diff options
author | Andrey Zhizhikin <andrey.zhizhikin@leica-geosystems.com> | 2020-10-01 16:20:39 +0000 |
---|---|---|
committer | Andrey Zhizhikin <andrey.zhizhikin@leica-geosystems.com> | 2020-10-01 16:20:39 +0000 |
commit | 84f1815a7d440786a7eee447a173864229ca8ef4 (patch) | |
tree | 037fa9b325765e44712dab8b2cb7067daed2e8f7 /arch | |
parent | 11f569dee0a848f60d01aa92d54334802d3d5c14 (diff) | |
parent | a9518c1aec5b6a8e1a04bbd54e6ba9725ef0db4c (diff) |
Merge tag 'v5.4.69' into 5.4-2.1.x-imx
This is the 5.4.69 stable release
Signed-off-by: Andrey Zhizhikin <andrey.zhizhikin@leica-geosystems.com>
Diffstat (limited to 'arch')
49 files changed, 514 insertions, 150 deletions
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index cbde9fa15792..c1747fcb86d3 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -204,7 +204,7 @@ static inline int kvm_vcpu_dabt_get_rd(struct kvm_vcpu *vcpu) return (kvm_vcpu_get_hsr(vcpu) & HSR_SRT_MASK) >> HSR_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_DABT_S1PTW; } @@ -236,16 +236,21 @@ static inline bool kvm_vcpu_trap_il_is32bit(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_IL; } -static inline u8 kvm_vcpu_trap_get_class(struct kvm_vcpu *vcpu) +static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) >> HSR_EC_SHIFT; } -static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) { return kvm_vcpu_trap_get_class(vcpu) == HSR_EC_IABT; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & HSR_FSC; diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index a082f6e4f0f4..76ea4178a55c 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -116,6 +116,8 @@ static int save_trace(struct stackframe *frame, void *d) return 0; regs = (struct pt_regs *)frame->sp; + if ((unsigned long)®s[1] > ALIGN(frame->sp, THREAD_SIZE)) + return 0; trace->entries[trace->nr_entries++] = regs->ARM_pc; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index c053abd1fb53..97a512551b21 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -64,14 +64,16 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long); void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame) { + unsigned long end = frame + 4 + sizeof(struct pt_regs); + #ifdef CONFIG_KALLSYMS printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from); #else printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from); #endif - if (in_entry_text(from)) - dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs)); + if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE)) + dump_mem("", "Exception stack", frame + 4, end); } void dump_backtrace_stm(u32 *stack, u32 instruction) diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c index 532a3e4b98c6..090a8aafb25e 100644 --- a/arch/arm/mach-omap2/cpuidle34xx.c +++ b/arch/arm/mach-omap2/cpuidle34xx.c @@ -109,6 +109,7 @@ static int omap3_enter_idle(struct cpuidle_device *dev, int index) { struct omap3_idle_statedata *cx = &omap3_idle_data[index]; + int error; if (omap_irq_pending() || need_resched()) goto return_sleep_time; @@ -125,8 +126,11 @@ static int omap3_enter_idle(struct cpuidle_device *dev, * Call idle CPU PM enter notifier chain so that * VFP context is saved. */ - if (cx->mpu_state == PWRDM_POWER_OFF) - cpu_pm_enter(); + if (cx->mpu_state == PWRDM_POWER_OFF) { + error = cpu_pm_enter(); + if (error) + goto out_clkdm_set; + } /* Execute ARM wfi */ omap_sram_idle(); @@ -139,6 +143,7 @@ static int omap3_enter_idle(struct cpuidle_device *dev, pwrdm_read_prev_pwrst(mpu_pd) == PWRDM_POWER_OFF) cpu_pm_exit(); +out_clkdm_set: /* Re-allow idle for C1 */ if (cx->flags & OMAP_CPUIDLE_CX_NO_CLKDM_IDLE) clkdm_allow_idle(mpu_pd->pwrdm_clkdms[0]); diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index fe75d4fa6073..6f5f89711f25 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -122,6 +122,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, { struct idle_statedata *cx = state_ptr + index; u32 mpuss_can_lose_context = 0; + int error; /* * CPU0 has to wait and stay ON until CPU1 is OFF state. @@ -159,7 +160,9 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, * Call idle CPU PM enter notifier chain so that * VFP and per CPU interrupt context is saved. */ - cpu_pm_enter(); + error = cpu_pm_enter(); + if (error) + goto cpu_pm_out; if (dev->cpu == 0) { pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); @@ -169,13 +172,17 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, * Call idle CPU cluster PM enter notifier chain * to save GIC and wakeupgen context. */ - if (mpuss_can_lose_context) - cpu_cluster_pm_enter(); + if (mpuss_can_lose_context) { + error = cpu_cluster_pm_enter(); + if (error) + goto cpu_cluster_pm_out; + } } omap4_enter_lowpower(dev->cpu, cx->cpu_state); cpu_done[dev->cpu] = true; +cpu_cluster_pm_out: /* Wakeup CPU1 only if it is not offlined */ if (dev->cpu == 0 && cpumask_test_cpu(1, cpu_online_mask)) { @@ -198,18 +205,19 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, } /* - * Call idle CPU PM exit notifier chain to restore - * VFP and per CPU IRQ context. - */ - cpu_pm_exit(); - - /* * Call idle CPU cluster