diff options
Diffstat (limited to 'arch')
-rw-r--r-- | arch/arc/kernel/perf_event.c | 4 | ||||
-rw-r--r-- | arch/arm64/include/asm/pgtable-prot.h | 15 | ||||
-rw-r--r-- | arch/arm64/kernel/armv8_deprecated.c | 5 | ||||
-rw-r--r-- | arch/arm64/kernel/cpu_errata.c | 1 | ||||
-rw-r--r-- | arch/arm64/kernel/entry.S | 1 | ||||
-rw-r--r-- | arch/arm64/kernel/ftrace.c | 12 | ||||
-rw-r--r-- | arch/mips/fw/sni/sniprom.c | 2 | ||||
-rw-r--r-- | arch/mips/include/asm/cmpxchg.h | 9 | ||||
-rw-r--r-- | arch/powerpc/platforms/powernv/smp.c | 53 | ||||
-rw-r--r-- | arch/riscv/kernel/traps.c | 14 | ||||
-rw-r--r-- | arch/s390/include/asm/uaccess.h | 4 | ||||
-rw-r--r-- | arch/s390/include/asm/unwind.h | 1 | ||||
-rw-r--r-- | arch/s390/kernel/idle.c | 29 | ||||
-rw-r--r-- | arch/s390/kernel/unwind_bc.c | 18 | ||||
-rw-r--r-- | arch/s390/mm/cmm.c | 12 | ||||
-rw-r--r-- | arch/s390/pci/pci_irq.c | 2 | ||||
-rw-r--r-- | arch/um/drivers/ubd_kern.c | 8 | ||||
-rw-r--r-- | arch/x86/events/amd/core.c | 30 | ||||
-rw-r--r-- | arch/x86/include/asm/fpu/internal.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/intel-family.h | 3 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 14 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi.c | 3 | ||||
-rw-r--r-- | arch/x86/xen/enlighten.c | 28 |
24 files changed, 184 insertions, 96 deletions
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c index 861a8aea51f9..661fd842ea97 100644 --- a/arch/arc/kernel/perf_event.c +++ b/arch/arc/kernel/perf_event.c @@ -614,8 +614,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev) /* loop thru all available h/w condition indexes */ for (i = 0; i < cc_bcr.c; i++) { write_aux_reg(ARC_REG_CC_INDEX, i); - cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0); - cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1); + cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0)); + cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1)); arc_pmu_map_hw_event(i, cc_name.str); arc_pmu_add_raw_event_attr(i, cc_name.str); diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index c81583be034b..87808be11ffa 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -32,11 +32,11 @@ #define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) #define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) -#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) -#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) -#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) -#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) -#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) +#define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) +#define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) +#define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) +#define PROT_NORMAL_WT (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT)) +#define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) @@ -80,8 +80,9 @@ #define PAGE_S2_DEVICE __pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PAGE_S2_XN) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) -#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) -#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE) +/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ +#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 2ec09debc2bb..ca158be21f83 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -174,6 +174,9 @@ static void __init register_insn_emulation(struct insn_emulation_ops *ops) struct insn_emulation *insn; insn = kzalloc(sizeof(*insn), GFP_KERNEL); + if (!insn) + return; + insn->ops = ops; insn->min = INSN_UNDEF; @@ -233,6 +236,8 @@ static void __init register_insn_emulation_sysctl(void) insns_sysctl = kcalloc(nr_insn_emulated + 1, sizeof(*sysctl), GFP_KERNEL); + if (!insns_sysctl) + return; raw_spin_lock_irqsave(&insn_emulation_lock, flags); list_for_each_entry(insn, &insn_emulation, node) { diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index ca11ff7bf55e..ca68142b10b9 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -780,6 +780,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { { .