diff options
Diffstat (limited to 'arch/x86')
117 files changed, 1679 insertions, 989 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index fe120da25625..3115eae96ad8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -121,6 +121,7 @@ config X86 select OLD_SIGACTION if X86_32 select COMPAT_OLD_SIGACTION if IA32_EMULATION select RTC_LIB + select ARCH_SUPPORTS_ATOMIC_RMW config INSTRUCTION_DECODER def_bool y @@ -207,6 +208,12 @@ config ARCH_HIBERNATION_POSSIBLE config ARCH_SUSPEND_POSSIBLE def_bool y +config ARCH_WANT_HUGE_PMD_SHARE + def_bool y + +config ARCH_WANT_GENERAL_HUGETLB + def_bool y + config ZONE_DMA32 bool default X86_64 @@ -951,10 +958,27 @@ config VM86 default y depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run 16-bit legacy - code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + This option is required by programs like DOSEMU to run + 16-bit real mode legacy code on x86 processors. It also may + be needed by software like XFree86 to initialize some video + cards via BIOS. Disabling this option saves about 6K. + +config X86_16BIT + bool "Enable support for 16-bit segments" if EXPERT + default y + ---help--- + This option is required by programs like Wine to run 16-bit + protected mode legacy code on x86 processors. Disabling + this option saves about 300 bytes on i386, or around 6K text + plus 16K runtime memory on x86-64, + +config X86_ESPFIX32 + def_bool y + depends on X86_16BIT && X86_32 + +config X86_ESPFIX64 + def_bool y + depends on X86_16BIT && X86_64 config TOSHIBA tristate "Toshiba Laptop support" @@ -1560,6 +1584,7 @@ config EFI config EFI_STUB bool "EFI stub support" depends on EFI + select RELOCATABLE ---help--- This kernel feature allows a bzImage to be loaded directly by EFI firmware without the use of a bootloader. 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/boot/header.S b/arch/x86/boot/header.S index 9ec06a1f6d61..425712462178 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -91,10 +91,9 @@ bs_die: .section ".bsdata", "a" bugger_off_msg: - .ascii "Direct floppy boot is not supported. " - .ascii "Use a boot loader program instead.\r\n" + .ascii "Use a boot loader.\r\n" .ascii "\n" - .ascii "Remove disk and press any key to reboot ...\r\n" + .ascii "Remove disk and press any key to reboot...\r\n" .byte 0 #ifdef CONFIG_EFI_STUB @@ -108,7 +107,7 @@ coff_header: #else .word 0x8664 # x86-64 #endif - .word 3 # nr_sections + .word 4 # nr_sections .long 0 # TimeDateStamp .long 0 # PointerToSymbolTable .long 1 # NumberOfSymbols @@ -250,6 +249,25 @@ section_table: .word 0 # NumberOfLineNumbers .long 0x60500020 # Characteristics (section flags) + # + # The offset & size fields are filled in by build.c. + # + .ascii ".bss" + .byte 0 + .byte 0 + .byte 0 + .byte 0 + .long 0 + .long 0x0 + .long 0 # Size of initialized data + # on disk + .long 0x0 + .long 0 # PointerToRelocations + .long 0 # PointerToLineNumbers + .word 0 # NumberOfRelocations + .word 0 # NumberOfLineNumbers + .long 0xc8000080 # Characteristics (section flags) + #endif /* CONFIG_EFI_STUB */ # Kernel attributes; used by setup. This is part 1 of the diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index 94c544650020..971a0ce062aa 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -141,7 +141,7 @@ static void usage(void) #ifdef CONFIG_EFI_STUB -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) { unsigned int pe_header; unsigned short num_sections; @@ -162,10 +162,10 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz put_unaligned_le32(size, section + 0x8); /* section header vma field */ - put_unaligned_le32(offset, section + 0xc); + put_unaligned_le32(vma, section + 0xc); /* section header 'size of initialised data' field */ - put_unaligned_le32(size, section + 0x10); + put_unaligned_le32(datasz, section + 0x10); /* section header 'file offset' field */ put_unaligned_le32(offset, section + 0x14); @@ -177,6 +177,11 @@ static void update_pecoff_section_header(char *section_name, u32 offset, u32 siz } } +static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) +{ + update_pecoff_section_header_fields(section_name, offset, size, size, offset); +} + static void update_pecoff_setup_and_reloc(unsigned int size) { u32 setup_offset = 0x200; @@ -201,9 +206,6 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) pe_header = get_unaligned_le32(&buf[0x3c]); - /* Size of image */ - put_unaligned_le32(file_sz, &buf[pe_header + 0x50]); - /* * Size of code: Subtract the size of the first sector (512 bytes) * which includes the header. @@ -218,6 +220,22 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz) update_pecoff_section_header(".text", text_start, text_sz); } +static void update_pecoff_bss(unsigned int file_sz, unsigned int init_sz) +{ + unsigned int pe_header; + unsigned int bss_sz = init_sz - file_sz; + + pe_header = get_unaligned_le32(&buf[0x3c]); + + /* Size of uninitialized data */ + put_unaligned_le32(bss_sz, &buf[pe_header + 0x24]); + + /* Size of image */ + put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); + + update_pecoff_section_header_fields(".bss", file_sz, bss_sz, 0, 0); +} + #endif /* CONFIG_EFI_STUB */ @@ -268,6 +286,9 @@ int main(int argc, char ** argv) int fd; void *kernel; u32 crc = 0xffffffffUL; +#ifdef CONFIG_EFI_STUB + unsigned int init_sz; +#endif /* Defaults for old kernel */ #ifdef CONFIG_X86_32 @@ -338,7 +359,9 @@ int main(int argc, char ** argv) put_unaligned_le32(sys_size, &buf[0x1f4]); #ifdef CONFIG_EFI_STUB - update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz)); + update_pecoff_text(setup_sectors * 512, i + (sys_size * 16)); + init_sz = get_unaligned_le32(&buf[0x260]); + update_pecoff_bss(i + (sys_size * 16), init_sz); #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ efi_stub_entry -= 0x200; 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/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 474dc1b59f72..c9305ef1d411 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target) 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) ASM_CLAC + + /* + * Sysenter doesn't filter flags, so we need to clear NT + * ourselves. To save a few cycles, we can check whether + * NT was set instead of doing an unconditional popfq. + */ + testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp) + jnz sysenter_fix_flags +sysenter_flags_fixed: + orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) CFI_REMEMBER_STATE @@ -184,6 +194,8 @@ sysexit_from_sys_call: TRACE_IRQS_ON ENABLE_INTERRUPTS_SYSEXIT32 + CFI_RESTORE_STATE + #ifdef CONFIG_AUDITSYSCALL .macro auditsys_entry_common movl %esi,%r9d /* 6th arg: 4th syscall arg */ @@ -226,7 +238,6 @@ sysexit_from_sys_call: .endm sysenter_auditsys: - CFI_RESTORE_STATE auditsys_entry_common movl %ebp,%r9d /* reload 6th syscall arg */ jmp sysenter_dispatch @@ -235,6 +246,11 @@ sysexit_audit: auditsys_exit sysexit_from_sys_call #endif +sysenter_fix_flags: + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) + popfq_cfi + jmp sysenter_flags_fixed + sysenter_tracesys: #ifdef CONFIG_AUDITSYSCALL testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) 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/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h index c09241659971..b4b38bacb404 100644 --- a/arch/x86/include/asm/dma-contiguous.h +++ b/arch/x86/include/asm/dma-contiguous.h @@ -4,7 +4,6 @@ #ifdef __KERNEL__ #include <linux/types.h> -#include <asm-generic/dma-contiguous.h> static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } 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/elf.h b/arch/x86/include/asm/elf.h index 9c999c1674fa..01f15b227d7e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -155,8 +155,9 @@ do { \ #define elf_check_arch(x) \ ((x)->e_machine == EM_X86_64) -#define compat_elf_check_arch(x) \ - (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64) +#define compat_elf_check_arch(x) \ + (elf_check_arch_ia32(x) || \ + (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) #if __USER32_DS != __USER_DS # error "The following