit(void) +{ + nmi_exit(); } +NOKPROBE_SYMBOL(asm_nmi_exit); diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 708051655ad9..416f537bf614 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -62,9 +62,6 @@ out: return default_cmdline; } -extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, - pgprot_t prot); - /* * This routine will be executed with the kernel mapped at its default virtual * address, and if it returns successfully, the kernel will be remapped, and @@ -93,7 +90,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * attempt at mapping the FDT in setup_machine() */ early_fixmap_init(); - fdt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); + fdt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); if (!fdt) return 0; @@ -116,15 +113,15 @@ u64 __init kaslr_early_init(u64 dt_phys) /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable * kernel image offset from the seed. Let's place the kernel in the - * middle half of the VMALLOC area (VA_BITS - 2), and stay clear of + * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of * the lower and upper quarters to avoid colliding with other * allocations. * Even if we could randomize at page granularity for 16k and 64k pages, * let's always round to 2 MB so we don't interfere with the ability to * map using contiguous PTEs */ - mask = ((1UL << (VA_BITS - 2)) - 1) & ~(SZ_2M - 1); - offset = BIT(VA_BITS - 3) + (seed & mask); + mask = ((1UL << (VA_BITS_MIN - 2)) - 1) & ~(SZ_2M - 1); + offset = BIT(VA_BITS_MIN - 3) + (seed & mask); /* use the top 16 bits to randomize the linear region */ memstart_offset_seed = seed >> 48; diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 07bf740bea91..29a9428486a5 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -53,7 +53,7 @@ static void *image_load(struct kimage *image, /* * We require a kernel with an unambiguous Image header. Per - * Documentation/booting.txt, this is the case when image_size + * Documentation/arm64/booting.rst, this is the case when image_size * is non-zero (practically speaking, since v3.17). */ h = (struct arm64_image_header *)kernel; @@ -84,7 +84,7 @@ static void *image_load(struct kimage *image, kbuf.buffer = kernel; kbuf.bufsz = kernel_len; - kbuf.mem = 0; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; kbuf.memsz = le64_to_cpu(h->image_size); text_offset = le64_to_cpu(h->text_offset); kbuf.buf_align = MIN_KIMG_ALIGN; diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S index 49825e9e421e..42bd8c0c60e0 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.txt for formal definitions. + * See Documentation/arm/kernel_user_helpers.rst for formal definitions. */ #include <asm/unistd.h> diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 58871333737a..7b08bf9499b6 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -27,6 +27,8 @@ #define FDT_PROP_INITRD_END "linux,initrd-end" #define FDT_PROP_BOOTARGS "bootargs" #define FDT_PROP_KASLR_SEED "kaslr-seed" +#define FDT_PROP_RNG_SEED "rng-seed" +#define RNG_SEED_SIZE 128 const struct kexec_file_ops * const kexec_file_loaders[] = { &kexec_image_ops, @@ -102,6 +104,19 @@ static int setup_dtb(struct kimage *image, FDT_PROP_KASLR_SEED); } + /* add rng-seed */ + if (rng_is_initialized()) { + u8 rng_seed[RNG_SEED_SIZE]; + get_random_bytes(rng_seed, RNG_SEED_SIZE); + ret = fdt_setprop(dtb, off, FDT_PROP_RNG_SEED, rng_seed, + RNG_SEED_SIZE); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_RNG_SEED); + } + out: if (ret) return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL; @@ -110,7 +125,8 @@ out: } /* - * More space needed so that we can add initrd, bootargs and kaslr-seed. + * More space needed so that we can add initrd, bootargs, kaslr-seed, and + * rng-seed. */ #define DTB_EXTRA_SPACE 0x1000 @@ -177,7 +193,7 @@ int load_other_segments(struct kimage *image, if (initrd) { kbuf.buffer = initrd; kbuf.bufsz = initrd_len; - kbuf.mem = 0; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; kbuf.memsz = initrd_len; kbuf.buf_align = 0; /* within 1GB-aligned window of up to 32GB in size */ @@ -204,7 +220,7 @@ int load_other_segments(struct kimage *image, dtb_len = fdt_totalsize(dtb); kbuf.buffer = dtb; kbuf.bufsz = dtb_len; - kbuf.mem = 0; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; kbuf.memsz = dtb_len; /* not across 2MB boundary */ kbuf.buf_align = SZ_2M; diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index 044c0ae4d6c8..b182442b87a3 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -302,7 +302,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, /* sort by type, symbol index and addend */ sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL); - if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0) + if (!str_has_prefix(secstrings + dstsec->sh_name, ".init")) core_plts += count_plts(syms, rels, numrels, sechdrs[i].sh_info, dstsec); else diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 71530e080ecc..03ff15bffbb6 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -34,7 +34,7 @@ void *module_alloc(unsigned long size) module_alloc_end = MODULES_END; p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_end, gfp_mask, PAGE_KERNEL_EXEC, 0, + module_alloc_end, gfp_mask, PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && @@ -50,7 +50,7 @@ void *module_alloc(unsigned long size) */ p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, module_alloc_base + SZ_2G, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_module_alloc(p, size) < 0)) { @@ -314,18 +314,21 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, /* MOVW instruction relocations. */ case R_AARCH64_MOVW_UABS_G0_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, AARCH64_INSN_IMM_MOVKZ); @@ -393,6 +396,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, break; case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; + /* Fall through */ case R_AARCH64_ADR_PREL_PG_HI21: ovf = reloc_insn_adrp(me, sechdrs, loc, val); if (ovf && ovf != -ERANGE) diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c index 575bd5517d21..570988c7a7ff 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -164,6 +164,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) struct acpi_pci_generic_root_info *ri; struct pci_bus *bus, *child; struct acpi_pci_root_ops *root_ops; + struct pci_host_bridge *host; ri = kzalloc(sizeof(*ri), GFP_KERNEL); if (!ri) @@ -189,8 +190,16 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (!bus) return NULL; - pci_bus_size_bridges(bus); - pci_bus_assign_resources(bus); + /* If we must preserve the resource configuration, claim now */ + host = pci_find_host_bridge(bus); + if (host->preserve_config) + pci_bus_claim_resources(bus); + + /* + * Assign whatever was left unassigned. If we didn't claim above, + * this will reassign everything. + */ + pci_assign_unassigned_root_bus_resources(bus); list_for_each_entry(child, &bus->children, node) pcie_bus_configure_settings(child); diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 9d63514b9836..b0e03e052dd1 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -154,12 +154,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, return; } - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, regs->regs[29], regs->pc); walk_stackframe(current, &frame, callchain_trace, entry); } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 96e90e270042..a0b4f1bca491 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -19,6 +19,7 @@ #include <linux/of.h> #include <linux/perf/arm_pmu.h> #include <linux/platform_device.h> +#include <linux/smp.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -157,7 +158,6 @@ armv8pmu_events_sysfs_show(struct device *dev, return sprintf(page, "event=0x%03llx\n", pmu_attr->id); } -#define ARMV8_EVENT_ATTR_RESOLVE(m) #m #define ARMV8_EVENT_ATTR(name, config) \ PMU_EVENT_ATTR(name, armv8_event_attr_##name, \ config, armv8pmu_events_sysfs_show) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 88ce502c8e6f..c4452827419b 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -21,6 +21,7 @@ #include <asm/ptrace.h> #include <asm/cacheflush.h> #include <asm/debug-monitors.h> +#include <asm/daifflags.h> #include <asm/system_misc.h> #include <asm/insn.h> #include <linux/uaccess.h> @@ -122,8 +123,10 @@ void *alloc_insn_page(void) void *page; page = vmalloc_exec(PAGE_SIZE); - if (page) + if (page) { set_memory_ro((unsigned long)page, 1); + set_vm_flush_reset_perms(page); + } return page; } @@ -166,33 +169,6 @@ static void __kprobes set_current_kprobe(struct kprobe *p) } /* - * When PSTATE.D is set (masked), then software step exceptions can not be - * generated. - * SPSR's D bit shows the value of PSTATE.D immediately before the - * exception was taken. PSTATE.D is set while entering into any exception - * mode, however software clears it for any normal (none-debug-exception) - * mode in the exception entry. Therefore, when we are entering into kprobe - * breakpoint handler from any normal mode then SPSR.D bit is already - * cleared, however it is set when we are entering from any debug exception - * mode. - * Since we always need to generate single step exception after a kprobe - * breakpoint exception therefore we need to clear it unconditionally, when - * we become sure that the current breakpoint exception is for kprobe. - */ -static void __kprobes -spsr_set_debug_flag(struct pt_regs *regs, int mask) -{ - unsigned long spsr = regs->pstate; - - if (mask) - spsr |= PSR_D_BIT; - else - spsr &= ~PSR_D_BIT; - - regs->pstate = spsr; -} - -/* * Interrupts need to be disabled before single-step mode is set, and not * reenabled until after single-step mode ends. * Without disabling interrupt on local CPU, there is a chance of @@ -203,17 +179,17 @@ spsr_set_debug_flag(struct pt_regs *regs, int mask) static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - kcb->saved_irqflag = regs->pstate; + kcb->saved_irqflag = regs->pstate & DAIF_MASK; regs->pstate |= PSR_I_BIT; + /* Unmask PSTATE.D for enabling software step exceptions. */ + regs->pstate &= ~PSR_D_BIT; } static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - if (kcb->saved_irqflag & PSR_I_BIT) - regs->pstate |= PSR_I_BIT; - else - regs->pstate &= ~PSR_I_BIT; + regs->pstate &= ~DAIF_MASK; + regs->pstate |= kcb->saved_irqflag; } static void __kprobes @@ -250,8 +226,6 @@ static void __kprobes setup_singlestep(struct kprobe *p, set_ss_context(kcb, slot); /* mark pending ss */ - spsr_set_debug_flag(regs, 0); - /* IRQs and single stepping do not mix well. */ kprobes_save_local_irqflag(kcb, regs); kernel_enable_single_step(regs); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 9856395ccdb7..a47462def04b 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/stddef.h> +#include <linux/sysctl.h> #include <linux/unistd.h> #include <linux/user.h> #include <linux/delay.h> @@ -38,6 +39,7 @@ #include <trace/events/power.h> #include <linux/percpu.h> #include <linux/thread_info.h> +#include <linux/prctl.h> #include <asm/alternative.h> #include <asm/arch_gicv3.h> @@ -83,7 +85,7 @@ static void __cpu_do_idle_irqprio(void) * be raised. */ pmr = gic_read_pmr(); - gic_write_pmr(GIC_PRIO_IRQON); + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); __cpu_do_idle(); @@ -307,11 +309,18 @@ static void tls_thread_flush(void) } } +static void flush_tagged_addr_state(void) +{ + if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI)) + clear_thread_flag(TIF_TAGGED_ADDR); +} + void flush_thread(void) { fpsimd_flush_thread(); tls_thread_flush(); flush_ptrace_hw_breakpoint(current); + flush_tagged_addr_state(); } void release_thread(struct task_struct *dead_task) @@ -398,7 +407,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, childregs->pstate |= PSR_UAO_BIT; if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) - childregs->pstate |= PSR_SSBS_BIT; + set_ssbs_bit(childregs); if (system_uses_irq_prio_masking()) childregs->pmr_save = GIC_PRIO_IRQON; @@ -443,6 +452,32 @@ void uao_thread_switch(struct task_struct *next) } /* + * Force SSBS state on context-switch, since it may be lost after migrating + * from a CPU which treats the bit as RES0 in a heterogeneous system. + */ +static void ssbs_thread_switch(struct task_struct *next) +{ + struct pt_regs *regs = task_pt_regs(next); + + /* + * Nothing to do for kernel threads, but 'regs' may be junk + * (e.g. idle task) so check the flags and bail early. + */ + if (unlikely(next->flags & PF_KTHREAD)) + return; + + /* If the mitigation is enabled, then we leave SSBS clear. */ + if ((arm64_get_ssbd_state() == ARM64_SSBD_FORCE_ENABLE) || + test_tsk_thread_flag(next, TIF_SSBD)) + return; + + if (compat_user_mode(regs)) + set_compat_ssbs_bit(regs); + else if (user_mode(regs)) + set_ssbs_bit(regs); +} + +/* * We store our current task in sp_el0, which is clobbered by userspace. Keep a * shadow copy so that we can restore this upon entry from userspace. * @@ -471,6 +506,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ptrauth_thread_switch(next); + ssbs_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case @@ -498,11 +534,8 @@ unsigned long get_wchan(struct task_struct *p) if (!stack_page) return 0; - frame.fp = thread_saved_fp(p); - frame.pc = thread_saved_pc(p); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif + start_backtrace(&frame, thread_saved_fp(p), thread_saved_pc(p)); + do { if (unwind_frame(p, &frame)) goto out; @@ -524,14 +557,6 @@ unsigned long arch_align_stack(unsigned long sp) return sp & ~0xf; } -unsigned long arch_randomize_brk(struct mm_struct *mm) -{ - if (is_compat_task()) - return randomize_page(mm->brk, SZ_32M); - else - return randomize_page(mm->brk, SZ_1G); -} - /* * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY. */ @@ -541,3 +566,70 @@ void arch_setup_new_exec(void) ptrauth_thread_init_user(current); } + +#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI +/* + * Control the relaxed ABI allowing tagged user addresses into the kernel. + */ +static unsigned int tagged_addr_disabled; + +long set_tagged_addr_ctrl(unsigned long arg) +{ + if (is_compat_task()) + return -EINVAL; + if (arg & ~PR_TAGGED_ADDR_ENABLE) + return -EINVAL; + + /* + * Do not allow the enabling of the tagged address ABI if globally + * disabled via sysctl abi.tagged_addr_disabled. + */ + if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled) + return -EINVAL; + + update_thread_flag(TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE); + + return 0; +} + +long get_tagged_addr_ctrl(void) +{ + if (is_compat_task()) + return -EINVAL; + + if (test_thread_flag(TIF_TAGGED_ADDR)) + return PR_TAGGED_ADDR_ENABLE; + + return 0; +} + +/* + * Global sysctl to disable the tagged user addresses support. This control + * only prevents the tagged address ABI enabling via prctl() and does not + * disable it for tasks that already opted in to the relaxed ABI. + */ +static int zero; +static int one = 1; + +static struct ctl_table tagged_addr_sysctl_table[] = { + { + .procname = "tagged_addr_disabled", + .mode = 0644, + .data = &tagged_addr_disabled, + .maxlen = sizeof(int), + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; + +static int __init tagged_addr_init(void) +{ + if (!register_sysctl("abi", tagged_addr_sysctl_table)) + return -EINVAL; + return 0; +} + +core_initcall(tagged_addr_init); +#endif /* CONFIG_ARM64_TAGGED_ADDR_ABI */ diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c index 85ee7d07889e..c9f72b2665f1 100644 --- a/arch/arm64/kernel/psci.c +++ b/arch/arm64/kernel/psci.c @@ -46,6 +46,11 @@ static int cpu_psci_cpu_boot(unsigned int cpu) } #ifdef CONFIG_HOTPLUG_CPU +static bool cpu_psci_cpu_can_disable(unsigned int cpu) +{ + return !psci_tos_resident_on(cpu); +} + static int cpu_psci_cpu_disable(unsigned int cpu) { /* Fail early if we don't have CPU_OFF support */ @@ -105,14 +110,11 @@ static int cpu_psci_cpu_kill(unsigned int cpu) const struct cpu_operations cpu_psci_ops = { .name = "psci", -#ifdef CONFIG_CPU_IDLE - .cpu_init_idle = psci_cpu_init_idle, - .cpu_suspend = psci_cpu_suspend_enter, -#endif .cpu_init = cpu_psci_cpu_init, .cpu_prepare = cpu_psci_cpu_prepare, .cpu_boot = cpu_psci_cpu_boot, #ifdef CONFIG_HOTPLUG_CPU + .cpu_can_disable = cpu_psci_cpu_can_disable, .cpu_disable = cpu_psci_cpu_disable, .cpu_die = cpu_psci_cpu_die, .cpu_kill = cpu_psci_cpu_kill, diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index da2441d7b066..21176d02e21a 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -870,7 +870,7 @@ static int sve_set(struct task_struct *target, goto out; /* - * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by + * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * sve_set_vector_length(), which will also validate them for us: */ ret = sve_set_vector_length(target, header.vl, @@ -1808,8 +1808,12 @@ static void tracehook_report_syscall(struct pt_regs *regs, int syscall_trace_enter(struct pt_regs *regs) { - if (test_thread_flag(TIF_SYSCALL_TRACE)) + if (test_thread_flag(TIF_SYSCALL_TRACE) || + test_thread_flag(TIF_SYSCALL_EMU)) { tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + if (!in_syscall(regs) || test_thread_flag(TIF_SYSCALL_EMU)) + return -1; + } /* Do the secure computing after ptrace; failures should be fast. */ if (secure_computing(NULL) == -1) diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index b21cba90f82d..a5e8b3b9d798 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -8,6 +8,7 @@ #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -29,6 +30,7 @@ static int save_return_addr(struct stackframe *frame, void *d) return 0; } } +NOKPROBE_SYMBOL(save_return_addr); void *return_address(unsigned int level) { @@ -38,12 +40,9 @@ void *return_address(unsigned int level) data.level = level + 2; data.addr = NULL; - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)return_address; /* dummy */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)return_address); walk_stackframe(current, &frame, save_return_addr, &data); if (!data.level) @@ -52,3 +51,4 @@ void *return_address(unsigned int level) return NULL; } EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 7e541f947b4c..56f664561754 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -170,9 +170,13 @@ static void __init smp_build_mpidr_hash(void) static void __init setup_machine_fdt(phys_addr_t dt_phys) { - void *dt_virt = fixmap_remap_fdt(dt_phys); + int size; + void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL); const char *name; + if (dt_virt) + memblock_reserve(dt_phys, size); + if (!dt_virt || !early_init_dt_scan(dt_virt)) { pr_crit("\n" "Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n" @@ -184,6 +188,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys) cpu_relax(); } + /* Early fixups are done, map the FDT as read-only now */ + fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO); + name = of_flat_dt_get_machine_name(); if (!name) return; @@ -283,6 +290,11 @@ void __init setup_arch(char **cmdline_p) setup_machine_fdt(__fdt_pointer); + /* + * Initialise the static keys early as they may be enabled by the + * cpufeature code and early parameters. + */ + jump_label_init(); parse_early_param(); /* @@ -352,6 +364,15 @@ 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); +#endif + return false; +} + static int __init topology_init(void) { int i; @@ -361,7 +382,7 @@ static int __init topology_init(void) for_each_possible_cpu(i) { struct cpu *cpu = &per_cpu(cpu_data.cpu, i); - cpu->hotpluggable = 1; + cpu->hotpluggable = cpu_can_disable(i); register_cpu(cpu, i); } diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 331d1e5acad4..12a585386c2f 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -18,42 +18,7 @@ #include <asm/traps.h> #include <linux/uaccess.h> #include <asm/unistd.h> - -struct compat_sigcontext { - /* We always set these two fields to 0 */ - compat_ulong_t trap_no; - compat_ulong_t error_code; - - compat_ulong_t oldmask; - compat_ulong_t arm_r0; - compat_ulong_t arm_r1; - compat_ulong_t arm_r2; - compat_ulong_t arm_r3; - compat_ulong_t arm_r4; - compat_ulong_t arm_r5; - compat_ulong_t arm_r6; - compat_ulong_t arm_r7; - compat_ulong_t arm_r8; - compat_ulong_t arm_r9; - compat_ulong_t arm_r10; - compat_ulong_t arm_fp; - compat_ulong_t arm_ip; - compat_ulong_t arm_sp; - compat_ulong_t arm_lr; - compat_ulong_t arm_pc; - compat_ulong_t arm_cpsr; - compat_ulong_t fault_address; -}; - -struct compat_ucontext { - compat_ulong_t uc_flags; - compat_uptr_t uc_link; - compat_stack_t uc_stack; - struct compat_sigcontext uc_mcontext; - compat_sigset_t uc_sigmask; - int __unused[32 - (sizeof (compat_sigset_t) / sizeof (int))]; - compat_ulong_t uc_regspace[128] __attribute__((__aligned__(8))); -}; +#include <asm/vdso.h> struct compat_vfp_sigframe { compat_ulong_t magic; @@ -81,16 +46,6 @@ struct compat_aux_sigframe { unsigned long end_magic; } __attribute__((__aligned__(8))); -struct compat_sigframe { - struct compat_ucontext uc; - compat_ulong_t retcode[2]; -}; - -struct compat_rt_sigframe { - struct compat_siginfo info; - struct compat_sigframe sig; -}; - #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set) @@ -387,6 +342,30 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, retcode = ptr_to_compat(ka->sa.sa_restorer); } else { /* Set up sigreturn pointer */ +#ifdef CONFIG_COMPAT_VDSO + void *vdso_base = current->mm->context.vdso; + void *vdso_trampoline; + + if (ka->sa.sa_flags & SA_SIGINFO) { + if (thumb) { + vdso_trampoline = VDSO_SYMBOL(vdso_base, + compat_rt_sigreturn_thumb); + } else { + vdso_trampoline = VDSO_SYMBOL(vdso_base, + compat_rt_sigreturn_arm); + } + } else { + if (thumb) { + vdso_trampoline = VDSO_SYMBOL(vdso_base, + compat_sigreturn_thumb); + } else { + vdso_trampoline = VDSO_SYMBOL(vdso_base, + compat_sigreturn_arm); + } + } + + retcode = ptr_to_compat(vdso_trampoline) + thumb; +#else unsigned int idx = thumb << 1; if (ka->sa.sa_flags & SA_SIGINFO) @@ -394,6 +373,7 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka, retcode = (unsigned long)current->mm->context.vdso + (idx << 2) + thumb; +#endif } regs->regs[0] = usig; diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 3e53ffa07994..f5b04dd8a710 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -27,7 +27,7 @@ * aff0 = mpidr_masked & 0xff; * aff1 = mpidr_masked & 0xff00; * aff2 = mpidr_masked & 0xff0000; - * aff2 = mpidr_masked & 0xff00000000; + * aff3 = mpidr_masked & 0xff00000000; * dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2 | aff3 >> rs3); *} * Input registers: rs0, rs1, rs2, rs3, mpidr, mask diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 6dcf9607d770..dc9fe879c279 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -123,7 +123,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) * time out. */ wait_for_completion_timeout(&cpu_running, - msecs_to_jiffies(1000)); + msecs_to_jiffies(5000)); if (!cpu_online(cpu)) { pr_crit("CPU%u: failed to come online\n", cpu); @@ -136,6 +136,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) secondary_data.task = NULL; secondary_data.stack = NULL; + __flush_dcache_area(&secondary_data, sizeof(secondary_data)); status = READ_ONCE(secondary_data.status); if (ret && status) { @@ -146,14 +147,15 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) 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; } - /* Fall through */ 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) @@ -181,11 +183,7 @@ static void init_gic_priority_masking(void) WARN_ON(!(cpuflags & PSR_I_BIT)); - gic_write_pmr(GIC_PRIO_IRQOFF); - - /* We can only unmask PSR.I if we can take aborts */ - if (!(cpuflags & PSR_A_BIT)) - write_sysreg(cpuflags & ~PSR_I_BIT, daif); + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); } /* @@ -424,11 +422,6 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { set_my_cpu_offset(per_cpu_offset(smp_processor_id())); - /* - * Initialise the static keys early as they may be enabled by the - * cpufeature code. - */ - jump_label_init(); cpuinfo_store_boot_cpu(); /* @@ -834,18 +827,23 @@ void arch_irq_work_raise(void) } #endif -/* - * ipi_cpu_stop - handle IPI from smp_send_stop() - */ -static void ipi_cpu_stop(unsigned int cpu) +static void local_cpu_stop(void) { - set_cpu_online(cpu, false); + set_cpu_online(smp_processor_id(), false); local_daif_mask(); sdei_mask_local_cpu(); + cpu_park_loop(); +} - while (1) - cpu_relax(); +/* + * We need to implement panic_smp_self_stop() for parallel panic() calls, so + * that cpu_online_mask gets correctly updated and smp_send_stop() can skip + * CPUs that have already stopped themselves. + */ +void panic_smp_self_stop(void) +{ + local_cpu_stop(); } #ifdef CONFIG_KEXEC_CORE @@ -898,7 +896,7 @@ void handle_IPI(int ipinr, struct pt_regs *regs) case IPI_CPU_STOP: irq_enter(); - ipi_cpu_stop(cpu); + local_cpu_stop(); irq_exit(); break; diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c index 76c2739ba8a4..c8a3fee00c11 100644 --- a/arch/arm64/kernel/smp_spin_table.c +++ b/arch/arm64/kernel/smp_spin_table.c @@ -19,7 +19,7 @@ #include <asm/smp_plat.h> extern void secondary_holding_pen(void); -volatile unsigned long __section(".mmuoff.data.read") +volatile unsigned long __section(.mmuoff.data.read) secondary_holding_pen_release = INVALID_HWID; static phys_addr_t cpu_release_addr[NR_CPUS]; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 62d395151abe..a336cb124320 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/export.h> #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> @@ -29,9 +30,18 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ + +/* + * Unwind from one frame record (A) to the next frame record (B). + * + * We terminate early if the location of B indicates a malformed chain of frame + * records (e.g. a cycle), determined based on the location and fp value of A + * and the location (but not the fp value) of B. + */ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) { unsigned long fp = frame->fp; + struct stack_info info; if (fp & 0xf) return -EINVAL; @@ -39,11 +49,40 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) if (!tsk) tsk = current; - if (!on_accessible_stack(tsk, fp, NULL)) + if (!on_accessible_stack(tsk, fp, &info)) + return -EINVAL; + + if (test_bit(info.type, frame->stacks_done)) return -EINVAL; + /* + * As stacks grow downward, any valid record on the same stack must be + * at a strictly higher address than the prior record. + * + * Stacks can nest in several valid orders, e.g. + * + * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL + * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW + * + * ... but the nesting itself is strict. Once we transition from one + * stack to another, it's never valid to unwind back to that first + * stack. + */ + if (info.type == frame->prev_type) { + if (fp <= frame->prev_fp) + return -EINVAL; + } else { + set_bit(frame->prev_type, frame->stacks_done); + } + + /* + * Record this frame record's values and location. The prev_fp and + * prev_type are only meaningful to the next unwind_frame() invocation. + */ frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); + frame->prev_fp = fp; + frame->prev_type = info.type; #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && @@ -73,6 +112,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) return 0; } +NOKPROBE_SYMBOL(unwind_frame); void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) @@ -87,6 +127,7 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, break; } } +NOKPROBE_SYMBOL(walk_stackframe); #ifdef CONFIG_STACKTRACE struct stack_trace_data { @@ -122,12 +163,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) data.skip = trace->skip; data.no_sched_functions = 0; - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif - + start_backtrace(&frame, regs->regs[29], regs->pc); walk_stackframe(current, &frame, save_trace, &data); } EXPORT_SYMBOL_GPL(save_stack_trace_regs); @@ -146,17 +182,15 @@ static noinline void __save_stack_trace(struct task_struct *tsk, data.no_sched_functions = nosched; if (tsk != current) { - frame.fp = thread_saved_fp(tsk); - frame.pc = thread_saved_pc(tsk); + start_backtrace(&frame, thread_saved_fp(tsk), + thread_saved_pc(tsk)); } else { /* We don't want this function nor the caller */ data.skip += 2; - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)__save_stack_trace; + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)__save_stack_trace); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif walk_stackframe(tsk, &frame, save_trace, &data); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 9f25aedeac9d..0b2946414dc9 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -38,11 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs) if (!in_lock_functions(regs->pc)) return regs->pc; - frame.fp = regs->regs[29]; - frame.pc = regs->pc; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif + start_backtrace(&frame, regs->regs[29], regs->pc); + do { int ret = unwind_frame(NULL, &frame); if (ret < 0) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 0825c4a856e3..fa9528dfd0ce 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -14,250 +14,13 @@ #include <linux/acpi.h> #include <linux/arch_topology.h> #include <linux/cacheinfo.h> -#include <linux/cpu.h> -#include <linux/cpumask.h> #include <linux/init.h> #include <linux/percpu.h> -#include <linux/node.h> -#include <linux/nodemask.h> -#include <linux/of.h> -#include <linux/sched.h> -#include <linux/sched/topology.h> -#include <linux/slab.h> -#include <linux/smp.h> -#include <linux/string.h> #include <asm/cpu.h> #include <asm/cputype.h> #include <asm/topology.h> -static int __init get_cpu_for_node(struct device_node *node) -{ - struct device_node *cpu_node; - int cpu; - - cpu_node = of_parse_phandle(node, "cpu", 0); - if (!cpu_node) - return -1; - - cpu = of_cpu_node_to_id(cpu_node); - if (cpu >= 0) - topology_parse_cpu_capacity(cpu_node, cpu); - else - pr_crit("Unable to find CPU node for %pOF\n", cpu_node); - - of_node_put(cpu_node); - return cpu; -} - -static int __init parse_core(struct device_node *core, int package_id, - int core_id) -{ - char name[10]; - bool leaf = true; - int i = 0; - int cpu; - struct device_node *t; - - do { - snprintf(name, sizeof(name), "thread%d", i); - t = of_get_child_by_name(core, name); - if (t) { - leaf = false; - cpu = get_cpu_for_node(t); - if (cpu >= 0) { - cpu_topology[cpu].package_id = package_id; - cpu_topology[cpu].core_id = core_id; - cpu_topology[cpu].thread_id = i; - } else { - pr_err("%pOF: Can't get CPU for thread\n", - t); - of_node_put(t); - return -EINVAL; - } - of_node_put(t); - } - i++; - } while (t); - - cpu = get_cpu_for_node(core); - if (cpu >= 0) { - if (!leaf) { - pr_err("%pOF: Core has both threads and CPU\n", - core); - return -EINVAL; - } - - cpu_topology[cpu].package_id = package_id; - cpu_topology[cpu].core_id = core_id; - } else if (leaf) { - pr_err("%pOF: Can't get CPU for leaf core\n", core); - return -EINVAL; - } - - return 0; -} - -static int __init parse_cluster(struct device_node *cluster, int depth) -{ - char name[10]; - bool leaf = true; - bool has_cores = false; - struct device_node *c; - static int package_id __initdata; - int core_id = 0; - int i, ret; - - /* - * First check for child clusters; we currently ignore any - * information about the nesting of clusters and present the - * scheduler with a flat list of them. - */ - i = 0; - do { - snprintf(name, sizeof(name), "cluster%d", i); - c = of_get_child_by_name(cluster, name); - if (c) { - leaf = false; - ret = parse_cluster(c, depth + 1); - of_node_put(c); - if (ret != 0) - return ret; - } - i++; - } while (c); - - /* Now check for cores */ - i = 0; - do { - snprintf(name, sizeof(name), "core%d", i); - c = of_get_child_by_name(cluster, name); - if (c) { - has_cores = true; - - if (depth == 0) { - pr_err("%pOF: cpu-map children should be clusters\n", - c); - of_node_put(c); - return -EINVAL; - } - - if (leaf) { - ret = parse_core(c, package_id, core_id++); - } else { - pr_err("%pOF: Non-leaf cluster with core %s\n", - cluster, name); - ret = -EINVAL; - } - - of_node_put(c); - if (ret != 0) - return ret; - } - i++; - } while (c); - - if (leaf && !has_cores) - pr_warn("%pOF: empty cluster\n", cluster); - - if (leaf) - package_id++; - - return 0; -} - -static int __init parse_dt_topology(void) -{ - struct device_node *cn, *map; - int ret = 0; - int cpu; - - cn = of_find_node_by_path("/cpus"); - if (!cn) { - pr_err("No CPU information found in DT\n"); - return 0; - } - - /* - * When topology is provided cpu-map is essentially a root - * cluster with restricted subnodes. - */ - map = of_get_child_by_name(cn, "cpu-map"); - if (!map) - goto out; - - ret = parse_cluster(map, 0); - if (ret != 0) - goto out_map; - - topology_normalize_cpu_scale(); - - /* - * Check that all cores are in the topology; the SMP code will - * only mark cores described in the DT as possible. - */ - for_each_possible_cpu(cpu) - if (cpu_topology[cpu].package_id == -1) - ret = -EINVAL; - -out_map: - of_node_put(map); -out: - of_node_put(cn); - return ret; -} - -/* - * cpu topology table - */ -struct cpu_topology cpu_topology[NR_CPUS]; -EXPORT_SYMBOL_GPL(cpu_topology); - -const struct cpumask *cpu_coregroup_mask(int cpu) -{ - const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu)); - - /* Find the smaller of NUMA, core or LLC siblings */ - if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) { - /* not numa in package, lets use the package siblings */ - core_mask = &cpu_topology[cpu].core_sibling; - } - if (cpu_topology[cpu].llc_id != -1) { - if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask)) - core_mask = &cpu_topology[cpu].llc_sibling; - } - - return core_mask; -} - -static void update_siblings_masks(unsigned int cpuid) -{ - struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; - int cpu; - - /* update core and thread sibling masks */ - for_each_online_cpu(cpu) { - cpu_topo = &cpu_topology[cpu]; - - if (cpuid_topo->llc_id == cpu_topo->llc_id) { - cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling); - cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling); - } - - if (cpuid_topo->package_id != cpu_topo->package_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); - - if (cpuid_topo->core_id != cpu_topo->core_id) - continue; - - cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling); - } -} - void store_cpu_topology(unsigned int cpuid) { struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; @@ -296,60 +59,31 @@ topology_populated: update_siblings_masks(cpuid); } -static void clear_cpu_topology(int cpu) -{ - struct cpu_topology *cpu_topo = &cpu_topology[cpu]; - - cpumask_clear(&cpu_topo->llc_sibling); - cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); - - cpumask_clear(&cpu_topo->core_sibling); - cpumask_set_cpu(cpu, &cpu_topo->core_sibling); - cpumask_clear(&cpu_topo->thread_sibling); - cpumask_set_cpu(cpu, &cpu_topo->thread_sibling); -} - -static void __init reset_cpu_topology(void) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) { - struct cpu_topology *cpu_topo = &cpu_topology[cpu]; - - cpu_topo->thread_id = -1; - cpu_topo->core_id = 0; - cpu_topo->package_id = -1; - cpu_topo->llc_id = -1; - - clear_cpu_topology(cpu); - } -} - -void remove_cpu_topology(unsigned int cpu) +#ifdef CONFIG_ACPI +static bool __init acpi_cpu_is_threaded(int cpu) { - int sibling; + int is_threaded = acpi_pptt_cpu_is_thread(cpu); - for_each_cpu(sibling, topology_core_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); - for_each_cpu(sibling, topology_sibling_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); - for_each_cpu(sibling, topology_llc_cpumask(cpu)) - cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); + /* + * if the PPTT doesn't have thread information, assume a homogeneous + * machine and return the current CPU's thread state. + */ + if (is_threaded < 0) + is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK; - clear_cpu_topology(cpu); + return !!is_threaded; } -#ifdef CONFIG_ACPI /* * Propagate the topology information of the processor_topology_node tree to the * cpu_topology array. */ -static int __init parse_acpi_topology(void) +int __init parse_acpi_topology(void) { - bool is_threaded; int cpu, topology_id; - is_threaded = read_cpuid_mpidr() & MPIDR_MT_BITMASK; + if (acpi_disabled) + return 0; for_each_possible_cpu(cpu) { int i, cache_id; @@ -358,7 +92,7 @@ static int __init parse_acpi_topology(void) if (topology_id < 0) return topology_id; - if (is_threaded) { + if (acpi_cpu_is_threaded(cpu)) { cpu_topology[cpu].thread_id = topology_id; topology_id = find_acpi_cpu_topology(cpu, 1); cpu_topology[cpu].core_id = topology_id; @@ -384,24 +118,6 @@ static int __init parse_acpi_topology(void) return 0; } - -#else -static inline int __init parse_acpi_topology(void) -{ - return -EINVAL; -} #endif -void __init init_cpu_topology(void) -{ - reset_cpu_topology(); - /* - * Discard anything that was parsed if we hit an error so we - * don't use partial information. - */ - if (!acpi_disabled && parse_acpi_topology()) - reset_cpu_topology(); - else if (of_have_populated_dt() && parse_dt_topology()) - reset_cpu_topology(); -} diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 985721a1264c..34739e80211b 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -7,9 +7,11 @@ */ #include <linux/bug.h> +#include <linux/context_tracking.h> #include <linux/signal.h> #include <linux/personality.h> #include <linux/kallsyms.h> +#include <linux/kprobes.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/hardirq.h> @@ -55,16 +57,19 @@ static void dump_backtrace_entry(unsigned long where) printk(" %pS\n", (void *)where); } -static void __dump_instr(const char *lvl, struct pt_regs *regs) +static void dump_kernel_instr(const char *lvl, struct pt_regs *regs) { unsigned long addr = instruction_pointer(regs); char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str; int i; + if (user_mode(regs)) + return; + for (i = -4; i < 1; i++) { unsigned int val, bad; - bad = get_user(val, &((u32 *)addr)[i]); + bad = aarch64_insn_read(&((u32 *)addr)[i], &val); if (!bad) p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val); @@ -73,19 +78,8 @@ static void __dump_instr(const char *lvl, struct pt_regs *regs) break; } } - printk("%sCode: %s\n", lvl, str); -} -static void dump_instr(const char *lvl, struct pt_regs *regs) -{ - if (!user_mode(regs)) { - mm_segment_t fs = get_fs(); - set_fs(KERNEL_DS); - __dump_instr(lvl, regs); - set_fs(fs); - } else { - __dump_instr(lvl, regs); - } + printk("%sCode: %s\n", lvl, str); } void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) @@ -108,18 +102,17 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) return; if (tsk == current) { - frame.fp = (unsigned long)__builtin_frame_address(0); - frame.pc = (unsigned long)dump_backtrace; + start_backtrace(&frame, + (unsigned long)__builtin_frame_address(0), + (unsigned long)dump_backtrace); } else { /* * task blocked in __switch_to */ - frame.fp = thread_saved_fp(tsk); - frame.pc = thread_saved_pc(tsk); + start_backtrace(&frame, + thread_saved_fp(tsk), + thread_saved_pc(tsk)); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = 0; -#endif printk("Call trace:\n"); do { @@ -171,8 +164,7 @@ static int __die(const char *str, int err, struct pt_regs *regs) print_modules(); show_regs(regs); - if (!user_mode(regs)) - dump_instr(KERN_EMERG, regs); + dump_kernel_instr(KERN_EMERG, regs); return ret; } @@ -242,16 +234,16 @@ void arm64_force_sig_fault(int signo, int code, void __user *addr, { arm64_show_signal(signo, str); if (signo == SIGKILL) - force_sig(SIGKILL, current); + force_sig(SIGKILL); else - force_sig_fault(signo, code, addr, current); + force_sig_fault(signo, code, addr); } void arm64_force_sig_mceerr(int code, void __user *addr, short lsb, const char *str) { arm64_show_signal(SIGBUS, str); - force_sig_mceerr(code, addr, lsb, current); + force_sig_mceerr(code, addr, lsb); } void arm64_force_sig_ptrace_errno_trap(int errno, void __user *addr, @@ -521,7 +513,7 @@ struct sys64_hook { void (*handler)(unsigned int esr, struct pt_regs *regs); }; -static struct sys64_hook sys64_hooks[] = { +static const struct sys64_hook sys64_hooks[] = { { .esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK, .esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL, @@ -646,7 +638,7 @@ static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs) arm64_compat_skip_faulting_instruction(regs, 4); } -static struct sys64_hook cp15_32_hooks[] = { +static const struct sys64_hook cp15_32_hooks[] = { { .esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ, @@ -666,7 +658,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs) arm64_compat_skip_faulting_instruction(regs, 4); } -static struct sys64_hook cp15_64_hooks[] = { +static const struct sys64_hook cp15_64_hooks[] = { { .