diff options
Diffstat (limited to 'arch/x86')
82 files changed, 806 insertions, 596 deletions
diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5c477260294f..412189d2bff9 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -31,6 +31,9 @@ ifeq ($(CONFIG_X86_32),y) KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return + # Don't autogenerate MMX or SSE instructions + KBUILD_CFLAGS += -mno-mmx -mno-sse + # Never want PIC in a 32-bit kernel, prevent breakage with GCC built # with nonstandard options KBUILD_CFLAGS += -fno-pic @@ -57,8 +60,11 @@ else KBUILD_AFLAGS += -m64 KBUILD_CFLAGS += -m64 + # Don't autogenerate MMX or SSE instructions + KBUILD_CFLAGS += -mno-mmx -mno-sse + # Use -mpreferred-stack-boundary=3 if supported. - KBUILD_CFLAGS += $(call cc-option,-mno-sse -mpreferred-stack-boundary=3) + KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3) # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu) cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 379814bc41e3..6cf0111783d3 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -53,18 +53,18 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE # 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. -KBUILD_CFLAGS := $(USERINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ +KBUILD_CFLAGS := $(USERINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ \ -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/code16gcc.h \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ + -mno-mmx -mno-sse \ $(call cc-option, -ffreestanding) \ $(call cc-option, -fno-toplevel-reorder,\ - $(call cc-option, -fno-unit-at-a-time)) \ + $(call cc-option, -fno-unit-at-a-time)) \ $(call cc-option, -fno-stack-protector) \ $(call cc-option, -mpreferred-stack-boundary=2) -KBUILD_CFLAGS += $(call cc-option, -m32) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ GCOV_PROFILE := n diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 5ef205c5f37b..7194d9f094bc 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -12,6 +12,7 @@ KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) +KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index c205035a6b96..17177e80d466 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -865,6 +865,9 @@ fail: * Because the x86 boot code expects to be passed a boot_params we * need to create one ourselves (usually the bootloader would create * one for us). + * + * The caller is responsible for filling out ->code32_start in the + * returned boot_params. */ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) { @@ -875,14 +878,15 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) struct efi_info *efi; efi_loaded_image_t *image; void *options; - u32 load_options_size; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; int options_size = 0; efi_status_t status; - unsigned long cmdline; + char *cmdline_ptr; u16 *s2; u8 *s1; int i; + unsigned long ramdisk_addr; + unsigned long ramdisk_size; sys_table = _table; @@ -893,13 +897,14 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) status = efi_call_phys3(sys_table->boottime->handle_protocol, handle, &proto, (void *)&image); if (status != EFI_SUCCESS) { - efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); + efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n"); return NULL; } - status = low_alloc(0x4000, 1, (unsigned long *)&boot_params); + status = efi_low_alloc(sys_table, 0x4000, 1, + (unsigned long *)&boot_params); if (status != EFI_SUCCESS) { - efi_printk("Failed to alloc lowmem for boot params\n"); + efi_printk(sys_table, "Failed to alloc lowmem for boot params\n"); return NULL; } @@ -921,45 +926,13 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) hdr->vid_mode = 0xffff; hdr->boot_flag = 0xAA55; - hdr->code32_start = (__u64)(unsigned long)image->image_base; - hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - options = image->load_options; - load_options_size = image->load_options_size / 2; /* ASCII */ - cmdline = 0; - s2 = (u16 *)options; - - if (s2) { - while (*s2 && *s2 != '\n' && options_size < load_options_size) { - s2++; - options_size++; - } - - if (options_size) { - if (options_size > hdr->cmdline_size) - options_size = hdr->cmdline_size; - - options_size++; /* NUL termination */ - - status = low_alloc(options_size, 1, &cmdline); - if (status != EFI_SUCCESS) { - efi_printk("Failed to alloc mem for cmdline\n"); - goto fail; - } - - s1 = (u8 *)(unsigned long)cmdline; - s2 = (u16 *)options; - - for (i = 0; i < options_size - 1; i++) - *s1++ = *s2++; - - *s1 = '\0'; - } - } - - hdr->cmd_line_ptr = cmdline; + cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); + if (!cmdline_ptr) + goto fail; + hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; hdr->ramdisk_image = 0; hdr->ramdisk_size = 0; @@ -969,16 +942,20 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) memset(sdt, 0, sizeof(*sdt)); - status = handle_ramdisks(image, hdr); + status = handle_cmdline_files(sys_table, image, + (char *)(unsigned long)hdr->cmd_line_ptr, + "initrd=", hdr->initrd_addr_max, + &ramdisk_addr, &ramdisk_size); if (status != EFI_SUCCESS) goto fail2; + hdr->ramdisk_image = ramdisk_addr; + hdr->ramdisk_size = ramdisk_size; return boot_params; fail2: - if (options_size) - low_free(options_size, hdr->cmd_line_ptr); + efi_free(sys_table, options_size, hdr->cmd_line_ptr); fail: - low_free(0x4000, (unsigned long)boot_params); + efi_free(sys_table, 0x4000, (unsigned long)boot_params); return NULL; } @@ -992,22 +969,24 @@ static efi_status_t exit_boot(struct boot_params *boot_params, efi_memory_desc_t *mem_map; efi_status_t status; __u32 desc_version; + bool called_exit = false; u8 nr_entries; int i; size = sizeof(*mem_map) * 32; again: - size += sizeof(*mem_map); + size += sizeof(*mem_map) * 2; _size = size; - status = low_alloc(size, 1, (unsigned long *)&mem_map); + status = efi_low_alloc(sys_table, size, 1, (unsigned long *)&mem_map); if (status != EFI_SUCCESS) return status; +get_map: status = efi_call_phys5(sys_table->boottime->get_memory_map, &size, mem_map, &key, &desc_size, &desc_version); if (status == EFI_BUFFER_TOO_SMALL) { - low_free(_size, (unsigned long)mem_map); + efi_free(sys_table, _size, (unsigned long)mem_map); goto again; } @@ -1029,8 +1008,20 @@ again: /* Might as well exit boot services now */ status = efi_call_phys2(sys_table->boottime->exit_boot_services, handle, key); - if (status != EFI_SUCCESS) - goto free_mem_map; + if (status != EFI_SUCCESS) { + /* + * ExitBootServices() will fail if any of the event + * handlers change the memory map. In which case, we + * must be prepared to retry, but only once so that + * we're guaranteed to exit on repeated failures instead + * of spinning forever. + */ + if (called_exit) + goto free_mem_map; + + called_exit = true; + goto get_map; + } /* Historic? */ boot_params->alt_mem_k = 32 * 1024; @@ -1097,44 +1088,10 @@ again: return EFI_SUCCESS; free_mem_map: - low_free(_size, (unsigned long)mem_map); + efi_free(sys_table, _size, (unsigned long)mem_map); return status; } -static efi_status_t relocate_kernel(struct setup_header *hdr) -{ - unsigned long start, nr_pages; - efi_status_t status; - - /* - * The EFI firmware loader could have placed the kernel image - * anywhere in memory, but the kernel has various restrictions - * on the max physical address it can run at. Attempt to move - * the kernel to boot_params.pref_address, or as low as - * possible. - */ - start = hdr->pref_address; - nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE; - - status = efi_call_phys4(sys_table->boottime->allocate_pages, - EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA, - nr_pages, &start); - if (status != EFI_SUCCESS) { - status = low_alloc(hdr->init_size, hdr->kernel_alignment, - &start); - if (status != EFI_SUCCESS) - efi_printk("Failed to alloc mem for kernel\n"); - } - - if (status == EFI_SUCCESS) - memcpy((void *)start, (void *)(unsigned long)hdr->code32_start, - hdr->init_size); - - hdr->pref_address = hdr->code32_start; - hdr->code32_start = (__u32)start; - - return status; -} /* * On success we return a pointer to a boot_params structure, and NULL @@ -1163,14 +1120,15 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, EFI_LOADER_DATA, sizeof(*gdt), (void **)&gdt); if (status != EFI_SUCCESS) { - efi_printk("Failed to alloc mem for gdt structure\n"); + efi_printk(sys_table, "Failed to alloc mem for gdt structure\n"); goto fail; } gdt->size = 0x800; - status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address); + status = efi_low_alloc(sys_table, gdt->size, 8, + (unsigned long *)&gdt->address); if (status != EFI_SUCCESS) { - efi_printk("Failed to alloc mem for gdt\n"); + efi_printk(sys_table, "Failed to alloc mem for gdt\n"); goto fail; } @@ -1178,7 +1136,7 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, EFI_LOADER_DATA, sizeof(*idt), (void **)&idt); if (status != EFI_SUCCESS) { - efi_printk("Failed to alloc mem for idt structure\n"); + efi_printk(sys_table, "Failed to alloc mem for idt structure\n"); goto fail; } @@ -1190,10 +1148,16 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table, * address, relocate it. */ if (hdr->pref_address != hdr->code32_start) { - status = relocate_kernel(hdr); - + unsigned long bzimage_addr = hdr->code32_start; + status = efi_relocate_kernel(sys_table, &bzimage_addr, + hdr->init_size, hdr->init_size, + hdr->pref_address, + hdr->kernel_alignment); if (status != EFI_SUCCESS) goto fail; + + hdr->pref_address = hdr->code32_start; + hdr->code32_start = bzimage_addr; } status = exit_boot(boot_params, handle); diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index e5b0a8f91c5f..cc78e2da7af9 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -10,8 +10,6 @@ #define SEG_GRANULARITY_4KB (1 << 0) #define DESC_TYPE_CODE_DATA (1 << 0) - -#define EFI_PAGE_SIZE (1UL << EFI_PAGE_SHIFT) #define EFI_READ_CHUNK_SIZE (1024 * 1024) #define EFI_CONSOLE_OUT_DEVICE_GUID \ @@ -40,6 +38,24 @@ struct efi_graphics_output_mode_info { u32 pixels_per_scan_line; } __packed; +struct efi_graphics_output_protocol_mode_32 { + u32 max_mode; + u32 mode; + u32 info; + u32 size_of_info; + u64 frame_buffer_base; + u32 frame_buffer_size; +} __packed; + +struct efi_graphics_output_protocol_mode_64 { + u32 max_mode; + u32 mode; + u64 info; + u64 size_of_info; + u64 frame_buffer_base; + u64 frame_buffer_size; +} __packed; + struct efi_graphics_output_protocol_mode { u32 max_mode; u32 mode; @@ -49,6 +65,20 @@ struct efi_graphics_output_protocol_mode { unsigned long frame_buffer_size; } __packed; +struct