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = cpucap_multi_entry_cap_matches, .match_list = qcom_erratum_1003_list, }, diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 84a822748c84..e304fe04b098 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -775,6 +775,7 @@ el0_sync_compat: b.ge el0_dbg b el0_inv el0_svc_compat: + gic_prio_kentry_setup tmp=x1 mov x0, sp bl el0_svc_compat_handler b ret_to_user diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 171773257974..06e56b470315 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -121,10 +121,16 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) /* * Ensure updated trampoline is visible to instruction - * fetch before we patch in the branch. + * fetch before we patch in the branch. Although the + * architecture doesn't require an IPI in this case, + * Neoverse-N1 erratum #1542419 does require one + * if the TLB maintenance in module_enable_ro() is + * skipped due to rodata_enabled. It doesn't seem worth + * it to make it conditional given that this is + * certainly not a fast-path. */ - __flush_icache_range((unsigned long)&dst[0], - (unsigned long)&dst[1]); + flush_icache_range((unsigned long)&dst[0], + (unsigned long)&dst[1]); } addr = (unsigned long)dst; #else /* CONFIG_ARM64_MODULE_PLTS */ diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c index 8772617b64ce..80112f2298b6 100644 --- a/arch/mips/fw/sni/sniprom.c +++ b/arch/mips/fw/sni/sniprom.c @@ -43,7 +43,7 @@ /* O32 stack has to be 8-byte aligned. */ static u64 o32_stk[4096]; -#define O32_STK &o32_stk[sizeof(o32_stk)] +#define O32_STK (&o32_stk[ARRAY_SIZE(o32_stk)]) #define __PROM_O32(fun, arg) fun arg __asm__(#fun); \ __asm__(#fun " = call_o32") diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h index c8a47d18f628..2b61052e10c9 100644 --- a/arch/mips/include/asm/cmpxchg.h +++ b/arch/mips/include/asm/cmpxchg.h @@ -77,8 +77,8 @@ extern unsigned long __xchg_called_with_bad_pointer(void) extern unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size); -static inline unsigned long __xchg(volatile void *ptr, unsigned long x, - int size) +static __always_inline +unsigned long __xchg(volatile void *ptr, unsigned long x, int size) { switch (size) { case 1: @@ -153,8 +153,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x, extern unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size); -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, unsigned int size) +static __always_inline +unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, unsigned int size) { switch (size) { case 1: diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 94cd96b9b7bb..001dfac8354a 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void) return 0; } +static void pnv_flush_interrupts(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (xive_enabled()) + xive_flush_interrupt(); + else + icp_opal_flush_interrupt(); + } else { + icp_native_flush_interrupt(); + } +} + static void pnv_smp_cpu_kill_self(void) { + unsigned long srr1, unexpected_mask, wmask; unsigned int cpu; - unsigned long srr1, wmask; u64 lpcr_val; /* Standard hot unplug procedure */ - /* - * This hard disables local interurpts, ensuring we have no lazy - * irqs pending. - */ - WARN_ON(irqs_disabled()); - hard_irq_disable(); - WARN_ON(lazy_irq_pending()); idle_task_exit(); current->active_mm = NULL; /* for sanity */ @@ -173,6 +178,27 @@ static void pnv_smp_cpu_kill_self(void) wmask = SRR1_WAKEMASK_P8; /* + * This turns the irq soft-disabled state we're called with, into a + * hard-disabled state with pending irq_happened interrupts cleared. + * + * PACA_IRQ_DEC - Decrementer should be ignored. + * PACA_IRQ_HMI - Can be ignored, processing is done in real mode. + * PACA_IRQ_DBELL, EE, PMI - Unexpected. + */ + hard_irq_disable(); + if (generic_check_cpu_restart(cpu)) + goto out; + + unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS); + if (local_paca->irq_happened & unexpected_mask) { + if (local_paca->irq_happened & PACA_IRQ_EE) + pnv_flush_interrupts(); + DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n", + cpu, local_paca->irq_happened); + } + local_paca->irq_happened = PACA_IRQ_HARD_DIS; + + /* * We don't want to take decrementer interrupts while we are * offline, so clear LPCR:PECE1. We keep PECE2 (and * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in. @@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void) srr1 = pnv_cpu_offline(cpu); + WARN_ON_ONCE(!irqs_disabled()); WARN_ON(lazy_irq_pending()); /* @@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void) */ if (((srr1 & wmask) == SRR1_WAKEEE) || ((srr1 & wmask) == SRR1_WAKEHVI)) { - if (cpu_has_feature(CPU_FTR_ARCH_300)) { - if (xive_enabled()) - xive_flush_interrupt(); - else - icp_opal_flush_interrupt(); - } else - icp_native_flush_interrupt(); + pnv_flush_interrupts(); } else if ((srr1 & wmask) == SRR1_WAKEHDBELL) { unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER); asm volatile(PPC_MSGCLR(%0) : : "r" (msg)); @@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void) */ lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1; pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val); - +out: DBG("CPU%d coming online...