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK, .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT, @@ -677,7 +669,7 @@ static struct sys64_hook cp15_64_hooks[] = { asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) { - struct sys64_hook *hook, *hook_base; + const struct sys64_hook *hook, *hook_base; if (!cp15_cond_valid(esr, regs)) { /* @@ -717,7 +709,7 @@ asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs) asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) { - struct sys64_hook *hook; + const struct sys64_hook *hook; for (hook = sys64_hooks; hook->handler; hook++) if ((hook->esr_mask & esr) == hook->esr_val) { @@ -743,6 +735,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_CP14_LS] = "CP14 LDC/STC", [ESR_ELx_EC_FP_ASIMD] = "ASIMD", [ESR_ELx_EC_CP10_ID] = "CP10 MRC/VMRS", + [ESR_ELx_EC_PAC] = "PAC", [ESR_ELx_EC_CP14_64] = "CP14 MCRR/MRRC", [ESR_ELx_EC_ILL] = "PSTATE.IL", [ESR_ELx_EC_SVC32] = "SVC (AArch32)", @@ -753,6 +746,7 @@ static const char *esr_class_str[] = { [ESR_ELx_EC_SMC64] = "SMC (AArch64)", [ESR_ELx_EC_SYS64] = "MSR/MRS (AArch64)", [ESR_ELx_EC_SVE] = "SVE", + [ESR_ELx_EC_ERET] = "ERET/ERETAA/ERETAB", [ESR_ELx_EC_IMP_DEF] = "EL3 IMP DEF", [ESR_ELx_EC_IABT_LOW] = "IABT (lower EL)", [ESR_ELx_EC_IABT_CUR] = "IABT (current EL)", @@ -880,6 +874,10 @@ bool arm64_is_fatal_ras_serror(struct pt_regs *regs, unsigned int esr) /* * The CPU can't make progress. The exception may have * been imprecise. + * + * Neoverse-N1 #1349291 means a non-KVM SError reported as + * Unrecoverable should be treated as Uncontainable. We + * call arm64_serror_panic() in both cases. */ return true; @@ -905,6 +903,13 @@ asmlinkage void do_serror(struct pt_regs *regs, unsigned int esr) nmi_exit(); } +asmlinkage void enter_from_user_mode(void) +{ + CT_WARN_ON(ct_state() != CONTEXT_USER); + user_exit_irqoff(); +} +NOKPROBE_SYMBOL(enter_from_user_mode); + void __pte_error(const char *file, int line, unsigned long val) { pr_err("%s:%d: bad pte %016lx.\n", file, line, val); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 663b166241d0..354b11e27c07 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -20,41 +20,212 @@ #include <linux/slab.h> #include <linux/timekeeper_internal.h> #include <linux/vmalloc.h> +#include <vdso/datapage.h> +#include <vdso/helpers.h> +#include <vdso/vsyscall.h> #include <asm/cacheflush.h> #include <asm/signal32.h> #include <asm/vdso.h> -#include <asm/vdso_datapage.h> extern char vdso_start[], vdso_end[]; -static unsigned long vdso_pages __ro_after_init; +#ifdef CONFIG_COMPAT_VDSO +extern char vdso32_start[], vdso32_end[]; +#endif /* CONFIG_COMPAT_VDSO */ + +/* vdso_lookup arch_index */ +enum arch_vdso_type { + ARM64_VDSO = 0, +#ifdef CONFIG_COMPAT_VDSO + ARM64_VDSO32 = 1, +#endif /* CONFIG_COMPAT_VDSO */ +}; +#ifdef CONFIG_COMPAT_VDSO +#define VDSO_TYPES (ARM64_VDSO32 + 1) +#else +#define VDSO_TYPES (ARM64_VDSO + 1) +#endif /* CONFIG_COMPAT_VDSO */ + +struct __vdso_abi { + const char *name; + const char *vdso_code_start; + const char *vdso_code_end; + unsigned long vdso_pages; + /* Data Mapping */ + struct vm_special_mapping *dm; + /* Code Mapping */ + struct vm_special_mapping *cm; +}; + +static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = { + { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, + }, +#ifdef CONFIG_COMPAT_VDSO + { + .name = "vdso32", + .vdso_code_start = vdso32_start, + .vdso_code_end = vdso32_end, + }, +#endif /* CONFIG_COMPAT_VDSO */ +}; /* * The vDSO data page. */ static union { - struct vdso_data data; + struct vdso_data data[CS_BASES]; u8 page[PAGE_SIZE]; } vdso_data_store __page_aligned_data; -struct vdso_data *vdso_data = &vdso_data_store.data; +struct vdso_data *vdso_data = vdso_data_store.data; + +static int __vdso_remap(enum arch_vdso_type arch_index, + const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + unsigned long new_size = new_vma->vm_end - new_vma->vm_start; + unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end - + vdso_lookup[arch_index].vdso_code_start; + + if (vdso_size != new_size) + return -EINVAL; + + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static int __vdso_init(enum arch_vdso_type arch_index) +{ + int i; + struct page **vdso_pagelist; + unsigned long pfn; + + if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) { + pr_err("vDSO is not a valid ELF object!\n"); + return -EINVAL; + } + + vdso_lookup[arch_index].vdso_pages = ( + vdso_lookup[arch_index].vdso_code_end - + vdso_lookup[arch_index].vdso_code_start) >> + PAGE_SHIFT; + + /* Allocate the vDSO pagelist, plus a page for the data. */ + vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1, + sizeof(struct page *), + GFP_KERNEL); + if (vdso_pagelist == NULL) + return -ENOMEM; + + /* Grab the vDSO data page. */ + vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data)); + + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start); + + for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++) + vdso_pagelist[i + 1] = pfn_to_page(pfn + i); + + vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0]; + vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1]; + + return 0; +} + +static int __setup_additional_pages(enum arch_vdso_type arch_index, + struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp) +{ + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; + + vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + PAGE_SIZE; + + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); + if (IS_ERR_VALUE(vdso_base)) { + ret = ERR_PTR(vdso_base); + goto up_fail; + } + + ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE, + VM_READ|VM_MAYREAD, + vdso_lookup[arch_index].dm); + if (IS_ERR(ret)) + goto up_fail; + + vdso_base += PAGE_SIZE; + mm->context.vdso = (void *)vdso_base; + ret = _install_special_mapping(mm, vdso_base, vdso_text_len, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + vdso_lookup[arch_index].cm); + if (IS_ERR(ret)) + goto up_fail; + + return 0; + +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); +} #ifdef CONFIG_COMPAT /* * Create and map the vectors page for AArch32 tasks. */ +#ifdef CONFIG_COMPAT_VDSO +static int aarch32_vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + return __vdso_remap(ARM64_VDSO32, sm, new_vma); +} +#endif /* CONFIG_COMPAT_VDSO */ + +/* + * aarch32_vdso_pages: + * 0 - kuser helpers + * 1 - sigreturn code + * or (CONFIG_COMPAT_VDSO): + * 0 - kuser helpers + * 1 - vdso data + * 2 - vdso code + */ #define C_VECTORS 0 +#ifdef CONFIG_COMPAT_VDSO +#define C_VVAR 1 +#define C_VDSO 2 +#define C_PAGES (C_VDSO + 1) +#else #define C_SIGPAGE 1 #define C_PAGES (C_SIGPAGE + 1) +#endif /* CONFIG_COMPAT_VDSO */ static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init; -static const struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = { +static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = { { .name = "[vectors]", /* ABI */ .pages = &aarch32_vdso_pages[C_VECTORS], }, +#ifdef CONFIG_COMPAT_VDSO + { + .name = "[vvar]", + }, + { + .name = "[vdso]", + .mremap = aarch32_vdso_mremap, + }, +#else { .name = "[sigpage]", /* ABI */ .pages = &aarch32_vdso_pages[C_SIGPAGE], }, +#endif /* CONFIG_COMPAT_VDSO */ }; static int aarch32_alloc_kuser_vdso_page(void) @@ -77,7 +248,33 @@ static int aarch32_alloc_kuser_vdso_page(void) return 0; } -static int __init aarch32_alloc_vdso_pages(void) +#ifdef CONFIG_COMPAT_VDSO +static int __aarch32_alloc_vdso_pages(void) +{ + int ret; + + vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR]; + vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO]; + + ret = __vdso_init(ARM64_VDSO32); + if (ret) + return ret; + + ret = aarch32_alloc_kuser_vdso_page(); + if (ret) { + unsigned long c_vvar = + (unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]); + unsigned long c_vdso = + (unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]); + + free_page(c_vvar); + free_page(c_vdso); + } + + return ret; +} +#else +static int __aarch32_alloc_vdso_pages(void) { extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[]; int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start; @@ -98,6 +295,12 @@ static int __init aarch32_alloc_vdso_pages(void) return ret; } +#endif /* CONFIG_COMPAT_VDSO */ + +static int __init aarch32_alloc_vdso_pages(void) +{ + return __aarch32_alloc_vdso_pages(); +} arch_initcall(aarch32_alloc_vdso_pages); static int aarch32_kuser_helpers_setup(struct mm_struct *mm) @@ -119,6 +322,7 @@ static int aarch32_kuser_helpers_setup(struct mm_struct *mm) return PTR_ERR_OR_ZERO(ret); } +#ifndef CONFIG_COMPAT_VDSO static int aarch32_sigreturn_setup(struct mm_struct *mm) { unsigned long addr; @@ -146,6 +350,7 @@ static int aarch32_sigreturn_setup(struct mm_struct *mm) out: return PTR_ERR_OR_ZERO(ret); } +#endif /* !CONFIG_COMPAT_VDSO */ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { @@ -159,7 +364,14 @@ int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (ret) goto out; +#ifdef CONFIG_COMPAT_VDSO + ret = __setup_additional_pages(ARM64_VDSO32, + mm, + bprm, + uses_interp); +#else ret = aarch32_sigreturn_setup(mm); +#endif /* CONFIG_COMPAT_VDSO */ out: up_write(&mm->mmap_sem); @@ -170,18 +382,18 @@ out: static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { - unsigned long new_size = new_vma->vm_end - new_vma->vm_start; - unsigned long vdso_size = vdso_end - vdso_start; - - if (vdso_size != new_size) - return -EINVAL; - - current->mm->context.vdso = (void *)new_vma->vm_start; - - return 0; + return __vdso_remap(ARM64_VDSO, sm, new_vma); } -static struct vm_special_mapping vdso_spec[2] __ro_after_init = { +/* + * aarch64_vdso_pages: + * 0 - vvar + * 1 - vdso + */ +#define A_VVAR 0 +#define A_VDSO 1 +#define A_PAGES (A_VDSO + 1) +static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = { { .name = "[vvar]", }, @@ -193,37 +405,10 @@ static struct vm_special_mapping vdso_spec[2] __ro_after_init = { static int __init vdso_init(void) { - int i; - struct page **vdso_pagelist; - unsigned long pfn; - - if (memcmp(vdso_start, "\177ELF", 4)) { - pr_err("vDSO is not a valid ELF object!