code assumes __USER32_DS == __USER_DS" diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 000000000000..99efebb2f69d --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_64 + +#include <asm/percpu.h> + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 0dc7d9e21c34..9d7d36c82fc2 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -123,14 +123,14 @@ enum fixed_addresses { __end_of_permanent_fixed_addresses, /* - * 256 temporary boot-time mappings, used by early_ioremap(), + * 512 temporary boot-time mappings, used by early_ioremap(), * before ioremap() is functional. * - * If necessary we round it up to the next 256 pages boundary so + * If necessary we round it up to the next 512 pages boundary so * that we can have a single pgd entry and a single pte table: */ #define NR_FIX_BTMAPS 64 -#define FIX_BTMAPS_SLOTS 4 +#define FIX_BTMAPS_SLOTS 8 #define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) FIX_BTMAP_END = (__end_of_permanent_fixed_addresses ^ 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/irqflags.h b/arch/x86/include/asm/irqflags.h index bba3cf88e624..0a8b519226b8 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void) #define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ -#define INTERRUPT_RETURN iretq +#define INTERRUPT_RETURN jmp native_iret #define USERGS_SYSRET64 \ swapgs; \ sysretq; 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..b15a6b5fa341 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -79,6 +79,13 @@ #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) +static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) +{ + /* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */ + return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) - + (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); +} + #define SELECTOR_TI_MASK (1 << 2) #define SELECTOR_RPL_MASK 0x03 @@ -96,10 +103,6 @@ #define ASYNC_PF_PER_VCPU 64 -struct kvm_vcpu; -struct kvm; -struct kvm_async_pf; - enum kvm_reg { VCPU_REGS_RAX = 0, VCPU_REGS_RCX = 1, @@ -445,7 +448,7 @@ 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]; @@ -463,6 +466,7 @@ struct kvm_vcpu_arch { u64 mmio_gva; unsigned access; gfn_t mmio_gfn; + u64 mmio_gen; struct kvm_pmu pmu; @@ -631,8 +635,8 @@ struct msr_data { struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ - int (*hardware_enable)(void *dummy); - void (*hardware_disable)(void *dummy); + int (*hardware_enable)(void); + void (*hardware_disable)(void); void (*check_processor_compatibility)(void *rtn); int (*hardware_setup)(void); /* __init */ void (*hardware_unsetup)(void); /* __exit */ @@ -952,6 +956,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code) kvm_queue_exception_e(vcpu, GP_VECTOR, error_code); } +static inline u64 get_canonical(u64 la) +{ + return ((int64_t)la << 16) >> 16; +} + +static inline bool is_noncanonical_address(u64 la) +{ +#ifdef CONFIG_X86_64 + return get_canonical(la) != la; +#else + return false; +#endif +} + #define TSS_IOPB_BASE_OFFSET 0x66 #define TSS_BASE_SIZE 0x68 #define TSS_IOPB_SIZE (65536 / 8) @@ -1010,7 +1028,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_define_shared_msr(unsigned index, u32 msr); -void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); +int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); 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/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 2d883440cb9a..b1609f2c524c 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_VADDR _AC(0xffffffffa0000000, UL) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) #define EARLY_DYNAMIC_PAGE_TABLES 64 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/setup.h b/arch/x86/include/asm/setup.h index b7bf3505e1ec..2e327f114a1b 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -62,6 +62,8 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP +#include <asm/espfix.h> + /* * This is set up by the setup-routine at boot-time */ 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/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 5d9a3033b3d7..d3a87780c70b 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -211,9 +211,9 @@ struct kvm_cpuid_entry2 { __u32 padding[3]; }; -#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1 -#define KVM_CPUID_FLAG_STATEFUL_FUNC 2 -#define KVM_CPUID_FLAG_STATE_READ_NEXT 4 +#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX BIT(0) +#define KVM_CPUID_FLAG_STATEFUL_FUNC BIT(1) +#define KVM_CPUID_FLAG_STATE_READ_NEXT BIT(2) /* for KVM_SET_CPUID2 */ struct kvm_cpuid2 { 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/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 54991a746043..b16e6d28f149 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -6,7 +6,7 @@ * EFLAGS bits */ #define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ -#define X86_EFLAGS_BIT1 0x00000002 /* Bit 1 - always on */ +#define X86_EFLAGS_FIXED 0x00000002 /* Bit 1 - always on */ #define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ #define X86_EFLAGS_AF 0x00000010 /* Auxiliary carry Flag */ #define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 7bd3bd310106..111eb356dbea 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-y += syscall_$(BITS).o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o 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/apic.c b/arch/x86/kernel/apic/apic.c index 904611bf0e5a..033eb44dc661 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1263,7 +1263,7 @@ void __cpuinit setup_local_APIC(void) unsigned int value, queued; int i, j, acked = 0; unsigned long long tsc = 0, ntsc; - long long max_loops = cpu_khz; + long long max_loops = cpu_khz ? cpu_khz : 1000000; if (cpu_has_tsc) rdtscll(tsc); @@ -1360,7 +1360,7 @@ void __cpuinit setup_local_APIC(void) break; } if (queued) { - if (cpu_has_tsc) { + if (cpu_has_tsc && cpu_khz) { rdtscll(ntsc); max_loops = (cpu_khz << 10) - (ntsc - tsc); } else 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..6a7e3e9cffc3 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 + } } /* @@ -1129,7 +1134,7 @@ void syscall_init(void) /* Flags to clear on syscall */ wrmsrl(MSR_SYSCALL_MASK, X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF| - X86_EFLAGS_IOPL|X86_EFLAGS_AC); + X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT); } /* diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 9b0c441c03f5..8533e69d2b89 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -154,6 +154,21 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_ERMS); } } + + /* + * Intel Quark Core DevMan_001.pdf section 6.4.11 + * "The operating system also is required to invalidate (i.e., flush) + * the TLB when any changes are made to any of the page table entries. + * The operating system must reload CR3 to cause the TLB to be flushed" + * + * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should + * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * to be modified + */ + if (c->x86 == 5 && c->x86_model == 9) { + pr_info("Disabling PGE capability bit\n"); + setup_clear_cpu_cap(X86_FEATURE_PGE); + } } #ifdef CONFIG_X86_32 @@ -387,7 +402,8 @@ 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 +643,7 @@ 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.c b/arch/x86/kernel/cpu/perf_event_intel.c index a9e22073bd56..6d6bb6f4fd43 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1199,6 +1199,15 @@ again: intel_pmu_lbr_read(); /* + * CondChgd bit 63 doesn't mean any overflow status. Ignore + * and clear the bit. + */ + if (__test_and_clear_bit(63, (unsigned long *)&status)) { + if (!status) + goto done; + } + + /* * PEBS overflow sets bit 62 in the global status register */ if (__test_and_clear_bit(62, (unsigned long *)&status)) { @@ -2163,6 +2172,9 @@ __init int intel_pmu_init(void) case 62: /* IvyBridge EP */ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + /* dTLB-load-misses on IVB is different than SNB */ + hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */ + memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); 