diff options
Diffstat (limited to 'arch/x86')
98 files changed, 1068 insertions, 376 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index e4098912fef2..09468b045172 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -22,6 +22,7 @@ config X86_64 config X86 def_bool y select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select HAVE_AOUT if X86_32 @@ -854,7 +855,7 @@ source "kernel/Kconfig.preempt" config X86_UP_APIC bool "Local APIC support on uniprocessors" - depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI + depends on X86_32 && !SMP && !X86_32_NON_STANDARD ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an integrated interrupt controller in the CPU. If you have a single-CPU @@ -865,6 +866,10 @@ config X86_UP_APIC performance counters), and the NMI watchdog which detects hard lockups. +config X86_UP_APIC_MSI + def_bool y + select X86_UP_APIC if X86_32 && !SMP && !X86_32_NON_STANDARD && PCI_MSI + config X86_UP_IOAPIC bool "IO-APIC support on uniprocessors" depends on X86_UP_APIC @@ -2436,12 +2441,9 @@ config X86_DMA_REMAP depends on STA2X11 config IOSF_MBI - bool + tristate + default m depends on PCI - ---help--- - To be selected by modules requiring access to the Intel OnChip System - Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms - enumerable by PCI. source "net/Kconfig" diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 0fcd9133790c..67e9f5cc91ed 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -75,8 +75,10 @@ suffix-$(CONFIG_KERNEL_XZ) := xz suffix-$(CONFIG_KERNEL_LZO) := lzo suffix-$(CONFIG_KERNEL_LZ4) := lz4 +RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \ + $(CONFIG_SHELL) $(srctree)/arch/x86/tools/calc_run_size.sh) quiet_cmd_mkpiggy = MKPIGGY $@ - cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false ) + cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false ) targets += piggy.S $(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index 4dbf967da50d..6cfcf2a2eb93 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -183,12 +183,27 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, static bool mem_avoid_overlap(struct mem_vector *img) { int i; + struct setup_data *ptr; for (i = 0; i < MEM_AVOID_MAX; i++) { if (mem_overlaps(img, &mem_avoid[i])) return true; } + /* Avoid all entries in the setup_data linked list. */ + ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data; + while (ptr) { + struct mem_vector avoid; + + avoid.start = (u64)ptr; + avoid.size = sizeof(*ptr) + ptr->len; + + if (mem_overlaps(img, &avoid)) + return true; + + ptr = (struct setup_data *)(unsigned long)ptr->next; + } + return false; } diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 78cbb2db5a85..832a6590e9b3 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -489,8 +489,7 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table) hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image, - &options_size); + cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h index 81b6b652b46a..cc78e2da7af9 100644 --- a/arch/x86/boot/compressed/eboot.h +++ b/arch/x86/boot/compressed/eboot.h @@ -10,6 +10,7 @@ #define SEG_GRANULARITY_4KB (1 << 0) #define DESC_TYPE_CODE_DATA (1 << 0) +#define EFI_READ_CHUNK_SIZE (1024 * 1024) #define EFI_CONSOLE_OUT_DEVICE_GUID \ EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x0, 0x90, 0x27, \ @@ -37,6 +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; @@ -46,6 +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; @@ -53,6 +86,18 @@ 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; diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index f45ab7a36fb6..c5b56ed10aff 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -186,7 +186,8 @@ relocated: * Do the decompression, and jump to the new kernel.. */ /* push arguments for decompress_kernel: */ - pushl $z_output_len /* decompressed length */ + pushl $z_run_size /* size of kernel with .bss and .brk */ + pushl $z_output_len /* decompressed length, end of relocs */ leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ @@ -196,7 +197,7 @@ relocated: pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call decompress_kernel /* returns kernel location in %eax */ - addl $24, %esp + addl $28, %esp /* * Jump to the decompressed kernel. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index b10fa66a2540..34bbc0911b7c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -334,13 +334,16 @@ relocated: * Do the decompression, and jump to the new kernel.. */ pushq %rsi /* Save the real mode argument */ + movq $z_run_size, %r9 /* size of kernel with .bss and .brk */ + pushq %r9 movq %rsi, %rdi /* real mode address */ leaq boot_heap(%rip), %rsi /* malloc area for uncompression */ leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ - movq $z_output_len, %r9 /* decompressed length */ + movq $z_output_len, %r9 /* decompressed length, end of relocs */ call decompress_kernel /* returns kernel location in %rax */ + popq %r9 popq %rsi /* diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 196eaf373a06..8f45c855f84c 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -393,8 +393,11 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, unsigned char *output, - unsigned long output_len) + unsigned long output_len, + unsigned long run_size) { + unsigned char *output_orig = output; + real_mode = rmode; sanitize_boot_params(real_mode); @@ -416,8 +419,14 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, free_mem_ptr = heap; /* Heap */ free_mem_end_ptr = heap + BOOT_HEAP_SIZE; - output = choose_kernel_location(input_data, input_len, - output, output_len); + /* + * The memory hole needed for the kernel is the larger of either + * the entire decompressed kernel plus relocation table, or the + * entire decompressed kernel plus .bss and .brk sections. + */ + output = choose_kernel_location(input_data, input_len, output, + output_len > run_size ? output_len + : run_size); /* Validate memory location choices. */ if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1)) @@ -437,7 +446,12 @@ asmlinkage void *decompress_kernel(void *rmode, memptr heap, debug_putstr("\nDecompressing Linux... "); decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); - handle_relocations(output, output_len); + /* + * 32-bit always performs relocations. 64-bit relocations are only + * needed if kASLR has chosen a different load address. + */ + if (!IS_ENABLED(CONFIG_X86_64) || output != output_orig) + handle_relocations(output, output_len); debug_putstr("done.\nBooting the kernel.\n"); return output; } diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c index b669ab65bf6c..d8222f213182 100644 --- a/arch/x86/boot/compressed/mkpiggy.c +++ b/arch/x86/boot/compressed/mkpiggy.c @@ -36,11 +36,13 @@ int main(int argc, char *argv[]) uint32_t olen; long ilen; unsigned long offs; + unsigned long run_size; FILE *f = NULL; int retval = 1; - if (argc < 2) { - fprintf(stderr, "Usage: %s compressed_file\n", argv[0]); + if (argc < 3) { + fprintf(stderr, "Usage: %s compressed_file run_size\n", + argv[0]); goto bail; } @@ -74,6 +76,7 @@ int main(int argc, char *argv[]) offs += olen >> 12; /* Add 8 bytes for each 32K block */ offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */ offs = (offs+4095) & ~4095; /* Round to a 4K boundary */ + run_size = atoi(argv[2]); printf(".section \".rodata..compressed\",\"a\",@progbits\n"); printf(".globl z_input_len\n"); @@ -85,6 +88,8 @@ int main(int argc, char *argv[]) /* z_extract_offset_negative allows simplification of head_32.S */ printf(".globl z_extract_offset_negative\n"); printf("z_extract_offset_negative = -0x%lx\n", offs); + printf(".globl z_run_size\n"); + printf("z_run_size = %lu\n", run_size); printf(".globl input_data, input_data_end\n"); printf("input_data:\n"); diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index aafe8ce0d65d..e26984f7ab8d 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -66,5 +66,5 @@ module_exit(aes_fini); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); -MODULE_ALIAS("aes-asm"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("aes-asm"); diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 948ad0e77741..6d4fabac779c 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -1109,7 +1109,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC); if (!src) return -ENOMEM; - assoc = (src + req->cryptlen + auth_tag_len); + assoc = (src + req->cryptlen); scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0); scatterwalk_map_and_copy(assoc, req->assoc, 0, req->assoclen, 0); @@ -1134,7 +1134,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) scatterwalk_done(&src_sg_walk, 0, 0); scatterwalk_done(&assoc_sg_walk, 0, 0); } else { - scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1); + scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1); kfree(src); } return retval; @@ -1514,4 +1514,4 @@ module_exit(aesni_exit); MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("aes"); +MODULE_ALIAS_CRYPTO("aes"); diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c index 50ec333b70e6..1477cfcdbf6b 100644 --- a/arch/x86/crypto/blowfish_glue.c +++ b/arch/x86/crypto/blowfish_glue.c @@ -481,5 +481,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized"); -MODULE_ALIAS("blowfish"); -MODULE_ALIAS("blowfish-asm"); +MODULE_ALIAS_CRYPTO("blowfish"); +MODULE_ALIAS_CRYPTO("blowfish-asm"); diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index 4209a76fcdaa..9a07fafe3831 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 87a041a10f4a..ed38d959add6 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c index c171dcbf192d..5c8b6266a394 100644 --- a/arch/x86/crypto/camellia_glue.c +++ b/arch/x86/crypto/camellia_glue.c @@ -1725,5 +1725,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized"); -MODULE_ALIAS("camellia"); -MODULE_ALIAS("camellia-asm"); +MODULE_ALIAS_CRYPTO("camellia"); +MODULE_ALIAS_CRYPTO("camellia-asm"); diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index e6a3700489b9..f62e9db5a462 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -494,4 +494,4 @@ module_exit(cast5_exit); MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("cast5"); +MODULE_ALIAS_CRYPTO("cast5"); diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index 09f3677393e4..0160f68a57ff 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -611,4 +611,4 @@ module_exit(cast6_exit); MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("cast6"); +MODULE_ALIAS_CRYPTO("cast6"); diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 9d014a74ef96..1937fc1d8763 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini); MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crc32"); -MODULE_ALIAS("crc32-pclmul"); +MODULE_ALIAS_CRYPTO("crc32"); +MODULE_ALIAS_CRYPTO("crc32-pclmul"); diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 6812ad98355c..28640c3d6af7 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang <austin.zhang@intel.com>, Kent Liu <kent.liu@intel.c MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crc32c"); -MODULE_ALIAS("crc32c-intel"); +MODULE_ALIAS_CRYPTO("crc32c"); +MODULE_ALIAS_CRYPTO("crc32c-intel"); diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c index 7845d7fd54c0..b6c67bf30fdf 100644 --- a/arch/x86/crypto/crct10dif-pclmul_glue.c +++ b/arch/x86/crypto/crct10dif-pclmul_glue.c @@ -147,5 +147,5 @@ MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>"); MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ."); MODULE_LICENSE("GPL"); -MODULE_ALIAS("crct10dif"); -MODULE_ALIAS("crct10dif-pclmul"); +MODULE_ALIAS_CRYPTO("crct10dif"); +MODULE_ALIAS_CRYPTO("crct10dif-pclmul"); diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c index 98d7a188f46b..f368ba261739 100644 --- a/arch/x86/crypto/fpu.c +++ b/arch/x86/crypto/fpu.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/crypto.h> #include <asm/i387.h> struct crypto_fpu_ctx { @@ -159,3 +160,5 @@ void __exit crypto_fpu_exit(void) { crypto_unregister_template(&crypto_fpu_tmpl); } + +MODULE_ALIAS_CRYPTO("fpu"); diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index d785cf2c529c..a8d6f69f92a3 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -341,4 +341,4 @@ module_exit(ghash_pclmulqdqni_mod_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("GHASH Message Digest Algorithm, " "acclerated by PCLMULQDQ-NI"); -MODULE_ALIAS("ghash"); +MODULE_ALIAS_CRYPTO("ghash"); diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c index 5e8e67739bb5..399a29d067d6 100644 --- a/arch/x86/crypto/salsa20_glue.c +++ b/arch/x86/crypto/salsa20_glue.c @@ -119,5 +119,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)"); -MODULE_ALIAS("salsa20"); -MODULE_ALIAS("salsa20-asm"); +MODULE_ALIAS_CRYPTO("salsa20"); +MODULE_ALIAS_CRYPTO("salsa20-asm"); diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 2fae489b1524..437e47a4d302 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -558,5 +558,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized"); -MODULE_ALIAS("serpent"); -MODULE_ALIAS("serpent-asm"); +MODULE_ALIAS_CRYPTO("serpent"); +MODULE_ALIAS_CRYPTO("serpent-asm"); diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index ff4870870972..7e217398b4eb 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -617,4 +617,4 @@ module_exit(serpent_exit); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("serpent"); diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index 8c95f8637306..bf025adaea01 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit); MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("serpent"); +MODULE_ALIAS_CRYPTO("serpent"); diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 4a11a9d72451..29e1060e9001 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -237,4 +237,4 @@ module_exit(sha1_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha1"); +MODULE_ALIAS_CRYPTO("sha1"); diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index f248546da1ca..4dc100d82902 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha256"); -MODULE_ALIAS("sha224"); +MODULE_ALIAS_CRYPTO("sha256"); +MODULE_ALIAS_CRYPTO("sha224"); diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 8626b03e83b7..26a5898a6f26 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated"); -MODULE_ALIAS("sha512"); -MODULE_ALIAS("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha384"); diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 4e3c665be129..1ac531ea9bcc 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -579,4 +579,4 @@ module_exit(twofish_exit); MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("twofish"); +MODULE_ALIAS_CRYPTO("twofish"); diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index 0a5202303501..77e06c2da83d 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -96,5 +96,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized"); -MODULE_ALIAS("twofish"); -MODULE_ALIAS("twofish-asm"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-asm"); diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 13e63b3e1dfb..56d8a08ee479 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -495,5 +495,5 @@ module_exit(fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized"); -MODULE_ALIAS("twofish"); -MODULE_ALIAS("twofish-asm"); +MODULE_ALIAS_CRYPTO("twofish"); +MODULE_ALIAS_CRYPTO("twofish-asm"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4299eb05023c..92a2e9333620 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/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 5f1296872aed..1717156f4dd1 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -203,6 +203,7 @@ #define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */ #define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */ +#define X86_FEATURE_VMMCALL (8*32+15) /* Prefer vmmcall to vmcall */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 50d033a8947d..a94b82e8f156 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -251,7 +251,8 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; } -#define _LDT_empty(info) \ +/* This intentionally ignores lm, since 32-bit apps don't have that field. */ +#define LDT_empty(info) \ ((info)->base_addr == 0 && \ (info)->limit == 0 && \ (info)->contents == 0 && \ @@ -261,11 +262,18 @@ static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) (info)->seg_not_present == 1 && \ (info)->useable == 0) -#ifdef CONFIG_X86_64 -#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0)) -#else -#define LDT_empty(info) (_LDT_empty(info)) -#endif +/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ +static inline bool LDT_zero(const struct user_desc *info) +{ + return (info->base_addr == 0 && + info->limit == 0 && + info->contents == 0 && + info->read_exec_only == 0 && + info->seg_32bit == 0 && + info->limit_in_pages == 0 && + info->seg_not_present == 0 && + info->useable == 0); +} static inline void clear_LDT(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/fixmap.h b/arch/x86/include/asm/fixmap.h index 7252cd339175..6762a55b798a 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 cea1c76d49bf..1ac1c009090d 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -368,7 +368,7 @@ static inline void drop_fpu(struct task_struct *tsk) preempt_disable(); tsk->thread.fpu_counter = 0; __drop_fpu(tsk); - clear_used_math(); + clear_stopped_child_used_math(tsk); preempt_enable(); } diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 8e71c7941767..57995f0596a6 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -50,6 +50,32 @@ #define BT_MBI_PCIE_READ 0x00 #define BT_MBI_PCIE_WRITE 0x01 +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Quark read/write opcodes */ +#define QRK_MBI_HBA_READ 0x10 +#define QRK_MBI_HBA_WRITE 0x11 +#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_WRITE 0x11 +#define QRK_MBI_RMU_READ 0x10 +#define QRK_MBI_RMU_WRITE 0x11 +#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_WRITE 0x11 +#define QRK_MBI_MMESRAM_READ 0x12 +#define QRK_MBI_MMESRAM_WRITE 0x13 +#define QRK_MBI_SOC_READ 0x06 +#define QRK_MBI_SOC_WRITE 0x07 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + /** * iosf_mbi_read() - MailBox Interface read command * @port: port indicating subunit being accessed @@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); */ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} +#endif /* CONFIG_IOSF_MBI */ + #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f86dea1ccb5c..829e3088b5a0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -476,6 +476,7 @@ struct kvm_vcpu_arch { u64 mmio_gva; unsigned access; gfn_t mmio_gfn; + u64 mmio_gen; struct kvm_pmu pmu; @@ -979,6 +980,20 @@ 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) @@ -1037,7 +1052,7 @@ 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/kvm_para.h b/arch/x86/include/asm/kvm_para.h index c7678e43465b..e62cf897f781 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -2,6 +2,7 @@ #define _ASM_X86_KVM_PARA_H #include <asm/processor.h> +#include <asm/alternative.h> #include <uapi/asm/kvm_para.h> extern void kvmclock_init(void); @@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void) } #endif /* CONFIG_KVM_GUEST */ -/* This instruction is vmcall. On non-VT architectures, it will generate a - * trap that we will then rewrite to the appropriate instruction. +#ifdef CONFIG_DEBUG_RODATA +#define KVM_HYPERCALL \ + ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL) +#else +/* On AMD processors, vmcall will generate a trap that we will + * then rewrite to the appropriate instruction. */ #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1" +#endif /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall * instruction. The hypervisor may replace it with something else but only the diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index f48b17df4224..3a52ee0e726d 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -20,7 +20,6 @@ #define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define STACKFAULT_STACK 0 #define DOUBLEFAULT_STACK 1 #define NMI_STACK 0 #define DEBUG_STACK 0 diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8de6d9cf3b95..d54d1eebeffe 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -14,12 +14,11 @@ #define IRQ_STACK_ORDER 2 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) -#define STACKFAULT_STACK 1 -#define DOUBLEFAULT_STACK 2 -#define NMI_STACK 3 -#define DEBUG_STACK 4 -#define MCE_STACK 5 -#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ +#define DOUBLEFAULT_STACK 1 +#define NMI_STACK 2 +#define DEBUG_STACK 3 +#define MCE_STACK 4 +#define N_EXCEPTION_STACKS 4 /* hw limit: 7 */ #define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT) #define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1dbf7feb..d869931bde62 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; +extern pte_t level1_fixmap_pgt[512]; extern pgd_t init_level4_pgt[]; #define swapper_pg_dir init_level4_pgt diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index e1940c06ed02..e870ea9232c3 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -144,7 +144,7 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ - _TIF_USER_RETURN_NOTIFY) + _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 58d66fe06b61..b409b17efb48 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void); #ifdef CONFIG_TRACING asmlinkage void trace_page_fault(void); +#define trace_stack_segment stack_segment #define trace_divide_error divide_error #define trace_bounds bounds #define trace_invalid_op invalid_op diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index 2a46ca720afc..2874be9aef0a 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -34,7 +34,7 @@ static inline unsigned int __getcpu(void) native_read_tscp(&p); } else { /* Load per CPU data from GDT */ - asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); + asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG)); } return p; diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h index 46727eb37bfe..6e1aaf73852a 100644 --- a/arch/x86/include/uapi/asm/ldt.h +++ b/arch/x86/include/uapi/asm/ldt.h @@ -28,6 +28,13 @@ struct user_desc { unsigned int seg_not_present:1; unsigned int useable:1; #ifdef __x86_64__ + /* + * Because this bit is not present in 32-bit user code, user + * programs can pass uninitialized values here. Therefore, in + * any context in which a user_desc comes from a 32-bit program, + * the kernel must act as though lm == 0, regardless of the + * actual value. + */ unsigned int lm:1; #endif }; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index 0e79420376eb..990a2fe1588d 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -67,6 +67,7 @@ #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 #define EXIT_REASON_PREEMPTION_TIMER 52 +#define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 #define EXIT_REASON_APIC_WRITE 56 @@ -114,6 +115,7 @@ { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ { EXIT_REASON_INVD, "INVD" }, \ + { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" } #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 7f26c9a70a9e..523f147b2470 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1290,7 +1290,7 @@ void 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); @@ -1387,7 +1387,7 @@ void 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/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c67ffa686064..c005fdd52529 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -508,6 +508,13 @@ static void early_init_amd(struct cpuinfo_x86 *c) } #endif + /* + * This is only needed to tell the kernel whether to use VMCALL + * and VMMCALL. VMMCALL is never executed except under virt, so + * we can set it unconditionally. + */ + set_cpu_cap(c, X86_FEATURE_VMMCALL); + /* F16h erratum 793, CVE-2013-6885 */ if (c->x86 == 0x16 && c->x86_model <= 0xf) { u64 val; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 8e28bf2fc3ef..e6bddd5b9da3 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -144,6 +144,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); static int __init x86_xsave_setup(char *s) { + if (strlen(s)) + return 0; setup_clear_cpu_cap(X86_FEATURE_XSAVE); setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT); setup_clear_cpu_cap(X86_FEATURE_AVX); @@ -1141,7 +1143,7 @@ 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 5cd9bfabd645..66746a880dec 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -153,6 +153,21 @@ static void 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 @@ -368,6 +383,13 @@ static void init_intel(struct cpuinfo_x86 *c) detect_extended_topology(c); l2 = init_intel_cacheinfo(c); + + /* Detect legacy cache sizes if init_intel_cacheinfo did not */ + if (l2 == 0) { + cpu_detect_cache_sizes(c); + l2 = c->x86_cache_size; + } + if (c->cpuid_level > 9) { unsigned eax = cpuid_eax(10); /* Check for version and the number of counters */ @@ -482,6 +504,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size) */ if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0)) size = 256; + + /* + * Intel Quark SoC X1000 contains a 4-way set associative + * 16K cache with a 16 byte cache line and 256 lines per tag + */ + if ((c->x86 == 5) && (c->x86_model == 9)) + size = 16; return size; } #endif @@ -709,7 +738,8 @@ static const struct cpu_dev intel_cpu_dev = { [3] = "OverDrive PODP5V83", [4] = "Pentium MMX", [7] = "Mobile Pentium 75 - 200", - [8] = "Mobile Pentium MMX" + [8] = "Mobile Pentium MMX", + [9] = "Quark SoC X1000", } }, { .family = 6, .model_names = diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c index 617a9e284245..b63773ba1646 100644 --- a/arch/x86/kernel/cpu/microcode/amd_early.c +++ b/arch/x86/kernel/cpu/microcode/amd_early.c @@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size) * load_microcode_amd() to save equivalent cpu table and microcode patches in * kernel heap memory. */ -static void apply_ucode_in_initrd(void *ucode, size_t size) +static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch) { struct equiv_cpu_entry *eq; size_t *cont_sz; u32 *header; u8 *data, **cont; + u8 (*patch)[PATCH_MAX_SIZE]; u16 eq_id = 0; int offset, left; u32 rev, eax, ebx, ecx, edx; @@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); cont_sz = (size_t *)__pa_nodebug(&container_size); cont = (u8 **)__pa_nodebug(&container); + patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch); #else new_rev = &ucode_new_rev; cont_sz = &container_size; cont = &container; + patch = &amd_ucode_patch; #endif data = ucode; @@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size) rev = mc->hdr.patch_id; *new_rev = rev; - /* save ucode patch */ - memcpy(amd_ucode_patch, mc, - min_t(u32, header[1], PATCH_MAX_SIZE)); + if (save_patch) + memcpy(patch, mc, + min_t(u32, header[1], PATCH_MAX_SIZE)); } } @@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void) *data = cp.data; *size = cp.size; - apply_ucode_in_initrd(cp.data, cp.size); + apply_ucode_in_initrd(cp.data, cp.size, true); } #ifdef CONFIG_X86_32 @@ -263,7 +266,7 @@ void load_ucode_amd_ap(void) size_t *usize; void **ucode; - mc = (struct microcode_amd *)__pa(amd_ucode_patch); + mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch); if (mc->hdr.patch_id && mc->hdr.processor_rev_id) { __apply_microcode_amd(mc); return; @@ -275,7 +278,7 @@ void load_ucode_amd_ap(void) if (!*ucode || !