diff options
| author | Tony Lindgren <tony@atomide.com> | 2020-06-16 09:25:03 -0700 |
|---|---|---|
| committer | Tony Lindgren <tony@atomide.com> | 2020-06-16 09:25:03 -0700 |
| commit | 07c7b547a79605f1041d55b84d91a4a4d9c5b363 (patch) | |
| tree | d98c1adacc8c65b475c325b427e54b8205b0013d /arch/x86/kernel | |
| parent | e4a8fc054340f4df761f6a73335f8fdc0b7ac4fd (diff) | |
| parent | b3a9e3b9622ae10064826dccb4f7a52bd88c7407 (diff) | |
| download | linux-07c7b547a79605f1041d55b84d91a4a4d9c5b363.tar.gz | |
Merge tag 'v5.8-rc1' into fixes
Linux 5.8-rc1
Diffstat (limited to 'arch/x86/kernel')
101 files changed, 2074 insertions, 1634 deletions
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index ba89cabe5fcf..e77261db2391 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -28,6 +28,10 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n +# With some compiler versions the generated code results in boot hangs, caused +# by several compilation units. To be safe, disable all instrumentation. +KCSAN_SANITIZE := n + OBJECT_FILES_NON_STANDARD_test_nx.o := y OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y @@ -90,7 +94,6 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_LIVEPATCH) += livepatch.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace_$(BITS).o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o @@ -102,9 +105,7 @@ obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o -ifeq ($(CONFIG_X86_32),y) -obj-$(CONFIG_DOUBLEFAULT) += doublefault_32.o -endif +obj-$(CONFIG_X86_32) += doublefault_32.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_VM86) += vm86_32.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 683ed9e12e6b..7bdc0239a943 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -20,11 +20,11 @@ #include <linux/pci.h> #include <linux/efi-bgrt.h> #include <linux/serial_core.h> +#include <linux/pgtable.h> #include <asm/e820/api.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> -#include <asm/pgtable.h> #include <asm/io_apic.h> #include <asm/apic.h> #include <asm/io.h> diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ed3b04483972..cc1fea76aab0 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -10,9 +10,9 @@ #include <linux/memblock.h> #include <linux/dmi.h> #include <linux/cpumask.h> +#include <linux/pgtable.h> #include <asm/segment.h> #include <asm/desc.h> -#include <asm/pgtable.h> #include <asm/cacheflush.h> #include <asm/realmode.h> diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 7867dfb3963e..8fd39ff74a49 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,7 +18,6 @@ #include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/sections.h> -#include <asm/pgtable.h> #include <asm/mce.h> #include <asm/nmi.h> #include <asm/cacheflush.h> @@ -783,6 +782,61 @@ void __init_or_module text_poke_early(void *addr, const void *opcode, } } +typedef struct { + struct mm_struct *mm; +} temp_mm_state_t; + +/* + * Using a temporary mm allows to set temporary mappings that are not accessible + * by other CPUs. Such mappings are needed to perform sensitive memory writes + * that override the kernel memory protections (e.g., W^X), without exposing the + * temporary page-table mappings that are required for these write operations to + * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the + * mapping is torn down. + * + * Context: The temporary mm needs to be used exclusively by a single core. To + * harden security IRQs must be disabled while the temporary mm is + * loaded, thereby preventing interrupt handler bugs from overriding + * the kernel memory protection. + */ +static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) +{ + temp_mm_state_t temp_state; + + lockdep_assert_irqs_disabled(); + temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); + switch_mm_irqs_off(NULL, mm, current); + + /* + * If breakpoints are enabled, disable them while the temporary mm is + * used. Userspace might set up watchpoints on addresses that are used + * in the temporary mm, which would lead to wrong signals being sent or + * crashes. + * + * Note that breakpoints are not disabled selectively, which also causes + * kernel breakpoints (e.g., perf's) to be disabled. This might be + * undesirable, but still seems reasonable as the code that runs in the + * temporary mm should be short. + */ + if (hw_breakpoint_active()) + hw_breakpoint_disable(); + + return temp_state; +} + +static inline void unuse_temporary_mm(temp_mm_state_t prev_state) +{ + lockdep_assert_irqs_disabled(); + switch_mm_irqs_off(NULL, prev_state.mm, current); + + /* + * Restore the breakpoints if they were disabled before the temporary mm + * was loaded. + */ + if (hw_breakpoint_active()) + hw_breakpoint_restore(); +} + __ro_after_init struct mm_struct *poking_mm; __ro_after_init unsigned long poking_addr; @@ -957,28 +1011,29 @@ struct bp_patching_desc { static struct bp_patching_desc *bp_desc; -static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +static __always_inline +struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) { - struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */ + struct bp_patching_desc *desc = __READ_ONCE(*descp); /* rcu_dereference */ - if (!desc || !atomic_inc_not_zero(&desc->refs)) + if (!desc || !arch_atomic_inc_not_zero(&desc->refs)) return NULL; return desc; } -static inline void put_desc(struct bp_patching_desc *desc) +static __always_inline void put_desc(struct bp_patching_desc *desc) { smp_mb__before_atomic(); - atomic_dec(&desc->refs); + arch_atomic_dec(&desc->refs); } -static inline void *text_poke_addr(struct text_poke_loc *tp) +static __always_inline void *text_poke_addr(struct text_poke_loc *tp) { return _stext + tp->rel_addr; } -static int notrace patch_cmp(const void *key, const void *elt) +static __always_inline int patch_cmp(const void *key, const void *elt) { struct text_poke_loc *tp = (struct text_poke_loc *) elt; @@ -988,9 +1043,8 @@ static int notrace patch_cmp(const void *key, const void *elt) return 1; return 0; } -NOKPROBE_SYMBOL(patch_cmp); -int notrace poke_int3_handler(struct pt_regs *regs) +int noinstr poke_int3_handler(struct pt_regs *regs) { struct bp_patching_desc *desc; struct text_poke_loc *tp; @@ -1023,9 +1077,9 @@ int notrace poke_int3_handler(struct pt_regs *regs) * Skip the binary search if there is a single member in the vector. */ if (unlikely(desc->nr_entries > 1)) { - tp = bsearch(ip, desc->vec, desc->nr_entries, - sizeof(struct text_poke_loc), - patch_cmp); + tp = __inline_bsearch(ip, desc->vec, desc->nr_entries, + sizeof(struct text_poke_loc), + patch_cmp); if (!tp) goto out_put; } else { @@ -1064,7 +1118,6 @@ out_put: put_desc(desc); return ret; } -NOKPROBE_SYMBOL(poke_int3_handler); #define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) static struct text_poke_loc tp_vec[TP_VEC_MAX]; diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 16133819415c..17cb5b933dcf 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -33,7 +33,6 @@ #include <linux/atomic.h> #include <linux/dma-direct.h> #include <asm/mtrr.h> -#include <asm/pgtable.h> #include <asm/proto.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -159,7 +158,7 @@ static void dump_leak(void) return; dump = 1; - show_stack(NULL, NULL); + show_stack(NULL, NULL, KERN_ERR); debug_dma_dump_mappings(NULL); } #endif diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index b6b3297851f3..18f6b7c4bd79 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -18,9 +18,11 @@ #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 +#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 +#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 #define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 @@ -33,6 +35,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, {} }; @@ -50,6 +53,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, @@ -65,6 +69,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index fe698f96617c..263eeaddb0aa 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -345,56 +345,3 @@ out_noapbt: apb_timer_block_enabled = 0; panic("failed to enable APB timer\n"); } - -/* called before apb_timer_enable, use early map */ -unsigned long apbt_quick_calibrate(void) -{ - int i, scale; - u64 old, new; - u64 t1, t2; - unsigned long khz = 0; - u32 loop, shift; - - apbt_set_mapping(); - dw_apb_clocksource_start(clocksource_apbt); - - /* check if the timer can count down, otherwise return */ - old = dw_apb_clocksource_read(clocksource_apbt); - i = 10000; - while (--i) { - if (old != dw_apb_clocksource_read(clocksource_apbt)) - break; - } - if (!i) - goto failed; - - /* count 16 ms */ - loop = (apbt_freq / 1000) << 4; - - /* restart the timer to ensure it won't get to 0 in the calibration */ - dw_apb_clocksource_start(clocksource_apbt); - - old = dw_apb_clocksource_read(clocksource_apbt); - old += loop; - - t1 = rdtsc(); - - do { - new = dw_apb_clocksource_read(clocksource_apbt); - } while (new < old); - - t2 = rdtsc(); - - shift = 5; - if (unlikely(loop >> shift == 0)) { - printk(KERN_INFO - "APBT TSC calibration failed, not enough resolution\n"); - return 0; - } - scale = (int)div_u64((t2 - t1), loop >> shift); - khz = (scale * (apbt_freq / 1000)) >> shift; - printk(KERN_INFO "TSC freq calculated by APB timer is %lu khz\n", khz); - return khz; -failed: - return 0; -} diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index e53dda210cd7..e0e2f020ec02 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -544,46 +544,20 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -static __init u32 hsx_deadline_rev(void) -{ - switch (boot_cpu_data.x86_stepping) { - case 0x02: return 0x3a; /* EP */ - case 0x04: return 0x0f; /* EX */ - } - - return ~0U; -} - -static __init u32 bdx_deadline_rev(void) -{ - switch (boot_cpu_data.x86_stepping) { - case 0x02: return 0x00000011; - case 0x03: return 0x0700000e; - case 0x04: return 0x0f00000c; - case 0x05: return 0x0e000003; - } - - return ~0U; -} - -static __init u32 skx_deadline_rev(void) -{ - switch (boot_cpu_data.x86_stepping) { - case 0x03: return 0x01000136; - case 0x04: return 0x02000014; - } +static const struct x86_cpu_id deadline_match[] __initconst = { + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */ + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */ - if (boot_cpu_data.x86_stepping > 4) - return 0; + X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), - return ~0U; -} + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003), -static const struct x86_cpu_id deadline_match[] __initconst = { - X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), - X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), - X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), - X86_MATCH_INTEL_FAM6_MODEL( SKYLAKE_X, &skx_deadline_rev), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0), X86_MATCH_INTEL_FAM6_MODEL( HASWELL, 0x22), X86_MATCH_INTEL_FAM6_MODEL( HASWELL_L, 0x20), @@ -615,14 +589,7 @@ static __init bool apic_validate_deadline_timer(void) if (!m) return true; - /* - * Function pointers will have the MSB set due to address layout, - * immediate revisions will not. - */ - if ((long)m->driver_data < 0) - rev = ((u32 (*)(void))(m->driver_data))(); - else - rev = (u32)m->driver_data; + rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) return true; @@ -1121,23 +1088,14 @@ static void local_apic_timer_interrupt(void) * [ if a single-CPU system runs an SMP kernel then we call the local * interrupt as well. Thus we cannot inline the local irq ... ] */ -__visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_apic_timer_interrupt) { struct pt_regs *old_regs = set_irq_regs(regs); - /* - * NOTE! We'd better ACK the irq immediately, - * because timer handling can be slow. - * - * update_process_times() expects us to have done irq_enter(). - * Besides, if we don't timer interrupts ignore the global - * interrupt lock, which is the WrongThing (tm) to do. - */ - entering_ack_irq(); + ack_APIC_irq(); trace_local_timer_entry(LOCAL_TIMER_VECTOR); local_apic_timer_interrupt(); trace_local_timer_exit(LOCAL_TIMER_VECTOR); - exiting_irq(); set_irq_regs(old_regs); } @@ -2093,7 +2051,7 @@ void __init init_apic_mappings(void) unsigned int new_apicid; if (apic_validate_deadline_timer()) - pr_debug("TSC deadline timer available\n"); + pr_info("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); @@ -2153,15 +2111,21 @@ void __init register_lapic_address(unsigned long address) * Local APIC interrupts */ -/* - * This interrupt should _never_ happen with our APIC/SMP architecture +/** + * spurious_interrupt - Catch all for interrupts raised on unused vectors + * @regs: Pointer to pt_regs on stack + * @vector: The vector number + * + * This is invoked from ASM entry code to catch all interrupts which + * trigger on an entry which is routed to the common_spurious idtentry + * point. + * + * Also called from sysvec_spurious_apic_interrupt(). */ -__visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_IRQ(spurious_interrupt) { - u8 vector = ~regs->orig_ax; u32 v; - entering_irq(); trace_spurious_apic_entry(vector); inc_irq_stat(irq_spurious_count); @@ -2191,13 +2155,17 @@ __visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs) } out: trace_spurious_apic_exit(vector); - exiting_irq(); +} + +DEFINE_IDTENTRY_SYSVEC(sysvec_spurious_apic_interrupt) +{ + __spurious_interrupt(regs, SPURIOUS_APIC_VECTOR); } /* * This interrupt should never happen with our APIC/SMP architecture */ -__visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_error_interrupt) { static const char * const error_interrupt_reason[] = { "Send CS error", /* APIC Error Bit 0 */ @@ -2211,7 +2179,6 @@ __visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) }; u32 v, i = 0; - entering_irq(); trace_error_apic_entry(ERROR_APIC_VECTOR); /* First tickle the hardware, only then report what went on. -- REW */ @@ -2235,7 +2202,6 @@ __visible void __irq_entry smp_error_interrupt(struct pt_regs *regs) apic_printk(APIC_DEBUG, KERN_CONT "\n"); trace_error_apic_exit(ERROR_APIC_VECTOR); - exiting_irq(); } /** diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index cdf45b4700f2..35edd57f064a 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -12,11 +12,11 @@ */ #include <linux/types.h> #include <linux/init.h> +#include <linux/pgtable.h> #include <asm/numachip/numachip.h> #include <asm/numachip/numachip_csr.h> -#include <asm/pgtable.h> #include "local.h" diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 913c88617848..ce61e3e7d399 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -154,19 +154,6 @@ static inline bool mp_is_legacy_irq(int irq) return irq >= 0 && irq < nr_legacy_irqs(); } -/* - * Initialize all legacy IRQs and all pins on the first IOAPIC - * if we have legacy interrupt controller. Kernel boot option "pirq=" - * may rely on non-legacy pins on the first IOAPIC. - */ -static inline int mp_init_irq_at_boot(int ioapic, int irq) -{ - if (!nr_legacy_irqs()) - return 0; - - return ioapic == 0 || mp_is_legacy_irq(irq); -} - static inline struct irq_domain *mp_ioapic_irqdomain(int ioapic) { return ioapics[ioapic].irqdomain; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 159bd0cb8548..5cbaca58af95 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -115,7 +115,8 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * denote it as spurious which is no harm as this is a rare event * and interrupt handlers have to cope with spurious interrupts * anyway. If the vector is unused, then it is marked so it won't - * trigger the 'No irq handler for vector' warning in do_IRQ(). + * trigger the 'No irq handler for vector' warning in + * common_interrupt(). * * This requires to hold vector lock to prevent concurrent updates to * the affected vector. diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 67768e54438b..c48be6e1f676 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -861,13 +861,13 @@ static void free_moved_vector(struct apic_chip_data *apicd) apicd->move_in_progress = 0; } -asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void) +DEFINE_IDTENTRY_SYSVEC(sysvec_irq_move_cleanup) { struct hlist_head *clhead = this_cpu_ptr(&cleanup_list); struct apic_chip_data *apicd; struct hlist_node *tmp; - entering_ack_irq(); + ack_APIC_irq(); /* Prevent vectors vanishing under us */ raw_spin_lock(&vector_lock); @@ -892,7 +892,6 @@ asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void) } raw_spin_unlock(&vector_lock); - exiting_irq(); } static void __send_cleanup_vector(struct apic_chip_data *apicd) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index ad53b2abc859..69e70ed0f5e6 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -30,8 +30,6 @@ static enum uv_system_type uv_system_type; static int uv_hubbed_system; static int uv_hubless_system; static u64 gru_start_paddr, gru_end_paddr; -static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr; -static u64 gru_dist_lmask, gru_dist_umask; static union uvh_apicid uvh_apicid; /* Unpack OEM/TABLE ID's to be NULL terminated strings */ @@ -48,11 +46,9 @@ static struct { unsigned int gnode_shift; } uv_cpuid; -int uv_min_hub_revision_id; -EXPORT_SYMBOL_GPL(uv_min_hub_revision_id); +static int uv_min_hub_revision_id; unsigned int uv_apicid_hibits; -EXPORT_SYMBOL_GPL(uv_apicid_hibits); static struct apic apic_x2apic_uv_x; static struct uv_hub_info_s uv_hub_info_node0; @@ -85,20 +81,7 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr) static inline bool is_GRU_range(u64 start, u64 end) { - if (gru_dist_base) { - u64 su = start & gru_dist_umask; /* Upper (incl pnode) bits */ - u64 sl = start & gru_dist_lmask; /* Base offset bits */ - u64 eu = end & gru_dist_umask; - u64 el = end & gru_dist_lmask; - - /* Must reside completely within a single GRU range: */ - return (sl == gru_dist_base && el == gru_dist_base && - su >= gru_first_node_paddr && - su <= gru_last_node_paddr && - eu == su); - } else { - return start >= gru_start_paddr && end <= gru_end_paddr; - } + return start >= gru_start_paddr && end <= gru_end_paddr; } static bool uv_is_untracked_pat_range(u64 start, u64 end) @@ -385,11 +368,10 @@ int is_uv_hubbed(int uvtype) } EXPORT_SYMBOL_GPL(is_uv_hubbed); -int is_uv_hubless(int uvtype) +static int is_uv_hubless(int uvtype) { return (uv_hubless_system & uvtype); } -EXPORT_SYMBOL_GPL(is_uv_hubless); void **__uv_hub_info_list; EXPORT_SYMBOL_GPL(__uv_hub_info_list); @@ -417,12 +399,6 @@ static __initdata struct uv_gam_range_s *_gr_table; #define SOCK_EMPTY ((unsigned short)~0) -extern int uv_hub_info_version(void) -{ - return UV_HUB_INFO_VERSION; -} -EXPORT_SYMBOL(uv_hub_info_version); - /* Default UV memory block size is 2GB */ static unsigned long mem_block_size __initdata = (2UL << 30); @@ -590,12 +566,21 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) static void uv_send_IPI_one(int cpu, int vector) { - unsigned long apicid; - int pnode; + unsigned long apicid = per_cpu(x86_cpu_to_apicid, cpu); + int pnode = uv_apicid_to_pnode(apicid); + unsigned long dmode, val; + + if (vector == NMI_VECTOR) + dmode = dest_NMI; + else + dmode = dest_Fixed; + + val = (1UL << UVH_IPI_INT_SEND_SHFT) | + ((apicid | uv_apicid_hibits) << UVH_IPI_INT_APIC_ID_SHFT) | + (dmode << UVH_IPI_INT_DELIVERY_MODE_SHFT) | + (vector << UVH_IPI_INT_VECTOR_SHFT); - apicid = per_cpu(x86_cpu_to_apicid, cpu); - pnode = uv_apicid_to_pnode(apicid); - uv_hub_send_ipi(pnode, apicid, vector); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } static void uv_send_IPI_mask(const struct cpumask *mask, int vector) @@ -797,42 +782,6 @@ static __init void map_high(char *id, unsigned long base, int pshift, int bshift init_extra_mapping_wb(paddr, bytes); } -static __init void map_gru_distributed(unsigned long c) -{ - union uvh_rh_gam_gru_overlay_config_mmr_u gru; - u64 paddr; - unsigned long bytes; - int nid; - - gru.v = c; - - /* Only base bits 42:28 relevant in dist mode */ - gru_dist_base = gru.v & 0x000007fff0000000UL; - if (!gru_dist_base) { - pr_info("UV: Map GRU_DIST base address NULL\n"); - return; - } - - bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; - gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1); - gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1); - gru_dist_base &= gru_dist_lmask; /* Clear bits above M */ - - for_each_online_node(nid) { - paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) | - gru_dist_base; - init_extra_mapping_wb(paddr, bytes); - gru_first_node_paddr = min(paddr, gru_first_node_paddr); - gru_last_node_paddr = max(paddr, gru_last_node_paddr); - } - - /* Save upper (63:M) bits of address only for is_GRU_range */ - gru_first_node_paddr &= gru_dist_umask; - gru_last_node_paddr &= gru_dist_umask; - - pr_debug("UV: Map GRU_DIST base 0x%016llx 0x%016llx - 0x%016llx\n", gru_dist_base, gru_first_node_paddr, gru_last_node_paddr); -} - static __init void map_gru_high(int max_pnode) { union uvh_rh_gam_gru_overlay_config_mmr_u gru; @@ -846,12 +795,6 @@ static __init void map_gru_high(int max_pnode) return; } - /* Only UV3 has distributed GRU mode */ - if (is_uv3_hub() && gru.s3.mode) { - map_gru_distributed(gru.v); - return; - } - base = (gru.v & mask) >> shift; map_high("GRU", base, shift, shift, max_pnode, map_wb); gru_start_paddr = ((u64)base << shift); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index c2a47016f243..828be792231e 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -57,9 +57,6 @@ int main(void) BLANK(); #undef ENTRY - OFFSET(TSS_ist, tss_struct, x86_tss.ist); - DEFINE(DB_STACK_OFFSET, offsetof(struct cea_exception_stacks, DB_stack) - - offsetof(struct cea_exception_stacks, DB1_stack)); BLANK(); #ifdef CONFIG_STACKPROTECTOR diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index e1efe44ebefc..83d9cad4e68b 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -3,6 +3,7 @@ #include <linux/types.h> #include <linux/audit.h> #include <asm/unistd.h> +#include <asm/audit.h> static unsigned dir_class[] = { #include <asm-generic/audit_dir_write.h> @@ -41,7 +42,6 @@ int audit_classify_arch(int arch) int audit_classify_syscall(int abi, unsigned syscall) { #ifdef CONFIG_IA32_EMULATION - extern int ia32_classify_syscall(unsigned); if (abi == AUDIT_ARCH_I386) return ia32_classify_syscall(syscall); #endif diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 7dc4ad68eb41..dba6a83bc349 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -13,6 +13,9 @@ endif KCOV_INSTRUMENT_common.o := n KCOV_INSTRUMENT_perf_event.o := n +# As above, instrumenting secondary CPU boot code causes boot hangs. +KCSAN_SANITIZE_common.o := n + # Make sure load_percpu_segment has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_common.o := $(nostackp) diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index 676022e71791..1da9b1c9a2db 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -10,10 +10,10 @@ */ #include <linux/interrupt.h> -#include <asm/acrn.h> #include <asm/apic.h> #include <asm/desc.h> #include <asm/hypervisor.h> +#include <asm/idtentry.h> #include <asm/irq_regs.h> static uint32_t __init acrn_detect(void) @@ -24,7 +24,7 @@ static uint32_t __init acrn_detect(void) static void __init acrn_init_platform(void) { /* Setup the IDT for ACRN hypervisor callback */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, acrn_hv_callback_vector); + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback); } static bool acrn_x2apic_available(void) @@ -39,7 +39,7 @@ static bool acrn_x2apic_available(void) static void (*acrn_intr_handler)(void); -__visible void __irq_entry acrn_hv_vector_handler(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_acrn_hv_callback) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -50,13 +50,12 @@ __visible void __irq_entry acrn_hv_vector_handler(struct pt_regs *regs) * will block the interrupt whose vector is lower than * HYPERVISOR_CALLBACK_VECTOR. */ - entering_ack_irq(); + ack_APIC_irq(); inc_irq_stat(irq_hv_callback_count); if (acrn_intr_handler) acrn_intr_handler(); - exiting_irq(); set_irq_regs(old_regs); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 547ad7bbf0e0..d4806eac9325 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -18,6 +18,7 @@ #include <asm/pci-direct.h> #include <asm/delay.h> #include <asm/debugreg.h> +#include <asm/resctrl.h> #ifdef CONFIG_X86_64 # include <asm/mmconfig.h> @@ -597,6 +598,8 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) x86_amd_ls_cfg_ssbd_mask = 1ULL << bit; } } + + resctrl_cpu_detect(c); } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -1142,8 +1145,7 @@ static const int amd_erratum_383[] = /* #1054: Instructions Retired Performance Counter May Be Inaccurate */ static const int amd_erratum_1054[] = - AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ed54b3b21c39..0b71970d2d3d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -15,6 +15,7 @@ #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched/smt.h> +#include <linux/pgtable.