diff options
Diffstat (limited to 'arch/x86')
70 files changed, 540 insertions, 312 deletions
diff --git a/arch/x86/boot/cmdline.c b/arch/x86/boot/cmdline.c index 4ff01176c1cc..21d56ae83cdf 100644 --- a/arch/x86/boot/cmdline.c +++ b/arch/x86/boot/cmdline.c @@ -54,7 +54,7 @@ int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *b /* else */ state = st_wordcmp; opptr = option; - /* fall through */ + fallthrough; case st_wordcmp: if (c == '=' && !*opptr) { @@ -129,7 +129,7 @@ int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option) state = st_wordcmp; opptr = option; wstart = pos; - /* fall through */ + fallthrough; case st_wordcmp: if (!*opptr) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3962f592633d..ff7894f39e0e 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -43,6 +43,8 @@ KBUILD_CFLAGS += -Wno-pointer-sign KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables KBUILD_CFLAGS += -D__DISABLE_EXPORTS +# Disable relocation relaxation in case the link is not PIE. +KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 0048269180d5..dde7cb3724df 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -178,7 +178,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size, } *size = 0; } - /* Fall through */ + fallthrough; default: /* * If w/o offset, only size specified, memmap=nn[KMG] has the diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b4..e478e40fbe5a 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512..a232da487cd2 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index d7577fece9eb..78210793d357 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -19,6 +19,7 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_BLK_DEV_INITRD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +# CONFIG_64BIT is not set CONFIG_SMP=y CONFIG_X86_GENERIC=y CONFIG_HPET_TIMER=y @@ -186,7 +187,6 @@ CONFIG_DRM_I915=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index f85600143747..9936528e1939 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -181,7 +181,6 @@ CONFIG_DRM_I915=y CONFIG_FB_MODE_HELPERS=y CONFIG_FB_TILEBLITTING=y CONFIG_FB_EFI=y -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 98e4d8886f11..ae9b0d4615b3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with * Fetch the per-CPU GSBASE value for this processor and put it in @reg. * We normally use %gs for accessing per-CPU data, but we are setting up * %gs here and obviously can not use %gs itself to access per-CPU data. + * + * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and + * may not restore the host's value until the CPU returns to userspace. + * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives + * while running KVM's run loop. */ .macro GET_PERCPU_BASE reg:req - ALTERNATIVE \ - "LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \ - "RDPID \reg", \ - X86_FEATURE_RDPID + LOAD_CPU_AND_NODE_SEG_LIMIT \reg andq $VDSO_CPUNODE_MASK, \reg movq __per_cpu_offset(, \reg, 8), \reg .endm diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 48512c7944e7..870efeec8bda 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -60,16 +60,10 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static __always_inline unsigned int syscall_32_enter(struct pt_regs *regs) { - unsigned int nr = (unsigned int)regs->orig_ax; - if (IS_ENABLED(CONFIG_IA32_EMULATION)) current_thread_info()->status |= TS_COMPAT; - /* - * Subtlety here: if ptrace pokes something larger than 2^32-1 into - * orig_ax, the unsigned int return value truncates it. This may - * or may not be necessary, but it matches the old asm behavior. - */ - return (unsigned int)syscall_enter_from_user_mode(regs, nr); + + return (unsigned int)regs->orig_ax; } /* @@ -91,15 +85,29 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { unsigned int nr = syscall_32_enter(regs); + /* + * Subtlety here: if ptrace pokes something larger than 2^32-1 into + * orig_ax, the unsigned int return value truncates it. This may + * or may not be necessary, but it matches the old asm behavior. + */ + nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + do_syscall_32_irqs_on(regs, nr); syscall_exit_to_user_mode(regs); } static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { - unsigned int nr = syscall_32_enter(regs); + unsigned int nr = syscall_32_enter(regs); int res; + /* + * This cannot use syscall_enter_from_user_mode() as it has to + * fetch EBP before invoking any of the syscall entry work + * functions. + */ + syscall_enter_from_user_mode_prepare(regs); + instrumentation_begin(); /* Fetch EBP from where the vDSO stashed it. */ if (IS_ENABLED(CONFIG_X86_64)) { @@ -122,6 +130,9 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) return false; } + /* The case truncates any ptrace induced syscall nr > 2^32 -1 */ + nr = (unsigned int)syscall_enter_from_user_mode_work(regs, nr); + /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); syscall_exit_to_user_mode(regs); @@ -288,7 +299,7 @@ __visible noinstr void xen_pv_evtchn_do_upcall(struct pt_regs *regs) old_regs = set_irq_regs(regs); instrumentation_begin(); - run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, NULL, regs); + run_on_irqstack_cond(__xen_pv_evtchn_do_upcall, regs); instrumentation_begin(); set_irq_regs(old_regs); diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 70dea9337816..d977079a7d02 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -682,6 +682,8 @@ SYM_CODE_END(.Lbad_gs) * rdx: Function argument (can be NULL if none) */ SYM_FUNC_START(asm_call_on_stack) +SYM_INNER_LABEL(asm_call_sysvec_on_stack, SYM_L_GLOBAL) +SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL) /* * Save the frame pointer unconditionally. This allows the ORC * unwinder to handle the stack switch. diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index 3a07ce3ec70b..f1f96d4d8cd6 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -29,11 +29,6 @@ SYM_CODE_START_NOALIGN(\name) SYM_CODE_END(\name) .endm -#ifdef CONFIG_TRACE_IRQFLAGS - THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1 - THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1 -#endif - #ifdef CONFIG_PREEMPTION THUNK preempt_schedule_thunk, preempt_schedule THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 50963472ee85..31e6887d24f1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4682,7 +4682,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_CORE2_MEROM: x86_add_quirk(intel_clovertown_quirk); - /* fall through */ + fallthrough; case INTEL_FAM6_CORE2_MEROM_L: case INTEL_FAM6_CORE2_PENRYN: @@ -5062,7 +5062,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SKYLAKE_X: pmem = true; - /* fall through */ + fallthrough; case INTEL_FAM6_SKYLAKE_L: case INTEL_FAM6_SKYLAKE: case INTEL_FAM6_KABYLAKE_L: @@ -5114,7 +5114,7 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ICELAKE_X: case INTEL_FAM6_ICELAKE_D: pmem = true; - /* fall through */ + fallthrough; case INTEL_FAM6_ICELAKE_L: case INTEL_FAM6_ICELAKE: case INTEL_FAM6_TIGERLAKE_L: diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 63f58bdf556c..8961653c5dd2 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1268,7 +1268,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) ret = X86_BR_ZERO_CALL; break; } - /* fall through */ + fallthrough; case 0x9a: /* call far absolute */ ret = X86_BR_CALL; break; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index cb94ba86efd2..6a4ca27b2c9e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"), + INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"), + INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"), + INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"), + { /* end: all zeroes */ }, }; @@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 #define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE +/* BW break down- legacy counters */ +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS 0x3 +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE 0x5040 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS 0x4 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE 0x5044 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS 0x5 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE 0x5048 + enum perf_snb_uncore_imc_freerunning_types { - SNB_PCI_UNCORE_IMC_DATA = 0, + SNB_PCI_UNCORE_IMC_DATA_READS = 0, + SNB_PCI_UNCORE_IMC_DATA_WRITES, + SNB_PCI_UNCORE_IMC_GT_REQUESTS, + SNB_PCI_UNCORE_IMC_IA_REQUESTS, + SNB_PCI_UNCORE_IMC_IO_REQUESTS, + SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, }; static struct freerunning_counters snb_uncore_imc_freerunning[] = { - [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IA_REQUESTS] = { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IO_REQUESTS] = { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, }; static struct attribute *snb_uncore_imc_formats_attr[] = { @@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event) base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; idx = UNCORE_PMC_IDX_FREERUNNING; break; + case SNB_UNCORE_PCI_IMC_GT_REQUESTS: + base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IA_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IO_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; default: return -EINVAL; } @@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { static struct intel_uncore_type snb_uncore_imc = { .name = "imc", - .num_counters = 2, + .num_counters = 5, .num_boxes = 1, .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, .mmio_map_size = SNB_UNCORE_PCI_IMC_MAP_SIZE, diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index ca0976456a6b..6d2df1ee427b 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -159,8 +159,6 @@ static inline u64 x86_default_get_root_pointer(void) extern int x86_acpi_numa_init(void); #endif /* CONFIG_ACPI_NUMA */ -#define acpi_unlazy_tlb(x) leave_mm(x) - #ifdef CONFIG_ACPI_APEI static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) { diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b9c2667ac46c..bc9758ef292e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table; kernel_fpu_end(); \ }) - #define arch_efi_call_virt(p, f, args...) p->f(args) -#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ #define EFI_LOADER_SIGNATURE "EL64" @@ -125,9 +122,6 @@ struct efi_scratch { kernel_fpu_end(); \ }) -extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, - u32 type, u64 attribute); - #ifdef CONFIG_KASAN /* * CONFIG_KASAN may redefine memset to __memset. __memset function is present @@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; -extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); -extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern int __init efi_alloc_page_tables(void); extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); -extern void __init old_map_region(efi_memory_desc_t *md); -extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_update_mappings(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index a8f9315b9eae..6fe54b2813c1 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -18,8 +18,16 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) * state, not the interrupt state as imagined by Xen. */ unsigned long flags = native_save_fl(); - WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF | - X86_EFLAGS_NT)); + unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT; + + /* + * For !SMAP hardware we patch out CLAC on entry. + */ + if (boot_cpu_has(X86_FEATURE_SMAP) || + (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + mask |= X86_EFLAGS_AC; + + WARN_ON_ONCE(flags & mask); /* We think we came from user mode. Make sure pt_regs agrees. */ WARN_ON_ONCE(!user_mode(regs)); diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h index 296b346184b2..fb42659f6e98 100644 --- a/arch/x86/include/asm/frame.h +++ b/arch/x86/include/asm/frame.h @@ -60,12 +60,26 @@ #define FRAME_END "pop %" _ASM_BP "\n" #ifdef CONFIG_X86_64 + #define ENCODE_FRAME_POINTER \ "lea 1(%rsp), %rbp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs + 1; +} + #else /* !CONFIG_X86_64 */ + #define ENCODE_FRAME_POINTER \ "movl %esp, %ebp\n\t" \ "andl $0x7fffffff, %ebp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs & 0x7fffffff; +} + #endif /* CONFIG_X86_64 */ #endif /* __ASSEMBLY__ */ @@ -83,6 +97,11 @@ #define ENCODE_FRAME_POINTER +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return 0; +} + #endif #define FRAME_BEGIN diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index a43366191212..a0638640f1ed 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -242,7 +242,7 @@ __visible noinstr void func(struct pt_regs *regs) \ instrumentation_begin(); \ irq_enter_rcu(); \ kvm_set_cpu_l1tf_flush_l1d(); \ - run_on_irqstack_cond(__##func, regs, regs); \ + run_sysvec_on_irqstack_cond(__##func, regs); \ irq_exit_rcu(); \ instrumentation_end(); \ irqentry_exit(regs, state); \ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 4ae66f097101..775816965c6a 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -12,20 +12,50 @@ static __always_inline bool irqstack_active(void) return __this_cpu_read(irq_count) != -1; } -void asm_call_on_stack(void *sp, void *func, void *arg); +void asm_call_on_stack(void *sp, void (*func)(void), void *arg); +void asm_call_sysvec_on_stack(void *sp, void (*func)(struct pt_regs *regs), + struct pt_regs *regs); +void asm_call_irq_on_stack(void *sp, void (*func)(struct irq_desc *desc), + struct irq_desc *desc); -static __always_inline void __run_on_irqstack(void *func, void *arg) +static __always_inline void __run_on_irqstack(void (*func)(void)) { void *tos = __this_cpu_read(hardirq_stack_ptr); __this_cpu_add(irq_count, 1); - asm_call_on_stack(tos - 8, func, arg); + asm_call_on_stack(tos - 8, func, NULL); + __this_cpu_sub(irq_count, 1); +} + +static __always_inline void +__run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) +{ + void *tos = __this_cpu_read(hardirq_stack_ptr); + + __this_cpu_add(irq_count, 1); + asm_call_sysvec_on_stack(tos - 8, func, regs); + __this_cpu_sub(irq_count, 1); +} + +static __always_inline void +__run_irq_on_irqstack(void (*func)(struct irq_desc *desc), + struct irq_desc *desc) +{ + void *tos = __this_cpu_read(hardirq_stack_ptr); + + __this_cpu_add(irq_count, 1); + asm_call_irq_on_stack(tos - 8, func, desc); __this_cpu_sub(irq_count, 1); } #else /* CONFIG_X86_64 */ static inline bool irqstack_active(void) { return false; } -static inline void __run_on_irqstack(void *func, void *arg) { } +static inline void __run_on_irqstack(void (*func)(void)) { } +static inline void __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) { } +static inline void __run_irq_on_irqstack(void (*func)(struct irq_desc *desc), + struct irq_desc *desc) { } #endif /* !CONFIG_X86_64 */ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) @@ -37,17 +67,40 @@ static __always_inline bool irq_needs_irq_stack(struct pt_regs *regs) return !user_mode(regs) && !irqstack_active(); } -static __always_inline void run_on_irqstack_cond(void *func, void *arg, + +static __always_inline void run_on_irqstack_cond(void (*func)(void), struct pt_regs *regs) { - void (*__func)(void *arg) = func; + lockdep_assert_irqs_disabled(); + + if (irq_needs_irq_stack(regs)) + __run_on_irqstack(func); + else + func(); +} + +static __always_inline void +run_sysvec_on_irqstack_cond(void (*func)(struct pt_regs *regs), + struct pt_regs *regs) +{ + lockdep_assert_irqs_disabled(); + if (irq_needs_irq_stack(regs)) + __run_sysvec_on_irqstack(func, regs); + else + func(regs); +} + +static __always_inline void +run_irq_on_irqstack_cond(void (*func)(struct irq_desc *desc), struct irq_desc *desc, + struct pt_regs *regs) +{ lockdep_assert_irqs_disabled(); if (irq_needs_irq_stack(regs)) - __run_on_irqstack(__func, arg); + __run_irq_on_irqstack(func, desc); else - __func(arg); + func(desc); } #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5ab3af7275d8..5303dbc5c9bc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1596,7 +1596,8 @@ asmlinkage void kvm_spurious_fault(void); _ASM_EXTABLE(666b, 667b) #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 0a301ad0b02f..9257667d13c5 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -59,5 +59,6 @@ typedef struct { } void leave_mm(int cpu); +#define leave_mm leave_mm #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 40aa69d04862..d8324a236696 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -327,8 +327,8 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), - offsetof(struct pt_regs, cx), offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c3daf0aaa0ee..cdaab30880b9 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -239,7 +239,7 @@ void __init arch_init_ideal_nops(void) return; } - /* fall through */ + fallthrough; default: #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 21325a4a78b9..21f9c7f11779 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -800,7 +800,7 @@ static int irq_polarity(int idx) return IOAPIC_POL_HIGH; case MP_IRQPOL_RESERVED: pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n"); - /* fall through */ + fallthrough; case MP_IRQPOL_ACTIVE_LOW: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_POL_LOW; @@ -848,7 +848,7 @@ static int irq_trigger(int idx) return IOAPIC_EDGE; case MP_IRQTRIG_RESERVED: pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n"); - /* fall through */ + fallthrough; case MP_IRQTRIG_LEVEL: default: /* Pointless default required due to do gcc stupidity */ return IOAPIC_LEVEL; @@ -2243,6 +2243,7 @@ static inline void __init check_timer(void) legacy_pic->init(0); legacy_pic->make_irq(0); apic_write(APIC_LVT0, APIC_DM_EXTINT); + legacy_pic->unmask(0); unlock_ExtINT_logic(); diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7bda71def557..99ee61c9ba54 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -149,7 +149,7 @@ void __init default_setup_apic_routing(void) break; } /* P4 and above */ - /* fall through */ + fallthrough; case X86_VENDOR_HYGON: case X86_VENDOR_AMD: def_to_bigsmp = 1; diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index dae32d948bf2..f8a56b5dc29f 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -161,6 +161,7 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec, apicd->move_in_progress = true; apicd->prev_vector = apicd->vector; apicd->prev_cpu = apicd->cpu; + WARN_ON_ONCE(apicd->cpu == newcpu); } else { irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector, managed); @@ -910,7 +911,7 @@ void send_cleanup_vector(struct irq_cfg *cfg) __send_cleanup_vector(apicd); } -static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) +void irq_complete_move(struct irq_cfg *cfg) { struct apic_chip_data *apicd; @@ -918,15 +919,16 @@ static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector) if (likely(!apicd->move_in_progress)) return; - if (vector == apicd->vector && apicd->cpu == smp_processor_id()) + /* + * If the interrupt arrived on the new target CPU, cleanup the + * vector on the old target CPU. A vector check is not required + * because an interrupt can never move from one vector to another + * on the same CPU. + */ + if (apicd->cpu == smp_processor_id()) __send_cleanup_vector(apicd); } -void irq_complete_move(struct irq_cfg *cfg) -{ - __irq_complete_move(cfg, ~get_irq_regs()->orig_ax); -} - /* * Called from fixup_irqs() with @desc->lock held and interrupts disabled. */ diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index c7503be92f35..57074cf3ad7c 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -248,7 +248,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, switch (leaf) { case 1: l1 = &l1i; - /* fall through */ + fallthrough; case 0: if (!l1->val) return; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 7843ab3fde09..3a44346f2276 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -199,7 +199,7 @@ static int raise_local(void) * calling irq_enter, but the necessary * machinery isn't exported currently. */ - /*FALL THROUGH*/ + fallthrough; case MCJ_CTX_PROCESS: raise_exception(m, NULL); break; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index d8f9230d2034..abe9fe0fb851 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -193,7 +193,7 @@ unsigned long cmci_intel_adjust_timer(unsigned long interval) if (!atomic_sub_return(1, &cmci_storm_on_cpus)) pr_notice("CMCI storm subsided: switching to interrupt mode\n"); - /* FALLTHROUGH */ + fallthrough; case CMCI_STORM_SUBSIDED: /* diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index 72182809b333..ca670919b561 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -98,7 +98,7 @@ cyrix_get_free_region(unsigned long base, unsigned long size, int replace_reg) case 7: if (size < 0x40) break; - /* Else, fall through */ + fallthrough; case 6: case 5: case 4: diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 8cdf29ffd95f..b98ff620ba77 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -349,7 +349,7 @@ static int arch_build_bp_info(struct perf_event *bp, hw->len = X86_BREAKPOINT_LEN_X; return 0; } - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 181060247e3c..c5dd50369e2f 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -227,7 +227,7 @@ 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); + run_irq_on_irqstack_cond(desc->handle_irq, desc, regs); else __handle_irq(desc, regs); } diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 1b4fe93a86c5..440eed558558 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -74,5 +74,5 @@ int irq_init_percpu_irqstack(unsigned