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/devicetree.c b/arch/x86/kernel/devicetree.c index b1581527a236..2fbad6b9f23c 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) } #ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end) +void __init early_init_dt_setup_initrd_arch(u64 start, u64 end) { initrd_start = (unsigned long)__va(start); initrd_end = (unsigned long)__va(end); 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..5c38e2b298cd 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -434,8 +434,9 @@ 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) +sysenter_after_call: movl %eax,PT_EAX(%esp) LOCKDEP_SYS_EXIT DISABLE_INTERRUPTS(CLBR_ANY) @@ -516,6 +517,7 @@ ENTRY(system_call) jae syscall_badsys syscall_call: call *sys_call_table(,%eax,4) +syscall_after_call: movl %eax,PT_EAX(%esp) # store the return value syscall_exit: LOCKDEP_SYS_EXIT @@ -530,6 +532,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -540,6 +543,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -552,13 +556,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 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 @@ -600,6 +600,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -690,8 +691,13 @@ syscall_fault: END(syscall_fault) syscall_badsys: - movl $-ENOSYS,PT_EAX(%esp) - jmp resume_userspace + movl $-ENOSYS,%eax + jmp syscall_after_call +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,%eax + jmp sysenter_after_call END(syscall_badsys) CFI_ENDPROC /* @@ -707,6 +713,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -716,8 +723,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -728,6 +737,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -1075,7 +1085,7 @@ 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 +1143,7 @@ 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) @@ -1335,11 +1345,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1379,6 +1391,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1400,6 +1413,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 727208941030..8c6b5c2284c7 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -58,6 +58,7 @@ #include <asm/asm.h> #include <asm/context_tracking.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -88,7 +89,7 @@ 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 @@ -365,7 +366,7 @@ ENDPROC(native_usergs_sysret64) /*CFI_REL_OFFSET ss,0*/ pushq_cfi %rax /* rsp */ CFI_REL_OFFSET rsp,0 - pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */ + pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED) /* eflags - interrupts on */ /*CFI_REL_OFFSET rflags,0*/ pushq_cfi $__KERNEL_CS /* cs */ /*CFI_REL_OFFSET cs,0*/ @@ -1056,12 +1057,45 @@ restore_args: irq_return: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) -#ifdef CONFIG_PARAVIRT ENTRY(native_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt +#endif + +native_irq_return_iret: iretq - _ASM_EXTABLE(native_iret, bad_iret) + _ASM_EXTABLE(native_irq_return_iret, bad_iret) + +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi + SWAPGS + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp native_irq_return_iret #endif .section .fixup,"ax" @@ -1127,9 +1161,40 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) + + /* + * If IRET takes a fault on the espfix stack, then we + * end up promoting it to a doublefault. In that case, + * modify the stack to make it look like we just entered + * the #GP handler from user space, similar to bad_iret. + */ +#ifdef CONFIG_X86_ESPFIX64 + ALIGN +__do_double_fault: + XCPT_FRAME 1 RDI+8 + movq RSP(%rdi),%rax /* Trap on the espfix stack? */ + sarq $PGDIR_SHIFT,%rax + cmpl $ESPFIX_PGD_ENTRY,%eax + jne do_double_fault /* No, just deliver the fault */ + cmpl $__KERNEL_CS,CS(%rdi) + jne do_double_fault + movq RIP(%rdi),%rax + cmpq $native_irq_return_iret,%rax + jne do_double_fault /* This shouldn't happen... */ + movq PER_CPU_VAR(kernel_stack),%rax + subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ + movq %rax,RSP(%rdi) + movq $0,(%rax) /* Missing (lost) #GP error code */ + movq $general_protection,RIP(%rdi) + retq + CFI_ENDPROC +END(__do_double_fault) +#else +# define __do_double_fault do_double_fault +#endif + /* * End of kprobes section */ @@ -1298,7 +1363,7 @@ zeroentry overflow do_overflow zeroentry bounds do_bounds zeroentry invalid_op do_invalid_op zeroentry device_not_available do_device_not_available -paranoiderrorentry double_fault do_double_fault +paranoiderrorentry double_fault __do_double_fault zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun errorentry invalid_TSS do_invalid_TSS errorentry segment_not_present do_segment_not_present @@ -1585,7 +1650,7 @@ error_sti: */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs movl %ecx,%eax /* zero extend */ diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 000000000000..94d857fb1033 --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,208 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/random.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/setup.h> +#include <asm/espfix.h> + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} 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..c37886d759cc 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -229,6 +229,11 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out_unlock; + } + 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/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 3f08f34f93eb..a1da6737ba5b 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); -DEF_NATIVE(pv_cpu_ops, iret, "iretq"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); @@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, iret); PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); 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/process_32.c b/arch/x86/kernel/process_32.c index 7305f7dfc7ab..0339f5c14bf9 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -147,7 +147,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; p->fpu_counter = 0; p->thread.io_bitmap_ptr = NULL; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 355ae06dbf94..f99a242730e9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -176,7 +176,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, childregs->bp = arg; childregs->orig_ax = -1; childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1; + childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; return 0; } *childregs = *current_pt_regs(); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 29a8120e6fe8..baa61e7370b7 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1475,15 +1475,6 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, force_sig_info(SIGTRAP, &info, tsk); } - -#ifdef CONFIG_X86_32 -# define IS_IA32 1 -#elif defined CONFIG_IA32_EMULATION -# define IS_IA32 is_compat_task() -#else -# define IS_IA32 0 -#endif - /* * We must return the syscall number to actually look up in the table. * This can be -1L to skip running any syscall at all. @@ -1521,7 +1512,7 @@ long syscall_trace_enter(struct pt_regs *regs) if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->orig_ax); - if (IS_IA32) + if (is_ia32_task()) audit_syscall_entry(AUDIT_ARCH_I386, regs->orig_ax, regs->bx, regs->cx, 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/resource.c b/arch/x86/kernel/resource.c index 2a26819bb6a8..80eab01c1a68 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail) void arch_remove_reservations(struct resource *avail) { - /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ + /* + * Trim out BIOS area (high 2MB) and E820 regions. We do not remove + * the low 1MB unconditionally, as this area is needed for some ISA + * cards requiring a memory range, e.g. the i82365 PCMCIA controller. + */ if (avail->flags & IORESOURCE_MEM) { - if (avail->start < BIOS_END) - avail->start = BIOS_END; resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); remove_e820_regions(avail); 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..66deef41512f 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) { @@ -677,6 +677,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~X86_EFLAGS_TF; + /* + * Ensure the signal handler starts with the new fpu state. + */ + if (used_math()) + drop_init_fpu(current); } signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index bfd348e99369..87084ab90d19 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -265,6 +265,13 @@ notrace static void __cpuinit start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -1277,6 +1284,9 @@ static void remove_siblinginfo(int cpu) for_each_cpu(sibling, cpu_sibling_mask(cpu)) cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); + cpumask_clear(cpu_llc_shared_mask(cpu)); cpumask_clear(cpu_sibling_mask(cpu)); cpumask_clear(cpu_core_mask(cpu)); c->phys_proc_id = 0; 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/kernel/tsc.c b/arch/x86/kernel/tsc.c index 098b3cfda72e..4e27ba53c40c 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -968,14 +968,17 @@ void __init tsc_init(void) x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) + if (!cpu_has_tsc) { + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; + } tsc_khz = x86_platform.calibrate_tsc(); cpu_khz = tsc_khz; if (!tsc_khz) { mark_tsc_unstable("could not calculate TSC khz"); + setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 9a907a67be8f..c52c07efe970 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -125,10 +125,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", - level, current->comm, task_pid_nr(current), - message, regs->ip, regs->cs, - regs->sp, regs->ax, regs->si, regs->di); + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + level, current->comm, task_pid_nr(current), + message, regs->ip, regs->cs, + regs->sp, regs->ax, regs->si, regs->di); } static int addr_to_vsyscall_nr(unsigned long addr) diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index ada87a329edc..1ee723298e90 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -268,8 +268,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size) if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate)) return -1; - drop_init_fpu(tsk); /* trigger finit */ - return 0; } @@ -400,8 +398,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) set_used_math(); } - if (use_eager_fpu()) + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a47a3e54b964..bdccfb62aa0d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select MMU_NOTIFIER select ANON_INODES select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD select HAVE_KVM_IRQ_ROUTING select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE @@ -38,6 +39,7 @@ config KVM select PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT + select KVM_VFIO ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index d609e1d84048..25d22b2d6509 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -5,12 +5,13 @@ CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. -kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o \ - irqchip.o) -kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(addprefix ../../../virt/kvm/, \ - assigned-dev.o iommu.o) -kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) +KVM := ../../../virt/kvm + +kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \ + $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \ + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o +kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o +kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ i8254.o cpuid.o pmu.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a20ecb5b6cbf..89d288237b9c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -187,8 +187,14 @@ static bool supported_xcr0_bit(unsigned bit) #define F(x) bit(X86_FEATURE_##x) -static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) +static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry, + u32 func, u32 index, int *nent, int maxnent) +{ + return 0; +} + +static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) { int r; unsigned f_nx = is_efer_nx() ? F(NX) : 0; @@ -480,6 +486,15 @@ out: return r; } +static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func, + u32 idx, int *nent, int maxnent, unsigned int type) +{ + if (type == KVM_GET_EMULATED_CPUID) + return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent); + + return __do_cpuid_ent(entry, func, idx, nent, maxnent); +} + #undef F struct kvm_cpuid_param { @@ -494,8 +509,34 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param) return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; } -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) +static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries, + __u32 num_entries, unsigned int ioctl_type) +{ + int i; + + if (ioctl_type != KVM_GET_EMULATED_CPUID) + return false; + + /* + * We want to make sure that ->padding is being passed clean from + * userspace in case we want to use it for something in the future. + * + * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we + * have to give ourselves satisfied only with the emulated side. /me + * sheds a tear. + */ + for (i = 0; i < num_entries; i++) { + if (entries[i].padding[0] || + entries[i].padding[1] || + entries[i].padding[2]) + return true; + } + return false; +} + +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type) { struct kvm_cpuid_entry2 *cpuid_entries; int limit, nent = 0, r = -E2BIG, i; @@ -512,6 +553,10 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, goto out; if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) cpuid->nent = KVM_MAX_CPUID_ENTRIES; + + if (sanity_check_entries(entries, cpuid->nent, type)) + return -EINVAL; + r = -ENOMEM; cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); if (!cpuid_entries) @@ -525,7 +570,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, continue; r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; @@ -536,7 +581,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, - &nent, cpuid->nent); + &nent, cpuid->nent, type); if (r) goto out_free; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index b7fd07984888..f1e4895174b2 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -6,8 +6,9 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, u32 function, u32 index); -int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); +int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries, + unsigned int type); int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, struct kvm_cpuid_entry __user *entries); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5953dcea752d..4c01f022c6ac 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -663,11 +663,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc); } -static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) -{ - register_address_increment(ctxt, &ctxt->_eip, rel); -} - static u32 desc_limit_scaled(struct desc_struct *desc) { u32 limit = get_desc_limit(desc); @@ -741,6 +736,38 @@ static int emulate_nm(struct x86_emulate_ctxt *ctxt) return emulate_exception(ctxt, NM_VECTOR, 0, false); } +static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, + int cs_l) +{ + switch (ctxt->op_bytes) { + case 2: + ctxt->_eip = (u16)dst; + break; + case 4: + ctxt->_eip = (u32)dst; + break; + case 8: + if ((cs_l && is_noncanonical_address(dst)) || + (!cs_l && (dst & ~(u32)-1))) + return emulate_gp(ctxt, 0); + ctxt->_eip = dst; + break; + default: + WARN(1, "unsupported eip assignment size\n"); + } + return X86EMUL_CONTINUE; +} + +static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) +{ + return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64); +} + +static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) +{ + return assign_eip_near(ctxt, ctxt->_eip + rel); +} + static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg) { u16 selector; @@ -2161,13 +2188,15 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) case 2: /* call near abs */ { long int old_eip; old_eip = ctxt->_eip; - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); + if (rc != X86EMUL_CONTINUE) + break; ctxt->src.val = old_eip; rc = em_push(ctxt); break; } case 4: /* jmp abs */ - ctxt->_eip = ctxt->src.val; + rc = assign_eip_near(ctxt, ctxt->src.val); break; case 5: /* jmp far */ rc = em_jmp_far(ctxt); @@ -2199,16 +2228,21 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) static int em_ret(struct x86_emulate_ctxt *ctxt) { - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - return em_pop(ctxt); + int rc; + unsigned long eip; + + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + + return assign_eip_near(ctxt, eip); } static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long cs; + int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2218,6 +2252,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &cs, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; + /* Outer-privilege level return is not implemented */ + if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl) + return X86EMUL_UNHANDLEABLE; rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS); return rc; } @@ -2465,7 +2502,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; - u64 msr_data; + u64 msr_data, rcx, rdx; int usermode; u16 cs_sel = 0, ss_sel = 0; @@ -2481,6 +2518,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) else usermode = X86EMUL_MODE_PROT32; + rcx = reg_read(ctxt, VCPU_REGS_RCX); + rdx = reg_read(ctxt, VCPU_REGS_RDX); + cs.dpl = 3; ss.dpl = 3; ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); @@ -2498,6 +2538,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; + if (is_noncanonical_address(rcx) || + is_noncanonical_address(rdx)) + return emulate_gp(ctxt, 0); break; } cs_sel |= SELECTOR_RPL_MASK; @@ -2506,8 +2549,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); - ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX); - *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX); + ctxt->_eip = rdx; + *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; } @@ -3046,10 +3089,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt) static int em_call(struct x86_emulate_ctxt *ctxt) { + int rc; long rel = ctxt->src.val; ctxt->src.val = (unsigned long)ctxt->_eip; - jmp_rel(ctxt, rel); + rc = jmp_rel(ctxt, rel); + if (rc != X86EMUL_CONTINUE) + return rc; return em_push(ctxt); } @@ -3081,11 +3127,12 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; + unsigned long eip; - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = &ctxt->_eip; - ctxt->dst.bytes = ctxt->op_bytes; - rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); + rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; + rc = assign_eip_near(ctxt, eip); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, ctxt->src.val); @@ -3375,20 +3422,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt) static int em_loop(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1); if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) && (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags))) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_jcxz(struct x86_emulate_ctxt *ctxt) { + int rc = X86EMUL_CONTINUE; + if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); - return X86EMUL_CONTINUE; + return rc; } static int em_in(struct x86_emulate_ctxt *ctxt) @@ -4207,7 +4258,10 @@ 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; @@ -4714,7 +4768,7 @@ special_insn: break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; @@ -4743,7 +4797,7 @@ special_insn: break; case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ @@ -4855,7 +4909,7 @@ twobyte_insn: break; case 0x80 ... 0x8f: /* jnz rel, etc*/ if (test_cc(ctxt->b, ctxt->eflags)) - jmp_rel(ctxt, ctxt->src.val); + rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 412a5aa0ef94..298781d4cfb4 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)) @@ -261,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) return; timer = &pit->pit_state.timer; + mutex_lock(&pit->pit_state.lock); if (hrtimer_cancel(timer)) hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + mutex_unlock(&pit->pit_state.lock); } static void destroy_pit_timer(struct kvm_pit *pit) @@ -349,6 +352,23 @@ 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/irq.c b/arch/x86/kvm/irq.c index 484bc874688b..3ec38cb56bd5 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) vector = kvm_cpu_get_extint(v); - if (kvm_apic_vid_enabled(v->kvm) || vector != -1) + if (vector != -1) return vector; /* PIC */ return kvm_get_apic_interrupt(v); /* APIC */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0eee2c8b64d1..681e4e251f00 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) { @@ -362,31 +362,90 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { - apic->irr_pending = false; + struct kvm_vcpu *vcpu; + + vcpu = apic->vcpu; + apic_clear_vector(vec, apic->regs + APIC_IRR); - if (apic_search_irr(apic) != -1) - apic->irr_pending = true; + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + /* try to update RVI */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + else { + vec = apic_search_irr(apic); + apic->irr_pending = (vec != -1); + } } static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { - if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + + if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * With APIC virtualization enabled, all caching is disabled + * because the processor can modify ISR under the hood. Instead + * just set SVI. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); + else { ++apic->isr_count; - BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + BUG_ON(apic->isr_count > MAX_APIC_VECTOR); + /* + * ISR (in service register) bit is set when injecting an interrupt. + * The highest vector is injected. Thus the latest bit set matches + * the highest bit in ISR. + */ + apic->highest_isr_cache = vec; + } +} + +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + /* - * ISR (in service register) bit is set when injecting an interrupt. - * The highest vector is injected. Thus the latest bit set matches - * the highest bit in ISR. + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. */ - apic->highest_isr_cache = vec; + 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 +525,6 @@ 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 +898,8 @@ 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 +1404,12 @@ 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 +1417,6 @@ 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); @@ -1621,6 +1665,13 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) if (vector == -1) return -1; + /* + * We get here even with APIC virtualization enabled, if doing + * nested virtualization and L1 runs with the "acknowledge interrupt + * on exit" mode. Then we cannot inject the interrupt via RVI, + * because the process would deliver it through the IDT. + */ + apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); @@ -1705,7 +1756,6 @@ 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 +1763,8 @@ 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 +1800,6 @@ 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 +1815,24 @@ 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..0cc34f594c2a 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; @@ -3066,7 +3072,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) return; - vcpu_clear_mmio_info(vcpu, ~0ul); + vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; @@ -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)) @@ -3232,7 +3241,7 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) arch.direct_map = vcpu->arch.mmu.direct_map; arch.cr3 = vcpu->arch.mmu.get_cr3(vcpu); - return kvm_setup_async_pf(vcpu, gva, gfn, &arch); + return kvm_setup_async_pf(vcpu, gva, gfn_to_hva(vcpu->kvm, gfn), &arch); } static bool can_do_async_pf(struct kvm_vcpu *vcpu) @@ -4220,7 +4229,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) if (nr_to_scan == 0) goto out; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { int idx; @@ -4256,7 +4265,7 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) break; } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); out: return percpu_counter_read_positive(&kvm_total_used_mmu_pages); @@ -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..a6a6370c2010 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -69,6 +69,7 @@ struct guest_walker { pt_element_t prefetch_ptes[PTE_PREFETCH_NUM]; gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; + bool pte_writable[PT_MAX_FULL_LEVELS]; unsigned pt_access; unsigned pte_access; gfn_t gfn; @@ -130,6 +131,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (pte == orig_pte) continue; + /* + * If the slot is read-only, simply do not process the accessed + * and dirty bits. This is the correct thing to do if the slot + * is ROM, and page tables in read-as-ROM/write-as-MMIO slots + * are only supported if the accessed and dirty bits are already + * set in the ROM (so that MMIO writes are never needed). + * + * Note that NPT does not allow this at all and faults, since + * it always wants nested page table entries for the guest + * page tables to be writable. And EPT works but will simply + * overwrite the read-only memory to set the accessed and dirty + * bits. + */ + if (unlikely(!walker->pte_writable[level - 1])) + continue; + ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte); if (ret) return ret; @@ -204,7 +221,8 @@ retry_walk: goto error; real_gfn = gpa_to_gfn(real_gfn); - host_addr = gfn_to_hva(vcpu->kvm, real_gfn); + host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn, + &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -423,6 +441,9 @@ 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 +692,11 @@ 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..03f7d03c92a2 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -606,7 +606,7 @@ static int has_svm(void) return 1; } -static void svm_hardware_disable(void *garbage) +static void svm_hardware_disable(void) { /* Make sure we clean up behind us */ if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) @@ -617,7 +617,7 @@ static void svm_hardware_disable(void *garbage) amd_pmu_disable_virt(); } -static int svm_hardware_enable(void *garbage) +static int svm_hardware_enable(void) { struct svm_cpu_data *sd; @@ -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; @@ -3198,7 +3196,7 @@ static int wrmsr_interception(struct vcpu_svm *svm) msr.host_initiated = false; svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, &msr)) { + if (kvm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); } else { @@ -3480,9 +3478,9 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_code; - return 0; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } return svm_exit_handlers[exit_code](svm); @@ -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..a3476bedd201 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2493,12 +2493,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; msr = find_msr_entry(vmx, msr_index); if (msr) { + u64 old_msr_data = msr->data; msr->data = data; if (msr - vmx->guest_msrs < vmx->save_nmsrs) { preempt_disable(); - kvm_set_shared_msr(msr->index, msr->data, - msr->mask); + ret = kvm_set_shared_msr(msr->index, msr->data, + msr->mask); preempt_enable(); + if (ret) + msr->data = old_msr_data; } break; } @@ -2566,7 +2569,7 @@ static void kvm_cpu_vmxon(u64 addr) : "memory", "cc"); } -static int hardware_enable(void *garbage) +static int hardware_enable(void) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); @@ -2630,7 +2633,7 @@ static void kvm_cpu_vmxoff(void) asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc"); } -static void hardware_disable(void *garbage) +static void hardware_disable(void) { if (vmm_exclusive) { vmclear_local_loaded_vmcss(); @@ -3399,15 +3402,22 @@ 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) @@ -5055,7 +5065,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu) msr.data = data; msr.index = ecx; msr.host_initiated = false; - if (vmx_set_msr(vcpu, &msr) != 0) { + if (kvm_set_msr(vcpu, &msr) != 0) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(vcpu, 0); return 1; @@ -6644,10 +6654,10 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) && kvm_vmx_exit_handlers[exit_reason]) return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; - vcpu->run->hw.hardware_exit_reason = exit_reason; + WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason); + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; } - return 0; } static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) @@ -7126,8 +7136,8 @@ 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); @@ -7942,7 +7952,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->host_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->host_rip); - vmx_set_rflags(vcpu, X86_EFLAGS_BIT1); + vmx_set_rflags(vcpu, X86_EFLAGS_FIXED); /* * Note that calling vmx_set_cr0 is important, even if cr0 hasn't * actually changed, because it depends on the current state of diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e8ba99c34180..ce20cb65de58 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; @@ -222,24 +225,29 @@ static void kvm_shared_msr_cpu_online(void) shared_msr_update(i, shared_msrs_global.msrs[i]); } -void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) { unsigned int cpu = smp_processor_id(); struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); + int err; if (((value ^ smsr->values[slot].curr) & mask) == 0) - return; + return 0; smsr->values[slot].curr = value; - wrmsrl(shared_msrs_global.msrs[slot], value); + err = wrmsrl_safe(shared_msrs_global.msrs[slot], value); + if (err) + return 1; + if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); smsr->registered = true; } + return 0; } EXPORT_SYMBOL_GPL(kvm_set_shared_msr); -static void drop_user_return_notifiers(void *ignore) +static void drop_user_return_notifiers(void) { unsigned int cpu = smp_processor_id(); struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu); @@ -917,7 +925,6 @@ void kvm_enable_efer_bits(u64 mask) } EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); - /* * Writes msr value into into the appropriate "register". * Returns 0 on success, non-0 otherwise. @@ -925,8 +932,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits); */ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { + switch (msr->index) { + case MSR_FS_BASE: + case MSR_GS_BASE: + case MSR_KERNEL_GS_BASE: + case MSR_CSTAR: + case MSR_LSTAR: + if (is_noncanonical_address(msr->data)) + return 1; + break; + case MSR_IA32_SYSENTER_EIP: + case MSR_IA32_SYSENTER_ESP: + /* + * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if + * non-canonical address is written on Intel but not on + * AMD (which ignores the top 32-bits, because it does + * not implement 64-bit SYSENTER). + * + * 64-bit code should hence be able to write a non-canonical + * value on AMD. Making the address canonical ensures that + * vmentry does not fail on Intel after writing a non-canonical + * value, and that something deterministic happens if the guest + * invokes 64-bit SYSENTER. + */ + msr->data = get_canonical(msr->data); + } return kvm_x86_ops->set_msr(vcpu, msr); } +EXPORT_SYMBOL_GPL(kvm_set_msr); /* * Adapt set_msr() to msr_io()'s calling convention @@ -1193,20 +1226,37 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr) elapsed = ns - kvm->arch.last_tsc_nsec; if (vcpu->arch.virtual_tsc_khz) { + int faulted = 0; + /* n.b - signed multiplication and division required */ usdiff = data - kvm->arch.last_tsc_write; #ifdef CONFIG_X86_64 usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz; #else /* do_div() only does unsigned */ - asm("idivl %2; xor %%edx, %%edx" - : "=A"(usdiff) - : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz)); + asm("1: idivl %[divisor]\n" + "2: xor %%edx, %%edx\n" + " movl $0, %[faulted]\n" + "3:\n" + ".section .fixup,\"ax\"\n" + "4: movl $1, %[faulted]\n" + " jmp 3b\n" + ".previous\n" + + _ASM_EXTABLE(1b, 4b) + + : "=A"(usdiff), [faulted] "=r" (faulted) + : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz)); + #endif do_div(elapsed, 1000); usdiff -= elapsed; if (usdiff < 