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> @@ -26,7 +27,6 @@ #include <asm/vmx.h> #include <asm/paravirt.h> #include <asm/alternative.h> -#include <asm/pgtable.h> #include <asm/set_memory.h> #include <asm/intel-family.h> #include <asm/e820/api.h> @@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void); static void __init mds_select_mitigation(void); static void __init mds_print_mitigation(void); static void __init taa_select_mitigation(void); +static void __init srbds_select_mitigation(void); /* The base value of the SPEC_CTRL MSR that always has to be preserved. */ u64 x86_spec_ctrl_base; @@ -108,6 +109,7 @@ void __init check_bugs(void) l1tf_select_mitigation(); mds_select_mitigation(); taa_select_mitigation(); + srbds_select_mitigation(); /* * As MDS and TAA mitigations are inter-related, print MDS @@ -398,6 +400,97 @@ static int __init tsx_async_abort_parse_cmdline(char *str) early_param("tsx_async_abort", tsx_async_abort_parse_cmdline); #undef pr_fmt +#define pr_fmt(fmt) "SRBDS: " fmt + +enum srbds_mitigations { + SRBDS_MITIGATION_OFF, + SRBDS_MITIGATION_UCODE_NEEDED, + SRBDS_MITIGATION_FULL, + SRBDS_MITIGATION_TSX_OFF, + SRBDS_MITIGATION_HYPERVISOR, +}; + +static enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL; + +static const char * const srbds_strings[] = { + [SRBDS_MITIGATION_OFF] = "Vulnerable", + [SRBDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [SRBDS_MITIGATION_FULL] = "Mitigation: Microcode", + [SRBDS_MITIGATION_TSX_OFF] = "Mitigation: TSX disabled", + [SRBDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status", +}; + +static bool srbds_off; + +void update_srbds_msr(void) +{ + u64 mcu_ctrl; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return; + + if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED) + return; + + rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); + + switch (srbds_mitigation) { + case SRBDS_MITIGATION_OFF: + case SRBDS_MITIGATION_TSX_OFF: + mcu_ctrl |= RNGDS_MITG_DIS; + break; + case SRBDS_MITIGATION_FULL: + mcu_ctrl &= ~RNGDS_MITG_DIS; + break; + default: + break; + } + + wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); +} + +static void __init srbds_select_mitigation(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return; + + /* + * Check to see if this is one of the MDS_NO systems supporting + * TSX that are only exposed to SRBDS when TSX is enabled. + */ + ia32_cap = x86_read_arch_cap_msr(); + if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM)) + srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; + else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR; + else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) + srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED; + else if (cpu_mitigations_off() || srbds_off) + srbds_mitigation = SRBDS_MITIGATION_OFF; + + update_srbds_msr(); + pr_info("%s\n", srbds_strings[srbds_mitigation]); +} + +static int __init srbds_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!boot_cpu_has_bug(X86_BUG_SRBDS)) + return 0; + + srbds_off = !strcmp(str, "off"); + return 0; +} +early_param("srbds", srbds_parse_cmdline); + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V1 : " fmt enum spectre_v1_mitigation { @@ -495,7 +588,9 @@ early_param("nospectre_v1", nospectre_v1_cmdline); static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE; -static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init = +static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = + SPECTRE_V2_USER_NONE; +static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; #ifdef CONFIG_RETPOLINE @@ -641,15 +736,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) break; } - /* - * At this point, an STIBP mode other than "off" has been set. - * If STIBP support is not being forced, check if STIBP always-on - * is preferred. - */ - if (mode != SPECTRE_V2_USER_STRICT && - boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) - mode = SPECTRE_V2_USER_STRICT_PREFERRED; - /* Initialize Indirect Branch Prediction Barrier */ if (boot_cpu_has(X86_FEATURE_IBPB)) { setup_force_cpu_cap(X86_FEATURE_USE_IBPB); @@ -672,23 +758,36 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", static_key_enabled(&switch_mm_always_ibpb) ? "always-on" : "conditional"); + + spectre_v2_user_ibpb = mode; } - /* If enhanced IBRS is enabled no STIBP required */ - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + /* + * If enhanced IBRS is enabled or SMT impossible, STIBP is not + * required. + */ + if (!smt_possible || spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return; /* - * If SMT is not possible or STIBP is not available clear the STIBP - * mode. + * At this point, an STIBP mode other than "off" has been set. + * If STIBP support is not being forced, check if STIBP always-on + * is preferred. + */ + if (mode != SPECTRE_V2_USER_STRICT && + boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + + /* + * If STIBP is not available, clear the STIBP mode. */ - if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP)) + if (!boot_cpu_has(X86_FEATURE_STIBP)) mode = SPECTRE_V2_USER_NONE; + + spectre_v2_user_stibp = mode; + set_mode: - spectre_v2_user = mode; - /* Only print the STIBP mode when SMT possible */ - if (smt_possible) - pr_info("%s\n", spectre_v2_user_strings[mode]); + pr_info("%s\n", spectre_v2_user_strings[mode]); } static const char * const spectre_v2_strings[] = { @@ -921,7 +1020,7 @@ void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; case SPECTRE_V2_USER_STRICT: @@ -1164,14 +1263,19 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { case PR_SPEC_ENABLE: - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; /* * Indirect branch speculation is always disabled in strict - * mode. + * mode. It can neither be enabled if it was force-disabled + * by a previous prctl call. + */ - if (spectre_v2_user == SPECTRE_V2_USER_STRICT || - spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + task_spec_ib_force_disable(task)) return -EPERM; task_clear_spec_ib_disable(task); task_update_spec_tif(task); @@ -1182,10 +1286,12 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) * Indirect branch speculation is always allowed when * mitigation is force disabled. */ - if (spectre_v2_user == SPECTRE_V2_USER_NONE) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user == SPECTRE_V2_USER_STRICT || - spectre_v2_user == SPECTRE_V2_USER_STRICT_PREFERRED) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) return 0; task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) @@ -1216,7 +1322,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) { if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); - if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP) + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif @@ -1247,22 +1354,24 @@ static int ib_prctl_get(struct task_struct *task) if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) return PR_SPEC_NOT_AFFECTED; - switch (spectre_v2_user) { - case SPECTRE_V2_USER_NONE: + if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && + spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - case SPECTRE_V2_USER_PRCTL: - case SPECTRE_V2_USER_SECCOMP: + else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - case SPECTRE_V2_USER_STRICT: - case SPECTRE_V2_USER_STRICT_PREFERRED: - return PR_SPEC_DISABLE; - default: + } else return PR_SPEC_NOT_AFFECTED; - } } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) @@ -1501,7 +1610,7 @@ static char *stibp_state(void) if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) return ""; - switch (spectre_v2_user) { + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: return ", STIBP: disabled"; case SPECTRE_V2_USER_STRICT: @@ -1528,6 +1637,11 @@ static char *ibpb_state(void) return ""; } +static ssize_t srbds_show_state(char *buf) +{ + return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1572,6 +1686,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_ITLB_MULTIHIT: return itlb_multihit_show_state(buf); + case X86_BUG_SRBDS: + return srbds_show_state(buf); + default: break; } @@ -1618,4 +1735,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr { return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT); } + +ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index bed0cb83fe24..043d93cdcaad 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -21,6 +21,7 @@ #include <linux/smp.h> #include <linux/io.h> #include <linux/syscore_ops.h> +#include <linux/pgtable.h> #include <asm/stackprotector.h> #include <asm/perf_event.h> @@ -35,7 +36,6 @@ #include <asm/vsyscall.h> #include <linux/topology.h> #include <linux/cpumask.h> -#include <asm/pgtable.h> #include <linux/atomic.h> #include <asm/proto.h> #include <asm/setup.h> @@ -387,7 +387,30 @@ set_register: bits_missing); } } -EXPORT_SYMBOL(native_write_cr4); +#if IS_MODULE(CONFIG_LKDTM) +EXPORT_SYMBOL_GPL(native_write_cr4); +#endif + +void cr4_update_irqsoff(unsigned long set, unsigned long clear) +{ + unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4); + + lockdep_assert_irqs_disabled(); + + newval = (cr4 & ~clear) | set; + if (newval != cr4) { + this_cpu_write(cpu_tlbstate.cr4, newval); + __write_cr4(newval); + } +} +EXPORT_SYMBOL(cr4_update_irqsoff); + +/* Read the CR4 shadow. */ +unsigned long cr4_read_shadow(void) +{ + return this_cpu_read(cpu_tlbstate.cr4); +} +EXPORT_SYMBOL_GPL(cr4_read_shadow); void cr4_init(void) { @@ -854,30 +877,6 @@ static void init_speculation_control(struct cpuinfo_x86 *c) } } -static void init_cqm(struct cpuinfo_x86 *c) -{ - if (!cpu_has(c, X86_FEATURE_CQM_LLC)) { - c->x86_cache_max_rmid = -1; - c->x86_cache_occ_scale = -1; - return; - } - - /* will be overridden if occupancy monitoring exists */ - c->x86_cache_max_rmid = cpuid_ebx(0xf); - - if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) || - cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) || - cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) { - u32 eax, ebx, ecx, edx; - - /* QoS sub-leaf, EAX=0Fh, ECX=1 */ - cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx); - - c->x86_cache_max_rmid = ecx; - c->x86_cache_occ_scale = ebx; - } -} - void get_cpu_cap(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; @@ -945,7 +944,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c) init_scattered_cpuid_features(c); init_speculation_control(c); - init_cqm(c); /* * Clear/Set all flags overridden by options, after probe. @@ -1075,9 +1073,30 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} }; -static bool __init cpu_matches(unsigned long which) +#define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ + X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, steppings, \ + X86_FEATURE_ANY, issues) + +#define SRBDS BIT(0) + +static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { + VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0xC), SRBDS), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0xD), SRBDS), + {} +}; + +static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long which) { - const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist); + const struct x86_cpu_id *m = x86_match_cpu(table); return m && !!(m->driver_data & which); } @@ -1097,31 +1116,34 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) u64 ia32_cap = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ - if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && + !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); - if (cpu_matches(NO_SPECULATION)) + if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - if (!cpu_matches(NO_SPECTRE_V2)) + if (!cpu_matches(cpu_vuln_whitelist, NO_SPECTRE_V2)) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); - if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && + if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && + !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); if (ia32_cap & ARCH_CAP_IBRS_ALL) setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); - if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) { + if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && + !(ia32_cap & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); - if (cpu_matches(MSBDS_ONLY)) + if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); } - if (!cpu_matches(NO_SWAPGS)) + if (!cpu_matches(cpu_vuln_whitelist, NO_SWAPGS)) setup_force_cpu_bug(X86_BUG_SWAPGS); /* @@ -1139,7 +1161,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); - if (cpu_matches(NO_MELTDOWN)) + /* + * SRBDS affects CPUs which support RDRAND or RDSEED and are listed + * in the vulnerability blacklist. + */ + if ((cpu_has(c, X86_FEATURE_RDRAND) || + cpu_has(c, X86_FEATURE_RDSEED)) && + cpu_matches(cpu_vuln_blacklist, SRBDS)) + setup_force_cpu_bug(X86_BUG_SRBDS); + + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ @@ -1148,7 +1179,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); - if (cpu_matches(NO_L1TF)) + if (cpu_matches(cpu_vuln_whitelist, NO_L1TF)) return; setup_force_cpu_bug(X86_BUG_L1TF); @@ -1377,20 +1408,6 @@ static void generic_identify(struct cpuinfo_x86 *c) #endif } -static void x86_init_cache_qos(struct cpuinfo_x86 *c) -{ - /* - * The heavy lifting of max_rmid and cache_occ_scale are handled - * in get_cpu_cap(). Here we just set the max_rmid for the boot_cpu - * in case CQM bits really aren't there in this CPU. - */ - if (c != &boot_cpu_data) { - boot_cpu_data.x86_cache_max_rmid = - min(boot_cpu_data.x86_cache_max_rmid, - c->x86_cache_max_rmid); - } -} - /* * Validate that ACPI/mptables have the same information about the * effective APIC id and update the package map. @@ -1503,7 +1520,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) #endif x86_init_rdrand(c); - x86_init_cache_qos(c); setup_pku(c); /* @@ -1591,6 +1607,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) mtrr_ap_init(); validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); + update_srbds_msr(); } static __init int setup_noclflush(char *arg) @@ -1689,25 +1706,6 @@ void syscall_init(void) X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } -DEFINE_PER_CPU(int, debug_stack_usage); -DEFINE_PER_CPU(u32, debug_idt_ctr); - -void debug_stack_set_zero(void) -{ - this_cpu_inc(debug_idt_ctr); - load_current_idt(); -} -NOKPROBE_SYMBOL(debug_stack_set_zero); - -void debug_stack_reset(void) -{ - if (WARN_ON(!this_cpu_read(debug_idt_ctr))) - return; - if (this_cpu_dec_return(debug_idt_ctr) == 0) - load_current_idt(); -} -NOKPROBE_SYMBOL(debug_stack_reset); - #else /* CONFIG_X86_64 */ DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 37fdefd14f28..fb538fccd24c 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -77,6 +77,7 @@ extern void detect_ht(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); extern void x86_spec_ctrl_setup_ap(void); +extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a19a680542ce..c25a67a34bd3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> +#include <linux/pgtable.h> #include <linux/string.h> #include <linux/bitops.h> @@ -11,7 +12,6 @@ #include <linux/uaccess.h> #include <asm/cpufeature.h> -#include <asm/pgtable.h> #include <asm/msr.h> #include <asm/bugs.h> #include <asm/cpu.h> @@ -22,6 +22,7 @@ #include <asm/cpu_device_id.h> #include <asm/cmdline.h> #include <asm/traps.h> +#include <asm/resctrl.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> @@ -322,6 +323,11 @@ static void early_init_intel(struct cpuinfo_x86 *c) detect_ht_early(c); } +static void bsp_init_intel(struct cpuinfo_x86 *c) +{ + resctrl_cpu_detect(c); +} + #ifdef CONFIG_X86_32 /* * Early probe support logic for ppro memory erratum #50 @@ -961,6 +967,7 @@ static const struct cpu_dev intel_cpu_dev = { #endif .c_detect_tlb = intel_detect_tlb, .c_early_init = early_init_intel, + .c_bsp_init = bsp_init_intel, .c_init = init_intel, .c_x86_vendor = X86_VENDOR_INTEL, }; @@ -1135,9 +1142,12 @@ void switch_to_sld(unsigned long tifn) static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, 0), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, 0), + X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, 0), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, 1), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, 1), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, 1), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, 1), + X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, 1), {} }; diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index d3482eb43ff3..ad6776081e60 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -39,13 +39,18 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; m->vendor | m->family | m->model | m->feature; m++) { + for (m = match; + m->vendor | m->family | m->model | m->steppings | m->feature; + m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) continue; if (m->model != X86_MODEL_ANY && c->x86_model != m->model) continue; + if (m->steppings != X86_STEPPING_ANY && + !(BIT(c->x86_stepping) & m->steppings)) + continue; if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) continue; return m; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 52de616a8065..99be063fcb1b 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -192,7 +192,12 @@ EXPORT_SYMBOL_GPL(smca_banks); static char buf_mcatype[MAX_MCATYPE_NAME_LEN]; static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); -static DEFINE_PER_CPU(unsigned int, bank_map); /* see which banks are on */ + +/* + * A list of the banks enabled on each logical CPU. Controls which respective + * descriptors to initialize later in mce_threshold_create_device(). + */ +static DEFINE_PER_CPU(unsigned int, bank_map); /* Map of banks that have more than MCA_MISC0 available. */ static DEFINE_PER_CPU(u32, smca_misc_banks_map); @@ -381,6 +386,10 @@ static void threshold_restart_bank(void *_tr) struct thresh_restart *tr = _tr; u32 hi, lo; + /* sysfs write might race against an offline operation */ + if (this_cpu_read(threshold_banks)) + return; + rdmsr(tr->b->address, lo, hi); if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) @@ -568,14 +577,19 @@ bool amd_filter_mce(struct mce *m) { enum smca_bank_types bank_type = smca_get_bank_type(m->bank); struct cpuinfo_x86 *c = &boot_cpu_data; - u8 xec = (m->status >> 16) & 0x3F; /* See Family 17h Models 10h-2Fh Erratum #1114. */ if (c->x86 == 0x17 && c->x86_model >= 0x10 && c->x86_model <= 0x2F && - bank_type == SMCA_IF && xec == 10) + bank_type == SMCA_IF && XEC(m->status, 0x3f) == 10) return true; + /* NB GART TLB error reporting is disabled by default. */ + if (c->x86 < 0x17) { + if (m->bank == 4 && XEC(m->status, 0x1f) == 0x5) + return true; + } + return false; } @@ -907,14 +921,13 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) mce_log(&m); } -asmlinkage __visible void __irq_entry smp_deferred_error_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error) { - entering_irq(); trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); inc_irq_stat(irq_deferred_error_count); deferred_error_int_vector(); trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); - exiting_ack_irq(); + ack_APIC_irq(); } /* @@ -1016,13 +1029,22 @@ static void log_and_reset_block(struct threshold_block *block) static void amd_threshold_interrupt(void) { struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL; + struct threshold_bank **bp = this_cpu_read(threshold_banks); unsigned int bank, cpu = smp_processor_id(); + /* + * Validate that the threshold bank has been initialized already. The + * handler is installed at boot time, but on a hotplug event the + * interrupt might fire before the data has been initialized. + */ + if (!bp) + return; + for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; - first_block = per_cpu(threshold_banks, cpu)[bank]->blocks; + first_block = bp[bank]->blocks; if (!first_block) continue; @@ -1071,7 +1093,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size) memset(&tr, 0, sizeof(tr)); tr.b = b; - smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); + if (smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1)) + return -ENODEV; return size; } @@ -1095,7 +1118,8 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size) b->threshold_limit = new; tr.b = b; - smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1); + if (smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1)) + return -ENODEV; return size; } @@ -1104,7 +1128,9 @@ static ssize_t show_error_count(struct threshold_block *b, char *buf) { u32 lo, hi; - rdmsr_on_cpu(b->cpu, b->address, &lo, &hi); + /* CPU might be offline by now */ + if (rdmsr_on_cpu(b->cpu, b->address, &lo, &hi)) + return -ENODEV; return sprintf(buf, "%u\n", ((hi & THRESHOLD_MAX) - (THRESHOLD_MAX - b->threshold_limit))); @@ -1209,10 +1235,10 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb u32 low, high; int err; - if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS)) + if ((bank >= this_cpu_read(mce_num_banks)) || (block >= NR_BLOCKS)) return 0; - if (rdmsr_safe_on_cpu(cpu, address, &low, &high)) + if (rdmsr_safe(address, &low, &high)) return 0; if (!(high & MASK_VALID_HI)) { @@ -1247,6 +1273,7 @@ static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb INIT_LIST_HEAD(&b->miscj); + /* This is safe as @tb is not visible yet */ if (tb->blocks) list_add(&b->miscj, &tb->blocks->miscj); else @@ -1267,13 +1294,12 @@ recurse: if (b) kobject_uevent(&b->kobj, KOBJ_ADD); - return err; + return 0; out_free: if (b) { - kobject_put(&b->kobj); list_del(&b->miscj); - kfree(b); + kobject_put(&b->kobj); } return err; } @@ -1302,9 +1328,10 @@ static int __threshold_add_blocks(struct threshold_bank *b) return err; } -static int threshold_create_bank(unsigned int cpu, unsigned int bank) +static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, + unsigned int bank) { - struct device *dev = per_cpu(mce_device, cpu); + struct device *dev = this_cpu_read(mce_device); struct amd_northbridge *nb = NULL; struct threshold_bank *b = NULL; const char *name = get_name(bank, NULL); @@ -1324,7 +1351,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - per_cpu(threshold_banks, cpu)[bank] = b; + bp[bank] = b; refcount_inc(&b->cpus); err = __threshold_add_blocks(b); @@ -1339,6 +1366,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; } + /* Associate the bank with the per-CPU MCE device */ b->kobj = kobject_create_and_add(name, &dev->kobj); if (!b->kobj) { err = -EINVAL; @@ -1346,6 +1374,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) } if (is_shared_bank(bank)) { + b->shared = 1; refcount_set(&b->cpus, 1); /* nb is already initialized, see above */ @@ -1357,16 +1386,16 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank)); if (err) - goto out_free; - - per_cpu(threshold_banks, cpu)[bank] = b; + goto out_kobj; + bp[bank] = b; return 0; - out_free: +out_kobj: + kobject_put(b->kobj); +out_free: kfree(b); - - out: +out: return err; } @@ -1375,21 +1404,16 @@ static void threshold_block_release(struct kobject *kobj) kfree(to_block(kobj)); } -static void deallocate_threshold_block(unsigned int cpu, unsigned int bank) +static void deallocate_threshold_blocks(struct threshold_bank *bank) { - struct threshold_block *pos = NULL; - struct threshold_block *tmp = NULL; - struct threshold_bank *head = per_cpu(threshold_banks, cpu)[bank]; + struct threshold_block *pos, *tmp; - if (!head) - return; - - list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) { + list_for_each_entry_safe(pos, tmp, &bank->blocks->miscj, miscj) { list_del(&pos->miscj); kobject_put(&pos->kobj); } - kobject_put(&head->blocks->kobj); + kobject_put(&bank->blocks->kobj); } static void __threshold_remove_blocks(struct threshold_bank *b) @@ -1403,122 +1427,102 @@ static void __threshold_remove_blocks(struct threshold_bank *b) kobject_del(&pos->kobj); } -static void threshold_remove_bank(unsigned int cpu, int bank) +static void threshold_remove_bank(struct threshold_bank *bank) { struct amd_northbridge *nb; - struct threshold_bank *b; - b = per_cpu(threshold_banks, cpu)[bank]; - if (!b) - return; + if (!bank->blocks) + goto out_free; - if (!b->blocks) - goto free_out; + if (!bank->shared) + goto out_dealloc; - if (is_shared_bank(bank)) { - if (!refcount_dec_and_test(&b->cpus)) { - __threshold_remove_blocks(b); - per_cpu(threshold_banks, cpu)[bank] = NULL; - return; - } else { - /* - * the last CPU on this node using the shared bank is - * going away, remove that bank now. - */ - nb = node_to_amd_nb(amd_get_nb_id(cpu)); - nb->bank4 = NULL; - } + if (!refcount_dec_and_test(&bank->cpus)) { + __threshold_remove_blocks(bank); + return; + } else { + /* + * The last CPU on this node using the shared bank is going + * away, remove that bank now. + */ + nb = node_to_amd_nb(amd_get_nb_id(smp_processor_id())); + nb->bank4 = NULL; } - deallocate_threshold_block(cpu, bank); +out_dealloc: + deallocate_threshold_blocks(bank); -free_out: - kobject_del(b->kobj); - kobject_put(b->kobj); - kfree(b); - per_cpu(threshold_banks, cpu)[bank] = NULL; +out_free: + kobject_put(bank->kobj); + kfree(bank); } int mce_threshold_remove_device(unsigned int cpu) { - unsigned int bank; + struct threshold_bank **bp = this_cpu_read(threshold_banks); + unsigned int bank, numbanks = this_cpu_read(mce_num_banks); - for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) { - if (!(per_cpu(bank_map, cpu) & (1 << bank))) - continue; - threshold_remove_bank(cpu, bank); + if (!bp) + return 0; + + /* + * Clear the pointer before cleaning up, so that the interrupt won't + * touch anything of this. + */ + this_cpu_write(threshold_banks, NULL); + + for (bank = 0; bank < numbanks; bank++) { + if (bp[bank]) { + threshold_remove_bank(bp[bank]); + bp[bank] = NULL; + } } - kfree(per_cpu(threshold_banks, cpu)); - per_cpu(threshold_banks, cpu) = NULL; + kfree(bp); return 0; } -/* create dir/files for all valid threshold banks */ +/** + * mce_threshold_create_device - Create the per-CPU MCE threshold device + * @cpu: The plugged in CPU + * + * Create directories and files for all valid threshold banks. + * + * This is invoked from the CPU hotplug callback which was installed in + * mcheck_init_device(). The invocation happens in context of the hotplug + * thread running on @cpu. The callback is invoked on all CPUs which are + * online when the callback is installed or during a real hotplug event. + */ int mce_threshold_create_device(unsigned int cpu) { - unsigned int bank; + unsigned int numbanks, bank; struct threshold_bank **bp; - int err = 0; + int err; - bp = per_cpu(threshold_banks, cpu); + if (!mce_flags.amd_threshold) + return 0; + + bp = this_cpu_read(threshold_banks); if (bp) return 0; - bp = kcalloc(per_cpu(mce_num_banks, cpu), sizeof(struct threshold_bank *), - GFP_KERNEL); + numbanks = this_cpu_read(mce_num_banks); + bp = kcalloc(numbanks, sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; - per_cpu(threshold_banks, cpu) = bp; - - for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) { - if (!(per_cpu(bank_map, cpu) & (1 << bank))) + for (bank = 0; bank < numbanks; ++bank) { + if (!(this_cpu_read(bank_map) & (1 << bank))) continue; - err = threshold_create_bank(cpu, bank); + err = threshold_create_bank(bp, cpu, bank); if (err) - goto err; - } - return err; -err: - mce_threshold_remove_device(cpu); - return err; -} - -static __init int threshold_init_device(void) -{ - unsigned lcpu = 0; - - /* to hit CPUs online before the notifier is up */ - for_each_online_cpu(lcpu) { - int err = mce_threshold_create_device(lcpu); - - if (err) - return err; + goto out_err; } + this_cpu_write(threshold_banks, bp); if (thresholding_irq_en) mce_threshold_vector = amd_threshold_interrupt; - return 0; +out_err: + mce_threshold_remove_device(cpu); + return err; } -/* - * there are 3 funcs which need to be _initcalled in a logic sequence: - * 1. xen_late_init_mcelog - * 2. mcheck_init_device - * 3. threshold_init_device - * - * xen_late_init_mcelog must register xen_mce_chrdev_device before - * native mce_chrdev_device registration if running under xen platform; - * - * mcheck_init_device should be inited before threshold_init_device to - * initialize mce_device, otherwise a NULL ptr dereference will cause panic. - * - * so we use following _initcalls - * 1. device_initcall(xen_late_init_mcelog); - * 2. device_initcall_sync(mcheck_init_device); - * 3. late_initcall(threshold_init_device); - * - * when running under xen, the initcall order is 1,2,3; - * on baremetal, we skip 1 and we do only 2 and 3. - */ -late_initcall(threshold_init_device); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 54165f3569e8..ce9120c4f740 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -42,6 +42,8 @@ #include <linux/export.h> #include <linux/jump_label.h> #include <linux/set_memory.h> +#include <linux/task_work.h> +#include <linux/hardirq.