efi_graphics_output_protocol_32 { + u32 query_mode; + u32 set_mode; + u32 blt; + u32 mode; +}; + +struct efi_graphics_output_protocol_64 { + u64 query_mode; + u64 set_mode; + u64 blt; + u64 mode; +}; + struct efi_graphics_output_protocol { void *query_mode; unsigned long set_mode; @@ -56,16 +86,22 @@ struct efi_graphics_output_protocol { struct efi_graphics_output_protocol_mode *mode; }; +struct efi_uga_draw_protocol_32 { + u32 get_mode; + u32 set_mode; + u32 blt; +}; + +struct efi_uga_draw_protocol_64 { + u64 get_mode; + u64 set_mode; + u64 blt; +}; + struct efi_uga_draw_protocol { void *get_mode; void *set_mode; void *blt; }; -struct efi_simple_text_output_protocol { - void *reset; - void *output_string; - void *test_string; -}; - #endif /* BOOT_COMPRESSED_EBOOT_H */ diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 1e3184f6072f..abb988a54c69 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -50,6 +50,13 @@ ENTRY(efi_pe_entry) pushl %eax pushl %esi pushl %ecx + + call reloc +reloc: + popl %ecx + subl reloc, %ecx + movl %ecx, BP_code32_start(%eax) + sub $0x4, %esp ENTRY(efi_stub_entry) @@ -63,12 +70,7 @@ ENTRY(efi_stub_entry) hlt jmp 1b 2: - call 3f -3: - popl %eax - subl $3b, %eax - subl BP_pref_address(%esi), %eax - add BP_code32_start(%esi), %eax + movl BP_code32_start(%esi), %eax leal preferred_addr(%eax), %eax jmp *%eax diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 16f24e6dad79..92059b8f3f7b 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -217,6 +217,8 @@ ENTRY(efi_pe_entry) cmpq $0,%rax je 1f mov %rax, %rdx + leaq startup_32(%rip), %rax + movl %eax, BP_code32_start(%rdx) popq %rsi popq %rdi @@ -230,12 +232,7 @@ ENTRY(efi_stub_entry) hlt jmp 1b 2: - call 3f -3: - popq %rax - subq $3b, %rax - subq BP_pref_address(%rsi), %rax - add BP_code32_start(%esi), %eax + movl BP_code32_start(%esi), %eax leaq preferred_addr(%rax), %rax jmp *%rax diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 586f41aac361..185fad49d86f 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -24,10 +24,6 @@ .align 16 .Lbswap_mask: .octa 0x000102030405060708090a0b0c0d0e0f -.Lpoly: - .octa 0xc2000000000000000000000000000001 -.Ltwo_one: - .octa 0x00000001000000000000000000000001 #define DATA %xmm0 #define SHASH %xmm1 @@ -134,28 +130,3 @@ ENTRY(clmul_ghash_update) .Lupdate_just_ret: ret ENDPROC(clmul_ghash_update) - -/* - * void clmul_ghash_setkey(be128 *shash, const u8 *key); - * - * Calculate hash_key << 1 mod poly - */ -ENTRY(clmul_ghash_setkey) - movaps .Lbswap_mask, BSWAP - movups (%rsi), %xmm0 - PSHUFB_XMM BSWAP %xmm0 - movaps %xmm0, %xmm1 - psllq $1, %xmm0 - psrlq $63, %xmm1 - movaps %xmm1, %xmm2 - pslldq $8, %xmm1 - psrldq $8, %xmm2 - por %xmm1, %xmm0 - # reduction - pshufd $0b00100100, %xmm2, %xmm1 - pcmpeqd .Ltwo_one, %xmm1 - pand .Lpoly, %xmm1 - pxor %xmm1, %xmm0 - movups %xmm0, (%rdi) - ret -ENDPROC(clmul_ghash_setkey) diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 6759dd1135be..d785cf2c529c 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -30,8 +30,6 @@ void clmul_ghash_mul(char *dst, const be128 *shash); void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, const be128 *shash); -void clmul_ghash_setkey(be128 *shash, const u8 *key); - struct ghash_async_ctx { struct cryptd_ahash *cryptd_tfm; }; @@ -58,13 +56,23 @@ static int ghash_setkey(struct crypto_shash *tfm, const u8 *key, unsigned int keylen) { struct ghash_ctx *ctx = crypto_shash_ctx(tfm); + be128 *x = (be128 *)key; + u64 a, b; if (keylen != GHASH_BLOCK_SIZE) { crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); return -EINVAL; } - clmul_ghash_setkey(&ctx->shash, key); + /* perform multiplication by 'x' in GF(2^128) */ + a = be64_to_cpu(x->a); + b = be64_to_cpu(x->b); + + ctx->shash.a = (__be64)((b << 1) | (a >> 63)); + ctx->shash.b = (__be64)((a << 1) | (b >> 63)); + + if (a >> 63) + ctx->shash.b ^= cpu_to_be64(0xc2); return 0; } diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 6cbd8df348d2..9f5e71f06671 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -141,7 +141,7 @@ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) /* save number of bits */ bits[1] = cpu_to_be64(sctx->count[0] << 3); - bits[0] = cpu_to_be64(sctx->count[1] << 3) | sctx->count[0] >> 61; + bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); /* Pad out to 112 mod 128 and append length */ index = sctx->count[0] & 0x7f; diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index cf1a471a18a2..10adb41f162e 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -459,7 +459,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 653668d140f9..4a8cb8d7cbd5 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->olpc_ofw_header, 0, + memset(&boot_params->ext_ramdisk_image, 0, (char *)&boot_params->efi_info - - (char *)&boot_params->olpc_ofw_header); + (char *)&boot_params->ext_ramdisk_image); memset(&boot_params->kbd_status, 0, (char *)&boot_params->hdr - (char *)&boot_params->kbd_status); diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 46fc474fd819..f50de6951738 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src, int len, __wsum sum, int *err_ptr) { + __wsum ret; + might_sleep(); - return csum_partial_copy_generic((__force void *)src, dst, - len, sum, err_ptr, NULL); + stac(); + ret = csum_partial_copy_generic((__force void *)src, dst, + len, sum, err_ptr, NULL); + clac(); + + return ret; } /* @@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src, int len, __wsum sum, int *err_ptr) { + __wsum ret; + might_sleep(); - if (access_ok(VERIFY_WRITE, dst, len)) - return csum_partial_copy_generic(src, (__force void *)dst, - len, sum, NULL, err_ptr); + if (access_ok(VERIFY_WRITE, dst, len)) { + stac(); + ret = csum_partial_copy_generic(src, (__force void *)dst, + len, sum, NULL, err_ptr); + clac(); + return ret; + } if (len) *err_ptr = -EFAULT; diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index e99ac27f95b2..4af181dacf9e 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -365,7 +365,7 @@ extern const char * const x86_power_flags[32]; static __always_inline __pure bool __static_cpu_has(u16 bit) { #if __GNUC__ > 4 || __GNUC_MINOR__ >= 5 - asm goto("1: jmp %l[t_no]\n" + asm_volatile_goto("1: jmp %l[t_no]\n" "2:\n" ".section .altinstructions,\"a\"\n" " .long 1b - .\n" diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index cccd07fa5e3a..779c2efe2e97 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -29,7 +29,7 @@ extern void e820_setup_gap(void); extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, unsigned long start_addr, unsigned long long end_addr); struct setup_data; -extern void parse_e820_ext(struct setup_data *data); +extern void parse_e820_ext(u64 phys_addr, u32 data_len); #if defined(CONFIG_X86_64) || \ (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 60c89f30c727..7a76dc284166 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -94,7 +94,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; -extern unsigned long x86_efi_facility; +extern struct efi_scratch efi_scratch; extern void efi_set_executable(efi_memory_desc_t *md, bool executable); extern int efi_memblock_x86_reserve_range(void); extern void efi_call_phys_prelog(void); diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index e25cc33ec54d..e72b2e41499e 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -295,12 +295,13 @@ static inline int restore_fpu_checking(struct task_struct *tsk) /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is pending. Clear the x87 state here by setting it to fixed values. "m" is a random variable that should be in L1 */ - alternative_input( - ASM_NOP8 ASM_NOP2, - "emms\n\t" /* clear stack tags */ - "fildl %P[addr]", /* set F?P to defined value */ - X86_FEATURE_FXSAVE_LEAK, - [addr] "m" (tsk->thread.fpu.has_fpu)); + if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) { + asm volatile( + "fnclex\n\t" + "emms\n\t" + "fildl %P[addr]" /* set F?P to defined value */ + : : [addr] "m" (tsk->thread.fpu.has_fpu)); + } return fpu_restore_checking(&tsk->thread.fpu); } diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h index a8091216963b..68c05398bba9 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + ptep_clear_flush(vma, addr, ptep); } static inline int huge_pte_none(pte_t pte) diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 3a16c1483b45..029766958e69 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -13,7 +13,7 @@ static __always_inline bool arch_static_branch(struct static_key *key) { - asm goto("1:" + asm_volatile_goto("1:" STATIC_KEY_INITIAL_NOP ".pushsection __jump_table, \"aw\" \n\t" _ASM_ALIGN "\n\t" diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3741c653767c..8b320722de7a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -92,7 +92,7 @@ #define KVM_REFILL_PAGES 25 #define KVM_MAX_CPUID_ENTRIES 80 #define KVM_NR_FIXED_MTRR_REGION 88 -#define KVM_NR_VAR_MTRR 8 +#define KVM_NR_VAR_MTRR 10 #define ASYNC_PF_PER_VCPU 64 @@ -445,7 +445,7 @@ struct kvm_vcpu_arch { bool nmi_injected; /* Trying to inject an NMI this entry */ struct mtrr_state_type mtrr_state; - u32 pat; + u64 pat; int switch_db_regs; unsigned long db[KVM_NR_DB_REGS]; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index fa5f71e021d5..e6833c655e59 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -32,11 +32,20 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ -#define MCACOD 0xffff /* MCA Error Code */ + +/* + * Note that the full MCACOD field of IA32_MCi_STATUS MSR is + * bits 15:0. But bit 12 is the 'F' bit, defined for corrected + * errors to indicate that errors are being filtered by hardware. + * We should mask out bit 12 when looking for specific signatures + * of uncorrected errors - so the F bit is deliberately skipped + * in this #define. + */ +#define MCACOD 0xefff /* MCA Error Code */ /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ #define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */ #define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ #define MCACOD_DATA 0x0134 /* Data Load */ #define MCACOD_INSTR 0x0150 /* Instruction Fetch */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index cdbf36776106..be12c534fd59 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); - /* stop flush ipis for the previous mm */ + /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); - /* - * load the LDT, if the LDT is different: - */ + /* Load the LDT, if the LDT is different: */ if (unlikely(prev->context.ldt != next->context.ldt)) load_LDT_nolock(&next->context); } #ifdef CONFIG_SMP - else { + else { this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) { - /* We were in lazy tlb mode and leave_mm disabled + 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. */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1e672234c4ff..5460bf923e16 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -415,9 +415,16 @@ static inline int pte_present(pte_t a) } #define pte_accessible pte_accessible -static inline int pte_accessible(pte_t a) +static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { - return pte_flags(a) & _PAGE_PRESENT; + if (pte_flags(a) & _PAGE_PRESENT) + return true; + + if ((pte_flags(a) & (_PAGE_PROTNONE | _PAGE_NUMA)) && + mm_tlb_flush_pending(mm)) + return true; + + return false; } static inline int pte_hidden(pte_t pte) diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 942a08623a1a..68e9f007cd4a 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -232,6 +232,22 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, #define ARCH_HAS_USER_SINGLE_STEP_INFO +/* + * When hitting ptrace_stop(), we cannot return using SYSRET because + * that does not restore the full CPU state, only a minimal set. The + * ptracer can change arbitrary register values, which is usually okay + * because the usual ptrace stops run off the signal delivery path which + * forces IRET; however, ptrace_event() stops happen in arbitrary places + * in the kernel and don't force IRET path. + * + * So force IRET path after a ptrace stop. + */ +#define arch_ptrace_stop_needed(code, info) \ +({ \ + set_thread_flag(TIF_NOTIFY_RESUME); \ + false; \ +}) + struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 33692eaabab5..e3ddd7db723f 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -233,8 +233,4 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() -/* The {read|write|spin}_lock() on x86 are full memory barriers. */ -static inline void smp_mb__after_lock(void) { } -#define ARCH_HAS_SMP_MB_AFTER_LOCK - #endif /* _ASM_X86_SPINLOCK_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 095b21507b6a..60bd2748a7c9 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -119,9 +119,10 @@ static inline void setup_node_to_cpumask_map(void) { } extern const struct cpumask *cpu_coregroup_mask(int cpu); -#ifdef ENABLE_TOPO_DEFINES #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) + +#ifdef ENABLE_TOPO_DEFINES #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 6aef9fbc09b7..b913915e8e63 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn) return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY; } -static inline unsigned long mfn_to_pfn(unsigned long mfn) +static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn) { unsigned long pfn; - int ret = 0; + int ret; if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely(mfn >= machine_to_phys_nr)) { - pfn = ~0; - goto try_override; - } - pfn = 0; + if (unlikely(mfn >= machine_to_phys_nr)) + return ~0; + /* * The array access can fail (e.g., device space beyond end of RAM). * In such cases it doesn't matter what we return (we return garbage), * but we must handle the fault without crashing! */ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); -try_override: - /* ret might be < 0 if there are no entries in the m2p for mfn */ if (ret < 0) - pfn = ~0; - else if (get_phys_to_machine(pfn) != mfn) + return ~0; + + return pfn; +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (xen_feature(XENFEAT_auto_translated_physmap)) + return mfn; + + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) != mfn) { /* * If this appears to be a foreign mfn (because the pfn * doesn't map back to the mfn), then check the local override @@ -111,6 +119,7 @@ try_override: * m2p_find_override_pfn returns ~0 if it doesn't find anything. */ pfn = m2p_find_override_pfn(mfn, ~0); + } /* * pfn is ~0 if there are no entries in the m2p for mfn or if the diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h index 7ea79c5fa1f2..492b29802f57 100644 --- a/arch/x86/include/asm/xor_avx.h +++ b/arch/x86/include/asm/xor_avx.h @@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = { #define AVX_XOR_SPEED \ do { \ - if (cpu_has_avx) \ + if (cpu_has_avx && cpu_has_osxsave) \ xor_speed(&xor_block_avx); \ } while (0) #define AVX_SELECT(FASTEST) \ - (cpu_has_avx ? &xor_block_avx : FASTEST) + (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST) #else diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 2af848dfa754..d3fd447ecbee 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -179,6 +179,7 @@ #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_BU_CFG2 0xc001102a #define MSR_AMD64_IBSFETCHCTL 0xc0011030 diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index b44577bc9744..ec94e11807dc 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -48,9 +48,20 @@ int acpi_suspend_lowlevel(void) #ifndef CONFIG_64BIT native_store_gdt((struct desc_ptr *)&header->pmode_gdt); + /* + * We have to check that we can write back the value, and not + * just read it. At least on 90 nm Pentium M (Family 6, Model + * 13), reading an invalid MSR is not guaranteed to trap, see + * Erratum X4 in "Intel Pentium M Processor on 90 nm Process + * with 2-MB L2 Cache and Intel® Processor A100 and A110 on 90 + * nm process with 512-KB L2 Cache Specification Update". + */ if (!rdmsr_safe(MSR_EFER, &header->pmode_efer_low, - &header->pmode_efer_high)) + &header->pmode_efer_high) && + !wrmsr_safe(MSR_EFER, + header->pmode_efer_low, + header->pmode_efer_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER); #endif /* !CONFIG_64BIT */ @@ -61,7 +72,10 @@ int acpi_suspend_lowlevel(void) } if (!rdmsr_safe(MSR_IA32_MISC_ENABLE, &header->pmode_misc_en_low, - &header->pmode_misc_en_high)) + &header->pmode_misc_en_high) && + !wrmsr_safe(MSR_IA32_MISC_ENABLE, + header->pmode_misc_en_low, + header->pmode_misc_en_high)) header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE); header->realmode_flags = acpi_realmode_flags; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3048ded1b598..59554dca96ec 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, {} }; @@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} }; @@ -81,13 +83,20 @@ int amd_cache_northbridges(void) next_northbridge(misc, amd_nb_misc_ids); node_to_amd_nb(i)->link = link = next_northbridge(link, amd_nb_link_ids); - } + } + /* GART present only on Fam15h upto model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - boot_cpu_data.x86 == 0x15) + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) amd_northbridges.flags |= AMD_NB_GART; /* + * Check for L3 cache presence. + */ + if (!cpuid_edx(0x80000006)) + return 0; + + /* * Some CPU families support L3 Cache Index Disable. There are some * limitations because of E382 and E388 on family 0x10. */ diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 794f6eb54cd3..b32dbb411a9a 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -98,7 +98,7 @@ static int __init early_get_pnodeid(void) break; case UV3_HUB_PART_NUMBER: case UV3_HUB_PART_NUMBER_X: - uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1; + uv_min_hub_revision_id += UV3_HUB_REVISION_BASE; break; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 5013a48d1aff..ae177a014180 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -508,6 +508,16 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_EXTD_APICID); } #endif + + /* F16h erratum 793, CVE-2013-6885 */ + if (c->x86 == 0x16 && c->x86_model <= 0xf) { + u64 val; + + rdmsrl(MSR_AMD64_LS_CFG, val); + if (!(val & BIT(15))) + wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15)); + } + } static const int amd_erratum_383[]; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 22018f70a671..deeb48d9459b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -284,8 +284,13 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c) raw_local_save_flags(eflags); BUG_ON(eflags & X86_EFLAGS_AC); - if (cpu_has(c, X86_FEATURE_SMAP)) + if (cpu_has(c, X86_FEATURE_SMAP)) { +#ifdef CONFIG_X86_SMAP set_in_cr4(X86_CR4_SMAP); +#else + clear_in_cr4(X86_CR4_SMAP); +#endif + } } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9b0c441c03f5..f187806dfc18 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -387,7 +387,8 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) + if (c->x86 == 6 && cpu_has_clflush && + (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); #ifdef CONFIG_X86_64 @@ -627,7 +628,7 @@ static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) tlb_flushall_shift = 5; break; case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 1; + tlb_flushall_shift = 2; break; default: tlb_flushall_shift = 6; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index fa72a39e5d46..3982357de5b0 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -510,8 +510,9 @@ generic_get_free_region(unsigned long base, unsigned long size, int replace_reg) static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { - unsigned int mask_lo, mask_hi, base_lo, base_hi; - unsigned int tmp, hi; + u32 mask_lo, mask_hi, base_lo, base_hi; + unsigned int hi; + u64 tmp, mask; /* * get_mtrr doesn't need to update mtrr_state, also it could be called @@ -532,18 +533,18 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask: */ - tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; - mask_lo = size_or_mask | tmp; + tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; + mask = size_or_mask | tmp; /* Expand tmp with high bits to all 1s: */ - hi = fls(tmp); + hi = fls64(tmp); if (hi > 0) { - tmp |= ~((1<<(hi - 1)) - 1); + tmp |= ~((1ULL<<(hi - 1)) - 1); - if (tmp != mask_lo) { + if (tmp != mask) { printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n"); add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); - mask_lo = tmp; + mask = tmp; } } @@ -551,8 +552,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, * This works correctly if size is a power of two, i.e. a * contiguous range: */ - *size = -mask_lo; - *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; + *size = -mask; + *base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; out_put_cpu: diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 726bf963c227..ca22b73aaa25 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -305,7 +305,8 @@ int mtrr_add_page(unsigned long base, unsigned long size, return -EINVAL; } - if (base & size_or_mask || size & size_or_mask) { + if ((base | (base + size - 1)) >> + (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) { pr_warning("mtrr: base or size exceeds the MTRR width\n"); return -EINVAL; } @@ -583,6 +584,7 @@ static struct