diff options
Diffstat (limited to 'arch/x86')
220 files changed, 4897 insertions, 3867 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cd18994a9555..94a18681353d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,7 +22,7 @@ config X86_64 def_bool y depends on 64BIT # Options that are inherently 64-bit kernel only: - select ARCH_HAS_GIGANTIC_PAGE + select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA select ARCH_SUPPORTS_INT128 select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_SOFT_DIRTY @@ -54,11 +54,13 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MMIO_FLUSH select ARCH_HAS_PMEM_API if X86_64 + select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_SET_MEMORY select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_ZONE_DEVICE if X86_64 select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI select ARCH_MIGHT_HAVE_PC_PARPORT @@ -69,9 +71,10 @@ config X86 select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS - select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if SMP + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH select ARCH_WANT_FRAME_POINTERS select ARCH_WANTS_DYNAMIC_TASK_STRUCT + select ARCH_WANTS_THP_SWAP if X86_64 select BUILDTIME_EXTABLE_SORT select CLKEVT_I8253 select CLOCKSOURCE_VALIDATE_LAST_CYCLE @@ -87,6 +90,8 @@ config X86 select GENERIC_EARLY_IOREMAP select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP + select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP + select GENERIC_IRQ_MIGRATION if SMP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_PENDING_IRQ if SMP @@ -166,6 +171,7 @@ config X86 select HAVE_UNSTABLE_SCHED_CLOCK select HAVE_USER_RETURN_NOTIFIER select IRQ_FORCED_THREADING + select PCI_LOCKLESS_CONFIG select PERF_EVENTS select RTC_LIB select RTC_MC146818_LIB @@ -360,7 +366,7 @@ config SMP Management" code will be disabled if you say Y here. See also <file:Documentation/x86/i386/IO-APIC.txt>, - <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at + <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO available at <http://www.tldp.org/docs.html#howto>. If you don't know what to do here, say N. @@ -1082,7 +1088,7 @@ config X86_MCE_THRESHOLD def_bool y config X86_MCE_INJECT - depends on X86_MCE && X86_LOCAL_APIC && X86_MCELOG_LEGACY + depends on X86_MCE && X86_LOCAL_APIC && DEBUG_FS tristate "Machine check injector support" ---help--- Provide support for injecting machine checks for testing purposes. @@ -2776,10 +2782,6 @@ config COMPAT_FOR_U64_ALIGNMENT config SYSVIPC_COMPAT def_bool y depends on SYSVIPC - -config KEYS_COMPAT - def_bool y - depends on KEYS endif endmenu @@ -2797,6 +2799,9 @@ config X86_DMA_REMAP bool depends on STA2X11 +config HAVE_GENERIC_GUP + def_bool y + source "net/Kconfig" source "drivers/Kconfig" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5851411e60fb..1e902f926be3 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -11,6 +11,14 @@ else KBUILD_DEFCONFIG := $(ARCH)_defconfig endif +# For gcc stack alignment is specified with -mpreferred-stack-boundary, +# clang has the option -mstack-alignment for that purpose. +ifneq ($(call cc-option, -mpreferred-stack-boundary=4),) + cc_stack_align_opt := -mpreferred-stack-boundary +else ifneq ($(call cc-option, -mstack-alignment=4),) + cc_stack_align_opt := -mstack-alignment +endif + # How to compile the 16-bit code. Note we always compile for -march=i386; # that way we can complain to the user if the CPU is insufficient. # @@ -24,10 +32,11 @@ REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -D__KERNEL__ \ -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ - -mno-mmx -mno-sse \ - $(call cc-option, -ffreestanding) \ - $(call cc-option, -fno-stack-protector) \ - $(call cc-option, -mpreferred-stack-boundary=2) + -mno-mmx -mno-sse + +REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding) +REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector) +REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align_opt)=2) export REALMODE_CFLAGS # BITS is used as extension for files which are available in a 32 bit @@ -64,8 +73,10 @@ ifeq ($(CONFIG_X86_32),y) # with nonstandard options KBUILD_CFLAGS += -fno-pic - # prevent gcc from keeping the stack 16 byte aligned - KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2) + # Align the stack to the register width instead of using the default + # alignment of 16 bytes. This reduces stack usage and the number of + # alignment instructions. + KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align_opt)=2) # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use # a lot more stack due to the lack of sharing of stacklots: @@ -97,8 +108,14 @@ else KBUILD_CFLAGS += $(call cc-option,-mno-80387) KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387) - # Use -mpreferred-stack-boundary=3 if supported. - KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) + # By default gcc and clang use a stack alignment of 16 bytes for x86. + # However the standard kernel entry on x86-64 leaves the stack on an + # 8-byte boundary. If the compiler isn't informed about the actual + # alignment it will generate extra alignment instructions for the + # default alignment which keep the stack *mis*aligned. + # Furthermore an alignment to the register width reduces stack usage + # and the number of alignment instructions. + KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align_opt)=3) # Use -mskip-rax-setup if supported. KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup) @@ -159,7 +176,7 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER # If '-Os' is enabled, disable it and print a warning. ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE undefine CONFIG_CC_OPTIMIZE_FOR_SIZE - $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.) + $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.) endif endif @@ -257,8 +274,6 @@ drivers-$(CONFIG_PM) += arch/x86/power/ drivers-$(CONFIG_FB) += arch/x86/video/ -drivers-$(CONFIG_RAS) += arch/x86/ras/ - #### # boot loader support. Several targets are kept for legacy purposes diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index a45eb15b7cf2..f3717d36718a 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -9,7 +9,6 @@ else tune = $(call cc-option,-mcpu=$(1),$(2)) endif -align := $(cc-option-align) cflags-$(CONFIG_M486) += -march=i486 cflags-$(CONFIG_M586) += -march=i586 cflags-$(CONFIG_M586TSC) += -march=i586 @@ -24,11 +23,11 @@ cflags-$(CONFIG_MK6) += -march=k6 # They make zero difference whatsosever to performance at this time. cflags-$(CONFIG_MK7) += -march=athlon cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,-march=athlon) -cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 -cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 +cflags-$(CONFIG_MCRUSOE) += -march=i686 -falign-functions=0 -falign-jumps=0 -falign-loops=0 +cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call tune,pentium3) -falign-functions=0 -falign-jumps=0 -falign-loops=0 cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586) -cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 +cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) -falign-functions=0 -falign-jumps=0 -falign-loops=0 cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) cflags-$(CONFIG_MVIAC7) += -march=i686 cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 44163e8c3868..2c860ad4fe06 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -94,7 +94,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o quiet_cmd_check_data_rel = DATAREL $@ define cmd_check_data_rel for obj in $(filter %.o,$^); do \ - readelf -S $$obj | grep -qF .rel.local && { \ + ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \ echo "error: $$obj has data relocations!" >&2; \ exit 1; \ } || true; \ diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index 73ccf63b0f48..9dc1ce6ba3c0 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -13,7 +13,7 @@ static inline char rdfs8(addr_t addr) return *((char *)(fs + addr)); } #include "../cmdline.c" -static unsigned long get_cmd_line_ptr(void) +unsigned long get_cmd_line_ptr(void) { unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index cbf4b87f55b9..c3e869eaef0c 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1046,9 +1046,31 @@ struct boot_params *efi_main(struct efi_config *c, memset((char *)gdt->address, 0x0, gdt->size); desc = (struct desc_struct *)gdt->address; - /* The first GDT is a dummy and the second is unused. */ - desc += 2; + /* The first GDT is a dummy. */ + desc++; + + if (IS_ENABLED(CONFIG_X86_64)) { + /* __KERNEL32_CS */ + desc->limit0 = 0xffff; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ; + desc->s = DESC_TYPE_CODE_DATA; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0xf; + desc->avl = 0; + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; + } else { + /* Second entry is unused on 32-bit */ + desc++; + } + /* __KERNEL_CS */ desc->limit0 = 0xffff; desc->base0 = 0x0000; desc->base1 = 0x0000; @@ -1058,12 +1080,18 @@ struct boot_params *efi_main(struct efi_config *c, desc->p = 1; desc->limit = 0xf; desc->avl = 0; - desc->l = 0; - desc->d = SEG_OP_SIZE_32BIT; + if (IS_ENABLED(CONFIG_X86_64)) { + desc->l = 1; + desc->d = 0; + } else { + desc->l = 0; + desc->d = SEG_OP_SIZE_32BIT; + } desc->g = SEG_GRANULARITY_4KB; desc->base2 = 0x00; - desc++; + + /* __KERNEL_DS */ desc->limit0 = 0xffff; desc->base0 = 0x0000; desc->base1 = 0x0000; @@ -1077,24 +1105,25 @@ struct boot_params *efi_main(struct efi_config *c, desc->d = SEG_OP_SIZE_32BIT; desc->g = SEG_GRANULARITY_4KB; desc->base2 = 0x00; - -#ifdef CONFIG_X86_64 - /* Task segment value */ desc++; - desc->limit0 = 0x0000; - desc->base0 = 0x0000; - desc->base1 = 0x0000; - desc->type = SEG_TYPE_TSS; - desc->s = 0; - desc->dpl = 0; - desc->p = 1; - desc->limit = 0x0; - desc->avl = 0; - desc->l = 0; - desc->d = 0; - desc->g = SEG_GRANULARITY_4KB; - desc->base2 = 0x00; -#endif /* CONFIG_X86_64 */ + + if (IS_ENABLED(CONFIG_X86_64)) { + /* Task segment value */ + desc->limit0 = 0x0000; + desc->base0 = 0x0000; + desc->base1 = 0x0000; + desc->type = SEG_TYPE_TSS; + desc->s = 0; + desc->dpl = 0; + desc->p = 1; + desc->limit = 0x0; + desc->avl = 0; + desc->l = 0; + desc->d = 0; + desc->g = SEG_GRANULARITY_4KB; + desc->base2 = 0x00; + desc++; + } asm volatile("cli"); asm volatile ("lgdt %0" : : "m" (*gdt)); diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d2ae1f821e0c..fbf4c32d0b62 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -346,6 +346,48 @@ preferred_addr: /* Set up the stack */ leaq boot_stack_end(%rbx), %rsp +#ifdef CONFIG_X86_5LEVEL + /* Check if 5-level paging has already enabled */ + movq %cr4, %rax + testl $X86_CR4_LA57, %eax + jnz lvl5 + + /* + * At this point we are in long mode with 4-level paging enabled, + * but we want to enable 5-level paging. + * + * The problem is that we cannot do it directly. Setting LA57 in + * long mode would trigger #GP. So we need to switch off long mode + * first. + * + * NOTE: This is not going to work if bootloader put us above 4G + * limit. + * + * The first step is go into compatibility mode. + */ + + /* Clear additional page table */ + leaq lvl5_pgtable(%rbx), %rdi + xorq %rax, %rax + movq $(PAGE_SIZE/8), %rcx + rep stosq + + /* + * Setup current CR3 as the first and only entry in a new top level + * page table. + */ + movq %cr3, %rdi + leaq 0x7 (%rdi), %rax + movq %rax, lvl5_pgtable(%rbx) + + /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */ + pushq $__KERNEL32_CS + leaq compatible_mode(%rip), %rax + pushq %rax + lretq +lvl5: +#endif + /* Zero EFLAGS */ pushq $0 popfq @@ -429,6 +471,44 @@ relocated: jmp *%rax .code32 +#ifdef CONFIG_X86_5LEVEL +compatible_mode: + /* Setup data and stack segments */ + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %ss + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Point CR3 to 5-level paging */ + leal lvl5_pgtable(%ebx), %eax + movl %eax, %cr3 + + /* Enable PAE and LA57 mode */ + movl %cr4, %eax + orl $(X86_CR4_PAE | X86_CR4_LA57), %eax + movl %eax, %cr4 + + /* Calculate address we are running at */ + call 1f +1: popl %edi + subl $1b, %edi + + /* Prepare stack for far return to Long Mode */ + pushl $__KERNEL_CS + leal lvl5(%edi), %eax + push %eax + + /* Enable paging back */ + movl $(X86_CR0_PG | X86_CR0_PE), %eax + movl %eax, %cr0 + + lret +#endif + no_longmode: /* This isn't an x86-64 CPU so hang */ 1: @@ -442,7 +522,7 @@ gdt: .word gdt_end - gdt .long gdt .word 0 - .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00cf9a000000ffff /* __KERNEL32_CS */ .quad 0x00af9a000000ffff /* __KERNEL_CS */ .quad 0x00cf92000000ffff /* __KERNEL_DS */ .quad 0x0080890000000000 /* TS descriptor */ @@ -486,3 +566,7 @@ boot_stack_end: .balign 4096 pgtable: .fill BOOT_PGT_SIZE, 1, 0 +#ifdef CONFIG_X86_5LEVEL +lvl5_pgtable: + .fill PAGE_SIZE, 1, 0 +#endif diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 54c24f0a43d3..91f27ab970ef 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -9,16 +9,42 @@ * contain the entire properly aligned running kernel image. * */ + +/* + * isspace() in linux/ctype.h is expected by next_args() to filter + * out "space/lf/tab". While boot/ctype.h conflicts with linux/ctype.h, + * since isdigit() is implemented in both of them. Hence disable it + * here. + */ +#define BOOT_CTYPE_H + +/* + * _ctype[] in lib/ctype.c is needed by isspace() of linux/ctype.h. + * While both lib/ctype.c and lib/cmdline.c will bring EXPORT_SYMBOL + * which is meaningless and will cause compiling error in some cases. + * So do not include linux/export.h and define EXPORT_SYMBOL(sym) + * as empty. + */ +#define _LINUX_EXPORT_H +#define EXPORT_SYMBOL(sym) + #include "misc.h" #include "error.h" -#include "../boot.h" +#include "../string.h" #include <generated/compile.h> #include <linux/module.h> #include <linux/uts.h> #include <linux/utsname.h> +#include <linux/ctype.h> #include <generated/utsrelease.h> +/* Macros used by the included decompressor code below. */ +#define STATIC +#include <linux/decompress/mm.h> + +extern unsigned long get_cmd_line_ptr(void); + /* Simplified build-specific string for starting entropy. */ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; @@ -62,6 +88,11 @@ struct mem_vector { static bool memmap_too_large; + +/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */ +unsigned long long mem_limit = ULLONG_MAX; + + enum mem_avoid_index { MEM_AVOID_ZO_RANGE = 0, MEM_AVOID_INITRD, @@ -85,49 +116,14 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two) return true; } -/** - * _memparse - Parse a string with mem suffixes into a number - * @ptr: Where parse begins - * @retptr: (output) Optional pointer to next char after parse completes - * - * Parses a string into a number. The number stored at @ptr is - * potentially suffixed with K, M, G, T, P, E. - */ -static unsigned long long _memparse(const char *ptr, char **retptr) +char *skip_spaces(const char *str) { - char *endptr; /* Local pointer to end of parsed string */ - - unsigned long long ret = simple_strtoull(ptr, &endptr, 0); - - switch (*endptr) { - case 'E': - case 'e': - ret <<= 10; - case 'P': - case 'p': - ret <<= 10; - case 'T': - case 't': - ret <<= 10; - case 'G': - case 'g': - ret <<= 10; - case 'M': - case 'm': - ret <<= 10; - case 'K': - case 'k': - ret <<= 10; - endptr++; - default: - break; - } - - if (retptr) - *retptr = endptr; - - return ret; + while (isspace(*str)) + ++str; + return (char *)str; } +#include "../../../../lib/ctype.c" +#include "../../../../lib/cmdline.c" static int parse_memmap(char *p, unsigned long long *start, unsigned long long *size) @@ -142,40 +138,41 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size) return -EINVAL; oldp = p; - *size = _memparse(p, &p); + *size = memparse(p, &p); if (p == oldp) return -EINVAL; switch (*p) { - case '@': - /* Skip this region, usable */ - *start = 0; - *size = 0; - return 0; case '#': case '$': case '!': - *start = _memparse(p + 1, &p); + *start = memparse(p + 1, &p); + return 0; + case '@': + /* memmap=nn@ss specifies usable region, should be skipped */ + *size = 0; + /* Fall through */ + default: + /* + * If w/o offset, only size specified, memmap=nn[KMG] has the + * same behaviour as mem=nn[KMG]. It limits the max address + * system can use. Region above the limit should be avoided. + */ + *start = 0; return 0; } return -EINVAL; } -static void mem_avoid_memmap(void) +static void mem_avoid_memmap(char *str) { - char arg[128]; + static int i; int rc; - int i; - char *str; - /* See if we have any memmap areas */ - rc = cmdline_find_option("memmap", arg, sizeof(arg)); - if (rc <= 0) + if (i >= MAX_MEMMAP_REGIONS) return; - i = 0; - str = arg; while (str && (i < MAX_MEMMAP_REGIONS)) { int rc; unsigned long long start, size; @@ -188,9 +185,14 @@ static void mem_avoid_memmap(void) if (rc < 0) break; str = k; - /* A usable region that should not be skipped */ - if (size == 0) + + if (start == 0) { + /* Store the specified memory limit if size > 0 */ + if (size > 0) + mem_limit = size; + continue; + } mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start; mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size; @@ -202,6 +204,57 @@ static void mem_avoid_memmap(void) memmap_too_large = true; } +static int handle_mem_memmap(void) +{ + char *args = (char *)get_cmd_line_ptr(); + size_t len = strlen((char *)args); + char *tmp_cmdline; + char *param, *val; + u64 mem_size; + + if (!strstr(args, "memmap=") && !strstr(args, "mem=")) + return 0; + + tmp_cmdline = malloc(len + 1); + if (!tmp_cmdline ) + error("Failed to allocate space for tmp_cmdline"); + + memcpy(tmp_cmdline, args, len); + tmp_cmdline[len] = 0; + args = tmp_cmdline; + + /* Chew leading spaces */ + args = skip_spaces(args); + + while (*args) { + args = next_arg(args, ¶m, &val); + /* Stop at -- */ + if (!val && strcmp(param, "--") == 0) { + warn("Only '--' specified in cmdline"); + free(tmp_cmdline); + return -1; + } + + if (!strcmp(param, "memmap")) { + mem_avoid_memmap(val); + } else if (!strcmp(param, "mem")) { + char *p = val; + + if (!strcmp(p, "nopentium")) + continue; + mem_size = memparse(p, &p); + if (mem_size == 0) { + free(tmp_cmdline); + return -EINVAL; + } + mem_limit = mem_size; + } + } + + free(tmp_cmdline); + return 0; +} + /* * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T). * The mem_avoid array is used to store the ranges that need to be avoided @@ -323,7 +376,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* We don't need to set a mapping for setup_data. */ /* Mark the memmap regions we need to avoid */ - mem_avoid_memmap(); + handle_mem_memmap(); #ifdef CONFIG_X86_VERBOSE_BOOTUP /* Make sure video RAM can be used. */ @@ -432,7 +485,8 @@ static void process_e820_entry(struct boot_e820_entry *entry, { struct mem_vector region, overlap; struct slot_area slot_area; - unsigned long start_orig; + unsigned long start_orig, end; + struct boot_e820_entry cur_entry; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) @@ -446,8 +500,15 @@ static void process_e820_entry(struct boot_e820_entry *entry, if (entry->addr + entry->size < minimum) return; - region.start = entry->addr; - region.size = entry->size; + /* Ignore entries above memory limit */ + end = min(entry->size + entry->addr, mem_limit); + if (entry->addr >= end) + return; + cur_entry.addr = entry->addr; + cur_entry.size = end - entry->addr; + + region.start = cur_entry.addr; + region.size = cur_entry.size; /* Give up if slot area array is full. */ while (slot_area_index < MAX_SLOT_AREA) { @@ -461,7 +522,7 @@ static void process_e820_entry(struct boot_e820_entry *entry, region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN); /* Did we raise the address above this e820 region? */ - if (region.start > entry->addr + entry->size) + if (region.start > cur_entry.addr + cur_entry.size) return; /* Reduce size by any delta from the original address. */ @@ -564,9 +625,6 @@ void choose_random_location(unsigned long input, { unsigned long random_addr, min_addr; - /* By default, keep output position unchanged. */ - *virt_addr = *output; - if (cmdline_find_option_bool("nokaslr")) { warn("KASLR disabled: 'nokaslr' on cmdline."); return; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index b3c5a5f030ce..00241c815524 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -338,7 +338,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, unsigned long output_len) { const unsigned long kernel_total_size = VO__end - VO__text; - unsigned long virt_addr = (unsigned long)output; + unsigned long virt_addr = LOAD_PHYSICAL_ADDR; /* Retain x86 boot parameters pointer passed from startup_32/64. */ boot_params = rmode; @@ -390,6 +390,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifdef CONFIG_X86_64 if (heap > 0x3fffffffffffUL) error("Destination address too large"); + if (virt_addr + max(output_len, kernel_total_size) > KERNEL_IMAGE_SIZE) + error("Destination virtual address is beyond the kernel mapping area"); #else if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff)) error("Destination address too large"); @@ -397,7 +399,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, #ifndef CONFIG_RELOCATABLE if ((unsigned long)output != LOAD_PHYSICAL_ADDR) error("Destination address does not match LOAD_PHYSICAL_ADDR"); - if ((unsigned long)output != virt_addr) + if (virt_addr != LOAD_PHYSICAL_ADDR) error("Destination virtual address changed when not relocatable"); #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 1c8355eadbd1..766a5211f827 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -81,8 +81,6 @@ static inline void choose_random_location(unsigned long input, unsigned long output_size, unsigned long *virt_addr) { - /* No change from existing output location. */ - *virt_addr = *output; } #endif diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index 1d78f1739087..28029be47fbb 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -63,7 +63,7 @@ static void *alloc_pgt_page(void *context) static struct alloc_pgt_data pgt_data; /* The top level page table entry pointer. */ -static unsigned long level4p; +static unsigned long top_level_pgt; /* * Mapping information structure passed to kernel_ident_mapping_init(). @@ -91,9 +91,15 @@ void initialize_identity_maps(void) * If we came here via startup_32(), cr3 will be _pgtable already * and we must append to the existing area instead of entirely * overwriting it. + * + * With 5-level paging, we use '_pgtable' to allocate the p4d page table, + * the top-level page table is allocated separately. + * + * p4d_offset(top_level_pgt, 0) would cover both the 4- and 5-level + * cases. On 4-level paging it's equal to 'top_level_pgt'. */ - level4p = read_cr3(); - if (level4p == (unsigned long)_pgtable) { + top_level_pgt = read_cr3_pa(); + if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { debug_putstr("booted via startup_32()\n"); pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; @@ -103,7 +109,7 @@ void initialize_identity_maps(void) pgt_data.pgt_buf = _pgtable; pgt_data.pgt_buf_size = BOOT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); - level4p = (unsigned long)alloc_pgt_page(&pgt_data); + top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); } } @@ -123,7 +129,7 @@ void add_identity_map(unsigned long start, unsigned long size) return; /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)level4p, + kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end); } @@ -134,5 +140,5 @@ void add_identity_map(unsigned long start, unsigned long size) */ void finalize_identity_maps(void) { - write_cr3(level4p); + write_cr3(top_level_pgt); } diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S index 1eb7d298b47d..15d9f74b0008 100644 --- a/arch/x86/boot/copy.S +++ b/arch/x86/boot/copy.S @@ -65,23 +65,3 @@ GLOBAL(copy_to_fs) popw %es retl ENDPROC(copy_to_fs) - -#if 0 /* Not currently used, but can be enabled as needed */ -GLOBAL(copy_from_gs) - pushw %ds - pushw %gs - popw %ds - calll memcpy - popw %ds - retl -ENDPROC(copy_from_gs) - -GLOBAL(copy_to_gs) - pushw %es - pushw %gs - popw %es - calll memcpy - popw %es - retl -ENDPROC(copy_to_gs) -#endif diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 5457b02fc050..630e3664906b 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -122,6 +122,14 @@ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int bas return result; } +long simple_strtol(const char *cp, char **endp, unsigned int base) +{ + if (*cp == '-') + return -simple_strtoull(cp + 1, endp, base); + + return simple_strtoull(cp, endp, base); +} + /** * strlen - Find the length of a string * @s: The string to be sized diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 113588ddb43f..f274a50db5fa 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -22,6 +22,7 @@ extern int strcmp(const char *str1, const char *str2); extern int strncmp(const char *cs, const char *ct, size_t count); extern size_t strlen(const char *s); extern char *strstr(const char *s1, const char *s2); +extern char *strchr(const char *s, int c); extern size_t strnlen(const char *s, size_t maxlen); extern unsigned int atou(const char *s); extern unsigned long long simple_strtoull(const char *cp, char **endp, diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 34b3fa2889d1..9e32d40d71bd 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +OBJECT_FILES_NON_STANDARD := y + avx_supported := $(call as-instr,vpxor %xmm0$(comma)%xmm0$(comma)%xmm0,yes,no) avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S index 910565547163..8739cf7795de 100644 --- a/arch/x86/crypto/aes-x86_64-asm_64.S +++ b/arch/x86/crypto/aes-x86_64-asm_64.S @@ -42,17 +42,15 @@ #define R5E %esi #define R6 %rdi #define R6E %edi -#define R7 %rbp -#define R7E %ebp +#define R7 %r9 /* don't use %rbp; it breaks stack traces */ +#define R7E %r9d #define R8 %r8 -#define R9 %r9 #define R10 %r10 #define R11 %r11 -#define prologue(FUNC,KEY,B128,B192,r1,r2,r3,r4,r5,r6,r7,r8,r9,r10,r11) \ +#define prologue(FUNC,KEY,B128,B192,r1,r2,r5,r6,r7,r8,r9,r10,r11) \ ENTRY(FUNC); \ movq r1,r2; \ - movq r3,r4; \ leaq KEY+48(r8),r9; \ movq r10,r11; \ movl (r7),r5 ## E; \ @@ -70,9 +68,8 @@ je B192; \ leaq 32(r9),r9; -#define epilogue(FUNC,r1,r2,r3,r4,r5,r6,r7,r8,r9) \ +#define epilogue(FUNC,r1,r2,r5,r6,r7,r8,r9) \ movq r1,r2; \ - movq r3,r4; \ movl r5 ## E,(r9); \ movl r6 ## E,4(r9); \ movl r7 ## E,8(r9); \ @@ -88,12 +85,12 @@ movl TAB(,r6,4),r6 ## E; \ roll $16,r2 ## E; \ shrl $16,r4 ## E; \ - movzbl r4 ## H,r7 ## E; \ - movzbl r4 ## L,r4 ## E; \ + movzbl r4 ## L,r7 ## E; \ + movzbl r4 ## H,r4 ## E; \ xorl OFFSET(r8),ra ## E; \ xorl OFFSET+4(r8),rb ## E; \ - xorl TAB+3072(,r7,4),r5 ## E;\ - xorl TAB+2048(,r4,4),r6 ## E;\ + xorl TAB+3072(,r4,4),r5 ## E;\ + xorl TAB+2048(,r7,4),r6 ## E;\ movzbl r1 ## L,r7 ## E; \ movzbl r1 ## H,r4 ## E; \ movl TAB+1024(,r4,4),r4 ## E;\ @@ -101,19 +98,19 @@ roll $16,r1 ## E; \ shrl $16,r3 ## E; \ xorl TAB(,r7,4),r5 ## E; \ - movzbl r3 ## H,r7 ## E; \ - movzbl r3 ## L,r3 ## E; \ - xorl TAB+3072(,r7,4),r4 ## E;\ - xorl TAB+2048(,r3,4),r5 ## E;\ - movzbl r1 ## H,r7 ## E; \ - movzbl r1 ## L,r3 ## E; \ + movzbl r3 ## L,r7 ## E; \ + movzbl r3 ## H,r3 ## E; \ + xorl TAB+3072(,r3,4),r4 ## E;\ + xorl TAB+2048(,r7,4),r5 ## E;\ + movzbl r1 ## L,r7 ## E; \ + movzbl r1 ## H,r3 ## E; \ shrl $16,r1 ## E; \ - xorl TAB+3072(,r7,4),r6 ## E;\ - movl TAB+2048(,r3,4),r3 ## E;\ - movzbl r1 ## H,r7 ## E; \ - movzbl r1 ## L,r1 ## E; \ - xorl TAB+1024(,r7,4),r6 ## E;\ - xorl TAB(,r1,4),r3 ## E; \ + xorl TAB+3072(,r3,4),r6 ## E;\ + movl TAB+2048(,r7,4),r3 ## E;\ + movzbl r1 ## L,r7 ## E; \ + movzbl r1 ## H,r1 ## E; \ + xorl TAB+1024(,r1,4),r6 ## E;\ + xorl TAB(,r7,4),r3 ## E; \ movzbl r2 ## H,r1 ## E; \ movzbl r2 ## L,r7 ## E; \ shrl $16,r2 ## E; \ @@ -131,9 +128,9 @@ movl r4 ## E,r2 ## E; #define entry(FUNC,KEY,B128,B192) \ - prologue(FUNC,KEY,B128,B192,R2,R8,R7,R9,R1,R3,R4,R6,R10,R5,R11) + prologue(FUNC,KEY,B128,B192,R2,R8,R1,R3,R4,R6,R10,R5,R11) -#define return(FUNC) epilogue(FUNC,R8,R2,R9,R7,R5,R6,R3,R4,R11) +#define return(FUNC) epilogue(FUNC,R8,R2,R5,R6,R3,R4,R11) #define encrypt_round(TAB,OFFSET) \ round(TAB,OFFSET,R1,R2,R3,R4,R5,R6,R7,R10,R5,R6,R3,R4) \ diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 3c465184ff8a..16627fec80b2 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -89,6 +89,29 @@ SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 ALL_F: .octa 0xffffffffffffffffffffffffffffffff .octa 0x00000000000000000000000000000000 +.section .rodata +.align 16 +.type aad_shift_arr, @object +.size aad_shift_arr, 272 +aad_shift_arr: + .octa 0xffffffffffffffffffffffffffffffff + .octa 0xffffffffffffffffffffffffffffff0C + .octa 0xffffffffffffffffffffffffffff0D0C + .octa 0xffffffffffffffffffffffffff0E0D0C + .octa 0xffffffffffffffffffffffff0F0E0D0C + .octa 0xffffffffffffffffffffff0C0B0A0908 + .octa 0xffffffffffffffffffff0D0C0B0A0908 + .octa 0xffffffffffffffffff0E0D0C0B0A0908 + .octa 0xffffffffffffffff0F0E0D0C0B0A0908 + .octa 0xffffffffffffff0C0B0A090807060504 + .octa 0xffffffffffff0D0C0B0A090807060504 + .octa 0xffffffffff0E0D0C0B0A090807060504 + .octa 0xffffffff0F0E0D0C0B0A090807060504 + .octa 0xffffff0C0B0A09080706050403020100 + .octa 0xffff0D0C0B0A09080706050403020100 + .octa 0xff0E0D0C0B0A09080706050403020100 + .octa 0x0F0E0D0C0B0A09080706050403020100 + .text @@ -252,32 +275,66 @@ XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation mov arg8, %r12 # %r12 = aadLen mov %r12, %r11 pxor %xmm\i, %xmm\i + pxor \XMM2, \XMM2 -_get_AAD_loop\num_initial_blocks\operation: - movd (%r10), \TMP1 - pslldq $12, \TMP1 - psrldq $4, %xmm\i + cmp $16, %r11 + jl _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_blocks\num_initial_blocks\operation: + movdqu (%r10), %xmm\i + PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor %xmm\i, \XMM2 + GHASH_MUL \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\num_initial_blocks\operation + + movdqu \XMM2, %xmm\i + cmp $0, %r11 + je _get_AAD_done\num_initial_blocks\operation + + pxor %xmm\i,%xmm\i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some CT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\num_initial_blocks\operation: + cmp $4, %r11 + jle _get_AAD_rest4\num_initial_blocks\operation + movq (%r10), \TMP1 + add $8, %r10 + sub $8, %r11 + pslldq $8, \TMP1 + psrldq $8, %xmm\i pxor \TMP1, %xmm\i + jmp _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_rest4\num_initial_blocks\operation: + cmp $0, %r11 + jle _get_AAD_rest0\num_initial_blocks\operation + mov (%r10), %eax + movq %rax, \TMP1 add $4, %r10 - sub $4, %r12 - jne _get_AAD_loop\num_initial_blocks\operation - - cmp $16, %r11 - je _get_AAD_loop2_done\num_initial_blocks\operation - - mov $16, %r12 -_get_AAD_loop2\num_initial_blocks\operation: + sub $4, %r10 + pslldq $12, \TMP1 psrldq $4, %xmm\i - sub $4, %r12 - cmp %r11, %r12 - jne _get_AAD_loop2\num_initial_blocks\operation - -_get_AAD_loop2_done\num_initial_blocks\operation: + pxor \TMP1, %xmm\i +_get_AAD_rest0\num_initial_blocks\operation: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \TMP1 + PSHUFB_XMM \TMP1, %xmm\i +_get_AAD_rest_final\num_initial_blocks\operation: PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor \XMM2, %xmm\i + GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 +_get_AAD_done\num_initial_blocks\operation: xor %r11, %r11 # initialise the data pointer offset as zero - - # start AES for num_initial_blocks blocks + # start AES for num_initial_blocks blocks mov %arg5, %rax # %rax = *Y0 movdqu (%rax), \XMM0 # XMM0 = Y0 @@ -322,7 +379,7 @@ aes_loop_initial_dec\num_initial_blocks: # prepare plaintext/ciphertext for GHASH computation .endr .endif - GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + # apply GHASH on num_initial_blocks blocks .if \i == 5 @@ -477,28 +534,66 @@ XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation mov arg8, %r12 # %r12 = aadLen mov %r12, %r11 pxor %xmm\i, %xmm\i -_get_AAD_loop\num_initial_blocks\operation: - movd (%r10), \TMP1 - pslldq $12, \TMP1 - psrldq $4, %xmm\i + pxor \XMM2, \XMM2 + + cmp $16, %r11 + jl _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_blocks\num_initial_blocks\operation: + movdqu (%r10), %xmm\i + PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor %xmm\i, \XMM2 + GHASH_MUL \XMM2, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\num_initial_blocks\operation + + movdqu \XMM2, %xmm\i + cmp $0, %r11 + je _get_AAD_done\num_initial_blocks\operation + + pxor %xmm\i,%xmm\i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some PT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\num_initial_blocks\operation: + cmp $4, %r11 + jle _get_AAD_rest4\num_initial_blocks\operation + movq (%r10), \TMP1 + add $8, %r10 + sub $8, %r11 + pslldq $8, \TMP1 + psrldq $8, %xmm\i pxor \TMP1, %xmm\i + jmp _get_AAD_rest8\num_initial_blocks\operation +_get_AAD_rest4\num_initial_blocks\operation: + cmp $0, %r11 + jle _get_AAD_rest0\num_initial_blocks\operation + mov (%r10), %eax + movq %rax, \TMP1 add $4, %r10 - sub $4, %r12 - jne _get_AAD_loop\num_initial_blocks\operation - cmp $16, %r11 - je _get_AAD_loop2_done\num_initial_blocks\operation - mov $16, %r12 -_get_AAD_loop2\num_initial_blocks\operation: + sub $4, %r10 + pslldq $12, \TMP1 psrldq $4, %xmm\i - sub $4, %r12 - cmp %r11, %r12 - jne _get_AAD_loop2\num_initial_blocks\operation -_get_AAD_loop2_done\num_initial_blocks\operation: + pxor \TMP1, %xmm\i +_get_AAD_rest0\num_initial_blocks\operation: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \TMP1 + PSHUFB_XMM \TMP1, %xmm\i +_get_AAD_rest_final\num_initial_blocks\operation: PSHUFB_XMM %xmm14, %xmm\i # byte-reflect the AAD data + pxor \XMM2, %xmm\i + GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 +_get_AAD_done\num_initial_blocks\operation: xor %r11, %r11 # initialise the data pointer offset as zero - - # start AES for num_initial_blocks blocks + # start AES for num_initial_blocks blocks mov %arg5, %rax # %rax = *Y0 movdqu (%rax), \XMM0 # XMM0 = Y0 @@ -543,7 +638,7 @@ aes_loop_initial_enc\num_initial_blocks: # prepare plaintext/ciphertext for GHASH computation .endr .endif - GHASH_MUL %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1 + # apply GHASH on num_initial_blocks blocks .if \i == 5 @@ -1454,18 +1549,35 @@ _return_T_decrypt: mov arg10, %r11 # %r11 = auth_tag_len cmp $16, %r11 je _T_16_decrypt - cmp $12, %r11 - je _T_12_decrypt + cmp $8, %r11 + jl _T_4_decrypt _T_8_decrypt: MOVQ_R64_XMM %xmm0, %rax mov %rax, (%r10) - jmp _return_T_done_decrypt -_T_12_decrypt: - MOVQ_R64_XMM %xmm0, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 psrldq $8, %xmm0 + cmp $0, %r11 + je _return_T_done_decrypt +_T_4_decrypt: + movd %xmm0, %eax + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + psrldq $4, %xmm0 + cmp $0, %r11 + je _return_T_done_decrypt +_T_123_decrypt: movd %xmm0, %eax - mov %eax, 8(%r10) + cmp $2, %r11 + jl _T_1_decrypt + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done_decrypt + add $2, %r10 + sar $16, %eax +_T_1_decrypt: + mov %al, (%r10) jmp _return_T_done_decrypt _T_16_decrypt: movdqu %xmm0, (%r10) @@ -1718,18 +1830,35 @@ _return_T_encrypt: mov arg10, %r11 # %r11 = auth_tag_len cmp $16, %r11 je _T_16_encrypt - cmp $12, %r11 - je _T_12_encrypt + cmp $8, %r11 + jl _T_4_encrypt _T_8_encrypt: MOVQ_R64_XMM %xmm0, %rax mov %rax, (%r10) - jmp _return_T_done_encrypt -_T_12_encrypt: - MOVQ_R64_XMM %xmm0, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 psrldq $8, %xmm0 + cmp $0, %r11 + je _return_T_done_encrypt +_T_4_encrypt: + movd %xmm0, %eax + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + psrldq $4, %xmm0 + cmp $0, %r11 + je _return_T_done_encrypt +_T_123_encrypt: movd %xmm0, %eax - mov %eax, 8(%r10) + cmp $2, %r11 + jl _T_1_encrypt + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done_encrypt + add $2, %r10 + sar $16, %eax +_T_1_encrypt: + mov %al, (%r10) jmp _return_T_done_encrypt _T_16_encrypt: movdqu %xmm0, (%r10) diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index d664382c6e56..faecb1518bf8 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -155,6 +155,30 @@ SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100 ALL_F: .octa 0xffffffffffffffffffffffffffffffff .octa 0x00000000000000000000000000000000 +.section .rodata +.align 16 +.type aad_shift_arr, @object +.size aad_shift_arr, 272 +aad_shift_arr: + .octa 0xffffffffffffffffffffffffffffffff + .octa 0xffffffffffffffffffffffffffffff0C + .octa 0xffffffffffffffffffffffffffff0D0C + .octa 0xffffffffffffffffffffffffff0E0D0C + .octa 0xffffffffffffffffffffffff0F0E0D0C + .octa 0xffffffffffffffffffffff0C0B0A0908 + .octa 0xffffffffffffffffffff0D0C0B0A0908 + .octa 0xffffffffffffffffff0E0D0C0B0A0908 + .octa 0xffffffffffffffff0F0E0D0C0B0A0908 + .octa 0xffffffffffffff0C0B0A090807060504 + .octa 0xffffffffffff0D0C0B0A090807060504 + .octa 0xffffffffff0E0D0C0B0A090807060504 + .octa 0xffffffff0F0E0D0C0B0A090807060504 + .octa 0xffffff0C0B0A09080706050403020100 + .octa 0xffff0D0C0B0A09080706050403020100 + .octa 0xff0E0D0C0B0A09080706050403020100 + .octa 0x0F0E0D0C0B0A09080706050403020100 + + .text @@ -372,41 +396,72 @@ VARIABLE_OFFSET = 16*8 .macro INITIAL_BLOCKS_AVX num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC i = (8-\num_initial_blocks) + j = 0 setreg - mov arg6, %r10 # r10 = AAD - mov arg7, %r12 # r12 = aadLen - - - mov %r12, %r11 - - vpxor reg_i, reg_i, reg_i -_get_AAD_loop\@: - vmovd (%r10), \T1 - vpslldq $12, \T1, \T1 - vpsrldq $4, reg_i, reg_i - vpxor \T1, reg_i, reg_i - - add $4, %r10 - sub $4, %r12 - jg _get_AAD_loop\@ - - - cmp $16, %r11 - je _get_AAD_loop2_done\@ - mov $16, %r12 - -_get_AAD_loop2\@: - vpsrldq $4, reg_i, reg_i - sub $4, %r12 - cmp %r11, %r12 - jg _get_AAD_loop2\@ - -_get_AAD_loop2_done\@: - - #byte-reflect the AAD data - vpshufb SHUF_MASK(%rip), reg_i, reg_i - + mov arg6, %r10 # r10 = AAD + mov arg7, %r12 # r12 = aadLen + + + mov %r12, %r11 + + vpxor reg_j, reg_j, reg_j + vpxor reg_i, reg_i, reg_i + cmp $16, %r11 + jl _get_AAD_rest8\@ +_get_AAD_blocks\@: + vmovdqu (%r10), reg_i + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_i, reg_j, reg_j + GHASH_MUL_AVX reg_j, \T2, \T1, \T3, \T4, \T5, \T6 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\@ + vmovdqu reg_j, reg_i + cmp $0, %r11 + je _get_AAD_done\@ + + vpxor reg_i, reg_i, reg_i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some CT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\@: + cmp $4, %r11 + jle _get_AAD_rest4\@ + movq (%r10), \T1 + add $8, %r10 + sub $8, %r11 + vpslldq $8, \T1, \T1 + vpsrldq $8, reg_i, reg_i + vpxor \T1, reg_i, reg_i + jmp _get_AAD_rest8\@ +_get_AAD_rest4\@: + cmp $0, %r11 + jle _get_AAD_rest0\@ + mov (%r10), %eax + movq %rax, \T1 + add $4, %r10 + sub $4, %r11 + vpslldq $12, \T1, \T1 + vpsrldq $4, reg_i, reg_i + vpxor \T1, reg_i, reg_i +_get_AAD_rest0\@: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \T1 + vpshufb \T1, reg_i, reg_i +_get_AAD_rest_final\@: + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_j, reg_i, reg_i + GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6 + +_get_AAD_done\@: # initialize the data pointer offset as zero xor %r11, %r11 @@ -480,7 +535,6 @@ _get_AAD_loop2_done\@: i = (8-\num_initial_blocks) j = (9-\num_initial_blocks) setreg - GHASH_MUL_AVX reg_i, \T2, \T1, \T3, \T4, \T5, \T6 .rep \num_initial_blocks vpxor reg_i, reg_j, reg_j @@ -1427,19 +1481,36 @@ _return_T\@: cmp $16, %r11 je _T_16\@ - cmp $12, %r11 - je _T_12\@ + cmp $8, %r11 + jl _T_4\@ _T_8\@: vmovq %xmm9, %rax mov %rax, (%r10) - jmp _return_T_done\@ -_T_12\@: - vmovq %xmm9, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 vpsrldq $8, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_4\@: vmovd %xmm9, %eax - mov %eax, 8(%r10) + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + vpsrldq $4, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_123\@: + vmovd %xmm9, %eax + cmp $2, %r11 + jl _T_1\@ + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done\@ + add $2, %r10 + sar $16, %eax +_T_1\@: + mov %al, (%r10) jmp _return_T_done\@ _T_16\@: @@ -1631,41 +1702,73 @@ ENDPROC(aesni_gcm_dec_avx_gen2) .macro INITIAL_BLOCKS_AVX2 num_initial_blocks T1 T2 T3 T4 T5 CTR XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 T6 T_key ENC_DEC VER i = (8-\num_initial_blocks) + j = 0 setreg - mov arg6, %r10 # r10 = AAD - mov arg7, %r12 # r12 = aadLen - - - mov %r12, %r11 - - vpxor reg_i, reg_i, reg_i -_get_AAD_loop\@: - vmovd (%r10), \T1 - vpslldq $12, \T1, \T1 - vpsrldq $4, reg_i, reg_i - vpxor \T1, reg_i, reg_i - - add $4, %r10 - sub $4, %r12 - jg _get_AAD_loop\@ - - - cmp $16, %r11 - je _get_AAD_loop2_done\@ - mov $16, %r12 - -_get_AAD_loop2\@: - vpsrldq $4, reg_i, reg_i - sub $4, %r12 - cmp %r11, %r12 - jg _get_AAD_loop2\@ - -_get_AAD_loop2_done\@: - - #byte-reflect the AAD data - vpshufb SHUF_MASK(%rip), reg_i, reg_i - + mov arg6, %r10 # r10 = AAD + mov arg7, %r12 # r12 = aadLen + + + mov %r12, %r11 + + vpxor reg_j, reg_j, reg_j + vpxor reg_i, reg_i, reg_i + + cmp $16, %r11 + jl _get_AAD_rest8\@ +_get_AAD_blocks\@: + vmovdqu (%r10), reg_i + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_i, reg_j, reg_j + GHASH_MUL_AVX2 reg_j, \T2, \T1, \T3, \T4, \T5, \T6 + add $16, %r10 + sub $16, %r12 + sub $16, %r11 + cmp $16, %r11 + jge _get_AAD_blocks\@ + vmovdqu reg_j, reg_i + cmp $0, %r11 + je _get_AAD_done\@ + + vpxor reg_i, reg_i, reg_i + + /* read the last <16B of AAD. since we have at least 4B of + data right after the AAD (the ICV, and maybe some CT), we can + read 4B/8B blocks safely, and then get rid of the extra stuff */ +_get_AAD_rest8\@: + cmp $4, %r11 + jle _get_AAD_rest4\@ + movq (%r10), \T1 + add $8, %r10 + sub $8, %r11 + vpslldq $8, \T1, \T1 + vpsrldq $8, reg_i, reg_i + vpxor \T1, reg_i, reg_i + jmp _get_AAD_rest8\@ +_get_AAD_rest4\@: + cmp $0, %r11 + jle _get_AAD_rest0\@ + mov (%r10), %eax + movq %rax, \T1 + add $4, %r10 + sub $4, %r11 + vpslldq $12, \T1, \T1 + vpsrldq $4, reg_i, reg_i + vpxor \T1, reg_i, reg_i +_get_AAD_rest0\@: + /* finalize: shift out the extra bytes we read, and align + left. since pslldq can only shift by an immediate, we use + vpshufb and an array of shuffle masks */ + movq %r12, %r11 + salq $4, %r11 + movdqu aad_shift_arr(%r11), \T1 + vpshufb \T1, reg_i, reg_i +_get_AAD_rest_final\@: + vpshufb SHUF_MASK(%rip), reg_i, reg_i + vpxor reg_j, reg_i, reg_i + GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6 + +_get_AAD_done\@: # initialize the data pointer offset as zero xor %r11, %r11 @@ -1740,7 +1843,6 @@ _get_AAD_loop2_done\@: i = (8-\num_initial_blocks) j = (9-\num_initial_blocks) setreg - GHASH_MUL_AVX2 reg_i, \T2, \T1, \T3, \T4, \T5, \T6 .rep \num_initial_blocks vpxor reg_i, reg_j, reg_j @@ -2702,19 +2804,36 @@ _return_T\@: cmp $16, %r11 je _T_16\@ - cmp $12, %r11 - je _T_12\@ + cmp $8, %r11 + jl _T_4\@ _T_8\@: vmovq %xmm9, %rax mov %rax, (%r10) - jmp _return_T_done\@ -_T_12\@: - vmovq %xmm9, %rax - mov %rax, (%r10) + add $8, %r10 + sub $8, %r11 vpsrldq $8, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_4\@: vmovd %xmm9, %eax - mov %eax, 8(%r10) + mov %eax, (%r10) + add $4, %r10 + sub $4, %r11 + vpsrldq $4, %xmm9, %xmm9 + cmp $0, %r11 + je _return_T_done\@ +_T_123\@: + vmovd %xmm9, %eax + cmp $2, %r11 + jl _T_1\@ + mov %ax, (%r10) + cmp $2, %r11 + je _return_T_done\@ + add $2, %r10 + sar $16, %eax +_T_1\@: + mov %al, (%r10) jmp _return_T_done\@ _T_16\@: diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 93de8ea51548..4a55cdcdc008 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -61,6 +61,11 @@ struct aesni_rfc4106_gcm_ctx { u8 nonce[4]; }; +struct generic_gcmaes_ctx { + u8 hash_subkey[16] AESNI_ALIGN_ATTR; + struct crypto_aes_ctx aes_key_expanded AESNI_ALIGN_ATTR; +}; + struct aesni_xts_ctx { u8 raw_tweak_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR; u8 raw_crypt_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR; @@ -102,13 +107,11 @@ asmlinkage void aesni_xts_crypt8(struct crypto_aes_ctx *ctx, u8 *out, * u8 *out, Ciphertext output. Encrypt in-place is allowed. * const u8 *in, Plaintext input * unsigned long plaintext_len, Length of data in bytes for encryption. - * u8 *iv, Pre-counter block j0: 4 byte salt (from Security Association) - * concatenated with 8 byte Initialisation Vector (from IPSec ESP - * Payload) concatenated with 0x00000001. 16-byte aligned pointer. + * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001. + * 16-byte aligned pointer. * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary. * const u8 *aad, Additional Authentication Data (AAD) - * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this - * is going to be 8 or 12 bytes + * unsigned long aad_len, Length of AAD in bytes. * u8 *auth_tag, Authenticated Tag output. * unsigned long auth_tag_len), Authenticated Tag Length in bytes. * Valid values are 16 (most likely), 12 or 8. @@ -123,9 +126,8 @@ asmlinkage void aesni_gcm_enc(void *ctx, u8 *out, * u8 *out, Plaintext output. Decrypt in-place is allowed. * const u8 *in, Ciphertext input * unsigned long ciphertext_len, Length of data in bytes for decryption. - * u8 *iv, Pre-counter block j0: 4 byte salt (from Security Association) - * concatenated with 8 byte Initialisation Vector (from IPSec ESP - * Payload) concatenated with 0x00000001. 