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -128,7 +130,7 @@ static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); /* Do initial initialization of a struct mce */ -void mce_setup(struct mce *m) +noinstr void mce_setup(struct mce *m) { memset(m, 0, sizeof(struct mce)); m->cpu = m->extcpu = smp_processor_id(); @@ -138,12 +140,12 @@ void mce_setup(struct mce *m) m->cpuid = cpuid_eax(1); m->socketid = cpu_data(m->extcpu).phys_proc_id; m->apicid = cpu_data(m->extcpu).initial_apicid; - rdmsrl(MSR_IA32_MCG_CAP, m->mcgcap); + m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); if (this_cpu_has(X86_FEATURE_INTEL_PPIN)) - rdmsrl(MSR_PPIN, m->ppin); + m->ppin = __rdmsr(MSR_PPIN); else if (this_cpu_has(X86_FEATURE_AMD_PPIN)) - rdmsrl(MSR_AMD_PPIN, m->ppin); + m->ppin = __rdmsr(MSR_AMD_PPIN); m->microcode = boot_cpu_data.microcode; } @@ -158,29 +160,17 @@ void mce_log(struct mce *m) } EXPORT_SYMBOL_GPL(mce_log); -/* - * We run the default notifier if we have only the UC, the first and the - * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS - * notifiers registered on the chain. - */ -#define NUM_DEFAULT_NOTIFIERS 3 -static atomic_t num_notifiers; - void mce_register_decode_chain(struct notifier_block *nb) { if (WARN_ON(nb->priority > MCE_PRIO_MCELOG && nb->priority < MCE_PRIO_EDAC)) return; - atomic_inc(&num_notifiers); - blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_register_decode_chain); void mce_unregister_decode_chain(struct notifier_block *nb) { - atomic_dec(&num_notifiers); - blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); @@ -263,6 +253,7 @@ static void __print_mce(struct mce *m) } pr_cont("\n"); + /* * Note this output is parsed by external tools and old fields * should not be changed. @@ -529,6 +520,14 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); +static bool whole_page(struct mce *m) +{ + if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV)) + return true; + + return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT; +} + bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) @@ -544,22 +543,7 @@ bool mce_is_correctable(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_correctable); -static bool cec_add_mce(struct mce *m) -{ - if (!m) - return false; - - /* We eat only correctable DRAM errors with usable addresses. */ - if (mce_is_memory_error(m) && - mce_is_correctable(m) && - mce_usable_address(m)) - if (!cec_add_elem(m->addr >> PAGE_SHIFT)) - return true; - - return false; -} - -static int mce_first_notifier(struct notifier_block *nb, unsigned long val, +static int mce_early_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct mce *m = (struct mce *)data; @@ -567,9 +551,6 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val, if (!m) return NOTIFY_DONE; - if (cec_add_mce(m)) - return NOTIFY_STOP; - /* Emit the trace record: */ trace_mce_record(m); @@ -580,9 +561,9 @@ static int mce_first_notifier(struct notifier_block *nb, unsigned long val, return NOTIFY_DONE; } -static struct notifier_block first_nb = { - .notifier_call = mce_first_notifier, - .priority = MCE_PRIO_FIRST, +static struct notifier_block early_nb = { + .notifier_call = mce_early_notifier, + .priority = MCE_PRIO_EARLY, }; static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, @@ -599,8 +580,10 @@ static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, return NOTIFY_DONE; pfn = mce->addr >> PAGE_SHIFT; - if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); + if (!memory_failure(pfn, 0)) { + set_mce_nospec(pfn, whole_page(mce)); + mce->kflags |= MCE_HANDLED_UC; + } return NOTIFY_OK; } @@ -618,10 +601,8 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val, if (!m) return NOTIFY_DONE; - if (atomic_read(&num_notifiers) > NUM_DEFAULT_NOTIFIERS) - return NOTIFY_DONE; - - __print_mce(m); + if (mca_cfg.print_all || !m->kflags) + __print_mce(m); return NOTIFY_DONE; } @@ -1086,23 +1067,6 @@ static void mce_clear_state(unsigned long *toclear) } } -static int do_memory_failure(struct mce *m) -{ - int flags = MF_ACTION_REQUIRED; - int ret; - - pr_err("Uncorrected hardware memory error in user-access at %llx", m->addr); - if (!(m->mcgstatus & MCG_STATUS_RIPV)) - flags |= MF_MUST_KILL; - ret = memory_failure(m->addr >> PAGE_SHIFT, flags); - if (ret) - pr_err("Memory error not recovered"); - else - set_mce_nospec(m->addr >> PAGE_SHIFT); - return ret; -} - - /* * Cases where we avoid rendezvous handler timeout: * 1) If this CPU is offline. @@ -1115,13 +1079,15 @@ static int do_memory_failure(struct mce *m) * kdump kernel establishing a new #MC handler where a broadcasted MCE * might not get handled properly. */ -static bool __mc_check_crashing_cpu(int cpu) +static noinstr bool mce_check_crashing_cpu(void) { + unsigned int cpu = smp_processor_id(); + if (cpu_is_offline(cpu) || (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; - mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS); if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { if (mcgstatus & MCG_STATUS_LMCES) @@ -1129,7 +1095,7 @@ static bool __mc_check_crashing_cpu(int cpu) } if (mcgstatus & MCG_STATUS_RIPV) { - mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); + __wrmsr(MSR_IA32_MCG_STATUS, 0, 0); return true; } } @@ -1204,6 +1170,30 @@ static void __mc_scan_banks(struct mce *m, struct mce *final, *m = *final; } +static void kill_me_now(struct callback_head *ch) +{ + force_sig(SIGBUS); +} + +static void kill_me_maybe(struct callback_head *cb) +{ + struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + int flags = MF_ACTION_REQUIRED; + + pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); + + if (!p->mce_ripv) + flags |= MF_MUST_KILL; + + if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) { + set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page); + return; + } + + pr_err("Memory error not recovered"); + kill_me_now(cb); +} + /* * The actual machine check handler. This only handles real * exceptions when something got corrupted coming in through int 18. @@ -1222,12 +1212,11 @@ static void __mc_scan_banks(struct mce *m, struct mce *final, * backing the user stack, tracing that reads the user stack will cause * potentially infinite recursion. */ -void notrace do_machine_check(struct pt_regs *regs, long error_code) +void noinstr do_machine_check(struct pt_regs *regs) { DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; - int cpu = smp_processor_id(); struct mce m, *final; char *msg = NULL; int worst = 0; @@ -1256,11 +1245,6 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code) */ int lmce = 1; - if (__mc_check_crashing_cpu(cpu)) - return; - - ist_enter(regs); - this_cpu_inc(mce_exception_count); mce_gather_info(&m, regs); @@ -1348,27 +1332,37 @@ void notrace do_machine_check(struct pt_regs *regs, long error_code) sync_core(); if (worst != MCE_AR_SEVERITY && !kill_it) - goto out_ist; + return; /* Fault was in user mode and we need to take some action */ if ((m.cs & 3) == 3) { - ist_begin_non_atomic(regs); - local_irq_enable(); - - if (kill_it || do_memory_failure(&m)) - force_sig(SIGBUS); - local_irq_disable(); - ist_end_non_atomic(); + /* If this triggers there is no way to recover. Die hard. */ + BUG_ON(!on_thread_stack() || !user_mode(regs)); + + current->mce_addr = m.addr; + current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(&m); + current->mce_kill_me.func = kill_me_maybe; + if (kill_it) + current->mce_kill_me.func = kill_me_now; + task_work_add(current, ¤t->mce_kill_me, true); } else { - if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) - mce_panic("Failed kernel mode recovery", &m, msg); + /* + * Handle an MCE which has happened in kernel space but from + * which the kernel can recover: ex_has_fault_handler() has + * already verified that the rIP at which the error happened is + * a rIP from which the kernel can recover (by jumping to + * recovery code specified in _ASM_EXTABLE_FAULT()) and the + * corresponding exception handler which would do that is the + * proper one. + */ + if (m.kflags & MCE_IN_KERNEL_RECOV) { + if (!fixup_exception(regs, X86_TRAP_MC, 0, 0)) + mce_panic("Failed kernel mode recovery", &m, msg); + } } - -out_ist: - ist_exit(regs); } EXPORT_SYMBOL_GPL(do_machine_check); -NOKPROBE_SYMBOL(do_machine_check); #ifndef CONFIG_MEMORY_FAILURE int memory_failure(unsigned long pfn, int flags) @@ -1756,6 +1750,7 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); + mce_flags.amd_threshold = 1; if (mce_flags.smca) { msr_ops.ctl = smca_ctl_reg; @@ -1893,21 +1888,84 @@ bool filter_mce(struct mce *m) } /* Handle unconfigured int18 (should never happen) */ -static void unexpected_machine_check(struct pt_regs *regs, long error_code) +static noinstr void unexpected_machine_check(struct pt_regs *regs) { + instrumentation_begin(); pr_err("CPU#%d: Unexpected int18 (Machine Check)\n", smp_processor_id()); + instrumentation_end(); } /* Call the installed machine check handler for this CPU setup. */ -void (*machine_check_vector)(struct pt_regs *, long error_code) = - unexpected_machine_check; +void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; -dotraplinkage notrace void do_mce(struct pt_regs *regs, long error_code) +static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { - machine_check_vector(regs, error_code); + /* + * Only required when from kernel mode. See + * mce_check_crashing_cpu() for details. + */ + if (machine_check_vector == do_machine_check && + mce_check_crashing_cpu()) + return; + + nmi_enter(); + /* + * The call targets are marked noinstr, but objtool can't figure + * that out because it's an indirect call. Annotate it. + */ + instrumentation_begin(); + trace_hardirqs_off_finish(); + machine_check_vector(regs); + if (regs->flags & X86_EFLAGS_IF) + trace_hardirqs_on_prepare(); + instrumentation_end(); + nmi_exit(); } -NOKPROBE_SYMBOL(do_mce); + +static __always_inline void exc_machine_check_user(struct pt_regs *regs) +{ + idtentry_enter_user(regs); + instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); + idtentry_exit_user(regs); +} + +#ifdef CONFIG_X86_64 +/* MCE hit kernel mode */ +DEFINE_IDTENTRY_MCE(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + exc_machine_check_kernel(regs); + local_db_restore(dr7); +} + +/* The user mode variant. */ +DEFINE_IDTENTRY_MCE_USER(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + exc_machine_check_user(regs); + local_db_restore(dr7); +} +#else +/* 32bit unified entry point */ +DEFINE_IDTENTRY_MCE(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + if (user_mode(regs)) + exc_machine_check_user(regs); + else + exc_machine_check_kernel(regs); + local_db_restore(dr7); +} +#endif /* * Called for each booted CPU to set up machine checks. @@ -1990,6 +2048,7 @@ void mce_disable_bank(int bank) * mce=no_cmci Disables CMCI * mce=no_lmce Disables LMCE * mce=dont_log_ce Clears corrected events silently, no log created for CEs. + * mce=print_all Print all machine check logs to console * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared. * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) * monarchtimeout is how long to wait for other CPUs on machine @@ -2018,6 +2077,8 @@ static int __init mcheck_enable(char *str) cfg->lmce_disabled = 1; else if (!strcmp(str, "dont_log_ce")) cfg->dont_log_ce = true; + else if (!strcmp(str, "print_all")) + cfg->print_all = true; else if (!strcmp(str, "ignore_ce")) cfg->ignore_ce = true; else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) @@ -2040,7 +2101,7 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); - mce_register_decode_chain(&first_nb); + mce_register_decode_chain(&early_nb); mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); @@ -2284,6 +2345,7 @@ static ssize_t store_int_with_restart(struct device *s, static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant); static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); +static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all); static struct dev_ext_attribute dev_attr_check_interval = { __ATTR(check_interval, 0644, device_show_int, store_int_with_restart), @@ -2308,6 +2370,7 @@ static struct device_attribute *mce_device_attrs[] = { #endif &dev_attr_monarch_timeout.attr, &dev_attr_dont_log_ce.attr, + &dev_attr_print_all.attr, &dev_attr_ignore_ce.attr, &dev_attr_cmci_disabled.attr, NULL @@ -2480,6 +2543,13 @@ static __init void mce_init_banks(void) } } +/* + * When running on XEN, this initcall is ordered against the XEN mcelog + * initcall: + * + * device_initcall(xen_late_init_mcelog); + * device_initcall_sync(mcheck_init_device); + */ static __init int mcheck_init_device(void) { int err; @@ -2511,6 +2581,10 @@ static __init int mcheck_init_device(void) if (err) goto err_out_mem; + /* + * Invokes mce_cpu_online() on all CPUs which are online when + * the state is installed. + */ err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online", mce_cpu_online, mce_cpu_pre_down); if (err < 0) @@ -2600,7 +2674,6 @@ static int __init mcheck_late_init(void) static_branch_inc(&mcsafe_key); mcheck_debugfs_init(); - cec_init(); /* * Flush out everything that has been logged during early boot, now that diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index d089567a9ce8..43c466020ed5 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -39,6 +39,9 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, struct mce *mce = (struct mce *)data; unsigned int entry; + if (mce->kflags & MCE_HANDLED_CEC) + return NOTIFY_DONE; + mutex_lock(&mce_chrdev_read_mutex); entry = mcelog->next; @@ -56,6 +59,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, memcpy(mcelog->entry + entry, mce, sizeof(struct mce)); mcelog->entry[entry].finished = 1; + mcelog->entry[entry].kflags = 0; /* wake processes polling /dev/mcelog */ wake_up_interruptible(&mce_chrdev_wait); @@ -63,6 +67,7 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val, unlock: mutex_unlock(&mce_chrdev_read_mutex); + mce->kflags |= MCE_HANDLED_MCELOG; return NOTIFY_OK; } @@ -324,6 +329,7 @@ static const struct file_operations mce_chrdev_ops = { .write = mce_chrdev_write, .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, .llseek = no_llseek, }; @@ -343,7 +349,7 @@ static __init int dev_mcelog_init_device(void) if (!mcelog) return -ENOMEM; - strncpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature)); + memcpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature)); mcelog->len = mce_log_len; mcelog->recordlen = sizeof(struct mce); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 3413b41b8d55..0593b192eb8f 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -146,9 +146,9 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs) regs.cs = m->cs; pregs = ®s; } - /* in mcheck exeception handler, irq will be disabled */ + /* do_machine_check() expects interrupts disabled -- at least */ local_irq_save(flags); - do_machine_check(pregs, 0); + do_machine_check(pregs); local_irq_restore(flags); m->finished = 0; } diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 3b008172ad73..6473070b5da4 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -9,7 +9,7 @@ #include <asm/mce.h> /* Pointer to the installed machine check handler for this CPU setup. */ -extern void (*machine_check_vector)(struct pt_regs *, long error_code); +extern void (*machine_check_vector)(struct pt_regs *); enum severity_level { MCE_NO_SEVERITY, @@ -119,6 +119,7 @@ struct mca_config { bool dont_log_ce; bool cmci_disabled; bool ignore_ce; + bool print_all; __u64 lmce_disabled : 1, disabled : 1, @@ -148,7 +149,7 @@ struct mce_vendor_flags { * Recovery. It indicates support for data poisoning in HW and deferred * error interrupts. */ - succor : 1, + succor : 1, /* * (AMD) SMCA: This bit indicates support for Scalable MCA which expands @@ -156,9 +157,12 @@ struct mce_vendor_flags { * banks. Also, to accommodate the new banks and registers, the MCA * register space is moved to a new MSR range. */ - smca : 1, + smca : 1, - __reserved_0 : 61; + /* AMD-style error thresholding banks present. */ + amd_threshold : 1, + + __reserved_0 : 60; }; extern struct mce_vendor_flags mce_flags; diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c index 4ae6df556526..19e90cae8e97 100644 --- a/arch/x86/kernel/cpu/mce/p5.c +++ b/arch/x86/kernel/cpu/mce/p5.c @@ -7,6 +7,7 @@ #include <linux/kernel.h> #include <linux/types.h> #include <linux/smp.h> +#include <linux/hardirq.h> #include <asm/processor.h> #include <asm/traps.h> @@ -20,12 +21,11 @@ int mce_p5_enabled __read_mostly; /* Machine check handler for Pentium class Intel CPUs: */ -static void pentium_machine_check(struct pt_regs *regs, long error_code) +static noinstr void pentium_machine_check(struct pt_regs *regs) { u32 loaddr, hi, lotype; - ist_enter(regs); - + instrumentation_begin(); rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); @@ -38,8 +38,7 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code) } add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - - ist_exit(regs); + instrumentation_end(); } /* Set up machine check reporting for processors with Intel style MCE: */ diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 87bcdc6dc2f0..e1da619add19 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -213,8 +213,12 @@ static int error_context(struct mce *m) { if ((m->cs & 3) == 3) return IN_USER; - if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) + + if (mc_recoverable(m->mcgstatus) && ex_has_fault_handler(m->ip)) { + m->kflags |= MCE_IN_KERNEL_RECOV; return IN_KERNEL_RECOV; + } + return IN_KERNEL; } diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index f36dc0742085..a7cd2d203ced 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -614,14 +614,13 @@ static void unexpected_thermal_interrupt(void) static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; -asmlinkage __visible void __irq_entry smp_thermal_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_thermal) { - entering_irq(); trace_thermal_apic_entry(THERMAL_APIC_VECTOR); inc_irq_stat(irq_thermal_count); smp_thermal_vector(); trace_thermal_apic_exit(THERMAL_APIC_VECTOR); - exiting_ack_irq(); + ack_APIC_irq(); } /* Thermal monitoring depends on APIC, ACPI and clock modulation */ diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index 28812cc15300..6a059a035021 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -21,12 +21,11 @@ static void default_threshold_interrupt(void) void (*mce_threshold_vector)(void) = default_threshold_interrupt; -asmlinkage __visible void __irq_entry smp_threshold_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_threshold) { - entering_irq(); trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); inc_irq_stat(irq_threshold_count); mce_threshold_vector(); trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); - exiting_ack_irq(); + ack_APIC_irq(); } diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c index a30ea13cccc2..9c9f0abd2d7f 100644 --- a/arch/x86/kernel/cpu/mce/winchip.c +++ b/arch/x86/kernel/cpu/mce/winchip.c @@ -6,6 +6,7 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/types.h> +#include <linux/hardirq.h> #include <asm/processor.h> #include <asm/traps.h> @@ -16,14 +17,12 @@ #include "internal.h" /* Machine check handler for WinChip C6: */ -static void winchip_machine_check(struct pt_regs *regs, long error_code) +static noinstr void winchip_machine_check(struct pt_regs *regs) { - ist_enter(regs); - + instrumentation_begin(); pr_emerg("CPU0: Machine Check Exception.\n"); add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); - - ist_exit(regs); + instrumentation_end(); } /* Set up machine check reporting on the Winchip C6 series */ diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 7019d4b2df0c..baec68b7e010 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -545,8 +545,7 @@ static int __wait_for_cpus(atomic_t *t, long long timeout) /* * Returns: * < 0 - on error - * 0 - no update done - * 1 - microcode was updated + * 0 - success (no update done or microcode was updated) */ static int __reload_late(void *info) { @@ -573,11 +572,11 @@ static int __reload_late(void *info) else goto wait_for_siblings; - if (err > UCODE_NFOUND) { - pr_warn("Error reloading microcode on CPU %d\n", cpu); + if (err >= UCODE_NFOUND) { + if (err == UCODE_ERROR) + pr_warn("Error reloading microcode on CPU %d\n", cpu); + ret = -1; - } else if (err == UCODE_UPDATED || err == UCODE_OK) { - ret = 1; } wait_for_siblings: @@ -608,7 +607,7 @@ static int microcode_reload_late(void) atomic_set(&late_cpus_out, 0); ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); - if (ret > 0) + if (ret == 0) microcode_check(); pr_info("Reload completed, microcode revision: 0x%x\n", boot_cpu_data.microcode); @@ -649,7 +648,7 @@ static ssize_t reload_store(struct device *dev, put: put_online_cpus(); - if (ret >= 0) + if (ret == 0) ret = size; return ret; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index ebf34c7bc8bc..af94f05a5c66 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -23,6 +23,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/desc.h> +#include <asm/idtentry.h> #include <asm/irq_regs.h> #include <asm/i8259.h> #include <asm/apic.h> @@ -40,11 +41,10 @@ static void (*hv_stimer0_handler)(void); static void (*hv_kexec_handler)(void); static void (*hv_crash_handler)(struct pt_regs *regs); -__visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback) { struct pt_regs *old_regs = set_irq_regs(regs); - entering_irq(); inc_irq_stat(irq_hv_callback_count); if (vmbus_handler) vmbus_handler(); @@ -52,7 +52,6 @@ __visible void __irq_entry hyperv_vector_handler(struct pt_regs *regs) if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED) ack_APIC_irq(); - exiting_irq(); set_irq_regs(old_regs); } @@ -73,19 +72,16 @@ EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq); * Routines to do per-architecture handling of stimer0 * interrupts when in Direct Mode */ - -__visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0) { struct pt_regs *old_regs = set_irq_regs(regs); - entering_irq(); inc_irq_stat(hyperv_stimer0_count); if (hv_stimer0_handler) hv_stimer0_handler(); add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0); ack_APIC_irq(); - exiting_irq(); set_irq_regs(old_regs); } @@ -331,17 +327,19 @@ static void __init ms_hyperv_init_platform(void) x86_platform.apic_post_init = hyperv_init; hyperv_setup_mmu_ops(); /* Setup the IDT for hypervisor callback */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback); /* Setup the IDT for reenlightenment notifications */ - if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) + if (ms_hyperv.features & HV_X64_ACCESS_REENLIGHTENMENT) { alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, - hyperv_reenlightenment_vector); + asm_sysvec_hyperv_reenlightenment); + } /* Setup the IDT for stimer0 */ - if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) + if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) { alloc_intr_gate(HYPERV_STIMER0_VECTOR, - hv_stimer0_callback_vector); + asm_sysvec_hyperv_stimer0); + } # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 51b9190c628b..23ad8e953dfb 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -761,7 +761,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock) /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb(); + flush_tlb_local(); /* Save MTRR state */ rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); @@ -778,7 +778,7 @@ static void post_set(void) __releases(set_atomicity_lock) { /* Flush TLBs (no need to flush caches - they are disabled) */ count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb(); + flush_tlb_local(); /* Intel (P6) standard MTRRs */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index 9556930cd8c1..a5ee607a3b89 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -63,6 +63,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr) case 15: return msr - MSR_P4_BPU_PERFCTR0; } + fallthrough; + case X86_VENDOR_ZHAOXIN: + case X86_VENDOR_CENTAUR: + return msr - MSR_ARCH_PERFMON_PERFCTR0; } return 0; } @@ -92,6 +96,10 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr) case 15: return msr - MSR_P4_BSU_ESCR0; } + fallthrough; + case X86_VENDOR_ZHAOXIN: + case X86_VENDOR_CENTAUR: + return msr - MSR_ARCH_PERFMON_EVENTSEL0; } return 0; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index d8cc5223b7ce..12f967c6b603 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -22,7 +22,7 @@ #include <linux/cpuhotplug.h> #include <asm/intel-family.h> -#include <asm/resctrl_sched.h> +#include <asm/resctrl.h> #include "internal.h" /* Mutex to protect rdtgroup access. */ @@ -958,6 +958,36 @@ static __init void rdt_init_res_defs(void) static enum cpuhp_state rdt_online; +/* Runs once on the BSP during boot. */ +void resctrl_cpu_detect(struct cpuinfo_x86 *c) +{ + if (!cpu_has(c, X86_FEATURE_CQM_LLC)) { + c->x86_cache_max_rmid = -1; + c->x86_cache_occ_scale = -1; + c->x86_cache_mbm_width_offset = -1; + return; + } + + /* will be overridden if occupancy monitoring exists */ + c->x86_cache_max_rmid = cpuid_ebx(0xf); + + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) || + cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) || + cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) { + u32 eax, ebx, ecx, edx; + + /* QoS sub-leaf, EAX=0Fh, ECX=1 */ + cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx); + + c->x86_cache_max_rmid = ecx; + c->x86_cache_occ_scale = ebx; + if (c->x86_vendor == X86_VENDOR_INTEL) + c->x86_cache_mbm_width_offset = eax & 0xff; + else + c->x86_cache_mbm_width_offset = -1; + } +} + static int __init resctrl_late_init(void) { struct rdt_resource *r; diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 055c8613b531..934c8fb8a64a 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -495,14 +495,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, return ret; } -void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, - struct rdtgroup *rdtgrp, int evtid, int first) +void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, + struct rdt_domain *d, struct rdtgroup *rdtgrp, + int evtid, int first) { /* * setup the parameters to send to the IPI to read the data. */ rr->rgrp = rdtgrp; rr->evtid = evtid; + rr->r = r; rr->d = d; rr->val = 0; rr->first = first; @@ -539,7 +541,7 