PM exit notifier chain * to restore GIC and wakeupgen context. */ if (dev->cpu == 0 && mpuss_can_lose_context) cpu_cluster_pm_exit(); + /* + * Call idle CPU PM exit notifier chain to restore + * VFP and per CPU IRQ context. + */ + cpu_pm_exit(); + +cpu_pm_out: tick_broadcast_exit(); fail: diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index 54254fc92c2e..fa66534a7ae2 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -194,6 +194,7 @@ void omap_sram_idle(void) int per_next_state = PWRDM_POWER_ON; int core_next_state = PWRDM_POWER_ON; u32 sdrc_pwr = 0; + int error; mpu_next_state = pwrdm_read_next_pwrst(mpu_pwrdm); switch (mpu_next_state) { @@ -222,8 +223,11 @@ void omap_sram_idle(void) pwrdm_pre_transition(NULL); /* PER */ - if (per_next_state == PWRDM_POWER_OFF) - cpu_cluster_pm_enter(); + if (per_next_state == PWRDM_POWER_OFF) { + error = cpu_cluster_pm_enter(); + if (error) + return; + } /* CORE */ if (core_next_state < PWRDM_POWER_ON) { diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index f47081b40523..f65ff6b90f4a 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -299,7 +299,7 @@ static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } -static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); } @@ -307,7 +307,7 @@ static inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) static inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || - kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ + kvm_vcpu_abt_iss1tw(vcpu); /* AF/DBM update */ } static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) @@ -336,6 +336,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW; } +static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); +} + static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; @@ -373,6 +378,9 @@ static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { + if (kvm_vcpu_abt_iss1tw(vcpu)) + return true; + if (kvm_vcpu_trap_is_iabt(vcpu)) return false; diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 788ae971f11c..25a73aab438f 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -15,6 +15,7 @@ extern char __hyp_text_start[], __hyp_text_end[]; extern char __idmap_text_start[], __idmap_text_end[]; extern char __initdata_begin[], __initdata_end[]; extern char __inittext_begin[], __inittext_end[]; +extern char __exittext_begin[], __exittext_end[]; extern char __irqentry_text_start[], __irqentry_text_end[]; extern char __mmuoff_data_start[], __mmuoff_data_end[]; extern char __entry_tramp_text_start[], __entry_tramp_text_end[]; diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a100483b47c4..46ec402e97ed 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/irq_work.h> #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/smp.h> @@ -269,6 +270,7 @@ pgprot_t __acpi_get_mem_attribute(phys_addr_t addr) int apei_claim_sea(struct pt_regs *regs) { int err = -ENOENT; + bool return_to_irqs_enabled; unsigned long current_flags; if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES)) @@ -276,6 +278,12 @@ int apei_claim_sea(struct pt_regs *regs) current_flags = local_daif_save_flags(); + /* current_flags isn't useful here as daif doesn't tell us about pNMI */ + return_to_irqs_enabled = !irqs_disabled_flags(arch_local_save_flags()); + + if (regs) + return_to_irqs_enabled = interrupts_enabled(regs); + /* * SEA can interrupt SError, mask it and describe this as an NMI so * that APEI defers the handling. @@ -284,6 +292,23 @@ int apei_claim_sea(struct pt_regs *regs) nmi_enter(); err = ghes_notify_sea(); nmi_exit(); + + /* + * APEI NMI-like notifications are deferred to irq_work. Unless + * we interrupted irqs-masked code, we can do that now. + */ + if (!err) { + if (return_to_irqs_enabled) { + local_daif_restore(DAIF_PROCCTX_NOIRQ); + __irq_enter(); + irq_work_run(); + __irq_exit(); + } else { + pr_warn_ratelimited("APEI work queued but not completed"); + err = -EINPROGRESS; + } + } + local_daif_restore(current_flags); return err; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 933f7a2eab59..5d790d45e737 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -160,11 +160,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), - /* Linux doesn't care about the EL3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), ARM64_FTR_END, }; @@ -320,7 +319,7 @@ static const struct arm64_ftr_bits ftr_id_pfr0[] = { }; static const struct arm64_ftr_bits ftr_id_dfr0[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), + /* [31:28] TraceFilt */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf), /* PerfMon */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 0), @@ -737,9 +736,6 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2); - /* - * EL3 is not our concern. - */ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index a612da533ea2..53bcf5386907 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -21,6 +21,7 @@ #include <asm/fixmap.h> #include <asm/insn.h> #include <asm/kprobes.h> +#include <asm/sections.h> #define AARCH64_INSN_SF_BIT BIT(31) #define AARCH64_INSN_N_BIT BIT(22) @@ -78,16 +79,29 @@ bool aarch64_insn_is_branch_imm(u32 