0) usdiff = -usdiff; + + /* idivl overflow => difference is larger than USEC_PER_SEC */ + if (faulted) + usdiff = USEC_PER_SEC; } else usdiff = USEC_PER_SEC; /* disable TSC match window below */ @@ -2500,7 +2550,7 @@ out: return r; } -int kvm_dev_ioctl_check_extension(long ext) +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r; @@ -2510,6 +2560,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_EXT_EMUL_CPUID: case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: @@ -2619,15 +2670,17 @@ long kvm_arch_dev_ioctl(struct file *filp, r = 0; break; } - case KVM_GET_SUPPORTED_CPUID: { + case KVM_GET_SUPPORTED_CPUID: + case KVM_GET_EMULATED_CPUID: { struct kvm_cpuid2 __user *cpuid_arg = argp; struct kvm_cpuid2 cpuid; r = -EFAULT; if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; - r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + + r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries, + ioctl); if (r) goto out; @@ -3138,8 +3191,7 @@ 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: { @@ -4785,7 +4837,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu) ++vcpu->stat.insn_emulation_fail; trace_kvm_emulate_insn_failed(vcpu); - if (!is_guest_mode(vcpu)) { + if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; @@ -5104,7 +5156,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1); - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->cpu != freq->cpu) @@ -5114,7 +5166,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va send_ipi = 1; } } - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); if (freq->old < freq->new && send_ipi) { /* @@ -5261,12 +5313,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work) struct kvm_vcpu *vcpu; int i; - raw_spin_lock(&kvm_lock); + spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests); atomic_set(&kvm_guest_has_master_clock, 0); - raw_spin_unlock(&kvm_lock); + spin_unlock(&kvm_lock); } static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn); @@ -5539,36 +5591,6 @@ 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 +5911,6 @@ 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) { @@ -5944,15 +5961,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) } if (need_resched()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_resched(vcpu); + cond_resched(); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - vapic_exit(vcpu); - return r; } @@ -6017,7 +6032,7 @@ 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; @@ -6600,7 +6615,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector) kvm_rip_write(vcpu, 0); } -int kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; @@ -6611,7 +6626,7 @@ int kvm_arch_hardware_enable(void *garbage) bool stable, backwards_tsc = false; kvm_shared_msr_cpu_online(); - ret = kvm_x86_ops->hardware_enable(garbage); + ret = kvm_x86_ops->hardware_enable(); if (ret != 0) return ret; @@ -6691,10 +6706,10 @@ int kvm_arch_hardware_enable(void *garbage) return 0; } -void kvm_arch_hardware_disable(void *garbage) +void kvm_arch_hardware_disable(void) { - kvm_x86_ops->hardware_disable(garbage); - drop_user_return_notifiers(garbage); + kvm_x86_ops->hardware_disable(); + drop_user_return_notifiers(); } int kvm_arch_hardware_setup(void) @@ -6806,6 +6821,10 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) static_key_slow_dec(&kvm_no_apic_vcpu); } +void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) +{ +} + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { if (type) @@ -6897,7 +6916,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(rcu_dereference_check(kvm->arch.apic_map, 1)); } -void kvm_arch_free_memslot(struct kvm_memory_slot *free, +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { int i; @@ -6918,7 +6937,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free, } } -int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) +int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, + unsigned long npages) { int i; @@ -6976,6 +6996,10 @@ out_free: return -ENOMEM; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, @@ -7114,7 +7138,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) int r; if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) || - is_error_page(work->page)) + work->wakeup_all) return; r = kvm_mmu_reload(vcpu); @@ -7224,7 +7248,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, struct x86_exception fault; trace_kvm_async_pf_ready(work->arch.token, work->gva); - if (is_error_page(work->page)) + if (work->wakeup_all) work->arch.token = ~0; /* broadcast wakeup */ else kvm_del_async_pf_gfn(vcpu, work->arch.gfn); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index e224f7a671b6..7626d3efa064 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -78,15 +78,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu, vcpu->arch.mmio_gva = gva & PAGE_MASK; vcpu->arch.access = access; vcpu->arch.mmio_gfn = gfn; + vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation; +} + +static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation; } /* - * Clear the mmio cache info for the given gva, - * specially, if gva is ~0ul, we clear all mmio cache info. + * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we + * clear all mmio cache info. */ +#define MMIO_GVA_ANY (~(gva_t)0) + static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) { - if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) + if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK)) return; vcpu->arch.mmio_gva = 0; @@ -94,7 +102,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva) static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) { - if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK)) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva && + vcpu->arch.mmio_gva == (gva & PAGE_MASK)) return true; return false; @@ -102,7 +111,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva) static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { - if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) + if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn && + vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT) return true; return false; @@ -124,5 +134,7 @@ 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/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0002a3a33081..e04e67753238 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,11 +30,13 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -45,6 +47,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; seq_printf(m, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || st->current_address >= st->marker[1].start_address) { @@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - seq_printf(m, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + seq_printf(m, "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = (st->current_address - st->start_address); + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + seq_printf(m, "%9lu%c ", delta, *unit); + printk_prot(m, st->current_prot, st->level); } - seq_printf(m, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level); + st->lines++; /* * We print markers for special areas of address space, @@ -206,7 +215,15 @@ static void note_page(struct seq_file *m, struct pg_state *st, * This helps in the interpretation. */ if (st->current_address >= st->marker[1].start_address) { + if (st->marker->max_lines && + st->lines > st->marker->max_lines) { + unsigned long nskip = + st->lines - st->marker->max_lines; + seq_printf(m, "... %lu entr%s skipped ... \n", + nskip, nskip == 1 ? "y" : "ies"); + } st->marker++; + st->lines = 0; seq_printf(m, "---[ %s ]---\n", st->marker->name); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 654be4ae3047..d8b1ff68dbb9 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, force_sig_info_fault(SIGBUS, code, address, tsk, fault); } -static noinline int +static noinline void mm_fault_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) { - /* - * Pagefault was interrupted by SIGKILL. We have no reason to - * continue pagefault. - */ - if (fatal_signal_pending(current)) { - if (!