syscore_ops mtrr_syscore_ops = { int __initdata changed_by_mtrr_cleanup; +#define SIZE_OR_MASK_BITS(n) (~((1ULL << ((n) - PAGE_SHIFT)) - 1)) /** * mtrr_bp_init - initialize mtrrs on the boot CPU * @@ -600,7 +602,7 @@ void __init mtrr_bp_init(void) if (cpu_has_mtrr) { mtrr_if = &generic_mtrr_ops; - size_or_mask = 0xff000000; /* 36 bits */ + size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; phys_addr = 36; @@ -619,7 +621,7 @@ void __init mtrr_bp_init(void) boot_cpu_data.x86_mask == 0x4)) phys_addr = 36; - size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1); + size_or_mask = SIZE_OR_MASK_BITS(phys_addr); size_and_mask = ~size_or_mask & 0xfffff00000ULL; } else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR && boot_cpu_data.x86 == 6) { @@ -627,7 +629,7 @@ void __init mtrr_bp_init(void) * VIA C* family have Intel style MTRRs, * but don't support PAE */ - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; phys_addr = 32; } @@ -637,21 +639,21 @@ void __init mtrr_bp_init(void) if (cpu_has_k6_mtrr) { /* Pre-Athlon (K6) AMD CPU MTRRs */ mtrr_if = mtrr_ops[X86_VENDOR_AMD]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CENTAUR: if (cpu_has_centaur_mcr) { mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: if (cpu_has_cyrix_arr) { mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; - size_or_mask = 0xfff00000; /* 32 bits */ + size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 1025f3c99d20..123d9e2271dc 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1165,6 +1165,9 @@ static void x86_pmu_del(struct perf_event *event, int flags) for (i = 0; i < cpuc->n_events; i++) { if (event == cpuc->event_list[i]) { + if (i >= cpuc->n_events - cpuc->n_added) + --cpuc->n_added; + if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, event); @@ -1249,10 +1252,20 @@ void perf_events_lapic_init(void) static int __kprobes perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { + int ret; + u64 start_clock; + u64 finish_clock; + if (!atomic_read(&active_events)) return NMI_DONE; - return x86_pmu.handle_irq(regs); + start_clock = local_clock(); + ret = x86_pmu.handle_irq(regs); + finish_clock = local_clock(); + + perf_sample_event_took(finish_clock - start_clock); + + return ret; } struct event_constraint emptyconstraint; diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 5f0581e713c2..b46601ada813 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -10,6 +10,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/ptrace.h> +#include <linux/syscore_ops.h> #include <asm/apic.h> @@ -816,6 +817,18 @@ out: return ret; } +static void ibs_eilvt_setup(void) +{ + /* + * Force LVT offset assignment for family 10h: The offsets are + * not assigned by the BIOS for this family, so the OS is + * responsible for doing it. If the OS assignment fails, fall + * back to BIOS settings and try to setup this. + */ + if (boot_cpu_data.x86 == 0x10) + force_ibs_eilvt_setup(); +} + static inline int get_ibs_lvt_offset(void) { u64 val; @@ -851,6 +864,36 @@ static void clear_APIC_ibs(void *dummy) setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1); } +#ifdef CONFIG_PM + +static int perf_ibs_suspend(void) +{ + clear_APIC_ibs(NULL); + return 0; +} + +static void perf_ibs_resume(void) +{ + ibs_eilvt_setup(); + setup_APIC_ibs(NULL); +} + +static struct syscore_ops perf_ibs_syscore_ops = { + .resume = perf_ibs_resume, + .suspend = perf_ibs_suspend, +}; + +static void perf_ibs_pm_init(void) +{ + register_syscore_ops(&perf_ibs_syscore_ops); +} + +#else + +static inline void perf_ibs_pm_init(void) { } + +#endif + static int __cpuinit perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -877,18 +920,12 @@ static __init int amd_ibs_init(void) if (!caps) return -ENODEV; /* ibs not supported by the cpu */ - /* - * Force LVT offset assignment for family 10h: The offsets are - * not assigned by the BIOS for this family, so the OS is - * responsible for doing it. If the OS assignment fails, fall - * back to BIOS settings and try to setup this. - */ - if (boot_cpu_data.x86 == 0x10) - force_ibs_eilvt_setup(); + ibs_eilvt_setup(); if (!ibs_eilvt_valid()) goto out; + perf_ibs_pm_init(); get_online_cpus(); ibs_caps = caps; /* make ibs_caps visible to other cpus: */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 52441a2af538..8aac56bda7dc 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = { static struct uncore_event_desc snbep_uncore_qpi_events[] = { INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"), INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"), - INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x02,umask=0x08"), - INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x03,umask=0x04"), + INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"), + INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"), { /* end: all zeroes */ }, }; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abeabbda5..174da5fc5a7b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -658,15 +658,18 @@ __init void e820_setup_gap(void) * boot_params.e820_map, others are passed via SETUP_E820_EXT node of * linked list of struct setup_data, which is parsed here. */ -void __init parse_e820_ext(struct setup_data *sdata) +void __init parse_e820_ext(u64 phys_addr, u32 data_len) { int entries; struct e820entry *extmap; + struct setup_data *sdata; + sdata = early_memremap(phys_addr, data_len); entries = sdata->len / sizeof(struct e820entry); extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + early_iounmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); } diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 94ab6b90dd3f..4f7c82cdd0f5 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -196,16 +196,21 @@ static void __init ati_bugs_contd(int num, int slot, int func) static void __init intel_remapping_check(int num, int slot, int func) { u8 revision; + u16 device; + device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID); revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID); /* - * Revision 0x13 of this chipset supports irq remapping - * but has an erratum that breaks its behavior, flag it as such + * Revision <= 13 of all triggering devices id in this quirk + * have a problem draining interrupts when irq remapping is + * enabled, and should be flagged as broken. Additionally + * revision 0x22 of device id 0x3405 has this problem. */ - if (revision == 0x13) + if (revision <= 0x13) + set_irq_remapping_broken(); + else if (device == 0x3405 && revision == 0x22) set_irq_remapping_broken(); - } #define QFLAG_APPLY_ONCE 0x1 @@ -239,6 +244,8 @@ static struct chipset early_qrk[] __initdata = { PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd }, { PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, + { PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST, + PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST, PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check }, {} diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 8f3e2dec1df3..ac6328176097 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -434,9 +434,10 @@ sysenter_past_esp: jnz sysenter_audit sysenter_do_call: cmpl $(NR_syscalls), %eax - jae syscall_badsys + jae sysenter_badsys call *sys_call_table(,%eax,4) movl %eax,PT_EAX(%esp) +sysenter_after_call: LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF @@ -554,11 +555,6 @@ ENTRY(iret_exc) CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -691,7 +687,12 @@ END(syscall_fault) syscall_badsys: movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + jmp syscall_exit +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,PT_EAX(%esp) + jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC /* @@ -1075,7 +1076,7 @@ ENTRY(ftrace_caller) pushl $0 /* Pass NULL as regs pointer */ movl 4*4(%esp), %eax movl 0x4(%ebp), %edx - leal function_trace_op, %ecx + movl function_trace_op, %ecx subl $MCOUNT_INSN_SIZE, %eax .globl ftrace_call @@ -1133,7 +1134,7 @@ ENTRY(ftrace_regs_caller) movl 12*4(%esp), %eax /* Load ip (1st parameter) */ subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ - leal function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ pushl %esp /* Save pt_regs as 4th parameter */ GLOBAL(ftrace_regs_call) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 727208941030..7ac938a4bfab 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -88,7 +88,7 @@ END(function_hook) MCOUNT_SAVE_FRAME \skip /* Load the ftrace_ops into the 3rd parameter */ - leaq function_trace_op, %rdx + movq function_trace_op(%rip), %rdx /* Load ip into the first parameter */ movq RIP(%rsp), %rdi diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 42a392a9fd02..1ffc32dbe450 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -77,8 +77,7 @@ within(unsigned long addr, unsigned long start, unsigned long end) return addr >= start && addr < end; } -static int -do_ftrace_mod_code(unsigned long ip, const void *new_code) +static unsigned long text_ip_addr(unsigned long ip) { /* * On x86_64, kernel text mappings are mapped read-only with @@ -91,7 +90,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code) if (within(ip, (unsigned long)_text, (unsigned long)_etext)) ip = (unsigned long)__va(__pa_symbol(ip)); - return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE); + return ip; } static const unsigned char *ftrace_nop_replace(void) @@ -123,8 +122,10 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) return -EINVAL; + ip = text_ip_addr(ip); + /* replace the text with the new text */ - if (do_ftrace_mod_code(ip, new_code)) + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) return -EPERM; sync_core(); @@ -221,33 +222,56 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, return -EINVAL; } -int ftrace_update_ftrace_func(ftrace_func_t func) +static unsigned long ftrace_update_func; + +static int update_ftrace_func(unsigned long ip, void *new) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char old[MCOUNT_INSN_SIZE], *new; + unsigned char old[MCOUNT_INSN_SIZE]; int ret; - memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, (unsigned long)func); + memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); + + ftrace_update_func = ip; + /* Make sure the breakpoints see the ftrace_update_func update */ + smp_wmb(); /* See comment above by declaration of modifying_ftrace_code */ atomic_inc(&modifying_ftrace_code); ret = ftrace_modify_code(ip, old, new); + atomic_dec(&modifying_ftrace_code); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long ip = (unsigned long)(&ftrace_call); + unsigned