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) goto out; } - mon_event_read(&rr, d, rdtgrp, evtid, false); + mon_event_read(&rr, r, d, rdtgrp, evtid, false); if (rr.val & RMID_VAL_ERROR) seq_puts(m, "Error\n"); diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 3dd13f3a8b23..f20a47d120b1 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -31,7 +31,7 @@ #define CQM_LIMBOCHECK_INTERVAL 1000 -#define MBM_CNTR_WIDTH 24 +#define MBM_CNTR_WIDTH_BASE 24 #define MBM_OVERFLOW_INTERVAL 1000 #define MAX_MBA_BW 100u #define MBA_IS_LINEAR 0x4 @@ -40,6 +40,12 @@ #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) +/* + * With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for + * data to be returned. The counter width is discovered from the hardware + * as an offset from MBM_CNTR_WIDTH_BASE. + */ +#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE) struct rdt_fs_context { @@ -87,6 +93,7 @@ union mon_data_bits { struct rmid_read { struct rdtgroup *rgrp; + struct rdt_resource *r; struct rdt_domain *d; int evtid; bool first; @@ -460,6 +467,7 @@ struct rdt_resource { struct list_head evt_list; int num_rmid; unsigned int mon_scale; + unsigned int mbm_width; unsigned long fflags; }; @@ -587,8 +595,9 @@ void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, unsigned int dom_id); void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r, struct rdt_domain *d); -void mon_event_read(struct rmid_read *rr, struct rdt_domain *d, - struct rdtgroup *rdtgrp, int evtid, int first); +void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, + struct rdt_domain *d, struct rdtgroup *rdtgrp, + int evtid, int first); void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms); void mbm_handle_overflow(struct work_struct *work); diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 773124b0e18a..837d7d012b7b 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -214,9 +214,9 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr) +static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) { - u64 shift = 64 - MBM_CNTR_WIDTH, chunks; + u64 shift = 64 - width, chunks; chunks = (cur_msr << shift) - (prev_msr << shift); return chunks >>= shift; @@ -256,7 +256,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) return 0; } - chunks = mbm_overflow_count(m->prev_msr, tval); + chunks = mbm_overflow_count(m->prev_msr, tval, rr->r->mbm_width); m->chunks += chunks; m->prev_msr = tval; @@ -278,7 +278,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) return; - chunks = mbm_overflow_count(m->prev_bw_msr, tval); + chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width); m->chunks_bw += chunks; m->chunks = m->chunks_bw; cur_bw = (chunks * r->mon_scale) >> 20; @@ -433,11 +433,12 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) } } -static void mbm_update(struct rdt_domain *d, int rmid) +static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) { struct rmid_read rr; rr.first = false; + rr.r = r; rr.d = d; /* @@ -510,6 +511,7 @@ void mbm_handle_overflow(struct work_struct *work) struct rdtgroup *prgrp, *crgrp; int cpu = smp_processor_id(); struct list_head *head; + struct rdt_resource *r; struct rdt_domain *d; mutex_lock(&rdtgroup_mutex); @@ -517,16 +519,18 @@ void mbm_handle_overflow(struct work_struct *work) if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; - d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); + r = &rdt_resources_all[RDT_RESOURCE_L3]; + + d = get_domain_from_cpu(cpu, r); if (!d) goto out_unlock; list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - mbm_update(d, prgrp->mon.rmid); + mbm_update(r, d, prgrp->mon.rmid); head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) - mbm_update(d, crgrp->mon.rmid); + mbm_update(r, d, crgrp->mon.rmid); if (is_mba_sc(NULL)) update_mba_bw(prgrp, d); @@ -614,11 +618,18 @@ static void l3_mon_evt_init(struct rdt_resource *r) int rdt_get_mon_l3_config(struct rdt_resource *r) { + unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset; unsigned int cl_size = boot_cpu_data.x86_cache_size; int ret; r->mon_scale = boot_cpu_data.x86_cache_occ_scale; r->num_rmid = boot_cpu_data.x86_cache_max_rmid + 1; + r->mbm_width = MBM_CNTR_WIDTH_BASE; + + if (mbm_offset > 0 && mbm_offset <= MBM_CNTR_WIDTH_OFFSET_MAX) + r->mbm_width += mbm_offset; + else if (mbm_offset > MBM_CNTR_WIDTH_OFFSET_MAX) + pr_warn("Ignoring impossible MBM counter offset\n"); /* * A reasonable upper limit on the max threshold is the number diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index d7623e1b927d..0daf2f1cf7a8 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -24,7 +24,7 @@ #include <asm/cacheflush.h> #include <asm/intel-family.h> -#include <asm/resctrl_sched.h> +#include <asm/resctrl.h> #include <asm/perf_event.h> #include "../../events/perf_event.h" /* For X86_CONFIG() */ @@ -1326,9 +1326,9 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) * pseudo-locked region will still be here on return. * * The mutex has to be released temporarily to avoid a potential - * deadlock with the mm->mmap_sem semaphore which is obtained in - * the device_create() and debugfs_create_dir() callpath below - * as well as before the mmap() callback is called. + * deadlock with the mm->mmap_lock which is obtained in the + * device_create() and debugfs_create_dir() callpath below as well as + * before the mmap() callback is called. */ mutex_unlock(&rdtgroup_mutex); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5a359d9fcc05..23b4b61319d3 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -29,7 +29,7 @@ #include <uapi/linux/magic.h> -#include <asm/resctrl_sched.h> +#include <asm/resctrl.h> #include "internal.h" DEFINE_STATIC_KEY_FALSE(rdt_enable_key); @@ -2472,7 +2472,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn, goto out_destroy; if (is_mbm_event(mevt->evtid)) - mon_event_read(&rr, d, prgrp, mevt->evtid, true); + mon_event_read(&rr, r, d, prgrp, mevt->evtid, true); } kernfs_activate(kn); return 0; @@ -3199,10 +3199,10 @@ int __init rdtgroup_init(void) * during the debugfs directory creation also &sb->s_type->i_mutex_key * (the lockdep class of inode->i_rwsem). Other filesystem * interactions (eg. SyS_getdents) have the lock ordering: - * &sb->s_type->i_mutex_key --> &mm->mmap_sem - * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex + * &sb->s_type->i_mutex_key --> &mm->mmap_lock + * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex * is taken, thus creating dependency: - * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause + * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause * issues considering the other two lock dependencies. * By creating the debugfs directory here we avoid a dependency * that may cause deadlock (even though file operations cannot diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/crash_core_32.c index c0159a7bca6d..8a89c109e20a 100644 --- a/arch/x86/kernel/crash_core_32.c +++ b/arch/x86/kernel/crash_core_32.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/crash_core.h> +#include <linux/pgtable.h> -#include <asm/pgtable.h> #include <asm/setup.h> void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/crash_core_64.c index 845a57eb4eb7..7d255f882afe 100644 --- a/arch/x86/kernel/crash_core_64.c +++ b/arch/x86/kernel/crash_core_64.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/crash_core.h> +#include <linux/pgtable.h> -#include <asm/pgtable.h> #include <asm/setup.h> void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index 3793646f0fb5..759d392cbe9f 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -6,12 +6,10 @@ #include <linux/fs.h> #include <linux/uaccess.h> -#include <asm/pgtable.h> #include <asm/processor.h> #include <asm/desc.h> #include <asm/traps.h> -extern void double_fault(void); #define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM) #define TSS(x) this_cpu_read(cpu_tss_rw.x86_tss.x) @@ -22,7 +20,7 @@ static void set_df_gdt_entry(unsigned int cpu); * Called by double_fault with CR0.TS and EFLAGS.NT cleared. The CPU thinks * we're running the doublefault task. Cannot return. */ -asmlinkage notrace void __noreturn doublefault_shim(void) +asmlinkage noinstr void __noreturn doublefault_shim(void) { unsigned long cr2; struct pt_regs regs; @@ -41,7 +39,7 @@ asmlinkage notrace void __noreturn doublefault_shim(void) * Fill in pt_regs. A downside of doing this in C is that the unwinder * won't see it (no ENCODE_FRAME_POINTER), so a nested stack dump * won't successfully unwind to the source of the double fault. - * The main dump from do_double_fault() is fine, though, since it + * The main dump from exc_double_fault() is fine, though, since it * uses these regs directly. * * If anyone ever cares, this could be moved to asm. @@ -71,7 +69,7 @@ asmlinkage notrace void __noreturn doublefault_shim(void) regs.cx = TSS(cx); regs.bx = TSS(bx); - do_double_fault(®s, 0, cr2); + exc_double_fault(®s, 0, cr2); /* * x86_32 does not save the original CR3 anywhere on a task switch. @@ -85,7 +83,6 @@ asmlinkage notrace void __noreturn doublefault_shim(void) */ panic("cannot return from double fault\n"); } -NOKPROBE_SYMBOL(doublefault_shim); DEFINE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack) = { .tss = { @@ -96,7 +93,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack) = { .ldt = 0, .io_bitmap_base = IO_BITMAP_OFFSET_INVALID, - .ip = (unsigned long) double_fault, + .ip = (unsigned long) asm_exc_double_fault, .flags = X86_EFLAGS_FIXED, .es = __USER_DS, .cs = __KERNEL_CS, diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index ae64ec7f752f..456511b2284e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -65,7 +65,7 @@ bool in_entry_stack(unsigned long *stack, struct stack_info *info) } static void printk_stack_address(unsigned long address, int reliable, - char *log_lvl) + const char *log_lvl) { touch_nmi_watchdog(); printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); @@ -160,7 +160,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, } void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, char *log_lvl) + unsigned long *stack, const char *log_lvl) { struct unwind_state state; struct stack_info stack_info = {0}; @@ -279,7 +279,8 @@ next: } } -void show_stack(struct task_struct *task, unsigned long *sp) +void show_stack(struct task_struct *task, unsigned long *sp, + const char *loglvl) { task = task ? : current; @@ -290,7 +291,7 @@ void show_stack(struct task_struct *task, unsigned long *sp) if (!sp && task == current) sp = get_stack_pointer(current, NULL); - show_trace_log_lvl(task, NULL, sp, KERN_DEFAULT); + show_trace_log_lvl(task, NULL, sp, loglvl); } void show_stack_regs(struct pt_regs *regs) diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 8e3a8fedfa4d..722fd712e1cf 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -87,7 +87,6 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) static bool in_doublefault_stack(unsigned long *stack, struct stack_info *info) { -#ifdef CONFIG_DOUBLEFAULT struct cpu_entry_area *cea = get_cpu_entry_area(raw_smp_processor_id()); struct doublefault_stack *ss = &cea->doublefault_stack; @@ -103,9 +102,6 @@ static bool in_doublefault_stack(unsigned long *stack, struct stack_info *info) info->next_sp = (unsigned long *)this_cpu_read(cpu_tss_rw.x86_tss.sp); return true; -#else - return false; -#endif } diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 460ae7f66818..4a94d38cd141 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -22,15 +22,13 @@ static const char * const exception_stack_names[] = { [ ESTACK_DF ] = "#DF", [ ESTACK_NMI ] = "NMI", - [ ESTACK_DB2 ] = "#DB2", - [ ESTACK_DB1 ] = "#DB1", [ ESTACK_DB ] = "#DB", [ ESTACK_MCE ] = "#MC", }; const char *stack_type_name(enum stack_type type) { - BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); + BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); if (type == STACK_TYPE_IRQ) return "IRQ"; @@ -79,7 +77,6 @@ static const struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = { EPAGERANGE(DF), EPAGERANGE(NMI), - EPAGERANGE(DB1), EPAGERANGE(DB), EPAGERANGE(MCE), }; @@ -91,7 +88,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info) struct pt_regs *regs; unsigned int k; - BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); + BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); begin = (unsigned long)__this_cpu_read(cea_exception_stacks); /* diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index c5399e80c59c..983cd53ed4c9 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -910,14 +910,6 @@ static int __init parse_memmap_one(char *p) return -EINVAL; if (!strncmp(p, "exactmap", 8)) { -#ifdef CONFIG_CRASH_DUMP - /* - * If we are doing a crash dump, we still need to know - * the real memory size before the original memory map is - * reset. - */ - saved_max_pfn = e820__end_of_ram_pfn(); -#endif e820_table->nr_entries = 0; userdef = 1; return 0; @@ -999,7 +991,15 @@ void __init e820__reserve_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + + /* + * SETUP_EFI is supplied by kexec and does not need to be + * reserved. + */ + if (data->type != SETUP_EFI) + e820__range_update_kexec(pa_data, + sizeof(*data) + data->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); if (data->type == SETUP_INDIRECT && ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 9b33904251a9..d3c531d3b244 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -8,6 +8,7 @@ #include <linux/pci_regs.h> #include <linux/pci_ids.h> #include <linux/errno.h> +#include <linux/pgtable.h> #include <asm/io.h> #include <asm/processor.h> #include <asm/fcntl.h> @@ -15,12 +16,8 @@ #include <xen/hvc-console.h> #include <asm/pci-direct.h> #include <asm/fixmap.h> -#include <asm/intel-mid.h> -#include <asm/pgtable.h> #include <linux/usb/ehci_def.h> #include <linux/usb/xhci-dbgp.h> -#include <linux/efi.h> -#include <asm/efi.h> #include <asm/pci_x86.h> /* Simple VGA output */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 12e7d4406c32..4fe7af58cfe1 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -29,7 +29,7 @@ #include <linux/percpu.h> #include <linux/gfp.h> #include <linux/random.h> -#include <asm/pgtable.h> +#include <linux/pgtable.h> #include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/espfix.h> diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 12c70840980e..06c818967bb6 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -291,15 +291,13 @@ void fpu__drop(struct fpu *fpu) } /* - * Clear FPU registers by setting them up from - * the init fpstate: + * Clear FPU registers by setting them up from the init fpstate. + * Caller must do fpregs_[un]lock() around it. */ -static inline void copy_init_fpstate_to_fpregs(void) +static inline void copy_init_fpstate_to_fpregs(u64 features_mask) { - fpregs_lock(); - if (use_xsave()) - copy_kernel_to_xregs(&init_fpstate.xsave, -1); + copy_kernel_to_xregs(&init_fpstate.xsave, features_mask); else if (static_cpu_has(X86_FEATURE_FXSR)) copy_kernel_to_fxregs(&init_fpstate.fxsave); else @@ -307,9 +305,6 @@ static inline void copy_init_fpstate_to_fpregs(void) if (boot_cpu_has(X86_FEATURE_OSPKE)) copy_init_pkru_to_fpregs(); - - fpregs_mark_activate(); - fpregs_unlock(); } /* @@ -318,18 +313,40 @@ static inline void copy_init_fpstate_to_fpregs(void) * Called by sys_execve(), by the signal handler code and by various * error paths. */ -void fpu__clear(struct fpu *fpu) +static void fpu__clear(struct fpu *fpu, bool user_only) { - WARN_ON_FPU(fpu != ¤t->thread.fpu); /* Almost certainly an anomaly */ + WARN_ON_FPU(fpu != ¤t->thread.fpu); - fpu__drop(fpu); + if (!static_cpu_has(X86_FEATURE_FPU)) { + fpu__drop(fpu); + fpu__initialize(fpu); + return; + } - /* - * Make sure fpstate is cleared and initialized. - */ - fpu__initialize(fpu); - if (static_cpu_has(X86_FEATURE_FPU)) - copy_init_fpstate_to_fpregs(); + fpregs_lock(); + + if (user_only) { + if (!fpregs_state_valid(fpu, smp_processor_id()) && + xfeatures_mask_supervisor()) + copy_kernel_to_xregs(&fpu->state.xsave, + xfeatures_mask_supervisor()); + copy_init_fpstate_to_fpregs(xfeatures_mask_user()); + } else { + copy_init_fpstate_to_fpregs(xfeatures_mask_all); + } + + fpregs_mark_activate(); + fpregs_unlock(); +} + +void fpu__clear_user_states(struct fpu *fpu) +{ + fpu__clear(fpu, true); +} + +void fpu__clear_all(struct fpu *fpu) +{ + fpu__clear(fpu, false); } /* diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 6ce7e0a23268..61ddc3a5e5c2 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -224,7 +224,8 @@ static void __init fpu__init_system_xstate_size_legacy(void) */ u64 __init fpu__get_supported_xfeatures_mask(void) { - return XCNTXT_MASK; + return XFEATURE_MASK_USER_SUPPORTED | + XFEATURE_MASK_SUPERVISOR_SUPPORTED; } /* Legacy code to initialize eager fpu mode. */ diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index d652b939ccfb..bd1d0649f8ce 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -139,7 +139,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, } else { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); if (!ret) - ret = validate_xstate_header(&xsave->header); + ret = validate_user_xstate_header(&xsave->header); } /* diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 400a05e1c1c5..9393a445d73c 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -211,9 +211,9 @@ retry: } static inline void -sanitize_restored_xstate(union fpregs_state *state, - struct user_i387_ia32_struct *ia32_env, - u64 xfeatures, int fx_only) +sanitize_restored_user_xstate(union fpregs_state *state, + struct user_i387_ia32_struct *ia32_env, + u64 user_xfeatures, int fx_only) { struct xregs_state *xsave = &state->xsave; struct xstate_header *header = &xsave->header; @@ -226,13 +226,22 @@ sanitize_restored_xstate(union fpregs_state *state, */ /* - * Init the state that is not present in the memory - * layout and not enabled by the OS. + * 'user_xfeatures' might have bits clear which are + * set in header->xfeatures. This represents features that + * were in init state prior to a signal delivery, and need + * to be reset back to the init state. Clear any user + * feature bits which are set in the kernel buffer to get + * them back to the init state. + * + * Supervisor state is unchanged by input from userspace. + * Ensure supervisor state bits stay set and supervisor + * state is not modified. */ if (fx_only) header->xfeatures = XFEATURE_MASK_FPSSE; else - header->xfeatures &= xfeatures; + header->xfeatures &= user_xfeatures | + xfeatures_mask_supervisor(); } if (use_fxsr()) { @@ -252,16 +261,24 @@ sanitize_restored_xstate(union fpregs_state *state, */ static int copy_user_to_fpregs_zeroing(void __user *buf, u64 xbv, int fx_only) { + u64 init_bv; + int r; + if (use_xsave()) { if (fx_only) { - u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE; - copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); - return copy_user_to_fxregs(buf); + init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE; + + r = copy_user_to_fxregs(buf); + if (!r) + copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); + return r; } else { - u64 init_bv = xfeatures_mask & ~xbv; - if (unlikely(init_bv)) + init_bv = xfeatures_mask_user() & ~xbv; + + r = copy_user_to_xregs(buf, xbv); + if (!r && unlikely(init_bv)) copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); - return copy_user_to_xregs(buf, xbv); + return r; } } else if (use_fxsr()) { return copy_user_to_fxregs(buf); @@ -277,7 +294,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) struct task_struct *tsk = current; struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; - u64 xfeatures = 0; + u64 user_xfeatures = 0; int fx_only = 0; int ret = 0; @@ -285,7 +302,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) IS_ENABLED(CONFIG_IA32_EMULATION)); if (!buf) { - fpu__clear(fpu); + fpu__clear_user_states(fpu); return 0; } @@ -310,32 +327,14 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) trace_x86_fpu_xstate_check_failed(fpu); } else { state_size = fx_sw_user.xstate_size; - xfeatures = fx_sw_user.xfeatures; + user_xfeatures = fx_sw_user.xfeatures; } } - /* - * The current state of the FPU registers does not matter. By setting - * TIF_NEED_FPU_LOAD unconditionally it is ensured that the our xstate - * is not modified on context switch and that the xstate is considered - * to be loaded again on return to userland (overriding last_cpu avoids - * the optimisation). - */ - set_thread_flag(TIF_NEED_FPU_LOAD); - __fpu_invalidate_fpregs_state(fpu); - if ((unsigned long)buf_fx % 64) fx_only = 1; - /* - * For 32-bit frames with fxstate, copy the fxstate so it can be - * reconstructed later. - */ - if (ia32_fxstate) { - ret = __copy_from_user(&env, buf, sizeof(env)); - if (ret) - goto err_out; - envp = &env; - } else { + + if (!ia32_fxstate) { /* * Attempt to restore the FPU registers directly from user * memory. For that to succeed, the user access cannot cause @@ -345,20 +344,65 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) */ fpregs_lock(); pagefault_disable(); - ret = copy_user_to_fpregs_zeroing(buf_fx, xfeatures, fx_only); + ret = copy_user_to_fpregs_zeroing(buf_fx, user_xfeatures, fx_only); pagefault_enable(); if (!ret) { + + /* + * Restore supervisor states: previous context switch + * etc has done XSAVES and saved the supervisor states + * in the kernel buffer from which they can be restored + * now. + * + * We cannot do a single XRSTORS here - which would + * be nice - because the rest of the FPU registers are + * being restored from a user buffer directly. The + * single XRSTORS happens below, when the user buffer + * has been copied to the kernel one. + */ + if (test_thread_flag(TIF_NEED_FPU_LOAD) && + xfeatures_mask_supervisor()) + copy_kernel_to_xregs(&fpu->state.xsave, + xfeatures_mask_supervisor()); fpregs_mark_activate(); fpregs_unlock(); return 0; } - fpregs_deactivate(fpu); fpregs_unlock(); + } else { + /* + * For 32-bit frames with fxstate, copy the fxstate so it can + * be reconstructed later. + */ + ret = __copy_from_user(&env, buf, sizeof(env)); + if (ret) + goto err_out; + envp = &env; } + /* + * By setting TIF_NEED_FPU_LOAD it is ensured that our xstate is + * not modified on context switch and that the xstate is considered + * to be loaded again on return to userland (overriding last_cpu avoids + * the optimisation). + */ + fpregs_lock(); + + if (!test_thread_flag(TIF_NEED_FPU_LOAD)) { + + /* + * Supervisor states are not modified by user space input. Save + * current supervisor states first and invalidate the FPU regs. + */ + if (xfeatures_mask_supervisor()) + copy_supervisor_to_kernel(&fpu->state.xsave); + set_thread_flag(TIF_NEED_FPU_LOAD); + } + __fpu_invalidate_fpregs_state(fpu); + fpregs_unlock(); if (use_xsave() && !fx_only) { - u64 init_bv = xfeatures_mask & ~xfeatures; + u64 init_bv = xfeatures_mask_user() & ~user_xfeatures; if (using_compacted_format()) { ret = copy_user_to_xstate(&fpu->state.xsave, buf_fx); @@ -366,17 +410,24 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) ret = __copy_from_user(&fpu->state.xsave, buf_fx, state_size); if (!ret && state_size > offsetof(struct xregs_state, header)) - ret = validate_xstate_header(&fpu->state.xsave.header); + ret = validate_user_xstate_header(&fpu->state.xsave.header); } if (ret) goto err_out; - sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only); + sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, + fx_only); fpregs_lock(); if (unlikely(init_bv)) copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); - ret = copy_kernel_to_xregs_err(&fpu->state.xsave, xfeatures); + + /* + * Restore previously saved supervisor xstates along with + * copied-in user xstates. + */ + ret = copy_kernel_to_xregs_err(&fpu->state.xsave, + user_xfeatures | xfeatures_mask_supervisor()); } else if (use_fxsr()) { ret = __copy_from_user(&fpu->state.fxsave, buf_fx, state_size); @@ -385,11 +436,14 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) goto err_out; } - sanitize_restored_xstate(&fpu->state, envp, xfeatures, fx_only); + sanitize_restored_user_xstate(&fpu->state, envp, user_xfeatures, + fx_only); fpregs_lock(); if (use_xsave()) { - u64 init_bv = xfeatures_mask & ~XFEATURE_MASK_FPSSE; + u64 init_bv; + + init_bv = xfeatures_mask_user() & ~XFEATURE_MASK_FPSSE; copy_kernel_to_xregs(&init_fpstate.xsave, init_bv); } @@ -410,7 +464,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) err_out: if (ret) - fpu__clear(fpu); + fpu__clear_user_states(fpu); return ret; } @@ -465,7 +519,7 @@ void fpu__init_prepare_fx_sw_frame(void) fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1; fx_sw_reserved.extended_size = size; - fx_sw_reserved.xfeatures = xfeatures_mask; + fx_sw_reserved.xfeatures = xfeatures_mask_user(); fx_sw_reserved.xstate_size = fpu_user_xstate_size; if (IS_ENABLED(CONFIG_IA32_EMULATION) || diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 6a54e83d5589..bda2e5eaca0e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -54,13 +54,15 @@ static short xsave_cpuid_features[] __initdata = { }; /* - * Mask of xstate features supported by the CPU and the kernel: + * This represents the full set of bits that should ever be set in a kernel + * XSAVE buffer, both supervisor and user xstates. */ -u64 xfeatures_mask __read_mostly; +u64 xfeatures_mask_all __read_mostly; static unsigned int xstate_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_sizes[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; static unsigned int xstate_comp_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; +static unsigned int xstate_supervisor_only_offsets[XFEATURE_MAX] = { [ 0 ... XFEATURE_MAX - 1] = -1}; /* * The XSAVE area of kernel can be in standard or compacted format; @@ -76,7 +78,7 @@ unsigned int fpu_user_xstate_size; */ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) { - u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask; + u64 xfeatures_missing = xfeatures_needed & ~xfeatures_mask_all; if (unlikely(feature_name)) { long xfeature_idx, max_idx; @@ -150,7 +152,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) * None of the feature bits are in init state. So nothing else * to do for us, as the memory layout is up to date. */ - if ((xfeatures & xfeatures_mask) == xfeatures_mask) + if ((xfeatures & xfeatures_mask_all) == xfeatures_mask_all) return; /* @@ -177,7 +179,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu) * in a special way already: */ feature_bit = 0x2; - xfeatures = (xfeatures_mask & ~xfeatures) >> 2; + xfeatures = (xfeatures_mask_user() & ~xfeatures) >> 2; /* * Update all the remaining memory layouts according to their @@ -205,30 +207,39 @@ void fpstate_sanitize_xstate(struct fpu *fpu) */ void fpu__init_cpu_xstate(void) { - if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask) + u64 unsup_bits; + + if (!boot_cpu_has(X86_FEATURE_XSAVE) || !xfeatures_mask_all) return; /* - * Make it clear that XSAVES supervisor states are not yet - * implemented should anyone expect it to work by changing - * bits in XFEATURE_MASK_* macros and XCR0. + * Unsupported supervisor xstates should not be found in + * the xfeatures mask. */ - WARN_ONCE((xfeatures_mask & XFEATURE_MASK_SUPERVISOR), - "x86/fpu: XSAVES supervisor states are not yet implemented.