diff options
| author | Dave Airlie <airlied@redhat.com> | 2015-04-20 04:32:26 +0300 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2015-04-20 06:05:20 +0300 |
| commit | 2c33ce009ca2389dbf0535d0672214d09738e35e (patch) | |
| tree | 6186a6458c3c160385d794a23eaf07c786a9e61b /arch/x86 | |
| parent | cec32a47010647e8b0603726ebb75b990a4057a4 (diff) | |
| parent | 09d51602cf84a1264946711dd4ea0dddbac599a1 (diff) | |
| download | linux-2c33ce009ca2389dbf0535d0672214d09738e35e.tar.xz | |
Merge Linus master into drm-next
The merge is clean, but the arm build fails afterwards,
due to API changes in the regulator tree.
I've included the patch into the merge to fix the build.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Diffstat (limited to 'arch/x86')
262 files changed, 9763 insertions, 5382 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b7d31ca55187..6049d587599e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -87,7 +87,7 @@ config X86 select HAVE_ARCH_KMEMCHECK select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP select HAVE_USER_RETURN_NOTIFIER - select ARCH_BINFMT_ELF_RANDOMIZE_PIE + select ARCH_HAS_ELF_RANDOMIZE select HAVE_ARCH_JUMP_LABEL select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select SPARSE_IRQ @@ -99,6 +99,7 @@ config X86 select IRQ_FORCED_THREADING select HAVE_BPF_JIT if X86_64 select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_HUGE_VMAP if X86_64 || (X86_32 && X86_PAE) select ARCH_HAS_SG_CHAIN select CLKEVT_I8253 select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -177,7 +178,7 @@ config SBUS config NEED_DMA_MAP_STATE def_bool y - depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG + depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB config NEED_SG_DMA_LENGTH def_bool y @@ -235,12 +236,10 @@ config ARCH_WANT_GENERAL_HUGETLB def_bool y config ZONE_DMA32 - bool - default X86_64 + def_bool y if X86_64 config AUDIT_ARCH - bool - default X86_64 + def_bool y if X86_64 config ARCH_SUPPORTS_OPTIMIZED_INLINING def_bool y @@ -279,6 +278,12 @@ config ARCH_SUPPORTS_UPROBES config FIX_EARLYCON_MEM def_bool y +config PGTABLE_LEVELS + int + default 4 if X86_64 + default 3 if X86_PAE + default 2 + source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -716,17 +721,6 @@ endif #HYPERVISOR_GUEST config NO_BOOTMEM def_bool y -config MEMTEST - bool "Memtest" - ---help--- - This option adds a kernel parameter 'memtest', which allows memtest - to be set. - memtest=0, mean disabled; -- default - memtest=1, mean do 1 test pattern; - ... - memtest=4, mean do 4 test patterns. - If you are unsure how to answer this question, answer N. - source "arch/x86/Kconfig.cpu" config HPET_TIMER @@ -891,7 +885,8 @@ config UP_LATE_INIT depends on !SMP && X86_LOCAL_APIC config X86_UP_APIC - bool "Local APIC support on uniprocessors" + bool "Local APIC support on uniprocessors" if !PCI_MSI + default PCI_MSI depends on X86_32 && !SMP && !X86_32_NON_STANDARD ---help--- A local APIC (Advanced Programmable Interrupt Controller) is an @@ -903,10 +898,6 @@ 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 @@ -925,8 +916,8 @@ config X86_LOCAL_APIC select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ config X86_IO_APIC - def_bool X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC - depends on X86_LOCAL_APIC + def_bool y + depends on X86_LOCAL_APIC || X86_UP_IOAPIC select IRQ_DOMAIN config X86_REROUTE_FOR_BROKEN_BOOT_IRQS @@ -1145,10 +1136,10 @@ config MICROCODE_OLD_INTERFACE depends on MICROCODE config MICROCODE_INTEL_EARLY - def_bool n + bool config MICROCODE_AMD_EARLY - def_bool n + bool config MICROCODE_EARLY bool "Early load microcode" @@ -1300,14 +1291,14 @@ config ARCH_DMA_ADDR_T_64BIT def_bool y depends on X86_64 || HIGHMEM64G -config DIRECT_GBPAGES - bool "Enable 1GB pages for kernel pagetables" if EXPERT - default y - depends on