16-byte aligned pointer. + * u8 *iv, Pre-counter block j0: 12 byte IV concatenated with 0x00000001. + * 16-byte aligned pointer. * u8 *hash_subkey, the Hash sub key input. Data starts on a 16-byte boundary. * const u8 *aad, Additional Authentication Data (AAD) * unsigned long aad_len, Length of AAD in bytes. With RFC4106 this is going @@ -275,6 +277,16 @@ aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) align = 1; return PTR_ALIGN(crypto_aead_ctx(tfm), align); } + +static inline struct +generic_gcmaes_ctx *generic_gcmaes_ctx_get(struct crypto_aead *tfm) +{ + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return PTR_ALIGN(crypto_aead_ctx(tfm), align); +} #endif static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) @@ -712,32 +724,34 @@ static int rfc4106_set_authsize(struct crypto_aead *parent, return crypto_aead_setauthsize(&cryptd_tfm->base, authsize); } -static int helper_rfc4106_encrypt(struct aead_request *req) +static int generic_gcmaes_set_authsize(struct crypto_aead *tfm, + unsigned int authsize) +{ + switch (authsize) { + case 4: + case 8: + case 12: + case 13: + case 14: + case 15: + case 16: + break; + default: + return -EINVAL; + } + + return 0; +} + +static int gcmaes_encrypt(struct aead_request *req, unsigned int assoclen, + u8 *hash_subkey, u8 *iv, void *aes_ctx) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; - __be32 counter = cpu_to_be32(1); struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); struct scatter_walk src_sg_walk; struct scatter_walk dst_sg_walk = {}; - unsigned int i; - - /* Assuming we are supporting rfc4106 64-bit extended */ - /* sequence numbers We need to have the AAD length equal */ - /* to 16 or 20 bytes */ - if (unlikely(req->assoclen != 16 && req->assoclen != 20)) - return -EINVAL; - - /* IV below built */ - for (i = 0; i < 4; i++) - *(iv+i) = ctx->nonce[i]; - for (i = 0; i < 8; i++) - *(iv+4+i) = req->iv[i]; - *((__be32 *)(iv+12)) = counter; if (sg_is_last(req->src) && (!PageHighMem(sg_page(req->src)) || @@ -768,7 +782,7 @@ static int helper_rfc4106_encrypt(struct aead_request *req) kernel_fpu_begin(); aesni_gcm_enc_tfm(aes_ctx, dst, src, req->cryptlen, iv, - ctx->hash_subkey, assoc, req->assoclen - 8, + hash_subkey, assoc, assoclen, dst + req->cryptlen, auth_tag_len); kernel_fpu_end(); @@ -791,37 +805,20 @@ static int helper_rfc4106_encrypt(struct aead_request *req) return 0; } -static int helper_rfc4106_decrypt(struct aead_request *req) +static int gcmaes_decrypt(struct aead_request *req, unsigned int assoclen, + u8 *hash_subkey, u8 *iv, void *aes_ctx) { u8 one_entry_in_sg = 0; u8 *src, *dst, *assoc; unsigned long tempCipherLen = 0; - __be32 counter = cpu_to_be32(1); - int retval = 0; struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - void *aes_ctx = &(ctx->aes_key_expanded); unsigned long auth_tag_len = crypto_aead_authsize(tfm); - u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); u8 authTag[16]; struct scatter_walk src_sg_walk; struct scatter_walk dst_sg_walk = {}; - unsigned int i; - - if (unlikely(req->assoclen != 16 && req->assoclen != 20)) - return -EINVAL; - - /* Assuming we are supporting rfc4106 64-bit extended */ - /* sequence numbers We need to have the AAD length */ - /* equal to 16 or 20 bytes */ + int retval = 0; tempCipherLen = (unsigned long)(req->cryptlen - auth_tag_len); - /* IV below built */ - for (i = 0; i < 4; i++) - *(iv+i) = ctx->nonce[i]; - for (i = 0; i < 8; i++) - *(iv+4+i) = req->iv[i]; - *((__be32 *)(iv+12)) = counter; if (sg_is_last(req->src) && (!PageHighMem(sg_page(req->src)) || @@ -838,7 +835,6 @@ static int helper_rfc4106_decrypt(struct aead_request *req) scatterwalk_start(&dst_sg_walk, req->dst); dst = scatterwalk_map(&dst_sg_walk) + req->assoclen; } - } else { /* Allocate memory for src, dst, assoc */ assoc = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); @@ -850,9 +846,10 @@ static int helper_rfc4106_decrypt(struct aead_request *req) dst = src; } + kernel_fpu_begin(); aesni_gcm_dec_tfm(aes_ctx, dst, src, tempCipherLen, iv, - ctx->hash_subkey, assoc, req->assoclen - 8, + hash_subkey, assoc, assoclen, authTag, auth_tag_len); kernel_fpu_end(); @@ -875,6 +872,60 @@ static int helper_rfc4106_decrypt(struct aead_request *req) kfree(assoc); } return retval; + +} + +static int helper_rfc4106_encrypt(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + unsigned int i; + __be32 counter = cpu_to_be32(1); + + /* Assuming we are supporting rfc4106 64-bit extended */ + /* sequence numbers We need to have the AAD length equal */ + /* to 16 or 20 bytes */ + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) + return -EINVAL; + + /* IV below built */ + for (i = 0; i < 4; i++) + *(iv+i) = ctx->nonce[i]; + for (i = 0; i < 8; i++) + *(iv+4+i) = req->iv[i]; + *((__be32 *)(iv+12)) = counter; + + return gcmaes_encrypt(req, req->assoclen - 8, ctx->hash_subkey, iv, + aes_ctx); +} + +static int helper_rfc4106_decrypt(struct aead_request *req) +{ + __be32 counter = cpu_to_be32(1); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + unsigned int i; + + if (unlikely(req->assoclen != 16 && req->assoclen != 20)) + return -EINVAL; + + /* Assuming we are supporting rfc4106 64-bit extended */ + /* sequence numbers We need to have the AAD length */ + /* equal to 16 or 20 bytes */ + + /* IV below built */ + for (i = 0; i < 4; i++) + *(iv+i) = ctx->nonce[i]; + for (i = 0; i < 8; i++) + *(iv+4+i) = req->iv[i]; + *((__be32 *)(iv+12)) = counter; + + return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv, + aes_ctx); } static int rfc4106_encrypt(struct aead_request *req) @@ -1035,6 +1086,46 @@ struct { }; #ifdef CONFIG_X86_64 +static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key, + unsigned int key_len) +{ + struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead); + + return aes_set_key_common(crypto_aead_tfm(aead), + &ctx->aes_key_expanded, key, key_len) ?: + rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); +} + +static int generic_gcmaes_encrypt(struct aead_request *req) +{ + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + __be32 counter = cpu_to_be32(1); + + memcpy(iv, req->iv, 12); + *((__be32 *)(iv+12)) = counter; + + return gcmaes_encrypt(req, req->assoclen, ctx->hash_subkey, iv, + aes_ctx); +} + +static int generic_gcmaes_decrypt(struct aead_request *req) +{ + __be32 counter = cpu_to_be32(1); + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + void *aes_ctx = &(ctx->aes_key_expanded); + u8 iv[16] __attribute__ ((__aligned__(AESNI_ALIGN))); + + memcpy(iv, req->iv, 12); + *((__be32 *)(iv+12)) = counter; + + return gcmaes_decrypt(req, req->assoclen, ctx->hash_subkey, iv, + aes_ctx); +} + static struct aead_alg aesni_aead_algs[] = { { .setkey = common_rfc4106_set_key, .setauthsize = common_rfc4106_set_authsize, @@ -1069,6 +1160,23 @@ static struct aead_alg aesni_aead_algs[] = { { .cra_ctxsize = sizeof(struct cryptd_aead *), .cra_module = THIS_MODULE, }, +}, { + .setkey = generic_gcmaes_set_key, + .setauthsize = generic_gcmaes_set_authsize, + .encrypt = generic_gcmaes_encrypt, + .decrypt = generic_gcmaes_decrypt, + .ivsize = 12, + .maxauthsize = 16, + .base = { + .cra_name = "gcm(aes)", + .cra_driver_name = "generic-gcm-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_ASYNC, + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct generic_gcmaes_ctx), + .cra_alignmask = AESNI_ALIGN - 1, + .cra_module = THIS_MODULE, + }, } }; #else static struct aead_alg aesni_aead_algs[0]; diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c index 24ac9fad832d..d61e57960fe0 100644 --- a/arch/x86/crypto/glue_helper.c +++ b/arch/x86/crypto/glue_helper.c @@ -176,9 +176,6 @@ __glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx, src -= 1; dst -= 1; } while (nbytes >= func_bytes); - - if (nbytes < bsize) - goto done; } } diff --git a/arch/x86/crypto/sha1-mb/Makefile b/arch/x86/crypto/sha1-mb/Makefile index 2f8756375df5..2e14acc3da25 100644 --- a/arch/x86/crypto/sha1-mb/Makefile +++ b/arch/x86/crypto/sha1-mb/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +OBJECT_FILES_NON_STANDARD := y + avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) ifeq ($(avx2_supported),yes) diff --git a/arch/x86/crypto/sha256-mb/Makefile b/arch/x86/crypto/sha256-mb/Makefile index 41089e7c400c..45b4fca6c4a8 100644 --- a/arch/x86/crypto/sha256-mb/Makefile +++ b/arch/x86/crypto/sha256-mb/Makefile @@ -2,6 +2,8 @@ # Arch-specific CryptoAPI modules. # +OBJECT_FILES_NON_STANDARD := y + avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\ $(comma)4)$(comma)%ymm2,yes,no) ifeq ($(avx2_supported),yes) diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index 2dd3674b5a1e..458409b7568d 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -269,19 +269,19 @@ static struct sha512_hash_ctx * LAST */ ctx->error = HASH_CTX_ERROR_INVALID_FLAGS; - return ctx; + goto unlock; } if (ctx->status & HASH_CTX_STS_PROCESSING) { /* Cannot submit to a currently processing job. */ ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING; - return ctx; + goto unlock; } if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) { /* Cannot update a finished job. */ ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED; - return ctx; + goto unlock; } @@ -363,6 +363,7 @@ static struct sha512_hash_ctx } ctx = sha512_ctx_mgr_resubmit(mgr, ctx); +unlock: spin_unlock_irqrestore(&cstate->work_lock, irqflags); return ctx; } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 50bc26949e9e..48ef7bb32c42 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -252,6 +252,23 @@ ENTRY(__switch_to_asm) END(__switch_to_asm) /* + * The unwinder expects the last frame on the stack to always be at the same + * offset from the end of the page, which allows it to validate the stack. + * Calling schedule_tail() directly would break that convention because its an + * asmlinkage function so its argument has to be pushed on the stack. This + * wrapper creates a proper "end of stack" frame header before the call. + */ +ENTRY(schedule_tail_wrapper) + FRAME_BEGIN + + pushl %eax + call schedule_tail + popl %eax + + FRAME_END + ret +ENDPROC(schedule_tail_wrapper) +/* * A newly forked process directly context switches into this address. * * eax: prev task we switched from @@ -259,24 +276,15 @@ END(__switch_to_asm) * edi: kernel thread arg */ ENTRY(ret_from_fork) - FRAME_BEGIN /* help unwinder find end of stack */ - - /* - * schedule_tail() is asmlinkage so we have to put its 'prev' argument - * on the stack. - */ - pushl %eax - call schedule_tail - popl %eax + call schedule_tail_wrapper testl %ebx, %ebx jnz 1f /* kernel threads are uncommon */ 2: /* When we fork, we trace the syscall return in the child, too. */ - leal FRAME_OFFSET(%esp), %eax + movl %esp, %eax call syscall_return_slowpath - FRAME_END jmp restore_all /* kernel thread */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 607d72c4a485..a9a8027a6c0e 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -36,7 +36,6 @@ #include <asm/smap.h> #include <asm/pgtable_types.h> #include <asm/export.h> -#include <asm/frame.h> #include <linux/err.h> .code64 @@ -266,7 +265,8 @@ return_from_SYSCALL_64: * If width of "canonical tail" ever becomes variable, this will need * to be updated to remain correct on both old and new CPUs. * - * Change top 16 bits to be the sign-extension of 47th bit + * Change top bits to match most significant bit (47th or 56th bit + * depending on paging mode) in the address. */ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx @@ -406,19 +406,17 @@ END(__switch_to_asm) * r12: kernel thread arg */ ENTRY(ret_from_fork) - FRAME_BEGIN /* help unwinder find end of stack */ movq %rax, %rdi - call schedule_tail /* rdi: 'prev' task parameter */ + call schedule_tail /* rdi: 'prev' task parameter */ - testq %rbx, %rbx /* from kernel_thread? */ - jnz 1f /* kernel threads are uncommon */ + testq %rbx, %rbx /* from kernel_thread? */ + jnz 1f /* kernel threads are uncommon */ 2: - leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */ + movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ SWAPGS - FRAME_END jmp restore_regs_and_iret 1: diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 139ad7726e10..726355ce8497 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -78,9 +78,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm, if (image->size != new_size) return -EINVAL; - if (WARN_ON_ONCE(current->mm != new_vma->vm_mm)) - return -EFAULT; - vdso_fix_landing(image, new_vma); current->mm->context.vdso = (void __user *)new_vma->vm_start; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 580b60f5ac83..ff1ea2fb9705 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1750,6 +1750,8 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) return ret; } +static struct attribute_group x86_pmu_attr_group; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1813,6 +1815,14 @@ static int __init init_hw_perf_events(void) x86_pmu_events_group.attrs = tmp; } + if (x86_pmu.attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs); + if (!WARN_ON(!tmp)) + x86_pmu_attr_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); @@ -2101,8 +2111,7 @@ static int x86_pmu_event_init(struct perf_event *event) static void refresh_pce(void *ignored) { - if (current->active_mm) - load_mm_cr4(current->active_mm); + load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); } static void x86_pmu_event_mapped(struct perf_event *event) @@ -2224,7 +2233,6 @@ void perf_check_microcode(void) if (x86_pmu.check_microcode) x86_pmu.check_microcode(); } -EXPORT_SYMBOL_GPL(perf_check_microcode); static struct pmu pmu = { .pmu_enable = x86_pmu_enable, @@ -2255,7 +2263,7 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now) { - struct cyc2ns_data *data; + struct cyc2ns_data data; u64 offset; userpg->cap_user_time = 0; @@ -2267,17 +2275,17 @@ void arch_perf_update_userpage(struct perf_event *event, if (!using_native_sched_clock() || !sched_clock_stable()) return; - data = cyc2ns_read_begin(); + cyc2ns_read_begin(&data); - offset = data->cyc2ns_offset + __sched_clock_offset; + offset = data.cyc2ns_offset + __sched_clock_offset; /* * Internal timekeeping for enabled/running/stopped times * is always in the local_clock domain. */ userpg->cap_user_time = 1; - userpg->time_mult = data->cyc2ns_mul; - userpg->time_shift = data->cyc2ns_shift; + userpg->time_mult = data.cyc2ns_mul; + userpg->time_shift = data.cyc2ns_shift; userpg->time_offset = offset - now; /* @@ -2289,7 +2297,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->time_zero = offset; } - cyc2ns_read_end(data); + cyc2ns_read_end(); } void @@ -2334,7 +2342,7 @@ static unsigned long get_segment_base(unsigned int segment) /* IRQs are off, so this synchronizes with smp_store_release */ ldt = lockless_dereference(current->active_mm->context.ldt); - if (!ldt || idx > ldt->size) + if (!ldt || idx > ldt->nr_entries) return 0; desc = &ldt->entries[idx]; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a6d91d4e37a1..aa62437d1aa1 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -431,11 +431,11 @@ static __initconst const u64 skl_hw_cache_event_ids [ C(DTLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_INST_RETIRED.ALL_LOADS */ - [ C(RESULT_MISS) ] = 0x608, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ + [ C(RESULT_MISS) ] = 0xe08, /* DTLB_LOAD_MISSES.WALK_COMPLETED */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_INST_RETIRED.ALL_STORES */ - [ C(RESULT_MISS) ] = 0x649, /* DTLB_STORE_MISSES.WALK_COMPLETED */ + [ C(RESULT_MISS) ] = 0xe49, /* DTLB_STORE_MISSES.WALK_COMPLETED */ }, [ C(OP_PREFETCH) ] = { [ C(RESULT_ACCESS) ] = 0x0, @@ -3160,6 +3160,19 @@ err: return -ENOMEM; } +static void flip_smm_bit(void *data) +{ + unsigned long set = *(unsigned long *)data; + + if (set > 0) { + msr_set_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } else { + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, + DEBUGCTLMSR_FREEZE_IN_SMM_BIT); + } +} + static void intel_pmu_cpu_starting(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); @@ -3174,6 +3187,8 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + flip_smm_bit(&x86_pmu.attr_freeze_on_smi); + if (!cpuc->shared_regs) return; @@ -3410,12 +3425,10 @@ static void intel_snb_check_microcode(void) int pebs_broken = 0; int cpu; - get_online_cpus(); for_each_online_cpu(cpu) { if ((pebs_broken = intel_snb_pebs_broken(cpu))) break; } - put_online_cpus(); if (pebs_broken == x86_pmu.pebs_broken) return; @@ -3488,7 +3501,9 @@ static bool check_msr(unsigned long msr, u64 mask) static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; + cpus_read_lock(); intel_snb_check_microcode(); + cpus_read_unlock(); } static const struct { int id; char *name; } intel_arch_events_map[] __initconst = { @@ -3595,6 +3610,52 @@ static struct attribute *hsw_events_attrs[] = { NULL }; +static ssize_t freeze_on_smi_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%lu\n", x86_pmu.attr_freeze_on_smi); +} + +static DEFINE_MUTEX(freeze_on_smi_mutex); + +static ssize_t freeze_on_smi_store(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val > 1) + return -EINVAL; + + mutex_lock(&freeze_on_smi_mutex); + + if (x86_pmu.attr_freeze_on_smi == val) + goto done; + + x86_pmu.attr_freeze_on_smi = val; + + get_online_cpus(); + on_each_cpu(flip_smm_bit, &val, 1); + put_online_cpus(); +done: + mutex_unlock(&freeze_on_smi_mutex); + + return count; +} + +static DEVICE_ATTR_RW(freeze_on_smi); + +static struct attribute *intel_pmu_attrs[] = { + &dev_attr_freeze_on_smi.attr, + NULL, +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -3641,6 +3702,8 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + + x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: @@ -4112,13 +4175,12 @@ static __init int fixup_ht_bug(void) lockup_detector_resume(); - get_online_cpus(); + cpus_read_lock(); - for_each_online_cpu(c) { + for_each_online_cpu(c) free_excl_cntrs(c); - } - put_online_cpus(); + cpus_read_unlock(); pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); return 0; } diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c index 8c00dc09a5d2..2521f771f2f5 100644 --- a/arch/x86/events/intel/cqm.c +++ b/arch/x86/events/intel/cqm.c @@ -1682,7 +1682,7 @@ static int __init intel_cqm_init(void) * * Also, check that the scales match on all cpus. */ - get_online_cpus(); + cpus_read_lock(); for_each_online_cpu(cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -1746,14 +1746,14 @@ static int __init intel_cqm_init(void) * Setup the hot cpu notifier once we are sure cqm * is enabled to avoid notifier leak. */ - cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING, - "perf/x86/cqm:starting", - intel_cqm_cpu_starting, NULL); - cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online", - NULL, intel_cqm_cpu_exit); - + cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING, + "perf/x86/cqm:starting", + intel_cqm_cpu_starting, NULL); + cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE, + "perf/x86/cqm:online", + NULL, intel_cqm_cpu_exit); out: - put_online_cpus(); + cpus_read_unlock(); if (ret) { kfree(str); diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f924629836a8..eb261656a320 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -18,7 +18,7 @@ enum { LBR_FORMAT_MAX_KNOWN = LBR_FORMAT_TIME, }; -static enum { +static const enum { LBR_EIP_FLAGS = 1, LBR_TSX = 2, } lbr_desc[LBR_FORMAT_MAX_KNOWN + 1] = { @@ -287,7 +287,7 @@ inline u64 lbr_from_signext_quirk_wr(u64 val) /* * If quirk is needed, ensure sign extension is 61 bits: */ -u64 lbr_from_signext_quirk_rd(u64 val) +static u64 lbr_from_signext_quirk_rd(u64 val) { if (static_branch_unlikely(&lbr_from_quirk_key)) { /* diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 758c1aa5009d..44ec523287f6 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1170,7 +1170,7 @@ static int uncore_event_cpu_online(unsigned int cpu) pmu = type->pmus; for (i = 0; i < type->num_boxes; i++, pmu++) { box = pmu->boxes[pkg]; - if (!box && atomic_inc_return(&box->refcnt) == 1) + if (box && atomic_inc_return(&box->refcnt) == 1) uncore_box_init(box); } } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index be3d36254040..53728eea1bed 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -562,6 +562,9 @@ struct x86_pmu { ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; + unsigned long attr_freeze_on_smi; + struct attribute **attrs; + /* * CPU Hotplug hooks */ diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 00c88a01301d..da181ad1d5f8 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -3,6 +3,7 @@ #include <linux/ioport.h> #include <linux/pci.h> +#include <linux/refcount.h> struct amd_nb_bus_dev_range { u8 bus; @@ -55,7 +56,7 @@ struct threshold_bank { struct threshold_block *blocks; /* initialized to the number of CPUs on the node sharing this bank */ - atomic_t cpus; + refcount_t cpus; }; struct amd_northbridge { diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index bdffcd9eab2b..5f01671c68f2 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -252,6 +252,8 @@ static inline int x2apic_enabled(void) { return 0; } #define x2apic_supported() (0) #endif /* !CONFIG_X86_X2APIC */ +struct irq_data; + /* * Copyright 2004 James Cleverdon, IBM. * Subject to the GNU Public License, v.2 @@ -296,9 +298,9 @@ struct apic { /* Can't be NULL on 64-bit */ unsigned long (*set_apic_id)(unsigned int id); - int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid); + int (*cpu_mask_to_apicid)(const struct cpumask *cpumask, + struct irq_data *irqdata, + unsigned int *apicid); /* ipi */ void (*send_IPI)(int cpu, int vector); @@ -540,28 +542,12 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) #endif -static inline int -flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) -{ - unsigned long cpu_mask = cpumask_bits(cpumask)[0] & - cpumask_bits(andmask)[0] & - cpumask_bits(cpu_online_mask)[0] & - APIC_ALL_CPUS; - - if (likely(cpu_mask)) { - *apicid = (unsigned int)cpu_mask; - return 0; - } else { - return -EINVAL; - } -} - -extern int -default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid); +extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask, + struct irq_data *irqdata, + unsigned int *apicid); +extern int default_cpu_mask_to_apicid(const struct cpumask *cpumask, + struct irq_data *irqdata, + unsigned int *apicid); static inline void flat_vector_allocation_domain(int cpu, struct cpumask *retmask, diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index caa5798c92f4..33380b871463 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -246,19 +246,6 @@ static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u) return c; } -/** - * atomic_inc_short - increment of a short integer - * @v: pointer to type int - * - * Atomically adds 1 to @v - * Returns the new value of @u - */ -static __always_inline short int atomic_inc_short(short int *v) -{ - asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v)); - return *v; -} - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 24118c0b4640..5343c19814b3 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -116,7 +116,6 @@ struct compat_statfs { int f_spare[4]; }; -#define COMPAT_RLIM_OLD_INFINITY 0x7fffffff #define COMPAT_RLIM_INFINITY 0xffffffff typedef u32 compat_old_sigset_t; /* at least 32 bits */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 08a0838b83fb..398c79889f5c 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -19,8 +19,6 @@ # define ISA_DMA_BIT_MASK DMA_BIT_MASK(32) #endif -#define DMA_ERROR_CODE 0 - extern int iommu_merge; extern struct device x86_dma_fallback_dev; extern int panic_on_overflow; @@ -35,9 +33,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp); #define arch_dma_alloc_attrs arch_dma_alloc_attrs -#define HAVE_ARCH_DMA_SUPPORTED 1 -extern int dma_supported(struct device *hwdev, u64 mask); - extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag, unsigned long attrs); diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index 8e0f8b85b209..a504adc661a4 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -4,6 +4,7 @@ #include <asm/e820/types.h> extern struct e820_table *e820_table; +extern struct e820_table *e820_table_kexec; extern struct e820_table *e820_table_firmware; extern unsigned long pci_mem_start; diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 2f77bcefe6b4..d2ff779f347e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -74,7 +74,7 @@ struct efi_scratch { __kernel_fpu_begin(); \ \ if (efi_scratch.use_pgd) { \ - efi_scratch.prev_cr3 = read_cr3(); \ + efi_scratch.prev_cr3 = __read_cr3(); \ write_cr3((unsigned long)efi_scratch.efi_pgt); \ __flush_tlb_all(); \ } \ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index e8ab9a46bc68..1c18d83d3f09 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -245,12 +245,13 @@ extern int force_personality32; #define CORE_DUMP_USE_REGSET #define ELF_EXEC_PAGESIZE 4096 -/* This is the location that an ET_DYN program is loaded if exec'ed. Typical - use of this is to invoke "./ld.so someprog" to test out a new version of - the loader. We need to make sure that it is out of the way of the program - that it will "exec", and that there is sufficient room for the brk. */ - -#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) +/* + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. + */ +#define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ + 0x100000000UL) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h index b8ad261d11dc..c66d19e3c23e 100644 --- a/arch/x86/include/asm/extable.h +++ b/arch/x86/include/asm/extable.h @@ -29,6 +29,7 @@ struct pt_regs; } while (0) extern int fixup_exception(struct pt_regs *regs, int trapnr); +extern int fixup_bug(struct pt_regs *regs, int trapnr); extern bool ex_has_fault_handler(unsigned long ip); extern void early_fixup_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 59405a248fc2..9b76cd331990 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,8 +22,8 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - unsigned int irq_tlb_count; #endif + unsigned int irq_tlb_count; #ifdef CONFIG_X86_THERMAL_VECTOR unsigned int irq_thermal_count; #endif diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index 3a106165e03a..535af0f2d8ac 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -85,4 +85,8 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } +#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE +static inline bool gigantic_page_supported(void) { return true; } +#endif + #endif /* _ASM_X86_HUGETLB_H */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 793869879464..fca144a104e4 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -6,6 +6,8 @@ extern int force_iommu, no_iommu; extern int iommu_detected; extern int iommu_pass_through; +int x86_dma_supported(struct device *dev, u64 mask); + /* 10 seconds */ #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 16d3fa211962..668cca540025 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -29,7 +29,6 @@ struct irq_desc; #include <linux/cpumask.h> extern int check_irq_vectors_for_cpu_disable(void); extern void fixup_irqs(void); -extern void irq_force_complete_move(struct irq_desc *desc); #endif #ifdef CONFIG_HAVE_KVM diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index a210eba2727c..023b4a9fc846 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -55,7 +55,8 @@ extern struct irq_domain * irq_remapping_get_irq_domain(struct irq_alloc_info *info); /* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ -extern struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent); +extern struct irq_domain * +arch_create_remap_msi_irq_domain(struct irq_domain *par, const char *n, int id); /* Get parent irqdomain for interrupt remapping irqdomain */ static inline struct irq_domain *arch_get_ir_parent_domain(void) diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 055962615779..722d0e568863 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -296,6 +296,7 @@ struct x86_emulate_ctxt { bool perm_ok; /* do not check permissions if true */ bool ud; /* inject an #UD if host doesn't support insn */ + bool tf; /* TF value before instruction (after for syscall/sysret) */ bool have_exception; struct x86_exception exception; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 9c761fea0c98..1588e9e3dc01 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -43,33 +43,36 @@ #define KVM_PRIVATE_MEM_SLOTS 3 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS) -#define KVM_HALT_POLL_NS_DEFAULT 400000 +#define KVM_HALT_POLL_NS_DEFAULT 200000 #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS /* x86-specific vcpu->requests bit members */ -#define KVM_REQ_MIGRATE_TIMER 8 -#define KVM_REQ_REPORT_TPR_ACCESS 9 -#define KVM_REQ_TRIPLE_FAULT 10 -#define KVM_REQ_MMU_SYNC 11 -#define KVM_REQ_CLOCK_UPDATE 12 -#define KVM_REQ_EVENT 14 -#define KVM_REQ_APF_HALT 15 -#define KVM_REQ_STEAL_UPDATE 16 -#define KVM_REQ_NMI 17 -#define KVM_REQ_PMU 18 -#define KVM_REQ_PMI 19 -#define KVM_REQ_SMI 20 -#define KVM_REQ_MASTERCLOCK_UPDATE 21 -#define KVM_REQ_MCLOCK_INPROGRESS (22 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_SCAN_IOAPIC (23 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24 -#define KVM_REQ_APIC_PAGE_RELOAD (25 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) -#define KVM_REQ_HV_CRASH 26 -#define KVM_REQ_IOAPIC_EOI_EXIT 27 -#define KVM_REQ_HV_RESET 28 -#define KVM_REQ_HV_EXIT 29 -#define KVM_REQ_HV_STIMER 30 +#define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) +#define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) +#define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) +#define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) +#define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) +#define KVM_REQ_EVENT KVM_ARCH_REQ(6) +#define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) +#define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) +#define KVM_REQ_NMI KVM_ARCH_REQ(9) +#define KVM_REQ_PMU KVM_ARCH_REQ(10) +#define KVM_REQ_PMI KVM_ARCH_REQ(11) +#define KVM_REQ_SMI KVM_ARCH_REQ(12) +#define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) +#define KVM_REQ_MCLOCK_INPROGRESS \ + KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_SCAN_IOAPIC \ + KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_GLOBAL_CLOCK_UPDATE KVM_ARCH_REQ(16) +#define KVM_REQ_APIC_PAGE_RELOAD \ + KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HV_CRASH KVM_ARCH_REQ(18) +#define KVM_REQ_IOAPIC_EOI_EXIT KVM_ARCH_REQ(19) +#define KVM_REQ_HV_RESET KVM_ARCH_REQ(20) +#define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) +#define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -254,7 +257,8 @@ union kvm_mmu_page_role { unsigned cr0_wp:1; unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; - unsigned :8; + unsigned ad_disabled:1; + unsigned :7; /* * This is left at the top of the word so that diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4fd5195deed0..181264989db5 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -266,6 +266,7 @@ static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *s #endif int mce_available(struct cpuinfo_x86 *c); +bool mce_is_memory_error(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); @@ -284,10 +285,6 @@ int mce_notify_irq(void); DECLARE_PER_CPU(struct mce, injectm); -extern void register_mce_write_callback(ssize_t (*)(struct file *filp, - const char __user *ubuf, - size_t usize, loff_t *off)); - /* Disable CMCI/polling for MCA bank claimed by firmware */ extern void mce_disable_bank(int bank); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index f9813b6d8b80..79b647a7ebd0 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -37,12 +37,6 @@ typedef struct { #endif } mm_context_t; -#ifdef CONFIG_SMP void leave_mm(int cpu); -#else -static inline void leave_mm(int cpu) -{ -} -#endif #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 68b329d77b3a..ecfcb6643c9b 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -47,7 +47,7 @@ struct ldt_struct { * allocations, but it's not worth trying to optimize. */ struct desc_struct *entries; - unsigned int size; + unsigned int nr_entries; }; /* @@ -87,22 +87,46 @@ static inline void load_mm_ldt(struct mm_struct *mm) */ if (unlikely(ldt)) - set_ldt(ldt->entries, ldt->size); + set_ldt(ldt->entries, ldt->nr_entries); else clear_LDT(); #else clear_LDT(); #endif +} + +static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ +#ifdef CONFIG_MODIFY_LDT_SYSCALL + /* + * Load the LDT if either the old or new mm had an LDT. + * + * An mm will never go from having an LDT to not having an LDT. Two + * mms never share an LDT, so we don't gain anything by checking to + * see whether the LDT changed. There's also no guarantee that + * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, + * then prev->context.ldt will also be non-NULL. + * + * If we really cared, we could optimize the case where prev == next + * and we're exiting lazy mode. Most of the time, if this happens, + * we don't actually need to reload LDTR, but modify_ldt() is mostly + * used by legacy code and emulators where we don't need this level of + * performance. + * + * This uses | instead of || because it generates better code. + */ + if (unlikely((unsigned long)prev->context.ldt | + (unsigned long)next->context.ldt)) + load_mm_ldt(next); +#endif DEBUG_LOCKS_WARN_ON(preemptible()); } static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) { -#ifdef CONFIG_SMP if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY); -#endif } static inline int init_new_context(struct task_struct *tsk, @@ -220,18 +244,6 @@ static inline int vma_pkey(struct vm_area_struct *vma) } #endif -static inline bool __pkru_allows_pkey(u16 pkey, bool write) -{ - u32 pkru = read_pkru(); - - if (!__pkru_allows_read(pkru, pkey)) - return false; - if (write && !__pkru_allows_write(pkru, pkey)) - return false; - - return true; -} - /* * We only want to enforce protection keys on the current process * because we effectively have no access to PKRU for other @@ -268,4 +280,23 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, return __pkru_allows_pkey(vma_pkey(vma), write); } + +/* + * This can be used from process context to figure out what the value of + * CR3 is without needing to do a (slow) __read_cr3(). + * + * It's intended to be used for code like KVM that sneakily changes CR3 + * and needs to restore it. It needs to be used very carefully. + */ +static inline unsigned long __get_current_cr3_fast(void) +{ + unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd); + + /* For now, be very restrictive about when this can be called. */ + VM_WARN_ON(in_nmi() || !in_atomic()); + + VM_BUG_ON(cr3 != __read_cr3()); + return cr3; +} + #endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index fba100713924..2b58c8c1eeaa 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -2,8 +2,7 @@ #define _ASM_X86_MSHYPER_H #include <linux/types.h> -#include <linux/interrupt.h> -#include <linux/clocksource.h> +#include <linux/atomic.h> #include <asm/hyperv.h> /* @@ -137,7 +136,6 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type) } } -#define hv_get_current_tick(tick) rdmsrl(HV_X64_MSR_TIME_REF_COUNT, tick) #define hv_init_timer(timer, tick) wrmsrl(timer, tick) #define hv_init_timer_config(config, val) wrmsrl(config, val) diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 673f9ac50f6d..5573c75f8e4c 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -137,6 +137,8 @@ #define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 +#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) #define MSR_PEBS_FRONTEND 0x000003f7 @@ -249,9 +251,13 @@ #define HWP_MIN_PERF(x) (x & 0xff) #define HWP_MAX_PERF(x) ((x & 0xff) << 8) #define HWP_DESIRED_PERF(x) ((x & 0xff) << 16) -#define HWP_ENERGY_PERF_PREFERENCE(x) ((x & 0xff) << 24) -#define HWP_ACTIVITY_WINDOW(x) ((x & 0xff3) << 32) -#define HWP_PACKAGE_CONTROL(x) ((x & 0x1) << 42) +#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24) +#define HWP_EPP_PERFORMANCE 0x00 +#define HWP_EPP_BALANCE_PERFORMANCE 0x80 +#define HWP_EPP_BALANCE_POWERSAVE 0xC0 +#define HWP_EPP_POWERSAVE 0xFF +#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32) +#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42) /* IA32_HWP_STATUS */ #define HWP_GUARANTEED_CHANGE(x) (x & 0x1) @@ -420,6 +426,8 @@ #define MSR_IA32_TSC_ADJUST 0x0000003b #define MSR_IA32_BNDCFGS 0x00000d90 +#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc + #define MSR_IA32_XSS 0x00000da0 #define FEATURE_CONTROL_LOCKED (1<<0) @@ -474,9 +482,11 @@ #define MSR_MISC_PWR_MGMT 0x000001aa #define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 -#define ENERGY_PERF_BIAS_PERFORMANCE 0 -#define ENERGY_PERF_BIAS_NORMAL 6 -#define ENERGY_PERF_BIAS_POWERSAVE 15 +#define ENERGY_PERF_BIAS_PERFORMANCE 0 +#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE 4 +#define ENERGY_PERF_BIAS_NORMAL 6 +#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE 8 +#define ENERGY_PERF_BIAS_POWERSAVE 15 #define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 55fa56fe4e45..9ccac1926587 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -61,7 +61,7 @@ static inline void write_cr2(unsigned long x) PVOP_VCALL1(pv_mmu_ops.write_cr2, x); } -static inline unsigned long read_cr3(void) +static inline unsigned long __read_cr3(void) { return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3); } @@ -118,7 +118,7 @@ static inline u64 paravirt_read_msr(unsigned msr) static inline void paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { - return PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); + PVOP_VCALL3(pv_cpu_ops.write_msr, msr, low, high); } static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) @@ -312,11 +312,9 @@ static inline void __flush_tlb_single(unsigned long addr) } static inline void flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { - PVOP_VCALL4(pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end); + PVOP_VCALL2(pv_mmu_ops.flush_tlb_others, cpumask, info); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7465d6fe336f..cb976bab6299 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -51,6 +51,7 @@ struct mm_struct; struct desc_struct; struct task_struct; struct cpumask; +struct flush_tlb_info; /* * Wrapper type for pointers to code which uses the non-standard @@ -223,9 +224,7 @@ struct pv_mmu_ops { void (*flush_tlb_kernel)(void); void (*flush_tlb_single)(unsigned long addr); void (*flush_tlb_others)(const struct cpumask *cpus, - struct mm_struct *mm, - unsigned long start, - unsigned long end); + const struct flush_tlb_info *info); /* Hooks for allocating and freeing a pagetable top-level */ int (*pgd_alloc)(struct mm_struct *mm); diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 0b1ff4c1c14e..fffb2794dd89 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -7,6 +7,7 @@ bool pat_enabled(void); void pat_disable(const char *reason); extern void pat_init(void); +extern void init_cache_modes(void); extern int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index f513cc231151..473a7295ab10 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -77,14 +77,8 @@ static inline bool is_vmd(struct pci_bus *bus) extern unsigned int pcibios_assign_all_busses(void); extern int pci_legacy_init(void); -# ifdef CONFIG_ACPI -# define x86_default_pci_init pci_acpi_init -# else -# define x86_default_pci_init pci_legacy_init -# endif #else -# define pcibios_assign_all_busses() 0 -# define x86_default_pci_init NULL +static inline int pcibios_assign_all_busses(void) { return 0; } #endif extern unsigned long pci_mem_start; diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 50d35e3185f5..c8821bab938f 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -212,4 +212,51 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) #define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) #define __swp_entry_to_pte(x) ((pte_t){ { .pte_high = (x).val } }) +#define gup_get_pte gup_get_pte +/* + * WARNING: only to be used in the get_user_pages_fast() implementation. + * + * With get_user_pages_fast(), we walk down the pagetables without taking + * any locks. For this we would like to load the pointers atomically, + * but that is not possible (without expensive cmpxchg8b) on PAE. What + * we do have is the guarantee that a PTE will only either go from not + * present to present, or present to not present or both -- it will not + * switch to a completely different present page without a TLB flush in + * between; something that we are blocking by holding interrupts off. + * + * Setting ptes from not present to present goes: + * + * ptep->pte_high = h; + * smp_wmb(); + * ptep->pte_low = l; + * + * And present to not present goes: + * + * ptep->pte_low = 0; + * smp_wmb(); + * ptep->pte_high = 0; + * + * We must ensure here that the load of pte_low sees 'l' iff pte_high + * sees 'h'. We load pte_high *after* loading pte_low, which ensures we + * don't see an older value of pte_high. *Then* we recheck pte_low, + * which ensures that we haven't picked up a changed pte high. We might + * have gotten rubbish values from pte_low and pte_high, but we are + * guaranteed that pte_low will not have the present bit set *unless* + * it is 'l'. Because get_user_pages_fast() only operates on present ptes + * we're safe. + */ +static inline pte_t gup_get_pte(pte_t *ptep) +{ + pte_t pte; + + do { + pte.pte_low = ptep->pte_low; + smp_rmb(); + pte.pte_high = ptep->pte_high; + smp_rmb(); + } while (unlikely(pte.pte_low != ptep->pte_low)); + + return pte; +} + #endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index f5af95a0c6b8..77037b6f1caa 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -244,6 +244,11 @@ static inline int pud_devmap(pud_t pud) return 0; } #endif + +static inline int pgd_devmap(pgd_t pgd) +{ + return 0; +} #endif #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -917,7 +922,7 @@ extern pgd_t trampoline_pgd_entry; static inline void __meminit init_trampoline_default(void) { /* Default trampoline pgd value */ - trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)]; + trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)]; } # ifdef CONFIG_RANDOMIZE_MEMORY void __meminit init_trampoline(void); @@ -1185,6 +1190,54 @@ static inline u16 pte_flags_pkey(unsigned long pte_flags) #endif } +static inline bool __pkru_allows_pkey(u16 pkey, bool write) +{ + u32 pkru = read_pkru(); + + if (!__pkru_allows_read(pkru, pkey)) + return false; + if (write && !__pkru_allows_write(pkru, pkey)) + return false; + + return true; +} + +/* + * 'pteval' can come from a PTE, PMD or PUD. We only check + * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the + * same value on all 3 types. + */ +static inline bool __pte_access_permitted(unsigned long pteval, bool write) +{ + unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; + + if (write) + need_pte_bits |= _PAGE_RW; + + if ((pteval & need_pte_bits) != need_pte_bits) + return 0; + + return __pkru_allows_pkey(pte_flags_pkey(pteval), write); +} + +#define pte_access_permitted pte_access_permitted +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + return __pte_access_permitted(pte_val(pte), write); +} + +#define pmd_access_permitted pmd_access_permitted +static inline bool pmd_access_permitted(pmd_t pmd, bool write) +{ + return __pte_access_permitted(pmd_val(pmd), write); +} + +#define pud_access_permitted pud_access_permitted +static inline bool pud_access_permitted(pud_t pud, bool write) +{ + return __pte_access_permitted(pud_val(pud), write); +} + #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 9991224f6238..2160c1fee920 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -14,15 +14,17 @@ #include <linux/bitops.h> #include <linux/threads.h> +extern p4d_t level4_kernel_pgt[512]; +extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512]; -extern pgd_t init_level4_pgt[]; +extern pgd_t init_top_pgt[]; -#define swapper_pg_dir init_level4_pgt +#define swapper_pg_dir init_top_pgt extern void paging_init(void); @@ -227,6 +229,20 @@ extern void cleanup_highmap(void); extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); -#endif /* !__ASSEMBLY__ */ +#define gup_fast_permitted gup_fast_permitted +static inline bool gup_fast_permitted(unsigned long start, int nr_pages, + int write) +{ + unsigned long len, end; + + len = (unsigned long)nr_pages << PAGE_SHIFT; + end = start + len; + if (end < start) + return false; + if (end >> __VIRTUAL_MASK_SHIFT) + return false; + return true; +} +#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h deleted file mode 100644 index 0ff8fe71b255..000000000000 --- a/arch/x86/include/asm/pmem.h +++ /dev/null @@ -1,136 +0,0 @@ -/* - * Copyright(c) 2015 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ -#ifndef __ASM_X86_PMEM_H__ -#define __ASM_X86_PMEM_H__ - -#include <linux/uaccess.h> -#include <asm/cacheflush.h> -#include <asm/cpufeature.h> -#include <asm/special_insns.h> - -#ifdef CONFIG_ARCH_HAS_PMEM_API -/** - * arch_memcpy_to_pmem - copy data to persistent memory - * @dst: destination buffer for the copy - * @src: source buffer for the copy - * @n: length of the copy in bytes - * - * Copy data to persistent memory media via non-temporal stores so that - * a subsequent pmem driver flush operation will drain posted write queues. - */ -static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n) -{ - int rem; - - /* - * We are copying between two kernel buffers, if - * __copy_from_user_inatomic_nocache() returns an error (page - * fault) we would have already reported a general protection fault - * before the WARN+BUG. - */ - rem = __copy_from_user_inatomic_nocache(dst, (void __user *) src, n); - if (WARN(rem, "%s: fault copying %p <- %p unwritten: %d\n", - __func__, dst, src, rem)) - BUG(); -} - -/** - * arch_wb_cache_pmem - write back a cache range with CLWB - * @vaddr: virtual start address - * @size: number of bytes to write back - * - * Write back a cache range using the CLWB (cache line write back) - * instruction. Note that @size is internally rounded up to be cache - * line size aligned. - */ -static inline void arch_wb_cache_pmem(void *addr, size_t size) -{ - u16 x86_clflush_size = boot_cpu_data.x86_clflush_size; - unsigned long clflush_mask = x86_clflush_size - 1; - void *vend = addr + size; - void *p; - - for (p = (void *)((unsigned long)addr & ~clflush_mask); - p < vend; p += x86_clflush_size) - clwb(p); -} - -/** - * arch_copy_from_iter_pmem - copy data from an iterator to PMEM - * @addr: PMEM destination address - * @bytes: number of bytes to copy - * @i: iterator with source data - * - * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. - */ -static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes, - struct iov_iter *i) -{ - size_t len; - - /* TODO: skip the write-back by always using non-temporal stores */ - len = copy_from_iter_nocache(addr, bytes, i); - - /* - * In the iovec case on x86_64 copy_from_iter_nocache() uses - * non-temporal stores for the bulk of the transfer, but we need - * to manually flush if the transfer is unaligned. A cached - * memory copy is used when destination or size is not naturally - * aligned. That is: - * - Require 8-byte alignment when size is 8 bytes or larger. - * - Require 4-byte alignment when size is 4 bytes. - * - * In the non-iovec case the entire destination needs to be - * flushed. - */ - if (iter_is_iovec(i)) { - unsigned long flushed, dest = (unsigned long) addr; - - if (bytes < 8) { - if (!IS_ALIGNED(dest, 4) || (bytes != 4)) - arch_wb_cache_pmem(addr, bytes); - } else { - if (!IS_ALIGNED(dest, 8)) { - dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); - arch_wb_cache_pmem(addr, 1); - } - - flushed = dest - (unsigned long) addr; - if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8)) - arch_wb_cache_pmem(addr + bytes - 1, 1); - } - } else - arch_wb_cache_pmem(addr, bytes); - - return len; -} - -/** - * arch_clear_pmem - zero a PMEM memory range - * @addr: virtual start address - * @size: number of bytes to zero - * - * Write zeros into the memory range starting at 'addr' for 'size' bytes. - */ -static inline void arch_clear_pmem(void *addr, size_t size) -{ - memset(addr, 0, size); - arch_wb_cache_pmem(addr, size); -} - -static inline void arch_invalidate_pmem(void *addr, size_t size) -{ - clflush_cache_range(addr, size); -} -#endif /* CONFIG_ARCH_HAS_PMEM_API */ -#endif /* __ASM_X86_PMEM_H__ */ diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 39fb618e2211..79aa2f98398d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -8,4 +8,40 @@ #else #define X86_VM_MASK 0 /* No VM86 support */ #endif + +/* + * CR3's layout varies depending on several things. + * + * If CR4.PCIDE is set (64-bit only), then CR3[11:0] is the address space ID. + * If PAE is enabled, then CR3[11:5] is part of the PDPT address + * (i.e. it's 32-byte aligned, not page-aligned) and CR3[4:0] is ignored. + * Otherwise (non-PAE, non-PCID), CR3[3] is PWT, CR3[4] is PCD, and + * CR3[2:0] and CR3[11:5] are ignored. + * + * In all cases, Linux puts zeros in the low ignored bits and in PWT and PCD. + * + * CR3[63] is always read as zero. If CR4.PCIDE is set, then CR3[63] may be + * written as 1 to prevent the write to CR3 from flushing the TLB. + * + * On systems with SME, one bit (in a variable position!) is stolen to indicate + * that the top-level paging structure is encrypted. + * + * All of the remaining bits indicate the physical address of the top-level + * paging structure. + * + * CR3_ADDR_MASK is the mask used by read_cr3_pa(). + */ +#ifdef CONFIG_X86_64 +/* Mask off the address space ID bits. */ +#define CR3_ADDR_MASK 0x7FFFFFFFFFFFF000ull +#define CR3_PCID_MASK 0xFFFull +#else +/* + * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save + * a tiny bit of code size by setting all the bits. + */ +#define CR3_ADDR_MASK 0xFFFFFFFFull +#define CR3_PCID_MASK 0ull +#endif + #endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 3cada998a402..6a79547e8ee0 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -231,6 +231,14 @@ native_cpuid_reg(ebx) native_cpuid_reg(ecx) native_cpuid_reg(edx) +/* + * Friendlier CR3 helpers. + */ +static inline unsigned long read_cr3_pa(void) +{ + return __read_cr3() & CR3_ADDR_MASK; +} + static inline void load_cr3(pgd_t *pgdir) { write_cr3(__pa(pgdir)); @@ -860,8 +868,6 @@ extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ -extern unsigned long thread_saved_pc(struct task_struct *tsk); - extern void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp); @@ -901,8 +907,13 @@ static inline int mpx_disable_management(void) } #endif /* CONFIG_X86_INTEL_MPX */ +#ifdef CONFIG_CPU_SUP_AMD extern u16 amd_get_nb_id(int cpu); extern u32 amd_get_nodes_per_socket(void); +#else +static inline u16 amd_get_nb_id(int cpu) { return 0; } +static inline u32 amd_get_nodes_per_socket(void) { return 0; } +#endif static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ac1d5da14734..e4585a393965 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -44,7 +44,6 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); -extern void setup_default_timer_irq(void); #ifdef CONFIG_X86_INTEL_MID extern void x86_intel_mid_early_setup(void); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 12af3e35edfa..9efaabf5b54b 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -39,7 +39,7 @@ static inline void native_write_cr2(unsigned long val) asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); } -static inline unsigned long native_read_cr3(void) +static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); @@ -159,9 +159,13 @@ static inline void write_cr2(unsigned long x) native_write_cr2(x); } -static inline unsigned long read_cr3(void) +/* + * Careful! CR3 contains more than just an address. You probably want + * read_cr3_pa() instead. + */ +static inline unsigned long __read_cr3(void) { - return native_read_cr3(); + return __native_read_cr3(); } static inline void write_cr3(unsigned long x) diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 733bae07fb29..1f22bc277c45 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -109,6 +109,11 @@ memcpy_mcsafe(void *dst, const void *src, size_t cnt) return 0; } +#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +#define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1 +void memcpy_flushcache(void *dst, const void *src, size_t cnt); +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_X86_STRING_64_H */ diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 6136a18152af..2bd96b4df140 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -42,8 +42,7 @@ struct saved_context { set_debugreg((thread)->debugreg##register, register) /* routines for saving/restoring kernel state */ -extern int acpi_save_state_mem(void); -extern char core_restore_code; -extern char restore_registers; +extern char core_restore_code[]; +extern char restore_registers[]; #endif /* _ASM_X86_SUSPEND_64_H */ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index 27e9f9d769b8..2016962103df 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -29,11 +29,9 @@ struct cyc2ns_data { u32 cyc2ns_mul; u32 cyc2ns_shift; u64 cyc2ns_offset; - u32 __count; - /* u32 hole */ -}; /* 24 bytes -- do not grow */ +}; /* 16 bytes */ -extern struct cyc2ns_data *cyc2ns_read_begin(void); -extern void cyc2ns_read_end(struct cyc2ns_data *); +extern void cyc2ns_read_begin(struct cyc2ns_data *); +extern void cyc2ns_read_end(void); #endif /* _ASM_X86_TIMER_H */ diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h new file mode 100644 index 000000000000..f4a6ff352a0e --- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,14 @@ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include <linux/cpumask.h> + +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; +}; + +#endif /* _ARCH_X86_TLBBATCH_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 6ed9ea469b48..50ea3482e1d1 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -7,6 +7,7 @@ #include <asm/processor.h> #include <asm/cpufeature.h> #include <asm/special_insns.h> +#include <asm/smp.h> static inline void __invpcid(unsigned long pcid, unsigned long addr, unsigned long type) @@ -65,10 +66,14 @@ static inline void invpcid_flush_all_nonglobals(void) #endif struct tlb_state { -#ifdef CONFIG_SMP - struct mm_struct *active_mm; + /* + * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts + * are on. This means that it may not match current->active_mm, + * which will contain the previous user mm when we're in lazy TLB + * mode even if we've already switched back to swapper_pg_dir. + */ + struct mm_struct *loaded_mm; int state; -#endif /* * Access to this CR4 shadow and to H/W CR4 is protected by @@ -151,7 +156,7 @@ static inline void __native_flush_tlb(void) * back: */ preempt_disable(); - native_write_cr3(native_read_cr3()); + native_write_cr3(__native_read_cr3()); preempt_enable(); } @@ -220,84 +225,16 @@ static inline void __flush_tlb_one(unsigned long addr) * - flush_tlb_page(vma, vmaddr) flushes one page * - flush_tlb_range(vma, start, end) flushes a range of pages * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages - * - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus + * - flush_tlb_others(cpumask, info) flushes TLBs on other cpus * * ..but the i386 has somewhat limited tlb flushing capabilities, * and page-granular flushes are available only on i486 and up. */ - -#ifndef CONFIG_SMP - -/* "_up" is for UniProcessor. - * - * This is a helper for other header functions. *Not* intended to be called - * directly. All global TLB flushes need to either call this, or to bump the - * vm statistics themselves. - */ -static inline void __flush_tlb_up(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb(); -} - -static inline void flush_tlb_all(void) -{ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - __flush_tlb_all(); -} - -static inline void local_flush_tlb(void) -{ - __flush_tlb_up(); -} - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long addr) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_one(addr); -} - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void flush_tlb_mm_range(struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned long vmflag) -{ - if (mm == current->active_mm) - __flush_tlb_up(); -} - -static inline void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end) -{ -} - -static inline void reset_lazy_tlbstate(void) -{ -} - -static inline void flush_tlb_kernel_range(unsigned long start, - unsigned long end) -{ - flush_tlb_all(); -} - -#else /* SMP */ - -#include <asm/smp.h> +struct flush_tlb_info { + struct mm_struct *mm; + unsigned long start; + unsigned long end; +}; #define local_flush_tlb() __flush_tlb() @@ -307,29 +244,32 @@ static inline void flush_tlb_kernel_range(unsigned long start, flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) extern void flush_tlb_all(void); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) +{ + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); +} + void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, unsigned long end); + const struct flush_tlb_info *info); #define TLBSTATE_OK 1 #define TLBSTATE_LAZY 2 -static inline void reset_lazy_tlbstate(void) +static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm) { - this_cpu_write(cpu_tlbstate.state, 0); - this_cpu_write(cpu_tlbstate.active_mm, &init_mm); + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); } -#endif /* SMP */ +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); #ifndef CONFIG_PARAVIRT -#define flush_tlb_others(mask, mm, start, end) \ - native_flush_tlb_others(mask, mm, start, end) +#define flush_tlb_others(mask, info) \ + native_flush_tlb_others(mask, info) #endif #endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 68766b276d9e..476ea27f490b 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -319,10 +319,10 @@ do { \ #define __get_user_asm_u64(x, ptr, retval, errret) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ - asm volatile(ASM_STAC "\n" \ + asm volatile("\n" \ "1: movl %2,%%eax\n" \ "2: movl %3,%%edx\n" \ - "3: " ASM_CLAC "\n" \ + "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: mov %4,%0\n" \ " xorl %%eax,%%eax\n" \ @@ -331,7 +331,7 @@ do { \ ".previous\n" \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ - : "=r" (retval), "=A"(x) \ + : "=r" (retval), "=&A"(x) \ : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) @@ -565,7 +565,6 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long strncpy_from_user(char *dst, const char __user *src, long count); -extern __must_check long strlen_user(const char __user *str); extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); @@ -703,14 +702,15 @@ extern struct movsl_mask { #define unsafe_put_user(x, ptr, err_label) \ do { \ int __pu_err; \ - __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ if (unlikely(__pu_err)) goto err_label; \ } while (0) #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ - unsigned long __gu_val; \ + __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index c5504b9a472e..b16f6a1d8b26 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -171,6 +171,10 @@ unsigned long raw_copy_in_user(void __user *dst, const void __user *src, unsigne extern long __copy_user_nocache(void *dst, const void __user *src, unsigned size, int zerorest); +extern long __copy_user_flushcache(void *dst, const void __user *src, unsigned size); +extern void memcpy_page_flushcache(char *to, struct page *page, size_t offset, + size_t len); + static inline int __copy_from_user_inatomic_nocache(void *dst, const void __user *src, unsigned size) @@ -179,6 +183,13 @@ __copy_from_user_inatomic_nocache(void *dst, const void __user *src, return __copy_user_nocache(dst, src, size, 0); } +static inline int +__copy_from_user_flushcache(void *dst, const void __user *src, unsigned size) +{ + kasan_check_write(dst, size); + return __copy_user_flushcache(dst, src, size); +} + unsigned long copy_user_handle_tail(char *to, char *from, unsigned len); diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h index 6686820feae9..b5a32231abd8 100644 --- a/arch/x86/include/asm/uv/uv.h +++ b/arch/x86/include/asm/uv/uv.h @@ -1,6 +1,8 @@ #ifndef _ASM_X86_UV_UV_H #define _ASM_X86_UV_UV_H +#include <asm/tlbflush.h> + enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC}; struct cpumask; @@ -15,10 +17,7 @@ extern void uv_cpu_init(void); extern void uv_nmi_init(void); extern void uv_system_init(void); extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - unsigned int cpu); + const struct flush_tlb_info *info); #else /* X86_UV */ @@ -28,8 +27,8 @@ static inline int is_uv_hubless(void) { return 0; } static inline void uv_cpu_init(void) { } static inline void uv_system_init(void) { } static inline const struct cpumask * -uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, - unsigned long start, unsigned long end, unsigned int cpu) +uv_flush_tlb_others(const struct cpumask *cpumask, + const struct flush_tlb_info *info) { return cpumask; } #endif /* X86_UV */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index f6d20f6cca12..11071fcd630e 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -43,6 +43,7 @@ #include <asm/page.h> #include <asm/pgtable.h> +#include <asm/smap.h> #include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -50,6 +51,8 @@ #include <xen/interface/platform.h> #include <xen/interface/xen-mca.h> +struct xen_dm_op_buf; + /* * The hypercall asms have to meet several constraints: * - Work on 32- and 64-bit. @@ -214,10 +217,12 @@ privcmd_call(unsigned call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); + stac(); asm volatile("call *%[call]" : __HYPERCALL_5PARAM : [call] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); + clac(); return (long)__res; } @@ -474,9 +479,13 @@ HYPERVISOR_xenpmu_op(unsigned int op, void *arg) static inline int HYPERVISOR_dm_op( - domid_t dom, unsigned int nr_bufs, void *bufs) + domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs) { - return _hypercall3(int, dm_op, dom, nr_bufs, bufs); + int ret; + stac(); + ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs); + clac(); + return ret; } static inline void diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index 83b6e9a0dce4..da1489cb64dc 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -1,6 +1,6 @@ # UAPI Header export list include include/uapi/asm-generic/Kbuild.asm -genhdr-y += unistd_32.h -genhdr-y += unistd_64.h -genhdr-y += unistd_x32.h +generated-y += unistd_32.h +generated-y += unistd_64.h +generated-y += unistd_x32.h diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 432df4b1baec..127ddadee1a5 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -34,16 +34,10 @@ #define HV_X64_MSR_REFERENCE_TSC 0x40000021 /* - * There is a single feature flag that signifies the presence of the MSR - * that can be used to retrieve both the local APIC Timer frequency as - * well as the TSC frequency. + * There is a single feature flag that signifies if the partition has access + * to MSRs with local APIC and TSC frequencies. */ - -/* Local APIC timer frequency MSR (HV_X64_MSR_APIC_FREQUENCY) is available */ -#define HV_X64_MSR_APIC_FREQUENCY_AVAILABLE (1 << 11) - -/* TSC frequency MSR (HV_X64_MSR_TSC_FREQUENCY) is available */ -#define HV_X64_MSR_TSC_FREQUENCY_AVAILABLE (1 << 11) +#define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11) /* * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM @@ -73,6 +67,9 @@ */ #define HV_X64_MSR_STAT_PAGES_AVAILABLE (1 << 8) +/* Frequency MSRs available */ +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE (1 << 8) + /* Crash MSR available */ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) @@ -153,6 +150,12 @@ #define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9) /* + * HV_VP_SET available + */ +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11) + + +/* * Crash notification flag. */ #define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63) diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 567de50a4c2a..185f3d10c194 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -104,6 +104,8 @@ #define X86_CR4_OSFXSR _BITUL(X86_CR4_OSFXSR_BIT) #define X86_CR4_OSXMMEXCPT_BIT 10 /* enable unmasked SSE exceptions */ #define X86_CR4_OSXMMEXCPT _BITUL(X86_CR4_OSXMMEXCPT_BIT) +#define X86_CR4_LA57_BIT 12 /* enable 5-level page tables */ +#define X86_CR4_LA57 _BITUL(X86_CR4_LA57_BIT) #define X86_CR4_VMXE_BIT 13 /* enable VMX virtualization */ #define X86_CR4_VMXE _BITUL(X86_CR4_VMXE_BIT) #define X86_CR4_SMXE_BIT 14 /* enable safer mode (TXT) */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 4b994232cb57..a01892bdd61a 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -18,6 +18,7 @@ CFLAGS_REMOVE_pvclock.o = -pg CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg +CFLAGS_REMOVE_head64.