insn) static DEFINE_RAW_SPINLOCK(patch_lock); +static bool is_exit_text(unsigned long addr) +{ + /* discarded with init text/data */ + return system_state < SYSTEM_RUNNING && + addr >= (unsigned long)__exittext_begin && + addr < (unsigned long)__exittext_end; +} + +static bool is_image_text(unsigned long addr) +{ + return core_kernel_text(addr) || is_exit_text(addr); +} + static void __kprobes *patch_map(void *addr, int fixmap) { unsigned long uintaddr = (uintptr_t) addr; - bool module = !core_kernel_text(uintaddr); + bool image = is_image_text(uintaddr); struct page *page; - if (module && IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) - page = vmalloc_to_page(addr); - else if (!module) + if (image) page = phys_to_page(__pa_symbol(addr)); + else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + page = vmalloc_to_page(addr); else return addr; diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 4f77de8ce138..0bab37b1acbe 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -170,9 +170,12 @@ SECTIONS __inittext_begin = .; INIT_TEXT_SECTION(8) + + __exittext_begin = .; .exit.text : { ARM_EXIT_KEEP(EXIT_TEXT) } + __exittext_end = .; . = ALIGN(4); .altinstructions : { diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 65660b614474..84964983198e 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -496,7 +496,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_dabt_isextabt(vcpu) && - !kvm_vcpu_dabt_iss1tw(vcpu); + !kvm_vcpu_abt_iss1tw(vcpu); if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index d26e6cd28953..2a7339aeb1ad 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -654,11 +654,13 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) inf = esr_to_fault_info(esr); - /* - * Return value ignored as we rely on signal merging. - * Future patches will make this more robust. - */ - apei_claim_sea(regs); + if (user_mode(regs) && apei_claim_sea(regs) == 0) { + /* + * APEI claimed this as a firmware-first notification. + * Some processing deferred to task_work before ret_to_user(). + */ + return 0; + } if (esr & ESR_ELx_FnV) siaddr = NULL; diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index e63eb5f06999..f31890078197 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -264,6 +264,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll) { int tmp = Q40_RTC_CTRL; + pll->pll_ctrl = 0; pll->pll_value = tmp & Q40_RTC_PLL_MASK; if (tmp & Q40_RTC_PLL_SIGN) pll->pll_value = -pll->pll_value; diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 7bbb66760a07..1809c408736b 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_34K: case CPU_1004K: case CPU_74K: + case CPU_1074K: case CPU_M14KC: case CPU_M14KEC: case CPU_INTERAPTIV: diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 635fb154b33f..a3633560493b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -150,4 +150,7 @@ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 021a5b0a9123..4b4c7d26ff6c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,6 +19,7 @@ CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) +CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code @@ -36,7 +37,6 @@ KASAN_SANITIZE_btext.o := n ifdef CONFIG_KASAN CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING -CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index bc8a551013be..c35069294ecf 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -503,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc = 1; if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { + if (pe->check_count == EEH_MAX_FAILS) { dn = pci_device_to_OF_node(dev); if (dn) location = of_get_property(dn, "ibm,loc-code", diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 014ff0701f24..9432fc6af28a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -510,11 +510,11 @@ out: #ifdef CONFIG_PPC_BOOK3S_64 BUG_ON(get_paca()->in_nmi == 0); if (get_paca()->in_nmi > 1) - nmi_panic(regs, "Unrecoverable nested System Reset"); + die("Unrecoverable nested System Reset", regs, SIGABRT); #endif /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable System Reset"); + die("Unrecoverable System Reset", regs, SIGABRT); if (saved_hsrrs) { mtspr(SPRN_HSRR0, hsrr0); @@ -858,7 +858,7 @@ void machine_check_exception(struct pt_regs *regs) /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable Machine check"); + die("Unrecoverable Machine check", regs, SIGBUS); return; diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index da8375437d16..9d7344835469 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -1104,6 +1104,11 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm, kvm->arch.lpid); gpa += PAGE_SIZE; } + /* + * Increase the mmu notifier sequence number to prevent any page + * fault that read the memslot earlier from writing a PTE. + */ + kvm->mmu_notifier_seq++; spin_unlock(&kvm->mmu_lock); } diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 0db937497169..cc90b8b82329 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -3,6 +3,8 @@ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/kvm_ppc.h> @@ -44,7 +46,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -105,7 +118,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -140,7 +154,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST; - case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -176,7 +191,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; - case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -208,6 +224,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 217246279dfa..fad931f224ef 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -23,7 +23,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -73,7 +84,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */ diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index 56cc84520577..ef164851738b 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -121,24 +121,6 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, goto free_exit; } - pageshift = PAGE_SHIFT; - for (i = 0; i < entries; ++i) { - struct page *page = mem->hpages[i]; - - /* - * Allow to use larger than 64k IOMMU pages. Only do that - * if we are backed by hugetlb. - */ - if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) - pageshift = page_shift(compound_head(page)); - mem->pageshift = min(mem->pageshift, pageshift); - /* - * We don't need struct page reference any more, switch - * to physical address. - */ - mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; - } - good_exit: atomic64_set(&mem->mapped, 1); mem->used = 1; @@ -158,6 +140,27 @@ good_exit: } } + if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) { + /* + * Allow to use larger than 64k IOMMU pages. Only do that + * if we are backed by hugetlb. Skip device memory as it is not + * backed with page structs. + */ + pageshift = PAGE_SHIFT; + for (i = 0; i < entries; ++i) { + struct page *page = mem->hpages[i]; + + if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) + pageshift = page_shift(compound_head(page)); + mem->pageshift = min(mem->pageshift, pageshift); + /* + * We don't need struct page reference any more, switch + * to physical address. + */ + mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; + } + } + list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); mutex_unlock(&mem_list_mutex); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index cb50a9e1fd2d..eb82dda884e5 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -44,6 +44,16 @@ static DEFINE_PER_CPU(u64 *, trace_imc_mem); static struct imc_pmu_ref *trace_imc_refc; static int trace_imc_mem_size; +/* + * Global data structure used to avoid races between thread, + * core and trace-imc + */ +static struct imc_pmu_ref imc_global_refc = { + .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .id = 0, + .refc = 0, +}; + static struct imc_pmu *imc_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct imc_pmu, pmu); @@ -698,6 +708,16 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) return -EINVAL; ref->refc = 0; + /* + * Reduce the global reference count, if this is the + * last cpu in this core and core-imc event running + * in this cpu. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_CORE) + imc_global_refc.refc--; + + mutex_unlock(&imc_global_refc.lock); } return 0; } @@ -710,6 +730,23 @@ static int core_imc_pmu_cpumask_init(void) ppc_core_imc_cpu_offline); } +static void reset_global_refc(struct perf_event *event) +{ + mutex_lock(&imc_global_refc.lock); + imc_global_refc.refc--; + + /* + * If no other thread is running any + * event for this domain(thread/core/trace), + * set the global id to zero. + */ + if (imc_global_refc.refc <= 0) { + imc_global_refc.refc = 0; + imc_global_refc.id = 0; + } + mutex_unlock(&imc_global_refc.lock); +} + static void core_imc_counters_release(struct perf_event *event) { int rc, core_id; @@ -759,6 +796,8 @@ static void core_imc_counters_release(struct perf_event *event) ref->refc = 0; } mutex_unlock(&ref->lock); + + reset_global_refc(event); } static int core_imc_event_init(struct perf_event *event) @@ -819,6 +858,29 @@ static int core_imc_event_init(struct perf_event *event) ++ref->refc; mutex_unlock(&ref->lock); + /* + * Since the system can run either in accumulation or trace-mode + * of IMC at a time, core-imc events are allowed only if no other + * trace/thread imc events are enabled/monitored. + * + * Take the global lock, and check the refc.id + * to know whether any other trace/thread imc + * events are running. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { + /* + * No other trace/thread imc events are running in + * the system, so set the refc.id to core-imc. + */ + imc_global_refc.id = IMC_DOMAIN_CORE; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; return 0; @@ -877,7 +939,23 @@ static int ppc_thread_imc_cpu_online(unsigned int cpu) static int ppc_thread_imc_cpu_offline(unsigned int cpu) { - mtspr(SPRN_LDBAR, 0); + /* + * Set the bit 0 of LDBAR to zero. + * + * If bit 0 of LDBAR is unset, it will stop posting + * the counter data to memory. + * For thread-imc, bit 0 of LDBAR will be set to 1 in the + * event_add function. So reset this bit here, to stop the updates + * to memory in the cpu_offline path. + */ + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); + + /* Reduce the refc if thread-imc event running on this cpu */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_THREAD) + imc_global_refc.refc--; + mutex_unlock(&imc_global_refc.lock); + return 0; } @@ -916,7 +994,22 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; + mutex_lock(&imc_global_refc.lock); + /* + * Check if any other trace/core imc events are running in the + * system, if not set the global id to thread-imc. + */ + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_THREAD) { + imc_global_refc.id = IMC_DOMAIN_THREAD; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->pmu->task_ctx_nr = perf_sw_context; + event->destroy = reset_global_refc; return 0; } @@ -1063,10 +1156,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) int core_id; struct imc_pmu_ref *ref; - mtspr(SPRN_LDBAR, 0); - core_id = smp_processor_id() / threads_per_core; ref = &core_imc_refc[core_id]; + if (!ref) { + pr_debug("imc: Failed to get event reference count\n"); + return; + } mutex_lock(&ref->lock); ref->refc--; @@ -1082,6 +1177,10 @@ static void thread_imc_event_del(struct perf_event *event, int flags) ref->refc = 0; } mutex_unlock(&ref->lock); + + /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); + /* * Take a snapshot and calculate the delta and update * the event counter values. @@ -1133,7 +1232,18 @@ static int ppc_trace_imc_cpu_online(unsigned int cpu) static int ppc_trace_imc_cpu_offline(unsigned int cpu) { - mtspr(SPRN_LDBAR, 0); + /* + * No need to set bit 0 of LDBAR to zero, as + * it is set to zero for imc trace-mode + * + * Reduce the refc if any trace-imc event running + * on this cpu. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_TRACE) + imc_global_refc.refc--; + mutex_unlock(&imc_global_refc.lock); + return 0; } @@ -1226,15 +1336,14 @@ static int trace_imc_event_add(struct perf_event *event, int flags) local_mem = get_trace_imc_event_base_addr(); ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE; - if (core_imc_refc) - ref = &core_imc_refc[core_id]; + /* trace-imc reference count */ + if (trace_imc_refc) + ref = &trace_imc_refc[core_id]; if (!ref) { - /* If core-imc is not enabled, use trace-imc reference count */ - if (trace_imc_refc) - ref = &trace_imc_refc[core_id]; - if (!ref) - return -EINVAL; + pr_debug("imc: Failed to get the event reference count\n"); + return -EINVAL; } + mtspr(SPRN_LDBAR, ldbar_value); mutex_lock(&ref->lock); if (ref->refc == 0) { @@ -1242,13 +1351,11 @@ static int trace_imc_event_add(struct perf_event *event, int flags) get_hard_smp_processor_id(smp_processor_id()))) { mutex_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); - mtspr(SPRN_LDBAR, 0); return -EINVAL; } } ++ref->refc; mutex_unlock(&ref->lock); - return 0; } @@ -1274,16 +1381,13 @@ static void trace_imc_event_del(struct perf_event *event, int flags) int core_id = smp_processor_id() / threads_per_core; struct imc_pmu_ref *ref = NULL; - if (core_imc_refc) - ref = &core_imc_refc[core_id]; + if (trace_imc_refc) + ref = &trace_imc_refc[core_id]; if (!ref) { - /* If core-imc is not enabled, use trace-imc reference count */ - if (trace_imc_refc) - ref = &trace_imc_refc[core_id]; - if (!ref) - return; + pr_debug("imc: Failed to get event reference count\n"); + return; } - mtspr(SPRN_LDBAR, 0); + mutex_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { @@ -1297,6 +1401,7 @@ static void trace_imc_event_del(struct perf_event *event, int flags) ref->refc = 0; } mutex_unlock(&ref->lock); + trace_imc_event_stop(event, flags); } @@ -1314,10 +1419,30 @@ static int trace_imc_event_init(struct perf_event *event) if (event->attr.sample_period == 0) return -ENOENT; + /* + * Take the global lock, and make sure + * no other thread is running any core/thread imc + * events + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { + /* + * No core/thread imc events are running in the + * system, so set the refc.id to trace-imc. + */ + imc_global_refc.id = IMC_DOMAIN_TRACE; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->hw.idx = -1; target = event->hw.target; event->pmu->task_ctx_nr = perf_hw_context; + event->destroy = reset_global_refc; return 0; } @@ -1429,10 +1554,10 @@ static void cleanup_all_core_imc_memory(void) static void thread_imc_ldbar_disable(void *dummy) { /* - * By Zeroing LDBAR, we disable thread-imc - * updates. + * By setting 0th bit of LDBAR to zero, we disable thread-imc + * updates to memory. */ - mtspr(SPRN_LDBAR, 0); + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); } void thread_imc_disable(void) diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index c6dcc5291f97..02fbc175142e 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -63,4 +63,11 @@ do { \ * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. */ #define MCOUNT_INSN_SIZE 8 + +#ifndef __ASSEMBLY__ +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop +#endif + #endif diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index c40fdcdeb950..291c579e1245 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -88,6 +88,25 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return __ftrace_modify_call(rec->ip, addr, false); } + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefor doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + int out; + + ftrace_arch_code_modify_prepare(); + out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ftrace_arch_code_modify_post_process(); + + return out; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { int ret = __ftrace_modify_call((unsigned long)&ftrace_call, diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 34a655ad7123..5ce586948d92 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1247,26 +1247,46 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address) #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address) #define pgd_offset_k(address) pgd_offset(&init_mm, address) -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) - return (p4d_t *) pgd_deref(*pgd) + p4d_index(address); - return (p4d_t *) pgd; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) + return (p4d_t *) pgd_deref(pgd) + p4d_index(address); + return (p4d_t *) pgdp; } +#define p4d_offset_lockless p4d_offset_lockless -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address) { - if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) - return (pud_t *) p4d_deref(*p4d) + pud_index(address); - return (pud_t *) p4d; + return p4d_offset_lockless(pgdp, *pgdp, address); } -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address) { - if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) - return (pmd_t *) pud_deref(*pud) + pmd_index(address); - return (pmd_t *) pud; + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) + return (pud_t *) p4d_deref(p4d) + pud_index(address); + return (pud_t *) p4dp; } +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address) +{ + return pud_offset_lockless(p4dp, *p4dp, address); +} +#define pud_offset pud_offset + +static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address) +{ + if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) + return (pmd_t *) pud_deref(pud) + pmd_index(address); + return (pmd_t *) pudp; +} +#define pmd_offset_lockless pmd_offset_lockless + +static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address) +{ + return pmd_offset_lockless(pudp, *pudp, address); +} +#define pmd_offset pmd_offset static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address) { diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index 0ae4bbf7779c..3679d224fd3c 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -111,4 +111,15 @@ struct stack_frame { r2; \ }) +#define CALL_ON_STACK_NORETURN(fn, stack) \ +({ \ + asm volatile( \ + " la 15,0(%[_stack])\n" \ + " xc %[_bc](8,15),%[_bc](15)\n" \ + " brasl 14,%[_fn]\n" \ + ::[_bc] "i" (offsetof(struct stack_frame, back_chain)), \ + [_stack] "a" (stack), [_fn] "X" (fn)); \ + BUG(); \ +}) + #endif /* _ASM_S390_STACKTRACE_H */ diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 8371855042dc..da550cb8b31b 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -294,11 +294,6 @@ static irqreturn_t do_ext_interrupt(int irq, void *dummy) return IRQ_HANDLED; } -static struct irqaction external_interrupt = { - .name = "EXT", - .handler = do_ext_interrupt, -}; - void __init init_ext_interrupts(void) { int idx; @@ -308,7 +303,8 @@ void __init init_ext_interrupts(void) irq_set_chip_and_handler(EXT_INTERRUPT, &dummy_irq_chip, handle_percpu_irq); - setup_irq(EXT_INTERRUPT, &external_interrupt); + if (request_irq(EXT_INTERRUPT, do_ext_interrupt, 0, "EXT", NULL)) + panic("Failed to register EXT interrupt\n"); } static DEFINE_SPINLOCK(irq_subclass_lock); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 229e1e2f8253..996e447ead3a 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1429,8 +1429,8 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK; + te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | + SDB_TE_ALERT_REQ_MASK); te->overflow = 0; } /* Save the position of empty SDBs */ @@ -1477,8 +1477,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, te = aux_sdb_trailer(aux, alert_index); do { orig_flags = te->flags; - orig_overflow = te->overflow; - *overflow = orig_overflow; + *overflow = orig_overflow = te->overflow; if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { /* * SDB is already set by hardware. @@ -1712,7 +1711,7 @@ static void *aux_buffer_setup(struct perf_event *event, void **pages, } /* Allocate aux_buffer struct for the event */ - aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL); + aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL); if (!aux) goto no_aux; sfb = &aux->sfb; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 07b2b61a0289..61c02a162d37 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -356,7 +356,6 @@ early_initcall(async_stack_realloc); void __init arch_call_rest_init(void) { - struct stack_frame *frame; unsigned long stack; stack = stack_alloc(); @@ -369,13 +368,7 @@ void __init arch_call_rest_init(void) set_task_stack_end_magic(current); stack += STACK_INIT_OFFSET; S390_lowcore.kernel_stack = stack; - frame = (struct stack_frame *) stack; - memset(frame, 0, sizeof(*frame)); - /* Branch to rest_init on the new stack, never returns */ - asm volatile( - " la 15,0(%[_frame])\n" - " jg rest_init\n" - : : [_frame] "a" (frame)); + CALL_ON_STACK_NORETURN(rest_init, stack); } static void __init setup_lowcore_dat_off(void) @@ -634,7 +627,7 @@ static struct notifier_block kdump_mem_nb = { /* * Make sure that the area behind memory_end is protected */ -static void reserve_memory_end(void) +static void __init reserve_memory_end(void) { if (memory_end_set) memblock_reserve(memory_end, ULONG_MAX); @@ -643,7 +636,7 @@ static void reserve_memory_end(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void reserve_oldmem(void) +static void __init reserve_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) @@ -655,7 +648,7 @@ static void reserve_oldmem(void) /* * Make sure that oldmem, where the dump is stored, is protected */ -static void remove_oldmem(void) +static void __init remove_oldmem(void) { #ifdef CONFIG_CRASH_DUMP if (OLDMEM_BASE) diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 66bf050d785c..ad426cc656e5 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -878,7 +878,7 @@ static void __no_sanitize_address smp_start_secondary(void *cpuvoid) S390_lowcore.restart_source = -1UL; __ctl_load(S390_lowcore.cregs_save_area, 0, 15); __load_psw_mask(PSW_KERNEL_BITS | PSW_MASK_DAT); - CALL_ON_STACK(smp_init_secondary, S390_lowcore.kernel_stack, 0); + CALL_ON_STACK_NORETURN(smp_init_secondary, S390_lowcore.kernel_stack); } /* Upping and downing of CPUs */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index ef5638f641f2..88eadd08ad70 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -10,4 +10,10 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params); void crash_smp_send_stop(void); +#ifdef CONFIG_KEXEC_CORE +void __init crash_reserve_low_1M(void); +#else +static inline void __init crash_reserve_low_1M(void) { } +#endif + #endif /* _ASM_X86_CRASH_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 5c24a7b35166..b222a3595946 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -320,7 +320,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear); * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ -static inline void mds_clear_cpu_buffers(void) +static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; @@ -341,7 +341,7 @@ static inline void mds_clear_cpu_buffers(void) * * Clear CPU buffers if the corresponding static key is enabled */ -static inline void mds_user_clear_cpu_buffers(void) +static __always_inline void mds_user_clear_cpu_buffers(void) { if (static_branch_likely(&mds_user_clear)) mds_clear_cpu_buffers(); diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 19b137f1b3be..2ff9b98812b7 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -4,6 +4,11 @@ #define ARCH_DEFAULT_PKEY 0 +/* + * If more than 16 keys are ever supported, a thorough audit + * will be necessary to ensure that the types that store key + * numbers and masks have sufficient capacity. + */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1) extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index ea6d9da9b094..4b6301946f45 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2256,6 +2256,7 @@ static inline void __init check_timer(void) legacy_pic->init(0); legacy_pic->make_irq(0); apic_write(APIC_LVT0, APIC_DM_EXTINT); + legacy_pic->unmask(0); unlock_ExtINT_logic(); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index eb651fbde92a..ff25a2ea271c 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/hardirq.h> @@ -39,6 +40,7 @@ #include <asm/virtext.h> #include <asm/intel_pt.h> #include <asm/crash.h> +#include <asm/cmdline.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -68,6 +70,19 @@ static inline void cpu_crash_vmclear_loaded_vmcss(void) rcu_read_unlock(); } +/* + * When the crashkernel option is specified, only use the low + * 1M for the real mode trampoline. + */ +void __init crash_reserve_low_1M(void) +{ + if (cmdline_find_option(boot_command_line, "crashkernel", NULL, 0) < 0) + return; + + memblock_reserve(0, 1<<20); + pr_info("Reserving the low 1M of memory for crashkernel\n"); +} + #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 755eb26cbec0..735d1f1bbabc 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -895,8 +895,6 @@ const void *get_xsave_field_ptr(int xfeature_nr) #ifdef CONFIG_ARCH_HAS_PKEYS -#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -915,6 +913,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + WARN_ON_ONCE(pkey >= arch_max_pkey()); + /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 128d3ad46e96..cc7823e7ef96 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5836,6 +5836,8 @@ writeback: } ctxt->eip = ctxt->_eip; + if (ctxt->mode != X86EMUL_MODE_PROT64) + ctxt->eip = (u32)ctxt->_eip; done: if (rc == X86EMUL_PROPAGATE_FAULT) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 6920f1d3b66f..9f793c9649cd 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1684,7 +1684,7 @@ static void start_sw_period(struct