int cpu) void do_softirq_own_stack(void) { - run_on_irqstack_cond(__do_softirq, NULL, NULL); + run_on_irqstack_cond(__do_softirq, NULL); } diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 68acd30c6b87..c2f02f308ecf 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -450,7 +450,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code, ptr = &remcomInBuffer[1]; if (kgdb_hex2long(&ptr, &addr)) linux_regs->ip = addr; - /* fall through */ + fallthrough; case 'D': case 'k': /* clear the trace bit */ @@ -539,7 +539,7 @@ static int __kgdb_notify(struct die_args *args, unsigned long cmd) * a system call which should be ignored */ return NOTIFY_DONE; - /* fall through */ + fallthrough; default: if (user_mode(regs)) return NOTIFY_DONE; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 08320b0b2b27..9663ba31347c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -270,9 +270,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) { struct pt_regs *old_regs = set_irq_regs(regs); u32 token; - irqentry_state_t state; - state = irqentry_enter(regs); + ack_APIC_irq(); inc_irq_stat(irq_hv_callback_count); @@ -283,7 +282,6 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1); } - irqentry_exit(regs, state); set_irq_regs(old_regs); } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 411af4aa7b51..baa21090c9be 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -312,7 +312,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) case 2: if (i == 0 || i == 13) continue; /* IRQ0 & IRQ13 not connected */ - /* fall through */ + fallthrough; default: if (i == 2) continue; /* IRQ2 is never connected */ @@ -356,7 +356,7 @@ static void __init construct_ioapic_table(int mpc_default_type) default: pr_err("???\nUnknown standard configuration %d\n", mpc_default_type); - /* fall through */ + fallthrough; case 1: case 5: memcpy(bus.bustype, "ISA ", 6); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 994d8393f2f7..ba4593a913fa 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -42,6 +42,7 @@ #include <asm/spec-ctrl.h> #include <asm/io_bitmap.h> #include <asm/proto.h> +#include <asm/frame.h> #include "process.h" @@ -133,7 +134,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; - frame->bp = 0; + frame->bp = encode_frame_pointer(childregs); frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; @@ -684,9 +685,7 @@ void arch_cpu_idle(void) */ void __cpuidle default_idle(void) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); safe_halt(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE) EXPORT_SYMBOL(default_idle); @@ -792,7 +791,6 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) static __cpuidle void mwait_idle(void) { if (!current_set_polling_and_test()) { - trace_cpu_idle_rcuidle(1, smp_processor_id()); if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { mb(); /* quirk */ clflush((void *)¤t_thread_info()->flags); @@ -804,7 +802,6 @@ static __cpuidle void mwait_idle(void) __sti_mwait(0, 0); else local_irq_enable(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } else { local_irq_enable(); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 5679aa3fdcb8..e7537c5440bb 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -204,7 +204,7 @@ static int set_segment_reg(struct task_struct *task, case offsetof(struct user_regs_struct, ss): if (unlikely(value == 0)) return -EIO; - /* Else, fall through */ + fallthrough; default: *pt_regs_access(task_pt_regs(task), offset) = value; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 0ec7ced727fe..a515e2d230b7 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -654,7 +654,7 @@ static void native_machine_emergency_restart(void) case BOOT_CF9_FORCE: port_cf9_safe = true; - /* Fall through */ + fallthrough; case BOOT_CF9_SAFE: if (port_cf9_safe) { diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index d5fa494c2304..be0d7d4152ec 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -726,7 +726,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) regs->ax = -EINTR; break; } - /* fallthrough */ + fallthrough; case -ERESTARTNOINTR: regs->ax = regs->orig_ax; regs->ip -= 2; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 27aa04a95702..f5ef689dd62a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1594,14 +1594,28 @@ int native_cpu_disable(void) if (ret) return ret; - /* - * Disable the local APIC. Otherwise IPI broadcasts will reach - * it. It still responds normally to INIT, NMI, SMI, and SIPI - * messages. - */ - apic_soft_disable(); cpu_disable_common(); + /* + * Disable the local APIC. Otherwise IPI broadcasts will reach + * it. It still responds normally to INIT, NMI, SMI, and SIPI + * messages. + * + * Disabling the APIC must happen after cpu_disable_common() + * which invokes fixup_irqs(). + * + * Disabling the APIC preserves already set bits in IRR, but + * an interrupt arriving after disabling the local APIC does not + * set the corresponding IRR bit. + * + * fixup_irqs() scans IRR for set bits so it can raise a not + * yet handled interrupt on the new destination CPU via an IPI + * but obviously it can't do so for IRR bits which are not set. + * IOW, interrupts arriving after disabling the local APIC will + * be lost. + */ + apic_soft_disable(); + return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1f66d2d1e998..81a2fb711091 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -729,20 +729,9 @@ static bool is_sysenter_singlestep(struct pt_regs *regs) #endif } -static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) +static __always_inline unsigned long debug_read_clear_dr6(void) { - /* - * 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(); + unsigned long dr6; /* * The Intel SDM says: @@ -755,15 +744,12 @@ static __always_inline void debug_enter(unsigned long *dr6, unsigned long *dr7) * * Keep it simple: clear DR6 immediately. */ - get_debugreg(*dr6, 6); + get_debugreg(dr6, 6); set_debugreg(0, 6); /* Filter out all the reserved bits which are preset to 1 */ - *dr6 &= ~DR6_RESERVED; -} + dr6 &= ~DR6_RESERVED; -static __always_inline void debug_exit(unsigned long dr7) -{ - local_db_restore(dr7); + return dr6; } /* @@ -863,6 +849,18 @@ out: static __always_inline void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6) { + /* + * 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. + */ + unsigned long dr7 = local_db_save(); bool irq_state = idtentry_enter_nmi(regs); instrumentation_begin(); @@ -883,6 +881,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, instrumentation_end(); idtentry_exit_nmi(regs, irq_state); + + local_db_restore(dr7); } static __always_inline void exc_debug_user(struct pt_regs *regs, @@ -894,6 +894,15 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, */ WARN_ON_ONCE(!user_mode(regs)); + /* + * NB: We can't easily clear DR7 here because + * idtentry_exit_to_usermode() can invoke ptrace, schedule, access + * user memory, etc. This means that a recursive #DB is possible. If + * this happens, that #DB will hit exc_debug_kernel() and clear DR7. + * Since we're not on the IST stack right now, everything will be + * fine. + */ + irqentry_enter_from_user_mode(regs); instrumentation_begin(); @@ -907,36 +916,24 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, /* IST stack entry */ DEFINE_IDTENTRY_DEBUG(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); - exc_debug_kernel(regs, dr6); - debug_exit(dr7); + exc_debug_kernel(regs, debug_read_clear_dr6()); } /* 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); + exc_debug_user(regs, debug_read_clear_dr6()); } #else /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) { - unsigned long dr6, dr7; - - debug_enter(&dr6, &dr7); + unsigned long dr6 = debug_read_clear_dr6(); if (user_mode(regs)) exc_debug_user(regs, dr6); else exc_debug_kernel(regs, dr6); - - debug_exit(dr7); } #endif diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 15e5aad8ac2c..3fdaa042823d 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -735,7 +735,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) * OPCODE1() of the "short" jmp which checks the same condition. */ opc1 = OPCODE2(insn) - 0x10; - /* fall through */ + fallthrough; default: if (!is_cond_jmp_opcode(opc1)) return -ENOSYS; @@ -892,7 +892,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, fix_ip_or_call = 0; break; } - /* fall through */ + fallthrough; default: riprel_analyze(auprobe, &insn); } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index d0e2825ae617..2f6510de6b0c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2505,9 +2505,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); val = GET_SMSTATE(u32, smstate, 0x7fcc); - ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1)) + return X86EMUL_UNHANDLEABLE; + val = GET_SMSTATE(u32, smstate, 0x7fc8); - ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1)) + return X86EMUL_UNHANDLEABLE; selector = GET_SMSTATE(u32, smstate, 0x7fc4); set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64)); @@ -2560,16 +2565,23 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; val = GET_SMSTATE(u32, smstate, 0x7f68); - ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1)) + return X86EMUL_UNHANDLEABLE; + val = GET_SMSTATE(u32, smstate, 0x7f60); - ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); + + if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1)) + return X86EMUL_UNHANDLEABLE; cr0 = GET_SMSTATE(u64, smstate, 0x7f58); cr3 = GET_SMSTATE(u64, smstate, 0x7f50); cr4 = GET_SMSTATE(u64, smstate, 0x7f48); ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00)); val = GET_SMSTATE(u64, smstate, 0x7ed0); - ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); + + if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA)) + return X86EMUL_UNHANDLEABLE; selector = GET_SMSTATE(u32, smstate, 0x7e90); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8); @@ -3016,7 +3028,7 @@ static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) case 0xa4: /* movsb */ case 0xa5: /* movsd/w */ *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; - /* fall through */ + fallthrough; case 0xaa: /* stosb */ case 0xab: /* stosd/w */ *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 814d3aee5cef..1d330564eed8 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1779,7 +1779,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = kvm_hvcall_signal_event(vcpu, fast, ingpa); if (ret != HV_STATUS_INVALID_PORT_ID) break; - /* fall through - maybe userspace knows this conn_id. */ + fallthrough; /* maybe userspace knows this conn_id */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) { diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index c47d2acec529..4aa1c2e00e2a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -285,7 +285,7 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->u.irqchip.irqchip) { case KVM_IRQCHIP_PIC_SLAVE: e->irqchip.pin += PIC_NUM_PINS / 2; - /* fall through */ + fallthrough; case KVM_IRQCHIP_PIC_MASTER: if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2) return -EINVAL; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 5ccbee7165a2..35cca2e0c802 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1053,7 +1053,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, switch (delivery_mode) { case APIC_DM_LOWEST: vcpu->arch.apic_arb_prio++; - /* fall through */ + fallthrough; case APIC_DM_FIXED: if (unlikely(trig_mode && !level)) break; @@ -1341,7 +1341,7 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset) break; case APIC_TASKPRI: report_tpr_access(apic, false); - /* fall thru */ + fallthrough; default: val = kvm_lapic_get_reg(apic, offset); break; @@ -2027,7 +2027,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVT0: apic_manage_nmi_watchdog(apic, val); - /* fall through */ + fallthrough; case APIC_LVTTHMR: case APIC_LVTPC: case APIC_LVT1: diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4e03841f053d..71aa3da2a0b7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1916,7 +1916,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } @@ -2468,7 +2469,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, } if (sp->unsync_children) - kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); + kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); __clear_sp_write_flooding_count(sp); @@ -4421,7 +4422,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; - /* fall through */ + fallthrough; case PT64_ROOT_4LEVEL: rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | nonleaf_bit8_rsvd | rsvd_bits(7, 7) | diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index fb68467e6049..e90bc436f584 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -586,7 +586,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; /* Give the current vmcb to the guest */ - svm_set_gif(svm, false); nested_vmcb->save.es = vmcb->save.es; nested_vmcb->save.cs = vmcb->save.cs; @@ -632,6 +631,9 @@ int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(&vmcb->control, &hsave->control); + /* On vmexit the GIF is set to false */ + svm_set_gif(svm, false); + svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset = svm->vcpu.arch.l1_tsc_offset; @@ -1132,6 +1134,9 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, load_nested_vmcb_control(svm, &ctl); nested_prepare_vmcb_control(svm); + if (!nested_svm_vmrun_msrpm(svm)) + return -EINVAL; + out_set_gif: svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET)); return 0; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 402dc4234e39..7bf7bf734979 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1106,6 +1106,7 @@ void sev_vm_destroy(struct kvm *kvm) list_for_each_safe(pos, q, head) { __unregister_enc_region_locked(kvm, list_entry(pos, struct enc_region, list)); + cond_resched(); } } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 03dd7bac8034..91ea74ae71b8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -2668,7 +2674,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_IA32_APICBASE: if (kvm_vcpu_apicv_active(vcpu)) avic_update_vapic_bar(to_svm(vcpu), data); - /* Fall through */ + fallthrough; default: return kvm_set_msr_common(vcpu, msr); } @@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, @@ -2938,8 +2944,6 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (npt_enabled) vcpu->arch.cr3 = svm->vmcb->save.cr3; - svm_complete_interrupts(svm); - if (is_guest_mode(vcpu)) { int vmexit; @@ -3504,7 +3508,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) stgi(); /* Any pending NMI will happen here */ - exit_fastpath = svm_exit_handlers_fastpath(vcpu); if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) kvm_after_interrupt(&svm->vcpu); @@ -3518,6 +3521,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) } svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; + vmcb_mark_all_clean(svm->vmcb); /* if exit due to PF check for async PF */ if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) @@ -3537,7 +3541,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) SVM_EXIT_EXCP_BASE + MC_VECTOR)) svm_handle_mce(svm); - vmcb_mark_all_clean(svm->vmcb); + svm_complete_interrupts(svm); + exit_fastpath = svm_exit_handlers_fastpath(vcpu); return exit_fastpath; } @@ -3900,21 +3905,28 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate) static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) { struct vcpu_svm *svm = to_svm(vcpu); - struct vmcb *nested_vmcb; struct kvm_host_map map; - u64 guest; - u64 vmcb; int ret = 0; - guest = GET_SMSTATE(u64, smstate, 0x7ed8); - vmcb = GET_SMSTATE(u64, smstate, 0x7ee0); + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); + u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8); + u64 vmcb = GET_SMSTATE(u64, smstate, 0x7ee0); - if (guest) { - if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL) - return 1; - nested_vmcb = map.hva; - ret = enter_svm_guest_mode(svm, vmcb, nested_vmcb); - kvm_vcpu_unmap(&svm->vcpu, &map, true); + if (guest) { + if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + return 1; + + if (!(saved_efer & EFER_SVME)) + return 1; + + if (kvm_vcpu_map(&svm->vcpu, + gpa_to_gfn(vmcb), &map) == -EINVAL) + return 1; + + ret = enter_svm_guest_mode(svm, vmcb, map.hva); + kvm_vcpu_unmap(&svm->vcpu, &map, true); + } } return ret; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 23b58c28a1c9..1bb6b31eb646 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4404,6 +4404,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); + /* + * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between + * now and the new vmentry. Ensure that the VMCS02 PDPTR fields are + * up-to-date before switching to L1. + */ + if (enable_ept && is_pae_paging(vcpu)) + vmx_ept_load_pdptrs(vcpu); + leave_guest_mode(vcpu); if (nested_cpu_has_preemption_timer(vmcs12)) @@ -4668,7 +4676,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu) vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; vmx->nested.msrs.exit_ctls_high &= - ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; } } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 46ba2e03a892..96979c09ebd1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1; module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #endif +extern bool __read_mostly allow_smaller_maxphyaddr; +module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); + #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ @@ -791,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; + else { + /* + * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched + * between guest and host. In that case we only care about present + * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in + * prepare_vmcs02_rare. + */ + bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR)); + int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0; + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask); + } vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -2971,7 +2986,7 @@ static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu) vpid_sync_context(to_vmx(vcpu)->vpid); } -static void ept_load_pdptrs(struct kvm_vcpu *vcpu) +void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.walk_mmu; @@ -3114,7 +3129,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd, guest_cr3 = vcpu->arch.cr3; else /* vmcs01.GUEST_CR3 is already up-to-date. */ update_guest_cr3 = false; - ept_load_pdptrs(vcpu); + vmx_ept_load_pdptrs(vcpu); } else { guest_cr3 = pgd; } @@ -4352,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } - - /* - * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched - * between guest and host. In that case we only care about present - * faults. - */ - if (enable_ept) { - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK); - } } static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -4654,7 +4659,7 @@ static bool rmode_exception(struct kvm_vcpu *vcpu, int vec) vmcs_read32(VM_EXIT_INSTRUCTION_LEN); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) return false; - /* fall through */ + fallthrough; case DB_VECTOR: return !(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)); @@ -4803,6 +4808,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * EPT will cause page fault only if we need to * detect illegal GPAs. */ + WARN_ON_ONCE(!allow_smaller_maxphyaddr); kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); return 1; } else @@ -4827,7 +4833,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) } kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); - /* fall through */ + fallthrough; case BP_VECTOR: /* * Update instruction length as we may reinject #BP from @@ -5257,7 +5263,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) error_code = vmcs_read32(IDT_VECTORING_ERROR_CODE); } - /* fall through */ + fallthrough; case INTR_TYPE_SOFT_EXCEPTION: kvm_clear_exception_queue(vcpu); break; @@ -5331,7 +5337,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -5610,7 +5616,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) * keeping track of global entries in shadow page tables. */ - /* fall-through */ + fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: kvm_mmu_unload(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -6054,6 +6060,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION && exit_reason != EXIT_REASON_PML_FULL && + exit_reason != EXIT_REASON_APIC_ACCESS && exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; @@ -6578,7 +6585,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, break; case INTR_TYPE_SOFT_EXCEPTION: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ + fallthrough; case INTR_TYPE_HARD_EXCEPTION: if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { u32 err = vmcs_read32(error_code_field); @@ -6588,7 +6595,7 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, break; case INTR_TYPE_SOFT_INTR: vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field); - /* fall through */ + fallthrough; case INTR_TYPE_EXT_INTR: kvm_queue_interrupt(vcpu, vector, type == INTR_TYPE_SOFT_INTR); break; @@ -8304,11 +8311,12 @@ static int __init vmx_init(void) vmx_check_vmcs12_offsets(); /* - * Intel processors don't have problems with - * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable - * it for VMX by default + * Shadow paging doesn't have a (further) performance penalty + * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it + * by default */ - allow_smaller_maxphyaddr = true; + if (!enable_ept) + allow_smaller_maxphyaddr = true; return 0; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 