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -29,6 +30,7 @@ OBJECT_FILES_NON_STANDARD_head_$(BITS).o := y OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o := y OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y OBJECT_FILES_NON_STANDARD_test_nx.o := y +OBJECT_FILES_NON_STANDARD_paravirt_patch_$(BITS).o := y # If instrumentation of this dir is enabled, boot hangs during first second. # Probably could be more selective here, but note that files related to irqs, diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile index 26b78d86f25a..85a9e17e0dbc 100644 --- a/arch/x86/kernel/acpi/Makefile +++ b/arch/x86/kernel/acpi/Makefile @@ -1,3 +1,5 @@ +OBJECT_FILES_NON_STANDARD_wakeup_$(BITS).o := y + obj-$(CONFIG_ACPI) += boot.o obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o obj-$(CONFIG_ACPI_APEI) += apei.o diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 8233a630280f..dde437f5d14f 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -167,7 +167,8 @@ static int __init ffh_cstate_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; - if (c->x86_vendor != X86_VENDOR_INTEL) + if (c->x86_vendor != X86_VENDOR_INTEL && + c->x86_vendor != X86_VENDOR_AMD) return -1; cpu_cstate_entry = alloc_percpu(struct cstate_entry); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c5b8f760473c..32e14d137416 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -409,8 +409,13 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, memcpy(insnbuf, replacement, a->replacementlen); insnbuf_sz = a->replacementlen; - /* 0xe8 is a relative jump; fix the offset. */ - if (*insnbuf == 0xe8 && a->replacementlen == 5) { + /* + * 0xe8 is a relative jump; fix the offset. + * + * Instruction length is checked before the opcode to avoid + * accessing uninitialized bytes for zero-length replacements. + */ + if (a->replacementlen == 5 && *insnbuf == 0xe8) { *(s32 *)(insnbuf + 1) += replacement - instr; DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx", *(s32 *)(insnbuf + 1), diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 815dd63f49d0..cc0e8bc0ea3f 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -704,6 +704,7 @@ static const struct dma_map_ops gart_dma_ops = { .alloc = gart_alloc_coherent, .free = gart_free_coherent, .mapping_error = gart_mapping_error, + .dma_supported = x86_dma_supported, }; static void gart_iommu_shutdown(void) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2d75faf743f2..98b3dd8cf2bf 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -54,6 +54,8 @@ #include <asm/mce.h> #include <asm/tsc.h> #include <asm/hypervisor.h> +#include <asm/cpu_device_id.h> +#include <asm/intel-family.h> unsigned int num_processors; @@ -545,6 +547,81 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); +#define DEADLINE_MODEL_MATCH_FUNC(model, func) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&func } + +#define DEADLINE_MODEL_MATCH_REV(model, rev) \ + { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)rev } + +static u32 hsx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x02: return 0x3a; /* EP */ + case 0x04: return 0x0f; /* EX */ + } + + return ~0U; +} + +static u32 bdx_deadline_rev(void) +{ + switch (boot_cpu_data.x86_mask) { + case 0x02: return 0x00000011; + case 0x03: return 0x0700000e; + case 0x04: return 0x0f00000c; + case 0x05: return 0x0e000003; + } + + return ~0U; +} + +static const struct x86_cpu_id deadline_match[] = { + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_HASWELL_X, hsx_deadline_rev), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_X, 0x0b000020), + DEADLINE_MODEL_MATCH_FUNC( INTEL_FAM6_BROADWELL_XEON_D, bdx_deadline_rev), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_X, 0x02000014), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_CORE, 0x22), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_ULT, 0x20), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_HASWELL_GT3E, 0x17), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_CORE, 0x25), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_BROADWELL_GT3E, 0x17), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_MOBILE, 0xb2), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_SKYLAKE_DESKTOP, 0xb2), + + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_MOBILE, 0x52), + DEADLINE_MODEL_MATCH_REV ( INTEL_FAM6_KABYLAKE_DESKTOP, 0x52), + + {}, +}; + +static void apic_check_deadline_errata(void) +{ + const struct x86_cpu_id *m = x86_match_cpu(deadline_match); + u32 rev; + + if (!m) + return; + + /* + * 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; + + if (boot_cpu_data.microcode >= rev) + return; + + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); + pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " + "please update microcode to version: 0x%x (or later)\n", rev); +} + /* * Setup the local APIC timer for this CPU. Copy the initialized values * of the boot CPU and register the clock event in the framework. @@ -563,6 +640,7 @@ static void setup_APIC_timer(void) levt->cpumask = cpumask_of(smp_processor_id()); if (this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) { + levt->name = "lapic-deadline"; levt->features &= ~(CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; @@ -1779,6 +1857,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; + apic_check_deadline_errata(); + if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); return; @@ -2201,23 +2281,32 @@ void default_init_apic_ldr(void) apic_write(APIC_LDR, val); } -int default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) +int default_cpu_mask_to_apicid(const struct cpumask *mask, + struct irq_data *irqdata, + unsigned int *apicid) { - unsigned int cpu; + unsigned int cpu = cpumask_first(mask); - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } + if (cpu >= nr_cpu_ids) + return -EINVAL; + *apicid = per_cpu(x86_cpu_to_apicid, cpu); + irq_data_update_effective_affinity(irqdata, cpumask_of(cpu)); + return 0; +} - if (likely(cpu < nr_cpu_ids)) { - *apicid = per_cpu(x86_cpu_to_apicid, cpu); - return 0; - } +int flat_cpu_mask_to_apicid(const struct cpumask *mask, + struct irq_data *irqdata, + unsigned int *apicid) - return -EINVAL; +{ + struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); + unsigned long cpu_mask = cpumask_bits(mask)[0] & APIC_ALL_CPUS; + + if (!cpu_mask) + return -EINVAL; + *apicid = (unsigned int)cpu_mask; + cpumask_bits(effmsk)[0] = cpu_mask; + return 0; } /* diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index a4d7ff20ed22..dedd5a41ba48 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -172,7 +172,7 @@ static struct apic apic_flat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, @@ -268,7 +268,7 @@ static struct apic apic_physflat __ro_after_init = { .get_apic_id = flat_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 2262eb6df796..6599f437b4ab 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -141,7 +141,7 @@ struct apic apic_noop __ro_after_init = { .get_apic_id = noop_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index e08fe2c8dd8c..2fda912219a6 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -267,7 +267,7 @@ static const struct apic apic_numachip1 __refconst = { .get_apic_id = numachip1_get_apic_id, .set_apic_id = numachip1_set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, @@ -318,7 +318,7 @@ static const struct apic apic_numachip2 __refconst = { .get_apic_id = numachip2_get_apic_id, .set_apic_id = numachip2_set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 56012010332c..456e45e8bf84 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -172,7 +172,7 @@ static struct apic apic_bigsmp __ro_after_init = { .get_apic_id = bigsmp_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single_phys, .send_IPI_mask = default_send_IPI_mask_sequence_phys, diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c index ae50d3454d78..56ccf9346b08 100644 --- a/arch/x86/kernel/apic/htirq.c +++ b/arch/x86/kernel/apic/htirq.c @@ -150,16 +150,27 @@ static const struct irq_domain_ops htirq_domain_ops = { .deactivate = htirq_domain_deactivate, }; -void arch_init_htirq_domain(struct irq_domain *parent) +void __init arch_init_htirq_domain(struct irq_domain *parent) { + struct fwnode_handle *fn; + if (disable_apic) return; - htirq_domain = irq_domain_add_tree(NULL, &htirq_domain_ops, NULL); + fn = irq_domain_alloc_named_fwnode("PCI-HT"); + if (!fn) + goto warn; + + htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL); + irq_domain_free_fwnode(fn); if (!htirq_domain) - pr_warn("failed to initialize irqdomain for HTIRQ.\n"); - else - htirq_domain->parent = parent; + goto warn; + + htirq_domain->parent = parent; + return; + +warn: + pr_warn("Failed to initialize irqdomain for HTIRQ.\n"); } int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 347bb9f65737..b4f5f73febdb 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1200,28 +1200,6 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); static struct irq_chip ioapic_chip, ioapic_ir_chip; -#ifdef CONFIG_X86_32 -static inline int IO_APIC_irq_trigger(int irq) -{ - int apic, idx, pin; - - for_each_ioapic_pin(apic, pin) { - idx = find_irq_entry(apic, pin, mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin, 0))) - return irq_trigger(idx); - } - /* - * nonexistent IRQs are edge default - */ - return 0; -} -#else -static inline int IO_APIC_irq_trigger(int irq) -{ - return 1; -} -#endif - static void __init setup_IO_APIC_irqs(void) { unsigned int ioapic, pin; @@ -2223,6 +2201,8 @@ static int mp_irqdomain_create(int ioapic) struct ioapic *ip = &ioapics[ioapic]; struct ioapic_domain_cfg *cfg = &ip->irqdomain_cfg; struct mp_ioapic_gsi *gsi_cfg = mp_ioapic_gsi_routing(ioapic); + struct fwnode_handle *fn; + char *name = "IO-APIC"; if (cfg->type == IOAPIC_DOMAIN_INVALID) return 0; @@ -2233,9 +2213,25 @@ static int mp_irqdomain_create(int ioapic) parent = irq_remapping_get_ir_irq_domain(&info); if (!parent) parent = x86_vector_domain; + else + name = "IO-APIC-IR"; + + /* Handle device tree enumerated APICs proper */ + if (cfg->dev) { + fn = of_node_to_fwnode(cfg->dev); + } else { + fn = irq_domain_alloc_named_id_fwnode(name, ioapic); + if (!fn) + return -ENOMEM; + } + + ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops, + (void *)(long)ioapic); + + /* Release fw handle if it was allocated above */ + if (!cfg->dev) + irq_domain_free_fwnode(fn); - ip->irqdomain = irq_domain_add_linear(cfg->dev, hwirqs, cfg->ops, - (void *)(long)ioapic); if (!ip->irqdomain) return -ENOMEM; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index c61aec7e65f4..9b18be764422 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -136,13 +136,20 @@ static struct msi_domain_info pci_msi_domain_info = { .handler_name = "edge", }; -void arch_init_msi_domain(struct irq_domain *parent) +void __init arch_init_msi_domain(struct irq_domain *parent) { + struct fwnode_handle *fn; + if (disable_apic) return; - msi_default_domain = pci_msi_create_irq_domain(NULL, - &pci_msi_domain_info, parent); + fn = irq_domain_alloc_named_fwnode("PCI-MSI"); + if (fn) { + msi_default_domain = + pci_msi_create_irq_domain(fn, &pci_msi_domain_info, + parent); + irq_domain_free_fwnode(fn); + } if (!msi_default_domain) pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n"); } @@ -167,9 +174,18 @@ static struct msi_domain_info pci_msi_ir_domain_info = { .handler_name = "edge", }; -struct irq_domain *arch_create_msi_irq_domain(struct irq_domain *parent) +struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, + const char *name, int id) { - return pci_msi_create_irq_domain(NULL, &pci_msi_ir_domain_info, parent); + struct fwnode_handle *fn; + struct irq_domain *d; + + fn = irq_domain_alloc_named_id_fwnode(name, id); + if (!fn) + return NULL; + d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); + irq_domain_free_fwnode(fn); + return d; } #endif @@ -221,13 +237,20 @@ static struct irq_domain *dmar_get_irq_domain(void) { static struct irq_domain *dmar_domain; static DEFINE_MUTEX(dmar_lock); + struct fwnode_handle *fn; mutex_lock(&dmar_lock); - if (dmar_domain == NULL) - dmar_domain = msi_create_irq_domain(NULL, &dmar_msi_domain_info, + if (dmar_domain) + goto out; + + fn = irq_domain_alloc_named_fwnode("DMAR-MSI"); + if (fn) { + dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info, x86_vector_domain); + irq_domain_free_fwnode(fn); + } +out: mutex_unlock(&dmar_lock); - return dmar_domain; } @@ -317,9 +340,10 @@ static struct msi_domain_info hpet_msi_domain_info = { struct irq_domain *hpet_create_irq_domain(int hpet_id) { - struct irq_domain *parent; - struct irq_alloc_info info; struct msi_domain_info *domain_info; + struct irq_domain *parent, *d; + struct irq_alloc_info info; + struct fwnode_handle *fn; if (x86_vector_domain == NULL) return NULL; @@ -340,7 +364,16 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id) else hpet_msi_controller.name = "IR-HPET-MSI"; - return msi_create_irq_domain(NULL, domain_info, parent); + fn = irq_domain_alloc_named_id_fwnode(hpet_msi_controller.name, + hpet_id); + if (!fn) { + kfree(domain_info); + return NULL; + } + + d = msi_create_irq_domain(fn, domain_info, parent); + irq_domain_free_fwnode(fn); + return d; } int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 2e8f7f048f4f..63287659adb6 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -102,7 +102,7 @@ static struct apic apic_default __ro_after_init = { .get_apic_id = default_get_apic_id, .set_apic_id = NULL, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index f3557a1eb562..b3af457ed667 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -103,7 +103,8 @@ static void free_apic_chip_data(struct apic_chip_data *data) } static int __assign_irq_vector(int irq, struct apic_chip_data *d, - const struct cpumask *mask) + const struct cpumask *mask, + struct irq_data *irqdata) { /* * NOTE! The local APIC isn't very good at handling @@ -141,7 +142,7 @@ static int __assign_irq_vector(int irq, struct apic_chip_data *d, /* * Clear the offline cpus from @vector_cpumask for searching * and verify whether the result overlaps with @mask. If true, - * then the call to apic->cpu_mask_to_apicid_and() will + * then the call to apic->cpu_mask_to_apicid() will * succeed as well. If not, no point in trying to find a * vector in this mask. */ @@ -221,34 +222,40 @@ success: * Cache destination APIC IDs into cfg->dest_apicid. This cannot fail * as we already established, that mask & d->domain & cpu_online_mask * is not empty. + * + * vector_searchmask is a subset of d->domain and has the offline + * cpus masked out. */ - BUG_ON(apic->cpu_mask_to_apicid_and(mask, d->domain, - &d->cfg.dest_apicid)); + cpumask_and(vector_searchmask, vector_searchmask, mask); + BUG_ON(apic->cpu_mask_to_apicid(vector_searchmask, irqdata, + &d->cfg.dest_apicid)); return 0; } static int assign_irq_vector(int irq, struct apic_chip_data *data, - const struct cpumask *mask) + const struct cpumask *mask, + struct irq_data *irqdata) { int err; unsigned long flags; raw_spin_lock_irqsave(&vector_lock, flags); - err = __assign_irq_vector(irq, data, mask); + err = __assign_irq_vector(irq, data, mask, irqdata); raw_spin_unlock_irqrestore(&vector_lock, flags); return err; } static int assign_irq_vector_policy(int irq, int node, struct apic_chip_data *data, - struct irq_alloc_info *info) + struct irq_alloc_info *info, + struct irq_data *irqdata) { if (info && info->mask) - return assign_irq_vector(irq, data, info->mask); + return assign_irq_vector(irq, data, info->mask, irqdata); if (node != NUMA_NO_NODE && - assign_irq_vector(irq, data, cpumask_of_node(node)) == 0) + assign_irq_vector(irq, data, cpumask_of_node(node), irqdata) == 0) return 0; - return assign_irq_vector(irq, data, apic->target_cpus()); + return assign_irq_vector(irq, data, apic->target_cpus(), irqdata); } static void clear_irq_vector(int irq, struct apic_chip_data *data) @@ -360,9 +367,17 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, irq_data->chip = &lapic_controller; irq_data->chip_data = data; irq_data->hwirq = virq + i; - err = assign_irq_vector_policy(virq + i, node, data, info); + err = assign_irq_vector_policy(virq + i, node, data, info, + irq_data); if (err) goto error; + /* + * If the apic destination mode is physical, then the + * effective affinity is restricted to a single target + * CPU. Mark the interrupt accordingly. + */ + if (!apic->irq_dest_mode) + irqd_set_single_target(irq_data); } return 0; @@ -405,7 +420,7 @@ int __init arch_probe_nr_irqs(void) } #ifdef CONFIG_X86_IO_APIC -static void init_legacy_irqs(void) +static void __init init_legacy_irqs(void) { int i, node = cpu_to_node(0); struct apic_chip_data *data; @@ -424,16 +439,21 @@ static void init_legacy_irqs(void) } } #else -static void init_legacy_irqs(void) { } +static inline void init_legacy_irqs(void) { } #endif int __init arch_early_irq_init(void) { + struct fwnode_handle *fn; + init_legacy_irqs(); - x86_vector_domain = irq_domain_add_tree(NULL, &x86_vector_domain_ops, - NULL); + fn = irq_domain_alloc_named_fwnode("VECTOR"); + BUG_ON(!fn); + x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops, + NULL); BUG_ON(x86_vector_domain == NULL); + irq_domain_free_fwnode(fn); irq_set_default_host(x86_vector_domain); arch_init_msi_domain(x86_vector_domain); @@ -529,11 +549,12 @@ static int apic_set_affinity(struct irq_data *irq_data, if (!cpumask_intersects(dest, cpu_online_mask)) return -EINVAL; - err = assign_irq_vector(irq, data, dest); + err = assign_irq_vector(irq, data, dest, irq_data); return err ? err : IRQ_SET_MASK_OK; } static struct irq_chip lapic_controller = { + .name = "APIC", .irq_ack = apic_ack_edge, .irq_set_affinity = apic_set_affinity, .irq_retrigger = apic_retrigger_irq, diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 5a35f208ed95..481237cb1544 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -4,6 +4,7 @@ #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/dmar.h> +#include <linux/irq.h> #include <linux/cpu.h> #include <asm/smp.h> @@ -104,35 +105,30 @@ static void x2apic_send_IPI_all(int vector) } static int -x2apic_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) +x2apic_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, + unsigned int *apicid) { + struct cpumask *effmsk = irq_data_get_effective_affinity_mask(irqdata); + unsigned int cpu; u32 dest = 0; u16 cluster; - int i; - - for_each_cpu_and(i, cpumask, andmask) { - if (!cpumask_test_cpu(i, cpu_online_mask)) - continue; - dest = per_cpu(x86_cpu_to_logical_apicid, i); - cluster = x2apic_cluster(i); - break; - } - if (!dest) + cpu = cpumask_first(mask); + if (cpu >= nr_cpu_ids) return -EINVAL; - for_each_cpu_and(i, cpumask, andmask) { - if (!cpumask_test_cpu(i, cpu_online_mask)) - continue; - if (cluster != x2apic_cluster(i)) + dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + cluster = x2apic_cluster(cpu); + + cpumask_clear(effmsk); + for_each_cpu(cpu, mask) { + if (cluster != x2apic_cluster(cpu)) continue; - dest |= per_cpu(x86_cpu_to_logical_apicid, i); + dest |= per_cpu(x86_cpu_to_logical_apicid, cpu); + cpumask_set_cpu(cpu, effmsk); } *apicid = dest; - return 0; } @@ -256,7 +252,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = x2apic_cpu_mask_to_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index ff111f05a314..3baf0c3dc875 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -127,7 +127,7 @@ static struct apic apic_x2apic_phys __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = x2apic_set_apic_id, - .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index b487b3a01615..0d57bb9079c9 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -526,27 +526,15 @@ static void uv_init_apic_ldr(void) } static int -uv_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask, - unsigned int *apicid) +uv_cpu_mask_to_apicid(const struct cpumask *mask, struct irq_data *irqdata, + unsigned int *apicid) { - int unsigned cpu; + int ret = default_cpu_mask_to_apicid(mask, irqdata, apicid); - /* - * We're using fixed IRQ delivery, can only return one phys APIC ID. - * May as well be the first. - */ - for_each_cpu_and(cpu, cpumask, andmask) { - if (cpumask_test_cpu(cpu, cpu_online_mask)) - break; - } - - if (likely(cpu < nr_cpu_ids)) { - *apicid = per_cpu(x86_cpu_to_apicid, cpu) | uv_apicid_hibits; - return 0; - } + if (!ret) + *apicid |= uv_apicid_hibits; - return -EINVAL; + return ret; } static unsigned int x2apic_get_apic_id(unsigned long x) @@ -614,7 +602,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .get_apic_id = x2apic_get_apic_id, .set_apic_id = set_apic_id, - .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = uv_cpu_mask_to_apicid, .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 52000010c62e..cdf82492b770 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -21,6 +21,7 @@ obj-y += common.o obj-y += rdrand.o obj-y += match.o obj-y += bugs.o +obj-$(CONFIG_CPU_FREQ) += aperfmperf.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c new file mode 100644 index 000000000000..d869c8671e36 --- /dev/null +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -0,0 +1,79 @@ +/* + * x86 APERF/MPERF KHz calculation for + * /sys/.../cpufreq/scaling_cur_freq + * + * Copyright (C) 2017 Intel Corp. + * Author: Len Brown <len.brown@intel.com> + * + * This file is licensed under GPLv2. + */ + +#include <linux/jiffies.h> +#include <linux/math64.h> +#include <linux/percpu.h> +#include <linux/smp.h> + +struct aperfmperf_sample { + unsigned int khz; + unsigned long jiffies; + u64 aperf; + u64 mperf; +}; + +static DEFINE_PER_CPU(struct aperfmperf_sample, samples); + +/* + * aperfmperf_snapshot_khz() + * On the current CPU, snapshot APERF, MPERF, and jiffies + * unless we already did it within 10ms + * calculate kHz, save snapshot + */ +static void aperfmperf_snapshot_khz(void *dummy) +{ + u64 aperf, aperf_delta; + u64 mperf, mperf_delta; + struct aperfmperf_sample *s = this_cpu_ptr(&samples); + + /* Don't bother re-computing within 10 ms */ + if (time_before(jiffies, s->jiffies + HZ/100)) + return; + + rdmsrl(MSR_IA32_APERF, aperf); + rdmsrl(MSR_IA32_MPERF, mperf); + + aperf_delta = aperf - s->aperf; + mperf_delta = mperf - s->mperf; + + /* + * There is no architectural guarantee that MPERF + * increments faster than we can read it. + */ + if (mperf_delta == 0) + return; + + /* + * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then + * khz = (cpu_khz * aperf_delta) / mperf_delta + */ + if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta) + s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); + else /* khz = aperf_delta / (mperf_delta / cpu_khz) */ + s->khz = div64_u64(aperf_delta, + div64_u64(mperf_delta, cpu_khz)); + s->jiffies = jiffies; + s->aperf = aperf; + s->mperf = mperf; +} + +unsigned int arch_freq_get_on_cpu(int cpu) +{ + if (!cpu_khz) + return 0; + + if (!static_cpu_has(X86_FEATURE_APERFMPERF)) + return 0; + + smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); + + return per_cpu(samples.khz, cpu); +} diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index a70fd61095f8..6f077445647a 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -255,6 +255,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) break; case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */ + case 11: /* GX1 with inverted Device ID */ #ifdef CONFIG_PCI { u32 vendor, device; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index f5af0cc7eb0d..9257bd9dc664 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -856,11 +856,13 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type, dentry = kernfs_mount(fs_type, flags, rdt_root, RDTGROUP_SUPER_MAGIC, NULL); if (IS_ERR(dentry)) - goto out_cdp; + goto out_destroy; static_branch_enable(&rdt_enable_key); goto out; +out_destroy: + kernfs_remove(kn_info); out_cdp: cdp_disable(); out: diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c index 9c632cb88546..10cec43aac38 100644 --- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c @@ -17,6 +17,8 @@ #include "mce-internal.h" +static BLOCKING_NOTIFIER_HEAD(mce_injector_chain); + static DEFINE_MUTEX(mce_chrdev_read_mutex); static char mce_helper[128]; @@ -345,24 +347,49 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, } } -static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off); +void mce_register_injector_chain(struct notifier_block *nb) +{ + blocking_notifier_chain_register(&mce_injector_chain, nb); +} +EXPORT_SYMBOL_GPL(mce_register_injector_chain); -void register_mce_write_callback(ssize_t (*fn)(struct file *filp, - const char __user *ubuf, - size_t usize, loff_t *off)) +void mce_unregister_injector_chain(struct notifier_block *nb) { - mce_write = fn; + blocking_notifier_chain_unregister(&mce_injector_chain, nb); } -EXPORT_SYMBOL_GPL(register_mce_write_callback); +EXPORT_SYMBOL_GPL(mce_unregister_injector_chain); static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, size_t usize, loff_t *off) { - if (mce_write) - return mce_write(filp, ubuf, usize, off); - else + struct mce m; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* + * There are some cases where real MSR reads could slip + * through. + */ + if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA)) + return -EIO; + + if ((unsigned long)usize > sizeof(struct mce)) + usize = sizeof(struct mce); + if (copy_from_user(&m, ubuf, usize)) + return -EFAULT; + + if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu)) return -EINVAL; + + /* + * Need to give user space some time to set everything up, + * so do it a jiffie or two later everywhere. + */ + schedule_timeout(2); + + blocking_notifier_call_chain(&mce_injector_chain, 0, &m); + + return usize; } static const struct file_operations mce_chrdev_ops = { @@ -388,9 +415,15 @@ static __init int dev_mcelog_init_device(void) /* register character device /dev/mcelog */ err = misc_register(&mce_chrdev_device); if (err) { - pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + if (err == -EBUSY) + /* Xen dom0 might have registered the device already. */ + pr_info("Unable to init device /dev/mcelog, already registered"); + else + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + return err; } + mce_register_decode_chain(&dev_mcelog_nb); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c index 99165b206df3..231ad23b24a9 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-inject.c +++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c @@ -10,23 +10,105 @@ * Authors: * Andi Kleen * Ying Huang + * + * The AMD part (from mce_amd_inj.c): a simple MCE injection facility + * for testing different aspects of the RAS code. This driver should be + * built as module so that it can be loaded on production kernels for + * testing purposes. + * + * This file may be distributed under the terms of the GNU General Public + * License version 2. + * + * Copyright (c) 2010-17: Borislav Petkov <bp@alien8.de> + * Advanced Micro Devices Inc. */ -#include <linux/uaccess.h> -#include <linux/module.h> -#include <linux/timer.h> + +#include <linux/cpu.h> +#include <linux/debugfs.h> #include <linux/kernel.h> -#include <linux/string.h> -#include <linux/fs.h> -#include <linux/preempt.h> -#include <linux/smp.h> +#include <linux/module.h> #include <linux/notifier.h> -#include <linux/kdebug.h> -#include <linux/cpu.h> -#include <linux/sched.h> -#include <linux/gfp.h> -#include <asm/mce.h> +#include <linux/pci.h> +#include <linux/uaccess.h> + +#include <asm/amd_nb.h> #include <asm/apic.h> +#include <asm/irq_vectors.h> +#include <asm/mce.h> #include <asm/nmi.h> +#include <asm/smp.h> + +#include "mce-internal.h" + +/* + * Collect all the MCi_XXX settings + */ +static struct mce i_mce; +static struct dentry *dfs_inj; + +static u8 n_banks; + +#define MAX_FLAG_OPT_SIZE 3 +#define NBCFG 0x44 + +enum injection_type { + SW_INJ = 0, /* SW injection, simply decode the error */ + HW_INJ, /* Trigger a #MC */ + DFR_INT_INJ, /* Trigger Deferred error interrupt */ + THR_INT_INJ, /* Trigger threshold interrupt */ + N_INJ_TYPES, +}; + +static const char * const flags_options[] = { + [SW_INJ] = "sw", + [HW_INJ] = "hw", + [DFR_INT_INJ] = "df", + [THR_INT_INJ] = "th", + NULL +}; + +/* Set default injection to SW_INJ */ +static enum injection_type inj_type = SW_INJ; + +#define MCE_INJECT_SET(reg) \ +static int inj_##reg##_set(void *data, u64 val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + m->reg = val; \ + return 0; \ +} + +MCE_INJECT_SET(status); +MCE_INJECT_SET(misc); +MCE_INJECT_SET(addr); +MCE_INJECT_SET(synd); + +#define MCE_INJECT_GET(reg) \ +static int inj_##reg##_get(void *data, u64 *val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + *val = m->reg; \ + return 0; \ +} + +MCE_INJECT_GET(status); +MCE_INJECT_GET(misc); +MCE_INJECT_GET(addr); +MCE_INJECT_GET(synd); + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); + +static void setup_inj_struct(struct mce *m) +{ + memset(m, 0, sizeof(struct mce)); + + m->cpuvendor = boot_cpu_data.x86_vendor; +} /* Update fake mce registers on current CPU. */ static void inject_mce(struct mce *m) @@ -143,7 +225,7 @@ static int raise_local(void) return ret; } -static void raise_mce(struct mce *m) +static void __maybe_unused raise_mce(struct mce *m) { int context = MCJ_CTX(m->inject_flags); @@ -198,55 +280,454 @@ static void raise_mce(struct mce *m) } } -/* Error injection interface */ -static ssize_t mce_write(struct file *filp, const char __user *ubuf, - size_t usize, loff_t *off) +static int mce_inject_raise(struct notifier_block *nb, unsigned long val, + void *data) { - struct mce m; + struct mce *m = (struct mce *)data; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - /* - * There are some cases where real MSR reads could slip - * through. - */ - if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA)) - return -EIO; + if (!m) + return NOTIFY_DONE; + + mutex_lock(&mce_inject_mutex); + raise_mce(m); + mutex_unlock(&mce_inject_mutex); + + return NOTIFY_DONE; +} + +static struct notifier_block inject_nb = { + .notifier_call = mce_inject_raise, +}; + +/* + * Caller needs to be make sure this cpu doesn't disappear + * from under us, i.e.: get_cpu/put_cpu. + */ +static int toggle_hw_mce_inject(unsigned int cpu, bool enable) +{ + u32 l, h; + int err; + + err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); + if (err) { + pr_err("%s: error reading HWCR\n", __func__); + return err; + } + + enable ? (l |= BIT(18)) : (l &= ~BIT(18)); + + err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); + if (err) + pr_err("%s: error writing HWCR\n", __func__); - if ((unsigned long)usize > sizeof(struct mce)) - usize = sizeof(struct mce); - if (copy_from_user(&m, ubuf, usize)) + return err; +} + +static int __set_inj(const char *buf) +{ + int i; + + for (i = 0; i < N_INJ_TYPES; i++) { + if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { + inj_type = i; + return 0; + } + } + return -EINVAL; +} + +static ssize_t flags_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE]; + int n; + + n = sprintf(buf, "%s\n", flags_options[inj_type]); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static ssize_t flags_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE], *__buf; + int err; + + if (cnt > MAX_FLAG_OPT_SIZE) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) return -EFAULT; - if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu)) + buf[cnt - 1] = 0; + + /* strip whitespace */ + __buf = strstrip(buf); + + err = __set_inj(__buf); + if (err) { + pr_err("%s: Invalid flags value: %s\n", __func__, __buf); + return err; + } + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations flags_fops = { + .read = flags_read, + .write = flags_write, + .llseek = generic_file_llseek, +}; + +/* + * On which CPU to inject? + */ +MCE_INJECT_GET(extcpu); + +static int inj_extcpu_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= nr_cpu_ids || !cpu_online(val)) { + pr_err("%s: Invalid CPU: %llu\n", __func__, val); return -EINVAL; + } + m->extcpu = val; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); + +static void trigger_mce(void *info) +{ + asm volatile("int $18"); +} + +static void trigger_dfr_int(void *info) +{ + asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); +} + +static void trigger_thr_int(void *info) +{ + asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); +} + +static u32 get_nbc_for_node(int node_id) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + u32 cores_per_node; + + cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); + + return cores_per_node * node_id; +} + +static void toggle_nb_mca_mst_cpu(u16 nid) +{ + struct amd_northbridge *nb; + struct pci_dev *F3; + u32 val; + int err; + + nb = node_to_amd_nb(nid); + if (!nb) + return; + + F3 = nb->misc; + if (!F3) + return; + + err = pci_read_config_dword(F3, NBCFG, &val); + if (err) { + pr_err("%s: Error reading F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); + return; + } + + if (val & BIT(27)) + return; + + pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", + __func__); + + val |= BIT(27); + err = pci_write_config_dword(F3, NBCFG, val); + if (err) + pr_err("%s: Error writing F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); +} + +static void prepare_msrs(void *info) +{ + struct mce m = *(struct mce *)info; + u8 b = m.bank; + + wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); + + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (m.inject_flags == DFR_INT_INJ) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr); + } else { + wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr); + } + + wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); + wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd); + } else { + wrmsrl(MSR_IA32_MCx_STATUS(b), m.status); + wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr); + wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); + } +} + +static void do_inject(void) +{ + u64 mcg_status = 0; + unsigned int cpu = i_mce.extcpu; + u8 b = i_mce.bank; + + rdtscll(i_mce.tsc); + + if (i_mce.misc) + i_mce.status |= MCI_STATUS_MISCV; + + if (i_mce.synd) + i_mce.status |= MCI_STATUS_SYNDV; + + if (inj_type == SW_INJ) { + mce_inject_log(&i_mce); + return; + } + + /* prep MCE global settings for the injection */ + mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; + + if (!(i_mce.status & MCI_STATUS_PCC)) + mcg_status |= MCG_STATUS_RIPV; /* - * Need to give user space some time to set everything up, - * so do it a jiffie or two later everywhere. + * Ensure necessary status bits for deferred errors: + * - MCx_STATUS[Deferred]: make sure it is a deferred error + * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC */ - schedule_timeout(2); + if (inj_type == DFR_INT_INJ) { + i_mce.status |= MCI_STATUS_DEFERRED; + i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); + } - mutex_lock(&mce_inject_mutex); - raise_mce(&m); - mutex_unlock(&mce_inject_mutex); - return usize; + /* + * For multi node CPUs, logging and reporting of bank 4 errors happens + * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for + * Fam10h and later BKDGs. + */ + if (static_cpu_has(X86_FEATURE_AMD_DCM) && + b == 4 && + boot_cpu_data.x86 < 0x17) { + toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); + cpu = get_nbc_for_node(amd_get_nb_id(cpu)); + } + + get_online_cpus(); + if (!cpu_online(cpu)) + goto err; + + toggle_hw_mce_inject(cpu, true); + + i_mce.mcgstatus = mcg_status; + i_mce.inject_flags = inj_type; + smp_call_function_single(cpu, prepare_msrs, &i_mce, 0); + + toggle_hw_mce_inject(cpu, false); + + switch (inj_type) { + case DFR_INT_INJ: + smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); + break; + case THR_INT_INJ: + smp_call_function_single(cpu, trigger_thr_int, NULL, 0); + break; + default: + smp_call_function_single(cpu, trigger_mce, NULL, 0); + } + +err: + put_online_cpus(); + +} + +/* + * This denotes into which bank we're injecting and triggers + * the injection, at the same time. + */ +static int inj_bank_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= n_banks) { + pr_err("Non-existent MCE bank: %llu\n", val); + return -EINVAL; + } + + m->bank = val; + do_inject(); + + return 0; +} + +MCE_INJECT_GET(bank); + +DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); + +static const char readme_msg[] = +"Description of the files and their usages:\n" +"\n" +"Note1: i refers to the bank number below.\n" +"Note2: See respective BKDGs for the exact bit definitions of the files below\n" +"as they mirror the hardware registers.\n" +"\n" +"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" +"\t attributes of the error which caused the MCE.\n" +"\n" +"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" +"\t used for error thresholding purposes and its validity is indicated by\n" +"\t MCi_STATUS[MiscV].\n" +"\n" +"synd:\t Set MCi_SYND: provide syndrome info about the error. Only valid on\n" +"\t Scalable MCA systems, and its validity is indicated by MCi_STATUS[SyndV].\n" +"\n" +"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" +"\t associated with the error.\n" +"\n" +"cpu:\t The CPU to inject the error on.\n" +"\n" +"bank:\t Specify the bank you want to inject the error into: the number of\n" +"\t banks in a processor varies and is family/model-specific, therefore, the\n" +"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" +"\t injection.\n" +"\n" +"flags:\t Injection type to be performed. Writing to this file will trigger a\n" +"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" +"\t for AMD processors.\n" +"\n" +"\t Allowed error injection types:\n" +"\t - \"sw\": Software error injection. Decode error to a human-readable \n" +"\t format only. Safe to use.\n" +"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" +"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" +"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" +"\t before injecting.\n" +"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" +"\t error APIC interrupt handler to handle the error if the feature is \n" +"\t is present in hardware. \n" +"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" +"\t APIC interrupt handler to handle the error. \n" +"\n"; + +static ssize_t +inj_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static const struct file_operations readme_fops = { + .read = inj_readme_read, +}; + +static struct dfs_node { + char *name; + struct dentry *d; + const struct file_operations *fops; + umode_t perm; +} dfs_fls[] = { + { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, +}; + +static int __init debugfs_init(void) +{ + unsigned int i; + u64 cap; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + n_banks = cap & MCG_BANKCNT_MASK; + + dfs_inj = debugfs_create_dir("mce-inject", NULL); + if (!dfs_inj) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { + dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, + dfs_fls[i].perm, + dfs_inj, + &i_mce, + dfs_fls[i].fops); + + if (!dfs_fls[i].d) + goto err_dfs_add; + } + + return 0; + +err_dfs_add: + while (i-- > 0) + debugfs_remove(dfs_fls[i].d); + + debugfs_remove(dfs_inj); + dfs_inj = NULL; + + return -ENODEV; } -static int inject_init(void) +static int __init inject_init(void) { + int err; + if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) return -ENOMEM; + + err = debugfs_init(); + if (err) { + free_cpumask_var(mce_inject_cpumask); + return err; + } + + register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify"); + mce_register_injector_chain(&inject_nb); + + setup_inj_struct(&i_mce); + pr_info("Machine check injector initialized\n"); - register_mce_write_callback(mce_write); - register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, - "mce_notify"); + return 0; } +static void __exit inject_exit(void) +{ + + mce_unregister_injector_chain(&inject_nb); + unregister_nmi_handler(NMI_LOCAL, "mce_notify"); + + debugfs_remove_recursive(dfs_inj); + dfs_inj = NULL; + + memset(&dfs_fls, 0, sizeof(dfs_fls)); + + free_cpumask_var(mce_inject_cpumask); +} + module_init(inject_init); -/* - * Cannot tolerate unloading currently because we cannot - * guarantee all openers of mce_chrdev will get a reference to us. - */ +module_exit(inject_exit); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 654ad0668d72..098530a93bb7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -100,7 +100,11 @@ static inline bool mce_cmp(struct mce *m1, struct mce *m2) extern struct device_attribute dev_attr_trigger; #ifdef CONFIG_X86_MCELOG_LEGACY -extern void mce_work_trigger(void); +void mce_work_trigger(void); +void mce_register_injector_chain(struct notifier_block *nb); +void mce_unregister_injector_chain(struct notifier_block *nb); #else static inline void mce_work_trigger(void) { } +static inline void mce_register_injector_chain(struct notifier_block *nb) { } +static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 5abd4bf73d6e..6dde0497efc7 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -499,16 +499,14 @@ static int mce_usable_address(struct mce *m) return 1; } -static bool memory_error(struct mce *m) +bool mce_is_memory_error(struct mce *m) { - struct cpuinfo_x86 *c = &boot_cpu_data; - - if (c->x86_vendor == X86_VENDOR_AMD) { + if (m->cpuvendor == X86_VENDOR_AMD) { /* ErrCodeExt[20:16] */ u8 xec = (m->status >> 16) & 0x1f; return (xec == 0x0 || xec == 0x8); - } else if (c->x86_vendor == X86_VENDOR_INTEL) { + } else if (m->cpuvendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes * @@ -529,6 +527,7 @@ static bool memory_error(struct mce *m) return false; } +EXPORT_SYMBOL_GPL(mce_is_memory_error); static bool cec_add_mce(struct mce *m) { @@ -536,7 +535,7 @@ static bool cec_add_mce(struct mce *m) return false; /* We eat only correctable DRAM errors with usable addresses. */ - if (memory_error(m) && + if (mce_is_memory_error(m) && !(m->status & MCI_STATUS_UC) && mce_usable_address(m)) if (!cec_add_elem(m->addr >> PAGE_SHIFT)) @@ -674,7 +673,6 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { bool error_seen = false; struct mce m; - int severity; int i; this_cpu_inc(mce_poll_count); @@ -711,11 +709,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) mce_read_aux(&m, i); - severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) - if (m.status & MCI_STATUS_ADDRV) - m.severity = severity; + m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); /* * Don't get the IP here because it's unlikely to @@ -1551,7 +1545,7 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) */ clear_bit(10, (unsigned long *)&mce_banks[4].ctl); } - if (c->x86 < 17 && cfg->bootlog < 0) { + if (c->x86 < 0x11 && cfg->bootlog < 0) { /* * Lots of broken BIOS around that don't clear them * by default and leave crap in there. Don't log: @@ -1833,7 +1827,8 @@ void mce_disable_bank(int bank) * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) * monarchtimeout is how long to wait for other CPUs on machine * check, or 0 to not wait - * mce=bootlog Log MCEs from before booting. Disabled by default on AMD. + * mce=bootlog Log MCEs from before booting. Disabled by default on AMD Fam10h + and older. * mce=nobootlog Don't log MCEs from before booting. * mce=bios_cmci_threshold Don't program the CMCI threshold * mce=recovery force enable memcpy_mcsafe() @@ -1913,12 +1908,13 @@ static void mce_disable_error_reporting(void) static void vendor_disable_error_reporting(void) { /* - * Don't clear on Intel CPUs. Some of these MSRs are socket-wide. + * Don't clear on Intel or AMD CPUs. Some of these MSRs are socket-wide. * Disabling them for just a single offlined CPU is bad, since it will * inhibit reporting for all shared resources on the socket like the * last level cache (LLC), the integrated memory controller (iMC), etc. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || + boot_cpu_data.x86_vendor == X86_VENDOR_AMD) return; mce_disable_error_reporting(); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 6e4a047e4b68..9e314bcf67cc 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -164,17 +164,48 @@ static void default_deferred_error_interrupt(void) } void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; -static void get_smca_bank_info(unsigned int bank) +static void smca_configure(unsigned int bank, unsigned int cpu) { - unsigned int i, hwid_mcatype, cpu = smp_processor_id(); + unsigned int i, hwid_mcatype; struct smca_hwid *s_hwid; - u32 high, instance_id; + u32 high, low; + u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank); + + /* Set appropriate bits in MCA_CONFIG */ + if (!rdmsr_safe(smca_config, &low, &high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + high |= BIT(0); + + /* + * SMCA sets the Deferred Error Interrupt type per bank. + * + * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us + * if the DeferredIntType bit field is available. + * + * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the + * high portion of the MSR). OS should set this to 0x1 to enable + * APIC based interrupt. First, check that no interrupt has been + * set. + */ + if ((low & BIT(5)) && !