char *new; + int ret; + + new = ftrace_call_replace(ip, (unsigned long)func); + ret = update_ftrace_func(ip, new); + /* Also update the regs callback function */ if (!ret) { ip = (unsigned long)(&ftrace_regs_call); - memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE); new = ftrace_call_replace(ip, (unsigned long)func); - ret = ftrace_modify_code(ip, old, new); + ret = update_ftrace_func(ip, new); } - atomic_dec(&modifying_ftrace_code); - return ret; } +static int is_ftrace_caller(unsigned long ip) +{ + if (ip == ftrace_update_func) + return 1; + + return 0; +} + /* * A breakpoint was added to the code address we are about to * modify, and this is the handle that will just skip over it. @@ -257,10 +281,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) */ int ftrace_int3_handler(struct pt_regs *regs) { + unsigned long ip; + if (WARN_ON_ONCE(!regs)) return 0; - if (!ftrace_location(regs->ip - 1)) + ip = regs->ip - 1; + if (!ftrace_location(ip) && !is_ftrace_caller(ip)) return 0; regs->ip += MCOUNT_INSN_SIZE - 1; @@ -632,8 +659,8 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code, ret = -EPERM; goto out; } - run_sync(); out: + run_sync(); return ret; fail_update: @@ -665,45 +692,41 @@ int __init ftrace_dyn_arch_init(void *data) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static int ftrace_mod_jmp(unsigned long ip, - int old_offset, int new_offset) +static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - unsigned char code[MCOUNT_INSN_SIZE]; + static union ftrace_code_union calc; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; + /* Jmp not a call (ignore the .e8) */ + calc.e8 = 0xe9; + calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - if (code[0] != 0xe9 || old_offset != *(int *)(&code[1])) - return -EINVAL; + /* + * ftrace external locks synchronize the access to the static variable. + */ + return calc.code; +} - *(int *)(&code[1]) = new_offset; +static int ftrace_mod_jmp(unsigned long ip, void *func) +{ + unsigned char *new; - if (do_ftrace_mod_code(ip, &code)) - return -EPERM; + new = ftrace_jmp_replace(ip, (unsigned long)func); - return 0; + return update_ftrace_func(ip, new); } int ftrace_enable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_graph_caller); } int ftrace_disable_ftrace_graph_caller(void) { unsigned long ip = (unsigned long)(&ftrace_graph_call); - int old_offset, new_offset; - - old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE); - new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE); - return ftrace_mod_jmp(ip, old_offset, new_offset); + return ftrace_mod_jmp(ip, &ftrace_stub); } #endif /* !CONFIG_DYNAMIC_FTRACE */ diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 73afd11799ca..df63cae573e0 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -566,6 +566,10 @@ ENDPROC(early_idt_handlers) /* This is global to keep gas from relaxing the jumps */ ENTRY(early_idt_handler) cld + + cmpl $2,(%esp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,%ss:early_recursion_flag je hlt_loop incl %ss:early_recursion_flag @@ -616,8 +620,9 @@ ex_entry: pop %edx pop %ecx pop %eax - addl $8,%esp /* drop vector number and error code */ decl %ss:early_recursion_flag +is_nmi: + addl $8,%esp /* drop vector number and error code */ iret ENDPROC(early_idt_handler) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 321d65ebaffe..f2a9a2aa98f3 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -343,6 +343,9 @@ early_idt_handlers: ENTRY(early_idt_handler) cld + cmpl $2,(%rsp) # X86_TRAP_NMI + je is_nmi # Ignore NMI + cmpl $2,early_recursion_flag(%rip) jz 1f incl early_recursion_flag(%rip) @@ -405,8 +408,9 @@ ENTRY(early_idt_handler) popq %rdx popq %rcx popq %rax - addq $16,%rsp # drop vector number and error code decl early_recursion_flag(%rip) +is_nmi: + addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler) @@ -513,7 +517,7 @@ ENTRY(phys_base) #include "../../x86/xen/xen-head.S" .section .bss, "aw", @nobits - .align L1_CACHE_BYTES + .align PAGE_SIZE ENTRY(idt_table) .skip IDT_ENTRIES * 16 diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index cb339097b9ea..b03ff1842547 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin); void __kernel_fpu_end(void) { - if (use_eager_fpu()) - math_state_restore(); - else + if (use_eager_fpu()) { + /* + * For eager fpu, most the time, tsk_used_math() is true. + * Restore the user math as we are done with the kernel usage. + * At few instances during thread exit, signal handling etc, + * tsk_used_math() is false. Those few places will take proper + * actions, so we don't need to restore the math here. + */ + if (likely(tsk_used_math(current))) + math_state_restore(); + } else { stts(); + } } EXPORT_SYMBOL(__kernel_fpu_end); @@ -116,7 +125,7 @@ static void __cpuinit mxcsr_feature_mask_init(void) if (cpu_has_fxsr) { memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct)); - asm volatile("fxsave %0" : : "m" (fx_scratch)); + asm volatile("fxsave %0" : "+m" (fx_scratch)); mask = fx_scratch.mxcsr_mask; if (mask == 0) mask = 0x0000ffbf; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ebc987398923..dcbbaa165bde 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -20,6 +20,8 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> +int sysctl_ldt16 = 0; + #ifdef CONFIG_SMP static void flush_ldt(void *current_mm) { @@ -229,6 +231,17 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } + /* + * On x86-64 we do not support 16-bit segments due to + * IRET leaking the high bits of the kernel stack address. + */ +#ifdef CONFIG_X86_64 + if (!ldt_info.seg_32bit && !sysctl_ldt16) { + error = -EINVAL; + goto out_unlock; + } +#endif + fill_ldt(&ldt, &ldt_info); if (oldmode) ldt.avl = 0; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index efdec7cd8e01..b516dfb411ec 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -430,7 +430,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); if (request_firmware(&fw, (const char *)fw_name, device)) { - pr_err("failed to load file %s\n", fw_name); + pr_debug("failed to load file %s\n", fw_name); goto out; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 872079a67e4d..f7d0672481fd 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -100,8 +100,10 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, flag |= __GFP_ZERO; again: page = NULL; - if (!(flag & GFP_ATOMIC)) + /* CMA can be used only in the context which permits sleeping */ + if (flag & __GFP_WAIT) page = dma_alloc_from_contiguous(dev, count, get_order(size)); + /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 81a5f5e8f142..59b90379cb6a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -391,9 +391,9 @@ static void amd_e400_idle(void) * The switch back from broadcast mode needs to be * called with interrupts disabled. */ - local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); - local_irq_enable(); + local_irq_disable(); + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + local_irq_enable(); } else default_idle(); } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 04ee1e2e4c02..52dbf1e400dc 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev) return; pci_read_config_dword(nb_ht, 0x60, &val); - node = val & 7; + node = pcibus_to_node(dev->bus) | (val & 7); /* * Some hardware may return an invalid node ID, * so check it first: diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 76fa1e9a2b39..90fd1195f276 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -447,6 +447,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"), }, }, + { /* Handle problems with rebooting on the Dell PowerEdge C6100. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, + { /* Some C6100 machines were shipped with vendor being 'Dell'. */ + .callback = set_pci_reboot, + .ident = "Dell PowerEdge C6100", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "C6100"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 56f7fcfe7fa2..a3627ade4b15 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -426,25 +426,23 @@ static void __init reserve_initrd(void) static void __init parse_setup_data(void) { struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; pa_data = boot_params.hdr.setup_data; while (pa_data) { - u32 data_len, map_len; + u32 data_len, map_len, data_type; map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), (u64)sizeof(struct setup_data)); data = early_memremap(pa_data, map_len); data_len = data->len + sizeof(struct setup_data); - if (data_len > map_len) { - early_iounmap(data, map_len); - data = early_memremap(pa_data, data_len); - map_len = data_len; - } + data_type = data->type; + pa_next = data->next; + early_iounmap(data, map_len); - switch (data->type) { + switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(data); + parse_e820_ext(pa_data, data_len); break; case SETUP_DTB: add_dtb(pa_data); @@ -452,8 +450,7 @@ static void __init parse_setup_data(void) default: break; } - pa_data = data->next; - early_iounmap(data, map_len); + pa_data = pa_next; } } @@ -911,11 +908,11 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_EFI if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL32", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature, "EL64", 4)) { - set_bit(EFI_BOOT, &x86_efi_facility); - set_bit(EFI_64BIT, &x86_efi_facility); + set_bit(EFI_BOOT, &efi.flags); + set_bit(EFI_64BIT, &efi.flags); } if (efi_enabled(EFI_BOOT)) diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 69562992e457..087ab2af381a 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -364,7 +364,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -429,7 +429,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -496,7 +496,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ksig->ka.sa.sa_flags & SA_RESTORER) { diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index dbded5aedb81..30277e27431a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = TASK_UNMAPPED_BASE; + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5953dcea752d..5484d54582ca 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4207,7 +4207,10 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, case OpMem8: ctxt->memop.bytes = 1; if (ctxt->memop.type == OP_REG) { - ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1); + int highbyte_regs = ctxt->rex_prefix == 0; + + ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, + highbyte_regs); fetch_register_operand(&ctxt->memop); } goto mem_common; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 412a5aa0ef94..518d86471b76 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -37,6 +37,7 @@ #include "irq.h" #include "i8254.h" +#include "x86.