*usize) return; - apply_ucode_in_initrd(*ucode, *usize); + apply_ucode_in_initrd(*ucode, *usize, false); } static void __init collect_cpu_sig_on_bsp(void *arg) @@ -339,7 +342,7 @@ void load_ucode_amd_ap(void) * AP has a different equivalence ID than BSP, looks like * mixed-steppings silicon so go through the ucode blob anew. */ - apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size); + apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false); } } #endif @@ -347,7 +350,9 @@ void load_ucode_amd_ap(void) int __init save_microcode_in_initrd_amd(void) { unsigned long cont; + int retval = 0; enum ucode_state ret; + u8 *cont_va; u32 eax; if (!container) @@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void) #ifdef CONFIG_X86_32 get_bsp_sig(); - cont = (unsigned long)container; + cont = (unsigned long)container; + cont_va = __va(container); #else /* * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa(container); + cont_va = container; #endif /* @@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void) if (relocated_ramdisk) container = (u8 *)(__va(relocated_ramdisk) + (cont - boot_params.hdr.ramdisk_image)); + else + container = cont_va; if (ucode_new_rev) pr_info("microcode: updated early to new patch_level=0x%08x\n", @@ -382,7 +391,7 @@ int __init save_microcode_in_initrd_amd(void) ret = load_microcode_amd(eax, container, container_size); if (ret != UCODE_OK) - return -EINVAL; + retval = -EINVAL; /* * This will be freed any msec now, stash patches for the current @@ -391,5 +400,5 @@ int __init save_microcode_in_initrd_amd(void) container = NULL; container_size = 0; - return 0; + return retval; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 832d05a914ba..317c81172c18 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -67,6 +67,7 @@ static struct clocksource hyperv_cs = { .rating = 400, /* use this when running on Hyperv*/ .read = read_hv_clock, .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; static void __init ms_hyperv_init_platform(void) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 79f9f848bee4..fb345c43815f 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event) continue; if (event->attr.config1 & ~er->valid_mask) return -EINVAL; + /* Check if the extra msrs can be safely accessed*/ + if (!er->extra_msr_access) + return -ENXIO; reg->idx = er->idx; reg->config = event->attr.config1; diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 4972c244d0bc..7876c346ed1a 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -293,14 +293,16 @@ struct extra_reg { u64 config_mask; u64 valid_mask; int idx; /* per_xxx->regs[] reg index */ + bool extra_msr_access; }; #define EVENT_EXTRA_REG(e, ms, m, vm, i) { \ - .event = (e), \ - .msr = (ms), \ - .config_mask = (m), \ - .valid_mask = (vm), \ - .idx = EXTRA_REG_##i, \ + .event = (e), \ + .msr = (ms), \ + .config_mask = (m), \ + .valid_mask = (vm), \ + .idx = EXTRA_REG_##i, \ + .extra_msr_access = true, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 1340ebfcb467..d4c0a0e46040 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -2183,6 +2183,41 @@ static void intel_snb_check_microcode(void) } } +/* + * Under certain circumstances, access certain MSR may cause #GP. + * The function tests if the input MSR can be safely accessed. + */ +static bool check_msr(unsigned long msr, u64 mask) +{ + u64 val_old, val_new, val_tmp; + + /* + * Read the current value, change it and read it back to see if it + * matches, this is needed to detect certain hardware emulators + * (qemu/kvm) that don't trap on the MSR access and always return 0s. + */ + if (rdmsrl_safe(msr, &val_old)) + return false; + + /* + * Only change the bits which can be updated by wrmsrl. + */ + val_tmp = val_old ^ mask; + if (wrmsrl_safe(msr, val_tmp) || + rdmsrl_safe(msr, &val_new)) + return false; + + if (val_new != val_tmp) + return false; + + /* Here it's sure that the MSR can be safely accessed. + * Restore the old value and return. + */ + wrmsrl(msr, val_old); + + return true; +} + static __init void intel_sandybridge_quirk(void) { x86_pmu.check_microcode = intel_snb_check_microcode; @@ -2272,7 +2307,8 @@ __init int intel_pmu_init(void) union cpuid10_ebx ebx; struct event_constraint *c; unsigned int unused; - int version; + struct extra_reg *er; + int version, i; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { switch (boot_cpu_data.x86) { @@ -2475,6 +2511,9 @@ __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)); @@ -2575,6 +2614,34 @@ __init int intel_pmu_init(void) } } + /* + * Access LBR MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support LBR MSR + * Check all LBT MSR here. + * Disable LBR access if any LBR MSRs can not be accessed. + */ + if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL)) + x86_pmu.lbr_nr = 0; + for (i = 0; i < x86_pmu.lbr_nr; i++) { + if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) && + check_msr(x86_pmu.lbr_to + i, 0xffffUL))) + x86_pmu.lbr_nr = 0; + } + + /* + * Access extra MSR may cause #GP under certain circumstances. + * E.g. KVM doesn't support offcore event + * Check all extra_regs here. + */ + if (x86_pmu.extra_regs) { + for (er = x86_pmu.extra_regs; er->msr; er++) { + er->extra_msr_access = check_msr(er->msr, 0x1ffUL); + /* Disable LBR select mapping */ + if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access) + x86_pmu.lbr_sel_map = NULL; + } + } + /* Support full width counters using alternative MSR range */ if (x86_pmu.intel_cap.full_width_write) { x86_pmu.max_period = x86_pmu.cntval_mask; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 5ad35ad94d0f..95700e52061d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu) struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu); int phys_id = topology_physical_package_id(cpu); u64 ms; + u64 msr_rapl_power_unit_bits; if (pmu) return 0; @@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; + if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu)); if (!pmu) return -1; @@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu) * * we cache in local PMU instance */ - rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit); - pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL; + pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void) get_online_cpus(); for_each_online_cpu(cpu) { - rapl_cpu_prepare(cpu); + ret = rapl_cpu_prepare(cpu); + if (ret) + goto out; rapl_cpu_init(cpu); } @@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void) hweight32(rapl_cntr_mask), ktime_to_ms(pmu->timer_interval)); +out: put_online_cpus(); return 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 047f540cf3f7..2f9858894d5a 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -2886,6 +2886,17 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event) return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id()); } +/* + * Using uncore_pmu_event_init pmu event_init callback + * as a detection point for uncore events. + */ +static int uncore_pmu_event_init(struct perf_event *event); + +static bool is_uncore_event(struct perf_event *event) +{ + return event->pmu->event_init == uncore_pmu_event_init; +} + static int uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp) { @@ -2900,13 +2911,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b return -EINVAL; n = box->n_events; - box->event_list[n] = leader; - n++; + + if (is_uncore_event(leader)) { + box->event_list[n] = leader; + n++; + } + if (!dogrp) return n; list_for_each_entry(event, &leader->sibling_list, group_entry) { - if (event->state <= PERF_EVENT_STATE_OFF) + if (!is_uncore_event(event) || + event->state <= PERF_EVENT_STATE_OFF) continue; if (n >= max_count) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index addb207dab92..66e274a3d968 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = { [ DEBUG_STACK-1 ] = "#DB", [ NMI_STACK-1 ] = "NMI", [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ STACKFAULT_STACK-1 ] = "#SS", [ MCE_STACK-1 ] = "#MC", #if DEBUG_STKSZ > EXCEPTION_STKSZ [ N_EXCEPTION_STACKS ... diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 03cd2a8f6009..06469ee0f26e 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -542,11 +542,14 @@ ENTRY(ret_from_fork) testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? jz 1f - testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET - jnz int_ret_from_sys_call - - RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET - jmp ret_from_sys_call # go to the SYSRET fastpath + /* + * By the time we get here, we have no idea whether our pt_regs, + * ti flags, and ti status came from the 64-bit SYSCALL fast path, + * the slow path, or one of the ia32entry paths. + * Use int_ret_from_sys_call to return, since it can safely handle + * all of the above. + */ + jmp int_ret_from_sys_call 1: subq $REST_SKIP, %rsp # leave space for volatiles @@ -1053,9 +1056,15 @@ ENTRY(native_iret) jnz native_irq_return_ldt #endif +.global native_irq_return_iret native_irq_return_iret: + /* + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. + */ iretq - _ASM_EXTABLE(native_irq_return_iret, bad_iret) #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: @@ -1083,25 +1092,6 @@ native_irq_return_ldt: jmp native_irq_return_iret #endif - .section .fixup,"ax" -bad_iret: - /* - * The iret traps when the %cs or %ss being restored is bogus. - * We've lost the original trap vector and error code. - * #GPF is the most likely one to get for an invalid selector. - * So pretend we completed the iret and took the #GPF in user mode. - * - * We are now running with the kernel GS after exception recovery. - * But error_entry