((high >> 5) & 0x3)) + high |= BIT(5); + + wrmsr(smca_config, low, high); + } /* Collect bank_info using CPU 0 for now. */ if (cpu) return; - if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &instance_id, &high)) { + if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { pr_warn("Failed to read MCA_IPID for bank %d\n", bank); return; } @@ -191,7 +222,7 @@ static void get_smca_bank_info(unsigned int bank) smca_get_name(s_hwid->bank_type)); smca_banks[bank].hwid = s_hwid; - smca_banks[bank].id = instance_id; + smca_banks[bank].id = low; smca_banks[bank].sysfs_id = s_hwid->count++; break; } @@ -433,7 +464,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, int offset, u32 misc_high) { unsigned int cpu = smp_processor_id(); - u32 smca_low, smca_high, smca_addr; + u32 smca_low, smca_high; struct threshold_block b; int new; @@ -457,51 +488,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, goto set_offset; } - smca_addr = MSR_AMD64_SMCA_MCx_CONFIG(bank); - - if (!rdmsr_safe(smca_addr, &smca_low, &smca_high)) { - /* - * OS is required to set the MCAX bit to acknowledge that it is - * now using the new MSR ranges and new registers under each - * bank. It also means that the OS will configure deferred - * errors in the new MCx_CONFIG register. If the bit is not set, - * uncorrectable errors will cause a system panic. - * - * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) - */ - smca_high |= BIT(0); - - /* - * SMCA logs Deferred Error information in MCA_DE{STAT,ADDR} - * registers with the option of additionally logging to - * MCA_{STATUS,ADDR} if MCA_CONFIG[LogDeferredInMcaStat] is set. - * - * This bit is usually set by BIOS to retain the old behavior - * for OSes that don't use the new registers. Linux supports the - * new registers so let's disable that additional logging here. - * - * MCA_CONFIG[LogDeferredInMcaStat] is bit 34 (bit 2 in the high - * portion of the MSR). - */ - smca_high &= ~BIT(2); - - /* - * SMCA sets the Deferred Error Interrupt type per bank. - * - * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us - * if the DeferredIntType bit field is available. - * - * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the - * high portion of the MSR). OS should set this to 0x1 to enable - * APIC based interrupt. First, check that no interrupt has been - * set. - */ - if ((smca_low & BIT(5)) && !((smca_high >> 5) & 0x3)) - smca_high |= BIT(5); - - wrmsr(smca_addr, smca_low, smca_high); - } - /* Gather LVT offset for thresholding: */ if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) goto out; @@ -530,7 +516,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) for (bank = 0; bank < mca_cfg.banks; ++bank) { if (mce_flags.smca) - get_smca_bank_info(bank); + smca_configure(bank, cpu); for (block = 0; block < NR_BLOCKS; ++block) { address = get_block_address(cpu, address, low, high, bank, block); @@ -755,37 +741,19 @@ out_err: } EXPORT_SYMBOL_GPL(umc_normaddr_to_sysaddr); -static void -__log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) +static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) { - u32 msr_status = msr_ops.status(bank); - u32 msr_addr = msr_ops.addr(bank); struct mce m; - u64 status; - - WARN_ON_ONCE(deferred_err && threshold_err); - - if (deferred_err && mce_flags.smca) { - msr_status = MSR_AMD64_SMCA_MCx_DESTAT(bank); - msr_addr = MSR_AMD64_SMCA_MCx_DEADDR(bank); - } - - rdmsrl(msr_status, status); - - if (!(status & MCI_STATUS_VAL)) - return; mce_setup(&m); m.status = status; + m.misc = misc; m.bank = bank; m.tsc = rdtsc(); - if (threshold_err) - m.misc = misc; - if (m.status & MCI_STATUS_ADDRV) { - rdmsrl(msr_addr, m.addr); + m.addr = addr; /* * Extract [55:<lsb>] where lsb is the least significant @@ -806,8 +774,6 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc) } mce_log(&m); - - wrmsrl(msr_status, 0); } static inline void __smp_deferred_error_interrupt(void) @@ -832,87 +798,126 @@ asmlinkage __visible void __irq_entry smp_trace_deferred_error_interrupt(void) exiting_ack_irq(); } -/* APIC interrupt handler for deferred errors */ -static void amd_deferred_error_interrupt(void) +/* + * Returns true if the logged error is deferred. False, otherwise. + */ +static inline bool +_log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) { - unsigned int bank; - u32 msr_status; - u64 status; + u64 status, addr = 0; - for (bank = 0; bank < mca_cfg.banks; ++bank) { - msr_status = (mce_flags.smca) ? MSR_AMD64_SMCA_MCx_DESTAT(bank) - : msr_ops.status(bank); + rdmsrl(msr_stat, status); + if (!(status & MCI_STATUS_VAL)) + return false; - rdmsrl(msr_status, status); + if (status & MCI_STATUS_ADDRV) + rdmsrl(msr_addr, addr); - if (!(status & MCI_STATUS_VAL) || - !(status & MCI_STATUS_DEFERRED)) - continue; + __log_error(bank, status, addr, misc); - __log_error(bank, true, false, 0); - break; - } + wrmsrl(msr_stat, 0); + + return status & MCI_STATUS_DEFERRED; } /* - * APIC Interrupt Handler + * We have three scenarios for checking for Deferred errors: + * + * 1) Non-SMCA systems check MCA_STATUS and log error if found. + * 2) SMCA systems check MCA_STATUS. If error is found then log it and also + * clear MCA_DESTAT. + * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and + * log it. */ +static void log_error_deferred(unsigned int bank) +{ + bool defrd; -/* - * threshold interrupt handler will service THRESHOLD_APIC_VECTOR. - * the interrupt goes off when error_count reaches threshold_limit. - * the handler will simply log mcelog w/ software defined bank number. - */ + defrd = _log_error_bank(bank, msr_ops.status(bank), + msr_ops.addr(bank), 0); -static void amd_threshold_interrupt(void) + if (!mce_flags.smca) + return; + + /* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */ + if (defrd) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return; + } + + /* + * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check + * for a valid error. + */ + _log_error_bank(bank, MSR_AMD64_SMCA_MCx_DESTAT(bank), + MSR_AMD64_SMCA_MCx_DEADDR(bank), 0); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) { - u32 low = 0, high = 0, address = 0; - unsigned int bank, block, cpu = smp_processor_id(); - struct thresh_restart tr; + unsigned int bank; - /* assume first bank caused it */ - for (bank = 0; bank < mca_cfg.banks; ++bank) { - if (!(per_cpu(bank_map, cpu) & (1 << bank))) - continue; - for (block = 0; block < NR_BLOCKS; ++block) { - address = get_block_address(cpu, address, low, high, bank, block); - if (!address) - break; + for (bank = 0; bank < mca_cfg.banks; ++bank) + log_error_deferred(bank); +} - if (rdmsr_safe(address, &low, &high)) - break; +static void log_error_thresholding(unsigned int bank, u64 misc) +{ + _log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc); +} - if (!(high & MASK_VALID_HI)) { - if (block) - continue; - else - break; - } +static void log_and_reset_block(struct threshold_block *block) +{ + struct thresh_restart tr; + u32 low = 0, high = 0; - if (!(high & MASK_CNTP_HI) || - (high & MASK_LOCKED_HI)) - continue; + if (!block) + return; - /* - * Log the machine check that caused the threshold - * event. - */ - if (high & MASK_OVERFLOW_HI) - goto log; - } - } - return; + if (rdmsr_safe(block->address, &low, &high)) + return; + + if (!(high & MASK_OVERFLOW_HI)) + return; -log: - __log_error(bank, false, true, ((u64)high << 32) | low); + /* Log the MCE which caused the threshold event. */ + log_error_thresholding(block->bank, ((u64)high << 32) | low); /* Reset threshold block after logging error. */ memset(&tr, 0, sizeof(tr)); - tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block]; + tr.b = block; threshold_restart_bank(&tr); } /* + * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt + * goes off when error_count reaches threshold_limit. + */ +static void amd_threshold_interrupt(void) +{ + struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL; + unsigned int bank, cpu = smp_processor_id(); + + for (bank = 0; bank < mca_cfg.banks; ++bank) { + if (!(per_cpu(bank_map, cpu) & (1 << bank))) + continue; + + first_block = per_cpu(threshold_banks, cpu)[bank]->blocks; + if (!first_block) + continue; + + /* + * The first block is also the head of the list. Check it first + * before iterating over the rest. + */ + log_and_reset_block(first_block); + list_for_each_entry_safe(block, tmp, &first_block->miscj, miscj) + log_and_reset_block(block); + } +} + +/* * Sysfs Interface */ @@ -1202,7 +1207,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) goto out; per_cpu(threshold_banks, cpu)[bank] = b; - atomic_inc(&b->cpus); + refcount_inc(&b->cpus); err = __threshold_add_blocks(b); @@ -1225,7 +1230,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank) per_cpu(threshold_banks, cpu)[bank] = b; if (is_shared_bank(bank)) { - atomic_set(&b->cpus, 1); + refcount_set(&b->cpus, 1); /* nb is already initialized, see above */ if (nb) { @@ -1289,7 +1294,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) goto free_out; if (is_shared_bank(bank)) { - if (!atomic_dec_and_test(&b->cpus)) { + if (!refcount_dec_and_test(&b->cpus)) { __threshold_remove_blocks(b); per_cpu(threshold_banks, cpu)[bank] = NULL; return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 45db4d2ebd01..21b185793c80 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -251,7 +251,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) #endif } -void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret) { struct ucode_cpu_info *uci; struct cpio_data cp; @@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax) } static enum ucode_state -load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size); +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size); int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) { @@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) if (!desc.mc) return -EINVAL; - ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax), - desc.data, desc.size); + ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size); if (ret != UCODE_OK) return -EINVAL; @@ -675,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, } static enum ucode_state -load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) +load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) { enum ucode_state ret; @@ -689,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size) #ifdef CONFIG_X86_32 /* save BSP's matching patch for early load */ - if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(cpu); + if (save) { + struct ucode_patch *p = find_patch(0); if (p) { memset(amd_ucode_patch, 0, PATCH_MAX_SIZE); memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), @@ -722,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); + bool bsp = c->cpu_index == boot_cpu_data.cpu_index; enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; /* reload ucode container only on the boot cpu */ - if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index) + if (!refresh_fw || !bsp) return UCODE_OK; if (c->x86 >= 0x15) @@ -743,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size); + ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index e53d3c909840..9cb98ee103db 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -290,6 +290,17 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) return (struct cpio_data){ NULL, 0, "" }; if (initrd_start) start = initrd_start; + } else { + /* + * The picture with physical addresses is a bit different: we + * need to get the *physical* address to which the ramdisk was + * relocated, i.e., relocated_ramdisk (not initrd_start) and + * since we're running from physical addresses, we need to access + * relocated_ramdisk through its *physical* address too. + */ + u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk); + if (*rr) + start = *rr; } return find_cpio_data(path, (void *)start, size, NULL); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index afdfd237b59f..59edbe9d4ccb 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -42,7 +42,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; /* Current microcode patch used in early patching on the APs. */ -struct microcode_intel *intel_ucode_patch; +static struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, unsigned int s2, unsigned int p2) @@ -166,7 +166,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size) static void save_microcode_patch(void *data, unsigned int size) { struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - struct ucode_patch *iter, *tmp, *p; + struct ucode_patch *iter, *tmp, *p = NULL; bool prev_found = false; unsigned int sig, pf; @@ -202,6 +202,18 @@ static void save_microcode_patch(void *data, unsigned int size) else list_add_tail(&p->plist, µcode_cache); } + + /* + * Save for early loading. On 32-bit, that needs to be a physical + * address as the APs are running from physical addresses, before + * paging has been enabled. + */ + if (p) { + if (IS_ENABLED(CONFIG_X86_32)) + intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + else + intel_ucode_patch = p->data; + } } static int microcode_sanity_check(void *mc, int print_err) @@ -607,6 +619,14 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; + /* + * initrd is going away, clear patch ptr. We will scan the microcode one + * last time before jettisoning and save a patch, if found. Then we will + * update that pointer too, with a stable patch address to use when + * resuming the cores. + */ + intel_ucode_patch = NULL; + if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 04cb8d34ccb8..70e717fccdd6 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -161,6 +161,15 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) } #endif +static unsigned long hv_get_tsc_khz(void) +{ + unsigned long freq; + + rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq); + + return freq / 1000; +} + static void __init ms_hyperv_init_platform(void) { int hv_host_info_eax; @@ -193,8 +202,15 @@ static void __init ms_hyperv_init_platform(void) hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF); } + if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { + x86_platform.calibrate_tsc = hv_get_tsc_khz; + x86_platform.calibrate_cpu = hv_get_tsc_khz; + } + #ifdef CONFIG_X86_LOCAL_APIC - if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) { + if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS && + ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { /* * Get the APIC frequency. */ diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 2bce84d91c2b..c5bb63be4ba1 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -807,10 +807,8 @@ void mtrr_save_state(void) if (!mtrr_enabled()) return; - get_online_cpus(); first_cpu = cpumask_first(cpu_online_mask); smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); - put_online_cpus(); } void set_mtrr_aps_delayed_init(void) diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 6df621ae62a7..218f79825b3c 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -2,7 +2,6 @@ #include <linux/timex.h> #include <linux/string.h> #include <linux/seq_file.h> -#include <linux/cpufreq.h> /* * Get CPU information for use by the procfs. @@ -76,14 +75,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (c->microcode) seq_printf(m, "microcode\t: 0x%x\n", c->microcode); - if (cpu_has(c, X86_FEATURE_TSC)) { - unsigned int freq = cpufreq_quick_get(cpu); - - if (!freq) - freq = cpu_khz; + if (cpu_has(c, X86_FEATURE_TSC)) seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - freq / 1000, (freq % 1000)); - } + cpu_khz / 1000, (cpu_khz % 1000)); /* Cache size */ if (c->x86_cache_size >= 0) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d78a586ba8dc..532da61d605c 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -20,10 +20,12 @@ #include <asm/setup.h> /* - * We organize the E820 table into two main data structures: + * We organize the E820 table into three main data structures: * * - 'e820_table_firmware': the original firmware version passed to us by the - * bootloader - not modified by the kernel. We use this to: + * bootloader - not modified by the kernel. It is composed of two parts: + * the first 128 E820 memory entries in boot_params.e820_table and the remaining + * (if any) entries of the SETUP_E820_EXT nodes. We use this to: * * - inform the user about the firmware's notion of memory layout * via /sys/firmware/memmap @@ -31,6 +33,14 @@ * - the hibernation code uses it to generate a kernel-independent MD5 * fingerprint of the physical memory layout of a system. * + * - 'e820_table_kexec': a slightly modified (by the kernel) firmware version + * passed to us by the bootloader - the major difference between + * e820_table_firmware[] and this one is that, the latter marks the setup_data + * list created by the EFI boot stub as reserved, so that kexec can reuse the + * setup_data information in the second kernel. Besides, e820_table_kexec[] + * might also be modified by the kexec itself to fake a mptable. + * We use this to: + * * - kexec, which is a bootloader in disguise, uses the original E820 * layout to pass to the kexec-ed kernel. This way the original kernel * can have a restricted E820 map while the kexec()-ed kexec-kernel @@ -46,9 +56,11 @@ * specific memory layout data during early bootup. */ static struct e820_table e820_table_init __initdata; +static struct e820_table e820_table_kexec_init __initdata; static struct e820_table e820_table_firmware_init __initdata; struct e820_table *e820_table __refdata = &e820_table_init; +struct e820_table *e820_table_kexec __refdata = &e820_table_kexec_init; struct e820_table *e820_table_firmware __refdata = &e820_table_firmware_init; /* For PCI or other memory-mapped resources */ @@ -470,9 +482,9 @@ u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum return __e820__range_update(e820_table, start, size, old_type, new_type); } -static u64 __init e820__range_update_firmware(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) +static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { - return __e820__range_update(e820_table_firmware, start, size, old_type, new_type); + return __e820__range_update(e820_table_kexec, start, size, old_type, new_type); } /* Remove a range of memory from the E820 table: */ @@ -546,9 +558,9 @@ void __init e820__update_table_print(void) e820__print_table("modified"); } -static void __init e820__update_table_firmware(void) +static void __init e820__update_table_kexec(void) { - e820__update_table(e820_table_firmware); + e820__update_table(e820_table_kexec); } #define MAX_GAP_END 0x100000000ull @@ -623,7 +635,7 @@ __init void e820__setup_pci_gap(void) /* * Called late during init, in free_initmem(). * - * Initial e820_table and e820_table_firmware are largish __initdata arrays. + * Initial e820_table and e820_table_kexec are largish __initdata arrays. * * Copy them to a (usually much smaller) dynamically allocated area that is * sized precisely after the number of e820 entries. @@ -643,6 +655,12 @@ __init void e820__reallocate_tables(void) memcpy(n, e820_table, size); e820_table = n; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_kexec->nr_entries; + n = kmalloc(size, GFP_KERNEL); + BUG_ON(!n); + memcpy(n, e820_table_kexec, size); + e820_table_kexec = n; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); @@ -669,6 +687,9 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len) __append_e820_table(extmap, entries); e820__update_table(e820_table); + memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec)); + memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); + early_memunmap(sdata, data_len); pr_info("e820: extended physical RAM map:\n"); e820__print_table("extended"); @@ -727,7 +748,7 @@ core_initcall(e820__register_nvs_regions); /* * Allocate the requested number of bytes with the requsted alignment * and return (the physical address) to the caller. Also register this - * range in the 'firmware' E820 table as a reserved range. + * range in the 'kexec' E820 table as a reserved range. * * This allows kexec to fake a new mptable, as if it came from the real * system. @@ -738,9 +759,9 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); if (addr) { - e820__range_update_firmware(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); - pr_info("e820: update e820_table_firmware for e820__memblock_alloc_reserved()\n"); - e820__update_table_firmware(); + e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + pr_info("e820: update e820_table_kexec for e820__memblock_alloc_reserved()\n"); + e820__update_table_kexec(); } return addr; @@ -923,13 +944,13 @@ 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); pa_data = data->next; early_memunmap(data, sizeof(*data)); } e820__update_table(e820_table); - - memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); + e820__update_table(e820_table_kexec); pr_info("extended physical RAM map:\n"); e820__print_table("reserve setup_data"); @@ -1062,6 +1083,7 @@ void __init e820__reserve_resources(void) res++; } + /* Expose the bootloader-provided memory layout to the sysfs. */ for (i = 0; i < e820_table_firmware->nr_entries; i++) { struct e820_entry *entry = e820_table_firmware->entries + i; @@ -1175,6 +1197,7 @@ void __init e820__memory_setup(void) who = x86_init.resources.memory_setup(); + memcpy(e820_table_kexec, e820_table, sizeof(*e820_table_kexec)); memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); pr_info("e820: BIOS-provided physical RAM map:\n"); diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 8e598a1ad986..6b91e2eb8d3f 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -125,7 +125,7 @@ void __init init_espfix_bsp(void) p4d_t *p4d; /* Install the espfix pud into the kernel page directory */ - pgd = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); p4d_populate(&init_mm, p4d, espfix_pud_page); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index c2f8dde3255c..d5d44c452624 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c) * Boot time FPU feature detection code: */ unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu; +EXPORT_SYMBOL_GPL(mxcsr_feature_mask); static void __init fpu__init_system_mxcsr(void) { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 0651e974dcb3..9bef1bbeba63 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -689,8 +689,12 @@ static inline void *alloc_tramp(unsigned long size) { return module_alloc(size); } -static inline void tramp_free(void *tramp) +static inline void tramp_free(void *tramp, int size) { + int npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + + set_memory_nx((unsigned long)tramp, npages); + set_memory_rw((unsigned long)tramp, npages); module_memfree(tramp); } #else @@ -699,7 +703,7 @@ static inline void *alloc_tramp(unsigned long size) { return NULL; } -static inline void tramp_free(void *tramp) { } +static inline void tramp_free(void *tramp, int size) { } #endif /* Defined as markers to the end of the ftrace default trampolines */ @@ -771,7 +775,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* Copy ftrace_caller onto the trampoline memory */ ret = probe_kernel_read(trampoline, (void *)start_offset, size); if (WARN_ON(ret < 0)) { - tramp_free(trampoline); + tramp_free(trampoline, *tramp_size); return 0; } @@ -797,7 +801,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* Are we pointing to the reference? */ if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) { - tramp_free(trampoline); + tramp_free(trampoline, *tramp_size); return 0; } @@ -839,7 +843,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops) unsigned long offset; unsigned long ip; unsigned int size; - int ret; + int ret, npages; if (ops->trampoline) { /* @@ -848,11 +852,14 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops) */ if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) return; + npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT; + set_memory_rw(ops->trampoline, npages); } else { ops->trampoline = create_trampoline(ops, &size); if (!ops->trampoline) return; ops->trampoline_size = size; + npages = PAGE_ALIGN(size) >> PAGE_SHIFT; } offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); @@ -863,6 +870,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops) /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); ret = update_ftrace_func(ip, new); + set_memory_ro(ops->trampoline, npages); /* The update should never fail */ WARN_ON(ret); @@ -939,7 +947,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) return; - tramp_free((void *)ops->trampoline); + tramp_free((void *)ops->trampoline, ops->trampoline_size); ops->trampoline = 0; } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 43b7002f44fb..46c3c73e7f43 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -33,17 +33,120 @@ /* * Manage page tables very early on. */ -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; -static unsigned int __initdata next_early_pgt = 2; +static unsigned int __initdata next_early_pgt; pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); +#define __head __section(.head.text) + +static void __head *fixup_pointer(void *ptr, unsigned long physaddr) +{ + return ptr - (void *)_text + (void *)physaddr; +} + +void __head __startup_64(unsigned long physaddr) +{ + unsigned long load_delta, *p; + pgdval_t *pgd; + p4dval_t *p4d; + pudval_t *pud; + pmdval_t *pmd, pmd_entry; + int i; + + /* Is the address too large? */ + if (physaddr >> MAX_PHYSMEM_BITS) + for (;;); + + /* + * Compute the delta between the address I am compiled to run at + * and the address I am actually running at. + */ + load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + + /* Is the address not 2M aligned? */ + if (load_delta & ~PMD_PAGE_MASK) + for (;;); + + /* Fixup the physical addresses in the page table */ + + pgd = fixup_pointer(&early_top_pgt, physaddr); + pgd[pgd_index(__START_KERNEL_map)] += load_delta; + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(&level4_kernel_pgt, physaddr); + p4d[511] += load_delta; + } + + pud = fixup_pointer(&level3_kernel_pgt, physaddr); + pud[510] += load_delta; + pud[511] += load_delta; + + pmd = fixup_pointer(level2_fixmap_pgt, physaddr); + pmd[506] += load_delta; + + /* + * Set up the identity mapping for the switchover. These + * entries should *NOT* have the global bit set! This also + * creates a bunch of nonsense entries but that is fine -- + * it avoids problems around wraparound. + */ + + pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) { + p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)p4d + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)p4d + _KERNPG_TABLE; + + i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; + p4d[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + p4d[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } else { + i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; + pgd[i + 0] = (pgdval_t)pud + _KERNPG_TABLE; + pgd[i + 1] = (pgdval_t)pud + _KERNPG_TABLE; + } + + i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; + pud[i + 0] = (pudval_t)pmd + _KERNPG_TABLE; + pud[i + 1] = (pudval_t)pmd + _KERNPG_TABLE; + + pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; + pmd_entry += physaddr; + + for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { + int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; + pmd[idx] = pmd_entry + i * PMD_SIZE; + } + + /* + * Fixup the kernel text+data virtual addresses. Note that + * we might write invalid pmds, when the kernel is relocated + * cleanup_highmap() fixes this up along with the mappings + * beyond _end. + */ + + pmd = fixup_pointer(level2_kernel_pgt, physaddr); + for (i = 0; i < PTRS_PER_PMD; i++) { + if (pmd[i] & _PAGE_PRESENT) + pmd[i] += load_delta; + } + + /* Fixup phys_base */ + p = fixup_pointer(&phys_base, physaddr); + *p += load_delta; +} + /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) { - memset(early_level4_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); + memset(early_top_pgt, 0, sizeof(pgd_t)*(PTRS_PER_PGD-1)); next_early_pgt = 0; - write_cr3(__pa_nodebug(early_level4_pgt)); + write_cr3(__pa_nodebug(early_top_pgt)); } /* Create a new PMD entry */ @@ -51,15 +154,16 @@ int __init early_make_pgtable(unsigned long address) { unsigned long physaddr = address - __PAGE_OFFSET; pgdval_t pgd, *pgd_p; + p4dval_t p4d, *p4d_p; pudval_t pud, *pud_p; pmdval_t pmd, *pmd_p; /* Invalid address or early pgt is done ? */ - if (physaddr >= MAXMEM || read_cr3() != __pa_nodebug(early_level4_pgt)) + if (physaddr >= MAXMEM || read_cr3_pa() != __pa_nodebug(early_top_pgt)) return -1; again: - pgd_p = &early_level4_pgt[pgd_index(address)].pgd; + pgd_p = &early_top_pgt[pgd_index(address)].pgd; pgd = *pgd_p; /* @@ -67,8 +171,25 @@ again: * critical -- __PAGE_OFFSET would point us back into the dynamic * range and we might end up looping forever... */ - if (pgd) - pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + p4d_p = pgd_p; + else if (pgd) + p4d_p = (p4dval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); + else { + if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { + reset_early_page_tables(); + goto again; + } + + p4d_p = (p4dval_t *)early_dynamic_pgts[next_early_pgt++]; + memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); + *pgd_p = (pgdval_t)p4d_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + } + p4d_p += p4d_index(address); + p4d = *p4d_p; + + if (p4d) + pud_p = (pudval_t *)((p4d & PTE_PFN_MASK) + __START_KERNEL_map - phys_base); else { if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) { reset_early_page_tables(); @@ -77,7 +198,7 @@ again: pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++]; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - *pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; + *p4d_p = (p4dval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } pud_p += pud_index(address); pud = *pud_p; @@ -156,7 +277,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) clear_bss(); - clear_page(init_level4_pgt); + clear_page(init_top_pgt); kasan_early_init(); @@ -171,8 +292,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - /* set init_level4_pgt kernel high mapping*/ - init_level4_pgt[511] = early_level4_pgt[511]; + /* set init_top_pgt kernel high mapping*/ + init_top_pgt[511] = early_top_pgt[511]; x86_64_start_reservations(real_mode_data); } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ac9d327d2e42..6225550883df 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -37,10 +37,11 @@ * */ +#define p4d_index(x) (((x) >> P4D_SHIFT) & (PTRS_PER_P4D-1)) #define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -L4_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) -L4_START_KERNEL = pgd_index(__START_KERNEL_map) +PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE) +PGD_START_KERNEL = pgd_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) .text @@ -72,101 +73,12 @@ startup_64: /* Sanitize CPU configuration */ call verify_cpu - /* - * Compute the delta between the address I am compiled to run at and the - * address I am actually running at. - */ - leaq _text(%rip), %rbp - subq $_text - __START_KERNEL_map, %rbp - - /* Is the address not 2M aligned? */ - testl $~PMD_PAGE_MASK, %ebp - jnz bad_address - - /* - * Is the address too large? - */ - leaq _text(%rip), %rax - shrq $MAX_PHYSMEM_BITS, %rax - jnz bad_address - - /* - * Fixup the physical addresses in the page table - */ - addq %rbp, early_level4_pgt + (L4_START_KERNEL*8)(%rip) - - addq %rbp, level3_kernel_pgt + (510*8)(%rip) - addq %rbp, level3_kernel_pgt + (511*8)(%rip) - - addq %rbp, level2_fixmap_pgt + (506*8)(%rip) - - /* - * Set up the identity mapping for the switchover. These - * entries should *NOT* have the global bit set! This also - * creates a bunch of nonsense entries but that is fine -- - * it avoids problems around wraparound. - */ leaq _text(%rip), %rdi - leaq early_level4_pgt(%rip), %rbx - - movq %rdi, %rax - shrq $PGDIR_SHIFT, %rax - - leaq (PAGE_SIZE + _KERNPG_TABLE)(%rbx), %rdx - movq %rdx, 0(%rbx,%rax,8) - movq %rdx, 8(%rbx,%rax,8) - - addq $PAGE_SIZE, %rdx - movq %rdi, %rax - shrq $PUD_SHIFT, %rax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - incl %eax - andl $(PTRS_PER_PUD-1), %eax - movq %rdx, PAGE_SIZE(%rbx,%rax,8) - - addq $PAGE_SIZE * 2, %rbx - movq %rdi, %rax - shrq $PMD_SHIFT, %rdi - addq $(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL), %rax - leaq (_end - 1)(%rip), %rcx - shrq $PMD_SHIFT, %rcx - subq %rdi, %rcx - incl %ecx - -1: - andq $(PTRS_PER_PMD - 1), %rdi - movq %rax, (%rbx,%rdi,8) - incq %rdi - addq $PMD_SIZE, %rax - decl %ecx - jnz 1b - - test %rbp, %rbp - jz .Lskip_fixup + pushq %rsi + call __startup_64 + popq %rsi - /* - * Fixup the kernel text+data virtual addresses. Note that - * we might write invalid pmds, when the kernel is relocated - * cleanup_highmap() fixes this up along with the mappings - * beyond _end. - */ - leaq level2_kernel_pgt(%rip), %rdi - leaq PAGE_SIZE(%rdi), %r8 - /* See if it is a valid page table entry */ -1: testb $_PAGE_PRESENT, 0(%rdi) - jz 2f - addq %rbp, 0(%rdi) - /* Go to the next page */ -2: addq $8, %rdi - cmp %r8, %rdi - jne 1b - - /* Fixup phys_base */ - addq %rbp, phys_base(%rip) - -.Lskip_fixup: - movq $(early_level4_pgt - __START_KERNEL_map), %rax + movq $(early_top_pgt - __START_KERNEL_map), %rax jmp 1f ENTRY(secondary_startup_64) /* @@ -186,14 +98,17 @@ ENTRY(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu - movq $(init_level4_pgt - __START_KERNEL_map), %rax + movq $(init_top_pgt - __START_KERNEL_map), %rax 1: - /* Enable PAE mode and PGE */ + /* Enable PAE mode, PGE and LA57 */ movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx +#ifdef CONFIG_X86_5LEVEL + orl $X86_CR4_LA57, %ecx +#endif movq %rcx, %cr4 - /* Setup early boot stage 4 level pagetables. */ + /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax movq %rax, %cr3 @@ -417,9 +332,13 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_level4_pgt) +NEXT_PAGE(early_top_pgt) .fill 511,8,0 +#ifdef CONFIG_X86_5LEVEL + .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#else .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -427,14 +346,14 @@ NEXT_PAGE(early_dynamic_pgts) .data #ifndef CONFIG_XEN -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .fill 512,8,0 #else -NEXT_PAGE(init_level4_pgt) +NEXT_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_PAGE_OFFSET*8, 0 + .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE - .org init_level4_pgt + L4_START_KERNEL*8, 0 + .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE @@ -448,6 +367,12 @@ NEXT_PAGE(level2_ident_pgt) PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #endif +#ifdef CONFIG_X86_5LEVEL +NEXT_PAGE(level4_kernel_pgt) + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE +#endif + NEXT_PAGE(level3_kernel_pgt) .fill L3_START_KERNEL,8,0 /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 89ff7af2de50..16f82a3aaec7 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -285,7 +285,7 @@ static void hpet_legacy_clockevent_register(void) * Start hpet with the boot cpu mask and make it * global after the IO_APIC has been initialized. */ - hpet_clockevent.cpumask = cpumask_of(smp_processor_id()); + hpet_clockevent.cpumask = cpumask_of(boot_cpu_data.cpu_index); clockevents_config_and_register(&hpet_clockevent, hpet_freq, HPET_MIN_PROG_DELTA, 0x7FFFFFFF); global_clock_event = &hpet_clockevent; diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index f34fe7444836..4aa03c5a14c9 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -432,84 +432,12 @@ int check_irq_vectors_for_cpu_disable(void) /* A cpu has been removed from cpu_online_mask. Reset irq affinities. */ void fixup_irqs(void) { - unsigned int irq, vector; - static int warned; + unsigned int irr, vector; struct irq_desc *desc; struct irq_data *data; struct irq_chip *chip; - int ret; - for_each_irq_desc(irq, desc) { - int break_affinity = 0; - int set_affinity = 1; - const struct cpumask *affinity; - - if (!desc) - continue; - if (irq == 2) - continue; - - /* interrupt's are disabled at this point */ - raw_spin_lock(&desc->lock); - - data = irq_desc_get_irq_data(desc); - affinity = irq_data_get_affinity_mask(data); - if (!irq_has_action(irq) || irqd_is_per_cpu(data) || - cpumask_subset(affinity, cpu_online_mask)) { - raw_spin_unlock(&desc->lock); - continue; - } - - /* - * Complete the irq move. This cpu is going down and for - * non intr-remapping case, we can't wait till this interrupt - * arrives at this cpu before completing the irq move. - */ - irq_force_complete_move(desc); - - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - break_affinity = 1; - affinity = cpu_online_mask; - } - - chip = irq_data_get_irq_chip(data); - /* - * The interrupt descriptor might have been cleaned up - * already, but it is not yet removed from the radix tree - */ - if (!chip) { - raw_spin_unlock(&desc->lock); - continue; - } - - if (!irqd_can_move_in_process_context(data) && chip->irq_mask) - chip->irq_mask(data); - - if (chip->irq_set_affinity) { - ret = chip->irq_set_affinity(data, affinity, true); - if (ret == -ENOSPC) - pr_crit("IRQ %d set affinity failed because there are no available vectors. The device assigned to this IRQ is unstable.\n", irq); - } else { - if (!(warned++)) - set_affinity = 0; - } - - /* - * We unmask if the irq was not marked masked by the - * core code. That respects the lazy irq disable - * behaviour. - */ - if (!irqd_can_move_in_process_context(data) && - !irqd_irq_masked(data) && chip->irq_unmask) - chip->irq_unmask(data); - - raw_spin_unlock(&desc->lock); - - if (break_affinity && set_affinity) - pr_notice("Broke affinity for irq %i\n", irq); - else if (!set_affinity) - pr_notice("Cannot set affinity for irq %i\n", irq); - } + irq_migrate_all_off_this_cpu(); /* * We can remove mdelay() and then send spuriuous interrupts to @@ -528,8 +456,6 @@ void fixup_irqs(void) * nothing else will touch it. */ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { - unsigned int irr; - if (IS_ERR_OR_NULL(__this_cpu_read(vector_irq[vector]))) continue; diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index c37bd0f39c70..ab4f491da2a9 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry, void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { - get_online_cpus(); mutex_lock(&text_mutex); __jump_label_transform(entry, type, NULL, 0); mutex_unlock(&text_mutex); - put_online_cpus(); } static enum { diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 9d7fd5e6689a..fb095ba0c02f 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -100,14 +100,14 @@ static int setup_e820_entries(struct boot_params *params) { unsigned int nr_e820_entries; - nr_e820_entries = e820_table_firmware->nr_entries; + nr_e820_entries = e820_table_kexec->nr_entries; /* TODO: Pass entries more than E820_MAX_ENTRIES_ZEROPAGE in bootparams setup data */ if (nr_e820_entries > E820_MAX_ENTRIES_ZEROPAGE) nr_e820_entries = E820_MAX_ENTRIES_ZEROPAGE; params->e820_entries = nr_e820_entries; - memcpy(¶ms->e820_table, &e820_table_firmware->entries, nr_e820_entries*sizeof(struct e820_entry)); + memcpy(¶ms->e820_table, &e820_table_kexec->entries, nr_e820_entries*sizeof(struct e820_entry)); return 0; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 5b2bbfbb3712..6b877807598b 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -52,6 +52,7 @@ #include <linux/ftrace.h> #include <linux/frame.h> #include <linux/kasan.h> +#include <linux/moduleloader.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -417,6 +418,14 @@ static void prepare_boost(struct kprobe *p, struct insn *insn) } } +/* Recover page to RW mode before releasing it */ +void free_insn_page(void *page) +{ + set_memory_nx((unsigned long)page & PAGE_MASK, 1); + set_memory_rw((unsigned long)page & PAGE_MASK, 1); + module_memfree(page); +} + static int arch_copy_kprobe(struct kprobe *p) { struct insn insn; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 901c640d152f..69ea0bc1cfa3 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -28,6 +28,7 @@ #include <linux/kdebug.h> #include <linux/kallsyms.h> #include <linux/ftrace.h> +#include <linux/frame.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -94,6 +95,7 @@ static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) } asm ( + "optprobe_template_func:\n" ".global optprobe_template_entry\n" "optprobe_template_entry:\n" #ifdef CONFIG_X86_64 @@ -131,7 +133,12 @@ asm ( " popf\n" #endif ".global optprobe_template_end\n" - "optprobe_template_end:\n"); + "optprobe_template_end:\n" + ".type optprobe_template_func, @function\n" + ".size optprobe_template_func, .-optprobe_template_func\n"); + +void optprobe_template_func(void); +STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_MOVE_IDX \ ((long)&optprobe_template_val - (long)&optprobe_template_entry) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index da5c09789984..43e10d6fdbed 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token) */ rcu_irq_exit(); native_safe_halt(); - rcu_irq_enter(); local_irq_disable(); + rcu_irq_enter(); } } if (!n.halted) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index d4a15831ac58..a870910c8565 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -22,24 +22,25 @@ #include <asm/syscalls.h> /* context.lock is held for us, so we don't need any locking. */ -static void flush_ldt(void *current_mm) +static void flush_ldt(void *__mm) { + struct mm_struct *mm = __mm; mm_context_t *pc; - if (current->active_mm != current_mm) + if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; - pc = ¤t->active_mm->context; - set_ldt(pc->ldt->entries, pc->ldt->size); + pc = &mm->context; + set_ldt(pc->ldt->entries, pc->ldt->nr_entries); } /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */ -static struct ldt_struct *alloc_ldt_struct(unsigned int size) +static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) { struct ldt_struct *new_ldt; unsigned int alloc_size; - if (size > LDT_ENTRIES) + if (num_entries > LDT_ENTRIES) return NULL; new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL); @@ -47,7 +48,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct)); - alloc_size = size * LDT_ENTRY_SIZE; + alloc_size = num_entries * LDT_ENTRY_SIZE; /* * Xen is very picky: it requires a page-aligned LDT that has no @@ -65,14 +66,14 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int size) return NULL; } - new_ldt->size = size; + new_ldt->nr_entries = num_entries; return new_ldt; } /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { - paravirt_alloc_ldt(ldt->entries, ldt->size); + paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } /* context.lock is held */ @@ -91,8 +92,8 @@ static void free_ldt_struct(struct ldt_struct *ldt) if (likely(!ldt)) return; - paravirt_free_ldt(ldt->entries, ldt->size); - if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE) + paravirt_free_ldt(ldt->entries, ldt->nr_entries); + if (ldt->nr_entries * LDT_ENTRY_SIZE > PAGE_SIZE) vfree_atomic(ldt->entries); else free_page((unsigned long)ldt->entries); @@ -122,14 +123,14 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) goto out_unlock; } - new_ldt = alloc_ldt_struct(old_mm->context.ldt->size); + new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { retval = -ENOMEM; goto out_unlock; } memcpy(new_ldt->entries, old_mm->context.ldt->entries, - new_ldt->size * LDT_ENTRY_SIZE); + new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); mm->context.ldt = new_ldt; @@ -152,9 +153,9 @@ void destroy_context_ldt(struct mm_struct *mm) static int read_ldt(void __user *ptr, unsigned long bytecount) { - int retval; - unsigned long size; struct mm_struct *mm = current->mm; + unsigned long entries_size; + int retval; mutex_lock(&mm->context.lock); @@ -166,18 +167,18 @@ static int read_ldt(void __user *ptr, unsigned long bytecount) if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES) bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES; - size = mm->context.ldt->size * LDT_ENTRY_SIZE; - if (size > bytecount) - size = bytecount; + entries_size = mm->context.ldt->nr_entries * LDT_ENTRY_SIZE; + if (entries_size > bytecount) + entries_size = bytecount; - if (copy_to_user(ptr, mm->context.ldt->entries, size)) { + if (copy_to_user(ptr, mm->context.ldt->entries, entries_size)) { retval = -EFAULT; goto out_unlock; } - if (size != bytecount) { + if (entries_size != bytecount) { /* Zero-fill the rest and pretend we read bytecount bytes. */ - if (clear_user(ptr + size, bytecount - size)) { + if (clear_user(ptr + entries_size, bytecount - entries_size)) { retval = -EFAULT; goto out_unlock; } @@ -208,7 +209,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; struct ldt_struct *new_ldt, *old_ldt; - unsigned int oldsize, newsize; + unsigned int old_nr_entries, new_nr_entries; struct user_desc ldt_info; struct desc_struct ldt; int error; @@ -247,17 +248,18 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) mutex_lock(&mm->context.lock); - old_ldt = mm->context.ldt; - oldsize = old_ldt ? old_ldt->size : 0; - newsize = max(ldt_info.entry_number + 1, oldsize); + old_ldt = mm->context.ldt; + old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; + new_nr_entries = max(ldt_info.entry_number + 1, old_nr_entries); error = -ENOMEM; - new_ldt = alloc_ldt_struct(newsize); + new_ldt = alloc_ldt_struct(new_nr_entries); if (!new_ldt) goto out_unlock; if (old_ldt) - memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE); + memcpy(new_ldt->entries, old_ldt->entries, old_nr_entries * LDT_ENTRY_SIZE); + new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 6f5ca4ebe6e5..cb0a30473c23 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -347,7 +347,7 @@ void machine_kexec(struct kimage *image) void arch_crash_save_vmcoreinfo(void) { VMCOREINFO_NUMBER(phys_base); - VMCOREINFO_SYMBOL(init_level4_pgt); + VMCOREINFO_SYMBOL(init_top_pgt); #ifdef CONFIG_NUMA VMCOREINFO_SYMBOL(node_data); diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c index 6d9582ec0324..d27f8d84c4ff 100644 --- a/arch/x86/kernel/nmi_selftest.c +++ b/arch/x86/kernel/nmi_selftest.c @@ -78,7 +78,7 @@ static void __init test_nmi_ipi(struct cpumask *mask) /* Don't wait longer than a second */ timeout = USEC_PER_SEC; - while (!cpumask_empty(mask) && timeout--) + while (!cpumask_empty(mask) && --timeout) udelay(1); /* What happens if we timeout, do we still unregister?? */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 3586996fc50d..bc0a849589bb 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -391,7 +391,7 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, - .read_cr3 = native_read_cr3, + .read_cr3 = __native_read_cr3, .write_cr3 = native_write_cr3, .flush_tlb_user = native_flush_tlb, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index fda7867046d0..5286a4a92cf7 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -50,6 +50,8 @@ #include <asm/x86_init.h> #include <asm/iommu_table.h> +#define CALGARY_MAPPING_ERROR 0 + #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT int use_calgary __read_mostly = 1; #else @@ -252,7 +254,7 @@ static unsigned long iommu_range_alloc(struct device *dev, if (panic_on_overflow) panic("Calgary: fix the allocator.\n"); else - return DMA_ERROR_CODE; + return CALGARY_MAPPING_ERROR; } } @@ -272,10 +274,10 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl, entry = iommu_range_alloc(dev, tbl, npages); - if (unlikely(entry == DMA_ERROR_CODE)) { + if (unlikely(entry == CALGARY_MAPPING_ERROR)) { pr_warn("failed to allocate %u pages in iommu %p\n", npages, tbl); - return DMA_ERROR_CODE; + return CALGARY_MAPPING_ERROR; } /* set the return dma address */ @@ -295,7 +297,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, unsigned long flags; /* were we called with bad_dma_address? */ - badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE); + badend = CALGARY_MAPPING_ERROR + (EMERGENCY_PAGES * PAGE_SIZE); if (unlikely(dma_addr < badend)) { WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); @@ -380,7 +382,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, npages = iommu_num_pages(vaddr, s->length, PAGE_SIZE); entry = iommu_range_alloc(dev, tbl, npages); - if (entry == DMA_ERROR_CODE) { + if (entry == CALGARY_MAPPING_ERROR) { /* makes sure unmap knows to stop */ s->dma_length = 0; goto error; @@ -398,7 +400,7 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, error: calgary_unmap_sg(dev, sg, nelems, dir, 0); for_each_sg(sg, s, nelems, i) { - sg->dma_address = DMA_ERROR_CODE; + sg->dma_address = CALGARY_MAPPING_ERROR; sg->dma_length = 0; } return 0; @@ -453,7 +455,7 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size, /* set up tces to cover the allocated range */ mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL); - if (mapping == DMA_ERROR_CODE) + if (mapping == CALGARY_MAPPING_ERROR) goto free; *dma_handle = mapping; return ret; @@ -478,6 +480,11 @@ static void calgary_free_coherent(struct device *dev, size_t size, free_pages((unsigned long)vaddr, get_order(size)); } +static int calgary_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == CALGARY_MAPPING_ERROR; +} + static const struct dma_map_ops calgary_dma_ops = { .alloc = calgary_alloc_coherent, .free = calgary_free_coherent, @@ -485,6 +492,8 @@ static const struct dma_map_ops calgary_dma_ops = { .unmap_sg = calgary_unmap_sg, .map_page = calgary_map_page, .unmap_page = calgary_unmap_page, + .mapping_error = calgary_mapping_error, + .dma_supported = x86_dma_supported, }; static inline void __iomem * busno_to_bbar(unsigned char num) @@ -732,7 +741,7 @@ static void __init calgary_reserve_regions(struct pci_dev *dev) struct iommu_table *tbl = pci_iommu(dev->bus); /* reserve EMERGENCY_PAGES from bad_dma_address and up */ - iommu_range_reserve(tbl, DMA_ERROR_CODE, EMERGENCY_PAGES); + iommu_range_reserve(tbl, CALGARY_MAPPING_ERROR, EMERGENCY_PAGES); /* avoid the BIOS/VGA first 640KB-1MB region */ /* for CalIOC2 - avoid the entire first MB */ diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 3a216ec869cd..5e16d3f29594 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -213,10 +213,8 @@ static __init int iommu_setup(char *p) } early_param("iommu", iommu_setup); -int dma_supported(struct device *dev, u64 mask) +int x86_dma_supported(struct device *dev, u64 mask) { - const struct dma_map_ops *ops = get_dma_ops(dev); - #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { dev_info(dev, "PCI: Disallowing DAC for device\n"); @@ -224,9 +222,6 @@ int dma_supported(struct device *dev, u64 mask) } #endif - if (ops->dma_supported) - return ops->dma_supported(dev, mask); - /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. The caller just has to use GFP_DMA in this case. */ @@ -252,7 +247,6 @@ int dma_supported(struct device *dev, u64 mask) return 1; } -EXPORT_SYMBOL(dma_supported); static int __init pci_iommu_init(void) { diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index a88952ef371c..a6d404087fe3 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -11,6 +11,8 @@ #include <asm/iommu.h> #include <asm/dma.h> +#define NOMMU_MAPPING_ERROR 0 + static int check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) { @@ -33,7 +35,7 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page, dma_addr_t bus = page_to_phys(page) + offset; WARN_ON(size == 0); if (!check_addr("map_single", dev, bus, size)) - return DMA_ERROR_CODE; + return NOMMU_MAPPING_ERROR; flush_write_buffers(); return bus; } @@ -88,6 +90,11 @@ static void nommu_sync_sg_for_device(struct device *dev, flush_write_buffers(); } +static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr) +{ + return dma_addr == NOMMU_MAPPING_ERROR; +} + const struct dma_map_ops nommu_dma_ops = { .alloc = dma_generic_alloc_coherent, .free = dma_generic_free_coherent, @@ -96,4 +103,6 @@ const struct dma_map_ops nommu_dma_ops = { .sync_single_for_device = nommu_sync_single_for_device, .sync_sg_for_device = nommu_sync_sg_for_device, .is_phys = 1, + .mapping_error = nommu_mapping_error, + .dma_supported = x86_dma_supported, }; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 0bb88428cbf2..3ca198080ea9 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -545,17 +545,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } /* - * Return saved PC of a blocked thread. - * What is this good for? it will be always the scheduler or ret_from_fork. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - struct inactive_task_frame *frame = - (struct inactive_task_frame *) READ_ONCE(tsk->thread.sp); - return READ_ONCE_NOCHECK(frame->ret_addr); -} - -/* * Called from fs/proc with a reference on @p to find the function * which called into schedule(). This needs to be done carefully * because the task might wake up and we might look at a stack diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index ff40e74c9181..c6d6dc5f8bb2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip); printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags, - smp_processor_id()); + raw_smp_processor_id()); printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", regs->ax, regs->bx, regs->cx, regs->dx); @@ -92,7 +92,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index b6840bf3940b..c3169be4c596 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -104,7 +104,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); - cr3 = read_cr3(); + cr3 = __read_cr3(); cr4 = __read_cr4(); printk(KERN_DEFAULT "FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", @@ -142,7 +142,7 @@ void release_thread(struct task_struct *dead_task) pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, dead_task->mm->context.ldt->entries, - dead_task->mm->context.ldt->size); + dead_task->mm->context.ldt->nr_entries); BUG(); } #endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2544700a2a87..67393fc88353 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -9,6 +9,7 @@ #include <linux/sched.h> #include <linux/tboot.h> #include <linux/delay.h> +#include <linux/frame.h> #include <acpi/reboot.h> #include <asm/io.h> #include <asm/apic.h> @@ -123,6 +124,7 @@ void __noreturn machine_real_restart(unsigned int type) #ifdef CONFIG_APM_MODULE EXPORT_SYMBOL(machine_real_restart); #endif +STACK_FRAME_NON_STANDARD(machine_real_restart); /* * Some Apple MacBook and MacBookPro's needs reboot=p to be able to reboot diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0b4d3c686b1e..3486d0498800 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -503,7 +503,7 @@ static int __init reserve_crashkernel_low(void) return 0; } - low_base = memblock_find_in_range(low_size, 1ULL << 32, low_size, CRASH_ALIGN); + low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN); if (!low_base) { pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n", (unsigned long)(low_size >> 20)); @@ -980,8 +980,6 @@ void __init setup_arch(char **cmdline_p) */ x86_configure_nx(); - simple_udelay_calibration(); - parse_early_param(); #ifdef CONFIG_MEMORY_HOTPLUG @@ -1041,6 +1039,8 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor_platform(); + simple_udelay_calibration(); + x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ @@ -1076,6 +1076,13 @@ void __init setup_arch(char **cmdline_p) max_possible_pfn = max_pfn; /* + * This call is required when the CPU does not support PAT. If + * mtrr_bp_init() invoked it already via pat_init() the call has no + * effect. + */ + init_cache_modes(); + + /* * Define random base addresses for memory sections after max_pfn is * defined and before each memory section base is used. */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index f04479a8f74f..b474c8de7fba 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -863,7 +863,7 @@ static void announce_cpu(int cpu, int apicid) if (cpu == 1) printk(KERN_INFO "x86: Booting SMP configuration:\n"); - if (system_state == SYSTEM_BOOTING) { + if (system_state < SYSTEM_RUNNING) { if (node != current_node) { if (current_node > (-1)) pr_cont("\n"); @@ -1589,7 +1589,6 @@ void native_cpu_die(unsigned int cpu) void play_dead_common(void) { idle_task_exit(); - reset_lazy_tlbstate(); /* Ack it */ (void)cpu_report_death(); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index f07f83b3611b..5f25cfbd952e 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -34,7 +34,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re mutex_lock(&child->mm->context.lock); if (unlikely(!child->mm->context.ldt || - seg >= child->mm->context.ldt->size)) + seg >= child->mm->context.ldt->nr_entries)) addr = -1L; /* bogus selector, access would fault */ else { desc = &child->mm->context.ldt->entries[seg]; diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 207b8f2582c7..213ddf3e937d 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (end - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } @@ -187,7 +187,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = PAGE_ALIGN(addr); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 4b1724059909..a4eb27918ceb 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -514,7 +514,7 @@ int tboot_force_iommu(void) if (!tboot_enabled()) return 0; - if (!intel_iommu_tboot_noforce) + if (intel_iommu_tboot_noforce) return 1; if (no_iommu || swiotlb || dmar_disabled) diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index d39c09119db6..e0754cdbad37 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -66,7 +66,7 @@ static struct irqaction irq0 = { .name = "timer" }; -void __init setup_default_timer_irq(void) +static void __init setup_default_timer_irq(void) { if (!nr_legacy_irqs()) return; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 3995d3a777d4..bf54309b85da 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -182,7 +182,7 @@ int is_valid_bugaddr(unsigned long addr) return ud == INSN_UD0 || ud == INSN_UD2; } -static int fixup_bug(struct pt_regs *regs, int trapnr) +int fixup_bug(struct pt_regs *regs, int trapnr) { if (trapnr != X86_TRAP_UD) return 0; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 714dfba6a1e7..796d96bb0821 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -51,115 +51,34 @@ static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; struct clocksource *art_related_clocksource; -/* - * Use a ring-buffer like data structure, where a writer advances the head by - * writing a new data entry and a reader advances the tail when it observes a - * new entry. - * - * Writers are made to wait on readers until there's space to write a new - * entry. - * - * This means that we can always use an {offset, mul} pair to compute a ns - * value that is 'roughly' in the right direction, even if we're writing a new - * {offset, mul} pair during the clock read. - * - * The down-side is that we can no longer guarantee strict monotonicity anymore - * (assuming the TSC was that to begin with), because while we compute the - * intersection point of the two clock slopes and make sure the time is - * continuous at the point of switching; we can no longer guarantee a reader is - * strictly before or after the switch point. - * - * It does mean a reader no longer needs to disable IRQs in order to avoid - * CPU-Freq updates messing with his times, and similarly an NMI reader will - * no longer run the risk of hitting half-written state. - */ - struct cyc2ns { - struct cyc2ns_data data[2]; /* 0 + 2*24 = 48 */ - struct cyc2ns_data *head; /* 48 + 8 = 56 */ - struct cyc2ns_data *tail; /* 56 + 8 = 64 */ -}; /* exactly fits one cacheline */ - -static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); - -struct cyc2ns_data *cyc2ns_read_begin(void) -{ - struct cyc2ns_data *head; - - preempt_disable(); + struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ + seqcount_t seq; /* 32 + 4 = 36 */ - head = this_cpu_read(cyc2ns.head); - /* - * Ensure we observe the entry when we observe the pointer to it. - * matches the wmb from cyc2ns_write_end(). - */ - smp_read_barrier_depends(); - head->__count++; - barrier(); - - return head; -} +}; /* fits one cacheline */ -void cyc2ns_read_end(struct cyc2ns_data *head) -{ - barrier(); - /* - * If we're the outer most nested read; update the tail pointer - * when we're done. This notifies possible pending writers - * that we've observed the head pointer and that the other - * entry is now free. - */ - if (!--head->__count) { - /* - * x86-TSO does not reorder writes with older reads; - * therefore once this write becomes visible to another - * cpu, we must be finished reading the cyc2ns_data. - * - * matches with cyc2ns_write_begin(). - */ - this_cpu_write(cyc2ns.tail, head); - } - preempt_enable(); -} +static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); -/* - * Begin writing a new @data entry for @cpu. - * - * Assumes some sort of write side lock; currently 'provided' by the assumption - * that cpufreq will call its notifiers sequentially. - */ -static struct cyc2ns_data *cyc2ns_write_begin(int cpu) +void cyc2ns_read_begin(struct cyc2ns_data *data) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - struct cyc2ns_data *data = c2n->data; + int seq, idx; - if (data == c2n->head) - data++; + preempt_disable_notrace(); - /* XXX send an IPI to @cpu in order to guarantee a read? */ + do { + seq = this_cpu_read(cyc2ns.seq.sequence); + idx = seq & 1; - /* - * When we observe the tail write from cyc2ns_read_end(), - * the cpu must be done with that entry and its safe - * to start writing to it. - */ - while (c2n->tail == data) - cpu_relax(); + data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); + data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); + data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); - return data; + } while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence))); } -static void cyc2ns_write_end(int cpu, struct cyc2ns_data *data) +void cyc2ns_read_end(void) { - struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu); - - /* - * Ensure the @data writes are visible before we publish the - * entry. Matches the data-depencency in cyc2ns_read_begin(). - */ - smp_wmb(); - - ACCESS_ONCE(c2n->head) = data; + preempt_enable_notrace(); } /* @@ -191,7 +110,6 @@ static void cyc2ns_data_init(struct cyc2ns_data *data) data->cyc2ns_mul = 0; data->cyc2ns_shift = 0; data->cyc2ns_offset = 0; - data->__count = 0; } static void cyc2ns_init(int cpu) @@ -201,51 +119,29 @@ static void cyc2ns_init(int cpu) cyc2ns_data_init(&c2n->data[0]); cyc2ns_data_init(&c2n->data[1]); - c2n->head = c2n->data; - c2n->tail = c2n->data; + seqcount_init(&c2n->seq); } static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data, *tail; + struct cyc2ns_data data; unsigned long long ns; - /* - * See cyc2ns_read_*() for details; replicated in order to avoid - * an extra few instructions that came with the abstraction. - * Notable, it allows us to only do the __count and tail update - * dance when its actually needed. - */ - - preempt_disable_notrace(); - data = this_cpu_read(cyc2ns.head); - tail = this_cpu_read(cyc2ns.tail); - - if (likely(data == tail)) { - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); - } else { - data->__count++; - - barrier(); + cyc2ns_read_begin(&data); - ns = data->cyc2ns_offset; - ns += mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + ns = data.cyc2ns_offset; + ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); - barrier(); - - if (!--data->__count) - this_cpu_write(cyc2ns.tail, data); - } - preempt_enable_notrace(); + cyc2ns_read_end(); return ns; } -static void set_cyc2ns_scale(unsigned long khz, int cpu) +static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { - unsigned long long tsc_now, ns_now; - struct cyc2ns_data *data; + unsigned long long ns_now; + struct cyc2ns_data data; + struct cyc2ns *c2n; unsigned long flags; local_irq_save(flags); @@ -254,9 +150,6 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) if (!khz) goto done; - data = cyc2ns_write_begin(cpu); - - tsc_now = rdtsc(); ns_now = cycles_2_ns(tsc_now); /* @@ -264,7 +157,7 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * time function is continuous; see the comment near struct * cyc2ns_data. */ - clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, khz, + clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* @@ -273,20 +166,26 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu) * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ - if (data->cyc2ns_shift == 32) { - data->cyc2ns_shift = 31; - data->cyc2ns_mul >>= 1; + if (data.cyc2ns_shift == 32) { + data.cyc2ns_shift = 31; + data.cyc2ns_mul >>= 1; } - data->cyc2ns_offset = ns_now - - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); + data.cyc2ns_offset = ns_now - + mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); - cyc2ns_write_end(cpu, data); + c2n = per_cpu_ptr(&cyc2ns, cpu); + + raw_write_seqcount_latch(&c2n->seq); + c2n->data[0] = data; + raw_write_seqcount_latch(&c2n->seq); + c2n->data[1] = data; done: - sched_clock_idle_wakeup_event(0); + sched_clock_idle_wakeup_event(); local_irq_restore(flags); } + /* * Scheduler clock - returns current time in nanosec units. */ @@ -374,6 +273,8 @@ static int __init tsc_setup(char *str) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; + if (!strcmp(str, "unstable")) + mark_tsc_unstable("boot parameter"); return 1; } @@ -986,7 +887,6 @@ void tsc_restore_sched_clock_state(void) } #ifdef CONFIG_CPU_FREQ - /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency * changes. * @@ -1027,7 +927,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); - set_cyc2ns_scale(tsc_khz, freq->cpu); + set_cyc2ns_scale(tsc_khz, freq->cpu, rdtsc()); } return 0; @@ -1127,6 +1027,15 @@ static void tsc_cs_mark_unstable(struct clocksource *cs) pr_info("Marking TSC unstable due to clocksource watchdog\n"); } +static void tsc_cs_tick_stable(struct clocksource *cs) +{ + if (tsc_unstable) + return; + + if (using_native_sched_clock()) + sched_clock_tick_stable(); +} + /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ @@ -1140,6 +1049,7 @@ static struct clocksource clocksource_tsc = { .archdata = { .vclock_mode = VCLOCK_TSC }, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, + .tick_stable = tsc_cs_tick_stable, }; void mark_tsc_unstable(char *reason) @@ -1255,6 +1165,7 @@ static void tsc_refine_calibration_work(struct work_struct *work) static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; + int cpu; /* Don't bother refining TSC on unstable systems */ if (check_tsc_unstable()) @@ -1305,6 +1216,10 @@ static void tsc_refine_calibration_work(struct work_struct *work) /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); + /* Update the sched_clock() rate to match the clocksource one */ + for_each_possible_cpu(cpu) + set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; @@ -1350,7 +1265,7 @@ device_initcall(init_tsc_clocksource); void __init tsc_init(void) { - u64 lpj; + u64 lpj, cyc; int cpu; if (!boot_cpu_has(X86_FEATURE_TSC)) { @@ -1390,9 +1305,10 @@ void __init tsc_init(void) * speed as the bootup CPU. (cpufreq notifiers will fix this * up if their speed diverges) */ + cyc = rdtsc(); for_each_possible_cpu(cpu) { cyc2ns_init(cpu); - set_cyc2ns_scale(tsc_khz, cpu); + set_cyc2ns_scale(tsc_khz, cpu, cyc); } if (tsc_disabled > 0) @@ -1412,11 +1328,11 @@ void __init tsc_init(void) use_tsc_delay(); + check_system_tsc_reliable(); + if (unsynchronized_tsc()) mark_tsc_unstable("TSCs unsynchronized"); - check_system_tsc_reliable(); - detect_art(); } diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 728f75378475..7842371bc9e4 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -71,13 +71,8 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval, * non zero. We don't do that on non boot cpus because physical * hotplug should have set the ADJUST register to a value > 0 so * the TSC is in sync with the already running cpus. - * - * But we always force positive ADJUST values. Otherwise the TSC - * deadline timer creates an interrupt storm. We also have to - * prevent values > 0x7FFFFFFF as those wreckage the timer as well. */ - if ((bootcpu && bootval != 0) || (!bootcpu && bootval < 0) || - (bootval > 0x7FFFFFFF)) { + if (bootcpu && bootval != 0) { pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", cpu, bootval); wrmsrl(MSR_IA32_TSC_ADJUST, 0); @@ -451,20 +446,6 @@ retry: */ cur->adjusted += cur_max_warp; - /* - * TSC deadline timer stops working or creates an interrupt storm - * with adjust values < 0 and > x07ffffff. - * - * To allow adjust values > 0x7FFFFFFF we need to disable the - * deadline timer and use the local APIC timer, but that requires - * more intrusive changes and we do not have any useful information - * from Intel about the underlying HW wreckage yet. - */ - if (cur->adjusted < 0) - cur->adjusted = 0; - if (cur->adjusted > 0x7FFFFFFF) - cur->adjusted = 0x7FFFFFFF; - pr_warn("TSC ADJUST compensate: CPU%u observed %lld warp. Adjust: %lld\n", cpu, cur_max_warp, cur->adjusted); diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index 82c6d7f1fd73..b9389d72b2f7 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -104,6 +104,11 @@ static inline unsigned long *last_frame(struct unwind_state *state) return (unsigned long *)task_pt_regs(state->task) - 2; } +static bool is_last_frame(struct unwind_state *state) +{ + return state->bp == last_frame(state); +} + #ifdef CONFIG_X86_32 #define GCC_REALIGN_WORDS 3 #else @@ -115,16 +120,15 @@ static inline unsigned long *last_aligned_frame(struct unwind_state *state) return last_frame(state) - GCC_REALIGN_WORDS; } -static bool is_last_task_frame(struct unwind_state *state) +static bool is_last_aligned_frame(struct unwind_state *state) { unsigned long *last_bp = last_frame(state); unsigned long *aligned_bp = last_aligned_frame(state); /* - * We have to check for the last task frame at two different locations - * because gcc can occasionally decide to realign the stack pointer and - * change the offset of the stack frame in the prologue of a function - * called by head/entry code. Examples: + * GCC can occasionally decide to realign the stack pointer and change + * the offset of the stack frame in the prologue of a function called + * by head/entry code. Examples: * * <start_secondary>: * push %edi @@ -141,11 +145,38 @@ static bool is_last_task_frame(struct unwind_state *state) * push %rbp * mov %rsp,%rbp * - * Note that after aligning the stack, it pushes a duplicate copy of - * the return address before pushing the frame pointer. + * After aligning the stack, it pushes a duplicate copy of the return + * address before pushing the frame pointer. + */ + return (state->bp == aligned_bp && *(aligned_bp + 1) == *(last_bp + 1)); +} + +static bool is_last_ftrace_frame(struct unwind_state *state) +{ + unsigned long *last_bp = last_frame(state); + unsigned long *last_ftrace_bp = last_bp - 3; + + /* + * When unwinding from an ftrace handler of a function called by entry + * code, the stack layout of the last frame is: + * + * bp + * parent ret addr + * bp + * function ret addr + * parent ret addr + * pt_regs + * ----------------- */ - return (state->bp == last_bp || - (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1))); + return (state->bp == last_ftrace_bp && + *state->bp == *(state->bp + 2) && + *(state->bp + 1) == *(state->bp + 4)); +} + +static bool is_last_task_frame(struct unwind_state *state) +{ + return is_last_frame(state) || is_last_aligned_frame(state) || + is_last_ftrace_frame(state); } /* diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a181ae76c71c..59ca2eea522c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -780,18 +780,20 @@ out: static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; + struct kvm_cpuid_entry2 *ej; + int j = i; + int nent = vcpu->arch.cpuid_nent; e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ + do { + j = (j + 1) % nent; + ej = &vcpu->arch.cpuid_entries[j]; + } while (ej->function != e->function); + + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + + return j; } /* find an entry with matching function, matching index (if needed), and that diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index a6fd40aade7c..da6728383052 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -144,6 +144,14 @@ static inline bool guest_cpuid_has_rtm(struct kvm_vcpu *vcpu) return best && (best->ebx & bit(X86_FEATURE_RTM)); } +static inline bool guest_cpuid_has_mpx(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_MPX)); +} + static inline bool guest_cpuid_has_rdtscp(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index c25cfaf584e7..fb0055953fbc 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -900,7 +900,7 @@ static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, if (rc != X86EMUL_CONTINUE) \ goto done; \ ctxt->_eip += sizeof(_type); \ - _x = *(_type __aligned(1) *) ctxt->fetch.ptr; \ + memcpy(&_x, ctxt->fetch.ptr, sizeof(_type)); \ ctxt->fetch.ptr += sizeof(_type); \ _x; \ }) @@ -2742,6 +2742,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; return X86EMUL_CONTINUE; } @@ -3941,6 +3942,25 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) } /* + * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save + * and restore MXCSR. + */ +static size_t __fxstate_size(int nregs) +{ + return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16; +} + +static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt) +{ + bool cr4_osfxsr; + if (ctxt->mode == X86EMUL_MODE_PROT64) + return __fxstate_size(16); + + cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR; + return __fxstate_size(cr4_osfxsr ? 8 : 0); +} + +/* * FXSAVE and FXRSTOR have 4 different formats depending on execution mode, * 1) 16 bit mode * 2) 32 bit mode @@ -3961,7 +3981,6 @@ static int check_fxsr(struct x86_emulate_ctxt *ctxt) static int em_fxsave(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; - size_t size; int rc; rc = check_fxsr(ctxt); @@ -3977,68 +3996,42 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR) - size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]); - else - size = offsetof(struct fxregs_state, xmm_space[0]); - - return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); -} - -static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, - struct fxregs_state *new) -{ - int rc = X86EMUL_CONTINUE; - struct fxregs_state old; - - rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old)); - if (rc != X86EMUL_CONTINUE) - return rc; - - /* - * 64 bit host will restore XMM 8-15, which is not correct on non-64 - * bit guests. Load the current values in order to preserve 64 bit - * XMMs after fxrstor. - */ -#ifdef CONFIG_X86_64 - /* XXX: accessing XMM 8-15 very awkwardly */ - memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16); -#endif - - /* - * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but - * does save and restore MXCSR. - */ - if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)) - memcpy(new->xmm_space, old.xmm_space, 8 * 16); - - return rc; + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, + fxstate_size(ctxt)); } static int em_fxrstor(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; int rc; + size_t size; rc = check_fxsr(ctxt); if (rc != X86EMUL_CONTINUE) return rc; - rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); - if (rc != X86EMUL_CONTINUE) - return rc; + ctxt->ops->get_fpu(ctxt); - if (fx_state.mxcsr >> 16) - return emulate_gp(ctxt, 0); + size = fxstate_size(ctxt); + if (size < __fxstate_size(16)) { + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + if (rc != X86EMUL_CONTINUE) + goto out; + } - ctxt->ops->get_fpu(ctxt); + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); + if (rc != X86EMUL_CONTINUE) + goto out; - if (ctxt->mode < X86EMUL_MODE_PROT64) - rc = fxrstor_fixup(ctxt, &fx_state); + if (fx_state.mxcsr >> 16) { + rc = emulate_gp(ctxt, 0); + goto out; + } if (rc == X86EMUL_CONTINUE) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); +out: ctxt->ops->put_fpu(ctxt); return rc; @@ -4173,7 +4166,7 @@ static int check_dr_write(struct x86_emulate_ctxt *ctxt) static int check_svme(struct x86_emulate_ctxt *ctxt) { - u64 efer; + u64 efer = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c329d2894905..2819d4c123eb 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1495,31 +1495,65 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); static void cancel_hv_timer(struct kvm_lapic *apic) { + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + preempt_disable(); kvm_x86_ops->cancel_hv_timer(apic->vcpu); apic->lapic_timer.hv_timer_in_use = false; + preempt_enable(); } static bool start_hv_timer(struct kvm_lapic *apic) { - u64 tscdeadline = apic->lapic_timer.tscdeadline; + struct kvm_timer *ktimer = &apic->lapic_timer; + int r; - if ((atomic_read(&apic->lapic_timer.pending) && - !apic_lvtt_period(apic)) || - kvm_x86_ops->set_hv_timer(apic->vcpu, tscdeadline)) { - if (apic->lapic_timer.hv_timer_in_use) - cancel_hv_timer(apic); - } else { - apic->lapic_timer.hv_timer_in_use = true; - hrtimer_cancel(&apic->lapic_timer.timer); + if (!kvm_x86_ops->set_hv_timer) + return false; + + if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) + return false; - /* In case the sw timer triggered in the window */ - if (atomic_read(&apic->lapic_timer.pending) && - !apic_lvtt_period(apic)) - cancel_hv_timer(apic); + r = kvm_x86_ops->set_hv_timer(apic->vcpu, ktimer->tscdeadline); + if (r < 0) + return false; + + ktimer->hv_timer_in_use = true; + hrtimer_cancel(&ktimer->timer); + + /* + * Also recheck ktimer->pending, in case the sw timer triggered in + * the window. For periodic timer, leave the hv timer running for + * simplicity, and the deadline will be recomputed on the next vmexit. + */ + if (!apic_lvtt_period(apic) && (r || atomic_read(&ktimer->pending))) { + if (r) + apic_timer_expired(apic); + return false; } - trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, - apic->lapic_timer.hv_timer_in_use); - return apic->lapic_timer.hv_timer_in_use; + + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, true); + return true; +} + +static void start_sw_timer(struct kvm_lapic *apic) +{ + struct kvm_timer *ktimer = &apic->lapic_timer; + if (apic->lapic_timer.hv_timer_in_use) + cancel_hv_timer(apic); + if (!apic_lvtt_period(apic) && atomic_read(&ktimer->pending)) + return; + + if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) + start_sw_period(apic); + else if (apic_lvtt_tscdeadline(apic)) + start_sw_tscdeadline(apic); + trace_kvm_hv_timer_state(apic->vcpu->vcpu_id, false); +} + +static void restart_apic_timer(struct kvm_lapic *apic) +{ + if (!start_hv_timer(apic)) + start_sw_timer(apic); } void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) @@ -1533,19 +1567,14 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) if (apic_lvtt_period(apic) && apic->lapic_timer.period) { advance_periodic_target_expiration(apic); - if (!start_hv_timer(apic)) - start_sw_period(apic); + restart_apic_timer(apic); } } EXPORT_SYMBOL_GPL(kvm_lapic_expired_hv_timer); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu) { - struct kvm_lapic *apic = vcpu->arch.apic; - - WARN_ON(apic->lapic_timer.hv_timer_in_use); - - start_hv_timer(apic); + restart_apic_timer(vcpu->arch.apic); } EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_hv_timer); @@ -1554,33 +1583,28 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; /* Possibly the TSC deadline timer is not enabled yet */ - if (!apic->lapic_timer.hv_timer_in_use) - return; - - cancel_hv_timer(apic); + if (apic->lapic_timer.hv_timer_in_use) + start_sw_timer(apic); +} +EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); - if (atomic_read(&apic->lapic_timer.pending)) - return; +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) - start_sw_period(apic); - else if (apic_lvtt_tscdeadline(apic)) - start_sw_tscdeadline(apic); + WARN_ON(!apic->lapic_timer.hv_timer_in_use); + restart_apic_timer(apic); } -EXPORT_SYMBOL_GPL(kvm_lapic_switch_to_sw_timer); static void start_apic_timer(struct kvm_lapic *apic) { atomic_set(&apic->lapic_timer.pending, 0); - if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) { - if (set_target_expiration(apic) && - !(kvm_x86_ops->set_hv_timer && start_hv_timer(apic))) - start_sw_period(apic); - } else if (apic_lvtt_tscdeadline(apic)) { - if (!(kvm_x86_ops->set_hv_timer && start_hv_timer(apic))) - start_sw_tscdeadline(apic); - } + if ((apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) + && !set_target_expiration(apic)) + return; + + restart_apic_timer(apic); } static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) @@ -1811,16 +1835,6 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) * LAPIC interface *---------------------------------------------------------------------- */ -u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - - if (!lapic_in_kernel(vcpu)) - return 0; - - return apic->lapic_timer.tscdeadline; -} - u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1934,7 +1948,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) for (i = 0; i < KVM_APIC_LVT_NUM; i++) kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED); apic_update_lvtt(apic); - if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) + if (kvm_vcpu_is_reset_bsp(vcpu) && + kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED)) kvm_lapic_set_reg(apic, APIC_LVT0, SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT)); apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0)); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index bcbe811f3b97..29caa2c3dff9 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -87,7 +87,6 @@ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); -u64 kvm_get_lapic_target_expiration_tsc(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); @@ -216,4 +215,5 @@ void kvm_lapic_switch_to_sw_timer(struct kvm_vcpu *vcpu); void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); +void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 5d3376f67794..aafd399cf8c6 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -183,13 +183,13 @@ static u64 __read_mostly shadow_user_mask; static u64 __read_mostly shadow_accessed_mask; static u64 __read_mostly shadow_dirty_mask; static u64 __read_mostly shadow_mmio_mask; +static u64 __read_mostly shadow_mmio_value; static u64 __read_mostly shadow_present_mask; /* - * The mask/value to distinguish a PTE that has been marked not-present for - * access tracking purposes. - * The mask would be either 0 if access tracking is disabled, or - * SPTE_SPECIAL_MASK|VMX_EPT_RWX_MASK if access tracking is enabled. + * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value. + * Non-present SPTEs with shadow_acc_track_value set are in place for access + * tracking. */ static u64 __read_mostly shadow_acc_track_mask; static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK; @@ -207,16 +207,40 @@ static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIF static void mmu_spte_set(u64 *sptep, u64 spte); static void mmu_free_roots(struct kvm_vcpu *vcpu); -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask) +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { + BUG_ON((mmio_mask & mmio_value) != mmio_value); + shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK; shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK; } EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) +{ + return sp->role.ad_disabled; +} + +static inline bool spte_ad_enabled(u64 spte) +{ + MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + return !(spte & shadow_acc_track_value); +} + +static inline u64 spte_shadow_accessed_mask(u64 spte) +{ + MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + return spte_ad_enabled(spte) ? shadow_accessed_mask : 0; +} + +static inline u64 spte_shadow_dirty_mask(u64 spte) +{ + MMU_WARN_ON((spte & shadow_mmio_mask) == shadow_mmio_value); + return spte_ad_enabled(spte) ? shadow_dirty_mask : 0; +} + static inline bool is_access_track_spte(u64 spte) { - /* Always false if shadow_acc_track_mask is zero. */ - return (spte & shadow_acc_track_mask) == shadow_acc_track_value; + return !spte_ad_enabled(spte) && (spte & shadow_acc_track_mask) == 0; } /* @@ -270,7 +294,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, u64 mask = generation_mmio_spte_mask(gen); access &= ACC_WRITE_MASK | ACC_USER_MASK; - mask |= shadow_mmio_mask | access | gfn << PAGE_SHIFT; + mask |= shadow_mmio_value | access | gfn << PAGE_SHIFT; trace_mark_mmio_spte(sptep, gfn, access, gen); mmu_spte_set(sptep, mask); @@ -278,7 +302,7 @@ static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, static bool is_mmio_spte(u64 spte) { - return (spte & shadow_mmio_mask) == shadow_mmio_mask; + return (spte & shadow_mmio_mask) == shadow_mmio_value; } static gfn_t get_mmio_spte_gfn(u64 spte) @@ -315,12 +339,20 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte) return likely(kvm_gen == spte_gen); } +/* + * Sets the shadow PTE masks used by the MMU. + * + * Assumptions: + * - Setting either @accessed_mask or @dirty_mask requires setting both + * - At least one of @accessed_mask or @acc_track_mask must be set + */ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask, u64 acc_track_mask) { - if (acc_track_mask != 0) - acc_track_mask |= SPTE_SPECIAL_MASK; + BUG_ON(!dirty_mask != !accessed_mask); + BUG_ON(!accessed_mask && !acc_track_mask); + BUG_ON(acc_track_mask & shadow_acc_track_value); shadow_user_mask = user_mask; shadow_accessed_mask = accessed_mask; @@ -329,7 +361,6 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, shadow_x_mask = x_mask; shadow_present_mask = p_mask; shadow_acc_track_mask = acc_track_mask; - WARN_ON(shadow_accessed_mask != 0 && shadow_acc_track_mask != 0); } EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes); @@ -549,7 +580,7 @@ static bool spte_has_volatile_bits(u64 spte) is_access_track_spte(spte)) return true; - if (shadow_accessed_mask) { + if (spte_ad_enabled(spte)) { if ((spte & shadow_accessed_mask) == 0 || (is_writable_pte(spte) && (spte & shadow_dirty_mask) == 0)) return true; @@ -560,14 +591,17 @@ static bool spte_has_volatile_bits(u64 spte) static bool is_accessed_spte(u64 spte) { - return shadow_accessed_mask ? spte & shadow_accessed_mask - : !is_access_track_spte(spte); + u64 accessed_mask = spte_shadow_accessed_mask(spte); + + return accessed_mask ? spte & accessed_mask + : !is_access_track_spte(spte); } static bool is_dirty_spte(u64 spte) { - return shadow_dirty_mask ? spte & shadow_dirty_mask - : spte & PT_WRITABLE_MASK; + u64 dirty_mask = spte_shadow_dirty_mask(spte); + + return dirty_mask ? spte & dirty_mask : spte & PT_WRITABLE_MASK; } /* Rules for using mmu_spte_set: @@ -707,10 +741,10 @@ static u64 mmu_spte_get_lockless(u64 *sptep) static u64 mark_spte_for_access_track(u64 spte) { - if (shadow_accessed_mask != 0) + if (spte_ad_enabled(spte)) return spte & ~shadow_accessed_mask; - if (shadow_acc_track_mask == 0 || is_access_track_spte(spte)) + if (is_access_track_spte(spte)) return spte; /* @@ -729,7 +763,6 @@ static u64 mark_spte_for_access_track(u64 spte) spte |= (spte & shadow_acc_track_saved_bits_mask) << shadow_acc_track_saved_bits_shift; spte &= ~shadow_acc_track_mask; - spte |= shadow_acc_track_value; return spte; } @@ -741,6 +774,7 @@ static u64 restore_acc_track_spte(u64 spte) u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift) & shadow_acc_track_saved_bits_mask; + WARN_ON_ONCE(spte_ad_enabled(spte)); WARN_ON_ONCE(!is_access_track_spte(spte)); new_spte &= ~shadow_acc_track_mask; @@ -759,7 +793,7 @@ static bool mmu_spte_age(u64 *sptep) if (!is_accessed_spte(spte)) return false; - if (shadow_accessed_mask) { + if (spte_ad_enabled(spte)) { clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } else { @@ -1390,6 +1424,22 @@ static bool spte_clear_dirty(u64 *sptep) return mmu_spte_update(sptep, spte); } +static bool wrprot_ad_disabled_spte(u64 *sptep) +{ + bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT, + (unsigned long *)sptep); + if (was_writable) + kvm_set_pfn_dirty(spte_to_pfn(*sptep)); + + return was_writable; +} + +/* + * Gets the GFN ready for another round of dirty logging by clearing the + * - D bit on ad-enabled SPTEs, and + * - W bit on ad-disabled SPTEs. + * Returns true iff any D or W bits were cleared. + */ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; @@ -1397,7 +1447,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_clear_dirty(sptep); + if (spte_ad_enabled(*sptep)) + flush |= spte_clear_dirty(sptep); + else + flush |= wrprot_ad_disabled_spte(sptep); return flush; } @@ -1420,7 +1473,8 @@ static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) bool flush = false; for_each_rmap_spte(rmap_head, &iter, sptep) - flush |= spte_set_dirty(sptep); + if (spte_ad_enabled(*sptep)) + flush |= spte_set_dirty(sptep); return flush; } @@ -1452,7 +1506,8 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, } /** - * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages + * kvm_mmu_clear_dirty_pt_masked - clear MMU D-bit for PT level pages, or write + * protect the page if the D-bit isn't supported. * @kvm: kvm instance * @slot: slot to clear D-bit * @gfn_offset: start of the BITS_PER_LONG pages we care about @@ -1766,18 +1821,9 @@ static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, u64 *sptep; struct rmap_iterator iter; - /* - * If there's no access bit in the secondary pte set by the hardware and - * fast access tracking is also not enabled, it's up to gup-fast/gup to - * set the access bit in the primary pte or in the page structure. - */ - if (!shadow_accessed_mask && !shadow_acc_track_mask) - goto out; - for_each_rmap_spte(rmap_head, &iter, sptep) if (is_accessed_spte(*sptep)) return 1; -out: return 0; } @@ -1798,18 +1844,6 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) { - /* - * In case of absence of EPT Access and Dirty Bits supports, - * emulate the accessed bit for EPT, by checking if this page has - * an EPT mapping, and clearing it if it does. On the next access, - * a new EPT mapping will be established. - * This has some overhead, but not as much as the cost of swapping - * out actively used pages or breaking up actively used hugepages. - */ - if (!shadow_accessed_mask && !shadow_acc_track_mask) - return kvm_handle_hva_range(kvm, start, end, 0, - kvm_unmap_rmapp); - return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp); } @@ -2398,7 +2432,12 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask | shadow_accessed_mask; + shadow_user_mask | shadow_x_mask; + + if (sp_ad_disabled(sp)) + spte |= shadow_acc_track_value; + else + spte |= shadow_accessed_mask; mmu_spte_set(sptep, spte); @@ -2666,10 +2705,15 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, { u64 spte = 0; int ret = 0; + struct kvm_mmu_page *sp; if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access)) return 0; + sp = page_header(__pa(sptep)); + if (sp_ad_disabled(sp)) + spte |= shadow_acc_track_value; + /* * For the EPT case, shadow_present_mask is 0 if hardware * supports exec-only page table entries. In that case, @@ -2678,7 +2722,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, */ spte |= shadow_present_mask; if (!speculative) - spte |= shadow_accessed_mask; + spte |= spte_shadow_accessed_mask(spte); if (pte_access & ACC_EXEC_MASK) spte |= shadow_x_mask; @@ -2735,7 +2779,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (pte_access & ACC_WRITE_MASK) { kvm_vcpu_mark_page_dirty(vcpu, gfn); - spte |= shadow_dirty_mask; + spte |= spte_shadow_dirty_mask(spte); } if (speculative) @@ -2877,16 +2921,16 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) { struct kvm_mmu_page *sp; + sp = page_header(__pa(sptep)); + /* - * Since it's no accessed bit on EPT, it's no way to - * distinguish between actually accessed translations - * and prefetched, so disable pte prefetch if EPT is - * enabled. + * Without accessed bits, there's no way to distinguish between + * actually accessed translations and prefetched, so disable pte + * prefetch if accessed bits aren't available. */ - if (!shadow_accessed_mask) + if (sp_ad_disabled(sp)) return; - sp = page_header(__pa(sptep)); if (sp->role.level > PT_PAGE_TABLE_LEVEL) return; @@ -3698,12 +3742,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); } -static bool can_do_async_pf(struct kvm_vcpu *vcpu) +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || kvm_event_needs_reinjection(vcpu))) return false; + if (is_guest_mode(vcpu)) + return false; + return kvm_x86_ops->interrupt_allowed(vcpu); } @@ -3719,7 +3766,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, if (!async) return false; /* *pfn has correct page already */ - if (!prefault && can_do_async_pf(vcpu)) { + if (!prefault && kvm_can_do_async_pf(vcpu)) { trace_kvm_try_async_get_page(gva, gfn); if (kvm_find_async_pf_gfn(vcpu, gfn)) { trace_kvm_async_pf_doublefault(gva, gfn); @@ -4287,6 +4334,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->base_role.word = 0; context->base_role.smm = is_smm(vcpu); + context->base_role.ad_disabled = (shadow_accessed_mask == 0); context->page_fault = tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = nonpaging_invlpg; @@ -4374,6 +4422,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->root_level = context->shadow_root_level; context->root_hpa = INVALID_PAGE; context->direct_map = false; + context->base_role.ad_disabled = !accessed_dirty; update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); @@ -4633,6 +4682,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.smep_andnot_wp = 1; mask.smap_andnot_wp = 1; mask.smm = 1; + mask.ad_disabled = 1; /* * If we don't have indirect shadow pages, it means no page is diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 27975807cc64..a276834950c1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -51,7 +51,7 @@ static inline u64 rsvd_bits(int s, int e) return ((1ULL << (e - s + 1)) - 1) << s; } -void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask); +void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value); void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context); @@ -76,6 +76,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct); void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu); void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool accessed_dirty); +bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index 5a24b846a1cb..8b97a6cba8d1 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -30,8 +30,9 @@ \ role.word = __entry->role; \ \ - trace_seq_printf(p, "sp gen %lx gfn %llx %u%s q%u%s %s%s" \ - " %snxe root %u %s%c", __entry->mmu_valid_gen, \ + trace_seq_printf(p, "sp gen %lx gfn %llx l%u%s q%u%s %s%s" \ + " %snxe %sad root %u %s%c", \ + __entry->mmu_valid_gen, \ __entry->gfn, role.level, \ role.cr4_pae ? " pae" : "", \ role.quadrant, \ @@ -39,6 +40,7 @@ access_str[role.access], \ role.invalid ? " invalid" : "", \ role.nxe ? "" : "!", \ + role.ad_disabled ? "!" : "", \ __entry->root_count, \ __entry->unsync ? "unsync" : "sync", 0); \ saved_ptr; \ diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 56241746abbd..b0454c7e4cff 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -283,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, pt_element_t pte; pt_element_t __user *uninitialized_var(ptep_user); gfn_t table_gfn; - unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey; + u64 pt_access, pte_access; + unsigned index, accessed_dirty, pte_pkey; unsigned nested_access; gpa_t pte_gpa; bool have_ad; int offset; + u64 walk_nx_mask = 0; const int write_fault = access & PFERR_WRITE_MASK; const int user_fault = access & PFERR_USER_MASK; const int fetch_fault = access & PFERR_FETCH_MASK; @@ -302,6 +304,7 @@ retry_walk: have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 + walk_nx_mask = 1ULL << PT64_NX_SHIFT; if (walker->level == PT32E_ROOT_LEVEL) { pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); @@ -313,8 +316,6 @@ retry_walk: walker->max_level = walker->level; ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu))); - accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0; - /* * FIXME: on Intel processors, loads of the PDPTE registers for PAE paging * by the MOV to CR instruction are treated as reads and do not cause the @@ -322,14 +323,14 @@ retry_walk: */ nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK; - pt_access = pte_access = ACC_ALL; + pte_access = ~0; ++walker->level; do { gfn_t real_gfn; unsigned long host_addr; - pt_access &= pte_access; + pt_access = pte_access; --walker->level; index = PT_INDEX(addr, walker->level); @@ -371,6 +372,12 @@ retry_walk: trace_kvm_mmu_paging_element(pte, walker->level); + /* + * Inverting the NX it lets us AND it like other + * permission bits. + */ + pte_access = pt_access & (pte ^ walk_nx_mask); + if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; @@ -379,14 +386,16 @@ retry_walk: goto error; } - accessed_dirty &= pte; - pte_access = pt_access & FNAME(gpte_access)(vcpu, pte); - walker->ptes[walker->level - 1] = pte; } while (!is_last_gpte(mmu, walker->level, pte)); pte_pkey = FNAME(gpte_pkeys)(vcpu, pte); - errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access); + accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0; + + /* Convert to ACC_*_MASK flags for struct guest_walker. */ + walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask); + walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask); + errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access); if (unlikely(errcode)) goto error; @@ -403,7 +412,7 @@ retry_walk: walker->gfn = real_gpa >> PAGE_SHIFT; if (!write_fault) - FNAME(protect_clean_gpte)(mmu, &pte_access, pte); + FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte); else /* * On a write fault, fold the dirty bit into accessed_dirty. @@ -421,10 +430,8 @@ retry_walk: goto retry_walk; } - walker->pt_access = pt_access; - walker->pte_access = pte_access; pgprintk("%s: pte %llx pte_access %x pt_access %x\n", - __func__, (u64)pte, pte_access, pt_access); + __func__, (u64)pte, walker->pte_access, walker->pt_access); return 1; error: @@ -452,7 +459,7 @@ error: */ if (!(errcode & PFERR_RSVD_MASK)) { vcpu->arch.exit_qualification &= 0x187; - vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3; + vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3; } #endif walker->fault.address = addr; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 9d4a8504a95a..5ab4a364348e 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) ((u64)1 << edx.split.bit_width_fixed) - 1; } - pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | + pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c27ac6923a18..905ea6052517 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -36,6 +36,7 @@ #include <linux/slab.h> #include <linux/amd-iommu.h> #include <linux/hashtable.h> +#include <linux/frame.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -189,6 +190,7 @@ struct vcpu_svm { struct nested_state nested; bool nmi_singlestep; + u64 nmi_singlestep_guest_rflags; unsigned int3_injected; unsigned long int3_rip; @@ -963,6 +965,18 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } +static void disable_nmi_singlestep(struct vcpu_svm *svm) +{ + svm->nmi_singlestep = false; + if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) { + /* Clear our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + svm->vmcb->save.rflags &= ~X86_EFLAGS_RF; + } +} + /* Note: * This hash table is used to map VM_ID to a struct kvm_arch, * when handling AMD IOMMU GALOG notification to schedule in @@ -1272,7 +1286,8 @@ static void init_vmcb(struct vcpu_svm *svm) } -static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index) +static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, + unsigned int index) { u64 *avic_physical_id_table; struct kvm_arch *vm_data = &vcpu->kvm->arch; @@ -1711,11 +1726,24 @@ static void svm_vcpu_unblocking(struct kvm_vcpu *vcpu) static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { - return to_svm(vcpu)->vmcb->save.rflags; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long rflags = svm->vmcb->save.rflags; + + if (svm->nmi_singlestep) { + /* Hide our flags if they were not set by the guest */ + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF)) + rflags &= ~X86_EFLAGS_TF; + if (!(svm->nmi_singlestep_guest_rflags & X86_EFLAGS_RF)) + rflags &= ~X86_EFLAGS_RF; + } + return rflags; } static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + if (to_svm(vcpu)->nmi_singlestep) + rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); + /* * Any change of EFLAGS.VM is accompanied by a reload of SS * (caused by either a task switch or an inter-privilege IRET), @@ -1806,7 +1834,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, * AMD's VMCB does not have an explicit unusable field, so emulate it * for cross vendor migration purposes by "not present" */ - var->unusable = !var->present || (var->type == 0); + var->unusable = !var->present; switch (seg) { case VCPU_SREG_TR: @@ -1839,6 +1867,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, */ if (var->unusable) var->db = 0; + /* This is symmetric with svm_set_segment() */ var->dpl = to_svm(vcpu)->vmcb->save.cpl; break; } @@ -1979,18 +2008,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->base = var->base; s->limit = var->limit; s->selector = var->selector; - if (var->unusable) - s->attrib = 0; - else { - s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); - s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; - s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; - s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT; - s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; - s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; - s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; - s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; - } + s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK); + s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT; + s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT; + s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT; + s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT; + s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT; + s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; + s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; /* * This is always accurate, except if SYSRET returned to a segment @@ -1999,7 +2024,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, * would entail passing the CPL to userspace and back. */ if (seg == VCPU_SREG_SS) - svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + /* This is symmetric with svm_get_segment() */ + svm->vmcb->save.cpl = (var->dpl & 3); mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2112,10 +2138,7 @@ static int db_interception(struct vcpu_svm *svm) } if (svm->nmi_singlestep) { - svm->nmi_singlestep = false; - if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) - svm->vmcb->save.rflags &= - ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + disable_nmi_singlestep(svm); } if (svm->vcpu.guest_debug & @@ -2370,8 +2393,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static int nested_svm_check_permissions(struct vcpu_svm *svm) { - if (!(svm->vcpu.arch.efer & EFER_SVME) - || !is_paging(&svm->vcpu)) { + if (!(svm->vcpu.arch.efer & EFER_SVME) || + !is_paging(&svm->vcpu)) { kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } @@ -2381,7 +2404,7 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm) return 1; } - return 0; + return 0; } static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, @@ -2534,6 +2557,31 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST; } +/* DB exceptions for our internal use must not cause vmexit */ +static int nested_svm_intercept_db(struct vcpu_svm *svm) +{ + unsigned long dr6; + + /* if we're not singlestepping, it's not ours */ + if (!svm->nmi_singlestep) + return NESTED_EXIT_DONE; + + /* if it's not a singlestep exception, it's not ours */ + if (kvm_get_dr(&svm->vcpu, 6, &dr6)) + return NESTED_EXIT_DONE; + if (!