\n", cpu); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 6b32190ba73c..6dc20fa5f46b 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -123,24 +123,24 @@ static inline unsigned long get_break_insn_length(unsigned long pc) asmlinkage void do_trap_break(struct pt_regs *regs) { -#ifdef CONFIG_GENERIC_BUG if (!user_mode(regs)) { enum bug_trap_type type; type = report_bug(regs->sepc, regs); switch (type) { - case BUG_TRAP_TYPE_NONE: - break; +#ifdef CONFIG_GENERIC_BUG case BUG_TRAP_TYPE_WARN: regs->sepc += get_break_insn_length(regs->sepc); - break; + return; case BUG_TRAP_TYPE_BUG: +#endif /* CONFIG_GENERIC_BUG */ + default: die(regs, "Kernel BUG"); } + } else { + force_sig_fault(SIGTRAP, TRAP_BRKPT, + (void __user *)(regs->sepc), current); } -#endif /* CONFIG_GENERIC_BUG */ - - force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)(regs->sepc), current); } #ifdef CONFIG_GENERIC_BUG diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index bd2fd9a7821d..a470f1fa9f2a 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -83,7 +83,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n); __rc; \ }) -static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) +static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) { unsigned long spec = 0x010000UL; int rc; @@ -113,7 +113,7 @@ static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) return rc; } -static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) +static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) { unsigned long spec = 0x01UL; int rc; diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h index 6eb2ef105d87..ac4568d60d08 100644 --- a/arch/s390/include/asm/unwind.h +++ b/arch/s390/include/asm/unwind.h @@ -35,6 +35,7 @@ struct unwind_state { struct task_struct *task; struct pt_regs *regs; unsigned long sp, ip; + bool reuse_sp; int graph_idx; bool reliable; bool error; diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index b9d8fe45737a..8f8456816d83 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL); static ssize_t show_idle_time(struct device *dev, struct device_attribute *attr, char *buf) { + unsigned long long now, idle_time, idle_enter, idle_exit, in_idle; struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id); - unsigned long long now, idle_time, idle_enter, idle_exit; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_time = READ_ONCE(idle->idle_time); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0; + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + idle_time += in_idle; return sprintf(buf, "%llu\n", idle_time >> 12); } DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); @@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL); u64 arch_cpu_idle_time(int cpu) { struct s390_idle_data *idle = &per_cpu(s390_idle, cpu); - unsigned long long now, idle_enter, idle_exit; + unsigned long long now, idle_enter, idle_exit, in_idle; unsigned int seq; do { - now = get_tod_clock(); seq = read_seqcount_begin(&idle->seqcount); idle_enter = READ_ONCE(idle->clock_idle_enter); idle_exit = READ_ONCE(idle->clock_idle_exit); } while (read_seqcount_retry(&idle->seqcount, seq)); - - return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0); + in_idle = 0; + now = get_tod_clock(); + if (idle_enter) { + if (idle_exit) { + in_idle = idle_exit - idle_enter; + } else if (now > idle_enter) { + in_idle = now - idle_enter; + } + } + return cputime_to_nsecs(in_idle); } void arch_cpu_idle_enter(void) diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c index 57fd4e902f1f..ea00f703f951 100644 --- a/arch/s390/kernel/unwind_bc.c +++ b/arch/s390/kernel/unwind_bc.c @@ -46,10 +46,15 @@ bool unwind_next_frame(struct unwind_state *state) regs = state->regs; if (unlikely(regs)) { - sp = READ_ONCE_TASK_STACK(state->task, regs->gprs[15]); - if (unlikely(outside_of_stack(state, sp))) { - if (!update_stack_info(state, sp)) - goto out_err; + if (state->reuse_sp) { + sp = state->sp; + state->reuse_sp = false; + } else { + sp = READ_ONCE_TASK_STACK(state->task, regs->gprs[15]); + if (unlikely(outside_of_stack(state, sp))) { + if (!update_stack_info(state, sp)) + goto out_err; + } } sf = (struct stack_frame *) sp; ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]); @@ -107,9 +112,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, { struct stack_info *info = &state->stack_info; unsigned long *mask = &state->stack_mask; + bool reliable, reuse_sp; struct stack_frame *sf; unsigned long ip; - bool reliable; memset(state, 0, sizeof(*state)); state->task = task; @@ -134,10 +139,12 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, if (regs) { ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr); reliable = true; + reuse_sp = true; } else { sf = (struct stack_frame *) sp; ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]); reliable = false; + reuse_sp = false; } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -151,5 +158,6 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, state->sp = sp; state->ip = ip; state->reliable = reliable; + state->reuse_sp = reuse_sp; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 510a18299196..a51c892f14f3 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -298,16 +298,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, } if (write) { - len = *lenp; - if (copy_from_user(buf, buffer, - len > sizeof(buf) ? sizeof(buf) : len)) + len = min(*lenp, sizeof(buf)); + if (copy_from_user(buf, buffer, len)) return -EFAULT; - buf[sizeof(buf) - 1] = '\0'; + buf[len - 1] = '\0'; cmm_skip_blanks(buf, &p); nr = simple_strtoul(p, &p, 0); cmm_skip_blanks(p, &p); seconds = simple_strtoul(p, &p, 0); cmm_set_timeout(nr, seconds); + *ppos += *lenp; } else { len = sprintf(buf, "%ld %ld\n", cmm_timeout_pages, cmm_timeout_seconds); @@ -315,9 +315,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write, len = *lenp; if (copy_to_user(buffer, buf, len)) return -EFAULT; + *lenp = len; + *ppos += len; } - *lenp = len; - *ppos += len; return 0; } diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index d80616ae8dd8..fbe97ab2e228 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -284,7 +284,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return rc; irq_set_chip_and_handler(irq, &zpci_irq_chip, handle_percpu_irq); - msg.data = hwirq; + msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { msg.address_lo = zdev->msi_addr & 0xff0000ff; msg.address_lo |= msi->affinity ? diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 33c1cd6a12ac..40ab9ad7aa96 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1403,8 +1403,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, spin_unlock_irq(&ubd_dev->lock); - if (ret < 0) - blk_mq_requeue_request(req, true); + if (ret < 0) { + if (ret == -ENOMEM) + res = BLK_STS_RESOURCE; + else + res = BLK_STS_DEV_RESOURCE; + } return res; } diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e7d35f60d53f..64c3e70b0556 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -5,12 +5,14 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <asm/apicdef.h> #include <asm/nmi.h> #include "../perf_event.h" -static DEFINE_PER_CPU(unsigned int, perf_nmi_counter); +static DEFINE_PER_CPU(unsigned long, perf_nmi_tstamp); +static unsigned long perf_nmi_window; static __initconst const u64 amd_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] @@ -641,11 +643,12 @@ static void amd_pmu_disable_event(struct perf_event *event) * handler when multiple PMCs are active or PMC overflow while handling some * other source of an NMI. * - * Attempt to mitigate this by using the number of active PMCs to determine - * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset - * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the - * number of active PMCs or 2. The value of 2 is used in case an NMI does not - * arrive at the LAPIC in time to be collapsed into an already pending NMI. + * Attempt to mitigate this by creating an NMI window in which un-handled NMIs + * received during this window will be claimed. This prevents extending the + * window past when it is possible that latent NMIs should be received. The + * per-CPU perf_nmi_tstamp will be set to the window end time whenever perf has + * handled a counter. When an un-handled NMI is received, it will be claimed + * only if arriving within that window. */ static int amd_pmu_handle_irq(struct pt_regs *regs) { @@ -663,21 +666,19 @@ static int amd_pmu_handle_irq(struct pt_regs *regs) handled = x86_pmu_handle_irq(regs); /* - * If a counter was handled, record the number of possible remaining - * NMIs that can occur. + * If a counter was handled, record a timestamp such that un-handled + * NMIs will be claimed if arriving within that window. */ if (handled) { - this_cpu_write(perf_nmi_counter, - min_t(unsigned int, 2, active)); + this_cpu_write(perf_nmi_tstamp, + jiffies + perf_nmi_window); return handled; } - if (!this_cpu_read(perf_nmi_counter)) + if (time_after(jiffies, this_cpu_read(perf_nmi_tstamp))) return NMI_DONE; - this_cpu_dec(perf_nmi_counter); - return NMI_HANDLED; } @@ -909,6 +910,9 @@ static int __init amd_core_pmu_init(void) if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; + /* Avoid calulating the value each time in the NMI handler */ + perf_nmi_window = msecs_to_jiffies(100); + switch (boot_cpu_data.x86) { case 0x15: pr_cont("Fam15h "); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 4c95c365058a..44c48e34d799 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -509,7 +509,7 @@ static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { - return fpu == this_cpu_read_stable(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; + return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } /* diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 82a57d344b9b..2a8e5f78e23c 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -61,6 +61,9 @@ #define INTEL_FAM6_TIGERLAKE_L 0x8C #define INTEL_FAM6_TIGERLAKE 0x8D +#define INTEL_FAM6_COMETLAKE 0xA5 +#define INTEL_FAM6_COMETLAKE_L 0xA6 + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ee7db075dd4d..68f63d9684a6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -732,8 +732,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu) static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) { vcpu->arch.efer = efer; - if (!npt_enabled && !(efer & EFER_LMA)) - efer &= ~EFER_LME; + + if (!npt_enabled) { + /* Shadow paging assumes NX to be available. */ + efer |= EFER_NX; + + if (!(efer & EFER_LMA)) + efer &= ~EFER_LME; + } to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e5fdd5f14c8e..ea5040117fbb 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -896,17 +896,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) u64 guest_efer = vmx->vcpu.arch.efer; u64 ignore_bits = 0; - if (!enable_ept) { - /* - * NX is needed to handle CR0.WP=1, CR4.SMEP=1. Testing - * host CPUID is more efficient than testing guest CPUID - * or CR4. Host SMEP is anyway a requirement for guest SMEP. - */ - if (boot_cpu_has(X86_FEATURE_SMEP)) - guest_efer |= EFER_NX; - else if (!(guest_efer & EFER_NX)) - ignore_bits |= EFER_NX; - } + /* Shadow paging assumes NX to be available. */ + if (!enable_ept) + guest_efer |= EFER_NX; /* * LMA and LME handled by hardware; SCE meaningless outside long mode. diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index a7189a3b4d70..3304f61538a2 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -894,9 +894,6 @@ static void __init kexec_enter_virtual_mode(void) if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) runtime_code_page_mkexec(); - - /* clean DUMMY object */ - efi_delete_dummy_variable(); #endif } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 750f46ad018a..205b1176084f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -269,19 +269,41 @@ void xen_reboot(int reason) BUG(); } +static int reboot_reason = SHUTDOWN_reboot; +static bool xen_legacy_crash; void xen_emergency_restart(void) { - xen_reboot(SHUTDOWN_reboot); + xen_reboot(reboot_reason); } static int xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) { - if (!kexec_crash_loaded()) - xen_reboot(SHUTDOWN_crash); + if (!kexec_crash_loaded()) { + if (xen_legacy_crash) + xen_reboot(SHUTDOWN_crash); + + reboot_reason = SHUTDOWN_crash; + + /* + * If panic_timeout==0 then we are supposed to wait forever. + * However, to preserve original dom0 behavior we have to drop + * into hypervisor. (domU behavior is controlled by its + * config file) + */ + if (panic_timeout == 0) + panic_timeout = -1; + } return NOTIFY_DONE; } +static int __init parse_xen_legacy_crash(char *arg) +{ + xen_legacy_crash = true; + return 0; +} +early_param("xen_legacy_crash", parse_xen_legacy_crash); + static struct notifier_block xen_panic_block = { .notifier_call = xen_panic_event, .priority = INT_MIN |