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -349,6 +350,23 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) atomic_set(&ps->pending, 0); ps->irq_ack = 1; + /* + * Do not allow the guest to program periodic timers with small + * interval, since the hrtimers are not throttled by the host + * scheduler. + */ + if (ps->is_periodic) { + s64 min_period = min_timer_period_us * 1000LL; + + if (ps->period < min_period) { + pr_info_ratelimited( + "kvm: requested %lld ns " + "i8254 timer period limited to %lld ns\n", + ps->period, min_period); + ps->period = min_period; + } + } + hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval), HRTIMER_MODE_ABS); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0eee2c8b64d1..279d093524b4 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -71,9 +71,6 @@ #define VEC_POS(v) ((v) & (32 - 1)) #define REG_POS(v) (((v) >> 5) << 4) -static unsigned int min_timer_period_us = 500; -module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); - static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) { *((u32 *) (apic->regs + reg_off)) = val; @@ -153,6 +150,8 @@ static inline int kvm_apic_id(struct kvm_lapic *apic) return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } +#define KVM_X2APIC_CID_BITS 0 + static void recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -190,7 +189,8 @@ static void recalculate_apic_map(struct kvm *kvm) if (apic_x2apic_mode(apic)) { new->ldr_bits = 32; new->cid_shift = 16; - new->cid_mask = new->lid_mask = 0xffff; + new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1; + new->lid_mask = 0xffff; } else if (kvm_apic_sw_enabled(apic) && !new->cid_mask /* flat mode */ && kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) { @@ -370,6 +370,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { + /* Note that we never get here with APIC virtualization enabled. */ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -381,12 +383,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) apic->highest_isr_cache = vec; } +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + + /* + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. + */ + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; +} + static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * We do get here for APIC virtualization enabled if the guest + * uses the Hyper-V APIC enlightenment. In this case we may need + * to trigger a new interrupt delivery by writing the SVI field; + * on the other hand isr_count and highest_isr_cache are unused + * and must be left alone. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); + else { --apic->isr_count; - BUG_ON(apic->isr_count < 0); - apic->highest_isr_cache = -1; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; + } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) @@ -466,22 +504,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - /* Note that isr_count is always 1 with vid enabled */ - if (!apic->isr_count) - return -1; - if (likely(apic->highest_isr_cache != -1)) - return apic->highest_isr_cache; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -855,7 +877,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic) ASSERT(apic != NULL); /* if initial count is 0, current count should also be 0 */ - if (kvm_apic_get_reg(apic, APIC_TMICT) == 0) + if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 || + apic->lapic_timer.period == 0) return 0; remaining = hrtimer_get_remaining(&apic->lapic_timer.timer); @@ -1360,8 +1383,12 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) return; } + if (!kvm_vcpu_is_bsp(apic->vcpu)) + value &= ~MSR_IA32_APICBASE_BSP; + vcpu->arch.apic_base = value; + /* update jump label if enable bit changes */ - if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) { + if ((old_value ^ value) & MSR_IA32_APICBASE_ENABLE) { if (value & MSR_IA32_APICBASE_ENABLE) static_key_slow_dec_deferred(&apic_hw_disabled); else @@ -1369,10 +1396,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) recalculate_apic_map(vcpu->kvm); } - if (!kvm_vcpu_is_bsp(apic->vcpu)) - value &= ~MSR_IA32_APICBASE_BSP; - - vcpu->arch.apic_base = value; if ((old_value ^ value) & X2APIC_ENABLE) { if (value & X2APIC_ENABLE) { u32 id = kvm_apic_id(apic); @@ -1618,6 +1641,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + /* Note that we never get here with APIC virtualization enabled. */ + if (vector == -1) return -1; @@ -1705,7 +1730,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu, void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) { u32 data; - void *vapic; if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention)) apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic); @@ -1713,9 +1737,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention)) return; - vapic = kmap_atomic(vcpu->arch.apic->vapic_page); - data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)); - kunmap_atomic(vapic); + kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32)); apic_set_tpr(vcpu->arch.apic, data & 0xff); } @@ -1751,7 +1774,6 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) u32 data, tpr; int max_irr, max_isr; struct kvm_lapic *apic = vcpu->arch.apic; - void *vapic; apic_sync_pv_eoi_to_guest(vcpu, apic); @@ -1767,18 +1789,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu) max_isr = 0; data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24); - vapic = kmap_atomic(vcpu->arch.apic->vapic_page); - *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data; - kunmap_atomic(vapic); + kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data, + sizeof(u32)); } -void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) +int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) { - vcpu->arch.apic->vapic_addr = vapic_addr; - if (vapic_addr) + if (vapic_addr) { + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, + &vcpu->arch.apic->vapic_cache, + vapic_addr, sizeof(u32))) + return -EINVAL; __set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention); - else + } else { __clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention); + } + + vcpu->arch.apic->vapic_addr = vapic_addr; + return 0; } int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index c730ac9fe801..c8b0d0d2da5c 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -34,7 +34,7 @@ struct kvm_lapic { */ void *regs; gpa_t vapic_addr; - struct page *vapic_page; + struct gfn_to_hva_cache vapic_cache; unsigned long pending_events; unsigned int sipi_vector; }; @@ -76,7 +76,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset); void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector); -void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); +int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr); void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu); void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 004cc87b781c..711c649f80b7 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2585,6 +2585,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, int emulate = 0; gfn_t pseudo_gfn; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return 0; + for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { if (iterator.level == level) { mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, @@ -2748,6 +2751,9 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, bool ret = false; u64 spte = 0ull; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return false; + if (!page_fault_can_be_fast(vcpu, error_code)) return false; @@ -3139,6 +3145,9 @@ static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr) struct kvm_shadow_walk_iterator iterator; u64 spte = 0ull; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return spte; + walk_shadow_page_lockless_begin(vcpu); for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) if (!is_shadow_present_pte(spte)) @@ -4329,6 +4338,9 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) u64 spte; int nr_sptes = 0; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + return nr_sptes; + walk_shadow_page_lockless_begin(vcpu); for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) { sptes[iterator.level-1] = spte; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index da20860b457a..7e6090e13237 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -423,6 +423,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (FNAME(gpte_changed)(vcpu, gw, top_level)) goto out_gpte_changed; + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + goto out_gpte_changed; + for (shadow_walk_init(&it, vcpu, addr); shadow_walk_okay(&it) && it.level > gw->level; shadow_walk_next(&it)) { @@ -671,6 +674,11 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) */ mmu_topup_memory_caches(vcpu); + if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) { + WARN_ON(1); + return; + } + spin_lock(&vcpu->kvm->mmu_lock); for_each_shadow_entry(vcpu, gva, iterator) { level = iterator.level; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a14a6eaf871d..765210d4d925 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -2985,10 +2985,8 @@ static int cr8_write_interception(struct vcpu_svm *svm) u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ r = cr_interception(svm); - if (irqchip_in_kernel(svm->vcpu.kvm)) { - clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); + if (irqchip_in_kernel(svm->vcpu.kvm)) return r; - } if (cr8_prev <= kvm_get_cr8(&svm->vcpu)) return r; kvm_run->exit_reason = KVM_EXIT_SET_TPR; @@ -3550,6 +3548,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK)) return; + clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); + if (irr == -1) return; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 260a91939555..7cdafb6dc705 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3399,15 +3399,22 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->limit = vmx_read_guest_seg_limit(vmx, seg); var->selector = vmx_read_guest_seg_selector(vmx, seg); ar = vmx_read_guest_seg_ar(vmx, seg); + var->unusable = (ar >> 16) & 1; var->type = ar & 15; var->s = (ar >> 4) & 1; var->dpl = (ar >> 5) & 3; - var->present = (ar >> 7) & 1; + /* + * Some userspaces do not preserve unusable property. Since usable + * segment has to be present according to VMX spec we can use present + * property to amend userspace bug by making unusable segment always + * nonpresent. vmx_segment_access_rights() already marks nonpresent + * segment as unusable. + */ + var->present = !var->unusable; var->avl = (ar >> 12) & 1; var->l = (ar >> 13) & 1; var->db = (ar >> 14) & 1; var->g = (ar >> 15) & 1; - var->unusable = (ar >> 16) & 1; } static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) @@ -7126,8 +7133,8 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); free_vpid(vmx); - free_nested(vmx); free_loaded_vmcs(vmx->loaded_vmcs); + free_nested(vmx); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e8ba99c34180..1be0a9e75d1f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -94,6 +94,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); static bool ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); +unsigned int min_timer_period_us = 500; +module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); + bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); u32 kvm_max_guest_tsc_khz; @@ -3138,8 +3141,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) goto out; - r = 0; - kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); break; } case KVM_X86_SETUP_MCE: { @@ -5539,36 +5541,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) !kvm_event_needs_reinjection(vcpu); } -static int vapic_enter(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - struct page *page; - - if (!apic || !apic->vapic_addr) - return 0; - - page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - if (is_error_page(page)) - return -EFAULT; - - vcpu->arch.apic->vapic_page = page; - return 0; -} - -static void vapic_exit(struct kvm_vcpu *vcpu) -{ - struct kvm_lapic *apic = vcpu->arch.apic; - int idx; - - if (!apic || !apic->vapic_addr) - return; - - idx = srcu_read_lock(&vcpu->kvm->srcu); - kvm_release_page_dirty(apic->vapic_page); - mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - srcu_read_unlock(&vcpu->kvm->srcu, idx); -} - static void update_cr8_intercept(struct kvm_vcpu *vcpu) { int max_irr, tpr; @@ -5889,11 +5861,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - r = vapic_enter(vcpu); - if (r) { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; - } r = 1; while (r > 0) { @@ -5951,8 +5918,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - vapic_exit(vcpu); - return r; } @@ -6017,7 +5982,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) frag->len -= len; } - if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) { + if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; if (vcpu->mmio_is_write) return 1; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index e224f7a671b6..3186542f2fa3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -124,5 +124,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, extern u64 host_xcr0; +extern unsigned int min_timer_period_us; + extern struct static_key kvm_no_apic_vcpu; #endif diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 25b7ae8d058a..7609e0e421ec 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -6,6 +6,7 @@ */ #include <asm/checksum.h> #include <linux/module.h> +#include <asm/smap.h> /** * csum_partial_copy_from_user - Copy and checksum from user space. @@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst, len -= 2; } } + stac(); isum = csum_partial_copy_generic((__force const void *)src, dst, len, isum, errp, NULL); + clac(); if (unlikely(*errp)) goto out_err; @@ -82,6 +85,8 @@ __wsum csum_partial_copy_to_user(const void *src, void __user *dst, int len, __wsum isum, int *errp) { + __wsum ret; + might_sleep(); if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) { @@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst, } *errp = 0; - return csum_partial_copy_generic(src, (void __force *)dst, - len, isum, NULL, errp); + stac(); + ret = csum_partial_copy_generic(src, (void __force *)dst, + len, isum, NULL, errp); + clac(); + return ret; } EXPORT_SYMBOL(csum_partial_copy_to_user); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 654be4ae3047..c1e9e4cbbd76 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -989,6 +989,12 @@ static int fault_in_kernel_space(unsigned long address) static inline bool smap_violation(int error_code, struct pt_regs *regs) { + if (!IS_ENABLED(CONFIG_X86_SMAP)) + return false; + + if (!static_cpu_has(X86_FEATURE_SMAP)) + return false; + if (error_code & PF_USER) return false; @@ -1091,11 +1097,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(error_code & PF_RSVD)) pgtable_bad(regs, error_code, address); - if (static_cpu_has(X86_FEATURE_SMAP)) { - if (unlikely(smap_violation(error_code, regs))) { - bad_area_nosemaphore(regs, error_code, address); - return; - } + if (unlikely(smap_violation(error_code, regs))) { + bad_area_nosemaphore(regs, error_code, address); + return; } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 1f34e9219775..7a5bf1b76e2f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -78,8 +78,8 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (5 * PAGE_SIZE) +/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ +#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 9a1e6583910c..86c758de4b34 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } +static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, + void *arg) +{ + unsigned long i; + + for (i = 0; i < nr_pages; ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return 1; + + WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); + + return 0; +} + /* * Remap an arbitrary physical address space into the kernel virtual * address space. Needed when the kernel wants to access high addresses @@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ + pfn = phys_addr >> PAGE_SHIFT; last_pfn = last_addr >> PAGE_SHIFT; - for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { - int is_ram = page_is_ram(pfn); - - if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) - return NULL; - WARN_ON_ONCE(is_ram); - } + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) + return NULL; /* * Mappings have to be page-aligned diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 845df6835f9f..5c1ae28825cd 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -112,12 +112,14 @@ static unsigned long mmap_legacy_base(void) */ void arch_pick_mmap_layout(struct mm_struct *mm) { + mm->mmap_legacy_base = mmap_legacy_base(); + mm->mmap_base = mmap_base(); + if (mmap_is_legacy()) { - mm->mmap_base = mmap_legacy_base(); + mm->mmap_base = mm->mmap_legacy_base; mm->get_unmapped_area = arch_get_unmapped_area; mm->unmap_area = arch_unmap_area; } else { - mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; mm->unmap_area = arch_unmap_area_topdown; } diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index 877b9a1b2152..01495755701b 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -140,7 +140,7 @@ bpf_slow_path_byte_msh: push %r9; \ push SKBDATA; \ /* rsi already has offset */ \ - mov $SIZE,%ecx; /* size */ \ + mov $SIZE,%edx; /* size */ \ call bpf_internal_load_pointer_neg_helper; \ test %rax,%rax; \ pop SKBDATA; \ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f66b54086ce5..0c966fecfb8c 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -324,15 +324,21 @@ void bpf_jit_compile(struct sk_filter *fp) EMIT2(0x89, 0xd0); /* mov %edx,%eax */ break; case BPF_S_ALU_MOD_K: /* A %= K; */ + if (K == 1) { + CLEAR_A(); + break; + } EMIT2(0x31, 0xd2); /* xor %edx,%edx */ EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ EMIT2(0xf7, 0xf1); /* div %ecx */ EMIT2(0x89, 0xd0); /* mov %edx,%eax */ break; - case BPF_S_ALU_DIV_K: /* A = reciprocal_divide(A, K); */ - EMIT3(0x48, 0x69, 0xc0); /* imul imm32,%rax,%rax */ - EMIT(K, 4); - EMIT4(0x48, 0xc1, 0xe8, 0x20); /* shr $0x20,%rax */ + case BPF_S_ALU_DIV_K: /* A /= K */ + if (K == 1) + break; + EMIT2(0x31, 0xd2); /* xor %edx,%edx */ + EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ + EMIT2(0xf7, 0xf1); /* div %ecx */ break; case BPF_S_ALU_AND_X: seen |= SEEN_XREG; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index d2fbcedcf6ea..816e940b3998 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -60,34 +60,19 @@ static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 }; -struct efi __read_mostly efi = { - .mps = EFI_INVALID_TABLE_ADDR, - .acpi = EFI_INVALID_TABLE_ADDR, - .acpi20 = EFI_INVALID_TABLE_ADDR, - .smbios = 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, -}; -EXPORT_SYMBOL(efi); - struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; -unsigned long x86_efi_facility; +static __initdata efi_config_table_type_t arch_tables[] = { +#ifdef CONFIG_X86_UV + {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab}, +#endif + {NULL_GUID, NULL, 0}, +}; -/* - * Returns 1 if 'facility' is enabled, 0 otherwise. - */ -int efi_enabled(int facility) -{ - return test_bit(facility, &x86_efi_facility) != 0; -} -EXPORT_SYMBOL(efi_enabled); +u64 efi_setup; /* efi setup_data physical address */ static bool __initdata disable_runtime = false; static int __init setup_noefi(char *arg) @@ -397,6 +382,8 @@ int __init efi_memblock_x86_reserve_range(void) memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); + efi.memmap = &memmap; + return 0; } @@ -438,7 +425,7 @@ void __init efi_reserve_boot_services(void) * - Not within any part of the kernel * - Not the bios reserved area */ - if ((start+size >= __pa_symbol(_text) + if ((start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) || !e820_all_mapped(start, start+size, E820_RAM) || memblock_is_region_reserved(start, size)) { @@ -454,7 +441,7 @@ void __init efi_reserve_boot_services(void) void __init efi_unmap_memmap(void) { - clear_bit(EFI_MEMMAP, &x86_efi_facility); + clear_bit(EFI_MEMMAP, &efi.flags); if (memmap.map) { early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; @@ -576,80 +563,6 @@ static int __init efi_systab_init(void *phys) return 0; } -static int __init efi_config_init(u64 tables, int nr_tables) -{ - void *config_tables, *tablep; - int i, sz; - - if (efi_enabled(EFI_64BIT)) - sz = sizeof(efi_config_table_64_t); - else - sz = sizeof(efi_config_table_32_t); - - /* - * Let's see what config tables the firmware passed to us. - */ - config_tables = early_ioremap(tables, nr_tables * sz); - if (config_tables == NULL) { - pr_err("Could not map Configuration table!\n"); - return -ENOMEM; - } - - tablep = config_tables; - pr_info(""); - for (i = 0; i < efi.systab->nr_tables; i++) { - efi_guid_t guid; - unsigned long table; - - if (efi_enabled(EFI_64BIT)) { - u64 table64; - guid = ((efi_config_table_64_t *)tablep)->guid; - table64 = ((efi_config_table_64_t *)tablep)->table; - table = table64; -#ifdef CONFIG_X86_32 - if (table64 >> 32) { - pr_cont("\n"); - pr_err("Table located above 4GB, disabling EFI.