(dr6 & DR6_BS)) + return NESTED_EXIT_DONE; + + /* if the guest is singlestepping, it should get the vmexit */ + if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { + disable_nmi_singlestep(svm); + return NESTED_EXIT_DONE; + } + + /* it's ours, the nested hypervisor must not see this one */ + return NESTED_EXIT_HOST; +} + static int nested_svm_exit_special(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; @@ -2589,8 +2637,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm) } case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); - if (svm->nested.intercept_exceptions & excp_bits) - vmexit = NESTED_EXIT_DONE; + if (svm->nested.intercept_exceptions & excp_bits) { + if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) + vmexit = nested_svm_intercept_db(svm); + else + vmexit = NESTED_EXIT_DONE; + } /* async page fault always cause vmexit */ else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && svm->apf_reason != 0) @@ -4627,10 +4679,17 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) == HF_NMI_MASK) return; /* IRET will cause a vm exit */ + if ((svm->vcpu.arch.hflags & HF_GIF_MASK) == 0) + return; /* STGI will cause a vm exit */ + + if (svm->nested.exit_required) + return; /* we're not going to run the guest yet */ + /* * Something prevents NMI from been injected. Single step over possible * problem (IRET or exception injection or interrupt shadow) */ + svm->nmi_singlestep_guest_rflags = svm_get_rflags(vcpu); svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); } @@ -4771,6 +4830,22 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->nested.exit_required)) return; + /* + * Disable singlestep if we're injecting an interrupt/exception. + * We don't want our modified rflags to be pushed on the stack where + * we might not be able to easily reset them if we disabled NMI + * singlestep later. + */ + if (svm->nmi_singlestep && svm->vmcb->control.event_inj) { + /* + * Event injection happens before external interrupts cause a + * vmexit and interrupts are disabled here, so smp_send_reschedule + * is enough to force an immediate vmexit. + */ + disable_nmi_singlestep(svm); + smp_send_reschedule(vcpu->cpu); + } + pre_svm_run(svm); sync_lapic_to_cr8(vcpu); @@ -4907,6 +4982,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) mark_all_clean(svm->vmcb); } +STACK_FRAME_NON_STANDARD(svm_vcpu_run); static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c6f4ad44aa95..f76efad248ab 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -33,6 +33,7 @@ #include <linux/slab.h> #include <linux/tboot.h> #include <linux/hrtimer.h> +#include <linux/frame.h> #include "kvm_cache_regs.h" #include "x86.h" @@ -48,6 +49,7 @@ #include <asm/kexec.h> #include <asm/apic.h> #include <asm/irq_remapping.h> +#include <asm/mmu_context.h> #include "trace.h" #include "pmu.h" @@ -596,6 +598,7 @@ struct vcpu_vmx { int gs_ldt_reload_needed; int fs_reload_needed; u64 msr_host_bndcfgs; + unsigned long vmcs_host_cr3; /* May not match real cr3 */ unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { @@ -910,8 +913,9 @@ static void nested_release_page_clean(struct page *page) kvm_release_page_clean(page); } +static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu); static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); -static u64 construct_eptp(unsigned long root_hpa); +static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa); static bool vmx_xsaves_supported(void); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, @@ -2425,7 +2429,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr) if (!(vmcs12->exception_bitmap & (1u << nr))) return 0; - nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason, + nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, vmcs_read32(VM_EXIT_INTR_INFO), vmcs_readl(EXIT_QUALIFICATION)); return 1; @@ -2769,7 +2773,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) if (enable_ept_ad_bits) { vmx->nested.nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_PML; - vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; + vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT; } } else vmx->nested.nested_vmx_ept_caps = 0; @@ -3195,7 +3199,8 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP); break; case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) + if (!kvm_mpx_supported() || + (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -3277,7 +3282,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) + if (!kvm_mpx_supported() || + (!msr_info->host_initiated && !guest_cpuid_has_mpx(vcpu))) + return 1; + if (is_noncanonical_address(data & PAGE_MASK) || + (data & MSR_IA32_BNDCFGS_RSVD)) return 1; vmcs_write64(GUEST_BNDCFGS, data); break; @@ -4010,7 +4019,7 @@ static inline void __vmx_flush_tlb(struct kvm_vcpu *vcpu, int vpid) if (enable_ept) { if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - ept_sync_context(construct_eptp(vcpu->arch.mmu.root_hpa)); + ept_sync_context(construct_eptp(vcpu, vcpu->arch.mmu.root_hpa)); } else { vpid_sync_context(vpid); } @@ -4185,14 +4194,15 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) vmx->emulation_required = emulation_required(vcpu); } -static u64 construct_eptp(unsigned long root_hpa) +static u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa) { u64 eptp; /* TODO write the value reading from MSR */ eptp = VMX_EPT_DEFAULT_MT | VMX_EPT_DEFAULT_GAW << VMX_EPT_GAW_EPTP_SHIFT; - if (enable_ept_ad_bits) + if (enable_ept_ad_bits && + (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu))) eptp |= VMX_EPT_AD_ENABLE_BIT; eptp |= (root_hpa & PAGE_MASK); @@ -4206,7 +4216,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) guest_cr3 = cr3; if (enable_ept) { - eptp = construct_eptp(cr3); + eptp = construct_eptp(vcpu, cr3); vmcs_write64(EPT_POINTER, eptp); if (is_paging(vcpu) || is_guest_mode(vcpu)) guest_cr3 = kvm_read_cr3(vcpu); @@ -5012,12 +5022,19 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; - unsigned long cr0, cr4; + unsigned long cr0, cr3, cr4; cr0 = read_cr0(); WARN_ON(cr0 & X86_CR0_TS); vmcs_writel(HOST_CR0, cr0); /* 22.2.3 */ - vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + + /* + * Save the most likely value for this task's CR3 in the VMCS. + * We can't use __get_current_cr3_fast() because we're not atomic. + */ + cr3 = __read_cr3(); + vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */ + vmx->host_state.vmcs_host_cr3 = cr3; /* Save the most likely value for this task's CR4 in the VMCS. */ cr4 = cr4_read_shadow(); @@ -5160,7 +5177,8 @@ static void ept_set_mmio_spte_mask(void) * EPT Misconfigurations can be generated if the value of bits 2:0 * of an EPT paging-structure entry is 110b (write/execute). */ - kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE); + kvm_mmu_set_mmio_spte_mask(VMX_EPT_RWX_MASK, + VMX_EPT_MISCONFIG_WX_VALUE); } #define VMX_XSS_EXIT_BITMAP 0 @@ -6210,17 +6228,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - if (is_guest_mode(vcpu) - && !(exit_qualification & EPT_VIOLATION_GVA_TRANSLATED)) { - /* - * Fix up exit_qualification according to whether guest - * page table accesses are reads or writes. - */ - u64 eptp = nested_ept_get_cr3(vcpu); - if (!(eptp & VMX_EPT_AD_ENABLE_BIT)) - exit_qualification &= ~EPT_VIOLATION_ACC_WRITE; - } - /* * EPT violation happened while executing iret from NMI, * "blocked by NMI" bit has to be set before next VM entry. @@ -6443,7 +6450,7 @@ void vmx_enable_tdp(void) enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull, 0ull, VMX_EPT_EXECUTABLE_MASK, cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK, - enable_ept_ad_bits ? 0ull : VMX_EPT_RWX_MASK); + VMX_EPT_RWX_MASK); ept_set_mmio_spte_mask(); kvm_enable_tdp(); @@ -6504,7 +6511,7 @@ static __init int hardware_setup(void) enable_ept_ad_bits = 0; } - if (!cpu_has_vmx_ept_ad_bits()) + if (!cpu_has_vmx_ept_ad_bits() || !enable_ept) enable_ept_ad_bits = 0; if (!cpu_has_vmx_unrestricted_guest()) @@ -6547,7 +6554,6 @@ static __init int hardware_setup(void) vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false); vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false); - vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true); memcpy(vmx_msr_bitmap_legacy_x2apic_apicv, vmx_msr_bitmap_legacy, PAGE_SIZE); @@ -6914,97 +6920,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, return 0; } -/* - * This function performs the various checks including - * - if it's 4KB aligned - * - No bits beyond the physical address width are set - * - Returns 0 on success or else 1 - * (Intel SDM Section 30.3) - */ -static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, - gpa_t *vmpointer) +static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer) { gva_t gva; - gpa_t vmptr; struct x86_exception e; - struct page *page; - struct vcpu_vmx *vmx = to_vmx(vcpu); - int maxphyaddr = cpuid_maxphyaddr(vcpu); if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva)) return 1; - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer, + sizeof(*vmpointer), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } - switch (exit_reason) { - case EXIT_REASON_VMON: - /* - * SDM 3: 24.11.5 - * The first 4 bytes of VMXON region contain the supported - * VMCS revision identifier - * - * Note - IA32_VMX_BASIC[48] will never be 1 - * for the nested case; - * which replaces physical address width with 32 - * - */ - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - - page = nested_get_page(vcpu, vmptr); - if (page == NULL) { - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - if (*(u32 *)kmap(page) != VMCS12_REVISION) { - kunmap(page); - nested_release_page_clean(page); - nested_vmx_failInvalid(vcpu); - return kvm_skip_emulated_instruction(vcpu); - } - kunmap(page); - nested_release_page_clean(page); - vmx->nested.vmxon_ptr = vmptr; - break; - case EXIT_REASON_VMCLEAR: - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failValid(vcpu, - VMXERR_VMCLEAR_INVALID_ADDRESS); - return kvm_skip_emulated_instruction(vcpu); - } - - if (vmptr == vmx->nested.vmxon_ptr) { - nested_vmx_failValid(vcpu, - VMXERR_VMCLEAR_VMXON_POINTER); - return kvm_skip_emulated_instruction(vcpu); - } - break; - case EXIT_REASON_VMPTRLD: - if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) { - nested_vmx_failValid(vcpu, - VMXERR_VMPTRLD_INVALID_ADDRESS); - return kvm_skip_emulated_instruction(vcpu); - } - - if (vmptr == vmx->nested.vmxon_ptr) { - nested_vmx_failValid(vcpu, - VMXERR_VMPTRLD_VMXON_POINTER); - return kvm_skip_emulated_instruction(vcpu); - } - break; - default: - return 1; /* shouldn't happen */ - } - - if (vmpointer) - *vmpointer = vmptr; return 0; } @@ -7066,6 +6996,8 @@ out_msr_bitmap: static int handle_vmon(struct kvm_vcpu *vcpu) { int ret; + gpa_t vmptr; + struct page *page; struct vcpu_vmx *vmx = to_vmx(vcpu); const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; @@ -7095,9 +7027,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; - + + /* + * SDM 3: 24.11.5 + * The first 4 bytes of VMXON region contain the supported + * VMCS revision identifier + * + * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case; + * which replaces physical address width with 32 + */ + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + + page = nested_get_page(vcpu, vmptr); + if (page == NULL) { + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + if (*(u32 *)kmap(page) != VMCS12_REVISION) { + kunmap(page); + nested_release_page_clean(page); + nested_vmx_failInvalid(vcpu); + return kvm_skip_emulated_instruction(vcpu); + } + kunmap(page); + nested_release_page_clean(page); + + vmx->nested.vmxon_ptr = vmptr; ret = enter_vmx_operation(vcpu); if (ret) return ret; @@ -7213,9 +7173,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); + return kvm_skip_emulated_instruction(vcpu); + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); + return kvm_skip_emulated_instruction(vcpu); + } + if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vmx); @@ -7545,9 +7515,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr)) + if (nested_vmx_get_vmptr(vcpu, &vmptr)) return 1; + if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) { + nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); + return kvm_skip_emulated_instruction(vcpu); + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); + return kvm_skip_emulated_instruction(vcpu); + } + if (vmx->nested.current_vmptr != vmptr) { struct vmcs12 *new_vmcs12; struct page *page; @@ -7677,7 +7657,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) unsigned long type, types; gva_t gva; struct x86_exception e; - int vpid; + struct { + u64 vpid; + u64 gla; + } operand; if (!(vmx->nested.nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_VPID) || @@ -7707,17 +7690,28 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), vmx_instruction_info, false, &gva)) return 1; - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vpid, - sizeof(u32), &e)) { + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, + sizeof(operand), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } + if (operand.vpid >> 16) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return kvm_skip_emulated_instruction(vcpu); + } switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + if (is_noncanonical_address(operand.gla)) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return kvm_skip_emulated_instruction(vcpu); + } + /* fall through */ case VMX_VPID_EXTENT_SINGLE_CONTEXT: case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: - if (!vpid) { + if (!operand.vpid) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); return kvm_skip_emulated_instruction(vcpu); @@ -7913,11 +7907,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); int cr = exit_qualification & 15; - int reg = (exit_qualification >> 8) & 15; - unsigned long val = kvm_register_readl(vcpu, reg); + int reg; + unsigned long val; switch ((exit_qualification >> 4) & 3) { case 0: /* mov to cr */ + reg = (exit_qualification >> 8) & 15; + val = kvm_register_readl(vcpu, reg); switch (cr) { case 0: if (vmcs12->cr0_guest_host_mask & @@ -7972,6 +7968,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, * lmsw can change bits 1..3 of cr0, and only set bit 0 of * cr0. Other attempted changes are ignored, with no exit. */ + val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) return true; @@ -8675,6 +8672,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu) ); } } +STACK_FRAME_NON_STANDARD(vmx_handle_external_intr); static bool vmx_has_high_real_mode_segbase(void) { @@ -8843,7 +8841,7 @@ static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr, cr4; + unsigned long debugctlmsr, cr3, cr4; /* Don't enter VMX if guest state is invalid, let the exit handler start emulation until we arrive back to a valid state */ @@ -8865,6 +8863,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->host_state.vmcs_host_cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { vmcs_writel(HOST_CR4, cr4); @@ -9051,6 +9055,7 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); } +STACK_FRAME_NON_STANDARD(vmx_vcpu_run); static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs) { @@ -9399,6 +9404,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vmcs12->guest_physical_address = fault->address; } +static bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu) +{ + return nested_ept_get_cr3(vcpu) & VMX_EPT_AD_ENABLE_BIT; +} + /* Callbacks for nested_ept_init_mmu_context: */ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) @@ -9409,18 +9419,18 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) { - u64 eptp; + bool wants_ad; WARN_ON(mmu_is_nested(vcpu)); - eptp = nested_ept_get_cr3(vcpu); - if ((eptp & VMX_EPT_AD_ENABLE_BIT) && !enable_ept_ad_bits) + wants_ad = nested_ept_ad_enabled(vcpu); + if (wants_ad && !enable_ept_ad_bits) return 1; kvm_mmu_unload(vcpu); kvm_init_shadow_ept_mmu(vcpu, to_vmx(vcpu)->nested.nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT, - eptp & VMX_EPT_AD_ENABLE_BIT); + wants_ad); vcpu->arch.mmu.set_cr3 = vmx_set_cr3; vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3; vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; @@ -10733,8 +10743,7 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); } - if (nested_cpu_has_ept(vmcs12)) - vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); + vmcs12->guest_linear_address = vmcs_readl(GUEST_LINEAR_ADDRESS); if (nested_cpu_has_vid(vmcs12)) vmcs12->guest_intr_status = vmcs_read16(GUEST_INTR_STATUS); @@ -10759,8 +10768,6 @@ static void sync_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP); if (kvm_mpx_supported()) vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS); - if (nested_cpu_has_xsaves(vmcs12)) - vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP); } /* @@ -11157,7 +11164,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc) vmx->hv_deadline_tsc = tscl + delta_tsc; vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); - return 0; + + return delta_tsc == 0; } static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu) @@ -11213,7 +11221,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index > PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { vmx->nested.pml_full = true; return 1; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 464da936c53d..6c7266f7766d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1763,6 +1763,7 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + u64 ret; spin_lock(&ka->pvclock_gtod_sync_lock); if (!ka->use_master_clock) { @@ -1774,10 +1775,17 @@ u64 get_kvmclock_ns(struct kvm *kvm) hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; spin_unlock(&ka->pvclock_gtod_sync_lock); + /* both __this_cpu_read() and rdtsc() should be on the same cpu */ + get_cpu(); + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - return __pvclock_read_cycles(&hv_clock, rdtsc()); + ret = __pvclock_read_cycles(&hv_clock, rdtsc()); + + put_cpu(); + + return ret; } static void kvm_setup_pvclock_page(struct kvm_vcpu *v) @@ -2833,10 +2841,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vcpu_write_tsc_offset(vcpu, offset); vcpu->arch.tsc_catchup = 1; } - if (kvm_lapic_hv_timer_in_use(vcpu) && - kvm_x86_ops->set_hv_timer(vcpu, - kvm_get_lapic_target_expiration_tsc(vcpu))) - kvm_lapic_switch_to_sw_timer(vcpu); + + if (kvm_lapic_hv_timer_in_use(vcpu)) + kvm_lapic_restart_hv_timer(vcpu); + /* * On a host with synchronized TSC, there is no need to update * kvmclock on vcpu->cpu migration @@ -3288,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, } } +#define XSAVE_MXCSR_OFFSET 24 + static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { u64 xstate_bv = *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)]; + u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)]; if (boot_cpu_has(X86_FEATURE_XSAVE)) { /* @@ -3300,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, * CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility * with old userspace. */ - if (xstate_bv & ~kvm_supported_xcr0()) + if (xstate_bv & ~kvm_supported_xcr0() || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; load_xsave(vcpu, (u8 *)guest_xsave->region); } else { - if (xstate_bv & ~XFEATURE_MASK_FPSSE) + if (xstate_bv & ~XFEATURE_MASK_FPSSE || + mxcsr & ~mxcsr_feature_mask) return -EINVAL; memcpy(&vcpu->arch.guest_fpu.state.fxsave, guest_xsave->region, sizeof(struct fxregs_state)); @@ -4818,16 +4831,20 @@ emul_write: static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) { - /* TODO: String I/O for in kernel device */ - int r; + int r = 0, i; - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); - else - r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, - vcpu->arch.pio.port, vcpu->arch.pio.size, - pd); + for (i = 0; i < vcpu->arch.pio.count; i++) { + if (vcpu->arch.pio.in) + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, + vcpu->arch.pio.size, pd); + else + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + if (r) + break; + pd += vcpu->arch.pio.size; + } return r; } @@ -4865,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (vcpu->arch.pio.count) goto data_avail; + memset(vcpu->arch.pio_data, 0, size * count); + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); if (ret) { data_avail: @@ -5048,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector, if (var.unusable) { memset(desc, 0, sizeof(*desc)); + if (base3) + *base3 = 0; return false; } @@ -5292,6 +5313,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); ctxt->eflags = kvm_get_rflags(vcpu); + ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; + ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : @@ -5507,36 +5530,25 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, return dr6; } -static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r) +static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r) { struct kvm_run *kvm_run = vcpu->run; - /* - * rflags is the old, "raw" value of the flags. The new value has - * not been saved yet. - * - * This is correct even for TF set by the guest, because "the - * processor will not generate this exception after the instruction - * that sets the TF flag". - */ - if (unlikely(rflags & X86_EFLAGS_TF)) { - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | - DR6_RTM; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; - *r = EMULATE_USER_EXIT; - } else { - /* - * "Certain debug exceptions may clear bit 0-3. The - * remaining contents of the DR6 register are never - * cleared by the processor". - */ - vcpu->arch.dr6 &= ~15; - vcpu->arch.dr6 |= DR6_BS | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + } else { + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS | DR6_RTM; + kvm_queue_exception(vcpu, DB_VECTOR); } } @@ -5546,7 +5558,17 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) int r = EMULATE_DONE; kvm_x86_ops->skip_emulated_instruction(vcpu); - kvm_vcpu_check_singlestep(vcpu, rflags, &r); + + /* + * rflags is the old, "raw" value of the flags. The new value has + * not been saved yet. + * + * This is correct even for TF set by the guest, because "the + * processor will not generate this exception after the instruction + * that sets the TF flag". + */ + if (unlikely(rflags & X86_EFLAGS_TF)) + kvm_vcpu_do_singlestep(vcpu, &r); return r == EMULATE_DONE; } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); @@ -5705,8 +5727,9 @@ restart: toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rip_write(vcpu, ctxt->eip); - if (r == EMULATE_DONE) - kvm_vcpu_check_singlestep(vcpu, rflags, &r); + if (r == EMULATE_DONE && + (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) + kvm_vcpu_do_singlestep(vcpu, &r); if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) __kvm_set_rflags(vcpu, ctxt->eflags); @@ -5988,7 +6011,7 @@ static void kvm_set_mmio_spte_mask(void) mask &= ~1ull; #endif - kvm_mmu_set_mmio_spte_mask(mask); + kvm_mmu_set_mmio_spte_mask(mask, mask); } #ifdef CONFIG_X86_64 @@ -6710,7 +6733,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; - if (vcpu->requests) { + if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) kvm_mmu_unload(vcpu); if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu)) @@ -6874,7 +6897,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->sync_pir_to_irr(vcpu); } - if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests + if (vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || need_resched() || signal_pending(current)) { vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); @@ -8373,10 +8396,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (vcpu->arch.pv.pv_unhalted) return true; - if (atomic_read(&vcpu->arch.nmi_queued)) + if (kvm_test_request(KVM_REQ_NMI, vcpu) || + (vcpu->arch.nmi_pending && + kvm_x86_ops->nmi_allowed(vcpu))) return true; - if (kvm_test_request(KVM_REQ_SMI, vcpu)) + if (kvm_test_request(KVM_REQ_SMI, vcpu) || + (vcpu->arch.smi_pending && !is_smm(vcpu))) return true; if (kvm_arch_interrupt_allowed(vcpu) && @@ -8583,8 +8609,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu) if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED)) return true; else - return !kvm_event_needs_reinjection(vcpu) && - kvm_x86_ops->interrupt_allowed(vcpu); + return kvm_can_do_async_pf(vcpu); } void kvm_arch_start_assignment(struct kvm *kvm) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index c5959576c315..020f75cc8cf6 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -37,7 +37,7 @@ ENTRY(copy_user_generic_unrolled) movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_copy_short_string 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -58,7 +58,8 @@ ENTRY(copy_user_generic_unrolled) leaq 64(%rdi),%rdi decl %ecx jnz 1b -17: movl %edx,%ecx +.L_copy_short_string: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx jz 20f @@ -174,6 +175,8 @@ EXPORT_SYMBOL(copy_user_generic_string) */ ENTRY(copy_user_enhanced_fast_string) ASM_STAC + cmpl $64,%edx + jb .L_copy_short_string /* less then 64 bytes, avoid the costly 'rep' */ movl %edx,%ecx 1: rep movsb diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index c81556409bbb..10ffa7e8519f 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -13,14 +13,14 @@ .macro op_safe_regs op ENTRY(\op\()_safe_regs) pushq %rbx - pushq %rbp + pushq %r12 movq %rdi, %r10 /* Save pointer */ xorl %r11d, %r11d /* Return value */ movl (%rdi), %eax movl 4(%rdi), %ecx movl 8(%rdi), %edx movl 12(%rdi), %ebx - movl 20(%rdi), %ebp + movl 20(%rdi), %r12d movl 24(%rdi), %esi movl 28(%rdi), %edi 1: \op @@ -29,10 +29,10 @@ ENTRY(\op\()_safe_regs) movl %ecx, 4(%r10) movl %edx, 8(%r10) movl %ebx, 12(%r10) - movl %ebp, 20(%r10) + movl %r12d, 20(%r10) movl %esi, 24(%r10) movl %edi, 28(%r10) - popq %rbp + popq %r12 popq %rbx ret 3: diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 3b7c40a2e3e1..75d3776123cc 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -7,6 +7,7 @@ */ #include <linux/export.h> #include <linux/uaccess.h> +#include <linux/highmem.h> /* * Zero Userspace @@ -73,3 +74,136 @@ copy_user_handle_tail(char *to, char *from, unsigned len) clac(); return len; } + +#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +/** + * clean_cache_range - write back a cache range with CLWB + * @vaddr: virtual start address + * @size: number of bytes to write back + * + * Write back a cache range using the CLWB (cache line write back) + * instruction. Note that @size is internally rounded up to be cache + * line size aligned. + */ +static void clean_cache_range(void *addr, size_t size) +{ + u16 x86_clflush_size = boot_cpu_data.x86_clflush_size; + unsigned long clflush_mask = x86_clflush_size - 1; + void *vend = addr + size; + void *p; + + for (p = (void *)((unsigned long)addr & ~clflush_mask); + p < vend; p += x86_clflush_size) + clwb(p); +} + +void arch_wb_cache_pmem(void *addr, size_t size) +{ + clean_cache_range(addr, size); +} +EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); + +long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) +{ + unsigned long flushed, dest = (unsigned long) dst; + long rc = __copy_user_nocache(dst, src, size, 0); + + /* + * __copy_user_nocache() uses non-temporal stores for the bulk + * of the transfer, but we need to manually flush if the + * transfer is unaligned. A cached memory copy is used when + * destination or size is not naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. + */ + if (size < 8) { + if (!IS_ALIGNED(dest, 4) || size != 4) + clean_cache_range(dst, 1); + } else { + if (!IS_ALIGNED(dest, 8)) { + dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); + clean_cache_range(dst, 1); + } + + flushed = dest - (unsigned long) dst; + if (size > flushed && !IS_ALIGNED(size - flushed, 8)) + clean_cache_range(dst + size - 1, 1); + } + + return rc; +} + +void memcpy_flushcache(void *_dst, const void *_src, size_t size) +{ + unsigned long dest = (unsigned long) _dst; + unsigned long source = (unsigned long) _src; + + /* cache copy and flush to align dest */ + if (!IS_ALIGNED(dest, 8)) { + unsigned len = min_t(unsigned, size, ALIGN(dest, 8) - dest); + + memcpy((void *) dest, (void *) source, len); + clean_cache_range((void *) dest, len); + dest += len; + source += len; + size -= len; + if (!size) + return; + } + + /* 4x8 movnti loop */ + while (size >= 32) { + asm("movq (%0), %%r8\n" + "movq 8(%0), %%r9\n" + "movq 16(%0), %%r10\n" + "movq 24(%0), %%r11\n" + "movnti %%r8, (%1)\n" + "movnti %%r9, 8(%1)\n" + "movnti %%r10, 16(%1)\n" + "movnti %%r11, 24(%1)\n" + :: "r" (source), "r" (dest) + : "memory", "r8", "r9", "r10", "r11"); + dest += 32; + source += 32; + size -= 32; + } + + /* 1x8 movnti loop */ + while (size >= 8) { + asm("movq (%0), %%r8\n" + "movnti %%r8, (%1)\n" + :: "r" (source), "r" (dest) + : "memory", "r8"); + dest += 8; + source += 8; + size -= 8; + } + + /* 1x4 movnti loop */ + while (size >= 4) { + asm("movl (%0), %%r8d\n" + "movnti %%r8d, (%1)\n" + :: "r" (source), "r" (dest) + : "memory", "r8"); + dest += 4; + source += 4; + size -= 4; + } + + /* cache copy for remaining bytes */ + if (size) { + memcpy((void *) dest, (void *) source, size); + clean_cache_range((void *) dest, size); + } +} +EXPORT_SYMBOL_GPL(memcpy_flushcache); + +void memcpy_page_flushcache(char *to, struct page *page, size_t offset, + size_t len) +{ + char *from = kmap_atomic(page); + + memcpy_flushcache(to, from + offset, len); + kunmap_atomic(from); +} +#endif diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 767be7c76034..12e377184ee4 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1009,7 +1009,7 @@ GrpTable: Grp15 1: fxstor | RDGSBASE Ry (F3),(11B) 2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B) 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B) -4: XSAVE +4: XSAVE | ptwrite Ey (F3),(11B) 5: XRSTOR | lfence (11B) 6: XSAVEOPT | clwb (66) | mfence (11B) 7: clflush | clflushopt (66) | sfence (11B) diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h index 5e044d506b7a..a179254a5122 100644 --- a/arch/x86/math-emu/fpu_system.h +++ b/arch/x86/math-emu/fpu_system.h @@ -27,7 +27,7 @@ static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg) #ifdef CONFIG_MODIFY_LDT_SYSCALL seg >>= 3; mutex_lock(¤t->mm->context.lock); - if (current->mm->context.ldt && seg < current->mm->context.ldt->size) + if (current->mm->context.ldt && seg < current->mm->context.ldt->nr_entries) ret = current->mm->context.ldt->entries[seg]; mutex_unlock(¤t->mm->context.lock); #endif diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 96d2b847e09e..0fbdcb64f9f8 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -2,7 +2,7 @@ KCOV_INSTRUMENT_tlb.o := n obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index bce6990b1d81..0470826d2bdc 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -431,7 +431,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, bool checkwx) { #ifdef CONFIG_X86_64 - pgd_t *start = (pgd_t *) &init_level4_pgt; + pgd_t *start = (pgd_t *) &init_top_pgt; #else pgd_t *start = swapper_pg_dir; #endif diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 35ea061010a1..0ea8afcb929c 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -162,6 +162,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) if (fixup_exception(regs, trapnr)) return; + if (fixup_bug(regs, trapnr)) + return; + fail: early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8ad91a01cbc8..2a1fa10c6a98 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -346,7 +346,7 @@ static noinline int vmalloc_fault(unsigned long address) * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ - pgd_paddr = read_cr3(); + pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; @@ -388,7 +388,7 @@ static bool low_pfn(unsigned long pfn) static void dump_pagetable(unsigned long address) { - pgd_t *base = __va(read_cr3()); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; @@ -451,7 +451,7 @@ static noinline int vmalloc_fault(unsigned long address) * happen within a race in page table update. In the later * case just flush: */ - pgd = (pgd_t *)__va(read_cr3()) + pgd_index(address); + pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(address); pgd_ref = pgd_offset_k(address); if (pgd_none(*pgd_ref)) return -1; @@ -555,7 +555,7 @@ static int bad_address(void *p) static void dump_pagetable(unsigned long address) { - pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; @@ -700,7 +700,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, pgd_t *pgd; pte_t *pte; - pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK); + pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd(pgd, address, &level); diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c deleted file mode 100644 index 456dfdfd2249..000000000000 --- a/arch/x86/mm/gup.c +++ /dev/null @@ -1,496 +0,0 @@ -/* - * Lockless get_user_pages_fast for x86 - * - * Copyright (C) 2008 Nick Piggin - * Copyright (C) 2008 Novell Inc. - */ -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmstat.h> -#include <linux/highmem.h> -#include <linux/swap.h> -#include <linux/memremap.h> - -#include <asm/mmu_context.h> -#include <asm/pgtable.h> - -static inline pte_t gup_get_pte(pte_t *ptep) -{ -#ifndef CONFIG_X86_PAE - return READ_ONCE(*ptep); -#else - /* - * With get_user_pages_fast, we walk down the pagetables without taking - * any locks. For this we would like to load the pointers atomically, - * but that is not possible (without expensive cmpxchg8b) on PAE. What - * we do have is the guarantee that a pte will only either go from not - * present to present, or present to not present or both -- it will not - * switch to a completely different present page without a TLB flush in - * between; something that we are blocking by holding interrupts off. - * - * Setting ptes from not present to present goes: - * ptep->pte_high = h; - * smp_wmb(); - * ptep->pte_low = l; - * - * And present to not present goes: - * ptep->pte_low = 0; - * smp_wmb(); - * ptep->pte_high = 0; - * - * We must ensure here that the load of pte_low sees l iff pte_high - * sees h. We load pte_high *after* loading pte_low, which ensures we - * don't see an older value of pte_high. *Then* we recheck pte_low, - * which ensures that we haven't picked up a changed pte high. We might - * have got rubbish values from pte_low and pte_high, but we are - * guaranteed that pte_low will not have the present bit set *unless* - * it is 'l'. And get_user_pages_fast only operates on present ptes, so - * we're safe. - * - * gup_get_pte should not be used or copied outside gup.c without being - * very careful -- it does not atomically load the pte or anything that - * is likely to be useful for you. - */ - pte_t pte; - -retry: - pte.pte_low = ptep->pte_low; - smp_rmb(); - pte.pte_high = ptep->pte_high; - smp_rmb(); - if (unlikely(pte.pte_low != ptep->pte_low)) - goto retry; - - return pte; -#endif -} - -static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages) -{ - while ((*nr) - nr_start) { - struct page *page = pages[--(*nr)]; - - ClearPageReferenced(page); - put_page(page); - } -} - -/* - * 'pteval' can come from a pte, pmd, pud or p4d. We only check - * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the - * same value on all 4 types. - */ -static inline int pte_allows_gup(unsigned long pteval, int write) -{ - unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; - - if (write) - need_pte_bits |= _PAGE_RW; - - if ((pteval & need_pte_bits) != need_pte_bits) - return 0; - - /* Check memory protection keys permissions. */ - if (!__pkru_allows_pkey(pte_flags_pkey(pteval), write)) - return 0; - - return 1; -} - -/* - * The performance critical leaf functions are made noinline otherwise gcc - * inlines everything into a single function which results in too much - * register pressure. - */ -static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct dev_pagemap *pgmap = NULL; - int nr_start = *nr, ret = 0; - pte_t *ptep, *ptem; - - /* - * Keep the original mapped PTE value (ptem) around since we - * might increment ptep off the end of the page when finishing - * our loop iteration. - */ - ptem = ptep = pte_offset_map(&pmd, addr); - do { - pte_t pte = gup_get_pte(ptep); - struct page *page; - - /* Similar to the PMD case, NUMA hinting must take slow path */ - if (pte_protnone(pte)) - break; - - if (!pte_allows_gup(pte_val(pte), write)) - break; - - if (pte_devmap(pte)) { - pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - break; - } - } else if (pte_special(pte)) - break; - - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - page = pte_page(pte); - get_page(page); - put_dev_pagemap(pgmap); - SetPageReferenced(page); - pages[*nr] = page; - (*nr)++; - - } while (ptep++, addr += PAGE_SIZE, addr != end); - if (addr == end) - ret = 1; - pte_unmap(ptem); - - return ret; -} - -static inline void get_head_page_multiple(struct page *page, int nr) -{ - VM_BUG_ON_PAGE(page != compound_head(page), page); - VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_add(page, nr); - SetPageReferenced(page); -} - -static int __gup_device_huge(unsigned long pfn, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - int nr_start = *nr; - struct dev_pagemap *pgmap = NULL; - - do { - struct page *page = pfn_to_page(pfn); - - pgmap = get_dev_pagemap(pfn, pgmap); - if (unlikely(!pgmap)) { - undo_dev_pagemap(nr, nr_start, pages); - return 0; - } - SetPageReferenced(page); - pages[*nr] = page; - get_page(page); - put_dev_pagemap(pgmap); - (*nr)++; - pfn++; - } while (addr += PAGE_SIZE, addr != end); - return 1; -} - -static int __gup_device_huge_pmd(pmd_t pmd, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - unsigned long fault_pfn; - - fault_pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - return __gup_device_huge(fault_pfn, addr, end, pages, nr); -} - -static int __gup_device_huge_pud(pud_t pud, unsigned long addr, - unsigned long end, struct page **pages, int *nr) -{ - unsigned long fault_pfn; - - fault_pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - return __gup_device_huge(fault_pfn, addr, end, pages, nr); -} - -static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct page *head, *page; - int refs; - - if (!pte_allows_gup(pmd_val(pmd), write)) - return 0; - - VM_BUG_ON(!pfn_valid(pmd_pfn(pmd))); - if (pmd_devmap(pmd)) - return __gup_device_huge_pmd(pmd, addr, end, pages, nr); - - /* hugepages are never "special" */ - VM_BUG_ON(pmd_flags(pmd) & _PAGE_SPECIAL); - - refs = 0; - head = pmd_page(pmd); - page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - get_head_page_multiple(head, refs); - - return 1; -} - -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pmd_t *pmdp; - - pmdp = pmd_offset(&pud, addr); - do { - pmd_t pmd = *pmdp; - - next = pmd_addr_end(addr, end); - if (pmd_none(pmd)) - return 0; - if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { - /* - * NUMA hinting faults need to be handled in the GUP - * slowpath for accounting purposes and so that they - * can be serialised against THP migration. - */ - if (pmd_protnone(pmd)) - return 0; - if (!gup_huge_pmd(pmd, addr, next, write, pages, nr)) - return 0; - } else { - if (!gup_pte_range(pmd, addr, next, write, pages, nr)) - return 0; - } - } while (pmdp++, addr = next, addr != end); - - return 1; -} - -static noinline int gup_huge_pud(pud_t pud, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) -{ - struct page *head, *page; - int refs; - - if (!pte_allows_gup(pud_val(pud), write)) - return 0; - - VM_BUG_ON(!pfn_valid(pud_pfn(pud))); - if (pud_devmap(pud)) - return __gup_device_huge_pud(pud, addr, end, pages, nr); - - /* hugepages are never "special" */ - VM_BUG_ON(pud_flags(pud) & _PAGE_SPECIAL); - - refs = 0; - head = pud_page(pud); - page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - do { - VM_BUG_ON_PAGE(compound_head(page) != head, page); - pages[*nr] = page; - (*nr)++; - page++; - refs++; - } while (addr += PAGE_SIZE, addr != end); - get_head_page_multiple(head, refs); - - return 1; -} - -static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - pud_t *pudp; - - pudp = pud_offset(&p4d, addr); - do { - pud_t pud = *pudp; - - next = pud_addr_end(addr, end); - if (pud_none(pud)) - return 0; - if (unlikely(pud_large(pud))) { - if (!gup_huge_pud(pud, addr, next, write, pages, nr)) - return 0; - } else { - if (!gup_pmd_range(pud, addr, next, write, pages, nr)) - return 0; - } - } while (pudp++, addr = next, addr != end); - - return 1; -} - -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, - int write, struct page **pages, int *nr) -{ - unsigned long next; - p4d_t *p4dp; - - p4dp = p4d_offset(&pgd, addr); - do { - p4d_t p4d = *p4dp; - - next = p4d_addr_end(addr, end); - if (p4d_none(p4d)) - return 0; - BUILD_BUG_ON(p4d_large(p4d)); - if (!gup_pud_range(p4d, addr, next, write, pages, nr)) - return 0; - } while (p4dp++, addr = next, addr != end); - - return 1; -} - -/* - * Like get_user_pages_fast() except its IRQ-safe in that it won't fall - * back to the regular GUP. - */ -int __get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - unsigned long flags; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - end = start + len; - if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ, - (void __user *)start, len))) - return 0; - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed on x86. - * - * So long as we atomically load page table pointers versus teardown - * (which we do on x86, with the above PAE exception), we can follow the - * address down to the the page and take a ref on it. - */ - local_irq_save(flags); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - break; - if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) - break; - } while (pgdp++, addr = next, addr != end); - local_irq_restore(flags); - - return nr; -} - -/** - * get_user_pages_fast() - pin user pages in memory - * @start: starting user address - * @nr_pages: number of pages from start to pin - * @write: whether pages will be written to - * @pages: array that receives pointers to the pages pinned. - * Should be at least nr_pages long. - * - * Attempt to pin user pages in memory without taking mm->mmap_sem. - * If not successful, it will fall back to taking the lock and - * calling get_user_pages(). - * - * Returns number of pages pinned. This may be fewer than the number - * requested. If nr_pages is 0 or negative, returns 0. If no pages - * were pinned, returns -errno. - */ -int get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages) -{ - struct mm_struct *mm = current->mm; - unsigned long addr, len, end; - unsigned long next; - pgd_t *pgdp; - int nr = 0; - - start &= PAGE_MASK; - addr = start; - len = (unsigned long) nr_pages << PAGE_SHIFT; - - end = start + len; - if (end < start) - goto slow_irqon; - -#ifdef CONFIG_X86_64 - if (end >> __VIRTUAL_MASK_SHIFT) - goto slow_irqon; -#endif - - /* - * XXX: batch / limit 'nr', to avoid large irq off latency - * needs some instrumenting to determine the common sizes used by - * important workloads (eg. DB2), and whether limiting the batch size - * will decrease performance. - * - * It seems like we're in the clear for the moment. Direct-IO is - * the main guy that batches up lots of get_user_pages, and even - * they are limited to 64-at-a-time which is not so many. - */ - /* - * This doesn't prevent pagetable teardown, but does prevent - * the pagetables and pages from being freed on x86. - * - * So long as we atomically load page table pointers versus teardown - * (which we do on x86, with the above PAE exception), we can follow the - * address down to the the page and take a ref on it. - */ - local_irq_disable(); - pgdp = pgd_offset(mm, addr); - do { - pgd_t pgd = *pgdp; - - next = pgd_addr_end(addr, end); - if (pgd_none(pgd)) - goto slow; - if (!gup_p4d_range(pgd, addr, next, write, pages, &nr)) - goto slow; - } while (pgdp++, addr = next, addr != end); - local_irq_enable(); - - VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT); - return nr; - - { - int ret; - -slow: - local_irq_enable(); -slow_irqon: - /* Try to get the remaining pages with get_user_pages */ - start += nr << PAGE_SHIFT; - pages += nr; - - ret = get_user_pages_unlocked(start, - (end - start) >> PAGE_SHIFT, - pages, write ? FOLL_WRITE : 0); - - /* Have to be a bit careful with return values */ - if (nr > 0) { - if (ret < 0) - ret = nr; - else - ret += nr; - } - - return ret; - } -} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 302f43fd9c28..2824607df108 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -33,7 +33,7 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) if (!vma || !is_vm_hugetlb_page(vma)) return ERR_PTR(-EINVAL); - pte = huge_pte_offset(mm, address); + pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); /* hugetlb should be locked, and hence, prefaulted */ WARN_ON(!pte || pte_none(*pte)); @@ -148,7 +148,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (TASK_SIZE - len >= addr && - (!vma || addr + len <= vma->vm_start)) + (!vma || addr + len <= vm_start_gap(vma))) return addr; } if (mm->get_unmapped_area == arch_get_unmapped_area) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index cbc87ea98751..673541eb3b3f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -161,16 +161,16 @@ static int page_size_mask; static void __init probe_page_size_mask(void) { -#if !defined(CONFIG_KMEMCHECK) /* * For CONFIG_KMEMCHECK or pagealloc debugging, identity mapping will * use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ - if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) + if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled() && !IS_ENABLED(CONFIG_KMEMCHECK)) page_size_mask |= 1 << PG_LEVEL_2M; -#endif + else + direct_gbpages = 0; /* Enable PSE if available */ if (boot_cpu_has(X86_FEATURE_PSE)) @@ -811,10 +811,8 @@ void __init zone_sizes_init(void) } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { -#ifdef CONFIG_SMP - .active_mm = &init_mm, + .loaded_mm = &init_mm, .state = 0, -#endif .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; EXPORT_SYMBOL_GPL(cpu_tlbstate); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 99fb83819a5f..8a64a6f2848d 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -823,15 +823,12 @@ void __init mem_init(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int arch_add_memory(int nid, u64 start, u64 size, bool for_device) +int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock) { - struct pglist_data *pgdata = NODE_DATA(nid); - struct zone *zone = pgdata->node_zones + - zone_for_memory(nid, start, size, ZONE_HIGHMEM, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - return __add_pages(nid, zone, start_pfn, nr_pages); + return __add_pages(nid, start_pfn, nr_pages, want_memblock); } #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 95651dc58e09..136422d7d539 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -92,6 +92,44 @@ __setup("noexec32=", nonx32_setup); * When memory was added make sure all the processes MM have * suitable PGD entries in the local PGD level page. */ +#ifdef CONFIG_X86_5LEVEL +void sync_global_pgds(unsigned long start, unsigned long end) +{ + unsigned long addr; + + for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) { + const pgd_t *pgd_ref = pgd_offset_k(addr); + struct page *page; + + /* Check for overflow */ + if (addr < start) + break; + + if (pgd_none(*pgd_ref)) + continue; + + spin_lock(&pgd_lock); + list_for_each_entry(page, &pgd_list, lru) { + pgd_t *pgd; + spinlock_t *pgt_lock; + + pgd = (pgd_t *)page_address(page) + pgd_index(addr); + /* the pgt_lock only for Xen */ + pgt_lock = &pgd_page_get_mm(page)->page_table_lock; + spin_lock(pgt_lock); + + if (!pgd_none(*pgd_ref) && !pgd_none(*pgd)) + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + + spin_unlock(pgt_lock); + } + spin_unlock(&pgd_lock); + } +} +#else void sync_global_pgds(unsigned long start, unsigned long end) { unsigned long addr; @@ -135,6 +173,7 @@ void sync_global_pgds(unsigned long start, unsigned long end) spin_unlock(&pgd_lock); } } +#endif /* * NOTE: This function is marked __ref because it calls __init function @@ -585,6 +624,57 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, return paddr_last; } +static unsigned long __meminit +phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, + unsigned long page_size_mask) +{ + unsigned long paddr_next, paddr_last = paddr_end; + unsigned long vaddr = (unsigned long)__va(paddr); + int i = p4d_index(vaddr); + + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask); + + for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) { + p4d_t *p4d; + pud_t *pud; + + vaddr = (unsigned long)__va(paddr); + p4d = p4d_page + p4d_index(vaddr); + paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + + if (paddr >= paddr_end) { + if (!after_bootmem && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & P4D_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) + set_p4d(p4d, __p4d(0)); + continue; + } + + if (!p4d_none(*p4d)) { + pud = pud_offset(p4d, 0); + paddr_last = phys_pud_init(pud, paddr, + paddr_end, + page_size_mask); + __flush_tlb_all(); + continue; + } + + pud = alloc_low_page(); + paddr_last = phys_pud_init(pud, paddr, paddr_end, + page_size_mask); + + spin_lock(&init_mm.page_table_lock); + p4d_populate(&init_mm, p4d, pud); + spin_unlock(&init_mm.page_table_lock); + } + __flush_tlb_all(); + + return paddr_last; +} + /* * Create page table mapping for the physical memory for specific physical * addresses. The virtual and physical addresses have to be aligned on PMD level @@ -606,26 +696,26 @@ kernel_physical_mapping_init(unsigned long paddr_start, for (; vaddr < vaddr_end; vaddr = vaddr_next) { pgd_t *pgd = pgd_offset_k(vaddr); p4d_t *p4d; - pud_t *pud; vaddr_next = (vaddr & PGDIR_MASK) + PGDIR_SIZE; - BUILD_BUG_ON(pgd_none(*pgd)); - p4d = p4d_offset(pgd, vaddr); - if (p4d_val(*p4d)) { - pud = (pud_t *)p4d_page_vaddr(*p4d); - paddr_last = phys_pud_init(pud, __pa(vaddr), + if (pgd_val(*pgd)) { + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask); continue; } - pud = alloc_low_page(); - paddr_last = phys_pud_init(pud, __pa(vaddr), __pa(vaddr_end), + p4d = alloc_low_page(); + paddr_last = phys_p4d_init(p4d, __pa(vaddr), __pa(vaddr_end), page_size_mask); spin_lock(&init_mm.page_table_lock); - p4d_populate(&init_mm, p4d, pud); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + pgd_populate(&init_mm, pgd, p4d); + else + p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d); spin_unlock(&init_mm.page_table_lock); pgd_changed = true; } @@ -682,22 +772,15 @@ static void update_end_of_memory_vars(u64 start, u64 size) } } -/* - * Memory is added always to NORMAL zone. This means you will never get - * additional DMA/DMA32 memory. - */ -int arch_add_memory(int nid, u64 start, u64 size, bool for_device) +int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock) { - struct pglist_data *pgdat = NODE_DATA(nid); - struct zone *zone = pgdat->node_zones + - zone_for_memory(nid, start, size, ZONE_NORMAL, for_device); unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; int ret; init_memory_mapping(start, start + size); - ret = __add_pages(nid, zone, start_pfn, nr_pages); + ret = __add_pages(nid, start_pfn, nr_pages, want_memblock); WARN_ON_ONCE(ret); /* update max_pfn, max_low_pfn and high_memory */ @@ -990,7 +1073,13 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, pud_base = pud_offset(p4d, 0); remove_pud_table(pud_base, addr, next, direct); - free_pud_table(pud_base, p4d); + /* + * For 4-level page tables we do not want to free PUDs, but in the + * 5-level case we should free them. This code will have to change + * to adapt for boot-time switching between 4 and 5 level page tables. + */ + if (CONFIG_PGTABLE_LEVELS == 5) + free_pud_table(pud_base, p4d); } if (direct) diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index bbc558b88a88..4c1b5fd0c7ad 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -424,7 +424,7 @@ static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) { /* Don't assume we're using swapper_pg_dir at this point */ - pgd_t *base = __va(read_cr3()); + pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(addr)]; p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0c7d8129bed6..02c9d7553409 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -12,7 +12,7 @@ #include <asm/tlbflush.h> #include <asm/sections.h> -extern pgd_t early_level4_pgt[PTRS_PER_PGD]; +extern pgd_t early_top_pgt[PTRS_PER_PGD]; extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) @@ -23,12 +23,7 @@ static int __init map_range(struct range *range) start = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->start)); end = (unsigned long)kasan_mem_to_shadow(pfn_to_kaddr(range->end)); - /* - * end + 1 here is intentional. We check several shadow bytes in advance - * to slightly speed up fastpath. In some rare cases we could cross - * boundary of mapped shadow, so we just map some more here. - */ - return vmemmap_populate(start, end + 1, NUMA_NO_NODE); + return vmemmap_populate(start, end, NUMA_NO_NODE); } static void __init clear_pgds(unsigned long start, @@ -109,8 +104,8 @@ void __init kasan_early_init(void) for (i = 0; CONFIG_PGTABLE_LEVELS >= 5 && i < PTRS_PER_P4D; i++) kasan_zero_p4d[i] = __p4d(p4d_val); - kasan_map_early_shadow(early_level4_pgt); - kasan_map_early_shadow(init_level4_pgt); + kasan_map_early_shadow(early_top_pgt); + kasan_map_early_shadow(init_top_pgt); } void __init kasan_init(void) @@ -121,8 +116,8 @@ void __init kasan_init(void) register_die_notifier(&kasan_die_notifier); #endif - memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt)); - load_cr3(early_level4_pgt); + memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); + load_cr3(early_top_pgt); __flush_tlb_all(); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); @@ -148,7 +143,7 @@ void __init kasan_init(void) kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), (void *)KASAN_SHADOW_END); - load_cr3(init_level4_pgt); + load_cr3(init_top_pgt); __flush_tlb_all(); /* diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index aed206475aa7..af599167fe3c 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -6,12 +6,12 @@ * * Entropy is generated using the KASLR early boot functions now shared in * the lib directory (originally written by Kees Cook). Randomization is - * done on PGD & PUD page table levels to increase possible addresses. The - * physical memory mapping code was adapted to support PUD level virtual - * addresses. This implementation on the best configuration provides 30,000 - * possible virtual addresses in average for each memory region. An additional - * low memory page is used to ensure each CPU can start with a PGD aligned - * virtual address (for realmode). + * done on PGD & P4D/PUD page table levels to increase possible addresses. + * The physical memory mapping code was adapted to support P4D/PUD level + * virtual addresses. This implementation on the best configuration provides + * 30,000 possible virtual addresses in average for each memory region. + * An additional low memory page is used to ensure each CPU can start with + * a PGD aligned virtual address (for realmode). * * The order of each memory region is not changed. The feature looks at * the available space for the regions based on different configuration @@ -70,7 +70,7 @@ static __initdata struct kaslr_memory_region { unsigned long *base; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 64/* Maximum */ }, + { &page_offset_base, 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT) /* Maximum */ }, { &vmalloc_base, VMALLOC_SIZE_TB }, { &vmemmap_base, 1 }, }; @@ -142,7 +142,10 @@ void __init kernel_randomize_memory(void) */ entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i); prandom_bytes_state(&rand_state, &rand, sizeof(rand)); - entropy = (rand % (entropy + 1)) & PUD_MASK; + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + entropy = (rand % (entropy + 1)) & P4D_MASK; + else + entropy = (rand % (entropy + 1)) & PUD_MASK; vaddr += entropy; *kaslr_regions[i].base = vaddr; @@ -151,27 +154,21 @@ void __init kernel_randomize_memory(void) * randomization alignment. */ vaddr += get_padding(&kaslr_regions[i]); - vaddr = round_up(vaddr + 1, PUD_SIZE); + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + vaddr = round_up(vaddr + 1, P4D_SIZE); + else + vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } } -/* - * Create PGD aligned trampoline table to allow real mode initialization - * of additional CPUs. Consume only 1 low memory page. - */ -void __meminit init_trampoline(void) +static void __meminit init_trampoline_pud(void) { unsigned long paddr, paddr_next; pgd_t *pgd; pud_t *pud_page, *pud_page_tramp; int i; - if (!kaslr_memory_enabled()) { - init_trampoline_default(); - return; - } - pud_page_tramp = alloc_low_page(); paddr = 0; @@ -192,3 +189,49 @@ void __meminit init_trampoline(void) set_pgd(&trampoline_pgd_entry, __pgd(_KERNPG_TABLE | __pa(pud_page_tramp))); } + +static void __meminit init_trampoline_p4d(void) +{ + unsigned long paddr, paddr_next; + pgd_t *pgd; + p4d_t *p4d_page, *p4d_page_tramp; + int i; + + p4d_page_tramp = alloc_low_page(); + + paddr = 0; + pgd = pgd_offset_k((unsigned long)__va(paddr)); + p4d_page = (p4d_t *) pgd_page_vaddr(*pgd); + + for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) { + p4d_t *p4d, *p4d_tramp; + unsigned long vaddr = (unsigned long)__va(paddr); + + p4d_tramp = p4d_page_tramp + p4d_index(paddr); + p4d = p4d_page + p4d_index(vaddr); + paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + + *p4d_tramp = *p4d; + } + + set_pgd(&trampoline_pgd_entry, + __pgd(_KERNPG_TABLE | __pa(p4d_page_tramp))); +} + +/* + * Create PGD aligned trampoline table to allow real mode initialization + * of additional CPUs. Consume only 1 low memory page. + */ +void __meminit init_trampoline(void) +{ + + if (!kaslr_memory_enabled()) { + init_trampoline_default(); + return; + } + + if (IS_ENABLED(CONFIG_X86_5LEVEL)) + init_trampoline_p4d(); + else + init_trampoline_pud(); +} diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 19ad095b41df..797295e792b2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -74,9 +74,6 @@ static int mmap_is_legacy(void) if (current->personality & ADDR_COMPAT_LAYOUT) return 1; - if (rlimit(RLIMIT_STACK) == RLIM_INFINITY) - return 1; - return sysctl_legacy_va_layout; } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 1dcd2be4cce4..757b0bcdf712 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -150,6 +150,12 @@ void clflush_cache_range(void *vaddr, unsigned int size) } EXPORT_SYMBOL_GPL(clflush_cache_range); +void arch_invalidate_pmem(void *addr, size_t size) +{ + clflush_cache_range(addr, size); +} +EXPORT_SYMBOL_GPL(arch_invalidate_pmem); + static void __cpa_flush_all(void *arg) { unsigned long cache = (unsigned long)arg; @@ -186,7 +192,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache) unsigned int i, level; unsigned long addr; - BUG_ON(irqs_disabled()); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); WARN_ON(PAGE_ALIGN(start) != start); on_each_cpu(__cpa_flush_range, NULL, 1); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 9b78685b66e6..45979502f64b 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -37,14 +37,14 @@ #undef pr_fmt #define pr_fmt(fmt) "" fmt -static bool boot_cpu_done; - -static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT); -static void init_cache_modes(void); +static bool __read_mostly boot_cpu_done; +static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); +static bool __read_mostly pat_initialized; +static bool __read_mostly init_cm_done; void pat_disable(const char *reason) { - if (!