expects us to have user GS to match the user %cs, - * so swap back. - */ - pushq $0 - - SWAPGS - jmp general_protection - - .previous - /* edi: workmask, edx: work */ retint_careful: CFI_RESTORE_STATE @@ -1147,37 +1137,6 @@ ENTRY(retint_kernel) 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 */ @@ -1379,7 +1338,7 @@ 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 @@ -1549,7 +1508,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ paranoidzeroentry_ist debug do_debug DEBUG_STACK paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +errorentry stack_segment do_stack_segment #ifdef CONFIG_XEN zeroentry xen_debug do_debug zeroentry xen_int3 do_int3 @@ -1659,16 +1618,15 @@ error_sti: /* * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. The exception handlers after iret run with - * kernel gs again, so don't set the user space flag. B stepping K8s - * sometimes report an truncated RIP for IRET exceptions returning to - * compat mode. Check for these here too. + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. */ error_kernelspace: incl %ebx leaq native_irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) - je error_swapgs + je error_bad_iret movl %ecx,%eax /* zero extend */ cmpq %rax,RIP+8(%rsp) je bstep_iret @@ -1679,7 +1637,15 @@ error_kernelspace: bstep_iret: /* Fix truncated RIP */ movq %rcx,RIP+8(%rsp) - jmp error_swapgs + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti CFI_ENDPROC END(error_entry) diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index c3aae6672843..2e97b3cfa6c7 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -25,6 +25,10 @@ #include <asm/iosf_mbi.h> +#define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_BRASWELL 0x2280 +#define PCI_DEVICE_ID_QUARK_X1000 0x0958 + static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -177,6 +181,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) } EXPORT_SYMBOL(iosf_mbi_modify); +bool iosf_mbi_available(void) +{ + /* Mbi isn't hot-pluggable. No remove routine is provided */ + return mbi_pdev; +} +EXPORT_SYMBOL(iosf_mbi_available); + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -193,7 +204,9 @@ static int iosf_mbi_probe(struct pci_dev *pdev, } static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 79a3f9682871..a1f5b1866cbe 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1017,6 +1017,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_IF; trace_hardirqs_off(); regs->ip = (unsigned long)(jp->entry); + + /* + * jprobes use jprobe_return() which skips the normal return + * path of the function, and this messes up the accounting of the + * function graph tracer to get messed up. + * + * Pause function graph tracing while performing the jprobe function. + */ + pause_graph_tracing(); return 1; } @@ -1042,24 +1051,25 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); struct jprobe *jp = container_of(p, struct jprobe, kp); + void *saved_sp = kcb->jprobe_saved_sp; if ((addr > (u8 *) jprobe_return) && (addr < (u8 *) jprobe_return_end)) { - if (stack_addr(regs) != kcb->jprobe_saved_sp) { + if (stack_addr(regs) != saved_sp) { struct pt_regs *saved_regs = &kcb->jprobe_saved_regs; printk(KERN_ERR "current sp %p does not match saved sp %p\n", - stack_addr(regs), kcb->jprobe_saved_sp); + stack_addr(regs), saved_sp); printk(KERN_ERR "Saved registers for jprobe %p\n", jp); show_regs(saved_regs); printk(KERN_ERR "Current registers\n"); show_regs(regs); BUG(); } + /* It's OK to start function graph tracing again */ + unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp), - kcb->jprobes_stack, - MIN_STACK_SIZE(kcb->jprobe_saved_sp)); + memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp)); preempt_enable_no_resched(); return 1; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 713f1b3bad52..0b1e1d5dbc5b 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -280,7 +280,14 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) static void __init paravirt_ops_setup(void) { pv_info.name = "KVM"; - pv_info.paravirt_enabled = 1; + + /* + * KVM isn't paravirt in the sense of paravirt_enabled. A KVM + * guest kernel works like a bare metal kernel with additional + * features, and paravirt_enabled is about features that are + * missing. + */ + pv_info.paravirt_enabled = 0; if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY)) pv_cpu_ops.io_delay = kvm_io_delay; diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index e6041094ff26..c8e98cdc84c2 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -263,7 +263,6 @@ void __init kvmclock_init(void) #endif kvm_get_preset_lpj(); clocksource_register_hz(&kvm_clock, NSEC_PER_SEC); - pv_info.paravirt_enabled = 1; pv_info.name = "KVM"; if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT)) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 9c0280f93d05..e2d26ce9b854 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -286,24 +286,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* - * Reload esp0, LDT and the page table pointer: - */ + /* Reload esp0 and ss1. */ load_sp0(tss, next); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - savesegment(es, prev->es); - if (unlikely(next->es | prev->es)) - loadsegment(es, next->es); - - savesegment(ds, prev->ds); - if (unlikely(next->ds | prev->ds)) - loadsegment(ds, next->ds); - - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -312,41 +297,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) savesegment(fs, fsindex); savesegment(gs, gsindex); + /* + * Load TLS before restoring any segments so that segment loads + * reference the correct GDT entries. + */ load_TLS(next, cpu); /* - * Leave lazy mode, flushing any hypercalls made here. - * This must be done before restoring TLS segments so - * the GDT and LDT are properly updated, and must be - * done before math_state_restore, so the TS bit is up - * to date. + * Leave lazy mode, flushing any hypercalls made here. This + * must be done after loading TLS entries in the GDT but before + * loading segments that might reference them, and and it must + * be done before math_state_restore, so the TS bit is up to + * date. */ arch_end_context_switch(next_p); + /* Switch DS and ES. + * + * Reading them only returns the selectors, but writing them (if + * nonzero) loads the full descriptor from the GDT or LDT. The + * LDT for next is loaded in switch_mm, and the GDT is loaded + * above. + * + * We therefore need to write new values to the segment + * registers on every context switch unless both the new and old + * values are zero. + * + * Note that we don't need to do anything for CS and SS, as + * those are saved and restored as part of pt_regs. + */ + savesegment(es, prev->es); + if (unlikely(next->es | prev->es)) + loadsegment(es, next->es); + + savesegment(ds, prev->ds); + if (unlikely(next->ds | prev->ds)) + loadsegment(ds, next->ds); + /* * Switch FS and GS. * - * Segment register != 0 always requires a reload. Also - * reload when it has changed. When prev process used 64bit - * base always reload to avoid an information leak. + * These are even more complicated than FS and GS: they have + * 64-bit bases are that controlled by arch_prctl. Those bases + * only differ from the values in the GDT or LDT if the selector + * is 0. + * + * Loading the segment register resets the hidden base part of + * the register to 0 or the value from the GDT / LDT. If the + * next base address zero, writing 0 to the segment register is + * much faster than using wrmsr to explicitly zero the base. + * + * The thread_struct.fs and thread_struct.gs values are 0 + * if the fs and gs bases respectively are not overridden + * from the values implied by fsindex and gsindex. They + * are nonzero, and store the nonzero base addresses, if + * the bases are overridden. + * + * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should + * be impossible. + * + * Therefore we need to reload the segment registers if either + * the old or new selector is nonzero, and we need to override + * the base address if next thread expects it to be overridden. + * + * This code is unnecessarily slow in the case where the old and + * new indexes are zero and the new base is nonzero -- it will + * unnecessarily write 0 to the selector before writing the new + * base address. + * + * Note: This all depends on arch_prctl being the only way that + * user code can override the segment base. Once wrfsbase and + * wrgsbase are enabled, most of this code will need to change. */ if (unlikely(fsindex | next->fsindex | prev->fs)) { loadsegment(fs, next->fsindex); + /* - * Check if the user used a selector != 0; if yes - * clear 64bit base, since overloaded base is always - * mapped to the Null selector + * If user code wrote a nonzero value to FS, then it also + * cleared the overridden base address. + * + * XXX: if user code wrote 0 to FS and cleared the base + * address itself, we won't notice and we'll incorrectly + * restore the prior base address next time we reschdule + * the process. */ if (fsindex) prev->fs = 0; } - /* when next process has a 64bit base use it */ if (next->fs) wrmsrl(MSR_FS_BASE, next->fs); prev->fsindex = fsindex; if (unlikely(gsindex | next->gsindex | prev->gs)) { load_gs_index(next->gsindex); + + /* This