\n"); + unsup_bits = xfeatures_mask_all & XFEATURE_MASK_SUPERVISOR_UNSUPPORTED; + WARN_ONCE(unsup_bits, "x86/fpu: Found unsupported supervisor xstates: 0x%llx\n", + unsup_bits); - xfeatures_mask &= ~XFEATURE_MASK_SUPERVISOR; + xfeatures_mask_all &= ~XFEATURE_MASK_SUPERVISOR_UNSUPPORTED; cr4_set_bits(X86_CR4_OSXSAVE); - xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); + + /* + * XCR_XFEATURE_ENABLED_MASK (aka. XCR0) sets user features + * managed by XSAVE{C, OPT, S} and XRSTOR{S}. Only XSAVE user + * states can be set here. + */ + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user()); + + /* + * MSR_IA32_XSS sets supervisor states managed by XSAVES. + */ + if (boot_cpu_has(X86_FEATURE_XSAVES)) + wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); } -/* - * Note that in the future we will likely need a pair of - * functions here: one for user xstates and the other for - * system xstates. For now, they are the same. - */ -static int xfeature_enabled(enum xfeature xfeature) +static bool xfeature_enabled(enum xfeature xfeature) { - return !!(xfeatures_mask & (1UL << xfeature)); + return xfeatures_mask_all & BIT_ULL(xfeature); } /* @@ -383,6 +394,33 @@ static void __init setup_xstate_comp_offsets(void) } /* + * Setup offsets of a supervisor-state-only XSAVES buffer: + * + * The offsets stored in xstate_comp_offsets[] only work for one specific + * value of the Requested Feature BitMap (RFBM). In cases where a different + * RFBM value is used, a different set of offsets is required. This set of + * offsets is for when RFBM=xfeatures_mask_supervisor(). + */ +static void __init setup_supervisor_only_offsets(void) +{ + unsigned int next_offset; + int i; + + next_offset = FXSAVE_SIZE + XSAVE_HDR_SIZE; + + for (i = FIRST_EXTENDED_XFEATURE; i < XFEATURE_MAX; i++) { + if (!xfeature_enabled(i) || !xfeature_is_supervisor(i)) + continue; + + if (xfeature_is_aligned(i)) + next_offset = ALIGN(next_offset, 64); + + xstate_supervisor_only_offsets[i] = next_offset; + next_offset += xstate_sizes[i]; + } +} + +/* * Print out xstate component offsets and sizes */ static void __init print_xstate_offset_size(void) @@ -415,7 +453,7 @@ static void __init setup_init_fpu_buf(void) if (boot_cpu_has(X86_FEATURE_XSAVES)) init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | - xfeatures_mask; + xfeatures_mask_all; /* * Init all the features state with header.xfeatures being 0x0 @@ -438,7 +476,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr) * format. Checking a supervisor state's uncompacted offset is * an error. */ - if (XFEATURE_MASK_SUPERVISOR & BIT_ULL(xfeature_nr)) { + if (XFEATURE_MASK_SUPERVISOR_ALL & BIT_ULL(xfeature_nr)) { WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr); return -1; } @@ -472,10 +510,10 @@ int using_compacted_format(void) } /* Validate an xstate header supplied by userspace (ptrace or sigreturn) */ -int validate_xstate_header(const struct xstate_header *hdr) +int validate_user_xstate_header(const struct xstate_header *hdr) { /* No unknown or supervisor features may be set */ - if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR)) + if (hdr->xfeatures & ~xfeatures_mask_user()) return -EINVAL; /* Userspace must use the uncompacted format */ @@ -610,15 +648,12 @@ static void do_extra_xstate_size_checks(void) /* - * Get total size of enabled xstates in XCR0/xfeatures_mask. + * Get total size of enabled xstates in XCR0 | IA32_XSS. * * Note the SDM's wording here. "sub-function 0" only enumerates * the size of the *user* states. If we use it to size a buffer * that we use 'XSAVES' on, we could potentially overflow the * buffer because 'XSAVES' saves system states too. - * - * Note that we do not currently set any bits on IA32_XSS so - * 'XCR0 | IA32_XSS == XCR0' for now. */ static unsigned int __init get_xsaves_size(void) { @@ -700,7 +735,7 @@ static int __init init_xstate_size(void) */ static void fpu__init_disable_system_xstate(void) { - xfeatures_mask = 0; + xfeatures_mask_all = 0; cr4_clear_bits(X86_CR4_OSXSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVE); } @@ -735,16 +770,26 @@ void __init fpu__init_system_xstate(void) return; } + /* + * Find user xstates supported by the processor. + */ cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); - xfeatures_mask = eax + ((u64)edx << 32); + xfeatures_mask_all = eax + ((u64)edx << 32); - if ((xfeatures_mask & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { + /* + * Find supervisor xstates supported by the processor. + */ + cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + xfeatures_mask_all |= ecx + ((u64)edx << 32); + + if ((xfeatures_mask_user() & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { /* * This indicates that something really unexpected happened * with the enumeration. Disable XSAVE and try to continue * booting without it. This is too early to BUG(). */ - pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", xfeatures_mask); + pr_err("x86/fpu: FP/SSE not present amongst the CPU's xstate features: 0x%llx.\n", + xfeatures_mask_all); goto out_disable; } @@ -753,10 +798,10 @@ void __init fpu__init_system_xstate(void) */ for (i = 0; i < ARRAY_SIZE(xsave_cpuid_features); i++) { if (!boot_cpu_has(xsave_cpuid_features[i])) - xfeatures_mask &= ~BIT(i); + xfeatures_mask_all &= ~BIT_ULL(i); } - xfeatures_mask &= fpu__get_supported_xfeatures_mask(); + xfeatures_mask_all &= fpu__get_supported_xfeatures_mask(); /* Enable xstate instructions to be able to continue with initialization: */ fpu__init_cpu_xstate(); @@ -768,15 +813,16 @@ void __init fpu__init_system_xstate(void) * Update info used for ptrace frames; use standard-format size and no * supervisor xstates: */ - update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR); + update_regset_xstate_info(fpu_user_xstate_size, xfeatures_mask_user()); fpu__init_prepare_fx_sw_frame(); setup_init_fpu_buf(); setup_xstate_comp_offsets(); + setup_supervisor_only_offsets(); print_xstate_offset_size(); pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n", - xfeatures_mask, + xfeatures_mask_all, fpu_kernel_xstate_size, boot_cpu_has(X86_FEATURE_XSAVES) ? "compacted" : "standard"); return; @@ -795,7 +841,14 @@ void fpu__resume_cpu(void) * Restore XCR0 on xsave capable CPUs: */ if (boot_cpu_has(X86_FEATURE_XSAVE)) - xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask); + xsetbv(XCR_XFEATURE_ENABLED_MASK, xfeatures_mask_user()); + + /* + * Restore IA32_XSS. The same CPUID bit enumerates support + * of XSAVES and MSR_IA32_XSS. + */ + if (boot_cpu_has(X86_FEATURE_XSAVES)) + wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); } /* @@ -840,10 +893,9 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr) /* * We should not ever be requesting features that we - * have not enabled. Remember that xfeatures_mask is - * what we write to the XCR0 register. + * have not enabled. */ - WARN_ONCE(!(xfeatures_mask & BIT_ULL(xfeature_nr)), + WARN_ONCE(!(xfeatures_mask_all & BIT_ULL(xfeature_nr)), "get of unsupported state"); /* * This assumes the last 'xsave*' instruction to @@ -1010,7 +1062,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of */ memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; - header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + header.xfeatures &= xfeatures_mask_user(); if (header.xfeatures & XFEATURE_MASK_FP) copy_part(0, off_mxcsr, @@ -1090,7 +1142,7 @@ int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned i */ memset(&header, 0, sizeof(header)); header.xfeatures = xsave->header.xfeatures; - header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR; + header.xfeatures &= xfeatures_mask_user(); /* * Copy xregs_state->header: @@ -1157,7 +1209,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) memcpy(&hdr, kbuf + offset, size); - if (validate_xstate_header(&hdr)) + if (validate_user_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { @@ -1183,7 +1235,7 @@ int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf) * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': */ - xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL; /* * Add back in the features that came in from userspace: @@ -1211,7 +1263,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) if (__copy_from_user(&hdr, ubuf + offset, size)) return -EFAULT; - if (validate_xstate_header(&hdr)) + if (validate_user_xstate_header(&hdr)) return -EINVAL; for (i = 0; i < XFEATURE_MAX; i++) { @@ -1239,7 +1291,7 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': */ - xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR; + xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR_ALL; /* * Add back in the features that came in from userspace: @@ -1249,6 +1301,61 @@ int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf) return 0; } +/* + * Save only supervisor states to the kernel buffer. This blows away all + * old states, and is intended to be used only in __fpu__restore_sig(), where + * user states are restored from the user buffer. + */ +void copy_supervisor_to_kernel(struct xregs_state *xstate) +{ + struct xstate_header *header; + u64 max_bit, min_bit; + u32 lmask, hmask; + int err, i; + + if (WARN_ON(!boot_cpu_has(X86_FEATURE_XSAVES))) + return; + + if (!xfeatures_mask_supervisor()) + return; + + max_bit = __fls(xfeatures_mask_supervisor()); + min_bit = __ffs(xfeatures_mask_supervisor()); + + lmask = xfeatures_mask_supervisor(); + hmask = xfeatures_mask_supervisor() >> 32; + XSTATE_OP(XSAVES, xstate, lmask, hmask, err); + + /* We should never fault when copying to a kernel buffer: */ + if (WARN_ON_FPU(err)) + return; + + /* + * At this point, the buffer has only supervisor states and must be + * converted back to normal kernel format. + */ + header = &xstate->header; + header->xcomp_bv |= xfeatures_mask_all; + + /* + * This only moves states up in the buffer. Start with + * the last state and move backwards so that states are + * not overwritten until after they are moved. Note: + * memmove() allows overlapping src/dst buffers. + */ + for (i = max_bit; i >= min_bit; i--) { + u8 *xbuf = (u8 *)xstate; + + if (!((header->xfeatures >> i) & 1)) + continue; + + /* Move xfeature 'i' into its normal location */ + memmove(xbuf + xstate_comp_offsets[i], + xbuf + xstate_supervisor_only_offsets[i], + xstate_sizes[i]); + } +} + #ifdef CONFIG_PROC_PID_ARCH_STATUS /* * Report the amount of time elapsed in millisecond since last AVX512 diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index b0e641793be4..c84d28e90a58 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -282,7 +282,8 @@ static inline void tramp_free(void *tramp) { } /* Defined as markers to the end of the ftrace default trampolines */ extern void ftrace_regs_caller_end(void); -extern void ftrace_epilogue(void); +extern void ftrace_regs_caller_ret(void); +extern void ftrace_caller_end(void); extern void ftrace_caller_op_ptr(void); extern void ftrace_regs_caller_op_ptr(void); @@ -334,7 +335,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) call_offset = (unsigned long)ftrace_regs_call; } else { start_offset = (unsigned long)ftrace_caller; - end_offset = (unsigned long)ftrace_epilogue; + end_offset = (unsigned long)ftrace_caller_end; op_offset = (unsigned long)ftrace_caller_op_ptr; call_offset = (unsigned long)ftrace_call; } @@ -366,6 +367,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) if (WARN_ON(ret < 0)) goto fail; + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller); + ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + if (WARN_ON(ret < 0)) + goto fail; + } + /* * The address of the ftrace_ops that is used for this trampoline * is stored at the end of the trampoline. This will be used to @@ -433,7 +441,7 @@ void set_ftrace_ops_ro(void) end_offset = (unsigned long)ftrace_regs_caller_end; } else { start_offset = (unsigned long)ftrace_caller; - end_offset = (unsigned long)ftrace_epilogue; + end_offset = (unsigned long)ftrace_caller_end; } size = end_offset - start_offset; size = size + RET_SIZE + sizeof(void *); diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index e8a9f8370112..e405fe1a8bf4 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -189,5 +189,5 @@ return_to_handler: movl %eax, %ecx popl %edx popl %eax - JMP_NOSPEC %ecx + JMP_NOSPEC ecx #endif diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 369e61faacfe..083a3da7bb73 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -12,7 +12,7 @@ #include <asm/frame.h> .code64 - .section .entry.text, "ax" + .section .text, "ax" #ifdef CONFIG_FRAME_POINTER /* Save parent and function stack frames (rip and rbp) */ @@ -23,7 +23,7 @@ #endif /* CONFIG_FRAME_POINTER */ /* Size of stack used to save mcount regs in save_mcount_regs */ -#define MCOUNT_REG_SIZE (SS+8 + MCOUNT_FRAME_SIZE) +#define MCOUNT_REG_SIZE (FRAME_SIZE + MCOUNT_FRAME_SIZE) /* * gcc -pg option adds a call to 'mcount' in most functions. @@ -77,7 +77,7 @@ /* * We add enough stack to save all regs. */ - subq $(MCOUNT_REG_SIZE - MCOUNT_FRAME_SIZE), %rsp + subq $(FRAME_SIZE), %rsp movq %rax, RAX(%rsp) movq %rcx, RCX(%rsp) movq %rdx, RDX(%rsp) @@ -157,8 +157,12 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) * think twice before adding any new code or changing the * layout here. */ -SYM_INNER_LABEL(ftrace_epilogue, SYM_L_GLOBAL) +SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) + jmp ftrace_epilogue +SYM_FUNC_END(ftrace_caller); + +SYM_FUNC_START(ftrace_epilogue) #ifdef CONFIG_FUNCTION_GRAPH_TRACER SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) jmp ftrace_stub @@ -170,14 +174,12 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) retq -SYM_FUNC_END(ftrace_caller) +SYM_FUNC_END(ftrace_epilogue) SYM_FUNC_START(ftrace_regs_caller) /* Save the current flags before any operations that can change them */ pushfq - UNWIND_HINT_SAVE - /* added 8 bytes to save flags */ save_mcount_regs 8 /* save_mcount_regs fills in first two parameters */ @@ -233,10 +235,13 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) movq ORIG_RAX(%rsp), %rax movq %rax, MCOUNT_REG_SIZE-8(%rsp) - /* If ORIG_RAX is anything but zero, make this a call to that */ + /* + * If ORIG_RAX is anything but zero, make this a call to that. + * See arch_ftrace_set_direct_caller(). + */ movq ORIG_RAX(%rsp), %rax - cmpq $0, %rax - je 1f + testq %rax, %rax + jz 1f /* Swap the flags with orig_rax */ movq MCOUNT_REG_SIZE(%rsp), %rdi @@ -244,20 +249,14 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) movq %rax, MCOUNT_REG_SIZE(%rsp) restore_mcount_regs 8 + /* Restore flags */ + popfq - jmp 2f +SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL); + UNWIND_HINT_RET_OFFSET + jmp ftrace_epilogue 1: restore_mcount_regs - - -2: - /* - * The stack layout is nondetermistic here, depending on which path was - * taken. This confuses objtool and ORC, rightfully so. For now, - * pretend the stack always looks like the non-direct case. - */ - UNWIND_HINT_RESTORE - /* Restore flags */ popfq @@ -268,7 +267,6 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) * to the return. */ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) - jmp ftrace_epilogue SYM_FUNC_END(ftrace_regs_caller) @@ -303,7 +301,7 @@ trace: * function tracing is enabled. */ movq ftrace_trace_function, %r8 - CALL_NOSPEC %r8 + CALL_NOSPEC r8 restore_mcount_regs jmp fgraph_trace @@ -340,6 +338,6 @@ SYM_CODE_START(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - JMP_NOSPEC %rdi + JMP_NOSPEC rdi SYM_CODE_END(return_to_handler) #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 206a4b6144c2..cbb71c1b574f 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -20,13 +20,13 @@ #include <linux/io.h> #include <linux/memblock.h> #include <linux/mem_encrypt.h> +#include <linux/pgtable.h> #include <asm/processor.h> #include <asm/proto.h> #include <asm/smp.h> #include <asm/setup.h> #include <asm/desc.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/kdebug.h> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 4bbc770af632..16da4ac01597 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -13,8 +13,8 @@ #include <linux/linkage.h> #include <linux/threads.h> #include <linux/init.h> +#include <linux/pgtable.h> #include <asm/segment.h> -#include <asm/pgtable.h> #include <asm/page.h> #include <asm/msr.h> #include <asm/cache.h> @@ -29,15 +29,16 @@ #ifdef CONFIG_PARAVIRT_XXL #include <asm/asm-offsets.h> #include <asm/paravirt.h> +#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg #else #define INTERRUPT_RETURN iretq +#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg #endif -/* we are not able to switch in one step to the final KERNEL ADDRESS SPACE +/* + * We are not able to switch in one step to the final KERNEL ADDRESS SPACE * because we need identity-mapped pages. - * */ - #define l4_index(x) (((x) >> 39) & 511) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 4d8d53ed02c9..8cdf29ffd95f 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -32,6 +32,8 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <asm/user.h> +#include <asm/desc.h> +#include <asm/tlbflush.h> /* Per cpu debug control register value */ DEFINE_PER_CPU(unsigned long, cpu_dr7); @@ -97,6 +99,8 @@ int arch_install_hw_breakpoint(struct perf_event *bp) unsigned long *dr7; int i; + lockdep_assert_irqs_disabled(); + for (i = 0; i < HBP_NUM; i++) { struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); @@ -115,6 +119,12 @@ int arch_install_hw_breakpoint(struct perf_event *bp) dr7 = this_cpu_ptr(&cpu_dr7); *dr7 |= encode_dr7(i, info->len, info->type); + /* + * Ensure we first write cpu_dr7 before we set the DR7 register. + * This ensures an NMI never see cpu_dr7 0 when DR7 is not. + */ + barrier(); + set_debugreg(*dr7, 7); if (info->mask) set_dr_addr_mask(info->mask, i); @@ -134,9 +144,11 @@ int arch_install_hw_breakpoint(struct perf_event *bp) void arch_uninstall_hw_breakpoint(struct perf_event *bp) { struct arch_hw_breakpoint *info = counter_arch_bp(bp); - unsigned long *dr7; + unsigned long dr7; int i; + lockdep_assert_irqs_disabled(); + for (i = 0; i < HBP_NUM; i++) { struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]); @@ -149,12 +161,20 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp) if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot")) return; - dr7 = this_cpu_ptr(&cpu_dr7); - *dr7 &= ~__encode_dr7(i, info->len, info->type); + dr7 = this_cpu_read(cpu_dr7); + dr7 &= ~__encode_dr7(i, info->len, info->type); - set_debugreg(*dr7, 7); + set_debugreg(dr7, 7); if (info->mask) set_dr_addr_mask(0, i); + + /* + * Ensure the write to cpu_dr7 is after we've set the DR7 register. + * This ensures an NMI never see cpu_dr7 0 when DR7 is not. + */ + barrier(); + + this_cpu_write(cpu_dr7, dr7); } static int arch_bp_generic_len(int x86_len) @@ -227,10 +247,76 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX); } +/* + * Checks whether the range [addr, end], overlaps the area [base, base + size). + */ +static inline bool within_area(unsigned long addr, unsigned long end, + unsigned long base, unsigned long size) +{ + return end >= base && addr < (base + size); +} + +/* + * Checks whether the range from addr to end, inclusive, overlaps the fixed + * mapped CPU entry area range or other ranges used for CPU entry. + */ +static inline bool within_cpu_entry(unsigned long addr, unsigned long end) +{ + int cpu; + + /* CPU entry erea is always used for CPU entry */ + if (within_area(addr, end, CPU_ENTRY_AREA_BASE, + CPU_ENTRY_AREA_TOTAL_SIZE)) + return true; + + for_each_possible_cpu(cpu) { + /* The original rw GDT is being used after load_direct_gdt() */ + if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu), + GDT_SIZE)) + return true; + + /* + * cpu_tss_rw is not directly referenced by hardware, but + * cpu_tss_rw is also used in CPU entry code, + */ + if (within_area(addr, end, + (unsigned long)&per_cpu(cpu_tss_rw, cpu), + sizeof(struct tss_struct))) + return true; + + /* + * cpu_tlbstate.user_pcid_flush_mask is used for CPU entry. + * If a data breakpoint on it, it will cause an unwanted #DB. + * Protect the full cpu_tlbstate structure to be sure. + */ + if (within_area(addr, end, + (unsigned long)&per_cpu(cpu_tlbstate, cpu), + sizeof(struct tlb_state))) + return true; + } + + return false; +} + static int arch_build_bp_info(struct perf_event *bp, const struct perf_event_attr *attr, struct arch_hw_breakpoint *hw) { + unsigned long bp_end; + + bp_end = attr->bp_addr + attr->bp_len - 1; + if (bp_end < attr->bp_addr) + return -EINVAL; + + /* + * Prevent any breakpoint of any type that overlaps the CPU + * entry area and data. This protects the IST stacks and also + * reduces the chance that we ever find out what happens if + * there's a data breakpoint on the GDT, IDT, or TSS. + */ + if (within_cpu_entry(attr->bp_addr, bp_end)) + return -EINVAL; + hw->address = attr->bp_addr; hw->mask = 0; @@ -439,7 +525,7 @@ static int hw_breakpoint_handler(struct die_args *args) { int i, cpu, rc = NOTIFY_STOP; struct perf_event *bp; - unsigned long dr7, dr6; + unsigned long dr6; unsigned long *dr6_p; /* The DR6 value is pointed by args->err */ @@ -454,9 +540,6 @@ static int hw_breakpoint_handler(struct die_args *args) if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; - get_debugreg(dr7, 7); - /* Disable breakpoints during exception handling */ - set_debugreg(0UL, 7); /* * Assert that local interrupts are disabled * Reset the DRn bits in the virtualized register value. @@ -513,7 +596,6 @@ static int hw_breakpoint_handler(struct die_args *args) (dr6 & (~DR_TRAP_BITS))) rc = NOTIFY_DONE; - set_debugreg(dr7, 7); put_cpu(); return rc; diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 519649ddf100..f3c76252247d 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -15,11 +15,11 @@ #include <linux/acpi.h> #include <linux/io.h> #include <linux/delay.h> +#include <linux/pgtable.h> #include <linux/atomic.h> #include <asm/timer.h> #include <asm/hw_irq.h> -#include <asm/pgtable.h> #include <asm/desc.h> #include <asm/apic.h> #include <asm/i8259.h> diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 87ef69a72c52..0db21206f2f3 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -4,6 +4,8 @@ */ #include <linux/interrupt.h> +#include <asm/cpu_entry_area.h> +#include <asm/set_memory.h> #include <asm/traps.h> #include <asm/proto.h> #include <asm/desc.h> @@ -51,15 +53,23 @@ struct idt_data { #define TSKG(_vector, _gdt) \ G(_vector, NULL, DEFAULT_STACK, GATE_TASK, DPL0, _gdt << 3) +#define IDT_TABLE_SIZE (IDT_ENTRIES * sizeof(gate_desc)) + +static bool idt_setup_done __initdata; + /* * Early traps running on the DEFAULT_STACK because the other interrupt * stacks work only after cpu_init(). */ static const __initconst struct idt_data early_idts[] = { - INTG(X86_TRAP_DB, debug), - SYSG(X86_TRAP_BP, int3), + INTG(X86_TRAP_DB, asm_exc_debug), + SYSG(X86_TRAP_BP, asm_exc_int3), + #ifdef CONFIG_X86_32 - INTG(X86_TRAP_PF, page_fault), + /* + * Not possible on 64-bit. See idt_setup_early_pf() for details. + */ + INTG(X86_TRAP_PF, asm_exc_page_fault), #endif }; @@ -70,33 +80,33 @@ static const __initconst struct idt_data early_idts[] = { * set up TSS. */ static const __initconst struct idt_data def_idts[] = { - INTG(X86_TRAP_DE, divide_error), - INTG(X86_TRAP_NMI, nmi), - INTG(X86_TRAP_BR, bounds), - INTG(X86_TRAP_UD, invalid_op), - INTG(X86_TRAP_NM, device_not_available), - INTG(X86_TRAP_OLD_MF, coprocessor_segment_overrun), - INTG(X86_TRAP_TS, invalid_TSS), - INTG(X86_TRAP_NP, segment_not_present), - INTG(X86_TRAP_SS, stack_segment), - INTG(X86_TRAP_GP, general_protection), - INTG(X86_TRAP_SPURIOUS, spurious_interrupt_bug), - INTG(X86_TRAP_MF, coprocessor_error), - INTG(X86_TRAP_AC, alignment_check), - INTG(X86_TRAP_XF, simd_coprocessor_error), + INTG(X86_TRAP_DE, asm_exc_divide_error), + INTG(X86_TRAP_NMI, asm_exc_nmi), + INTG(X86_TRAP_BR, asm_exc_bounds), + INTG(X86_TRAP_UD, asm_exc_invalid_op), + INTG(X86_TRAP_NM, asm_exc_device_not_available), + INTG(X86_TRAP_OLD_MF, asm_exc_coproc_segment_overrun), + INTG(X86_TRAP_TS, asm_exc_invalid_tss), + INTG(X86_TRAP_NP, asm_exc_segment_not_present), + INTG(X86_TRAP_SS, asm_exc_stack_segment), + INTG(X86_TRAP_GP, asm_exc_general_protection), + INTG(X86_TRAP_SPURIOUS, asm_exc_spurious_interrupt_bug), + INTG(X86_TRAP_MF, asm_exc_coprocessor_error), + INTG(X86_TRAP_AC, asm_exc_alignment_check), + INTG(X86_TRAP_XF, asm_exc_simd_coprocessor_error), #ifdef CONFIG_X86_32 TSKG(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS), #else - INTG(X86_TRAP_DF, double_fault), + INTG(X86_TRAP_DF, asm_exc_double_fault), #endif - INTG(X86_TRAP_DB, debug), + INTG(X86_TRAP_DB, asm_exc_debug), #ifdef CONFIG_X86_MCE - INTG(X86_TRAP_MC, &machine_check), + INTG(X86_TRAP_MC, asm_exc_machine_check), #endif - SYSG(X86_TRAP_OF, overflow), + SYSG(X86_TRAP_OF, asm_exc_overflow), #if defined(CONFIG_IA32_EMULATION) SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), #elif defined(CONFIG_X86_32) @@ -109,95 +119,63 @@ static const __initconst struct idt_data def_idts[] = { */ static const __initconst struct idt_data apic_idts[] = { #ifdef CONFIG_SMP - INTG(RESCHEDULE_VECTOR, reschedule_interrupt), - INTG(CALL_FUNCTION_VECTOR, call_function_interrupt), - INTG(CALL_FUNCTION_SINGLE_VECTOR, call_function_single_interrupt), - INTG(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt), - INTG(REBOOT_VECTOR, reboot_interrupt), + INTG(RESCHEDULE_VECTOR, asm_sysvec_reschedule_ipi), + INTG(CALL_FUNCTION_VECTOR, asm_sysvec_call_function), + INTG(CALL_FUNCTION_SINGLE_VECTOR, asm_sysvec_call_function_single), + INTG(IRQ_MOVE_CLEANUP_VECTOR, asm_sysvec_irq_move_cleanup), + INTG(REBOOT_VECTOR, asm_sysvec_reboot), #endif #ifdef CONFIG_X86_THERMAL_VECTOR - INTG(THERMAL_APIC_VECTOR, thermal_interrupt), + INTG(THERMAL_APIC_VECTOR, asm_sysvec_thermal), #endif #ifdef CONFIG_X86_MCE_THRESHOLD - INTG(THRESHOLD_APIC_VECTOR, threshold_interrupt), + INTG(THRESHOLD_APIC_VECTOR, asm_sysvec_threshold), #endif #ifdef CONFIG_X86_MCE_AMD - INTG(DEFERRED_ERROR_VECTOR, deferred_error_interrupt), + INTG(DEFERRED_ERROR_VECTOR, asm_sysvec_deferred_error), #endif #ifdef