(fault & VM_FAULT_RETRY)) - up_read(¤t->mm->mmap_sem); - if (!(error_code & PF_USER)) - no_context(regs, error_code, address, 0, 0); - return 1; + if (fatal_signal_pending(current) && !(error_code & PF_USER)) { + up_read(¤t->mm->mmap_sem); + no_context(regs, error_code, address, 0, 0); + return; } - if (!(fault & VM_FAULT_ERROR)) - return 0; if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ @@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, up_read(¤t->mm->mmap_sem); no_context(regs, error_code, address, SIGSEGV, SEGV_MAPERR); - return 1; + return; } up_read(¤t->mm->mmap_sem); @@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, else BUG(); } - return 1; } static int spurious_fault_check(unsigned long error_code, pte_t *pte) @@ -989,6 +980,12 @@ 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; @@ -1011,9 +1008,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) unsigned long address; struct mm_struct *mm; int fault; - int write = error_code & PF_WRITE; - unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE | - (write ? FAULT_FLAG_WRITE : 0); + unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; tsk = current; mm = tsk->mm; @@ -1083,6 +1078,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) if (user_mode_vm(regs)) { local_irq_enable(); error_code |= PF_USER; + flags |= FAULT_FLAG_USER; } else { if (regs->flags & X86_EFLAGS_IF) local_irq_enable(); @@ -1091,11 +1087,9 @@ __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); @@ -1109,6 +1103,9 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code) return; } + if (error_code & PF_WRITE) + flags |= FAULT_FLAG_WRITE; + /* * When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in @@ -1187,9 +1184,17 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, flags); - if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) { - if (mm_fault_error(regs, error_code, address, fault)) - return; + /* + * If we need to retry but a fatal signal is pending, handle the + * signal first. We do not need to release the mmap_sem because it + * would already be released in __lock_page_or_retry in mm/filemap.c. + */ + if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))) + return; + + if (unlikely(fault & VM_FAULT_ERROR)) { + mm_fault_error(regs, error_code, address, fault); + return; } /* diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index ae1aa71d0115..7e73e8c69096 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -16,169 +16,6 @@ #include <asm/tlbflush.h> #include <asm/pgalloc.h> -static unsigned long page_table_shareable(struct vm_area_struct *svma, - struct vm_area_struct *vma, - unsigned long addr, pgoff_t idx) -{ - unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + - svma->vm_start; - unsigned long sbase = saddr & PUD_MASK; - unsigned long s_end = sbase + PUD_SIZE; - - /* Allow segments to share if only one is marked locked */ - unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; - unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; - - /* - * match the virtual addresses, permission and the alignment of the - * page table page. - */ - if (pmd_index(addr) != pmd_index(saddr) || - vm_flags != svm_flags || - sbase < svma->vm_start || svma->vm_end < s_end) - return 0; - - return saddr; -} - -static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) -{ - unsigned long base = addr & PUD_MASK; - unsigned long end = base + PUD_SIZE; - - /* - * check on proper vm_flags and page table alignment - */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) - return 1; - return 0; -} - -/* - * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() - * and returns the corresponding pte. While this is not necessary for the - * !shared pmd case because we can allocate the pmd later as well, it makes the - * code much cleaner. pmd allocation is essential for the shared case because - * pud has to be populated inside the same i_mmap_mutex section - otherwise - * racing tasks could either miss the sharing (see huge_pte_offset) or select a - * bad pmd for sharing. - */ -static pte_t * -huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) -{ - struct vm_area_struct *vma = find_vma(mm, addr); - struct address_space *mapping = vma->vm_file->f_mapping; - pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + - vma->vm_pgoff; - struct vm_area_struct *svma; - unsigned long saddr; - pte_t *spte = NULL; - pte_t *pte; - - if (!vma_shareable(vma, addr)) - return (pte_t *)pmd_alloc(mm, pud, addr); - - mutex_lock(&mapping->i_mmap_mutex); - vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { - if (svma == vma) - continue; - - saddr = page_table_shareable(svma, vma, addr, idx); - if (saddr) { - spte = huge_pte_offset(svma->vm_mm, saddr); - if (spte) { - get_page(virt_to_page(spte)); - break; - } - } - } - - if (!spte) - goto out; - - spin_lock(&mm->page_table_lock); - if (pud_none(*pud)) - pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); - else - put_page(virt_to_page(spte)); - spin_unlock(&mm->page_table_lock); -out: - pte = (pte_t *)pmd_alloc(mm, pud, addr); - mutex_unlock(&mapping->i_mmap_mutex); - return pte; -} - -/* - * unmap huge page backed by shared pte. - * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * - * called with vma->vm_mm->page_table_lock held. - * - * returns: 1 successfully unmapped a shared pte page - * 0 the underlying pte page is not shared, or it is the last user - */ -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) -{ - pgd_t *pgd = pgd_offset(mm, *addr); - pud_t *pud = pud_offset(pgd, *addr); - - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) - return 0; - - pud_clear(pud); - put_page(virt_to_page(ptep)); - *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; - return 1; -} - -pte_t *huge_pte_alloc(struct mm_struct *mm, - unsigned long addr, unsigned long sz) -{ - pgd_t *pgd; - pud_t *pud; - pte_t *pte = NULL; - - pgd = pgd_offset(mm, addr); - pud = pud_alloc(mm, pgd, addr); - if (pud) { - if (sz == PUD_SIZE) { - pte = (pte_t *)pud; - } else { - BUG_ON(sz != PMD_SIZE); - if (pud_none(*pud)) - pte = huge_pmd_share(mm, addr, pud); - else - pte = (pte_t *)pmd_alloc(mm, pud, addr); - } - } - BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); - - return pte; -} - -pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd = NULL; - - pgd = pgd_offset(mm, addr); - if (pgd_present(*pgd)) { - pud = pud_offset(pgd, addr); - if (pud_present(*pud)) { - if (pud_large(*pud)) - return (pte_t *)pud; - pmd = pmd_offset(pud, addr); - } - } - return (pte_t *) pmd; -} - #if 0 /* This is just for testing */ struct page * follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) @@ -240,30 +77,6 @@ int pud_huge(pud_t pud) return !!(pud_val(pud) & _PAGE_PSE); } -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); - return page; -} - -struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - struct page *page; - - page = pte_page(*(pte_t *)pud); - if (page) - page += ((address & ~PUD_MASK) >> PAGE_SHIFT); - return page; -} - #endif /* x86_64 also uses this file */ 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/mm/pageattr.c b/arch/x86/mm/pageattr.c index bb32480c2d71..aabdf762f592 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -389,7 +389,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr) psize = page_level_size(level); pmask = page_level_mask(level); offset = virt_addr & ~pmask; - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; return (phys_addr | offset); } EXPORT_SYMBOL_GPL(slow_virt_to_phys); 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/pci/i386.c b/arch/x86/pci/i386.c index 94919e307f8e..2883f0840201 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res, return start; if (start & 0x300) start = (start + 0x3ff) & ~0x3ff; + } else if (res->flags & IORESOURCE_MEM) { + /* The low 1MB range is reserved for ISA cards */ + if (start < BIOS_END) + start = BIOS_END; } return start; } 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/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 */ |