works (and fails) the same way as fsindex above. */ if (gsindex) prev->gs = 0; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 7461f50d5bb1..0686fe313b3b 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1441,15 +1441,6 @@ 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. @@ -1487,7 +1478,7 @@ 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/reboot.c b/arch/x86/kernel/reboot.c index c752cb43e52f..a6aa91f77654 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -181,6 +181,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { }, }, + /* ASRock */ + { /* Handle problems with rebooting on ASRock Q1900DC-ITX */ + .callback = set_pci_reboot, + .ident = "ASRock Q1900DC-ITX", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"), + DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"), + }, + }, + /* ASUS */ { /* Handle problems with rebooting on ASUS P4S800 */ .callback = set_bios_reboot, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index ce72964b2f46..fa511acff7e6 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -926,11 +926,11 @@ 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 9e5de6813e1f..b88fc86309bc 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -673,6 +673,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * handler too. */ regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|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 395be6d8bbde..682876533ed9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1287,6 +1287,9 @@ 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/tls.c b/arch/x86/kernel/tls.c index f7fec09e3e3a..7fc5e843f247 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -27,6 +27,58 @@ static int get_free_idx(void) return -ESRCH; } +static bool tls_desc_okay(const struct user_desc *info) +{ + /* + * For historical reasons (i.e. no one ever documented how any + * of the segmentation APIs work), user programs can and do + * assume that a struct user_desc that's all zeros except for + * entry_number means "no segment at all". This never actually + * worked. In fact, up to Linux 3.19, a struct user_desc like + * this would create a 16-bit read-write segment with base and + * limit both equal to zero. + * + * That was close enough to "no segment at all" until we + * hardened this function to disallow 16-bit TLS segments. Fix + * it up by interpreting these zeroed segments the way that they + * were almost certainly intended to be interpreted. + * + * The correct way to ask for "no segment at all" is to specify + * a user_desc that satisfies LDT_empty. To keep everything + * working, we accept both. + * + * Note that there's a similar kludge in modify_ldt -- look at + * the distinction between modes 1 and 0x11. + */ + if (LDT_empty(info) || LDT_zero(info)) + return true; + + /* + * espfix is required for 16-bit data segments, but espfix + * only works for LDT segments. + */ + if (!info->seg_32bit) + return false; + + /* Only allow data segments in the TLS array. */ + if (info->contents > 1) + return false; + + /* + * Non-present segments with DPL 3 present an interesting attack + * surface. The kernel should handle such segments correctly, + * but TLS is very difficult to protect in a sandbox, so prevent + * such segments from being created. + * + * If userspace needs to remove a TLS entry, it can still delete + * it outright. + */ + if (info->seg_not_present) + return false; + + return true; +} + static void set_tls_desc(struct task_struct *p, int idx, const struct user_desc *info, int n) { @@ -40,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info)) + if (LDT_empty(info) || LDT_zero(info)) desc->a = desc->b = 0; else fill_ldt(desc, info); @@ -66,6 +118,9 @@ int do_set_thread_area(struct task_struct *p, int idx, if (copy_from_user(&info, u_info, sizeof(info))) return -EFAULT; + if (!tls_desc_okay(&info)) + return -EINVAL; + if (idx == -1) idx = info.entry_number; @@ -192,6 +247,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, { struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES]; const struct user_desc *info; + int i; if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) || (pos % sizeof(struct user_desc)) != 0 || @@ -205,6 +261,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset, else info = infobuf; + for (i = 0; i < count / sizeof(struct user_desc); i++) + if (!tls_desc_okay(info + i)) + return -EINVAL; + set_tls_desc(target, GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)), info, count / sizeof(struct user_desc)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 57409f6b8c62..b1d9002af7db 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -218,32 +218,40 @@ DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) -#ifdef CONFIG_X86_32 DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) -#endif DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) #ifdef CONFIG_X86_64 /* Runs on IST stack */ -dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) -{ - enum ctx_state prev_state; - - prev_state = exception_enter(); - if (notify_die(DIE_TRAP, "stack segment", regs, error_code, - X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { - preempt_conditional_sti(regs); - do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); - preempt_conditional_cli(regs); - } - exception_exit(prev_state); -} - dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_X86_ESPFIX64 + extern unsigned char native_irq_return_iret[]; + + /* + * If IRET takes a non-IST fault on the espfix64 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. + */ + if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + regs->cs == __KERNEL_CS && + regs->ip == (unsigned long)native_irq_return_iret) + { + struct pt_regs *normal_regs = task_pt_regs(current); + + /* Fake a #GP(0) from userspace. */ + memmove(&normal_regs->ip, (void *)regs->sp, 5*8); + normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + regs->ip = (unsigned long)general_protection; + regs->sp = (unsigned long)&normal_regs->orig_ax; + return; + } +#endif + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -357,7 +365,7 @@ exit: * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage notrace __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -376,6 +384,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } + +struct bad_iret_stack { + void *error_entry_ret; + struct pt_regs regs; +}; + +asmlinkage __visible notrace __kprobes +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) +{ + /* + * This is called from entry_64.S early in handling a fault + * caused by a bad iret to user mode. To handle the fault + * correctly, we want move our stack frame to task_pt_regs + * and we want to pretend that the exception came from the + * iret target. + */ + struct bad_iret_stack *new_stack = + container_of(task_pt_regs(current), + struct bad_iret_stack, regs); + + /* Copy the IRET target to the new stack. */ + memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); + + /* Copy the remainder of the stack from the current stack. */ + memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip)); + + BUG_ON(!user_mode_vm(&new_stack->regs)); + return new_stack; +} #endif /* @@ -748,7 +785,7 @@ void __init trap_init(void) set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun); set_intr_gate(X86_TRAP_TS, invalid_TSS); set_intr_gate(X86_TRAP_NP, segment_not_present); - set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK); + set_intr_gate(X86_TRAP_SS, stack_segment); set_intr_gate(X86_TRAP_GP, general_protection); set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug); set_intr_gate(X86_TRAP_MF, coprocessor_error); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e0d1d7a8354e..b20bced0090f 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -618,7 +618,7 @@ static unsigned long quick_pit_calibrate(void) goto success; } } - pr_err("Fast TSC calibration failed\n"); + pr_info("Fast TSC calibration failed\n"); return 0; success: @@ -1173,14 +1173,17 @@ 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/xsave.c b/arch/x86/kernel/xsave.c index a4b451c6addf..7a09aca4b33a 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; } @@ -377,7 +375,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) * thread's fpu state, reconstruct fxstate from the fsave * header. Sanitize the copied state etc. */ - struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave; + struct fpu *fpu = &tsk->thread.fpu; struct user_i387_ia32_struct env; int err = 0; @@ -391,16 +389,20 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) */ drop_fpu(tsk); - if (__copy_from_user(xsave, buf_fx, state_size) || + if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) || __copy_from_user(&env, buf, sizeof(env))) { + fpu_finit(fpu); err = -1; } else { sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only); - set_used_math(); } - if (use_eager_fpu()) + set_used_math(); + if (use_eager_fpu()) { + preempt_disable(); math_state_restore(); + preempt_enable(); + } return err; } else { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 7bff3e2a7a11..09651d4a9038 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -498,11 +498,6 @@ 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); @@ -576,6 +571,38 @@ 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; @@ -1958,13 +1985,15 @@ 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); @@ -1996,10 +2025,14 @@ 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) @@ -2277,7 +2310,7 @@ 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; @@ -2293,6 +2326,9 @@ 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); @@ -2310,6 +2346,9 @@ 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; @@ -2318,8 +2357,8 @@ 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; } @@ -2858,10 +2897,13 @@ 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); } @@ -2893,11 +2935,12 @@ 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); @@ -3227,20 +3270,24 @@ 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) @@ -4599,7 +4646,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) goto done; } - ctxt->dst.orig_val = ctxt->dst.val; + /* Copy full 64-bit value for CMPXCHG8B. */ + ctxt->dst.orig_val64 = ctxt->dst.val64; special_insn: @@ -4637,7 +4685,7 @@ 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; @@ -4666,7 +4714,7 @@ 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 */ @@ -4786,7 +4834,7 @@ 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 518d86471b76..298781d4cfb4 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -262,8 +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) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2790d688c780..32e5329ab0b6 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3156,7 +3156,7 @@ 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; @@ -4379,7 +4379,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) * zap all shadow pages. */ if (unlikely(kvm_current_mmio_generation(kvm) == 0)) { - printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); + printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 945b426c2550..78cfcb348f8a 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -3213,7 +3213,7 @@ 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 { @@ -3495,9 +3495,9 @@ 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); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8123dc70b443..8b75f5f90a96 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -441,6 +441,7 @@ struct vcpu_vmx { #endif int gs_ldt_reload_needed; int fs_reload_needed; + unsigned long vmcs_host_cr4; /* May not match real cr4 */ } host_state; struct { int vm86_active; @@ -2320,12 +2321,12 @@ static __init void nested_vmx_setup_ctls_msrs(void) nested_vmx_secondary_ctls_low = 0; nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | - SECONDARY_EXEC_UNRESTRICTED_GUEST | SECONDARY_EXEC_WBINVD_EXITING; if (enable_ept) { /* nested EPT: emulate EPT also to L1 */ - nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; + nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT | + SECONDARY_EXEC_UNRESTRICTED_GUEST; nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT | VMX_EPT_INVEPT_BIT; @@ -2582,12 +2583,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: 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; } @@ -4162,11 +4166,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx) u32 low32, high32; unsigned long tmpl; struct desc_ptr dt; + unsigned long cr4; vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */ - vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */ vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */ + /* Save the most likely value for this task's CR4 in the VMCS. */ + cr4 = read_cr4(); + vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */ + vmx->host_state.vmcs_host_cr4 = cr4; + vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */ #ifdef CONFIG_X86_64 /* @@ -5169,7 +5178,7 @@ 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; @@ -6441,6 +6450,12 @@ static int handle_invept(struct kvm_vcpu *vcpu) return 1; } +static int handle_invvpid(struct kvm_vcpu *vcpu) +{ + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -6486,6 +6501,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_INVEPT] = handle_invept, + [EXIT_REASON_INVVPID] = handle_invvpid, }; static const int kvm_vmx_max_exit_handlers = @@ -6719,7 +6735,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: - case EXIT_REASON_INVEPT: + case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID: /* * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! @@ -6884,10 +6900,10 @@ 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) @@ -7186,7 +7202,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long debugctlmsr; + unsigned long debugctlmsr, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) @@ -7207,6 +7223,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); + cr4 = read_cr4(); + if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) { + vmcs_writel(HOST_CR4, cr4); + vmx->host_state.vmcs_host_cr4 = cr4; + } + /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fc39a0cdfd03..52b2f778f329 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -225,20 +225,25 @@ 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); @@ -946,7 +951,6 @@ 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. @@ -954,8 +958,34 @@ 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 @@ -1177,21 +1207,22 @@ void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 bool vcpus_matched; - bool do_request = false; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == atomic_read(&vcpu->kvm->online_vcpus)); - if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC) - if (!ka->use_master_clock) - do_request = 1; - - if (!vcpus_matched && ka->use_master_clock) - do_request = 1; - - if (do_request) + /* + * Once the masterclock is enabled, always perform request in + * order to update it. + * + * In order to enable masterclock, the host clocksource must be TSC + * and the vcpus need to have matched TSCs. When that happens, + * perform request to enable masterclock. + */ + if (ka->use_master_clock || + (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -4881,7 +4912,7 @@ 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; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 8da5823bcde6..21ea4fc91b5b 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; diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 207d9aef662d..448ee8912d9b 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -172,7 +172,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, */ if (pmd_none(pmd) || pmd_trans_splitting(pmd)) return 0; - if (unlikely(pmd_large(pmd))) { + if (unlikely(pmd_large(pmd) || !pmd_present(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8b977ebf9388..006cc914994b 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -66,9 +66,15 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, int write) return ERR_PTR(-EINVAL); } +/* + * pmd_huge() returns 1 if @pmd is hugetlb related entry, that is normal + * hugetlb entry or non-present (migration or hwpoisoned) hugetlb entry. + * Otherwise, returns 0. + */ int pmd_huge(pmd_t pmd) { - return !!(pmd_val(pmd) & _PAGE_PSE); + return !pmd_none(pmd) && + (pmd_val(pmd) & (_PAGE_PRESENT|_PAGE_PSE)) != _PAGE_PRESENT; } int pud_huge(pud_t pud) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c5959a..2308a401a1c5 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1110,7 +1110,7 @@ void mark_rodata_ro(void) unsigned long end = (unsigned long) &__end_rodata_hpage_align; unsigned long text_end = PFN_ALIGN(&__stop___ex_table); unsigned long rodata_end = PFN_ALIGN(&__end_rodata); - unsigned long all_end = PFN_ALIGN(&_end); + unsigned long all_end; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -1121,7 +1121,16 @@ void mark_rodata_ro(void) /* * The rodata/data/bss/brk section (but not the kernel text!) * should also be not-executable. + * + * We align all_end to PMD_SIZE because the existing mapping + * is a full PMD. If we would align _brk_end to PAGE_SIZE we + * split the PMD and the reminder between _brk_end and the end + * of the PMD will remain mapped executable. + * + * Any PMD which was setup after the one which covers _brk_end + * has been zapped already via cleanup_highmem(). */ + all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT); rodata_test(); diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 25e7e1372bb2..3601ff284b92 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -35,12 +35,12 @@ struct __read_mostly va_alignment va_align = { .flags = -1, }; -static unsigned int stack_maxrandom_size(void) +static unsigned long stack_maxrandom_size(void) { - unsigned int max = 0; + unsigned long max = 0; if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT; + max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT; } return max; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3488689e301..fed892de9baf 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -405,7 +405,7 @@ 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/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314abd144..0004ac72dbdd 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 981c2dbd72cc..88f143d9754e 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -448,6 +448,22 @@ static const struct dmi_system_id pciprobe_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"), }, }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"), + }, + }, + { + .callback = set_scan_all, + .ident = "Stratus/NEC ftServer", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"), + }, + }, {} }; diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index abb81b0ad83f..2b42f0a6d381 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -68,8 +68,6 @@ 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}, @@ -79,15 +77,6 @@ static __initdata efi_config_table_type_t arch_tables[] = { u64 efi_setup; /* efi setup_data physical address */ -/* - * 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); - static bool __initdata disable_runtime = false; static int __init setup_noefi(char *arg) { @@ -456,7 +445,7 @@ 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; @@ -589,6 +578,8 @@ static int __init efi_systab_init(void *phys) efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + return 0; } @@ -624,6 +615,8 @@ static int __init efi_runtime_init(void) efi.get_time = phys_efi_get_time; early_iounmap(runtime, sizeof(efi_runtime_services_t)); + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return 0; } @@ -641,6 +634,8 @@ static int __init efi_memmap_init(void) if (add_efi_memmap) do_add_efi_memmap(); + set_bit(EFI_MEMMAP, &efi.flags); + return 0; } @@ -723,7 +718,7 @@ 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; @@ -751,8 +746,6 @@ void __init efi_init(void) if (efi_config_init(arch_tables)) return; - set_bit(EFI_CONFIG_TABLES, &x86_efi_facility); - /* * Note: We currently don't support runtime services on an EFI * that doesn't match the kernel 32/64-bit mode. @@ -763,12 +756,11 @@ void __init efi_init(void) else { if (disable_runtime || efi_runtime_init()) return; - set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); } if (efi_memmap_init()) return; - set_bit(EFI_MEMMAP, &x86_efi_facility); + set_bit(EFI_MEMMAP, &efi.flags); print_efi_memmap(); } @@ -1263,7 +1255,7 @@ static int __init parse_efi_cmdline(char *str) str++; if (!strncmp(str, "old_map", 7)) - set_bit(EFI_OLD_MEMMAP, &x86_efi_facility); + set_bit(EFI_OLD_MEMMAP, &efi.flags); return 0; } diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 7f517ca19d32..ec255a1646d2 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -322,6 +322,7 @@ 313 common finit_module sys_finit_module 314 common sched_setattr sys_sched_setattr 315 common sched_getattr sys_sched_getattr +316 common renameat2 sys_renameat2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/tools/calc_run_size.sh b/arch/x86/tools/calc_run_size.sh new file mode 100644 index 000000000000..1a4c17bb3910 --- /dev/null +++ b/arch/x86/tools/calc_run_size.sh @@ -0,0 +1,42 @@ +#!/bin/sh +# +# Calculate the amount of space needed to run the kernel, including room for +# the .bss and .brk sections. +# +# Usage: +# objdump -h a.out | sh calc_run_size.sh + +NUM='\([0-9a-fA-F]*[ \t]*\)' +OUT=$(sed -n 's/^[ \t0-9]*.b[sr][sk][ \t]*'"$NUM$NUM$NUM$NUM"'.*/\1\4/p') +if [ -z "$OUT" ] ; then + echo "Never found .bss or .brk file offset" >&2 + exit 1 +fi + +OUT=$(echo ${OUT# }) +sizeA=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +offsetA=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +sizeB=$(printf "%d" 0x${OUT%% *}) +OUT=${OUT#* } +offsetB=$(printf "%d" 0x${OUT%% *}) + +run_size=$(( $offsetA + $sizeA + $sizeB )) + +# BFD linker shows the same file offset in ELF. +if [ "$offsetA" -ne "$offsetB" ] ; then + # Gold linker shows them as consecutive. + endB=$(( $offsetB + $sizeB )) + if [ "$endB" != "$run_size" ] ; then + printf "sizeA: 0x%x\n" $sizeA >&2 + printf "offsetA: 0x%x\n" $offsetA >&2 + printf "sizeB: 0x%x\n" $sizeB >&2 + printf "offsetB: 0x%x\n" $offsetB >&2 + echo ".bss and .brk are non-contiguous" >&2 + exit 1 + fi +fi + +printf "%d\n" $run_size +exit 0 diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c index 531d4269e2e3..bd16d6c370ec 100644 --- a/arch/x86/um/sys_call_table_32.c +++ b/arch/x86/um/sys_call_table_32.c @@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index f2f0723070ca..95783087f0d3 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -46,7 +46,7 @@ typedef void (*sys_call_ptr_t)(void); extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[] __cacheline_aligned = { +const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S index 31776d0efc8c..d7ec4e251c0a 100644 --- a/arch/x86/vdso/vdso32/sigreturn.S +++ b/arch/x86/vdso/vdso32/sigreturn.S @@ -17,6 +17,7 @@ .text .globl __kernel_sigreturn .type __kernel_sigreturn,@function + nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */ ALIGN __kernel_sigreturn: .LSTART_sigreturn: diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 431e87544411..ab6ba35a9357 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -117,30 +117,45 @@ subsys_initcall(init_vdso); struct linux_binprm; -/* Put the vdso above the (randomized) stack with another randomized offset. - This way there is no hole in the middle of address space. - To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits */ +/* + * Put the vdso above the (randomized) stack with another randomized + * offset. This way there is no hole in the middle of address space. + * To save memory make sure it is still in the same PTE as the stack + * top. This doesn't give that many random bits. + * + * Note that this algorithm is imperfect: the distribution of the vdso + * start address within a PMD is biased toward the end. + * + * Only used for the 64-bit and x32 vdsos. + */ static unsigned long vdso_addr(unsigned long start, unsigned len) { unsigned long addr, end; unsigned offset; - end = (start + PMD_SIZE - 1) & PMD_MASK; + + /* + * Round up the start address. It can start out unaligned as a result + * of stack start randomization. + */ + start = PAGE_ALIGN(start); + + /* Round the lowest possible end address up to a PMD boundary. */ + end = (start + len + PMD_SIZE - 1) & PMD_MASK; if (end >= TASK_SIZE_MAX) end = TASK_SIZE_MAX; end -= len; - /* This loses some more bits than a modulo, but is cheaper */ - offset = get_random_int() & (PTRS_PER_PTE - 1); - addr = start + (offset << PAGE_SHIFT); - if (addr >= end) - addr = end; + + if (end > start) { + offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); + addr = start + (offset << PAGE_SHIFT); + } else { + addr = start; + } /* - * page-align it here so that get_unmapped_area doesn't - * align it wrongfully again to the next page. addr can come in 4K - * unaligned here as a result of stack start randomization. + * Forcibly align the final address in case we have a hardware + * issue that requires alignment for performance reasons. */ - addr = PAGE_ALIGN(addr); addr = align_vdso_addr(addr); return addr; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 2423ef04ffea..c83da6fb2dee 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end, * * We can construct this by grafting the Xen provided pagetable into * head_64.S's preconstructed pagetables. We copy the Xen L2's into - * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt. This - * means that only the kernel has a physical mapping to start with - - * but that's enough to get __va working. We need to fill in the rest - * of the physical mapping once some sort of allocator has been set - * up. - * NOTE: for PVH, the page tables are native. + * level2_ident_pgt, and level2_kernel_pgt. This means that only the + * kernel has a physical mapping to start with - but that's enough to + * get __va working. We need to fill in the rest of the physical + * mapping once some sort of allocator has been set up. NOTE: for + * PVH, the page tables are native. */ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) { @@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* L3_i[0] -> level2_ident_pgt */ convert_pfn_mfn(level3_ident_pgt); /* L3_k[510] -> level2_kernel_pgt - * L3_i[511] -> level2_fixmap_pgt */ + * L3_k[511] -> level2_fixmap_pgt */ convert_pfn_mfn(level3_kernel_pgt); + + /* L3_k[511][506] -> level1_fixmap_pgt */ + convert_pfn_mfn(level2_fixmap_pgt); } /* We get [511][511] and have Xen's version of level2_kernel_pgt */ l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd); @@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][511] have entries that point to the same + * Both L4[272][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you * are OK - which is what cleanup_highmap does) */ copy_page(level2_ident_pgt, l2); - /* Graft it onto L4[511][511] */ + /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); - /* Get [511][510] and graft that in level2_fixmap_pgt */ - l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd); - l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud); - copy_page(level2_fixmap_pgt, l2); - /* Note that we don't do anything with level1_fixmap_pgt which - * we don't need. */ if (!xen_feature(XENFEAT_auto_translated_physmap)) { /* Make pagetable pieces RO */ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO); @@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO); set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO); set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO); + set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO); /* Pin down new L4 */ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE, |