\n"); - return -EINVAL; - } - - vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; - - /* Allocate the vDSO pagelist, plus a page for the data. */ - vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *), - GFP_KERNEL); - if (vdso_pagelist == NULL) - return -ENOMEM; - - /* Grab the vDSO data page. */ - vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data)); - - - /* Grab the vDSO code pages. */ - pfn = sym_to_pfn(vdso_start); - - for (i = 0; i < vdso_pages; i++) - vdso_pagelist[i + 1] = pfn_to_page(pfn + i); + vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR]; + vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO]; - vdso_spec[0].pages = &vdso_pagelist[0]; - vdso_spec[1].pages = &vdso_pagelist[1]; - - return 0; + return __vdso_init(ARM64_VDSO); } arch_initcall(vdso_init); @@ -231,84 +416,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; - unsigned long vdso_base, vdso_text_len, vdso_mapping_len; - void *ret; - - vdso_text_len = vdso_pages << PAGE_SHIFT; - /* Be sure to map the data page */ - vdso_mapping_len = vdso_text_len + PAGE_SIZE; + int ret; if (down_write_killable(&mm->mmap_sem)) return -EINTR; - vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); - if (IS_ERR_VALUE(vdso_base)) { - ret = ERR_PTR(vdso_base); - goto up_fail; - } - ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE, - VM_READ|VM_MAYREAD, - &vdso_spec[0]); - if (IS_ERR(ret)) - goto up_fail; - - vdso_base += PAGE_SIZE; - mm->context.vdso = (void *)vdso_base; - ret = _install_special_mapping(mm, vdso_base, vdso_text_len, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - &vdso_spec[1]); - if (IS_ERR(ret)) - goto up_fail; + ret = __setup_additional_pages(ARM64_VDSO, + mm, + bprm, + uses_interp); up_write(&mm->mmap_sem); - return 0; - -up_fail: - mm->context.vdso = NULL; - up_write(&mm->mmap_sem); - return PTR_ERR(ret); -} -/* - * Update the vDSO data page to keep in sync with kernel timekeeping. - */ -void update_vsyscall(struct timekeeper *tk) -{ - u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct; - - ++vdso_data->tb_seq_count; - smp_wmb(); - - vdso_data->use_syscall = use_syscall; - vdso_data->xtime_coarse_sec = tk->xtime_sec; - vdso_data->xtime_coarse_nsec = tk->tkr_mono.xtime_nsec >> - tk->tkr_mono.shift; - vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec; - vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; - - /* Read without the seqlock held by clock_getres() */ - WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution); - - if (!use_syscall) { - /* tkr_mono.cycle_last == tkr_raw.cycle_last */ - vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; - vdso_data->raw_time_sec = tk->raw_sec; - vdso_data->raw_time_nsec = tk->tkr_raw.xtime_nsec; - vdso_data->xtime_clock_sec = tk->xtime_sec; - vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; - vdso_data->cs_mono_mult = tk->tkr_mono.mult; - vdso_data->cs_raw_mult = tk->tkr_raw.mult; - /* tkr_mono.shift == tkr_raw.shift */ - vdso_data->cs_shift = tk->tkr_mono.shift; - } - - smp_wmb(); - ++vdso_data->tb_seq_count; -} - -void update_vsyscall_tz(void) -{ - vdso_data->tz_minuteswest = sys_tz.tz_minuteswest; - vdso_data->tz_dsttime = sys_tz.tz_dsttime; + return ret; } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index fa230ff09aa1..dd2514bb1511 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -6,7 +6,12 @@ # Heavily based on the vDSO Makefiles for other archs. # -obj-vdso := gettimeofday.o note.o sigreturn.o +# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before +# the inclusion of generic Makefile. +ARCH_REL_TYPE_ABS := R_AARCH64_JUMP_SLOT|R_AARCH64_GLOB_DAT|R_AARCH64_ABS64 +include $(srctree)/lib/vdso/Makefile + +obj-vdso := vgettimeofday.o note.o sigreturn.o # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg @@ -15,6 +20,31 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ --build-id -n -T +ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 +ccflags-y += -DDISABLE_BRANCH_PROFILING + +VDSO_LDFLAGS := -Bsymbolic + +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os +KBUILD_CFLAGS += $(DISABLE_LTO) +KASAN_SANITIZE := n +UBSAN_SANITIZE := n +OBJECT_FILES_NON_STANDARD := y +KCOV_INSTRUMENT := n + +CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) +endif + +# Clang versions less than 8 do not support -mcmodel=tiny +ifeq ($(CONFIG_CC_IS_CLANG), y) + ifeq ($(shell test $(CONFIG_CLANG_VERSION) -lt 80000; echo $$?),0) + CFLAGS_REMOVE_vgettimeofday.o += -mcmodel=tiny + endif +endif + # Disable gcov profiling for VDSO code GCOV_PROFILE := n @@ -27,7 +57,7 @@ $(obj)/vdso.o : $(obj)/vdso.so # Link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE - $(call if_changed,ld) + $(call if_changed,vdsold_and_vdso_check) # Strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -42,13 +72,9 @@ quiet_cmd_vdsosym = VDSOSYM $@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) -# Assembly rules for the .S files -$(obj-vdso): %.o: %.S FORCE - $(call if_changed_dep,vdsoas) - # Actual build commands -quiet_cmd_vdsoas = VDSOA $@ - cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $< +quiet_cmd_vdsold_and_vdso_check = LD $@ + cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check) # Install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index 80f780f56e0d..e69de29bb2d1 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -1,323 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Userspace implementations of gettimeofday() and friends. - * - * Copyright (C) 2012 ARM Limited - * - * Author: Will Deacon <will.deacon@arm.com> - */ - -#include <linux/linkage.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> - -#define NSEC_PER_SEC_LO16 0xca00 -#define NSEC_PER_SEC_HI16 0x3b9a - -vdso_data .req x6 -seqcnt .req w7 -w_tmp .req w8 -x_tmp .req x8 - -/* - * Conventions for macro arguments: - * - An argument is write-only if its name starts with "res". - * - All other arguments are read-only, unless otherwise specified. - */ - - .macro seqcnt_acquire -9999: ldr seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT] - tbnz seqcnt, #0, 9999b - dmb ishld - .endm - - .macro seqcnt_check fail - dmb ishld - ldr w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT] - cmp w_tmp, seqcnt - b.ne \fail - .endm - - .macro syscall_check fail - ldr w_tmp, [vdso_data, #VDSO_USE_SYSCALL] - cbnz w_tmp, \fail - .endm - - .macro get_nsec_per_sec res - mov \res, #NSEC_PER_SEC_LO16 - movk \res, #NSEC_PER_SEC_HI16, lsl #16 - .endm - - /* - * Returns the clock delta, in nanoseconds left-shifted by the clock - * shift. - */ - .macro get_clock_shifted_nsec res, cycle_last, mult - /* Read the virtual counter. */ - isb - mrs x_tmp, cntvct_el0 - /* Calculate cycle delta and convert to ns. */ - sub \res, x_tmp, \cycle_last - /* We can only guarantee 56 bits of precision. */ - movn x_tmp, #0xff00, lsl #48 - and \res, x_tmp, \res - mul \res, \res, \mult - /* - * Fake address dependency from the value computed from the counter - * register to subsequent data page accesses so that the sequence - * locking also orders the read of the counter. - */ - and x_tmp, \res, xzr - add vdso_data, vdso_data, x_tmp - .endm - - /* - * Returns in res_{sec,nsec} the REALTIME timespec, based on the - * "wall time" (xtime) and the clock_mono delta. - */ - .macro get_ts_realtime res_sec, res_nsec, \ - clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec - add \res_nsec, \clock_nsec, \xtime_nsec - udiv x_tmp, \res_nsec, \nsec_to_sec - add \res_sec, \xtime_sec, x_tmp - msub \res_nsec, x_tmp, \nsec_to_sec, \res_nsec - .endm - - /* - * Returns in res_{sec,nsec} the timespec based on the clock_raw delta, - * used for CLOCK_MONOTONIC_RAW. - */ - .macro get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec - udiv \res_sec, \clock_nsec, \nsec_to_sec - msub \res_nsec, \res_sec, \nsec_to_sec, \clock_nsec - .endm - - /* sec and nsec are modified in place. */ - .macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec - /* Add timespec. */ - add \sec, \sec, \ts_sec - add \nsec, \nsec, \ts_nsec - - /* Normalise the new timespec. */ - cmp \nsec, \nsec_to_sec - b.lt 9999f - sub \nsec, \nsec, \nsec_to_sec - add \sec, \sec, #1 -9999: - cmp \nsec, #0 - b.ge 9998f - add \nsec, \nsec, \nsec_to_sec - sub \sec, \sec, #1 -9998: - .endm - - .macro clock_gettime_return, shift=0 - .if \shift == 1 - lsr x11, x11, x12 - .endif - stp x10, x11, [x1, #TSPEC_TV_SEC] - mov x0, xzr - ret - .endm - - .macro jump_slot jumptable, index, label - .if (. - \jumptable) != 4 * (\index) - .error "Jump slot