__pat_enabled) + if (pat_disabled) return; if (boot_cpu_done) { @@ -52,10 +52,8 @@ void pat_disable(const char *reason) return; } - __pat_enabled = 0; + pat_disabled = true; pr_info("x86/PAT: %s\n", reason); - - init_cache_modes(); } static int __init nopat(char *str) @@ -67,7 +65,7 @@ early_param("nopat", nopat); bool pat_enabled(void) { - return !!__pat_enabled; + return pat_initialized; } EXPORT_SYMBOL_GPL(pat_enabled); @@ -205,6 +203,8 @@ static void __init_cache_modes(u64 pat) update_cache_mode_entry(i, cache); } pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); + + init_cm_done = true; } #define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) @@ -225,6 +225,7 @@ static void pat_bsp_init(u64 pat) } wrmsrl(MSR_IA32_CR_PAT, pat); + pat_initialized = true; __init_cache_modes(pat); } @@ -242,10 +243,9 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -static void init_cache_modes(void) +void init_cache_modes(void) { u64 pat = 0; - static int init_cm_done; if (init_cm_done) return; @@ -287,8 +287,6 @@ static void init_cache_modes(void) } __init_cache_modes(pat); - - init_cm_done = 1; } /** @@ -306,10 +304,8 @@ void pat_init(void) u64 pat; struct cpuinfo_x86 *c = &boot_cpu_data; - if (!pat_enabled()) { - init_cache_modes(); + if (pat_disabled) return; - } if ((c->x86_vendor == X86_VENDOR_INTEL) && (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 6e7bedf69af7..014d07a80053 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -15,7 +15,7 @@ #include <linux/debugfs.h> /* - * Smarter SMP flushing macros. + * TLB flushing, formerly SMP-only * c/o Linus Torvalds. * * These mean you can really definitely utterly forget about @@ -28,39 +28,28 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ -#ifdef CONFIG_SMP - -struct flush_tlb_info { - struct mm_struct *flush_mm; - unsigned long flush_start; - unsigned long flush_end; -}; - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - */ void leave_mm(int cpu) { - struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm); + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + + /* + * It's plausible that we're in lazy TLB mode while our mm is init_mm. + * If so, our callers still expect us to flush the TLB, but there + * aren't any user TLB entries in init_mm to worry about. + * + * This needs to happen before any other sanity checks due to + * intel_idle's shenanigans. + */ + if (loaded_mm == &init_mm) + return; + if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) BUG(); - if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) { - cpumask_clear_cpu(cpu, mm_cpumask(active_mm)); - load_cr3(swapper_pg_dir); - /* - * This gets called in the idle path where RCU - * functions differently. Tracing normally - * uses RCU, so we have to call the tracepoint - * specially here. - */ - trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - } + + switch_mm(NULL, &init_mm, NULL); } EXPORT_SYMBOL_GPL(leave_mm); -#endif /* CONFIG_SMP */ - void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -75,216 +64,167 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { unsigned cpu = smp_processor_id(); + struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); - if (likely(prev != next)) { - if (IS_ENABLED(CONFIG_VMAP_STACK)) { - /* - * If our current stack is in vmalloc space and isn't - * mapped in the new pgd, we'll double-fault. Forcibly - * map it. - */ - unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - - pgd_t *pgd = next->pgd + stack_pgd_index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[stack_pgd_index]); - } + /* + * NB: The scheduler will call us with prev == next when + * switching from lazy TLB mode to normal mode if active_mm + * isn't changing. When this happens, there is no guarantee + * that CR3 (and hence cpu_tlbstate.loaded_mm) matches next. + * + * NB: leave_mm() calls us with prev == NULL and tsk == NULL. + */ -#ifdef CONFIG_SMP - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - this_cpu_write(cpu_tlbstate.active_mm, next); -#endif + this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - cpumask_set_cpu(cpu, mm_cpumask(next)); + if (real_prev == next) { + /* + * There's nothing to do: we always keep the per-mm control + * regs in sync with cpu_tlbstate.loaded_mm. Just + * sanity-check mm_cpumask. + */ + if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(next)))) + cpumask_set_cpu(cpu, mm_cpumask(next)); + return; + } + if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* - * Re-load page tables. - * - * This logic has an ordering constraint: - * - * CPU 0: Write to a PTE for 'next' - * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. - * CPU 1: set bit 1 in next's mm_cpumask - * CPU 1: load from the PTE that CPU 0 writes (implicit) - * - * We need to prevent an outcome in which CPU 1 observes - * the new PTE value and CPU 0 observes bit 1 clear in - * mm_cpumask. (If that occurs, then the IPI will never - * be sent, and CPU 0's TLB will contain a stale entry.) - * - * The bad outcome can occur if either CPU's load is - * reordered before that CPU's store, so both CPUs must - * execute full barriers to prevent this from happening. - * - * Thus, switch_mm needs a full barrier between the - * store to mm_cpumask and any operation that could load - * from next->pgd. TLB fills are special and can happen - * due to instruction fetches or for no reason at all, - * and neither LOCK nor MFENCE orders them. - * Fortunately, load_cr3() is serializing and gives the - * ordering guarantee we need. - * + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. */ - load_cr3(next->pgd); + unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + pgd_t *pgd = next->pgd + stack_pgd_index; - /* Stop flush ipis for the previous mm */ - cpumask_clear_cpu(cpu, mm_cpumask(prev)); + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[stack_pgd_index]); + } - /* Load per-mm CR4 state */ - load_mm_cr4(next); + this_cpu_write(cpu_tlbstate.loaded_mm, next); -#ifdef CONFIG_MODIFY_LDT_SYSCALL - /* - * Load the LDT, if the LDT is different. - * - * It's possible that prev->context.ldt doesn't match - * the LDT register. This can happen if leave_mm(prev) - * was called and then modify_ldt changed - * prev->context.ldt but suppressed an IPI to this CPU. - * In this case, prev->context.ldt != NULL, because we - * never set context.ldt to NULL while the mm still - * exists. That means that next->context.ldt != - * prev->context.ldt, because mms never share an LDT. - */ - if (unlikely(prev->context.ldt != next->context.ldt)) - load_mm_ldt(next); -#endif + WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); + cpumask_set_cpu(cpu, mm_cpumask(next)); + + /* + * Re-load page tables. + * + * This logic has an ordering constraint: + * + * CPU 0: Write to a PTE for 'next' + * CPU 0: load bit 1 in mm_cpumask. if nonzero, send IPI. + * CPU 1: set bit 1 in next's mm_cpumask + * CPU 1: load from the PTE that CPU 0 writes (implicit) + * + * We need to prevent an outcome in which CPU 1 observes + * the new PTE value and CPU 0 observes bit 1 clear in + * mm_cpumask. (If that occurs, then the IPI will never + * be sent, and CPU 0's TLB will contain a stale entry.) + * + * The bad outcome can occur if either CPU's load is + * reordered before that CPU's store, so both CPUs must + * execute full barriers to prevent this from happening. + * + * Thus, switch_mm needs a full barrier between the + * store to mm_cpumask and any operation that could load + * from next->pgd. TLB fills are special and can happen + * due to instruction fetches or for no reason at all, + * and neither LOCK nor MFENCE orders them. + * Fortunately, load_cr3() is serializing and gives the + * ordering guarantee we need. + */ + load_cr3(next->pgd); + + /* + * This gets called via leave_mm() in the idle path where RCU + * functions differently. Tracing normally uses RCU, so we have to + * call the tracepoint specially here. + */ + trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); + + /* Stop flush ipis for the previous mm */ + WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) && + real_prev != &init_mm); + cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + + /* Load per-mm CR4 and LDTR state */ + load_mm_cr4(next); + switch_ldt(real_prev, next); +} + +static void flush_tlb_func_common(const struct flush_tlb_info *f, + bool local, enum tlb_flush_reason reason) +{ + /* This code cannot presently handle being reentered. */ + VM_WARN_ON(!irqs_disabled()); + + if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { + leave_mm(smp_processor_id()); + return; } -#ifdef CONFIG_SMP - else { - this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); - BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - - if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { - /* - * On established mms, the mm_cpumask is only changed - * from irq context, from ptep_clear_flush() while in - * lazy tlb mode, and here. Irqs are blocked during - * schedule, protecting us from simultaneous changes. - */ - cpumask_set_cpu(cpu, mm_cpumask(next)); - /* - * We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload CR3 - * to make sure to use no freed page tables. - * - * As above, load_cr3() is serializing and orders TLB - * fills with respect to the mm_cpumask write. - */ - load_cr3(next->pgd); - trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); - load_mm_cr4(next); - load_mm_ldt(next); + if (f->end == TLB_FLUSH_ALL) { + local_flush_tlb(); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); + } else { + unsigned long addr; + unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + addr = f->start; + while (addr < f->end) { + __flush_tlb_single(addr); + addr += PAGE_SIZE; } + if (local) + count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); + trace_tlb_flush(reason, nr_pages); } -#endif } -#ifdef CONFIG_SMP +static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) +{ + const struct flush_tlb_info *f = info; -/* - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) set cpu_tlbstate to TLBSTATE_OK - * Now the tlb flush NMI handler flush_tlb_func won't call leave_mm - * if cpu0 was in lazy tlb mode. - * 1a2) update cpu active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a3) cpu_set(cpu, new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1a5) cpu_clear(cpu, old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but flush_tlb_func ignore flush ipis for the wrong - * mm, and in the worst case we perform a superfluous tlb flush. - * 1b) thread switch without mm change - * cpu active_mm is correct, cpu0 already handles flush ipis. - * 1b1) set cpu_tlbstate to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu_tlbstate is local to each cpu, no - * write/read ordering problems. - */ + flush_tlb_func_common(f, true, reason); +} -/* - * TLB flush funcation: - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ -static void flush_tlb_func(void *info) +static void flush_tlb_func_remote(void *info) { - struct flush_tlb_info *f = info; + const struct flush_tlb_info *f = info; inc_irq_stat(irq_tlb_count); - if (f->flush_mm && f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm)) + if (f->mm && f->mm != this_cpu_read(cpu_tlbstate.loaded_mm)) return; count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); - if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) { - if (f->flush_end == TLB_FLUSH_ALL) { - local_flush_tlb(); - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, TLB_FLUSH_ALL); - } else { - unsigned long addr; - unsigned long nr_pages = - (f->flush_end - f->flush_start) / PAGE_SIZE; - addr = f->flush_start; - while (addr < f->flush_end) { - __flush_tlb_single(addr); - addr += PAGE_SIZE; - } - trace_tlb_flush(TLB_REMOTE_SHOOTDOWN, nr_pages); - } - } else - leave_mm(smp_processor_id()); - + flush_tlb_func_common(f, false, TLB_REMOTE_SHOOTDOWN); } void native_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { - struct flush_tlb_info info; - - info.flush_mm = mm; - info.flush_start = start; - info.flush_end = end; - count_vm_tlb_event(NR_TLB_REMOTE_FLUSH); - if (end == TLB_FLUSH_ALL) + if (info->end == TLB_FLUSH_ALL) trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL); else trace_tlb_flush(TLB_REMOTE_SEND_IPI, - (end - start) >> PAGE_SHIFT); + (info->end - info->start) >> PAGE_SHIFT); if (is_uv_system()) { unsigned int cpu; cpu = smp_processor_id(); - cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu); + cpumask = uv_flush_tlb_others(cpumask, info); if (cpumask) - smp_call_function_many(cpumask, flush_tlb_func, - &info, 1); + smp_call_function_many(cpumask, flush_tlb_func_remote, + (void *)info, 1); return; } - smp_call_function_many(cpumask, flush_tlb_func, &info, 1); + smp_call_function_many(cpumask, flush_tlb_func_remote, + (void *)info, 1); } /* @@ -302,85 +242,41 @@ static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long vmflag) { - unsigned long addr; - /* do a global flush by default */ - unsigned long base_pages_to_flush = TLB_FLUSH_ALL; - - preempt_disable(); + int cpu; - if ((end != TLB_FLUSH_ALL) && !(vmflag & VM_HUGETLB)) - base_pages_to_flush = (end - start) >> PAGE_SHIFT; - if (base_pages_to_flush > tlb_single_page_flush_ceiling) - base_pages_to_flush = TLB_FLUSH_ALL; + struct flush_tlb_info info = { + .mm = mm, + }; - if (current->active_mm != mm) { - /* Synchronize with switch_mm. */ - smp_mb(); + cpu = get_cpu(); - goto out; - } - - if (!current->mm) { - leave_mm(smp_processor_id()); + /* Synchronize with switch_mm. */ + smp_mb(); - /* Synchronize with switch_mm. */ - smp_mb(); - - goto out; - } - - /* - * Both branches below are implicit full barriers (MOV to CR or - * INVLPG) that synchronize with switch_mm. - */ - if (base_pages_to_flush == TLB_FLUSH_ALL) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - local_flush_tlb(); + /* Should we flush just the requested range? */ + if ((end != TLB_FLUSH_ALL) && + !(vmflag & VM_HUGETLB) && + ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) { + info.start = start; + info.end = end; } else { - /* flush range by one by one 'invlpg' */ - for (addr = start; addr < end; addr += PAGE_SIZE) { - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); - __flush_tlb_single(addr); - } - } - trace_tlb_flush(TLB_LOCAL_MM_SHOOTDOWN, base_pages_to_flush); -out: - if (base_pages_to_flush == TLB_FLUSH_ALL) { - start = 0UL; - end = TLB_FLUSH_ALL; + info.start = 0UL; + info.end = TLB_FLUSH_ALL; } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, end); - preempt_enable(); -} -void flush_tlb_page(struct vm_area_struct *vma, unsigned long start) -{ - struct mm_struct *mm = vma->vm_mm; - - preempt_disable(); - - if (current->active_mm == mm) { - if (current->mm) { - /* - * Implicit full barrier (INVLPG) that synchronizes - * with switch_mm. - */ - __flush_tlb_one(start); - } else { - leave_mm(smp_processor_id()); - - /* Synchronize with switch_mm. */ - smp_mb(); - } + if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { + VM_WARN_ON(irqs_disabled()); + local_irq_disable(); + flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN); + local_irq_enable(); } - if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids) - flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE); - - preempt_enable(); + if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) + flush_tlb_others(mm_cpumask(mm), &info); + put_cpu(); } + static void do_flush_tlb_all(void *info) { count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); @@ -401,7 +297,7 @@ static void do_kernel_range_flush(void *info) unsigned long addr; /* flush range by one by one 'invlpg' */ - for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE) + for (addr = f->start; addr < f->end; addr += PAGE_SIZE) __flush_tlb_single(addr); } @@ -410,16 +306,40 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end) /* Balance as user space task's flush, a bit conservative */ if (end == TLB_FLUSH_ALL || - (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) { + (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) { on_each_cpu(do_flush_tlb_all, NULL, 1); } else { struct flush_tlb_info info; - info.flush_start = start; - info.flush_end = end; + info.start = start; + info.end = end; on_each_cpu(do_kernel_range_flush, &info, 1); } } +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + struct flush_tlb_info info = { + .mm = NULL, + .start = 0UL, + .end = TLB_FLUSH_ALL, + }; + + int cpu = get_cpu(); + + if (cpumask_test_cpu(cpu, &batch->cpumask)) { + VM_WARN_ON(irqs_disabled()); + local_irq_disable(); + flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN); + local_irq_enable(); + } + + if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) + flush_tlb_others(&batch->cpumask, &info); + cpumask_clear(&batch->cpumask); + + put_cpu(); +} + static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -465,5 +385,3 @@ static int __init create_tlb_single_page_flush_ceiling(void) return 0; } late_initcall(create_tlb_single_page_flush_ceiling); - -#endif /* CONFIG_SMP */ diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile index 90568c33ddb0..fefb4b619598 100644 --- a/arch/x86/net/Makefile +++ b/arch/x86/net/Makefile @@ -1,4 +1,6 @@ # # Arch-specific network modules # +OBJECT_FILES_NON_STANDARD_bpf_jit.o += y + obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index f2a7faf4706e..b33093f84528 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -19,9 +19,6 @@ */ #define SKBDATA %r10 #define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ -#define MAX_BPF_STACK (512 /* from filter.h */ + \ - 32 /* space for rbx,r13,r14,r15 */ + \ - 8 /* space for skb_copy_bits */) #define FUNC(name) \ .globl name; \ @@ -66,7 +63,7 @@ FUNC(sk_load_byte_positive_offset) /* rsi contains offset and can be scratched */ #define bpf_slow_path_common(LEN) \ - lea -MAX_BPF_STACK + 32(%rbp), %rdx;\ + lea 32(%rbp), %rdx;\ FRAME_BEGIN; \ mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ @@ -83,14 +80,14 @@ FUNC(sk_load_byte_positive_offset) bpf_slow_path_word: bpf_slow_path_common(4) js bpf_error - mov - MAX_BPF_STACK + 32(%rbp),%eax + mov 32(%rbp),%eax bswap %eax ret bpf_slow_path_half: bpf_slow_path_common(2) js bpf_error - mov - MAX_BPF_STACK + 32(%rbp),%ax + mov 32(%rbp),%ax rol $8,%ax movzwl %ax,%eax ret @@ -98,7 +95,7 @@ bpf_slow_path_half: bpf_slow_path_byte: bpf_slow_path_common(1) js bpf_error - movzbl - MAX_BPF_STACK + 32(%rbp),%eax + movzbl 32(%rbp),%eax ret #define sk_negative_common(SIZE) \ @@ -148,9 +145,10 @@ FUNC(sk_load_byte_negative_offset) bpf_error: # force a return 0 from jit handler xor %eax,%eax - mov - MAX_BPF_STACK(%rbp),%rbx - mov - MAX_BPF_STACK + 8(%rbp),%r13 - mov - MAX_BPF_STACK + 16(%rbp),%r14 - mov - MAX_BPF_STACK + 24(%rbp),%r15 + mov (%rbp),%rbx + mov 8(%rbp),%r13 + mov 16(%rbp),%r14 + mov 24(%rbp),%r15 + add $40, %rbp leaveq ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f58939393eef..e1324f280e06 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -197,17 +197,16 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -#define STACKSIZE \ - (MAX_BPF_STACK + \ - 32 /* space for rbx, r13, r14, r15 */ + \ +#define AUX_STACK_SPACE \ + (32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 48 +#define PROLOGUE_SIZE 37 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program */ -static void emit_prologue(u8 **pprog) +static void emit_prologue(u8 **pprog, u32 stack_depth) { u8 *prog = *pprog; int cnt = 0; @@ -215,13 +214,17 @@ static void emit_prologue(u8 **pprog) EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ - /* sub rsp, STACKSIZE */ - EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE); + /* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */ + EMIT3_off32(0x48, 0x81, 0xEC, + round_up(stack_depth, 8) + AUX_STACK_SPACE); + + /* sub rbp, AUX_STACK_SPACE */ + EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE); /* all classic BPF filters use R6(rbx) save it */ - /* mov qword ptr [rbp-X],rbx */ - EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE); + /* mov qword ptr [rbp+0],rbx */ + EMIT4(0x48, 0x89, 0x5D, 0); /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and @@ -231,12 +234,12 @@ static void emit_prologue(u8 **pprog) * than synthetic ones. Therefore not worth adding complexity. */ - /* mov qword ptr [rbp-X],r13 */ - EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8); - /* mov qword ptr [rbp-X],r14 */ - EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16); - /* mov qword ptr [rbp-X],r15 */ - EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); + /* mov qword ptr [rbp+8],r13 */ + EMIT4(0x4C, 0x89, 0x6D, 8); + /* mov qword ptr [rbp+16],r14 */ + EMIT4(0x4C, 0x89, 0x75, 16); + /* mov qword ptr [rbp+24],r15 */ + EMIT4(0x4C, 0x89, 0x7D, 24); /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls * we need to reset the counter to 0. It's done in two instructions, @@ -246,8 +249,8 @@ static void emit_prologue(u8 **pprog) /* xor eax, eax */ EMIT2(0x31, 0xc0); - /* mov qword ptr [rbp-X], rax */ - EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); + /* mov qword ptr [rbp+32], rax */ + EMIT4(0x48, 0x89, 0x45, 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); *pprog = prog; @@ -289,13 +292,13 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ + EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ #define OFFSET2 36 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ + EMIT2_off32(0x89, 0x85, 36); /* mov dword ptr [rbp + 36], eax */ /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ @@ -361,7 +364,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int proglen = 0; u8 *prog = temp; - emit_prologue(&prog); + emit_prologue(&prog, bpf_prog->aux->stack_depth); if (seen_ld_abs) emit_load_skb_data_hlen(&prog); @@ -877,7 +880,7 @@ xadd: if (is_imm8(insn->off)) } break; - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: emit_bpf_tail_call(&prog); break; @@ -1036,15 +1039,17 @@ common_load: seen_exit = true; /* update cleanup_addr */ ctx->cleanup_addr = proglen; - /* mov rbx, qword ptr [rbp-X] */ - EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE); - /* mov r13, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8); - /* mov r14, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16); - /* mov r15, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24); - + /* mov rbx, qword ptr [rbp+0] */ + EMIT4(0x48, 0x8B, 0x5D, 0); + /* mov r13, qword ptr [rbp+8] */ + EMIT4(0x4C, 0x8B, 0x6D, 8); + /* mov r14, qword ptr [rbp+16] */ + EMIT4(0x4C, 0x8B, 0x75, 16); + /* mov r15, qword ptr [rbp+24] */ + EMIT4(0x4C, 0x8B, 0x7D, 24); + + /* add rbp, AUX_STACK_SPACE */ + EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE); EMIT1(0xC9); /* leave */ EMIT1(0xC3); /* ret */ break; @@ -1162,6 +1167,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_jit_binary_lock_ro(header); prog->bpf_func = (void *)image; prog->jited = 1; + prog->jited_len = proglen; } else { prog = orig_prog; } diff --git a/arch/x86/pci/ce4100.c b/arch/x86/pci/ce4100.c index b914e20b5a00..3353b76dcff0 100644 --- a/arch/x86/pci/ce4100.c +++ b/arch/x86/pci/ce4100.c @@ -65,6 +65,9 @@ struct sim_reg_op { { PCI_DEVFN(device, func), offset, init_op, read_op, write_op,\ {0, SIZE_TO_MASK(size)} }, +/* + * All read/write functions are called with pci_config_lock held. + */ static void reg_init(struct sim_dev_reg *reg) { pci_direct_conf1.read(0, 1, reg->dev_func, reg->reg, 4, @@ -73,21 +76,13 @@ static void reg_init(struct sim_dev_reg *reg) static void reg_read(struct sim_dev_reg *reg, u32 *value) { - unsigned long flags; - - raw_spin_lock_irqsave(&pci_config_lock, flags); *value = reg->sim_reg.value; - raw_spin_unlock_irqrestore(&pci_config_lock, flags); } static void reg_write(struct sim_dev_reg *reg, u32 value) { - unsigned long flags; - - raw_spin_lock_irqsave(&pci_config_lock, flags); reg->sim_reg.value = (value & reg->sim_reg.mask) | (reg->sim_reg.value & ~reg->sim_reg.mask); - raw_spin_unlock_irqrestore(&pci_config_lock, flags); } static void sata_reg_init(struct sim_dev_reg *reg) @@ -117,12 +112,8 @@ static void sata_revid_read(struct sim_dev_reg *reg, u32 *value) static void reg_noirq_read(struct sim_dev_reg *reg, u32 *value) { - unsigned long flags; - - raw_spin_lock_irqsave(&pci_config_lock, flags); /* force interrupt pin value to 0 */ *value = reg->sim_reg.value & 0xfff00ff; - raw_spin_unlock_irqrestore(&pci_config_lock, flags); } static struct sim_dev_reg bus1_fixups[] = { @@ -265,24 +256,33 @@ int bridge_read(unsigned int devfn, int reg, int len, u32 *value) return retval; } -static int ce4100_conf_read(unsigned int seg, unsigned int bus, - unsigned int devfn, int reg, int len, u32 *value) +static int ce4100_bus1_read(unsigned int devfn, int reg, int len, u32 *value) { + unsigned long flags; int i; - WARN_ON(seg); - if (bus == 1) { - for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) { - if (bus1_fixups[i].dev_func == devfn && - bus1_fixups[i].reg == (reg & ~3) && - bus1_fixups[i].read) { - bus1_fixups[i].read(&(bus1_fixups[i]), - value); - extract_bytes(value, reg, len); - return 0; - } + for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) { + if (bus1_fixups[i].dev_func == devfn && + bus1_fixups[i].reg == (reg & ~3) && + bus1_fixups[i].read) { + + raw_spin_lock_irqsave(&pci_config_lock, flags); + bus1_fixups[i].read(&(bus1_fixups[i]), value); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); + extract_bytes(value, reg, len); + return 0; } } + return -1; +} + +static int ce4100_conf_read(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, u32 *value) +{ + WARN_ON(seg); + + if (bus == 1 && !ce4100_bus1_read(devfn, reg, len, value)) + return 0; if (bus == 0 && (PCI_DEVFN(1, 0) == devfn) && !bridge_read(devfn, reg, len, value)) @@ -291,23 +291,32 @@ static int ce4100_conf_read(unsigned int seg, unsigned int bus, return pci_direct_conf1.read(seg, bus, devfn, reg, len, value); } -static int ce4100_conf_write(unsigned int seg, unsigned int bus, - unsigned int devfn, int reg, int len, u32 value) +static int ce4100_bus1_write(unsigned int devfn, int reg, int len, u32 value) { + unsigned long flags; int i; - WARN_ON(seg); - if (bus == 1) { - for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) { - if (bus1_fixups[i].dev_func == devfn && - bus1_fixups[i].reg == (reg & ~3) && - bus1_fixups[i].write) { - bus1_fixups[i].write(&(bus1_fixups[i]), - value); - return 0; - } + for (i = 0; i < ARRAY_SIZE(bus1_fixups); i++) { + if (bus1_fixups[i].dev_func == devfn && + bus1_fixups[i].reg == (reg & ~3) && + bus1_fixups[i].write) { + + raw_spin_lock_irqsave(&pci_config_lock, flags); + bus1_fixups[i].write(&(bus1_fixups[i]), value); + raw_spin_unlock_irqrestore(&pci_config_lock, flags); + return 0; } } + return -1; +} + +static int ce4100_conf_write(unsigned int seg, unsigned int bus, + unsigned int devfn, int reg, int len, u32 value) +{ + WARN_ON(seg); + + if (bus == 1 && !ce4100_bus1_write(devfn, reg, len, value)) + return 0; /* Discard writes to A/V bridge BAR. */ if (bus == 0 && PCI_DEVFN(1, 0) == devfn && @@ -318,8 +327,8 @@ static int ce4100_conf_write(unsigned int seg, unsigned int bus, } static const struct pci_raw_ops ce4100_pci_conf = { - .read = ce4100_conf_read, - .write = ce4100_conf_write, + .read = ce4100_conf_read, + .write = ce4100_conf_write, }; int __init ce4100_pci_init(void) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 190e718694b1..dbe2132b0ed4 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -24,7 +24,6 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 | unsigned int pci_early_dump_regs; static int pci_bf_sort; -static int smbios_type_b1_flag; int pci_routeirq; int noioapicquirk; #ifdef CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS @@ -75,8 +74,8 @@ struct pci_ops pci_root_ops = { }; /* - * This interrupt-safe spinlock protects all accesses to PCI - * configuration space. + * This interrupt-safe spinlock protects all accesses to PCI configuration + * space, except for the mmconfig (ECAM) based operations. */ DEFINE_RAW_SPINLOCK(pci_config_lock); @@ -197,34 +196,18 @@ static int __init set_bf_sort(const struct dmi_system_id *d) static void __init read_dmi_type_b1(const struct dmi_header *dm, void *private_data) { - u8 *d = (u8 *)dm + 4; + u8 *data = (u8 *)dm + 4; if (dm->type != 0xB1) return; - switch (((*(u32 *)d) >> 9) & 0x03) { - case 0x00: - printk(KERN_INFO "dmi type 0xB1 record - unknown flag\n"); - break; - case 0x01: /* set pci=bfsort */ - smbios_type_b1_flag = 1; - break; - case 0x02: /* do not set pci=bfsort */ - smbios_type_b1_flag = 2; - break; - default: - break; - } + if ((((*(u32 *)data) >> 9) & 0x03) == 0x01) + set_bf_sort((const struct dmi_system_id *)private_data); } static int __init find_sort_method(const struct dmi_system_id *d) { - dmi_walk(read_dmi_type_b1, NULL); - - if (smbios_type_b1_flag == 1) { - set_bf_sort(d); - return 0; - } - return -1; + dmi_walk(read_dmi_type_b1, (void *)d); + return 0; } /* diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 6d52b94f4bb9..11e407489db0 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -571,3 +571,50 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar); + +/* + * Device [1022:7808] + * 23. USB Wake on Connect/Disconnect with Low Speed Devices + * https://support.amd.com/TechDocs/46837.pdf + * Appendix A2 + * https://support.amd.com/TechDocs/42413.pdf + */ +static void pci_fixup_amd_ehci_pme(struct pci_dev *dev) +{ + dev_info(&dev->dev, "PME# does not work under D3, disabling it\n"); + dev->pme_support &= ~((PCI_PM_CAP_PME_D3 | PCI_PM_CAP_PME_D3cold) + >> PCI_PM_CAP_PME_SHIFT); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, 0x7808, pci_fixup_amd_ehci_pme); + +/* + * Apple MacBook Pro: Avoid [mem 0x7fa00000-0x7fbfffff] + * + * Using the [mem 0x7fa00000-0x7fbfffff] region, e.g., by assigning it to + * the 00:1c.0 Root Port, causes a conflict with [io 0x1804], which is used + * for soft poweroff and suspend-to-RAM. + * + * As far as we know, this is related to the address space, not to the Root + * Port itself. Attaching the quirk to the Root Port is a convenience, but + * it could probably also be a standalone DMI quirk. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=103211 + */ +static void quirk_apple_mbp_poweroff(struct pci_dev *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *res; + + if ((!dmi_match(DMI_PRODUCT_NAME, "MacBookPro11,4") && + !dmi_match(DMI_PRODUCT_NAME, "MacBookPro11,5")) || + pdev->bus->number != 0 || pdev->devfn != PCI_DEVFN(0x1c, 0)) + return; + + res = request_mem_region(0x7fa00000, 0x200000, + "MacBook Pro poweroff workaround"); + if (res) + dev_info(dev, "claimed %s %pR\n", res->name, res); + else + dev_info(dev, "can't work around MacBook Pro poweroff issue\n"); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8c10, quirk_apple_mbp_poweroff); diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index ea6f3802c17b..1cb01abcb1be 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -24,12 +24,10 @@ static void pcibios_fixup_peer_bridges(void) int __init pci_legacy_init(void) { - if (!raw_pci_ops) { - printk("PCI: System does not support PCI\n"); - return 0; - } + if (!raw_pci_ops) + return 1; - printk("PCI: Probing PCI hardware\n"); + pr_info("PCI: Probing PCI hardware\n"); pcibios_scan_root(0); return 0; } @@ -46,7 +44,7 @@ void pcibios_scan_specific_bus(int busn) if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) && l != 0x0000 && l != 0xffff) { DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l); - printk(KERN_INFO "PCI: Discovered peer bus %02x\n", busn); + pr_info("PCI: Discovered peer bus %02x\n", busn); pcibios_scan_root(busn); return; } @@ -60,8 +58,12 @@ static int __init pci_subsys_init(void) * The init function returns an non zero value when * pci_legacy_init should be invoked. */ - if (x86_init.pci.init()) - pci_legacy_init(); + if (x86_init.pci.init()) { + if (pci_legacy_init()) { + pr_info("PCI: System does not support PCI\n"); + return -ENODEV; + } + } pcibios_fixup_peer_bridges(); x86_init.pci.init_irq(); diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index c1bdb9edcae7..76595408ff53 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -46,7 +46,7 @@ static inline void set_bios_x(void) pcibios_enabled = 1; set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT); if (__supported_pte_mask & _PAGE_NX) - printk(KERN_INFO "PCI : PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n"); + printk(KERN_INFO "PCI: PCI BIOS area is rw and x. Use pci=nobios if you want it NX.\n"); } /* diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index ec008e800b45..53d600217973 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -26,6 +26,7 @@ #include <linux/pci_ids.h> #include <linux/export.h> #include <linux/list.h> +#include <asm/iommu.h> #define STA2X11_SWIOTLB_SIZE (4*1024*1024) extern int swiotlb_late_init_with_default_size(size_t default_size); @@ -191,7 +192,7 @@ static const struct dma_map_ops sta2x11_dma_ops = { .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, .mapping_error = swiotlb_dma_mapping_error, - .dma_supported = NULL, /* FIXME: we should use this instead! */ + .dma_supported = x86_dma_supported, }; /* At setup time, we use our own ops if the device is a ConneXt one */ diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index f1d83b34c329..2f56e1ed61c3 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,4 +1,5 @@ OBJECT_FILES_NON_STANDARD_efi_thunk_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_efi_stub_$(BITS).o := y obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 7e76a4d8304b..f084d8718ac4 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -828,9 +828,11 @@ static void __init kexec_enter_virtual_mode(void) /* * We don't do virtual mode, since we don't do runtime services, on - * non-native EFI + * non-native EFI. With efi=old_map, we don't do runtime services in + * kexec kernel because in the initial boot something else might + * have been mapped at these virtual addresses. */ - if (!efi_is_native()) { + if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) { efi_memmap_unmap(); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); return; @@ -1012,7 +1014,6 @@ static void __init __efi_enter_virtual_mode(void) * necessary relocation fixups for the new virtual addresses. */ efi_runtime_update_mappings(); - efi_dump_pagetable(); /* clean DUMMY object */ efi_delete_dummy_variable(); @@ -1027,6 +1028,8 @@ void __init efi_enter_virtual_mode(void) kexec_enter_virtual_mode(); else __efi_enter_virtual_mode(); + + efi_dump_pagetable(); } /* diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 3481268da3d0..52f7faa1538f 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -44,7 +44,14 @@ int __init efi_alloc_page_tables(void) } void efi_sync_low_kernel_mappings(void) {} -void __init efi_dump_pagetable(void) {} + +void __init efi_dump_pagetable(void) +{ +#ifdef CONFIG_EFI_PGT_DUMP + ptdump_walk_pgd_level(NULL, swapper_pg_dir); +#endif +} + int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { return 0; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index c488625c9712..9bf72f5bfedb 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -71,14 +71,16 @@ static void __init early_code_mapping_set_exec(int executable) pgd_t * __init efi_call_phys_prolog(void) { - unsigned long vaddress; - pgd_t *save_pgd; + unsigned long vaddr, addr_pgd, addr_p4d, addr_pud; + pgd_t *save_pgd, *pgd_k, *pgd_efi; + p4d_t *p4d, *p4d_k, *p4d_efi; + pud_t *pud; int pgd; - int n_pgds; + int n_pgds, i, j; if (!efi_enabled(EFI_OLD_MEMMAP)) { - save_pgd = (pgd_t *)read_cr3(); + save_pgd = (pgd_t *)__read_cr3(); write_cr3((unsigned long)efi_scratch.efi_pgt); goto out; } @@ -88,10 +90,49 @@ pgd_t * __init efi_call_phys_prolog(void) n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); + /* + * Build 1:1 identity mapping for efi=old_map usage. Note that + * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while + * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical + * address X, the pud_index(X) != pud_index(__va(X)), we can only copy + * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping. + * This means here we can only reuse the PMD tables of the direct mapping. + */ for (pgd = 0; pgd < n_pgds; pgd++) { - save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE); - vaddress = (unsigned long)__va(pgd * PGDIR_SIZE); - set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress)); + addr_pgd = (unsigned long)(pgd * PGDIR_SIZE); + vaddr = (unsigned long)__va(pgd * PGDIR_SIZE); + pgd_efi = pgd_offset_k(addr_pgd); + save_pgd[pgd] = *pgd_efi; + + p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd); + if (!p4d) { + pr_err("Failed to allocate p4d table!\n"); + goto out; + } + + for (i = 0; i < PTRS_PER_P4D; i++) { + addr_p4d = addr_pgd + i * P4D_SIZE; + p4d_efi = p4d + p4d_index(addr_p4d); + + pud = pud_alloc(&init_mm, p4d_efi, addr_p4d); + if (!pud) { + pr_err("Failed to allocate pud table!\n"); + goto out; + } + + for (j = 0; j < PTRS_PER_PUD; j++) { + addr_pud = addr_p4d + j * PUD_SIZE; + + if (addr_pud > (max_pfn << PAGE_SHIFT)) + break; + + vaddr = (unsigned long)__va(addr_pud); + + pgd_k = pgd_offset_k(vaddr); + p4d_k = p4d_offset(pgd_k, vaddr); + pud[j] = *pud_offset(p4d_k, vaddr); + } + } } out: __flush_tlb_all(); @@ -104,8 +145,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) /* * After the lock is released, the original page table is restored. */ - int pgd_idx; + int pgd_idx, i; int nr_pgds; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; if (!efi_enabled(EFI_OLD_MEMMAP)) { write_cr3((unsigned long)save_pgd); @@ -115,9 +159,28 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd) nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); - for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) + for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) { + pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE); set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); + if (!(pgd_val(*pgd) & _PAGE_PRESENT)) + continue; + + for (i = 0; i < PTRS_PER_P4D; i++) { + p4d = p4d_offset(pgd, + pgd_idx * PGDIR_SIZE + i * P4D_SIZE); + + if (!(p4d_val(*p4d) & _PAGE_PRESENT)) + continue; + + pud = (pud_t *)p4d_page_vaddr(*p4d); + pud_free(&init_mm, pud); + } + + p4d = (p4d_t *)pgd_page_vaddr(*pgd); + p4d_free(&init_mm, p4d); + } + kfree(save_pgd); __flush_tlb_all(); @@ -526,7 +589,10 @@ void __init efi_runtime_update_mappings(void) void __init efi_dump_pagetable(void) { #ifdef CONFIG_EFI_PGT_DUMP - ptdump_walk_pgd_level(NULL, efi_pgd); + if (efi_enabled(EFI_OLD_MEMMAP)) + ptdump_walk_pgd_level(NULL, swapper_pg_dir); + else + ptdump_walk_pgd_level(NULL, efi_pgd); #endif } @@ -583,7 +649,7 @@ efi_status_t efi_thunk_set_virtual_address_map( efi_sync_low_kernel_mappings(); local_irq_save(flags); - efi_scratch.prev_cr3 = read_cr3(); + efi_scratch.prev_cr3 = __read_cr3(); write_cr3((unsigned long)efi_scratch.efi_pgt); __flush_tlb_all(); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 26615991d69c..8a99a2e96537 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -15,12 +15,66 @@ #include <asm/e820/api.h> #include <asm/efi.h> #include <asm/uv/uv.h> +#include <asm/cpu_device_id.h> #define EFI_MIN_RESERVE 5120 #define EFI_DUMMY_GUID \ EFI_GUID(0x4424ac57, 0xbe4b, 0x47dd, 0x9e, 0x97, 0xed, 0x50, 0xf0, 0x9f, 0x92, 0xa9) +#define QUARK_CSH_SIGNATURE 0x5f435348 /* _CSH */ +#define QUARK_SECURITY_HEADER_SIZE 0x400 + +/* + * Header prepended to the standard EFI capsule on Quark systems the are based + * on Intel firmware BSP. + * @csh_signature: Unique identifier to sanity check signed module + * presence ("_CSH"). + * @version: Current version of CSH used. Should be one for Quark A0. + * @modulesize: Size of the entire module including the module header + * and payload. + * @security_version_number_index: Index of SVN to use for validation of signed + * module. + * @security_version_number: Used to prevent against roll back of modules. + * @rsvd_module_id: Currently unused for Clanton (Quark). + * @rsvd_module_vendor: Vendor Identifier. For Intel products value is + * 0x00008086. + * @rsvd_date: BCD representation of build date as yyyymmdd, where + * yyyy=4 digit year, mm=1-12, dd=1-31. + * @headersize: Total length of the header including including any + * padding optionally added by the signing tool. + * @hash_algo: What Hash is used in the module signing. + * @cryp_algo: What Crypto is used in the module signing. + * @keysize: Total length of the key data including including any + * padding optionally added by the signing tool. + * @signaturesize: Total length of the signature including including any + * padding optionally added by the signing tool. + * @rsvd_next_header: 32-bit pointer to the next Secure Boot Module in the + * chain, if there is a next header. + * @rsvd: Reserved, padding structure to required size. + * + * See also QuartSecurityHeader_t in + * Quark_EDKII_v1.2.1.1/QuarkPlatformPkg/Include/QuarkBootRom.h + * from https://downloadcenter.intel.com/download/23197/Intel-Quark-SoC-X1000-Board-Support-Package-BSP + */ +struct quark_security_header { + u32 csh_signature; + u32 version; + u32 modulesize; + u32 security_version_number_index; + u32 security_version_number; + u32 rsvd_module_id; + u32 rsvd_module_vendor; + u32 rsvd_date; + u32 headersize; + u32 hash_algo; + u32 cryp_algo; + u32 keysize; + u32 signaturesize; + u32 rsvd_next_header; + u32 rsvd[2]; +}; + static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; static bool efi_no_storage_paranoia; @@ -360,6 +414,9 @@ void __init efi_free_boot_services(void) free_bootmem_late(start, size); } + if (!num_entries) + return; + new_size = efi.memmap.desc_size * num_entries; new_phys = efi_memmap_alloc(num_entries); if (!new_phys) { @@ -501,3 +558,86 @@ bool efi_poweroff_required(void) { return acpi_gbl_reduced_hardware || acpi_no_s5; } + +#ifdef CONFIG_EFI_CAPSULE_QUIRK_QUARK_CSH + +static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff, + size_t hdr_bytes) +{ + struct quark_security_header *csh = *pkbuff; + + /* Only process data block that is larger than the security header */ + if (hdr_bytes < sizeof(struct quark_security_header)) + return 0; + + if (csh->csh_signature != QUARK_CSH_SIGNATURE || + csh->headersize != QUARK_SECURITY_HEADER_SIZE) + return 1; + + /* Only process data block if EFI header is included */ + if (hdr_bytes < QUARK_SECURITY_HEADER_SIZE + + sizeof(efi_capsule_header_t)) + return 0; + + pr_debug("Quark security header detected\n"); + + if (csh->rsvd_next_header != 0) { + pr_err("multiple Quark security headers not supported\n"); + return -EINVAL; + } + + *pkbuff += csh->headersize; + cap_info->total_size = csh->headersize; + + /* + * Update the first page pointer to skip over the CSH header. + */ + cap_info->pages[0] += csh->headersize; + + return 1; +} + +#define ICPU(family, model, quirk_handler) \ + { X86_VENDOR_INTEL, family, model, X86_FEATURE_ANY, \ + (unsigned long)&quirk_handler } + +static const struct x86_cpu_id efi_capsule_quirk_ids[] = { + ICPU(5, 9, qrk_capsule_setup_info), /* Intel Quark X1000 */ + { } +}; + +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes) +{ + int (*quirk_handler)(struct capsule_info *, void **, size_t); + const struct x86_cpu_id *id; + int ret; + + if (hdr_bytes < sizeof(efi_capsule_header_t)) + return 0; + + cap_info->total_size = 0; + + id = x86_match_cpu(efi_capsule_quirk_ids); + if (id) { + /* + * The quirk handler is supposed to return + * - a value > 0 if the setup should continue, after advancing + * kbuff as needed + * - 0 if not enough hdr_bytes are available yet + * - a negative error code otherwise + */ + quirk_handler = (typeof(quirk_handler))id->driver_data; + ret = quirk_handler(cap_info, &kbuff, hdr_bytes); + if (ret <= 0) + return ret; + } + + memcpy(&cap_info->header, kbuff, sizeof(cap_info->header)); + + cap_info->total_size += cap_info->header.imagesize; + + return __efi_capsule_setup_info(cap_info); +} + +#endif diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index c5350fd27d70..0668aaff8bfe 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -77,7 +77,7 @@ static int xo1_power_state_enter(suspend_state_t pm_state) asmlinkage __visible int xo1_do_sleep(u8 sleep_state) { - void *pgd_addr = __va(read_cr3()); + void *pgd_addr = __va(read_cr3_pa()); /* Program wakeup mask (using dword access to CS5536_PM1_EN) */ outl(wakeup_mask << 16, acpi_base + CS5536_PM1_STS); diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 42e65fee5673..d4a61ddf9e62 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -456,12 +456,13 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp) */ static inline unsigned long long cycles_2_ns(unsigned long long cyc) { - struct cyc2ns_data *data = cyc2ns_read_begin(); + struct cyc2ns_data data; unsigned long long ns; - ns = mul_u64_u32_shr(cyc, data->cyc2ns_mul, data->cyc2ns_shift); + cyc2ns_read_begin(&data); + ns = mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); + cyc2ns_read_end(); - cyc2ns_read_end(data); return ns; } @@ -470,12 +471,13 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc) */ static inline unsigned long long ns_2_cycles(unsigned long long ns) { - struct cyc2ns_data *data = cyc2ns_read_begin(); + struct cyc2ns_data data; unsigned long long cyc; - cyc = (ns << data->cyc2ns_shift) / data->cyc2ns_mul; + cyc2ns_read_begin(&data); + cyc = (ns << data.cyc2ns_shift) / data.cyc2ns_mul; + cyc2ns_read_end(); - cyc2ns_read_end(data); return cyc; } @@ -586,31 +588,11 @@ static unsigned long uv2_3_read_status(unsigned long offset, int rshft, int desc } /* - * Return whether the status of the descriptor that is normally used for this - * cpu (the one indexed by its hub-relative cpu number) is busy. - * The status of the original 32 descriptors is always reflected in the 64 - * bits of UVH_LB_BAU_SB_ACTIVATION_STATUS_0. - * The bit provided by the activation_status_2 register is irrelevant to - * the status if it is only being tested for busy or not busy. - */ -int normal_busy(struct bau_control *bcp) -{ - int cpu = bcp->uvhub_cpu; - int mmr_offset; - int