\n"); - early_iounmap(config_tables, - efi.systab->nr_tables * sz); - return -EINVAL; - } -#endif - } else { - guid = ((efi_config_table_32_t *)tablep)->guid; - table = ((efi_config_table_32_t *)tablep)->table; - } - if (!efi_guidcmp(guid, MPS_TABLE_GUID)) { - efi.mps = table; - pr_cont(" MPS=0x%lx ", table); - } else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) { - efi.acpi20 = table; - pr_cont(" ACPI 2.0=0x%lx ", table); - } else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) { - efi.acpi = table; - pr_cont(" ACPI=0x%lx ", table); - } else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) { - efi.smbios = table; - pr_cont(" SMBIOS=0x%lx ", table); -#ifdef CONFIG_X86_UV - } else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) { - efi.uv_systab = table; - pr_cont(" UVsystab=0x%lx ", table); -#endif - } else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) { - efi.hcdp = table; - pr_cont(" HCDP=0x%lx ", table); - } else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) { - efi.uga = table; - pr_cont(" UGA=0x%lx ", table); - } - tablep += sz; - } - pr_cont("\n"); - early_iounmap(config_tables, efi.systab->nr_tables * sz); - return 0; -} - static int __init efi_runtime_init(void) { efi_runtime_services_t *runtime; @@ -725,7 +638,11 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + + efi.config_table = (unsigned long)efi.systab->tables; + efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; + efi.runtime = (unsigned long)efi.systab->runtime; /* * Show what we know for posterity @@ -743,10 +660,10 @@ void __init efi_init(void) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff, vendor); - if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) + if (efi_config_init(arch_tables)) return; - set_bit(EFI_CONFIG_TABLES, &x86_efi_facility); + set_bit(EFI_CONFIG_TABLES, &efi.flags); /* * Note: We currently don't support runtime services on an EFI @@ -758,20 +675,13 @@ void __init efi_init(void) else { if (disable_runtime || efi_runtime_init()) return; - set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); } if (efi_memmap_init()) return; - set_bit(EFI_MEMMAP, &x86_efi_facility); - -#ifdef CONFIG_X86_32 - if (efi_is_native()) { - x86_platform.get_wallclock = efi_get_time; - x86_platform.set_wallclock = efi_set_rtc_mmss; - } -#endif + set_bit(EFI_MEMMAP, &efi.flags); #if EFI_DEBUG print_efi_memmap(); @@ -814,34 +724,6 @@ static void __init runtime_code_page_mkexec(void) } } -/* - * We can't ioremap data in EFI boot services RAM, because we've already mapped - * it as RAM. So, look it up in the existing EFI memory map instead. Only - * callable after efi_enter_virtual_mode and before efi_free_boot_services. - */ -void __iomem *efi_lookup_mapped_addr(u64 phys_addr) -{ - void *p; - if (WARN_ON(!memmap.map)) - return NULL; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - efi_memory_desc_t *md = p; - u64 size = md->num_pages << EFI_PAGE_SHIFT; - u64 end = md->phys_addr + size; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; - if (!md->virt_addr) - continue; - if (phys_addr >= md->phys_addr && phys_addr < end) { - phys_addr += md->virt_addr - md->phys_addr; - return (__force void __iomem *)(unsigned long)phys_addr; - } - } - return NULL; -} - void efi_memory_uc(u64 addr, unsigned long size) { unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; @@ -910,10 +792,13 @@ void __init efi_enter_virtual_mode(void) for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; - if (!(md->attribute & EFI_MEMORY_RUNTIME) && - md->type != EFI_BOOT_SERVICES_CODE && - md->type != EFI_BOOT_SERVICES_DATA) - continue; + if (!(md->attribute & EFI_MEMORY_RUNTIME)) { +#ifdef CONFIG_X86_64 + if (md->type != EFI_BOOT_SERVICES_CODE && + md->type != EFI_BOOT_SERVICES_DATA) +#endif + continue; + } size = md->num_pages << EFI_PAGE_SHIFT; end = md->phys_addr + size; diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 88692871823f..9cac82588cbc 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -73,9 +73,10 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/../../boot/code16gcc.h \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ + -mno-mmx -mno-sse \ $(call cc-option, -ffreestanding) \ $(call cc-option, -fno-toplevel-reorder,\ - $(call cc-option, -fno-unit-at-a-time)) \ + $(call cc-option, -fno-unit-at-a-time)) \ $(call cc-option, -fno-stack-protector) \ $(call cc-option, -mpreferred-stack-boundary=2) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 38ae65dfd14f..63a899304d27 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -212,10 +212,10 @@ 203 common sched_setaffinity sys_sched_setaffinity 204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 common io_setup sys_io_setup +206 64 io_setup sys_io_setup 207 common io_destroy sys_io_destroy 208 common io_getevents sys_io_getevents -209 common io_submit sys_io_submit +209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area 212 common lookup_dcookie sys_lookup_dcookie @@ -356,3 +356,5 @@ 540 x32 process_vm_writev compat_sys_process_vm_writev 541 x32 setsockopt compat_sys_setsockopt 542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 0faad646f5fd..0f134c7cfc24 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -41,6 +41,7 @@ enum { #ifdef CONFIG_X86_64 #define vdso_enabled sysctl_vsyscall32 #define arch_setup_additional_pages syscall32_setup_pages +extern int sysctl_ldt16; #endif /* @@ -380,6 +381,13 @@ static ctl_table abi_table2[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ldt16", + .data = &sysctl_ldt16, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, {} }; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 95fb2aa5927e..156344448d19 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -878,7 +878,6 @@ int m2p_add_override(unsigned long mfn, struct page *page, unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; - int ret = 0; pfn = page_to_pfn(page); if (!PageHighMem(page)) { @@ -925,8 +924,8 @@ int m2p_add_override(unsigned long mfn, struct page *page, * frontend pages while they are being shared with the backend, * because mfn_to_pfn (that ends up being called by GUPF) will * return the backend pfn rather than the frontend pfn. */ - ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); - if (ret == 0 && get_phys_to_machine(pfn) == mfn) + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) == mfn) set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)); return 0; @@ -941,7 +940,6 @@ int m2p_remove_override(struct page *page, unsigned long uninitialized_var(address); unsigned level; pte_t *ptep = NULL; - int ret = 0; pfn = page_to_pfn(page); mfn = get_phys_to_machine(pfn); @@ -1019,8 +1017,8 @@ int m2p_remove_override(struct page *page, * the original pfn causes mfn_to_pfn(mfn) to return the frontend * pfn again. */ mfn &= ~FOREIGN_FRAME_BIT; - ret = __get_user(pfn, &machine_to_phys_mapping[mfn]); - if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && + pfn = mfn_to_pfn_no_overrides(mfn); + if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) && m2p_find_override(mfn) == NULL) set_phys_to_machine(pfn, mfn); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 94eac5c85cdc..0a9fb7a0b452 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type) e820_add_region(start, end - start, type); } +void xen_ignore_unusable(struct e820entry *list, size_t map_size) +{ + struct e820entry *entry; + unsigned int i; + + for (i = 0, entry = list; i < map_size; i++, entry++) { + if (entry->type == E820_UNUSABLE) + entry->type = E820_RAM; + } +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ @@ -353,6 +364,17 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); + /* + * Xen won't allow a 1:1 mapping to be created to UNUSABLE + * regions, so if we're using the machine memory map leave the + * region as RAM as it is in the pseudo-physical map. + * + * UNUSABLE regions in domUs are not handled and will need + * a patch in the future. + */ + if (xen_initial_domain()) + xen_ignore_unusable(map, memmap.nr_entries); + /* Make sure the Xen-supplied memory map is well-ordered. */ sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index d99cae8147d1..570c9a5c4d3f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -245,6 +245,15 @@ static void __init xen_smp_prepare_boot_cpu(void) old memory can be recycled */ make_lowmem_page_readwrite(xen_initial_gdt); +#ifdef CONFIG_X86_32 + /* + * Xen starts us with XEN_FLAT_RING1_DS, but linux code + * expects __USER_DS + */ + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#endif + xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); } @@ -667,8 +676,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc; - rc = native_cpu_up(cpu, tidle); - WARN_ON (xen_smp_intr_init(cpu)); + /* + * xen_smp_intr_init() needs to run before native_cpu_up() + * so that IPI vectors are set up on the booting CPU before + * it is marked online in native_cpu_up(). + */ + rc = xen_smp_intr_init(cpu); + WARN_ON(rc); + if (!rc) + rc = native_cpu_up(cpu, tidle); return rc; } diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 3d88bfdf9e1c..13e8935e2eab 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -36,9 +36,8 @@ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); -/* unused ns of stolen and blocked time */ +/* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -static DEFINE_PER_CPU(u64, xen_residual_blocked); /* return an consistent snapshot of 64-bit time/counter value */ static u64 get64(const u64 *p) @@ -115,7 +114,7 @@ static void do_stolen_accounting(void) { struct vcpu_runstate_info state; struct vcpu_runstate_info *snap; - s64 blocked, runnable, offline, stolen; + s64 runnable, offline, stolen; cputime_t ticks; get_runstate_snapshot(&state); @@ -125,7 +124,6 @@ static void do_stolen_accounting(void) snap = &__get_cpu_var(xen_runstate_snapshot); /* work out how much time the VCPU has not been runn*ing* */ - blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked]; runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable]; offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline]; @@ -141,17 +139,6 @@ static void do_stolen_accounting(void) ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen); __this_cpu_write(xen_residual_stolen, stolen); account_steal_ticks(ticks); - - /* Add the appropriate number of ticks of blocked time, - including any left-overs from last time. */ - blocked += __this_cpu_read(xen_residual_blocked); - - if (blocked < 0) - blocked = 0; - - ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked); - __this_cpu_write(xen_residual_blocked, blocked); - account_idle_ticks(ticks); } /* Get the TSC speed from Xen */ |