26175a4759fa..a0e47720f60c 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -356,6 +356,7 @@ void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); int vmx_find_msr_index(struct vmx_msrs *m, u32 msr); int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); +void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu); #define POSTED_INTR_ON 0 #define POSTED_INTR_SN 1 @@ -551,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) { - return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + if (!enable_ept) + return true; + + return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; } void dump_vmcs(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 599d73206299..ce856e0ece84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs; u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); -bool __read_mostly allow_smaller_maxphyaddr; +bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); static u64 __read_mostly host_xss; @@ -975,7 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops.set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -1116,14 +1117,12 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) vcpu->arch.eff_db[dr] = val; break; case 4: - /* fall through */ case 6: if (!kvm_dr6_valid(val)) return -1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: - /* fall through */ default: /* 7 */ if (!kvm_dr7_valid(val)) return -1; /* #GP */ @@ -1154,12 +1153,10 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) *val = vcpu->arch.db[array_index_nospec(dr, size)]; break; case 4: - /* fall through */ case 6: *val = vcpu->arch.dr6; break; case 5: - /* fall through */ default: /* 7 */ *val = vcpu->arch.dr7; break; @@ -2735,7 +2732,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) return 1; if (!lapic_in_kernel(vcpu)) - return 1; + return data ? 1 : 0; vcpu->arch.apf.msr_en_val = data; @@ -3051,7 +3048,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; /* fall through */ + pr = true; + fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) @@ -3224,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_POWER_CTL: msr_info->data = vcpu->arch.msr_ia32_power_ctl; break; - case MSR_IA32_TSC: - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + case MSR_IA32_TSC: { + /* + * Intel SDM states that MSR_IA32_TSC read adds the TSC offset + * even when not intercepted. AMD manual doesn't explicitly + * state this but appears to behave the same. + * + * On userspace reads and writes, however, we unconditionally + * operate L1's TSC value to ensure backwards-compatible + * behavior for migration. + */ + u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : + vcpu->arch.tsc_offset; + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; break; + } case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); @@ -3581,6 +3592,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; + case KVM_CAP_STEAL_TIME: + r = sched_info_on(); + break; default: break; } @@ -4359,7 +4373,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; - /* fall through */ + fallthrough; case KVM_CAP_HYPERV_SYNIC: if (!irqchip_in_kernel(vcpu->kvm)) @@ -8672,7 +8686,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; - /* fall through */ + fallthrough; case KVM_MP_STATE_RUNNABLE: vcpu->arch.apf.halted = false; break; @@ -10751,9 +10765,11 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct x86_exception fault; + u32 access = error_code & + (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, error_code, &fault) != UNMAPPED_GVA) { + vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index d46fff11f06f..aa067859a70b 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_cmdline.o = -pg endif -CFLAGS_cmdline.o := -fno-stack-protector +CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables endif inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c index 4f1719e22d3c..b6da09339308 100644 --- a/arch/x86/lib/cmdline.c +++ b/arch/x86/lib/cmdline.c @@ -58,7 +58,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, state = st_wordcmp; opptr = option; wstart = pos; - /* fall through */ + fallthrough; case st_wordcmp: if (!*opptr) { @@ -89,7 +89,7 @@ __cmdline_find_option_bool(const char *cmdline, int max_cmdline_size, break; } state = st_wordskip; - /* fall through */ + fallthrough; case st_wordskip: if (!c) @@ -151,7 +151,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, state = st_wordcmp; opptr = option; - /* fall through */ + fallthrough; case st_wordcmp: if ((c == '=') && !*opptr) { @@ -172,7 +172,7 @@ __cmdline_find_option(const char *cmdline, int max_cmdline_size, break; } state = st_wordskip; - /* fall through */ + fallthrough; case st_wordskip: if (myisspace(c)) diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 31600d851fd8..5e69603ff63f 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -179,7 +179,7 @@ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) if (insn->addr_bytes == 2) return -EINVAL; - /* fall through */ + fallthrough; case -EDOM: case offsetof(struct pt_regs, bx): @@ -362,7 +362,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) case INAT_SEG_REG_GS: return vm86regs->gs; case INAT_SEG_REG_IGNORE: - /* fall through */ default: return -EINVAL; } @@ -386,7 +385,6 @@ static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx) */ return get_user_gs(regs); case INAT_SEG_REG_IGNORE: - /* fall through */ default: return -EINVAL; } @@ -786,7 +784,7 @@ int insn_get_code_seg_params(struct pt_regs *regs) */ return INSN_CODE_SEG_PARAMS(4, 8); case 3: /* Invalid setting. CS.L=1, CS.D=1 */ - /* fall through */ + fallthrough; default: return -EINVAL; } diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b0dfac3d3df7..1847e993ac63 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c index 73dc66d887f3..ec071cbb0804 100644 --- a/arch/x86/math-emu/errors.c +++ b/arch/x86/math-emu/errors.c @@ -186,7 +186,7 @@ void FPU_printall(void) case TAG_Special: /* Update tagi for the printk below */ tagi = FPU_Special(r); - /* fall through */ + fallthrough; case TAG_Valid: printk("st(%d) %c .%04lx %04lx %04lx %04lx e%+-6d ", i, getsign(r) ? '-' : '+', diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c index 127ea54122d7..4a9887851ad8 100644 --- a/arch/x86/math-emu/fpu_trig.c +++ b/arch/x86/math-emu/fpu_trig.c @@ -1352,7 +1352,7 @@ static void fyl2xp1(FPU_REG *st0_ptr, u_char st0_tag) case TW_Denormal: if (denormal_operand() < 0) return; - /* fall through */ + fallthrough; case TAG_Zero: case TAG_Valid: setsign(st0_ptr, getsign(st0_ptr) ^ getsign(st1_ptr)); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 35f1498e9832..6e3e8a124903 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -190,6 +190,53 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) return pmd_k; } +/* + * Handle a fault on the vmalloc or module mapping area + * + * This is needed because there is a race condition between the time + * when the vmalloc mapping code updates the PMD to the point in time + * where it synchronizes this update with the other page-tables in the + * system. + * + * In this race window another thread/CPU can map an area on the same + * PMD, finds it already present and does not synchronize it with the + * rest of the system yet. As a result v[mz]alloc might return areas + * which are not mapped in every page-table in the system, causing an + * unhandled page-fault when they are accessed. + */ +static noinline int vmalloc_fault(unsigned long address) +{ + unsigned long pgd_paddr; + pmd_t *pmd_k; + pte_t *pte_k; + + /* Make sure we are in vmalloc area: */ + if (!