index mismatch" - .endif - b \label - .endm - - .text - -/* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */ -ENTRY(__kernel_gettimeofday) - .cfi_startproc - adr vdso_data, _vdso_data - /* If tv is NULL, skip to the timezone code. */ - cbz x0, 2f - - /* Compute the time of day. */ -1: seqcnt_acquire - syscall_check fail=4f - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - /* w11 = cs_mono_mult, w12 = cs_shift */ - ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] - ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] - - get_nsec_per_sec res=x9 - lsl x9, x9, x12 - - get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 - seqcnt_check fail=1b - get_ts_realtime res_sec=x10, res_nsec=x11, \ - clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - - /* Convert ns to us. */ - mov x13, #1000 - lsl x13, x13, x12 - udiv x11, x11, x13 - stp x10, x11, [x0, #TVAL_TV_SEC] -2: - /* If tz is NULL, return 0. */ - cbz x1, 3f - ldp w4, w5, [vdso_data, #VDSO_TZ_MINWEST] - stp w4, w5, [x1, #TZ_MINWEST] -3: - mov x0, xzr - ret -4: - /* Syscall fallback. */ - mov x8, #__NR_gettimeofday - svc #0 - ret - .cfi_endproc -ENDPROC(__kernel_gettimeofday) - -#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE - -/* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */ -ENTRY(__kernel_clock_gettime) - .cfi_startproc - cmp w0, #JUMPSLOT_MAX - b.hi syscall - adr vdso_data, _vdso_data - adr x_tmp, jumptable - add x_tmp, x_tmp, w0, uxtw #2 - br x_tmp - - ALIGN -jumptable: - jump_slot jumptable, CLOCK_REALTIME, realtime - jump_slot jumptable, CLOCK_MONOTONIC, monotonic - b syscall - b syscall - jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw - jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse - jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse - - .if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1) - .error "Wrong jumptable size" - .endif - - ALIGN -realtime: - seqcnt_acquire - syscall_check fail=syscall - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - /* w11 = cs_mono_mult, w12 = cs_shift */ - ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] - ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] - - /* All computations are done with left-shifted nsecs. */ - get_nsec_per_sec res=x9 - lsl x9, x9, x12 - - get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 - seqcnt_check fail=realtime - get_ts_realtime res_sec=x10, res_nsec=x11, \ - clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - clock_gettime_return, shift=1 - - ALIGN -monotonic: - seqcnt_acquire - syscall_check fail=syscall - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - /* w11 = cs_mono_mult, w12 = cs_shift */ - ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] - ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] - ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC] - - /* All computations are done with left-shifted nsecs. */ - lsl x4, x4, x12 - get_nsec_per_sec res=x9 - lsl x9, x9, x12 - - get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 - seqcnt_check fail=monotonic - get_ts_realtime res_sec=x10, res_nsec=x11, \ - clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - - add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9 - clock_gettime_return, shift=1 - - ALIGN -monotonic_raw: - seqcnt_acquire - syscall_check fail=syscall - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - /* w11 = cs_raw_mult, w12 = cs_shift */ - ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT] - ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC] - - /* All computations are done with left-shifted nsecs. */ - get_nsec_per_sec res=x9 - lsl x9, x9, x12 - - get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 - seqcnt_check fail=monotonic_raw - get_ts_clock_raw res_sec=x10, res_nsec=x11, \ - clock_nsec=x15, nsec_to_sec=x9 - - add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 - clock_gettime_return, shift=1 - - ALIGN -realtime_coarse: - seqcnt_acquire - ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] - seqcnt_check fail=realtime_coarse - clock_gettime_return - - ALIGN -monotonic_coarse: - seqcnt_acquire - ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] - ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] - seqcnt_check fail=monotonic_coarse - - /* Computations are done in (non-shifted) nsecs. */ - get_nsec_per_sec res=x9 - add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 - clock_gettime_return - - ALIGN -syscall: /* Syscall fallback. */ - mov x8, #__NR_clock_gettime - svc #0 - ret - .cfi_endproc -ENDPROC(__kernel_clock_gettime) - -/* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */ -ENTRY(__kernel_clock_getres) - .cfi_startproc - cmp w0, #CLOCK_REALTIME - ccmp w0, #CLOCK_MONOTONIC, #0x4, ne - ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne - b.ne 1f - - adr vdso_data, _vdso_data - ldr w2, [vdso_data, #CLOCK_REALTIME_RES] - b 2f -1: - cmp w0, #CLOCK_REALTIME_COARSE - ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne - b.ne 4f - ldr x2, 5f -2: - cbz x1, 3f - stp xzr, x2, [x1] - -3: /* res == NULL. */ - mov w0, wzr - ret - -4: /* Syscall fallback. */ - mov x8, #__NR_clock_getres - svc #0 - ret -5: - .quad CLOCK_COARSE_RES - .cfi_endproc -ENDPROC(__kernel_clock_getres) diff --git a/arch/arm64/kernel/vdso/vgettimeofday.c b/arch/arm64/kernel/vdso/vgettimeofday.c new file mode 100644 index 000000000000..747635501a14 --- /dev/null +++ b/arch/arm64/kernel/vdso/vgettimeofday.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ARM64 userspace implementations of gettimeofday() and similar. + * + * Copyright (C) 2018 ARM Limited + * + */ +#include <linux/time.h> +#include <linux/types.h> + +int __kernel_clock_gettime(clockid_t clock, + struct __kernel_timespec *ts) +{ + return __cvdso_clock_gettime(clock, ts); +} + +int __kernel_gettimeofday(struct __kernel_old_timeval *tv, + struct timezone *tz) +{ + return __cvdso_gettimeofday(tv, tz); +} + +int __kernel_clock_getres(clockid_t clock_id, + struct __kernel_timespec *res) +{ + return __cvdso_clock_getres(clock_id, res); +} diff --git a/arch/arm64/kernel/vdso32/.gitignore b/arch/arm64/kernel/vdso32/.gitignore new file mode 100644 index 000000000000..4fea950fa5ed --- /dev/null +++ b/arch/arm64/kernel/vdso32/.gitignore @@ -0,0 +1,2 @@ +vdso.lds +vdso.so.raw diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile new file mode 100644 index 000000000000..1fba0776ed40 --- /dev/null +++ b/arch/arm64/kernel/vdso32/Makefile @@ -0,0 +1,188 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for vdso32 +# + +# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before +# the inclusion of generic Makefile. +ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32 +include $(srctree)/lib/vdso/Makefile + +COMPATCC := $(CROSS_COMPILE_COMPAT)gcc + +# Same as cc-*option, but using COMPATCC instead of CC +cc32-option = $(call try-run,\ + $(COMPATCC) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) +cc32-disable-warning = $(call try-run,\ + $(COMPATCC) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) +cc32-ldoption = $(call try-run,\ + $(COMPATCC) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2)) + +# We cannot use the global flags to compile the vDSO files, the main reason +# being that the 32-bit compiler may be older than the main (64-bit) compiler +# and therefore may not understand flags set using $(cc-option ...). Besides, +# arch-specific options should be taken from the arm Makefile instead of the +# arm64 one. +# As a result we set our own flags here. + +# From top-level Makefile +# NOSTDINC_FLAGS +VDSO_CPPFLAGS := -nostdinc -isystem $(shell $(COMPATCC) -print-file-name=include) +VDSO_CPPFLAGS += $(LINUXINCLUDE) +VDSO_CPPFLAGS += $(KBUILD_CPPFLAGS) + +# Common C and assembly flags +# From top-level Makefile +VDSO_CAFLAGS := $(VDSO_CPPFLAGS) +VDSO_CAFLAGS += $(call cc32-option,-fno-PIE) +ifdef CONFIG_DEBUG_INFO +VDSO_CAFLAGS += -g +endif +ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(COMPATCC)), y) +VDSO_CAFLAGS += -DCC_HAVE_ASM_GOTO +endif + +# From arm Makefile +VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm) +VDSO_CAFLAGS += -mabi=aapcs-linux -mfloat-abi=soft +ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) +VDSO_CAFLAGS += -mbig-endian +else +VDSO_CAFLAGS += -mlittle-endian +endif + +# From arm vDSO Makefile +VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector +VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING + +# Try to compile for ARMv8. If the compiler is too old and doesn't support it, +# fall back to v7. There is no easy way to check for what architecture the code +# is being compiled, so define a macro specifying that (see arch/arm/Makefile). +VDSO_CAFLAGS += $(call cc32-option,-march=armv8-a -D__LINUX_ARM_ARCH__=8,\ + -march=armv7-a -D__LINUX_ARM_ARCH__=7) + +VDSO_CFLAGS := $(VDSO_CAFLAGS) +VDSO_CFLAGS += -DENABLE_COMPAT_VDSO=1 +# KBUILD_CFLAGS from top-level Makefile +VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ + -fno-strict-aliasing -fno-common \ + -Werror-implicit-function-declaration \ + -Wno-format-security \ + -std=gnu89 +VDSO_CFLAGS += -O2 +# Some useful compiler-dependent flags from top-level Makefile +VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,) +VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign) +VDSO_CFLAGS += $(call cc32-option,-fno-strict-overflow) +VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes) +VDSO_CFLAGS += $(call cc32-option,-Werror=date-time) +VDSO_CFLAGS += $(call cc32-option,-Werror=incompatible-pointer-types) + +# The 32-bit compiler does not provide 128-bit integers, which are used in +# some headers that are indirectly included from the vDSO code. +# This hack makes the compiler happy and should trigger a warning/error if +# variables of such type are referenced. +VDSO_CFLAGS += -D__uint128_t='void*' +# Silence some warnings coming from headers that operate