CONFIG_X86_LOCAL_APIC - INTG(LOCAL_TIMER_VECTOR, apic_timer_interrupt), - INTG(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi), + INTG(LOCAL_TIMER_VECTOR, asm_sysvec_apic_timer_interrupt), + INTG(X86_PLATFORM_IPI_VECTOR, asm_sysvec_x86_platform_ipi), # ifdef CONFIG_HAVE_KVM - INTG(POSTED_INTR_VECTOR, kvm_posted_intr_ipi), - INTG(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi), - INTG(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi), + INTG(POSTED_INTR_VECTOR, asm_sysvec_kvm_posted_intr_ipi), + INTG(POSTED_INTR_WAKEUP_VECTOR, asm_sysvec_kvm_posted_intr_wakeup_ipi), + INTG(POSTED_INTR_NESTED_VECTOR, asm_sysvec_kvm_posted_intr_nested_ipi), # endif # ifdef CONFIG_IRQ_WORK - INTG(IRQ_WORK_VECTOR, irq_work_interrupt), + INTG(IRQ_WORK_VECTOR, asm_sysvec_irq_work), # endif -#ifdef CONFIG_X86_UV - INTG(UV_BAU_MESSAGE, uv_bau_message_intr1), -#endif - INTG(SPURIOUS_APIC_VECTOR, spurious_interrupt), - INTG(ERROR_APIC_VECTOR, error_interrupt), +# ifdef CONFIG_X86_UV + INTG(UV_BAU_MESSAGE, asm_sysvec_uv_bau_message), +# endif + INTG(SPURIOUS_APIC_VECTOR, asm_sysvec_spurious_apic_interrupt), + INTG(ERROR_APIC_VECTOR, asm_sysvec_error_interrupt), #endif }; -#ifdef CONFIG_X86_64 -/* - * Early traps running on the DEFAULT_STACK because the other interrupt - * stacks work only after cpu_init(). - */ -static const __initconst struct idt_data early_pf_idts[] = { - INTG(X86_TRAP_PF, page_fault), -}; - -/* - * Override for the debug_idt. Same as the default, but with interrupt - * stack set to DEFAULT_STACK (0). Required for NMI trap handling. - */ -static const __initconst struct idt_data dbg_idts[] = { - INTG(X86_TRAP_DB, debug), -}; -#endif - -/* Must be page-aligned because the real IDT is used in a fixmap. */ -gate_desc idt_table[IDT_ENTRIES] __page_aligned_bss; +/* Must be page-aligned because the real IDT is used in the cpu entry area */ +static gate_desc idt_table[IDT_ENTRIES] __page_aligned_bss; struct desc_ptr idt_descr __ro_after_init = { - .size = (IDT_ENTRIES * 2 * sizeof(unsigned long)) - 1, + .size = IDT_TABLE_SIZE - 1, .address = (unsigned long) idt_table, }; -#ifdef CONFIG_X86_64 -/* No need to be aligned, but done to keep all IDTs defined the same way. */ -gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss; - -/* - * The exceptions which use Interrupt stacks. They are setup after - * cpu_init() when the TSS has been initialized. - */ -static const __initconst struct idt_data ist_idts[] = { - ISTG(X86_TRAP_DB, debug, IST_INDEX_DB), - ISTG(X86_TRAP_NMI, nmi, IST_INDEX_NMI), - ISTG(X86_TRAP_DF, double_fault, IST_INDEX_DF), -#ifdef CONFIG_X86_MCE - ISTG(X86_TRAP_MC, &machine_check, IST_INDEX_MCE), -#endif -}; +void load_current_idt(void) +{ + lockdep_assert_irqs_disabled(); + load_idt(&idt_descr); +} -/* - * Override for the debug_idt. Same as the default, but with interrupt - * stack set to DEFAULT_STACK (0). Required for NMI trap handling. - */ -const struct desc_ptr debug_idt_descr = { - .size = IDT_ENTRIES * 16 - 1, - .address = (unsigned long) debug_idt_table, -}; +#ifdef CONFIG_X86_F00F_BUG +bool idt_is_f00f_address(unsigned long address) +{ + return ((address - idt_descr.address) >> 3) == 6; +} #endif static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) @@ -214,7 +192,7 @@ static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) #endif } -static void +static __init void idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sys) { gate_desc desc; @@ -227,7 +205,7 @@ idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sy } } -static void set_intr_gate(unsigned int n, const void *addr) +static __init void set_intr_gate(unsigned int n, const void *addr) { struct idt_data data; @@ -266,6 +244,27 @@ void __init idt_setup_traps(void) } #ifdef CONFIG_X86_64 +/* + * Early traps running on the DEFAULT_STACK because the other interrupt + * stacks work only after cpu_init(). + */ +static const __initconst struct idt_data early_pf_idts[] = { + INTG(X86_TRAP_PF, asm_exc_page_fault), +}; + +/* + * The exceptions which use Interrupt stacks. They are setup after + * cpu_init() when the TSS has been initialized. + */ +static const __initconst struct idt_data ist_idts[] = { + ISTG(X86_TRAP_DB, asm_exc_debug, IST_INDEX_DB), + ISTG(X86_TRAP_NMI, asm_exc_nmi, IST_INDEX_NMI), + ISTG(X86_TRAP_DF, asm_exc_double_fault, IST_INDEX_DF), +#ifdef CONFIG_X86_MCE + ISTG(X86_TRAP_MC, asm_exc_machine_check, IST_INDEX_MCE), +#endif +}; + /** * idt_setup_early_pf - Initialize the idt table with early pagefault handler * @@ -273,8 +272,10 @@ void __init idt_setup_traps(void) * cpu_init() is invoked and sets up TSS. The IST variant is installed * after that. * - * FIXME: Why is 32bit and 64bit installing the PF handler at different - * places in the early setup code? + * Note, that X86_64 cannot install the real #PF handler in + * idt_setup_early_traps() because the memory intialization needs the #PF + * handler from the early_idt_handler_array to initialize the early page + * tables. */ void __init idt_setup_early_pf(void) { @@ -289,17 +290,20 @@ void __init idt_setup_ist_traps(void) { idt_setup_from_table(idt_table, ist_idts, ARRAY_SIZE(ist_idts), true); } +#endif -/** - * idt_setup_debugidt_traps - Initialize the debug idt table with debug traps - */ -void __init idt_setup_debugidt_traps(void) +static void __init idt_map_in_cea(void) { - memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16); - - idt_setup_from_table(debug_idt_table, dbg_idts, ARRAY_SIZE(dbg_idts), false); + /* + * Set the IDT descriptor to a fixed read-only location in the cpu + * entry area, so that the "sidt" instruction will not leak the + * location of the kernel, and to defend the IDT against arbitrary + * memory write vulnerabilities. + */ + cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table), + PAGE_KERNEL_RO); + idt_descr.address = CPU_ENTRY_AREA_RO_IDT; } -#endif /** * idt_setup_apic_and_irq_gates - Setup APIC/SMP and normal interrupt gates @@ -318,11 +322,23 @@ void __init idt_setup_apic_and_irq_gates(void) #ifdef CONFIG_X86_LOCAL_APIC for_each_clear_bit_from(i, system_vectors, NR_VECTORS) { - set_bit(i, system_vectors); + /* + * Don't set the non assigned system vectors in the + * system_vectors bitmap. Otherwise they show up in + * /proc/interrupts. + */ entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR); set_intr_gate(i, entry); } #endif + /* Map IDT into CPU entry area and reload it. */ + idt_map_in_cea(); + load_idt(&idt_descr); + + /* Make the IDT table read only */ + set_memory_ro((unsigned long)&idt_table, 1); + + idt_setup_done = true; } /** @@ -352,16 +368,14 @@ void idt_invalidate(void *addr) load_idt(&idt); } -void __init update_intr_gate(unsigned int n, const void *addr) +void __init alloc_intr_gate(unsigned int n, const void *addr) { - if (WARN_ON_ONCE(!test_bit(n, system_vectors))) + if (WARN_ON(n < FIRST_SYSTEM_VECTOR)) return; - set_intr_gate(n, addr); -} -void alloc_intr_gate(unsigned int n, const void *addr) -{ - BUG_ON(n < FIRST_SYSTEM_VECTOR); - if (!test_and_set_bit(n, system_vectors)) + if (WARN_ON(idt_setup_done)) + return; + + if (!WARN_ON(test_and_set_bit(n, system_vectors))) set_intr_gate(n, addr); } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index c7965ff429c5..181060247e3c 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -13,12 +13,14 @@ #include <linux/export.h> #include <linux/irq.h> +#include <asm/irq_stack.h> #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/irq.h> #include <asm/mce.h> #include <asm/hw_irq.h> #include <asm/desc.h> +#include <asm/traps.h> #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> @@ -26,9 +28,6 @@ DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); EXPORT_PER_CPU_SYMBOL(irq_stat); -DEFINE_PER_CPU(struct pt_regs *, irq_regs); -EXPORT_PER_CPU_SYMBOL(irq_regs); - atomic_t irq_err_count; /* @@ -224,35 +223,35 @@ u64 arch_irq_stat(void) return sum; } +static __always_inline void handle_irq(struct irq_desc *desc, + struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_X86_64)) + run_on_irqstack_cond(desc->handle_irq, desc, regs); + else + __handle_irq(desc, regs); +} /* - * do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). + * common_interrupt() handles all normal device IRQ's (the special SMP + * cross-CPU interrupts have their own entry points). */ -__visible void __irq_entry do_IRQ(struct pt_regs *regs) +DEFINE_IDTENTRY_IRQ(common_interrupt) { struct pt_regs *old_regs = set_irq_regs(regs); - struct irq_desc * desc; - /* high bit used in ret_from_ code */ - unsigned vector = ~regs->orig_ax; - - entering_irq(); + struct irq_desc *desc; - /* entering_irq() tells RCU that we're not quiescent. Check it. */ + /* entry code tells RCU that we're not quiescent. Check it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU"); desc = __this_cpu_read(vector_irq[vector]); if (likely(!IS_ERR_OR_NULL(desc))) { - if (IS_ENABLED(CONFIG_X86_32)) - handle_irq(desc, regs); - else - generic_handle_irq_desc(desc); + handle_irq(desc, regs); } else { ack_APIC_irq(); if (desc == VECTOR_UNUSED) { - pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n", + pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n", __func__, smp_processor_id(), vector); } else { @@ -260,8 +259,6 @@ __visible void __irq_entry do_IRQ(struct pt_regs *regs) } } - exiting_irq(); - set_irq_regs(old_regs); } @@ -271,17 +268,16 @@ void (*x86_platform_ipi_callback)(void) = NULL; /* * Handler for X86_PLATFORM_IPI_VECTOR. */ -__visible void __irq_entry smp_x86_platform_ipi(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_x86_platform_ipi) { struct pt_regs *old_regs = set_irq_regs(regs); - entering_ack_irq(); + ack_APIC_irq(); trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR); inc_irq_stat(x86_platform_ipis); if (x86_platform_ipi_callback) x86_platform_ipi_callback(); trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR); - exiting_irq(); set_irq_regs(old_regs); } #endif @@ -302,41 +298,29 @@ EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); /* * Handler for POSTED_INTERRUPT_VECTOR. */ -__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_ipi) { - struct pt_regs *old_regs = set_irq_regs(regs); - - entering_ack_irq(); + ack_APIC_irq(); inc_irq_stat(kvm_posted_intr_ipis); - exiting_irq(); - set_irq_regs(old_regs); } /* * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR. */ -__visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_posted_intr_wakeup_ipi) { - struct pt_regs *old_regs = set_irq_regs(regs); - - entering_ack_irq(); + ack_APIC_irq(); inc_irq_stat(kvm_posted_intr_wakeup_ipis); kvm_posted_intr_wakeup_handler(); - exiting_irq(); - set_irq_regs(old_regs); } /* * Handler for POSTED_INTERRUPT_NESTED_VECTOR. */ -__visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_kvm_posted_intr_nested_ipi) { - struct pt_regs *old_regs = set_irq_regs(regs); - - entering_ack_irq(); + ack_APIC_irq(); inc_irq_stat(kvm_posted_intr_nested_ipis); - exiting_irq(); - set_irq_regs(old_regs); } #endif diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index a759ca97cd01..0b79efc87be5 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -148,7 +148,7 @@ void do_softirq_own_stack(void) call_on_stack(__do_softirq, isp); } -void handle_irq(struct irq_desc *desc, struct pt_regs *regs) +void __handle_irq(struct irq_desc *desc, struct pt_regs *regs) { int overflow = check_stack_overflow(); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 12df3a4abfdd..1b4fe93a86c5 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -20,6 +20,7 @@ #include <linux/sched/task_stack.h> #include <asm/cpu_entry_area.h> +#include <asm/irq_stack.h> #include <asm/io_apic.h> #include <asm/apic.h> @@ -43,7 +44,7 @@ static int map_irq_stack(unsigned int cpu) pages[i] = pfn_to_page(pa >> PAGE_SHIFT); } - va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); + va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, VM_MAP, PAGE_KERNEL); if (!va) return -ENOMEM; @@ -70,3 +71,8 @@ int irq_init_percpu_irqstack(unsigned int cpu) return 0; return map_irq_stack(cpu); } + +void do_softirq_own_stack(void) +{ + run_on_irqstack_cond(__do_softirq, NULL, NULL); +} diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 80bee7695a20..890d4778cd35 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -9,18 +9,18 @@ #include <linux/irq_work.h> #include <linux/hardirq.h> #include <asm/apic.h> +#include <asm/idtentry.h> #include <asm/trace/irq_vectors.h> #include <linux/interrupt.h> #ifdef CONFIG_X86_LOCAL_APIC -__visible void __irq_entry smp_irq_work_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_irq_work) { - ipi_entering_ack_irq(); + ack_APIC_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); inc_irq_stat(apic_irq_work_irqs); irq_work_run(); trace_irq_work_exit(IRQ_WORK_VECTOR); - exiting_irq(); } void arch_irq_work_raise(void) diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 5aa523c2d573..dd73135d7cee 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -16,11 +16,11 @@ #include <linux/acpi.h> #include <linux/io.h> #include <linux/delay.h> +#include <linux/pgtable.h> #include <linux/atomic.h> #include <asm/timer.h> #include <asm/hw_irq.h> -#include <asm/pgtable.h> #include <asm/desc.h> #include <asm/apic.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 1cb3ca9bba49..1afbdd1dd777 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -39,8 +39,7 @@ static bool __read_mostly sched_itmt_capable; unsigned int __read_mostly sysctl_sched_itmt_enabled; static int sched_itmt_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { unsigned int old_sysctl; int ret; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 4d7022a740ab..3bafe1bd4dc7 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -41,11 +41,11 @@ #include <linux/kasan.h> #include <linux/moduleloader.h> #include <linux/vmalloc.h> +#include <linux/pgtable.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/desc.h> -#include <asm/pgtable.h> #include <linux/uaccess.h> #include <asm/alternative.h> #include <asm/insn.h> @@ -1073,13 +1073,6 @@ NOKPROBE_SYMBOL(kprobe_fault_handler); int __init arch_populate_kprobe_blacklist(void) { - int ret; - - ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, - (unsigned long)__irqentry_text_end); - if (ret) - return ret; - return kprobe_add_area_blacklist((unsigned long)__entry_text_start, (unsigned long)__entry_text_end); } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index ea13f6888284..321c19950285 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -16,11 +16,11 @@ #include <linux/kallsyms.h> #include <linux/ftrace.h> #include <linux/frame.h> +#include <linux/pgtable.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> #include <asm/desc.h> -#include <asm/pgtable.h> #include <linux/uaccess.h> #include <asm/alternative.h> #include <asm/insn.h> @@ -286,9 +286,7 @@ static int can_optimize(unsigned long paddr) * stack handling and registers setup. */ if (((paddr >= (unsigned long)__entry_text_start) && - (paddr < (unsigned long)__entry_text_end)) || - ((paddr >= (unsigned long)__irqentry_text_start) && - (paddr < (unsigned long)__irqentry_text_end))) + (paddr < (unsigned long)__entry_text_end))) return 0; /* Check there is enough space for a relative jump. */ diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 6efe0410fb72..df63786e7bfa 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -21,7 +21,6 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/kprobes.h> -#include <linux/debugfs.h> #include <linux/nmi.h> #include <linux/swait.h> #include <asm/timer.h> @@ -35,6 +34,8 @@ #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> +DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled); + static int kvmapf = 1; static int __init parse_no_kvmapf(char *arg) @@ -73,7 +74,6 @@ struct kvm_task_sleep_node { struct swait_queue_head wq; u32 token; int cpu; - bool halted; }; static struct kvm_task_sleep_head { @@ -96,77 +96,64 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b, return NULL; } -/* - * @interrupt_kernel: Is this called from a routine which interrupts the kernel - * (other than user space)? - */ -void kvm_async_pf_task_wait(u32 token, int interrupt_kernel) +static bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; - struct kvm_task_sleep_node n, *e; - DECLARE_SWAITQUEUE(wait); - - rcu_irq_enter(); + struct kvm_task_sleep_node *e; raw_spin_lock(&b->lock); e = _find_apf_task(b, token); if (e) { /* dummy entry exist -> wake up was delivered ahead of PF */ hlist_del(&e->link); - kfree(e); raw_spin_unlock(&b->lock); - - rcu_irq_exit(); - return; + kfree(e); + return false; } - n.token = token; - n.cpu = smp_processor_id(); - n.halted = is_idle_task(current) || - (IS_ENABLED(CONFIG_PREEMPT_COUNT) - ? preempt_count() > 1 || rcu_preempt_depth() - : interrupt_kernel); - init_swait_queue_head(&n.wq); - hlist_add_head(&n.link, &b->list); + n->token = token; + n->cpu = smp_processor_id(); + init_swait_queue_head(&n->wq); + hlist_add_head(&n->link, &b->list); raw_spin_unlock(&b->lock); + return true; +} + +/* + * kvm_async_pf_task_wait_schedule - Wait for pagefault to be handled + * @token: Token to identify the sleep node entry + * + * Invoked from the async pagefault handling code or from the VM exit page + * fault handler. In both cases RCU is watching. + */ +void kvm_async_pf_task_wait_schedule(u32 token) +{ + struct kvm_task_sleep_node n; + DECLARE_SWAITQUEUE(wait); + + lockdep_assert_irqs_disabled(); + + if (!kvm_async_pf_queue_task(token, &n)) + return; for (;;) { - if (!n.halted) - prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE); if (hlist_unhashed(&n.link)) break; - rcu_irq_exit(); - - if (!n.halted) { - local_irq_enable(); - schedule(); - local_irq_disable(); - } else { - /* - * We cannot reschedule. So halt. - */ - native_safe_halt(); - local_irq_disable(); - } - - rcu_irq_enter(); + local_irq_enable(); + schedule(); + local_irq_disable(); } - if (!n.halted) - finish_swait(&n.wq, &wait); - - rcu_irq_exit(); - return; + finish_swait(&n.wq, &wait); } -EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait); +EXPORT_SYMBOL_GPL(kvm_async_pf_task_wait_schedule); static void apf_task_wake_one(struct kvm_task_sleep_node *n) { hlist_del_init(&n->link); - if (n->halted) - smp_send_reschedule(n->cpu); - else if (swq_has_sleeper(&n->wq)) + if (swq_has_sleeper(&n->wq)) swake_up_one(&n->wq); } @@ -175,12 +162,13 @@ static void apf_task_wake_all(void) int i; for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) { - struct hlist_node *p, *next; struct kvm_task_sleep_head *b = &async_pf_sleepers[i]; + struct kvm_task_sleep_node *n; + struct hlist_node *p, *next; + raw_spin_lock(&b->lock); hlist_for_each_safe(p, next, &b->list) { - struct kvm_task_sleep_node *n = - hlist_entry(p, typeof(*n), link); + n = hlist_entry(p, typeof(*n), link); if (n->cpu == smp_processor_id()) apf_task_wake_one(n); } @@ -221,46 +209,64 @@ again: n->cpu = smp_processor_id(); init_swait_queue_head(&n->wq); hlist_add_head(&n->link, &b->list); - } else + } else { apf_task_wake_one(n); + } raw_spin_unlock(&b->lock); return; } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); -u32 kvm_read_and_reset_pf_reason(void) +noinstr u32 kvm_read_and_reset_apf_flags(void) { - u32 reason = 0; + u32 flags = 0; if (__this_cpu_read(apf_reason.enabled)) { - reason = __this_cpu_read(apf_reason.reason); - __this_cpu_write(apf_reason.reason, 0); + flags = __this_cpu_read(apf_reason.flags); + __this_cpu_write(apf_reason.flags, 0); } - return reason; + return flags; } -EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); -NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); +EXPORT_SYMBOL_GPL(kvm_read_and_reset_apf_flags); -dotraplinkage void -do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) +noinstr bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token) { - switch (kvm_read_and_reset_pf_reason()) { - default: - do_page_fault(regs, error_code, address); - break; + u32 reason = kvm_read_and_reset_apf_flags(); + bool rcu_exit; + + switch (reason) { case KVM_PV_REASON_PAGE_NOT_PRESENT: - /* page is swapped out by the host. */ - kvm_async_pf_task_wait((u32)address, !user_mode(regs)); - break; case KVM_PV_REASON_PAGE_READY: - rcu_irq_enter(); - kvm_async_pf_task_wake((u32)address); - rcu_irq_exit(); break; + default: + return false; } + + rcu_exit = idtentry_enter_cond_rcu(regs); + instrumentation_begin(); + + /* + * If the host managed to inject an async #PF into an interrupt + * disabled region, then die hard as this is not going to end well + * and the host side is seriously broken. + */ + if (unlikely(!(regs->flags & X86_EFLAGS_IF))) + panic("Host injected async #PF in interrupt disabled region\n"); + + if (reason == KVM_PV_REASON_PAGE_NOT_PRESENT) { + if (unlikely(!(user_mode(regs)))) + panic("Host injected async #PF in kernel mode\n"); + /* Page is swapped out by the host. */ + kvm_async_pf_task_wait_schedule(token); + } else { + kvm_async_pf_task_wake(token); + } + + instrumentation_end(); + idtentry_exit_cond_rcu(regs, rcu_exit); + return true; } -NOKPROBE_SYMBOL(do_async_page_fault); static void __init paravirt_ops_setup(void) { @@ -306,11 +312,11 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) static void kvm_guest_cpu_init(void) { if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) { - u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); + u64 pa; -#ifdef CONFIG_PREEMPTION - pa |= KVM_ASYNC_PF_SEND_ALWAYS; -#endif + WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled)); + + pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); pa |= KVM_ASYNC_PF_ENABLED; if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT)) @@ -318,12 +324,12 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); __this_cpu_write(apf_reason.enabled, 1); - printk(KERN_INFO"KVM setup async PF for cpu %d\n", - smp_processor_id()); + pr_info("KVM setup async PF for cpu %d\n", smp_processor_id()); } if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) { unsigned long pa; + /* Size alignment is implied but just to make it explicit. */ BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4); __this_cpu_write(kvm_apic_eoi, 0); @@ -344,8 +350,7 @@ static void kvm_pv_disable_apf(void) wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); __this_cpu_write(apf_reason.enabled, 0); - printk(KERN_INFO"Unregister pv shared memory for cpu %d\n", - smp_processor_id()); + pr_info("Unregister pv shared memory for cpu %d\n", smp_processor_id()); } static void kvm_pv_guest_cpu_reboot(void *unused) @@ -592,12 +597,6 @@ static int kvm_cpu_down_prepare(unsigned int cpu) } #endif -static void __init kvm_apf_trap_init(void) -{ - update_intr_gate(X86_TRAP_PF, async_page_fault); -} - - static void kvm_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) { @@ -632,8 +631,6 @@ static void __init kvm_guest_init(void) register_reboot_notifier(&kvm_pv_reboot_nb); for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) raw_spin_lock_init(&async_pf_sleepers[i].lock); - if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF)) - x86_init.irqs.trap_init = kvm_apf_trap_init; if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { has_steal_clock = 1; @@ -649,6 +646,9 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) apic_set_eoi_write(kvm_guest_apic_eoi_write); + if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) + static_branch_enable(&kvm_async_pf_enabled); + #ifdef CONFIG_SMP smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus; smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 84c3ba32f211..8748321c4486 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -8,7 +8,7 @@ * * Lock order: * contex.ldt_usr_sem - * mmap_sem + * mmap_lock * context.lock */ diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c deleted file mode 100644 index 6a68e41206e7..000000000000 --- a/arch/x86/kernel/livepatch.c +++ /dev/null @@ -1,53 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * livepatch.c - x86-specific Kernel Live Patching Core - */ - -#include <linux/module.h> -#include <linux/kallsyms.h> -#include <linux/livepatch.h> -#include <asm/text-patching.h> - -/* Apply per-object alternatives. Based on x86 module_finalize() */ -void arch_klp_init_object_loaded(struct klp_patch *patch, - struct klp_object *obj) -{ - int cnt; - struct klp_modinfo *info; - Elf_Shdr *s, *alt = NULL, *para = NULL; - void *aseg, *pseg; - const char *objname; - char sec_objname[MODULE_NAME_LEN]; - char secname[KSYM_NAME_LEN]; - - info = patch->mod->klp_info; - objname = obj->name ? obj->name : "vmlinux"; - - /* See livepatch core code for BUILD_BUG_ON() explanation */ - BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128); - - for (s = info->sechdrs; s < info->sechdrs + info->hdr.e_shnum; s++) { - /* Apply per-object .klp.arch sections */ - cnt = sscanf(info->secstrings + s->sh_name, - ".klp.arch.%55[^.].%127s", - sec_objname, secname); - if (cnt != 2) - continue; - if (strcmp(sec_objname, objname)) - continue; - if (!strcmp(".altinstructions", secname)) - alt = s; - if (!strcmp(".parainstructions", secname)) - para = s; - } - - if (alt) { - aseg = (void *) alt->sh_addr; - apply_alternatives(aseg, aseg + alt->sh_size); - } - - if (para) { - pseg = (void *) para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } -} diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 02bddfc122a4..64b00b0d7fe8 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -13,7 +13,6 @@ #include <linux/gfp.h> #include <linux/io.h> -#include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index ad5cdd6a5f23..a29a44a98e5b 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -19,7 +19,6 @@ #include <linux/efi.h> #include <asm/init.