(address >= VMALLOC_START && address < VMALLOC_END)) + return -1; + + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "current" here. We might be inside + * an interrupt in the middle of a task switch.. + */ + pgd_paddr = read_cr3_pa(); + pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); + if (!pmd_k) + return -1; + + if (pmd_large(*pmd_k)) + return 0; + + pte_k = pte_offset_kernel(pmd_k, address); + if (!pte_present(*pte_k)) + return -1; + + return 0; +} +NOKPROBE_SYMBOL(vmalloc_fault); + void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; @@ -1110,6 +1157,37 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); +#ifdef CONFIG_X86_32 + /* + * We can fault-in kernel-space virtual memory on-demand. The + * 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + * + * Before doing this on-demand faulting, ensure that the + * fault is not any of the following: + * 1. A fault on a PTE with a reserved bit set. + * 2. A fault caused by a user-mode access. (Do not demand- + * fault kernel memory due to user-mode accesses). + * 3. A fault caused by a page-level protection violation. + * (A demand fault would be on a non-present page which + * would have X86_PF_PROT==0). + * + * This is only needed to close a race condition on x86-32 in + * the vmalloc mapping/unmapping code. See the comment above + * vmalloc_fault() for details. On x86-64 the race does not + * exist as the vmalloc mappings don't need to be synchronized + * there. + */ + if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { + if (vmalloc_fault(address) >= 0) + return; + } +#endif + /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 84d85dbd1dad..9e5ccc56f8e0 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -574,7 +574,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, /* For SEV, these areas are encrypted */ if (sev_active()) break; - /* Fallthrough */ + fallthrough; case E820_TYPE_PRAM: return true; diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index c5174b4e318b..683cd12f4793 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -321,7 +321,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, u64 addr, u64 max_addr, u64 size) { return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size, - 0, NULL, NUMA_NO_NODE); + 0, NULL, 0); } static int __init setup_emu2phys_nid(int *dfl_phys_nid) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 1a3569b43aa5..0951b47e64c1 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -555,21 +555,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); load_new_mm_cr3(next->pgd, new_asid, true); - /* - * NB: This gets called via leave_mm() in the idle path - * where RCU functions differently. Tracing normally - * uses RCU, so we need to use the _rcuidle variant. - * - * (There is no good reason for this. The idle code should - * be rearranged to call this before rcu_idle_enter().) - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ load_new_mm_cr3(next->pgd, new_asid, false); - /* See above wrt _rcuidle. */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); + trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0); } /* Make sure we write CR3 before loaded_mm. */ diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9f9aad42ccff..89395a5049bb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -26,6 +26,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f6ea8f1a9d57..d37ebe6e70d7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -49,7 +49,6 @@ #include <asm/efi.h> #include <asm/e820/api.h> #include <asm/time.h> -#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/uv/uv.h> @@ -496,74 +495,6 @@ void __init efi_init(void) efi_print_memmap(); } -#if defined(CONFIG_X86_32) - -void __init efi_set_executable(efi_memory_desc_t *md, bool executable) -{ - u64 addr, npages; - - addr = md->virt_addr; - npages = md->num_pages; - - memrange_efi_to_native(&addr, &npages); - - if (executable) - set_memory_x(addr, npages); - else - set_memory_nx(addr, npages); -} - -void __init runtime_code_page_mkexec(void) -{ - efi_memory_desc_t *md; - - /* Make EFI runtime service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_RUNTIME_SERVICES_CODE) - continue; - - efi_set_executable(md, true); - } -} - -void __init efi_memory_uc(u64 addr, unsigned long size) -{ - unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; - u64 npages; - - npages = round_up(size, page_shift) / page_shift; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); -} - -void __init old_map_region(efi_memory_desc_t *md) -{ - u64 start_pfn, end_pfn, end; - unsigned long size; - void *va; - - start_pfn = PFN_DOWN(md->phys_addr); - size = md->num_pages << PAGE_SHIFT; - end = md->phys_addr + size; - end_pfn = PFN_UP(end); - - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); - - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); - - md->virt_addr = (u64) (unsigned long) va; - if (!va) - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); -} - -#endif - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 826ead67753d..e06a199423c0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -29,9 +29,35 @@ #include <asm/io.h> #include <asm/desc.h> #include <asm/page.h> +#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/efi.h> +void __init efi_map_region(efi_memory_desc_t *md) +{ + u64 start_pfn, end_pfn, end; + unsigned long size; + void *va; + + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); + + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); + + if (!(md->attribute & EFI_MEMORY_WB)) + set_memory_uc((unsigned long)va, md->num_pages); + } else { + va = ioremap_cache(md->phys_addr, size); + } + + md->virt_addr = (unsigned long)va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", md->phys_addr); +} + /* * To make EFI call EFI runtime service in physical addressing mode we need * prolog/epilog before/after the invocation to claim the EFI runtime service @@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; } -void __init efi_map_region(efi_memory_desc_t *md) -{ - old_map_region(md); -} - void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} @@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, void __init efi_runtime_update_mappings(void) { - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (__supported_pte_mask & _PAGE_NX) { + efi_memory_desc_t *md; + + /* Make EFI runtime service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages); + } + } } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 413583f904a6..6af4da1149ba 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; rodata = __pa(__start_rodata); pfn = rodata >> PAGE_SHIFT; + + pf = _PAGE_NX | _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { pr_err("Failed to map kernel rodata 1:1\n"); return 1; |