on long's +# (on GCC 4.8 or older, there is unfortunately no way to silence this warning) +VDSO_CFLAGS += $(call cc32-disable-warning,shift-count-overflow) +VDSO_CFLAGS += -Wno-int-to-pointer-cast + +VDSO_AFLAGS := $(VDSO_CAFLAGS) +VDSO_AFLAGS += -D__ASSEMBLY__ + +VDSO_LDFLAGS := $(VDSO_CPPFLAGS) +# From arm vDSO Makefile +VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 +VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 +VDSO_LDFLAGS += -nostdlib -shared -mfloat-abi=soft +VDSO_LDFLAGS += -Wl,--hash-style=sysv +VDSO_LDFLAGS += -Wl,--build-id +VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd) + + +# Borrow vdsomunge.c from the arm vDSO +# We have to use a relative path because scripts/Makefile.host prefixes +# $(hostprogs-y) with $(obj) +munge := ../../../arm/vdso/vdsomunge +hostprogs-y := $(munge) + +c-obj-vdso := note.o +c-obj-vdso-gettimeofday := vgettimeofday.o +asm-obj-vdso := sigreturn.o + +ifneq ($(c-gettimeofday-y),) +VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y) +endif + +VDSO_CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os + +# Build rules +targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso.so.dbg vdso.so.raw +c-obj-vdso := $(addprefix $(obj)/, $(c-obj-vdso)) +c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday)) +asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso)) +obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) + +obj-y += vdso.o +extra-y += vdso.lds +CPPFLAGS_vdso.lds += -P -C -U$(ARCH) + +# Force dependency (vdso.s includes vdso.so through incbin) +$(obj)/vdso.o: $(obj)/vdso.so + +include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE + $(call if_changed,vdsosym) + +# Strip rule for vdso.so +$(obj)/vdso.so: OBJCOPYFLAGS := -S +$(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE + $(call if_changed,objcopy) + +$(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE + $(call if_changed,vdsomunge) + +# Link rule for the .so file, .lds has to be first +$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE + $(call if_changed,vdsold_and_vdso_check) + +# Compilation rules for the vDSO sources +$(c-obj-vdso): %.o: %.c FORCE + $(call if_changed_dep,vdsocc) +$(c-obj-vdso-gettimeofday): %.o: %.c FORCE + $(call if_changed_dep,vdsocc_gettimeofday) +$(asm-obj-vdso): %.o: %.S FORCE + $(call if_changed_dep,vdsoas) + +# Actual build commands +quiet_cmd_vdsold_and_vdso_check = LD32 $@ + cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check) + +quiet_cmd_vdsold = LD32 $@ + cmd_vdsold = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \ + -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@ +quiet_cmd_vdsocc = CC32 $@ + cmd_vdsocc = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $< +quiet_cmd_vdsocc_gettimeofday = CC32 $@ + cmd_vdsocc_gettimeofday = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $< +quiet_cmd_vdsoas = AS32 $@ + cmd_vdsoas = $(COMPATCC) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $< + +quiet_cmd_vdsomunge = MUNGE $@ + cmd_vdsomunge = $(obj)/$(munge) $< $@ + +# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO) +gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh +quiet_cmd_vdsosym = VDSOSYM $@ +# The AArch64 nm should be able to read an AArch32 binary + cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ + +# Install commands for the unstripped file +quiet_cmd_vdso_install = INSTALL $@ + cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so + +vdso.so: $(obj)/vdso.so.dbg + @mkdir -p $(MODLIB)/vdso + $(call cmd,vdso_install) + +vdso_install: vdso.so diff --git a/arch/arm64/kernel/vdso32/note.c b/arch/arm64/kernel/vdso32/note.c new file mode 100644 index 000000000000..eff5bf9efb8b --- /dev/null +++ b/arch/arm64/kernel/vdso32/note.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2012-2018 ARM Limited + * + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/uts.h> +#include <linux/version.h> +#include <linux/elfnote.h> +#include <linux/build-salt.h> + +ELFNOTE32("Linux", 0, LINUX_VERSION_CODE); +BUILD_SALT; diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S new file mode 100644 index 000000000000..1a81277c2d09 --- /dev/null +++ b/arch/arm64/kernel/vdso32/sigreturn.S @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file provides both A32 and T32 versions, in accordance with the + * arm sigreturn code. + * + * Copyright (C) 2018 ARM Limited + */ + +#include <linux/linkage.h> +#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 + .fnstart + .save {r0-r15} + .pad #COMPAT_SIGFRAME_REGS_OFFSET + nop +ARM_ENTRY(__kernel_sigreturn_arm) + mov r7, #__NR_compat_sigreturn + svc #0 + .fnend +ARM_ENDPROC(__kernel_sigreturn_arm) + + .fnstart + .save {r0-r15} + .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET + nop +ARM_ENTRY(__kernel_rt_sigreturn_arm) + mov r7, #__NR_compat_rt_sigreturn + svc #0 + .fnend +ARM_ENDPROC(__kernel_rt_sigreturn_arm) + + .thumb + .fnstart + .save {r0-r15} + .pad #COMPAT_SIGFRAME_REGS_OFFSET + nop +ARM_ENTRY(__kernel_sigreturn_thumb) + mov r7, #__NR_compat_sigreturn + svc #0 + .fnend +ARM_ENDPROC(__kernel_sigreturn_thumb) + + .fnstart + .save {r0-r15} + .pad #COMPAT_RT_SIGFRAME_REGS_OFFSET + nop +ARM_ENTRY(__kernel_rt_sigreturn_thumb) + mov r7, #__NR_compat_rt_sigreturn + svc #0 + .fnend +ARM_ENDPROC(__kernel_rt_sigreturn_thumb) diff --git a/arch/arm64/kernel/vdso32/vdso.S b/arch/arm64/kernel/vdso32/vdso.S new file mode 100644 index 000000000000..e72ac7bc4c04 --- /dev/null +++ b/arch/arm64/kernel/vdso32/vdso.S @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2012 ARM Limited + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <linux/const.h> +#include <asm/page.h> + + .globl vdso32_start, vdso32_end + .section .rodata + .balign PAGE_SIZE +vdso32_start: + .incbin "arch/arm64/kernel/vdso32/vdso.so" + .balign PAGE_SIZE +vdso32_end: + + .previous diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S new file mode 100644 index 000000000000..a3944927eaeb --- /dev/null +++ b/arch/arm64/kernel/vdso32/vdso.lds.S @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Adapted from arm64 version. + * + * GNU linker script for the VDSO library. + * Heavily based on the vDSO linker scripts for other archs. + * + * Copyright (C) 2012-2018 ARM Limited + */ + +#include <linux/const.h> +#include <asm/page.h> +#include <asm/vdso.h> + +OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm") +OUTPUT_ARCH(arm) + +SECTIONS +{ + PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE); + . = VDSO_LBASE + SIZEOF_HEADERS; + + .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .note : { *(.note.*) } :text :note + + .dynamic : { *(.dynamic) } :text :dynamic + + .rodata : { *(.rodata*) } :text + + .text : { *(.text*) } :text =0xe7f001f2 + + .got : { *(.got) } + .rel.plt : { *(.rel.plt) } + + /DISCARD/ : { + *(.note.GNU-stack) + *(.data .data.* .gnu.linkonce.d.* .sdata*) + *(.bss .sbss .dynbss .dynsbss) + } +} + +/* + * We must supply the ELF program headers explicitly to get just one + * PT_LOAD segment, and set the flags explicitly to make segments read-only. + */ +PHDRS +{ + text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + note PT_NOTE FLAGS(4); /* PF_R */ +} + +VERSION +{ + LINUX_2.6 { + global: + __vdso_clock_gettime; + __vdso_gettimeofday; + __vdso_clock_getres; + __kernel_sigreturn_arm; + __kernel_sigreturn_thumb; + __kernel_rt_sigreturn_arm; + __kernel_rt_sigreturn_thumb; + __vdso_clock_gettime64; + local: *; + }; +} + +/* + * Make the sigreturn code visible to the kernel. + */ +VDSO_compat_sigreturn_arm = __kernel_sigreturn_arm; +VDSO_compat_sigreturn_thumb = __kernel_sigreturn_thumb; +VDSO_compat_rt_sigreturn_arm = __kernel_rt_sigreturn_arm; +VDSO_compat_rt_sigreturn_thumb = __kernel_rt_sigreturn_thumb; diff --git a/arch/arm64/kernel/vdso32/vgettimeofday.c b/arch/arm64/kernel/vdso32/vgettimeofday.c new file mode 100644 index 000000000000..54fc1c2ce93f --- /dev/null +++ b/arch/arm64/kernel/vdso32/vgettimeofday.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ARM64 compat userspace implementations of gettimeofday() and similar. + * + * Copyright (C) 2018 ARM Limited + * + */ +#include <linux/time.h> +#include <linux/types.h> + +int __vdso_clock_gettime(clockid_t clock, + struct old_timespec32 *ts) +{ + /* The checks below are required for ABI consistency with arm */ + if ((u32)ts >= TASK_SIZE_32) + return -EFAULT; + + return __cvdso_clock_gettime32(clock, ts); +} + +int __vdso_clock_gettime64(clockid_t clock, + struct __kernel_timespec *ts) +{ + /* The checks below are required for ABI consistency with arm */ + if ((u32)ts >= TASK_SIZE_32) + return -EFAULT; + + return __cvdso_clock_gettime(clock, ts); +} + +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, + struct timezone *tz) +{ + return __cvdso_gettimeofday(tv, tz); +} + +int __vdso_clock_getres(clockid_t clock_id, + struct old_timespec32 *res) +{ + /* The checks below are required for ABI consistency with arm */ + if ((u32)res >= TASK_SIZE_32) + return -EFAULT; + + return __cvdso_clock_getres_time32(clock_id, res); +} + +/* Avoid unresolved references emitted by GCC */ + +void __aeabi_unwind_cpp_pr0(void) +{ +} + +void __aeabi_unwind_cpp_pr1(void) +{ +} + +void __aeabi_unwind_cpp_pr2(void) +{ +} diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 7fa008374907..aa76f7259668 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -200,6 +200,15 @@ SECTIONS __rela_offset = ABSOLUTE(ADDR(.rela.dyn) - KIMAGE_VADDR); __rela_size = SIZEOF(.rela.dyn); +#ifdef CONFIG_RELR + .relr.dyn : ALIGN(8) { + *(.relr.dyn) + } + + __relr_offset = ABSOLUTE(ADDR(.relr.dyn) - KIMAGE_VADDR); + __relr_size = SIZEOF(.relr.dyn); +#endif + . = ALIGN(SEGMENT_ALIGN); __initdata_end = .; __init_end = .; @@ -245,6 +254,8 @@ SECTIONS HEAD_SYMBOLS } +#include "image-vars.h" + /* * The HYP init code and ID map text can't be longer than a page each, * and should not cross a page boundary. |