right_shift; - - mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0; - right_shift = cpu * UV_ACT_STATUS_SIZE; - return (((((read_lmmr(mmr_offset) >> right_shift) & - UV_ACT_STATUS_MASK)) << 1) == UV2H_DESC_BUSY); -} - -/* * Entered when a bau descriptor has gone into a permanent busy wait because * of a hardware bug. * Workaround the bug. */ -int handle_uv2_busy(struct bau_control *bcp) +static int handle_uv2_busy(struct bau_control *bcp) { struct ptc_stats *stat = bcp->statp; @@ -915,8 +897,9 @@ static void handle_cmplt(int completion_status, struct bau_desc *bau_desc, * Returns 1 if it gives up entirely and the original cpu mask is to be * returned to the kernel. */ -int uv_flush_send_and_wait(struct cpumask *flush_mask, struct bau_control *bcp, - struct bau_desc *bau_desc) +static int uv_flush_send_and_wait(struct cpumask *flush_mask, + struct bau_control *bcp, + struct bau_desc *bau_desc) { int seq_number = 0; int completion_stat = 0; @@ -1121,11 +1104,9 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp, * done. The returned pointer is valid till preemption is re-enabled. */ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - unsigned int cpu) + const struct flush_tlb_info *info) { + unsigned int cpu = smp_processor_id(); int locals = 0, remotes = 0, hubs = 0; struct bau_desc *bau_desc; struct cpumask *flush_mask; @@ -1179,8 +1160,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, record_send_statistics(stat, locals, hubs, remotes, bau_desc); - if (!end || (end - start) <= PAGE_SIZE) - address = start; + if (!info->end || (info->end - info->start) <= PAGE_SIZE) + address = info->start; else address = TLB_FLUSH_ALL; @@ -1212,8 +1193,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, * Search the message queue for any 'other' unprocessed message with the * same software acknowledge resource bit vector as the 'msg' message. */ -struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, - struct bau_control *bcp) +static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, + struct bau_control *bcp) { struct bau_pq_entry *msg_next = msg + 1; unsigned char swack_vec = msg->swack_vec; diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 776c6592136c..03fc397335b7 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -160,13 +160,21 @@ static struct irq_domain *uv_get_irq_domain(void) { static struct irq_domain *uv_domain; static DEFINE_MUTEX(uv_lock); + struct fwnode_handle *fn; mutex_lock(&uv_lock); - if (uv_domain == NULL) { - uv_domain = irq_domain_add_tree(NULL, &uv_domain_ops, NULL); - if (uv_domain) - uv_domain->parent = x86_vector_domain; - } + if (uv_domain) + goto out; + + fn = irq_domain_alloc_named_fwnode("UV-CORE"); + if (!fn) + goto out; + + uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL); + irq_domain_free_fwnode(fn); + if (uv_domain) + uv_domain->parent = x86_vector_domain; +out: mutex_unlock(&uv_lock); return uv_domain; diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index a6a198c33623..05041871ac90 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,3 +1,5 @@ +OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y + # __restore_processor_state() restores %gs after S3 resume and so should not # itself be stack-protected nostackp := $(call cc-option, -fno-stack-protector) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 6b05a9219ea2..78459a6d455a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -129,7 +129,7 @@ static void __save_processor_state(struct saved_context *ctxt) */ ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); - ctxt->cr3 = read_cr3(); + ctxt->cr3 = __read_cr3(); ctxt->cr4 = __read_cr4(); #ifdef CONFIG_X86_64 ctxt->cr8 = read_cr8(); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index a6e21fee22ea..f2598d81cd55 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -147,10 +147,11 @@ static int relocate_restore_code(void) if (!relocated_restore_code) return -ENOMEM; - memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE); + memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); /* Make the page containing the relocated code executable */ - pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code); + pgd = (pgd_t *)__va(read_cr3_pa()) + + pgd_index(relocated_restore_code); p4d = p4d_offset(pgd, relocated_restore_code); if (p4d_large(*p4d)) { set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); @@ -292,8 +293,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size) if (max_size < sizeof(struct restore_data_record)) return -EOVERFLOW; - rdr->jump_address = (unsigned long)&restore_registers; - rdr->jump_address_phys = __pa_symbol(&restore_registers); + rdr->jump_address = (unsigned long)restore_registers; + rdr->jump_address_phys = __pa_symbol(restore_registers); rdr->cr3 = restore_cr3; rdr->magic = RESTORE_MAGIC; diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig index 2a2d89d39af6..bb026699ad19 100644 --- a/arch/x86/ras/Kconfig +++ b/arch/x86/ras/Kconfig @@ -1,13 +1,3 @@ -config MCE_AMD_INJ - tristate "Simple MCE injection interface for AMD processors" - depends on RAS && X86_MCE && DEBUG_FS && AMD_NB - default n - help - This is a simple debugfs interface to inject MCEs and test different - aspects of the MCE handling code. - - WARNING: Do not even assume this interface is staying stable! - config RAS_CEC bool "Correctable Errors Collector" depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS @@ -20,4 +10,3 @@ config RAS_CEC Bear in mind that this is absolutely useless if your platform doesn't have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS. - diff --git a/arch/x86/ras/Makefile b/arch/x86/ras/Makefile deleted file mode 100644 index 5f94546db280..000000000000 --- a/arch/x86/ras/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -obj-$(CONFIG_MCE_AMD_INJ) += mce_amd_inj.o - diff --git a/arch/x86/ras/mce_amd_inj.c b/arch/x86/ras/mce_amd_inj.c deleted file mode 100644 index 8730c2882fff..000000000000 --- a/arch/x86/ras/mce_amd_inj.c +++ /dev/null @@ -1,492 +0,0 @@ -/* - * A simple MCE injection facility for testing different aspects of the RAS - * code. This driver should be built as module so that it can be loaded - * on production kernels for testing purposes. - * - * This file may be distributed under the terms of the GNU General Public - * License version 2. - * - * Copyright (c) 2010-15: Borislav Petkov <bp@alien8.de> - * Advanced Micro Devices Inc. - */ - -#include <linux/kobject.h> -#include <linux/debugfs.h> -#include <linux/device.h> -#include <linux/module.h> -#include <linux/cpu.h> -#include <linux/string.h> -#include <linux/uaccess.h> -#include <linux/pci.h> - -#include <asm/mce.h> -#include <asm/smp.h> -#include <asm/amd_nb.h> -#include <asm/irq_vectors.h> - -#include "../kernel/cpu/mcheck/mce-internal.h" - -/* - * Collect all the MCi_XXX settings - */ -static struct mce i_mce; -static struct dentry *dfs_inj; - -static u8 n_banks; - -#define MAX_FLAG_OPT_SIZE 3 -#define NBCFG 0x44 - -enum injection_type { - SW_INJ = 0, /* SW injection, simply decode the error */ - HW_INJ, /* Trigger a #MC */ - DFR_INT_INJ, /* Trigger Deferred error interrupt */ - THR_INT_INJ, /* Trigger threshold interrupt */ - N_INJ_TYPES, -}; - -static const char * const flags_options[] = { - [SW_INJ] = "sw", - [HW_INJ] = "hw", - [DFR_INT_INJ] = "df", - [THR_INT_INJ] = "th", - NULL -}; - -/* Set default injection to SW_INJ */ -static enum injection_type inj_type = SW_INJ; - -#define MCE_INJECT_SET(reg) \ -static int inj_##reg##_set(void *data, u64 val) \ -{ \ - struct mce *m = (struct mce *)data; \ - \ - m->reg = val; \ - return 0; \ -} - -MCE_INJECT_SET(status); -MCE_INJECT_SET(misc); -MCE_INJECT_SET(addr); -MCE_INJECT_SET(synd); - -#define MCE_INJECT_GET(reg) \ -static int inj_##reg##_get(void *data, u64 *val) \ -{ \ - struct mce *m = (struct mce *)data; \ - \ - *val = m->reg; \ - return 0; \ -} - -MCE_INJECT_GET(status); -MCE_INJECT_GET(misc); -MCE_INJECT_GET(addr); -MCE_INJECT_GET(synd); - -DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); -DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); - -/* - * Caller needs to be make sure this cpu doesn't disappear - * from under us, i.e.: get_cpu/put_cpu. - */ -static int toggle_hw_mce_inject(unsigned int cpu, bool enable) -{ - u32 l, h; - int err; - - err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); - if (err) { - pr_err("%s: error reading HWCR\n", __func__); - return err; - } - - enable ? (l |= BIT(18)) : (l &= ~BIT(18)); - - err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); - if (err) - pr_err("%s: error writing HWCR\n", __func__); - - return err; -} - -static int __set_inj(const char *buf) -{ - int i; - - for (i = 0; i < N_INJ_TYPES; i++) { - if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { - inj_type = i; - return 0; - } - } - return -EINVAL; -} - -static ssize_t flags_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[MAX_FLAG_OPT_SIZE]; - int n; - - n = sprintf(buf, "%s\n", flags_options[inj_type]); - - return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); -} - -static ssize_t flags_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[MAX_FLAG_OPT_SIZE], *__buf; - int err; - - if (cnt > MAX_FLAG_OPT_SIZE) - return -EINVAL; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt - 1] = 0; - - /* strip whitespace */ - __buf = strstrip(buf); - - err = __set_inj(__buf); - if (err) { - pr_err("%s: Invalid flags value: %s\n", __func__, __buf); - return err; - } - - *ppos += cnt; - - return cnt; -} - -static const struct file_operations flags_fops = { - .read = flags_read, - .write = flags_write, - .llseek = generic_file_llseek, -}; - -/* - * On which CPU to inject? - */ -MCE_INJECT_GET(extcpu); - -static int inj_extcpu_set(void *data, u64 val) -{ - struct mce *m = (struct mce *)data; - - if (val >= nr_cpu_ids || !cpu_online(val)) { - pr_err("%s: Invalid CPU: %llu\n", __func__, val); - return -EINVAL; - } - m->extcpu = val; - return 0; -} - -DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); - -static void trigger_mce(void *info) -{ - asm volatile("int $18"); -} - -static void trigger_dfr_int(void *info) -{ - asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); -} - -static void trigger_thr_int(void *info) -{ - asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); -} - -static u32 get_nbc_for_node(int node_id) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - u32 cores_per_node; - - cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); - - return cores_per_node * node_id; -} - -static void toggle_nb_mca_mst_cpu(u16 nid) -{ - struct pci_dev *F3 = node_to_amd_nb(nid)->misc; - u32 val; - int err; - - if (!F3) - return; - - err = pci_read_config_dword(F3, NBCFG, &val); - if (err) { - pr_err("%s: Error reading F%dx%03x.\n", - __func__, PCI_FUNC(F3->devfn), NBCFG); - return; - } - - if (val & BIT(27)) - return; - - pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", - __func__); - - val |= BIT(27); - err = pci_write_config_dword(F3, NBCFG, val); - if (err) - pr_err("%s: Error writing F%dx%03x.\n", - __func__, PCI_FUNC(F3->devfn), NBCFG); -} - -static void prepare_msrs(void *info) -{ - struct mce m = *(struct mce *)info; - u8 b = m.bank; - - wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); - - if (boot_cpu_has(X86_FEATURE_SMCA)) { - if (m.inject_flags == DFR_INT_INJ) { - wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status); - wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr); - } else { - wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status); - wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr); - } - - wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); - wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd); - } else { - wrmsrl(MSR_IA32_MCx_STATUS(b), m.status); - wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr); - wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); - } -} - -static void do_inject(void) -{ - u64 mcg_status = 0; - unsigned int cpu = i_mce.extcpu; - u8 b = i_mce.bank; - - rdtscll(i_mce.tsc); - - if (i_mce.misc) - i_mce.status |= MCI_STATUS_MISCV; - - if (i_mce.synd) - i_mce.status |= MCI_STATUS_SYNDV; - - if (inj_type == SW_INJ) { - mce_inject_log(&i_mce); - return; - } - - /* prep MCE global settings for the injection */ - mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; - - if (!(i_mce.status & MCI_STATUS_PCC)) - mcg_status |= MCG_STATUS_RIPV; - - /* - * Ensure necessary status bits for deferred errors: - * - MCx_STATUS[Deferred]: make sure it is a deferred error - * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC - */ - if (inj_type == DFR_INT_INJ) { - i_mce.status |= MCI_STATUS_DEFERRED; - i_mce.status |= (i_mce.status & ~MCI_STATUS_UC); - } - - /* - * For multi node CPUs, logging and reporting of bank 4 errors happens - * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for - * Fam10h and later BKDGs. - */ - if (static_cpu_has(X86_FEATURE_AMD_DCM) && - b == 4 && - boot_cpu_data.x86 < 0x17) { - toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu)); - cpu = get_nbc_for_node(amd_get_nb_id(cpu)); - } - - get_online_cpus(); - if (!cpu_online(cpu)) - goto err; - - toggle_hw_mce_inject(cpu, true); - - i_mce.mcgstatus = mcg_status; - i_mce.inject_flags = inj_type; - smp_call_function_single(cpu, prepare_msrs, &i_mce, 0); - - toggle_hw_mce_inject(cpu, false); - - switch (inj_type) { - case DFR_INT_INJ: - smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); - break; - case THR_INT_INJ: - smp_call_function_single(cpu, trigger_thr_int, NULL, 0); - break; - default: - smp_call_function_single(cpu, trigger_mce, NULL, 0); - } - -err: - put_online_cpus(); - -} - -/* - * This denotes into which bank we're injecting and triggers - * the injection, at the same time. - */ -static int inj_bank_set(void *data, u64 val) -{ - struct mce *m = (struct mce *)data; - - if (val >= n_banks) { - pr_err("Non-existent MCE bank: %llu\n", val); - return -EINVAL; - } - - m->bank = val; - do_inject(); - - return 0; -} - -MCE_INJECT_GET(bank); - -DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); - -static const char readme_msg[] = -"Description of the files and their usages:\n" -"\n" -"Note1: i refers to the bank number below.\n" -"Note2: See respective BKDGs for the exact bit definitions of the files below\n" -"as they mirror the hardware registers.\n" -"\n" -"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" -"\t attributes of the error which caused the MCE.\n" -"\n" -"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" -"\t used for error thresholding purposes and its validity is indicated by\n" -"\t MCi_STATUS[MiscV].\n" -"\n" -"synd:\t Set MCi_SYND: provide syndrome info about the error. Only valid on\n" -"\t Scalable MCA systems, and its validity is indicated by MCi_STATUS[SyndV].\n" -"\n" -"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" -"\t associated with the error.\n" -"\n" -"cpu:\t The CPU to inject the error on.\n" -"\n" -"bank:\t Specify the bank you want to inject the error into: the number of\n" -"\t banks in a processor varies and is family/model-specific, therefore, the\n" -"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" -"\t injection.\n" -"\n" -"flags:\t Injection type to be performed. Writing to this file will trigger a\n" -"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" -"\t for AMD processors.\n" -"\n" -"\t Allowed error injection types:\n" -"\t - \"sw\": Software error injection. Decode error to a human-readable \n" -"\t format only. Safe to use.\n" -"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" -"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" -"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" -"\t before injecting.\n" -"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" -"\t error APIC interrupt handler to handle the error if the feature is \n" -"\t is present in hardware. \n" -"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" -"\t APIC interrupt handler to handle the error. \n" -"\n"; - -static ssize_t -inj_readme_read(struct file *filp, char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - return simple_read_from_buffer(ubuf, cnt, ppos, - readme_msg, strlen(readme_msg)); -} - -static const struct file_operations readme_fops = { - .read = inj_readme_read, -}; - -static struct dfs_node { - char *name; - struct dentry *d; - const struct file_operations *fops; - umode_t perm; -} dfs_fls[] = { - { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, - { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, -}; - -static int __init init_mce_inject(void) -{ - unsigned int i; - u64 cap; - - rdmsrl(MSR_IA32_MCG_CAP, cap); - n_banks = cap & MCG_BANKCNT_MASK; - - dfs_inj = debugfs_create_dir("mce-inject", NULL); - if (!dfs_inj) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) { - dfs_fls[i].d = debugfs_create_file(dfs_fls[i].name, - dfs_fls[i].perm, - dfs_inj, - &i_mce, - dfs_fls[i].fops); - - if (!dfs_fls[i].d) - goto err_dfs_add; - } - - return 0; - -err_dfs_add: - while (i-- > 0) - debugfs_remove(dfs_fls[i].d); - - debugfs_remove(dfs_inj); - dfs_inj = NULL; - - return -ENODEV; -} - -static void __exit exit_mce_inject(void) -{ - - debugfs_remove_recursive(dfs_inj); - dfs_inj = NULL; - - memset(&dfs_fls, 0, sizeof(dfs_fls)); -} -module_init(init_mce_inject); -module_exit(exit_mce_inject); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Borislav Petkov <bp@alien8.de>"); -MODULE_AUTHOR("AMD Inc."); -MODULE_DESCRIPTION("MCE injection facility for RAS testing"); diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index a163a90af4aa..cd4be19c36dc 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -102,7 +102,7 @@ static void __init setup_real_mode(void) trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; - trampoline_pgd[511] = init_level4_pgt[511].pgd; + trampoline_pgd[511] = init_top_pgt[511].pgd; #endif } diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index d72dec406ccb..329406224330 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -53,7 +53,7 @@ CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage targets += vdso-syms.lds -obj-$(VDSO64-y) += vdso-syms.lds +extra-$(VDSO64-y) += vdso-syms.lds # # Match symbols in the DSO that look like VDSO*; produce a file of constants. diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index fffb0a16f9e3..bced7a369a11 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,3 +1,6 @@ +OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_xen-pvh.o := y + ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities CFLAGS_REMOVE_spinlock.o = -pg diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index bcea81f36fc5..b5e48da7fbff 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -178,7 +178,7 @@ static struct apic xen_pv_apic = { .get_apic_id = xen_get_apic_id, .set_apic_id = xen_set_apic_id, /* Can be NULL on 32-bit. */ - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, #ifdef CONFIG_SMP .send_IPI_mask = xen_send_IPI_mask, diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c index 30bb2e80cfe7..a18703be9ead 100644 --- a/arch/x86/xen/efi.c +++ b/arch/x86/xen/efi.c @@ -54,38 +54,6 @@ static efi_system_table_t efi_systab_xen __initdata = { .tables = EFI_INVALID_TABLE_ADDR /* Initialized later. */ }; -static const struct efi efi_xen __initconst = { - .systab = NULL, /* Initialized later. */ - .runtime_version = 0, /* Initialized later. */ - .mps = EFI_INVALID_TABLE_ADDR, - .acpi = EFI_INVALID_TABLE_ADDR, - .acpi20 = EFI_INVALID_TABLE_ADDR, - .smbios = EFI_INVALID_TABLE_ADDR, - .smbios3 = EFI_INVALID_TABLE_ADDR, - .sal_systab = EFI_INVALID_TABLE_ADDR, - .boot_info = EFI_INVALID_TABLE_ADDR, - .hcdp = EFI_INVALID_TABLE_ADDR, - .uga = EFI_INVALID_TABLE_ADDR, - .uv_systab = EFI_INVALID_TABLE_ADDR, - .fw_vendor = EFI_INVALID_TABLE_ADDR, - .runtime = EFI_INVALID_TABLE_ADDR, - .config_table = EFI_INVALID_TABLE_ADDR, - .get_time = xen_efi_get_time, - .set_time = xen_efi_set_time, - .get_wakeup_time = xen_efi_get_wakeup_time, - .set_wakeup_time = xen_efi_set_wakeup_time, - .get_variable = xen_efi_get_variable, - .get_next_variable = xen_efi_get_next_variable, - .set_variable = xen_efi_set_variable, - .query_variable_info = xen_efi_query_variable_info, - .update_capsule = xen_efi_update_capsule, - .query_capsule_caps = xen_efi_query_capsule_caps, - .get_next_high_mono_count = xen_efi_get_next_high_mono_count, - .reset_system = xen_efi_reset_system, - .set_virtual_address_map = NULL, /* Not used under Xen. */ - .flags = 0 /* Initialized later. */ -}; - static efi_system_table_t __init *xen_efi_probe(void) { struct xen_platform_op op = { @@ -102,7 +70,18 @@ static efi_system_table_t __init *xen_efi_probe(void) /* Here we know that Xen runs on EFI platform. */ - efi = efi_xen; + efi.get_time = xen_efi_get_time; + efi.set_time = xen_efi_set_time; + efi.get_wakeup_time = xen_efi_get_wakeup_time; + efi.set_wakeup_time = xen_efi_set_wakeup_time; + efi.get_variable = xen_efi_get_variable; + efi.get_next_variable = xen_efi_get_next_variable; + efi.set_variable = xen_efi_set_variable; + efi.query_variable_info = xen_efi_query_variable_info; + efi.update_capsule = xen_efi_update_capsule; + efi.query_capsule_caps = xen_efi_query_capsule_caps; + efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count; + efi.reset_system = xen_efi_reset_system; efi_systab_xen.tables = info->cfg.addr; efi_systab_xen.nr_tables = info->cfg.nent; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a5ffcbb20cc0..0e7ef69e8531 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -106,15 +106,83 @@ int xen_cpuhp_setup(int (*cpu_up_prepare_cb)(unsigned int), return rc >= 0 ? 0 : rc; } -static void clamp_max_cpus(void) +static int xen_vcpu_setup_restore(int cpu) { -#ifdef CONFIG_SMP - if (setup_max_cpus > MAX_VIRT_CPUS) - setup_max_cpus = MAX_VIRT_CPUS; -#endif + int rc = 0; + + /* Any per_cpu(xen_vcpu) is stale, so reset it */ + xen_vcpu_info_reset(cpu); + + /* + * For PVH and PVHVM, setup online VCPUs only. The rest will + * be handled by hotplug. + */ + if (xen_pv_domain() || + (xen_hvm_domain() && cpu_online(cpu))) { + rc = xen_vcpu_setup(cpu); + } + + return rc; +} + +/* + * On restore, set the vcpu placement up again. + * If it fails, then we're in a bad state, since + * we can't back out from using it... + */ +void xen_vcpu_restore(void) +{ + int cpu, rc; + + for_each_possible_cpu(cpu) { + bool other_cpu = (cpu != smp_processor_id()); + bool is_up; + + if (xen_vcpu_nr(cpu) == XEN_VCPU_ID_INVALID) + continue; + + /* Only Xen 4.5 and higher support this. */ + is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, + xen_vcpu_nr(cpu), NULL) > 0; + + if (other_cpu && is_up && + HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL)) + BUG(); + + if (xen_pv_domain() || xen_feature(XENFEAT_hvm_safe_pvclock)) + xen_setup_runstate_info(cpu); + + rc = xen_vcpu_setup_restore(cpu); + if (rc) + pr_emerg_once("vcpu restore failed for cpu=%d err=%d. " + "System will hang.\n", cpu, rc); + /* + * In case xen_vcpu_setup_restore() fails, do not bring up the + * VCPU. This helps us avoid the resulting OOPS when the VCPU + * accesses pvclock_vcpu_time via xen_vcpu (which is NULL.) + * Note that this does not improve the situation much -- now the + * VM hangs instead of OOPSing -- with the VCPUs that did not + * fail, spinning in stop_machine(), waiting for the failed + * VCPUs to come up. + */ + if (other_cpu && is_up && (rc == 0) && + HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL)) + BUG(); + } } -void xen_vcpu_setup(int cpu) +void xen_vcpu_info_reset(int cpu) +{ + if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) { + per_cpu(xen_vcpu, cpu) = + &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)]; + } else { + /* Set to NULL so that if somebody accesses it we get an OOPS */ + per_cpu(xen_vcpu, cpu) = NULL; + } +} + +int xen_vcpu_setup(int cpu) { struct vcpu_register_vcpu_info info; int err; @@ -123,11 +191,11 @@ void xen_vcpu_setup(int cpu) BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); /* - * This path is called twice on PVHVM - first during bootup via - * smp_init -> xen_hvm_cpu_notify, and then if the VCPU is being - * hotplugged: cpu_up -> xen_hvm_cpu_notify. - * As we can only do the VCPUOP_register_vcpu_info once lets - * not over-write its result. + * This path is called on PVHVM at bootup (xen_hvm_smp_prepare_boot_cpu) + * and at restore (xen_vcpu_restore). Also called for hotplugged + * VCPUs (cpu_init -> xen_hvm_cpu_prepare_hvm). + * However, the hypercall can only be done once (see below) so if a VCPU + * is offlined and comes back online then let's not redo the hypercall. * * For PV it is called during restore (xen_vcpu_restore) and bootup * (xen_setup_vcpu_info_placement). The hotplug mechanism does not @@ -135,42 +203,44 @@ void xen_vcpu_setup(int cpu) */ if (xen_hvm_domain()) { if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu)) - return; + return 0; } - if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) - per_cpu(xen_vcpu, cpu) = - &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)]; - if (!xen_have_vcpu_info_placement) { - if (cpu >= MAX_VIRT_CPUS) - clamp_max_cpus(); - return; + if (xen_have_vcpu_info_placement) { + vcpup = &per_cpu(xen_vcpu_info, cpu); + info.mfn = arbitrary_virt_to_mfn(vcpup); + info.offset = offset_in_page(vcpup); + + /* + * Check to see if the hypervisor will put the vcpu_info + * structure where we want it, which allows direct access via + * a percpu-variable. + * N.B. This hypercall can _only_ be called once per CPU. + * Subsequent calls will error out with -EINVAL. This is due to + * the fact that hypervisor has no unregister variant and this + * hypercall does not allow to over-write info.mfn and + * info.offset. + */ + err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, + xen_vcpu_nr(cpu), &info); + + if (err) { + pr_warn_once("register_vcpu_info failed: cpu=%d err=%d\n", + cpu, err); + xen_have_vcpu_info_placement = 0; + } else { + /* + * This cpu is using the registered vcpu info, even if + * later ones fail to. + */ + per_cpu(xen_vcpu, cpu) = vcpup; + } } - vcpup = &per_cpu(xen_vcpu_info, cpu); - info.mfn = arbitrary_virt_to_mfn(vcpup); - info.offset = offset_in_page(vcpup); - - /* Check to see if the hypervisor will put the vcpu_info - structure where we want it, which allows direct access via - a percpu-variable. - N.B. This hypercall can _only_ be called once per CPU. Subsequent - calls will error out with -EINVAL. This is due to the fact that - hypervisor has no unregister variant and this hypercall does not - allow to over-write info.mfn and info.offset. - */ - err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu), - &info); + if (!xen_have_vcpu_info_placement) + xen_vcpu_info_reset(cpu); - if (err) { - printk(KERN_DEBUG "register_vcpu_info failed: err=%d\n", err); - xen_have_vcpu_info_placement = 0; - clamp_max_cpus(); - } else { - /* This cpu is using the registered vcpu info, even if - later ones fail to. */ - per_cpu(xen_vcpu, cpu) = vcpup; - } + return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0); } void xen_reboot(int reason) diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index a6d014f47e52..87d791356ea9 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -1,5 +1,6 @@ #include <linux/cpu.h> #include <linux/kexec.h> +#include <linux/memblock.h> #include <xen/features.h> #include <xen/events.h> @@ -10,9 +11,11 @@ #include <asm/reboot.h> #include <asm/setup.h> #include <asm/hypervisor.h> +#include <asm/e820/api.h> #include <asm/xen/cpuid.h> #include <asm/xen/hypervisor.h> +#include <asm/xen/page.h> #include "xen-ops.h" #include "mmu.h" @@ -20,37 +23,34 @@ void __ref xen_hvm_init_shared_info(void) { - int cpu; struct xen_add_to_physmap xatp; - static struct shared_info *shared_info_page; + u64 pa; + + if (HYPERVISOR_shared_info == &xen_dummy_shared_info) { + /* + * Search for a free page starting at 4kB physical address. + * Low memory is preferred to avoid an EPT large page split up + * by the mapping. + * Starting below X86_RESERVE_LOW (usually 64kB) is fine as + * the BIOS used for HVM guests is well behaved and won't + * clobber memory other than the first 4kB. + */ + for (pa = PAGE_SIZE; + !e820__mapped_all(pa, pa + PAGE_SIZE, E820_TYPE_RAM) || + memblock_is_reserved(pa); + pa += PAGE_SIZE) + ; + + memblock_reserve(pa, PAGE_SIZE); + HYPERVISOR_shared_info = __va(pa); + } - if (!shared_info_page) - shared_info_page = (struct shared_info *) - extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; + xatp.gpfn = virt_to_pfn(HYPERVISOR_shared_info); if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); - - HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; - - /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info - * page, we use it in the event channel upcall and in some pvclock - * related functions. We don't need the vcpu_info placement - * optimizations because we don't use any pv_mmu or pv_irq op on - * HVM. - * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is - * online but xen_hvm_init_shared_info is run at resume time too and - * in that case multiple vcpus might be online. */ - for_each_online_cpu(cpu) { - /* Leave it to be NULL. */ - if (xen_vcpu_nr(cpu) >= MAX_VIRT_CPUS) - continue; - per_cpu(xen_vcpu, cpu) = - &HYPERVISOR_shared_info->vcpu_info[xen_vcpu_nr(cpu)]; - } } static void __init init_hvm_pv_info(void) @@ -106,7 +106,7 @@ static void xen_hvm_crash_shutdown(struct pt_regs *regs) static int xen_cpu_up_prepare_hvm(unsigned int cpu) { - int rc; + int rc = 0; /* * This can happen if CPU was offlined earlier and @@ -121,7 +121,9 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); else per_cpu(xen_vcpu_id, cpu) = cpu; - xen_vcpu_setup(cpu); + rc = xen_vcpu_setup(cpu); + if (rc) + return rc; if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); @@ -130,9 +132,8 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) if (rc) { WARN(1, "xen_smp_intr_init() for CPU %d failed: %d\n", cpu, rc); - return rc; } - return 0; + return rc; } static int xen_cpu_dead_hvm(unsigned int cpu) @@ -154,6 +155,13 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_shared_info(); + /* + * xen_vcpu is a pointer to the vcpu_info struct in the shared_info + * page, we use it in the event channel upcall and in some pvclock + * related functions. + */ + xen_vcpu_info_reset(0); + xen_panic_handler_init(); if (xen_feature(XENFEAT_hvm_callback_vector)) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 7cd442690f9d..811e4ddb3f37 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -89,8 +89,6 @@ void *xen_initial_gdt; -RESERVE_BRK(shared_info_page_brk, PAGE_SIZE); - static int xen_cpu_up_prepare_pv(unsigned int cpu); static int xen_cpu_dead_pv(unsigned int cpu); @@ -107,44 +105,13 @@ struct tls_descs { */ static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc); -/* - * On restore, set the vcpu placement up again. - * If it fails, then we're in a bad state, since - * we can't back out from using it... - */ -void xen_vcpu_restore(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - bool other_cpu = (cpu != smp_processor_id()); - bool is_up = HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu), - NULL); - - if (other_cpu && is_up && - HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL)) - BUG(); - - xen_setup_runstate_info(cpu); - - if (xen_have_vcpu_info_placement) - xen_vcpu_setup(cpu); - - if (other_cpu && is_up && - HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL)) - BUG(); - } -} - static void __init xen_banner(void) { unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL); struct xen_extraversion extra; HYPERVISOR_xen_version(XENVER_extraversion, &extra); - pr_info("Booting paravirtualized kernel %son %s\n", - xen_feature(XENFEAT_auto_translated_physmap) ? - "with PVH extensions " : "", pv_info.name); + pr_info("Booting paravirtualized kernel on %s\n", pv_info.name); printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); @@ -957,40 +924,48 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high) void xen_setup_shared_info(void) { - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - set_fixmap(FIX_PARAVIRT_BOOTMAP, - xen_start_info->shared_info); + set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info); - HYPERVISOR_shared_info = - (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); - } else - HYPERVISOR_shared_info = - (struct shared_info *)__va(xen_start_info->shared_info); - -#ifndef CONFIG_SMP - /* In UP this is as good a place as any to set up shared info */ - xen_setup_vcpu_info_placement(); -#endif + HYPERVISOR_shared_info = + (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP); xen_setup_mfn_list_list(); - /* - * Now that shared info is set up we can start using routines that - * point to pvclock area. - */ - if (system_state == SYSTEM_BOOTING) + if (system_state == SYSTEM_BOOTING) { +#ifndef CONFIG_SMP + /* + * In UP this is as good a place as any to set up shared info. + * Limit this to boot only, at restore vcpu setup is done via + * xen_vcpu_restore(). + */ + xen_setup_vcpu_info_placement(); +#endif + /* + * Now that shared info is set up we can start using routines + * that point to pvclock area. + */ xen_init_time_ops(); + } } /* This is called once we have the cpu_possible_mask */ -void xen_setup_vcpu_info_placement(void) +void __ref xen_setup_vcpu_info_placement(void) { int cpu; for_each_possible_cpu(cpu) { /* Set up direct vCPU id mapping for PV guests. */ per_cpu(xen_vcpu_id, cpu) = cpu; - xen_vcpu_setup(cpu); + + /* + * xen_vcpu_setup(cpu) can fail -- in which case it + * falls back to the shared_info version for cpus + * where xen_vcpu_nr(cpu) < MAX_VIRT_CPUS. + * + * xen_cpu_up_prepare_pv() handles the rest by failing + * them in hotplug. + */ + (void) xen_vcpu_setup(cpu); } /* @@ -1339,9 +1314,17 @@ asmlinkage __visible void __init xen_start_kernel(void) */ acpi_numa = -1; #endif - /* Don't do the full vcpu_info placement stuff until we have a - possible map and a non-dummy shared_info. */ - per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; + /* Let's presume PV guests always boot on vCPU with id 0. */ + per_cpu(xen_vcpu_id, 0) = 0; + + /* + * Setup xen_vcpu early because start_kernel needs it for + * local_irq_disable(), irqs_disabled(). + * + * Don't do the full vcpu_info placement stuff until we have + * the cpu_possible_mask and a non-dummy shared_info. + */ + xen_vcpu_info_reset(0); WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); @@ -1438,9 +1421,7 @@ asmlinkage __visible void __init xen_start_kernel(void) #endif xen_raw_console_write("about to get started...\n"); - /* Let's presume PV guests always boot on vCPU with id 0. */ - per_cpu(xen_vcpu_id, 0) = 0; - + /* We need this for printk timestamps */ xen_setup_runstate_info(0); xen_efi_init(); @@ -1458,6 +1439,9 @@ static int xen_cpu_up_prepare_pv(unsigned int cpu) { int rc; + if (per_cpu(xen_vcpu, cpu) == NULL) + return -ENODEV; + xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 5e375a5e815f..3be06f3caf3c 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,7 +42,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) } EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); -void xen_flush_tlb_all(void) +static void xen_flush_tlb_all(void) { struct mmuext_op *op; struct multicall_space mcs; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 7397d8b8459d..1d7a7213a310 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -355,10 +355,8 @@ static pteval_t pte_pfn_to_mfn(pteval_t val) pteval_t flags = val & PTE_FLAGS_MASK; unsigned long mfn; - if (!xen_feature(XENFEAT_auto_translated_physmap)) - mfn = __pfn_to_mfn(pfn); - else - mfn = pfn; + mfn = __pfn_to_mfn(pfn); + /* * If there's no mfn for the pfn, then just create an * empty non-present pte. Unfortunately this loses @@ -647,9 +645,6 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, limit--; BUG_ON(limit >= FIXADDR_TOP); - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - /* * 64-bit has a great big hole in the middle of the address * space, which contains the Xen mappings. On 32-bit these @@ -980,37 +975,32 @@ static void xen_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) spin_unlock(&mm->page_table_lock); } - -#ifdef CONFIG_SMP -/* Another cpu may still have their %cr3 pointing at the pagetable, so - we need to repoint it somewhere else before we can unpin it. */ -static void drop_other_mm_ref(void *info) +static void drop_mm_ref_this_cpu(void *info) { struct mm_struct *mm = info; - struct mm_struct *active_mm; - - active_mm = this_cpu_read(cpu_tlbstate.active_mm); - if (active_mm == mm && this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) + if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) leave_mm(smp_processor_id()); - /* If this cpu still has a stale cr3 reference, then make sure - it has been flushed. */ + /* + * If this cpu still has a stale cr3 reference, then make sure + * it has been flushed. + */ if (this_cpu_read(xen_current_cr3) == __pa(mm->pgd)) - load_cr3(swapper_pg_dir); + xen_mc_flush(); } +#ifdef CONFIG_SMP +/* + * Another cpu may still have their %cr3 pointing at the pagetable, so + * we need to repoint it somewhere else before we can unpin it. + */ static void xen_drop_mm_ref(struct mm_struct *mm) { cpumask_var_t mask; unsigned cpu; - if (current->active_mm == mm) { - if (current->mm == mm) - load_cr3(swapper_pg_dir); - else - leave_mm(smp_processor_id()); - } + drop_mm_ref_this_cpu(mm); /* Get the "official" set of cpus referring to our pagetable. */ if (!alloc_cpumask_var(&mask, GFP_ATOMIC)) { @@ -1018,31 +1008,31 @@ static void xen_drop_mm_ref(struct mm_struct *mm) if (!cpumask_test_cpu(cpu, mm_cpumask(mm)) && per_cpu(xen_current_cr3, cpu) != __pa(mm->pgd)) continue; - smp_call_function_single(cpu, drop_other_mm_ref, mm, 1); + smp_call_function_single(cpu, drop_mm_ref_this_cpu, mm, 1); } return; } cpumask_copy(mask, mm_cpumask(mm)); - /* It's possible that a vcpu may have a stale reference to our - cr3, because its in lazy mode, and it hasn't yet flushed - its set of pending hypercalls yet. In this case, we can - look at its actual current cr3 value, and force it to flush - if needed. */ + /* + * It's possible that a vcpu may have a stale reference to our + * cr3, because its in lazy mode, and it hasn't yet flushed + * its set of pending hypercalls yet. In this case, we can + * look at its actual current cr3 value, and force it to flush + * if needed. + */ for_each_online_cpu(cpu) { if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd)) cpumask_set_cpu(cpu, mask); } - if (!cpumask_empty(mask)) - smp_call_function_many(mask, drop_other_mm_ref, mm, 1); + smp_call_function_many(mask, drop_mm_ref_this_cpu, mm, 1); free_cpumask_var(mask); } #else static void xen_drop_mm_ref(struct mm_struct *mm) { - if (current->active_mm == mm) - load_cr3(swapper_pg_dir); + drop_mm_ref_this_cpu(mm); } #endif @@ -1289,9 +1279,6 @@ static void __init xen_pagetable_cleanhighmap(void) static void __init xen_pagetable_p2m_setup(void) { - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - xen_vmalloc_p2m_tree(); #ifdef CONFIG_X86_64 @@ -1314,8 +1301,7 @@ static void __init xen_pagetable_init(void) xen_build_mfn_list_list(); /* Remap memory freed due to conflicts with E820 map */ - if (!xen_feature(XENFEAT_auto_translated_physmap)) - xen_remap_memory(); + xen_remap_memory(); xen_setup_shared_info(); } @@ -1375,8 +1361,7 @@ static void xen_flush_tlb_single(unsigned long addr) } static void xen_flush_tlb_others(const struct cpumask *cpus, - struct mm_struct *mm, unsigned long start, - unsigned long end) + const struct flush_tlb_info *info) { struct { struct mmuext_op op; @@ -1388,7 +1373,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_others(cpus, mm, start, end); + trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end); if (cpumask_empty(cpus)) return; /* nothing to do */ @@ -1402,9 +1387,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask)); args->op.cmd = MMUEXT_TLB_FLUSH_MULTI; - if (end != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) { + if (info->end != TLB_FLUSH_ALL && + (info->end - info->start) <= PAGE_SIZE) { args->op.cmd = MMUEXT_INVLPG_MULTI; - args->op.arg1.linear_addr = start; + args->op.arg1.linear_addr = info->start; } MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF); @@ -1479,8 +1465,8 @@ static void xen_write_cr3(unsigned long cr3) * At the start of the day - when Xen launches a guest, it has already * built pagetables for the guest. We diligently look over them * in xen_setup_kernel_pagetable and graft as appropriate them in the - * init_level4_pgt and its friends. Then when we are happy we load - * the new init_level4_pgt - and continue on. + * init_top_pgt and its friends. Then when we are happy we load + * the new init_top_pgt - and continue on. * * The generic code starts (start_kernel) and 'init_mem_mapping' sets * up the rest of the pagetables. When it has completed it loads the cr3. @@ -1923,23 +1909,22 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) pt_end = pt_base + xen_start_info->nr_pt_frames; /* Zap identity mapping */ - init_level4_pgt[0] = __pgd(0); - - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt - * L4[511] -> level3_kernel_pgt */ - convert_pfn_mfn(init_level4_pgt); - - /* L3_i[0] -> level2_ident_pgt */ - convert_pfn_mfn(level3_ident_pgt); - /* L3_k[510] -> level2_kernel_pgt - * L3_k[511] -> level2_fixmap_pgt */ - convert_pfn_mfn(level3_kernel_pgt); - - /* L3_k[511][506] -> level1_fixmap_pgt */ - convert_pfn_mfn(level2_fixmap_pgt); - } + init_top_pgt[0] = __pgd(0); + + /* Pre-constructed entries are in pfn, so convert to mfn */ + /* L4[272] -> level3_ident_pgt */ + /* L4[511] -> level3_kernel_pgt */ + convert_pfn_mfn(init_top_pgt); + + /* L3_i[0] -> level2_ident_pgt */ + convert_pfn_mfn(level3_ident_pgt); + /* L3_k[510] -> level2_kernel_pgt */ + /* L3_k[511] -> level2_fixmap_pgt */ + convert_pfn_mfn(level3_kernel_pgt); + + /* L3_k[511][506] -> level1_fixmap_pgt */ + convert_pfn_mfn(level2_fixmap_pgt); + /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud); @@ -1960,36 +1945,32 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Copy the initial P->M table mappings if necessary. */ i = pgd_index(xen_start_info->mfn_list); if (i && i < pgd_index(__START_KERNEL_map)) - init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; - - if (!xen_feature(XENFEAT_auto_translated_physmap)) { - /* Make pagetable pieces RO */ - set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); - set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); - set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); - set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); - set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); - - /* Pin down new L4 */ - pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa_symbol(init_level4_pgt))); - - /* Unpin Xen-provided one */ - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); + init_top_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i]; + + /* Make pagetable pieces RO */ + set_page_prot(init_top_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO); + set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); + set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); + set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); + + /* Pin down new L4 */ + pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, + PFN_DOWN(__pa_symbol(init_top_pgt))); + + /* Unpin Xen-provided one */ + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - /* - * At this stage there can be no user pgd, and no page - * structure to attach it to, so make sure we just set kernel - * pgd. - */ - xen_mc_batch(); - __xen_write_cr3(true, __pa(init_level4_pgt)); - xen_mc_issue(PARAVIRT_LAZY_CPU); - } else - native_write_cr3(__pa(init_level4_pgt)); + /* + * At this stage there can be no user pgd, and no page structure to + * attach it to, so make sure we just set kernel pgd. + */ + xen_mc_batch(); + __xen_write_cr3(true, __pa(init_top_pgt)); + xen_mc_issue(PARAVIRT_LAZY_CPU); /* We can't that easily rip out L3 and L2, as the Xen pagetables are * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for @@ -2036,7 +2017,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) pmd_t pmd; pte_t pte; - pa = read_cr3(); + pa = read_cr3_pa(); pgd = native_make_pgd(xen_read_phys_ulong(pa + pgd_index(vaddr) * sizeof(pgd))); if (!pgd_present(pgd)) @@ -2116,7 +2097,7 @@ void __init xen_relocate_p2m(void) pt_phys = pmd_phys + PFN_PHYS(n_pmd); p2m_pfn = PFN_DOWN(pt_phys) + n_pt; - pgd = __va(read_cr3()); + pgd = __va(read_cr3_pa()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); idx_p4d = 0; save_pud = n_pud; @@ -2223,7 +2204,7 @@ static void __init xen_write_cr3_init(unsigned long cr3) { unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); - BUG_ON(read_cr3() != __pa(initial_page_table)); + BUG_ON(read_cr3_pa() != __pa(initial_page_table)); BUG_ON(cr3 != __pa(swapper_pg_dir)); /* @@ -2403,9 +2384,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) static void __init xen_post_allocator_init(void) { - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; @@ -2511,9 +2489,6 @@ void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - pv_mmu_ops = xen_mmu_ops; memset(dummy_mapping, 0xff, PAGE_SIZE); @@ -2650,9 +2625,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, * this function are redundant and can be ignored. */ - if (xen_feature(XENFEAT_auto_translated_physmap)) - return 0; - if (unlikely(order > MAX_CONTIG_ORDER)) return -ENOMEM; @@ -2689,9 +2661,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) int success; unsigned long vstart; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return; - if (unlikely(order > MAX_CONTIG_ORDER)) return; diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c index 42b08f8fc2ca..37c6056a7bba 100644 --- a/arch/x86/xen/pci-swiotlb-xen.c +++ b/arch/x86/xen/pci-swiotlb-xen.c @@ -18,20 +18,6 @@ int xen_swiotlb __read_mostly; -static const struct dma_map_ops xen_swiotlb_dma_ops = { - .alloc = xen_swiotlb_alloc_coherent, - .free = xen_swiotlb_free_coherent, - .sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu, - .sync_single_for_device = xen_swiotlb_sync_single_for_device, - .sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu, - .sync_sg_for_device = xen_swiotlb_sync_sg_for_device, - .map_sg = xen_swiotlb_map_sg_attrs, - .unmap_sg = xen_swiotlb_unmap_sg_attrs, - .map_page = xen_swiotlb_map_page, - .unmap_page = xen_swiotlb_unmap_page, - .dma_supported = xen_swiotlb_dma_supported, -}; - /* * pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary * diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a5bf7c451435..c81046323ebc 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -499,7 +499,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, void __init xen_remap_memory(void) { unsigned long buf = (unsigned long)&xen_remap_buf; - unsigned long mfn_save, mfn, pfn; + unsigned long mfn_save, pfn; unsigned long remapped = 0; unsigned int i; unsigned long pfn_s = ~0UL; @@ -515,8 +515,7 @@ void __init xen_remap_memory(void) pfn = xen_remap_buf.target_pfn; for (i = 0; i < xen_remap_buf.size; i++) { - mfn = xen_remap_buf.mfns[i]; - xen_update_mem_tables(pfn, mfn); + xen_update_mem_tables(pfn, xen_remap_buf.mfns[i]); remapped++; pfn++; } @@ -530,8 +529,6 @@ void __init xen_remap_memory(void) pfn_s = xen_remap_buf.target_pfn; len = xen_remap_buf.size; } - - mfn = xen_remap_mfn; xen_remap_mfn = xen_remap_buf.next_area_mfn; } diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 82ac611f2fc1..e7f02eb73727 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -1,4 +1,5 @@ #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/slab.h> #include <linux/cpumask.h> #include <linux/percpu.h> @@ -114,6 +115,36 @@ int xen_smp_intr_init(unsigned int cpu) return rc; } +void __init xen_smp_cpus_done(unsigned int max_cpus) +{ + int cpu, rc, count = 0; + + if (xen_hvm_domain()) + native_smp_cpus_done(max_cpus); + + if (xen_have_vcpu_info_placement) + return; + + for_each_online_cpu(cpu) { + if (xen_vcpu_nr(cpu) < MAX_VIRT_CPUS) + continue; + + rc = cpu_down(cpu); + + if (rc == 0) { + /* + * Reset vcpu_info so this cpu cannot be onlined again. + */ + xen_vcpu_info_reset(cpu); + count++; + } else { + pr_warn("%s: failed to bring CPU %d down, error %d\n", + __func__, cpu, rc); + } + } + WARN(count, "%s: brought %d CPUs offline\n", __func__, count); +} + void xen_smp_send_reschedule(int cpu) { xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR); diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index 8ebb6acca64a..87d3c76cba37 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -14,6 +14,8 @@ extern void xen_smp_intr_free(unsigned int cpu); int xen_smp_intr_init_pv(unsigned int cpu); void xen_smp_intr_free_pv(unsigned int cpu); +void xen_smp_cpus_done(unsigned int max_cpus); + void xen_smp_send_reschedule(int cpu); void xen_smp_send_call_function_ipi(const struct cpumask *mask); void xen_smp_send_call_function_single_ipi(int cpu); diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f18561bbf5c9..fd60abedf658 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -12,7 +12,8 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void) native_smp_prepare_boot_cpu(); /* - * Setup vcpu_info for boot CPU. + * Setup vcpu_info for boot CPU. Secondary CPUs get their vcpu_info + * in xen_cpu_up_prepare_hvm(). */ xen_vcpu_setup(0); @@ -27,10 +28,20 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void) static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) { + int cpu; + native_smp_prepare_cpus(max_cpus); WARN_ON(xen_smp_intr_init(0)); xen_init_lock_cpu(0); + + for_each_possible_cpu(cpu) { + if (cpu == 0) + continue; + + /* Set default vcpu_id to make sure that we don't use cpu-0's */ + per_cpu(xen_vcpu_id, cpu) = XEN_VCPU_ID_INVALID; + } } #ifdef CONFIG_HOTPLUG_CPU @@ -60,4 +71,5 @@ void __init xen_hvm_smp_init(void) smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_cpus_done = xen_smp_cpus_done; } diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index aae32535f4ec..1ea598e5f030 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -371,10 +371,6 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle) return 0; } -static void xen_pv_smp_cpus_done(unsigned int max_cpus) -{ -} - #ifdef CONFIG_HOTPLUG_CPU static int xen_pv_cpu_disable(void) { @@ -469,7 +465,7 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id) static const struct smp_ops xen_smp_ops __initconst = { .smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu, .smp_prepare_cpus = xen_pv_smp_prepare_cpus, - .smp_cpus_done = xen_pv_smp_cpus_done, + .smp_cpus_done = xen_smp_cpus_done, .cpu_up = xen_pv_cpu_up, .cpu_die = xen_pv_cpu_die, diff --git a/arch/x86/xen/suspend_hvm.c b/arch/x86/xen/suspend_hvm.c index 01afcadde50a..484999416d8b 100644 --- a/arch/x86/xen/suspend_hvm.c +++ b/arch/x86/xen/suspend_hvm.c @@ -8,15 +8,10 @@ void xen_hvm_post_suspend(int suspend_cancelled) { - int cpu; - - if (!suspend_cancelled) + if (!suspend_cancelled) { xen_hvm_init_shared_info(); + xen_vcpu_restore(); + } xen_callback_vector(); xen_unplug_emulated_devices(); - if (xen_feature(XENFEAT_hvm_safe_pvclock)) { - for_each_online_cpu(cpu) { - xen_setup_runstate_info(cpu); - } - } } diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 9a440a42c618..0d5004477db6 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -78,7 +78,8 @@ bool xen_vcpu_stolen(int vcpu); extern int xen_have_vcpu_info_placement; -void xen_vcpu_setup(int cpu); +int xen_vcpu_setup(int cpu); +void xen_vcpu_info_reset(int cpu); void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP diff --git a/arch/x86/xen/xen-pvh.S b/arch/x86/xen/xen-pvh.S index 5e246716d58f..e1a5fbeae08d 100644 --- a/arch/x86/xen/xen-pvh.S +++ b/arch/x86/xen/xen-pvh.S @@ -87,7 +87,7 @@ ENTRY(pvh_start_xen) wrmsr /* Enable pre-constructed page tables. */ - mov $_pa(init_level4_pgt), %eax + mov $_pa(init_top_pgt), %eax mov %eax, %cr3 mov $(X86_CR0_PG | X86_CR0_PE), %eax mov %eax, %cr0 |