kvm_lapic *apic) hrtimer_start(&apic->lapic_timer.timer, apic->lapic_timer.target_expiration, - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_HARD); } bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 3c6522b84ff1..ffcd96fc02d0 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ), TP_fast_assign( diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 3243a80ea32c..b58495fde2e8 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -787,9 +787,6 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) return 0; } else { - if (svm->next_rip - kvm_rip_read(vcpu) > MAX_INST_SIZE) - pr_err("%s: ip 0x%lx next 0x%llx\n", - __func__, kvm_rip_read(vcpu), svm->next_rip); kvm_rip_write(vcpu, svm->next_rip); } svm_set_interrupt_shadow(vcpu, 0); @@ -3970,6 +3967,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -4822,7 +4825,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index a1e62dda5607..2a1ed3aae100 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1130,6 +1130,10 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->guest_msrs[i].mask); } + + if (vmx->nested.need_vmcs12_to_shadow_sync) + nested_sync_vmcs12_to_shadow(vcpu); + if (vmx->guest_state_loaded) return; @@ -1537,7 +1541,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) static int skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rip; + unsigned long rip, orig_rip; /* * Using VMCS.VM_EXIT_INSTRUCTION_LEN on EPT misconfig depends on @@ -1549,8 +1553,17 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) */ if (!static_cpu_has(X86_FEATURE_HYPERVISOR) || to_vmx(vcpu)->exit_reason != EXIT_REASON_EPT_MISCONFIG) { - rip = kvm_rip_read(vcpu); - rip += vmcs_read32(VM_EXIT_INSTRUCTION_LEN); + orig_rip = kvm_rip_read(vcpu); + rip = orig_rip + vmcs_read32(VM_EXIT_INSTRUCTION_LEN); +#ifdef CONFIG_X86_64 + /* + * We need to mask out the high 32 bits of RIP if not in 64-bit + * mode, but just finding out that we are in 64-bit mode is + * quite expensive. Only do it if there was a carry. + */ + if (unlikely(((rip ^ orig_rip) >> 31) == 3) && !is_64_bit_mode(vcpu)) + rip = (u32)rip; +#endif kvm_rip_write(vcpu, rip); } else { if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) @@ -6486,8 +6499,11 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_write32(PLE_WINDOW, vmx->ple_window); } - if (vmx->nested.need_vmcs12_to_shadow_sync) - nested_sync_vmcs12_to_shadow(vcpu); + /* + * We did this in prepare_switch_to_guest, because it needs to + * be within srcu_read_lock. + */ + WARN_ON_ONCE(vmx->nested.need_vmcs12_to_shadow_sync); if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 8920ee7b2881..12e83297ea02 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -973,6 +973,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1000,7 +1001,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops->set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -5050,10 +5051,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof(u.ps))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -5073,10 +5077,13 @@ set_identity_unlock: r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: { diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b0dfac3d3df7..1847e993ac63 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 7dce39c8c034..262f83cad355 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -8,6 +8,7 @@ #include <asm/pgtable.h> #include <asm/realmode.h> #include <asm/tlbflush.h> +#include <asm/crash.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -34,6 +35,7 @@ void __init reserve_real_mode(void) memblock_reserve(mem, size); set_real_mode_mem(mem); + crash_reserve_low_1M(); } static void __init setup_real_mode(void) diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S index 59671603c9c6..1f07876ea2ed 100644 --- a/arch/xtensa/kernel/entry.S +++ b/arch/xtensa/kernel/entry.S @@ -1897,6 +1897,7 @@ ENTRY(system_call) mov a6, a2 call4 do_syscall_trace_enter + beqz a6, .Lsyscall_exit l32i a7, a2, PT_SYSCALL 1: @@ -1911,8 +1912,6 @@ ENTRY(system_call) addx4 a4, a7, a4 l32i a4, a4, 0 - movi a5, sys_ni_syscall; - beq a4, a5, 1f /* Load args: arg0 - arg5 are passed via regs. */ @@ -1932,6 +1931,7 @@ ENTRY(system_call) s32i a6, a2, PT_AREG2 bnez a3, 1f +.Lsyscall_exit: abi_ret(4) 1: diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index b964f0b2d886..145742d70a9f 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -542,14 +542,28 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } -void do_syscall_trace_enter(struct pt_regs *regs) +void do_syscall_trace_leave(struct pt_regs *regs); +int do_syscall_trace_enter(struct pt_regs *regs) { + if (regs->syscall == NO_SYSCALL) + regs->areg[2] = -ENOSYS; + if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) + tracehook_report_syscall_entry(regs)) { + regs->areg[2] = -ENOSYS; regs->syscall = NO_SYSCALL; + return 0; + } + + if (regs->syscall == NO_SYSCALL) { + do_syscall_trace_leave(regs); + return 0; + } if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, syscall_get_nr(current, regs)); + + return 1; } void do_syscall_trace_leave(struct pt_regs *regs) |