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/io_apic.h> diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index d5c72cb877b3..34b153cbd4ac 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -18,10 +18,10 @@ #include <linux/gfp.h> #include <linux/jump_label.h> #include <linux/random.h> +#include <linux/memory.h> #include <asm/text-patching.h> #include <asm/page.h> -#include <asm/pgtable.h> #include <asm/setup.h> #include <asm/unwind.h> @@ -126,11 +126,12 @@ int apply_relocate(Elf32_Shdr *sechdrs, return 0; } #else /*X86_64*/ -int apply_relocate_add(Elf64_Shdr *sechdrs, +static int __apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, unsigned int symindex, unsigned int relsec, - struct module *me) + struct module *me, + void *(*write)(void *dest, const void *src, size_t len)) { unsigned int i; Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr; @@ -162,19 +163,19 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_X86_64_64: if (*(u64 *)loc != 0) goto invalid_relocation; - *(u64 *)loc = val; + write(loc, &val, 8); break; case R_X86_64_32: if (*(u32 *)loc != 0) goto invalid_relocation; - *(u32 *)loc = val; + write(loc, &val, 4); if (val != *(u32 *)loc) goto overflow; break; case R_X86_64_32S: if (*(s32 *)loc != 0) goto invalid_relocation; - *(s32 *)loc = val; + write(loc, &val, 4); if ((s64)val != *(s32 *)loc) goto overflow; break; @@ -183,7 +184,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, if (*(u32 *)loc != 0) goto invalid_relocation; val -= (u64)loc; - *(u32 *)loc = val; + write(loc, &val, 4); #if 0 if ((s64)val != *(s32 *)loc) goto overflow; @@ -193,7 +194,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, if (*(u64 *)loc != 0) goto invalid_relocation; val -= (u64)loc; - *(u64 *)loc = val; + write(loc, &val, 8); break; default: pr_err("%s: Unknown rela relocation: %llu\n", @@ -215,6 +216,33 @@ overflow: me->name); return -ENOEXEC; } + +int apply_relocate_add(Elf64_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ + int ret; + bool early = me->state == MODULE_STATE_UNFORMED; + void *(*write)(void *, const void *, size_t) = memcpy; + + if (!early) { + write = text_poke; + mutex_lock(&text_mutex); + } + + ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me, + write); + + if (!early) { + text_poke_sync(); + mutex_unlock(&text_mutex); + } + + return ret; +} + #endif int module_finalize(const Elf_Ehdr *hdr, diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 6407ea21fa1b..2de365f15684 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -25,10 +25,6 @@ #include <linux/atomic.h> #include <linux/sched/clock.h> -#if defined(CONFIG_EDAC) -#include <linux/edac.h> -#endif - #include <asm/cpu_entry_area.h> #include <asm/traps.h> #include <asm/mach_traps.h> @@ -307,7 +303,7 @@ NOKPROBE_SYMBOL(unknown_nmi_error); static DEFINE_PER_CPU(bool, swallow_nmi); static DEFINE_PER_CPU(unsigned long, last_nmi_rip); -static void default_do_nmi(struct pt_regs *regs) +static noinstr void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; int handled; @@ -333,6 +329,9 @@ static void default_do_nmi(struct pt_regs *regs) __this_cpu_write(last_nmi_rip, regs->ip); + instrumentation_begin(); + trace_hardirqs_off_finish(); + handled = nmi_handle(NMI_LOCAL, regs); __this_cpu_add(nmi_stats.normal, handled); if (handled) { @@ -346,7 +345,7 @@ static void default_do_nmi(struct pt_regs *regs) */ if (handled > 1) __this_cpu_write(swallow_nmi, true); - return; + goto out; } /* @@ -378,7 +377,7 @@ static void default_do_nmi(struct pt_regs *regs) #endif __this_cpu_add(nmi_stats.external, 1); raw_spin_unlock(&nmi_reason_lock); - return; + goto out; } raw_spin_unlock(&nmi_reason_lock); @@ -416,8 +415,12 @@ static void default_do_nmi(struct pt_regs *regs) __this_cpu_add(nmi_stats.swallow, 1); else unknown_nmi_error(reason, regs); + +out: + if (regs->flags & X86_EFLAGS_IF) + trace_hardirqs_on_prepare(); + instrumentation_end(); } -NOKPROBE_SYMBOL(default_do_nmi); /* * NMIs can page fault or hit breakpoints which will cause it to lose @@ -471,44 +474,9 @@ enum nmi_states { }; static DEFINE_PER_CPU(enum nmi_states, nmi_state); static DEFINE_PER_CPU(unsigned long, nmi_cr2); +static DEFINE_PER_CPU(unsigned long, nmi_dr7); -#ifdef CONFIG_X86_64 -/* - * In x86_64, we need to handle breakpoint -> NMI -> breakpoint. Without - * some care, the inner breakpoint will clobber the outer breakpoint's - * stack. - * - * If a breakpoint is being processed, and the debug stack is being - * used, if an NMI comes in and also hits a breakpoint, the stack - * pointer will be set to the same fixed address as the breakpoint that - * was interrupted, causing that stack to be corrupted. To handle this - * case, check if the stack that was interrupted is the debug stack, and - * if so, change the IDT so that new breakpoints will use the current - * stack and not switch to the fixed address. On return of the NMI, - * switch back to the original IDT. - */ -static DEFINE_PER_CPU(int, update_debug_stack); - -static bool notrace is_debug_stack(unsigned long addr) -{ - struct cea_exception_stacks *cs = __this_cpu_read(cea_exception_stacks); - unsigned long top = CEA_ESTACK_TOP(cs, DB); - unsigned long bot = CEA_ESTACK_BOT(cs, DB1); - - if (__this_cpu_read(debug_stack_usage)) - return true; - /* - * Note, this covers the guard page between DB and DB1 as well to - * avoid two checks. But by all means @addr can never point into - * the guard page. - */ - return addr >= bot && addr < top; -} -NOKPROBE_SYMBOL(is_debug_stack); -#endif - -dotraplinkage notrace void -do_nmi(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY_RAW(exc_nmi) { if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) return; @@ -521,18 +489,7 @@ do_nmi(struct pt_regs *regs, long error_code) this_cpu_write(nmi_cr2, read_cr2()); nmi_restart: -#ifdef CONFIG_X86_64 - /* - * If we interrupted a breakpoint, it is possible that - * the nmi handler will have breakpoints too. We need to - * change the IDT such that breakpoints that happen here - * continue to use the NMI stack. - */ - if (unlikely(is_debug_stack(regs->sp))) { - debug_stack_set_zero(); - this_cpu_write(update_debug_stack, 1); - } -#endif + this_cpu_write(nmi_dr7, local_db_save()); nmi_enter(); @@ -543,12 +500,7 @@ nmi_restart: nmi_exit(); -#ifdef CONFIG_X86_64 - if (unlikely(this_cpu_read(update_debug_stack))) { - debug_stack_reset(); - this_cpu_write(update_debug_stack, 0); - } -#endif + local_db_restore(this_cpu_read(nmi_dr7)); if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); @@ -558,7 +510,6 @@ nmi_restart: if (user_mode(regs)) mds_user_clear_cpu_buffers(); } -NOKPROBE_SYMBOL(do_nmi); void stop_nmi(void) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c131ba4e70ef..674a7d66d960 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -13,13 +13,13 @@ #include <linux/bcd.h> #include <linux/highmem.h> #include <linux/kprobes.h> +#include <linux/pgtable.h> #include <asm/bug.h> #include <asm/paravirt.h> #include <asm/debugreg.h> #include <asm/desc.h> #include <asm/setup.h> -#include <asm/pgtable.h> #include <asm/time.h> #include <asm/pgalloc.h> #include <asm/irq.h> @@ -160,25 +160,6 @@ unsigned paravirt_patch_insns(void *insn_buff, unsigned len, return insn_len; } -static void native_flush_tlb(void) -{ - __native_flush_tlb(); -} - -/* - * Global pages have to be flushed a bit differently. Not a real - * performance problem because this does not happen often. - */ -static void native_flush_tlb_global(void) -{ - __native_flush_tlb_global(); -} - -static void native_flush_tlb_one_user(unsigned long addr) -{ - __native_flush_tlb_one_user(addr); -} - struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; @@ -359,7 +340,7 @@ struct paravirt_patch_template pv_ops = { #endif /* CONFIG_PARAVIRT_XXL */ /* Mmu ops. */ - .mmu.flush_tlb_user = native_flush_tlb, + .mmu.flush_tlb_user = native_flush_tlb_local, .mmu.flush_tlb_kernel = native_flush_tlb_global, .mmu.flush_tlb_one_user = native_flush_tlb_one_user, .mmu.flush_tlb_others = native_flush_tlb_others, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 35638f1c5791..f362ce0d5ac0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -191,7 +191,7 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - fpu__clear(&tsk->thread.fpu); + fpu__clear_all(&tsk->thread.fpu); } void disable_TSC(void) @@ -545,28 +545,20 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, lockdep_assert_irqs_disabled(); - /* - * If TIF_SSBD is different, select the proper mitigation - * method. Note that if SSBD mitigation is disabled or permanentely - * enabled this branch can't be taken because nothing can set - * TIF_SSBD. - */ - if (tif_diff & _TIF_SSBD) { - if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + /* Handle change of TIF_SSBD depending on the mitigation method. */ + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_ssb_virt_state(tifn); - } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + if (tif_diff & _TIF_SSBD) amd_set_core_ssb_state(tifn); - } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - msr |= ssbd_tif_to_spec_ctrl(tifn); - updmsr = true; - } + } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + updmsr |= !!(tif_diff & _TIF_SSBD); + msr |= ssbd_tif_to_spec_ctrl(tifn); } - /* - * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled, - * otherwise avoid the MSR write. - */ + /* Only evaluate TIF_SPEC_IB if conditional STIBP is enabled. */ if (IS_ENABLED(CONFIG_SMP) && static_branch_unlikely(&switch_to_cond_stibp)) { updmsr |= !!(tif_diff & _TIF_SPEC_IB); @@ -612,6 +604,17 @@ void speculation_ctrl_update_current(void) preempt_enable(); } +static inline void cr4_toggle_bits_irqsoff(unsigned long mask) +{ + unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4); + + newval = cr4 ^ mask; + if (newval != cr4) { + this_cpu_write(cpu_tlbstate.cr4, newval); + __write_cr4(newval); + } +} + void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) { unsigned long tifp, tifn; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 954b013cc585..acfd6d2a0cbf 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -39,7 +39,6 @@ #include <linux/kdebug.h> #include <linux/syscalls.h> -#include <asm/pgtable.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/fpu/internal.h> @@ -52,7 +51,7 @@ #include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> -#include <asm/resctrl_sched.h> +#include <asm/resctrl.h> #include <asm/proto.h> #include "process.h" diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 5ef9d8f25b0e..9a97415b2139 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -40,7 +40,6 @@ #include <linux/ftrace.h> #include <linux/syscalls.h> -#include <asm/pgtable.h> #include <asm/processor.h> #include <asm/fpu/internal.h> #include <asm/mmu_context.h> @@ -52,7 +51,7 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> -#include <asm/resctrl_sched.h> +#include <asm/resctrl.h> #include <asm/unistd.h> #include <asm/fsgsbase.h> #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f0e1ddbc2fd7..44130588987f 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -28,7 +28,6 @@ #include <linux/nospec.h> #include <linux/uaccess.h> -#include <asm/pgtable.h> #include <asm/processor.h> #include <asm/fpu/internal.h> #include <asm/fpu/signal.h> diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 3ca43be4f9cf..0ec7ced727fe 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -11,13 +11,13 @@ #include <linux/tboot.h> #include <linux/delay.h> #include <linux/frame.h> +#include <linux/pgtable.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/desc.h> #include <asm/hpet.h> -#include <asm/pgtable.h> #include <asm/proto.h> #include <asm/reboot_fixups.h> #include <asm/reboot.h> @@ -197,6 +197,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"), }, }, + { /* Handle problems with rebooting on Apple MacBook6,1 */ + .callback = set_pci_reboot, + .ident = "Apple MacBook6,1", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "MacBook6,1"), + }, + }, { /* Handle problems with rebooting on Apple MacBookPro5 */ .callback = set_pci_reboot, .ident = "Apple MacBookPro5", diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 4b3fa6cd3106..a3767e74c758 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -237,6 +237,9 @@ static u64 __init get_ramdisk_image(void) ramdisk_image |= (u64)boot_params.ext_ramdisk_image << 32; + if (ramdisk_image == 0) + ramdisk_image = phys_initrd_start; + return ramdisk_image; } static u64 __init get_ramdisk_size(void) @@ -245,6 +248,9 @@ static u64 __init get_ramdisk_size(void) ramdisk_size |= (u64)boot_params.ext_ramdisk_size << 32; + if (ramdisk_size == 0) + ramdisk_size = phys_initrd_size; + return ramdisk_size; } diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index e6d7894ad127..fd945ce78554 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -287,9 +287,9 @@ void __init setup_per_cpu_areas(void) /* * Sync back kernel address range again. We already did this in * setup_arch(), but percpu data also needs to be available in - * the smpboot asm. We can't reliably pick up percpu mappings - * using vmalloc_fault(), because exception dispatch needs - * percpu data. + * the smpboot asm and arch_sync_kernel_mappings() doesn't sync to + * swapper_pg_dir on 32-bit. The per-cpu mappings need to be available + * there too. * * FIXME: Can the later sync in setup_cpu_entry_areas() replace * this call? diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 83b74fb38c8f..399f97abee02 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -37,6 +37,7 @@ #include <asm/vm86.h> #ifdef CONFIG_X86_64 +#include <linux/compat.h> #include <asm/proto.h> #include <asm/ia32_unistd.h> #endif /* CONFIG_X86_64 */ @@ -511,6 +512,31 @@ Efault: } #endif /* CONFIG_X86_32 */ +#ifdef CONFIG_X86_X32_ABI +static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to, + const struct kernel_siginfo *from) +{ + struct compat_siginfo new; + + copy_siginfo_to_external32(&new, from); + if (from->si_signo == SIGCHLD) { + new._sifields._sigchld_x32._utime = from->si_utime; + new._sifields._sigchld_x32._stime = from->si_stime; + } + if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) + return -EFAULT; + return 0; +} + +int copy_siginfo_to_user32(struct compat_siginfo __user *to, + const struct kernel_siginfo *from) +{ + if (in_x32_syscall()) + return x32_copy_siginfo_to_user(to, from); + return __copy_siginfo_to_user32(to, from); +} +#endif /* CONFIG_X86_X32_ABI */ + static int x32_setup_rt_frame(struct ksignal *ksig, compat_sigset_t *set, struct pt_regs *regs) @@ -543,7 +569,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, user_access_end(); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (__copy_siginfo_to_user32(&frame->info, &ksig->info, true)) + if (x32_copy_siginfo_to_user(&frame->info, &ksig->info)) return -EFAULT; } @@ -732,7 +758,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) /* * Ensure the signal handler starts with the new fpu state. */ - fpu__clear(fpu); + fpu__clear_user_states(fpu); } signal_setup_done(failed, ksig, stepping); } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index b8d4e9c3c070..eff4ce3b10da 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -27,6 +27,7 @@ #include <asm/mmu_context.h> #include <asm/proto.h> #include <asm/apic.h> +#include <asm/idtentry.h> #include <asm/nmi.h> #include <asm/mce.h> #include <asm/trace/irq_vectors.h> @@ -130,13 +131,11 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) /* * this function calls the 'stop' function on all other CPUs in the system. */ - -asmlinkage __visible void smp_reboot_interrupt(void) +DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { - ipi_entering_ack_irq(); + ack_APIC_irq(); cpu_emergency_vmxoff(); stop_this_cpu(NULL); - irq_exit(); } static int register_stop_handler(void) @@ -221,47 +220,33 @@ static void native_stop_other_cpus(int wait) /* * Reschedule call back. KVM uses this interrupt to force a cpu out of - * guest mode + * guest mode. */ -__visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_reschedule_ipi) { ack_APIC_irq(); + trace_reschedule_entry(RESCHEDULE_VECTOR); inc_irq_stat(irq_resched_count); - kvm_set_cpu_l1tf_flush_l1d(); - - if (trace_resched_ipi_enabled()) { - /* - * scheduler_ipi() might call irq_enter() as well, but - * nested calls are fine. - */ - irq_enter(); - trace_reschedule_entry(RESCHEDULE_VECTOR); - scheduler_ipi(); - trace_reschedule_exit(RESCHEDULE_VECTOR); - irq_exit(); - return; - } scheduler_ipi(); + trace_reschedule_exit(RESCHEDULE_VECTOR); } -__visible void __irq_entry smp_call_function_interrupt(struct pt_regs *regs) +DEFINE_IDTENTRY_SYSVEC(sysvec_call_function) { - ipi_entering_ack_irq(); + ack_APIC_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); inc_irq_stat(irq_call_count); generic_smp_call_function_interrupt(); trace_call_function_exit(CALL_FUNCTION_VECTOR); - exiting_irq(); } -__visible void __irq_entry smp_call_function_single_interrupt(struct pt_regs *r) +DEFINE_IDTENTRY_SYSVEC(sysvec_call_function_single) { - ipi_entering_ack_irq(); + ack_APIC_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); inc_irq_stat(irq_call_count); generic_smp_call_function_single_interrupt(); trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR); - exiting_irq(); } static int __init nonmi_ipi_setup(char *str) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2f24c334a938..ffbd9a3d78d8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -55,6 +55,7 @@ #include <linux/gfp.h> #include <linux/cpuidle.h> #include <linux/numa.h> +#include <linux/pgtable.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -63,7 +64,6 @@ #include <asm/realmode.h> #include <asm/cpu.h> #include <asm/numa.h> -#include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/mwait.h> @@ -1384,12 +1384,12 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) speculative_store_bypass_ht_init(); } -void arch_enable_nonboot_cpus_begin(void) +void arch_thaw_secondary_cpus_begin(void) { set_mtrr_aps_delayed_init(); } -void arch_enable_nonboot_cpus_end(void) +void arch_thaw_secondary_cpus_end(void) { mtrr_aps_init(); } @@ -1857,24 +1857,25 @@ static bool slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) #include <asm/cpu_device_id.h> #include <asm/intel-family.h> -#define ICPU(model) \ - {X86_VENDOR_INTEL, 6, model, X86_FEATURE_APERFMPERF, 0} +#define X86_MATCH(model) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, \ + INTEL_FAM6_##model, X86_FEATURE_APERFMPERF, NULL) static const struct x86_cpu_id has_knl_turbo_ratio_limits[] = { - ICPU(INTEL_FAM6_XEON_PHI_KNL), - ICPU(INTEL_FAM6_XEON_PHI_KNM), + X86_MATCH(XEON_PHI_KNL), + X86_MATCH(XEON_PHI_KNM), {} }; static const struct x86_cpu_id has_skx_turbo_ratio_limits[] = { - ICPU(INTEL_FAM6_SKYLAKE_X), + X86_MATCH(SKYLAKE_X), {} }; static const struct x86_cpu_id has_glm_turbo_ratio_limits[] = { - ICPU(INTEL_FAM6_ATOM_GOLDMONT), - ICPU(INTEL_FAM6_ATOM_GOLDMONT_D), - ICPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS), + X86_MATCH(ATOM_GOLDMONT), + X86_MATCH(ATOM_GOLDMONT_D), + X86_MATCH(ATOM_GOLDMONT_PLUS), {} }; diff --git a/arch/x86/kernel/sys_ia32.c b/arch/x86/kernel/sys_ia32.c index ab03fede1422..f8d65c99feb8 100644 --- a/arch/x86/kernel/sys_ia32.c +++ b/arch/x86/kernel/sys_ia32.c @@ -135,26 +135,30 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat) typeof(ubuf->st_gid) gid = 0; SET_UID(uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(gid, from_kgid_munged(current_user_ns(), stat->gid)); - if (!access_ok(ubuf, sizeof(struct stat64)) || - __put_user(huge_encode_dev(stat->dev), &ubuf->st_dev) || - __put_user(stat->ino, &ubuf->__st_ino) || - __put_user(stat->ino, &ubuf->st_ino) || - __put_user(stat->mode, &ubuf->st_mode) || - __put_user(stat->nlink, &ubuf->st_nlink) || - __put_user(uid, &ubuf->st_uid) || - __put_user(gid, &ubuf->st_gid) || - __put_user(huge_encode_dev(stat->rdev), &ubuf->st_rdev) || - __put_user(stat->size, &ubuf->st_size) || - __put_user(stat->atime.tv_sec, &ubuf->st_atime) || - __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec) || - __put_user(stat->mtime.tv_sec, &ubuf->st_mtime) || - __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec) || - __put_user(stat->ctime.tv_sec, &ubuf->st_ctime) || - __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec) || - __put_user(stat->blksize, &ubuf->st_blksize) || - __put_user(stat->blocks, &ubuf->st_blocks)) + if (!user_write_access_begin(ubuf, sizeof(struct stat64))) return -EFAULT; + unsafe_put_user(huge_encode_dev(stat->dev), &ubuf->st_dev, Efault); + unsafe_put_user(stat->ino, &ubuf->__st_ino, Efault); + unsafe_put_user(stat->ino, &ubuf->st_ino, Efault); + unsafe_put_user(stat->mode, &ubuf->st_mode, Efault); + unsafe_put_user(stat->nlink, &ubuf->st_nlink, Efault); + unsafe_put_user(uid, &ubuf->st_uid, Efault); + unsafe_put_user(gid, &ubuf->st_gid, Efault); + unsafe_put_user(huge_encode_dev(stat->rdev), &ubuf->st_rdev, Efault); + unsafe_put_user(stat->size, &ubuf->st_size, Efault); + unsafe_put_user(stat->atime.tv_sec, &ubuf->st_atime, Efault); + unsafe_put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec, Efault); + unsafe_put_user(stat->mtime.tv_sec, &ubuf->st_mtime, Efault); + unsafe_put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec, Efault); + unsafe_put_user(stat->ctime.tv_sec, &ubuf->st_ctime, Efault); + unsafe_put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec, Efault); + unsafe_put_user(stat->blksize, &ubuf->st_blksize, Efault); + unsafe_put_user(stat->blocks, &ubuf->st_blocks, Efault); + user_access_end(); return 0; +Efault: + user_write_access_end(); + return -EFAULT; } COMPAT_SYSCALL_DEFINE2(ia32_stat64, const char __user *, filename, diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index b89f6ac6a0c0..992fb1415c0f 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -23,7 +23,6 @@ #include <asm/realmode.h> #include <asm/processor.h> #include <asm/bootparam.h> -#include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/swiotlb.h> #include <asm/fixmap.h> @@ -35,8 +34,7 @@ #include "../realmode/rm/wakeup.h" /* Global pointer to shared data; NULL means no measured launch. */ -struct tboot *tboot __read_mostly; -EXPORT_SYMBOL(tboot); +static struct tboot *tboot __read_mostly; /* timeout for APs (in secs) to enter wait-for-SIPI state during shutdown */ #define AP_WAIT_TIMEOUT 1 @@ -46,6 +44,11 @@ EXPORT_SYMBOL(tboot); static u8 tboot_uuid[16] __initdata = TBOOT_UUID; +bool tboot_enabled(void) +{ + return tboot != NULL; +} + void __init tboot_probe(void) { /* Look for valid page-aligned address for shared page. */ @@ -90,7 +93,7 @@ static struct mm_struct tboot_mm = { .pgd = swapper_pg_dir, .mm_users = ATOMIC_INIT(2), .mm_count = ATOMIC_INIT(1), - .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), + MMAP_LOCK_INITIALIZER(init_mm) .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), }; diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 106e7f87f534..e42faa792c07 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -25,10 +25,6 @@ #include <asm/hpet.h> #include <asm/time.h> -#ifdef CONFIG_X86_64 -__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES; -#endif - unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); @@ -103,6 +99,9 @@ static __init void x86_late_time_init(void) */ x86_init.irqs.intr_mode_init(); tsc_init(); + + if (static_cpu_has(X86_FEATURE_WAITPKG)) + use_tpause_delay(); } /* diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c index 496748ed266a..fcfc077afe2d 100644 --- a/arch/x86/kernel/tracepoint.c +++ b/arch/x86/kernel/tracepoint.c @@ -25,20 +25,3 @@ void trace_pagefault_unreg(void) { static_branch_dec(&trace_pagefault_key); } - -#ifdef CONFIG_SMP - -DEFINE_STATIC_KEY_FALSE(trace_resched_ipi_key); - -int trace_resched_ipi_reg(void) -{ - static_branch_inc(&trace_resched_ipi_key); - return 0; -} - -void trace_resched_ipi_unreg(void) -{ - static_branch_dec(&trace_resched_ipi_key); -} - -#endif diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d54cffdc7cac..af75109485c2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -37,10 +37,12 @@ #include <linux/mm.h> #include <linux/smp.h> #include <linux/io.h> +#include <linux/hardirq.h> +#include <linux/atomic.h> + #include <asm/stacktrace.h> #include <asm/processor.h> #include <asm/debugreg.h> -#include <linux/atomic.h> #include <asm/text-patching.h> #include <asm/ftrace.h> #include <asm/traps.h> @@ -82,78 +84,6 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } -/* - * In IST context, we explicitly disable preemption. This serves two - * purposes: it makes it much less likely that we would accidentally - * schedule in IST context and it will force a warning if we somehow - * manage to schedule by accident. - */ -void ist_enter(struct pt_regs *regs) -{ - if (user_mode(regs)) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - } else { - /* - * We might have interrupted pretty much anything. In - * fact, if we're a machine check, we can even interrupt - * NMI processing. We don't want in_nmi() to return true, - * but we need to notify RCU. - */ - rcu_nmi_enter(); - } - - preempt_disable(); - - /* This code is a bit fragile. Test it. */ - RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); -} -NOKPROBE_SYMBOL(ist_enter); - -void ist_exit(struct pt_regs *regs) -{ - preempt_enable_no_resched(); - - if (!user_mode(regs)) - rcu_nmi_exit(); -} - -/** - * ist_begin_non_atomic() - begin a non-atomic section in an IST exception - * @regs: regs passed to the IST exception handler - * - * IST exception handlers normally cannot schedule. As a special - * exception, if the exception interrupted userspace code (i.e. - * user_mode(regs) would return true) and the exception was not - * a double fault, it can be safe to schedule. ist_begin_non_atomic() - * begins a non-atomic section within an ist_enter()/ist_exit() region. - * Callers are responsible for enabling interrupts themselves inside - * the non-atomic section, and callers must call ist_end_non_atomic() - * before ist_exit(). - */ -void ist_begin_non_atomic(struct pt_regs *regs) -{ - BUG_ON(!user_mode(regs)); - - /* - * Sanity check: we need to be on the normal thread stack. This - * will catch asm bugs and any attempt to use ist_preempt_enable - * from double_fault. - */ - BUG_ON(!on_thread_stack()); - - preempt_enable_no_resched(); -} - -/** - * ist_end_non_atomic() - begin a non-atomic section in an IST exception - * - * Ends a non-atomic section started with ist_begin_non_atomic(). - */ -void ist_end_non_atomic(void) -{ - preempt_disable(); -} - int is_valid_bugaddr(unsigned long addr) { unsigned short ud; @@ -167,24 +97,6 @@ int is_valid_bugaddr(unsigned long addr) return ud == INSN_UD0 || ud == INSN_UD2; } -int fixup_bug(struct pt_regs *regs, int trapnr) -{ - if (trapnr != X86_TRAP_UD) - return 0; - - switch (report_bug(regs->ip, regs)) { - case BUG_TRAP_TYPE_NONE: - case BUG_TRAP_TYPE_BUG: - break; - - case BUG_TRAP_TYPE_WARN: - regs->ip += LEN_UD2; - return 1; - } - - return 0; -} - static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, struct pt_regs *regs, long error_code) @@ -215,7 +127,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, const char *str, * process no chance to handle the signal and notice the * kernel fault information, so that won't result in polluting * the information about previously queued, but not yet - * delivered, faults. See also do_general_protection below. + * delivered, faults. See also exc_general_protection below. */ tsk->thread.error_code = error_code; tsk->thread.trap_nr = trapnr; @@ -260,41 +172,119 @@ static void do_error_trap(struct pt_regs *regs, long error_code, char *str, { RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - /* - * WARN*()s end up here; fix them up before we call the - * notifier chain. - */ - if (!user_mode(regs) && fixup_bug(regs, trapnr)) - return; - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != NOTIFY_STOP) { cond_local_irq_enable(regs); do_trap(trapnr, signr, str, regs, error_code, sicode, addr); + cond_local_irq_disable(regs); } } -#define IP ((void __user *)uprobe_get_trap_addr(regs)) -#define DO_ERROR(trapnr, signr, sicode, addr, str, name) \ -dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - do_error_trap(regs, error_code, str, trapnr, signr, sicode, addr); \ +/* + * Posix requires to provide the address of the faulting instruction for + * SIGILL (#UD) and SIGFPE (#DE) in the si_addr member of siginfo_t. + * + * This address is usually regs->ip, but when an uprobe moved the code out + * of line then regs->ip points to the XOL code which would confuse + * anything which analyzes the fault address vs. the unmodified binary. If + * a trap happened in XOL code then uprobe maps regs->ip back to the + * original instruction address. + */ +static __always_inline void __user *error_get_trap_addr(struct pt_regs *regs) +{ + return (void __user *)uprobe_get_trap_addr(regs); +} + +DEFINE_IDTENTRY(exc_divide_error) +{ + do_error_trap(regs, 0, "divide_error", X86_TRAP_DE, SIGFPE, + FPE_INTDIV, error_get_trap_addr(regs)); } -DO_ERROR(X86_TRAP_DE, SIGFPE, FPE_INTDIV, IP, "divide error", divide_error) -DO_ERROR(X86_TRAP_OF, SIGSEGV, 0, NULL, "overflow", overflow) -DO_ERROR(X86_TRAP_UD, SIGILL, ILL_ILLOPN, IP, "invalid opcode", invalid_op) -DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, 0, NULL, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(X86_TRAP_TS, SIGSEGV, 0, NULL, "invalid TSS", invalid_TSS) -DO_ERROR(X86_TRAP_NP, SIGBUS, 0, NULL, "segment not present", segment_not_present) -DO_ERROR(X86_TRAP_SS, SIGBUS, 0, NULL, "stack segment", stack_segment) -#undef IP +DEFINE_IDTENTRY(exc_overflow) +{ + do_error_trap(regs, 0, "overflow", X86_TRAP_OF, SIGSEGV, 0, NULL); +} -dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code) +#ifdef CONFIG_X86_F00F_BUG +void handle_invalid_op(struct pt_regs *regs) +#else +static inline void handle_invalid_op(struct pt_regs *regs) +#endif { - char *str = "alignment check"; + do_error_trap(regs, 0, "invalid opcode", X86_TRAP_UD, SIGILL, + ILL_ILLOPN, error_get_trap_addr(regs)); +} - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); +DEFINE_IDTENTRY_RAW(exc_invalid_op) +{ + bool rcu_exit; + + /* + * Handle BUG/WARN like NMIs instead of like normal idtentries: + * if we bugged/warned in a bad RCU context, for example, the last + * thing we want is to BUG/WARN again in the idtentry code, ad + * infinitum. + */ + if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) { + enum bug_trap_type type; + + nmi_enter(); + instrumentation_begin(); + trace_hardirqs_off_finish(); + type = report_bug(regs->ip, regs); + if (regs->flags & X86_EFLAGS_IF) + trace_hardirqs_on_prepare(); + instrumentation_end(); + nmi_exit(); + + if (type == BUG_TRAP_TYPE_WARN) { + /* Skip the ud2. */ + regs->ip += LEN_UD2; + return; + } + + /* + * Else, if this was a BUG and report_bug returns or if this + * was just a normal #UD, we want to continue onward and + * crash. + */ + } + + rcu_exit = idtentry_enter_cond_rcu(regs); + instrumentation_begin(); + handle_invalid_op(regs); + instrumentation_end(); + idtentry_exit_cond_rcu(regs, rcu_exit); +} + +DEFINE_IDTENTRY(exc_coproc_segment_overrun) +{ + do_error_trap(regs, 0, "coprocessor segment overrun", + X86_TRAP_OLD_MF, SIGFPE, 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_invalid_tss) +{ + do_error_trap(regs, error_code, "invalid TSS", X86_TRAP_TS, SIGSEGV, + 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_segment_not_present) +{ + do_error_trap(regs, error_code, "segment not present", X86_TRAP_NP, + SIGBUS, 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_stack_segment) +{ + do_error_trap(regs, error_code, "stack segment", X86_TRAP_SS, SIGBUS, + 0, NULL); +} + +DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check) +{ + char *str = "alignment check"; if (notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_AC, SIGBUS) == NOTIFY_STOP) return; @@ -326,7 +316,6 @@ __visible void __noreturn handle_stack_overflow(const char *message, } #endif -#if defined(CONFIG_X86_64) || defined(CONFIG_DOUBLEFAULT) /* * Runs on an IST stack for x86_64 and on a special task stack for x86_32. * @@ -342,12 +331,19 @@ __visible void __noreturn handle_stack_overflow(const char *message, * from the TSS. Returning is, in principle, okay, but changes to regs will * be lost. If, for some reason, we need to return to a context with modified * regs, the shim code could be adjusted to synchronize the registers. + * + * The 32bit #DF shim provides CR2 already as an argument. On 64bit it needs + * to be read before doing anything else. */ -dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long cr2) +DEFINE_IDTENTRY_DF(exc_double_fault) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_VMAP_STACK + unsigned long address = read_cr2(); +#endif + #ifdef CONFIG_X86_ESPFIX64 extern unsigned char native_irq_return_iret[]; @@ -363,13 +359,14 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * The net result is that our #GP handler will think that we * entered from usermode with the bad user context. * - * No need for ist_enter here because we don't use RCU. + * No need for nmi_enter() here because we don't use RCU. */ if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY && regs->cs == __KERNEL_CS && regs->ip == (unsigned long)native_irq_return_iret) { struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + unsigned long *p = (unsigned long *)regs->sp; /* * regs->sp points to the failing IRET frame on the @@ -377,7 +374,11 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * in gpregs->ss through gpregs->ip. * */ - memmove(&gpregs->ip, (void *)regs->sp, 5*8); + gpregs->ip = p[0]; + gpregs->cs = p[1]; + gpregs->flags = p[2]; + gpregs->sp = p[3]; + gpregs->ss = p[4]; gpregs->orig_ax = 0; /* Missing (lost) #GP error code */ /* @@ -391,14 +392,15 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * which is what the stub expects, given that the faulting * RIP will be the IRET instruction. */ - regs->ip = (unsigned long)general_protection; + regs->ip = (unsigned long)asm_exc_general_protection; regs->sp = (unsigned long)&gpregs->orig_ax; return; } #endif - ist_enter(regs); + nmi_enter(); + instrumentation_begin(); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); tsk->thread.error_code = error_code; @@ -442,28 +444,31 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsign * stack even if the actual trigger for the double fault was * something else. */ - if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE) - handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2); + if ((unsigned long)task_stack_page(tsk) - 1 - address < PAGE_SIZE) { + handle_stack_overflow("kernel stack overflow (double-fault)", + regs, address); + } #endif pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); die("double fault", regs, error_code); panic("Machine halted."); + instrumentation_end(); } -#endif -dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_bounds) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - if (notify_die(DIE_TRAP, "bounds", regs, error_code, + if (notify_die(DIE_TRAP, "bounds", regs, 0, X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP) return; cond_local_irq_enable(regs); if (!user_mode(regs)) - die("bounds", regs, error_code); + die("bounds", regs, 0); - do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL); + do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, 0, 0, NULL); + + cond_local_irq_disable(regs); } enum kernel_gp_hint { @@ -510,7 +515,7 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, #define GPFSTR "general protection fault" -dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; enum kernel_gp_hint hint = GP_NO_HINT; @@ -518,17 +523,17 @@ dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) unsigned long gp_addr; int ret; - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); cond_local_irq_enable(regs); if (static_cpu_has(X86_FEATURE_UMIP)) { if (user_mode(regs) && fixup_umip_exception(regs)) - return; + goto exit; } if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + local_irq_disable(); return; } @@ -540,12 +545,11 @@ dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) show_signal(tsk, SIGSEGV, "", desc, regs, error_code); force_sig(SIGSEGV); - - return; + goto exit; } if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - return; + goto exit; tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -557,11 +561,11 @@ dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) if (!preemptible() && kprobe_running() && kprobe_fault_handler(regs, X86_TRAP_GP)) - return; + goto exit; ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); if (ret == NOTIFY_STOP) - return; + goto exit; if (error_code) snprintf(desc, sizeof(desc), "segment-related " GPFSTR); @@ -583,55 +587,74 @@ dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) die_addr(desc, regs, error_code, gp_addr); +exit: + cond_local_irq_disable(regs); } -NOKPROBE_SYMBOL(do_general_protection); -dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) +static bool do_int3(struct pt_regs *regs) { - if (poke_int3_handler(regs)) - return; - - /* - * Unlike any other non-IST entry, we can be called from a kprobe in - * non-CONTEXT_KERNEL kernel mode or even during context tracking - * state changes. Make sure that we wake up RCU even if we're coming - * from kernel code. - * - * This means that we can't schedule even if we came from a - * preemptible kernel context. That's okay. - */ - if (!user_mode(regs)) { - rcu_nmi_enter(); - preempt_disable(); - } - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); + int res; #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP - if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, - SIGTRAP) == NOTIFY_STOP) - goto exit; + if (kgdb_ll_trap(DIE_INT3, "int3", regs, 0, X86_TRAP_BP, + SIGTRAP) == NOTIFY_STOP) + return true; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ #ifdef CONFIG_KPROBES if (kprobe_int3_handler(regs)) - goto exit; + return true; #endif + res = notify_die(DIE_INT3, "int3", regs, 0, X86_TRAP_BP, SIGTRAP); - if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, - SIGTRAP) == NOTIFY_STOP) - goto exit; + return res == NOTIFY_STOP; +} + +static void do_int3_user(struct pt_regs *regs) +{ + if (do_int3(regs)) + return; cond_local_irq_enable(regs); - do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, 0, NULL); + do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, 0, 0, NULL); cond_local_irq_disable(regs); +} -exit: - if (!user_mode(regs)) { - preempt_enable_no_resched(); - rcu_nmi_exit(); +DEFINE_IDTENTRY_RAW(exc_int3) +{ + /* + * poke_int3_handler() is completely self contained code; it does (and + * must) *NOT* call out to anything, lest it hits upon yet another + * INT3. + */ + if (poke_int3_handler(regs)) + return; + + /* + * idtentry_enter_user() uses static_branch_{,un}likely() and therefore + * can trigger INT3, hence poke_int3_handler() must be done + * before. If the entry came from kernel mode, then use nmi_enter() + * because the INT3 could have been hit in any context including + * NMI. + */ + if (user_mode(regs)) { + idtentry_enter_user(regs); + instrumentation_begin(); + do_int3_user(regs); + instrumentation_end(); + idtentry_exit_user(regs); + } else { + nmi_enter(); + instrumentation_begin(); + trace_hardirqs_off_finish(); + if (!do_int3(regs)) + die("int3", regs, 0); + if (regs->flags & X86_EFLAGS_IF) + trace_hardirqs_on_prepare(); + instrumentation_end(); + nmi_exit(); } } -NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* @@ -639,21 +662,20 @@ NOKPROBE_SYMBOL(do_int3); * to switch to the normal thread stack if the interrupted code was in * user mode. The actual stack switch is done in entry_64.S */ -asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; if (regs != eregs) *regs = *eregs; return regs; } -NOKPROBE_SYMBOL(sync_regs); struct bad_iret_stack { void *error_entry_ret; struct pt_regs regs; }; -asmlinkage __visible notrace +asmlinkage __visible noinstr struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) { /* @@ -664,19 +686,21 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) * just below the IRET frame) and we want to pretend that the * exception came from the IRET target. */ - struct bad_iret_stack *new_stack = - (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; + struct bad_iret_stack tmp, *new_stack = + (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; - /* Copy the IRET target to the new stack. */ - memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + /* Copy the IRET target to the temporary storage. */ + memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + + /* Update the entry stack */ + memcpy(new_stack, &tmp, sizeof(tmp)); BUG_ON(!user_mode(&new_stack->regs)); return new_stack; } -NOKPROBE_SYMBOL(fixup_bad_iret); #endif static bool is_sysenter_singlestep(struct pt_regs *regs) @@ -702,6 +726,43 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } +static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) +{ + /* + * Disable breakpoints during exception handling; recursive exceptions + * are exceedingly 'fun'. + * + * Since this function is NOKPROBE, and that also applies to + * HW_BREAKPOINT_X, we can't hit a breakpoint before this (XXX except a + * HW_BREAKPOINT_W on our stack) + * + * Entry text is excluded for HW_BP_X and cpu_entry_area, which + * includes the entry stack is excluded for everything. + */ + *dr7 = local_db_save(); + + /* + * The Intel SDM says: + * + * Certain debug exceptions may clear bits 0-3. The remaining + * contents of the DR6 register are never cleared by the + * processor. To avoid confusion in identifying debug + * exceptions, debug handlers should clear the register before + * returning to the interrupted task. + * + * Keep it simple: clear DR6 immediately. + */ + get_debugreg(*dr6, 6); + set_debugreg(0, 6); + /* Filter out all the reserved bits which are preset to 1 */ + *dr6 &= ~DR6_RESERVED; +} + +static __always_inline void debug_exit(unsigned long dr7) +{ + local_db_restore(dr7); +} + /* * Our handling of the processor debug registers is non-trivial. * We do not clear them on entry and exit from the kernel. Therefore @@ -726,86 +787,54 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) * * May run on IST stack. */ -dotraplinkage void do_debug(struct pt_regs *regs, long error_code) +static void handle_debug(struct pt_regs *regs, unsigned long dr6, bool user) { struct task_struct *tsk = current; - int user_icebp = 0; - unsigned long dr6; + bool user_icebp; int si_code; - ist_enter(regs); - - get_debugreg(dr6, 6); - /* - * The Intel SDM says: - * - * Certain debug exceptions may clear bits 0-3. The remaining - * contents of the DR6 register are never cleared by the - * processor. To avoid confusion in identifying debug - * exceptions, debug handlers should clear the register before - * returning to the interrupted task. - * - * Keep it simple: clear DR6 immediately. - */ - set_debugreg(0, 6); - - /* Filter out all the reserved bits which are preset to 1 */ - dr6 &= ~DR6_RESERVED; - /* * The SDM says "The processor clears the BTF flag when it * generates a debug exception." Clear TIF_BLOCKSTEP to keep * TIF_BLOCKSTEP in sync with the hardware BTF flag. */ - clear_tsk_thread_flag(tsk, TIF_BLOCKSTEP); + clear_thread_flag(TIF_BLOCKSTEP); - if (unlikely(!user_mode(regs) && (dr6 & DR_STEP) && - is_sysenter_singlestep(regs))) { - dr6 &= ~DR_STEP; - if (!dr6) - goto exit; - /* - * else we might have gotten a single-step trap and hit a - * watchpoint at the same time, in which case we should fall - * through and handle the watchpoint. - */ - } + /* + * If DR6 is zero, no point in trying to handle it. The kernel is + * not using INT1. + */ + if (!user && !dr6) + return; /* * If dr6 has no reason to give us about the origin of this trap, * then it's very likely the result of an icebp/int01 trap. * User wants a sigtrap for that. */ - if (!dr6 && user_mode(regs)) - user_icebp = 1; + user_icebp = user && !dr6; /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; #ifdef CONFIG_KPROBES - if (kprobe_debug_handler(regs)) - goto exit; + if (kprobe_debug_handler(regs)) { + return; + } #endif - if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, - SIGTRAP) == NOTIFY_STOP) - goto exit; - - /* - * Let others (NMI) know that the debug stack is in use - * as we may switch to the interrupt stack. - */ - debug_stack_usage_inc(); + if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, 0, + SIGTRAP) == NOTIFY_STOP) { + return; + } /* It's safe to allow irq's after DR6 has been saved */ cond_local_irq_enable(regs); if (v8086_mode(regs)) { - handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, - X86_TRAP_DB); - cond_local_irq_disable(regs); - debug_stack_usage_dec(); - goto exit; + handle_vm86_trap((struct kernel_vm86_regs *) regs, 0, + X86_TRAP_DB); + goto out; } if (WARN_ON_ONCE((dr6 & DR_STEP) && !user_mode(regs))) { @@ -819,23 +848,91 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) set_tsk_thread_flag(tsk, TIF_SINGLESTEP); regs->flags &= ~X86_EFLAGS_TF; } + si_code = get_si_code(tsk->thread.debugreg6); if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp) - send_sigtrap(regs, error_code, si_code); + send_sigtrap(regs, 0, si_code); + +out: cond_local_irq_disable(regs); - debug_stack_usage_dec(); +} -exit: - ist_exit(regs); +static __always_inline void exc_debug_kernel(struct pt_regs *regs, + unsigned long dr6) +{ + nmi_enter(); + instrumentation_begin(); + trace_hardirqs_off_finish(); + + /* + * Catch SYSENTER with TF set and clear DR_STEP. If this hit a + * watchpoint at the same time then that will still be handled. + */ + if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs)) + dr6 &= ~DR_STEP; + + handle_debug(regs, dr6, false); + + if (regs->flags & X86_EFLAGS_IF) + trace_hardirqs_on_prepare(); + instrumentation_end(); + nmi_exit(); +} + +static __always_inline void exc_debug_user(struct pt_regs *regs, + unsigned long dr6) +{ + idtentry_enter_user(regs); + instrumentation_begin(); + + handle_debug(regs, dr6, true); + instrumentation_end(); + idtentry_exit_user(regs); +} + +#ifdef CONFIG_X86_64 +/* IST stack entry */ +DEFINE_IDTENTRY_DEBUG(exc_debug) +{ + unsigned long dr6, dr7; + + debug_enter(&dr6, &dr7); + exc_debug_kernel(regs, dr6); + debug_exit(dr7); +} + +/* User entry, runs on regular task stack */ +DEFINE_IDTENTRY_DEBUG_USER(exc_debug) +{ + unsigned long dr6, dr7; + + debug_enter(&dr6, &dr7); + exc_debug_user(regs, dr6); + debug_exit(dr7); } -NOKPROBE_SYMBOL(do_debug); +#else +/* 32 bit does not have separate entry points. */ +DEFINE_IDTENTRY_DEBUG(exc_debug) +{ + unsigned long dr6, dr7; + + debug_enter(&dr6, &dr7); + + if (user_mode(regs)) + exc_debug_user(regs, dr6); + else + exc_debug_kernel(regs, dr6); + + debug_exit(dr7); +} +#endif /* * Note that we play around with the 'TS' bit in an attempt to get * the correct behaviour even in the presence of the asynchronous * IRQ13 behaviour */ -static void math_error(struct pt_regs *regs, int error_code, int trapnr) +static void math_error(struct pt_regs *regs, int trapnr) { struct task_struct *task = current; struct fpu *fpu = &task->thread.fpu; @@ -846,16 +943,16 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) cond_local_irq_enable(regs); if (!user_mode(regs)) { - if (fixup_exception(regs, trapnr, error_code, 0)) - return; + if (fixup_exception(regs, trapnr, 0, 0)) + goto exit; - task->thread.error_code = error_code; + task->thread.error_code = 0; task->thread.trap_nr = trapnr; - if (notify_die(DIE_TRAP, str, regs, error_code, - trapnr, SIGFPE) != NOTIFY_STOP) - die(str, regs, error_code); - return; + if (notify_die(DIE_TRAP, str, regs, 0, trapnr, + SIGFPE) != NOTIFY_STOP) + die(str, regs, 0); + goto exit; } /* @@ -864,32 +961,37 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) fpu__save(fpu); task->thread.trap_nr = trapnr; - task->thread.error_code = error_code; + task->thread.error_code = 0; si_code = fpu__exception_code(fpu, trapnr); /* Retry when we get spurious exceptions: */ if (!si_code) - return; + goto exit; force_sig_fault(SIGFPE, si_code, (void __user *)uprobe_get_trap_addr(regs)); +exit: + cond_local_irq_disable(regs); } -dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_coprocessor_error) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - math_error(regs, error_code, X86_TRAP_MF); + math_error(regs, X86_TRAP_MF); } -dotraplinkage void -do_simd_coprocessor_error(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_simd_coprocessor_error) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - math_error(regs, error_code, X86_TRAP_XF); + if (IS_ENABLED(CONFIG_X86_INVD_BUG)) { + /* AMD 486 bug: INVD in CPL 0 raises #XF instead of #GP */ + if (!static_cpu_has(X86_FEATURE_XMM)) { + __exc_general_protection(regs, 0); + return; + } + } + math_error(regs, X86_TRAP_XF); } -dotraplinkage void -do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_spurious_interrupt_bug) { /* * This addresses a Pentium Pro Erratum: @@ -912,13 +1014,10 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code) */ } -dotraplinkage void -do_device_not_available(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY(exc_device_not_available) { unsigned long cr0 = read_cr0(); - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); - #ifdef CONFIG_MATH_EMULATION if (!boot_cpu_has(X86_FEATURE_FPU) && (cr0 & X86_CR0_EM)) { struct math_emu_info info = { }; @@ -927,6 +1026,8 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); + + cond_local_irq_disable(regs); return; } #endif @@ -941,22 +1042,20 @@ do_device_not_available(struct pt_regs *regs, long error_code) * to kill the task than getting stuck in a never-ending * loop of #NM faults. */ - die("unexpected #NM exception", regs, error_code); + die("unexpected #NM exception", regs, 0); } } -NOKPROBE_SYMBOL(do_device_not_available); #ifdef CONFIG_X86_32 -dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) +DEFINE_IDTENTRY_SW(iret_error) { - RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); local_irq_enable(); - - if (notify_die(DIE_TRAP, "iret exception", regs, error_code, + if (notify_die(DIE_TRAP, "iret exception", regs, 0, X86_TRAP_IRET, SIGILL) != NOTIFY_STOP) { - do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, + do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, 0, ILL_BADSTK, (void __user *)NULL); } + local_irq_disable(); } #endif @@ -968,22 +1067,9 @@ void __init trap_init(void) idt_setup_traps(); /* - * Set the IDT descriptor to a fixed read-only location, so that the - * "sidt" instruction will not leak the location of the kernel, and - * to defend the IDT against arbitrary memory write vulnerabilities. - * It will be reloaded in cpu_init() */ - cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table), - PAGE_KERNEL_RO); - idt_descr.address = CPU_ENTRY_AREA_RO_IDT; - - /* * Should be a barrier for any external CPU state: */ cpu_init(); idt_setup_ist_traps(); - - x86_init.irqs.trap_init(); - - idt_setup_debugidt_traps(); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index fdd4c1078632..49d925043171 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -41,6 +41,7 @@ EXPORT_SYMBOL(tsc_khz); * TSC can be unstable due to cpufreq or due to unsynced TSCs */ static int __read_mostly tsc_unstable; +static unsigned int __initdata tsc_early_khz; static DEFINE_STATIC_KEY_FALSE(__use_tsc); @@ -59,6 +60,12 @@ struct cyc2ns { static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); +static int __init tsc_early_khz_setup(char *buf) +{ + return kstrtouint(buf, 0, &tsc_early_khz); +} +early_param("tsc_early_khz", tsc_early_khz_setup); + __always_inline void cyc2ns_read_begin(struct cyc2ns_data *data) { int seq, idx; @@ -1412,7 +1419,10 @@ static bool __init determine_cpu_tsc_frequencies(bool early) if (early) { cpu_khz = x86_platform.calibrate_cpu(); - tsc_khz = x86_platform.calibrate_tsc(); + if (tsc_early_khz) + tsc_khz = tsc_early_khz; + else + tsc_khz = x86_platform.calibrate_tsc(); } else { /* We should not be here with non-native cpu calibration */ WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu); diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 54226110bc7f..722a85f3b2dd 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -74,13 +74,7 @@ static bool in_entry_code(unsigned long ip) { char *addr = (char *)ip; - if (addr >= __entry_text_start && addr < __entry_text_end) - return true; - - if (addr >= __irqentry_text_start && addr < __irqentry_text_end) - return true; - - return false; + return addr >= __entry_text_start && addr < __entry_text_end; } static inline unsigned long *last_frame(struct unwind_state *state) diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 47a8676c7395..764573de3996 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -171,7 +171,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pte_t *pte; int i; - down_write(&mm->mmap_sem); + mmap_write_lock(mm); pgd = pgd_offset(mm, 0xA0000); if (pgd_none_or_clear_bad(pgd)) goto out; @@ -197,7 +197,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) } pte_unmap_unlock(pte, ptl); out: - up_write(&mm->mmap_sem); + mmap_write_unlock(mm); flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT, false); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 1bf7e312361f..3bfc8dd8a43d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -40,13 +40,13 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT) #ifdef CONFIG_X86_32 OUTPUT_ARCH(i386) ENTRY(phys_startup_32) -jiffies = jiffies_64; #else OUTPUT_ARCH(i386:x86-64) ENTRY(phys_startup_64) -jiffies_64 = jiffies; #endif +jiffies = jiffies_64; + #if defined(CONFIG_X86_64) /* * On 64-bit, align RODATA to 2MB so we retain large page mappings for @@ -134,7 +134,6 @@ SECTIONS KPROBES_TEXT ALIGN_ENTRY_TEXT_BEGIN ENTRY_TEXT - IRQENTRY_TEXT ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT *(.fixup) diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 85f1a90c55cd..123f1c1f1788 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -79,7 +79,6 @@ struct x86_init_ops x86_init __initdata = { .irqs = { .pre_vector_init = init_ISA_irqs, .intr_init = native_init_IRQ, - .trap_init = x86_init_noop, .intr_mode_select = apic_intr_mode_select, .intr_mode_init = apic_intr_mode_init }, |