X86_64 +config X86_DIRECT_GBPAGES + def_bool y + depends on X86_64 && !DEBUG_PAGEALLOC && !KMEMCHECK ---help--- - Allow the kernel linear mapping to use 1GB pages on CPUs that - support it. This can improve the kernel's performance a tiny bit by - reducing TLB pressure. If in doubt, say "Y". + Certain kernel features effectively disable kernel + linear 1 GB mappings (even if the CPU otherwise + supports them), so don't confuse the user by printing + that we have them enabled. # Common NUMA Features config NUMA @@ -1430,6 +1421,16 @@ config ILLEGAL_POINTER_VALUE source "mm/Kconfig" +config X86_PMEM_LEGACY + bool "Support non-standard NVDIMMs and ADR protected memory" + help + Treat memory marked using the non-standard e820 type of 12 as used + by the Intel Sandy Bridge-EP reference BIOS as protected memory. + The kernel will offer these regions to the 'pmem' driver so + they can be used for persistent storage. + + Say Y if unsure. + config HIGHPTE bool "Allocate 3rd-level pagetables from highmem" depends on HIGHMEM @@ -1747,14 +1748,11 @@ config KEXEC_VERIFY_SIG depends on KEXEC_FILE ---help--- This option makes kernel signature verification mandatory for - kexec_file_load() syscall. If kernel is signature can not be - verified, kexec_file_load() will fail. - - This option enforces signature verification at generic level. - One needs to enable signature verification for type of kernel - image being loaded to make sure it works. For example, enable - bzImage signature verification option to be able to load and - verify signatures of bzImage. Otherwise kernel loading will fail. + the kexec_file_load() syscall. + + In addition to that option, you need to enable signature + verification for the corresponding kernel image type being + loaded in order for this to work. config KEXEC_BZIMAGE_VERIFY_SIG bool "Enable bzImage signature verification support" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5ba2d9ce82dc..2fda005bb334 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -63,7 +63,7 @@ ifeq ($(CONFIG_X86_32),y) $(call cc-option,-fno-unit-at-a-time)) # CPU-specific tuning. Anything which can be shared with UML should go here. - include $(srctree)/arch/x86/Makefile_32.cpu + include arch/x86/Makefile_32.cpu KBUILD_CFLAGS += $(cflags-y) # temporary until string.h is fixed diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um index 95eba554baf9..5b7e898ffd9a 100644 --- a/arch/x86/Makefile.um +++ b/arch/x86/Makefile.um @@ -18,7 +18,7 @@ LDS_EXTRA := -Ui386 export LDS_EXTRA # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y. -include $(srctree)/arch/x86/Makefile_32.cpu +include arch/x86/Makefile_32.cpu # prevent gcc from keeping the stack 16 byte aligned. Taken from i386. cflags-y += $(call cc-option,-mpreferred-stack-boundary=2) diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c index bb1376381985..d7b1f655b3ef 100644 --- a/arch/x86/boot/compressed/aslr.c +++ b/arch/x86/boot/compressed/aslr.c @@ -295,7 +295,8 @@ static unsigned long find_random_addr(unsigned long minimum, return slots_fetch_random(); } -unsigned char *choose_kernel_location(unsigned char *input, +unsigned char *choose_kernel_location(struct boot_params *boot_params, + unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size) @@ -315,6 +316,8 @@ unsigned char *choose_kernel_location(unsigned char *input, } #endif + boot_params->hdr.loadflags |= KASLR_FLAG; + /* Record the various known unsafe memory ranges. */ mem_avoid_init((unsigned long)input, input_size, (unsigned long)output, output_size); diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 1d7fbbcc196d..8ef964ddc18e 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -29,6 +29,7 @@ #include <asm/page_types.h> #include <asm/boot.h> #include <asm/asm-offsets.h> +#include <asm/bootparam.h> __HEAD ENTRY(startup_32) @@ -102,7 +103,7 @@ preferred_addr: * Test KEEP_SEGMENTS flag to see if the bootloader is asking * us to not reload segments */ - testb $(1<<6), BP_loadflags(%esi) + testb $KEEP_SEGMENTS, BP_loadflags(%esi) jnz 1f cli diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 6b1766c6c082..b0c0d16ef58d 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -31,6 +31,7 @@ #include <asm/msr.h> #include <asm/processor-flags.h> #include <asm/asm-offsets.h> +#include <asm/bootparam.h> __HEAD .code32 @@ -46,7 +47,7 @@ ENTRY(startup_32) * Test KEEP_SEGMENTS flag to see if the bootloader is asking * us to not reload segments */ - testb $(1<<6), BP_loadflags(%esi) + testb $KEEP_SEGMENTS, BP_loadflags(%esi) jnz 1f cli @@ -164,7 +165,7 @@ ENTRY(startup_32) /* After gdt is loaded */ xorl %eax, %eax lldt %ax - movl $0x20, %eax + movl $__BOOT_TSS, %eax ltr %ax /* diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a950864a64da..a107b935e22f 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -377,6 +377,9 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, real_mode = rmode; + /* Clear it for solely in-kernel use */ + real_mode->hdr.loadflags &= ~KASLR_FLAG; + sanitize_boot_params(real_mode); if (real_mode->screen_info.orig_video_mode == 7) { @@ -401,7 +404,7 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, * 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 = choose_kernel_location(real_mode, input_data, input_len, output, output_len > run_size ? output_len : run_size); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 04477d68403f..89dd0d78013a 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -57,7 +57,8 @@ int cmdline_find_option_bool(const char *option); #if CONFIG_RANDOMIZE_BASE /* aslr.c */ -unsigned char *choose_kernel_location(unsigned char *input, +unsigned char *choose_kernel_location(struct boot_params *boot_params, + unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size); @@ -65,7 +66,8 @@ unsigned char *choose_kernel_location(unsigned char *input, bool has_cpuflag(int flag); #else static inline -unsigned char *choose_kernel_location(unsigned char *input, +unsigned char *choose_kernel_location(struct boot_params *boot_params, + unsigned char *input, unsigned long input_size, unsigned char *output, unsigned long output_size) diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 493f3fd9f139..318b8465d302 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -30,7 +30,7 @@ int strcmp(const char *str1, const char *str2) int delta = 0; while (*s1 || *s2) { - delta = *s2 - *s1; + delta = *s1 - *s2; if (delta) return delta; s1++; diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c index 748e8d06290a..aa8a96b052e3 100644 --- a/arch/x86/boot/video-mode.c +++ b/arch/x86/boot/video-mode.c @@ -22,10 +22,8 @@ /* * Common variables */ -int adapter; /* 0=CGA/MDA/HGC, 1=EGA, 2=VGA+ */ -u16 video_segment; +int adapter; /* 0=CGA/MDA/HGC, 1=EGA, 2=VGA+ */ int force_x, force_y; /* Don't query the BIOS for cols/rows */ - int do_restore; /* Screen contents changed during mode flip */ int graphic_mode; /* Graphic mode with linear frame buffer */ diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c index 43eda284d27f..05111bb8d018 100644 --- a/arch/x86/boot/video.c +++ b/arch/x86/boot/video.c @@ -17,6 +17,8 @@ #include "video.h" #include "vesa.h" +static u16 video_segment; + static void store_cursor_position(void) { struct biosregs ireg, oreg; diff --git a/arch/x86/boot/video.h b/arch/x86/boot/video.h index 0bb25491262d..b54e0328c449 100644 --- a/arch/x86/boot/video.h +++ b/arch/x86/boot/video.h @@ -91,7 +91,6 @@ int mode_defined(u16 mode); /* video.c */ #define ADAPTER_VGA 2 extern int adapter; -extern u16 video_segment; extern int force_x, force_y; /* Don't query the BIOS for cols/rows */ extern int do_restore; /* Restore screen contents */ extern int graphic_mode; /* Graphics mode with linear frame buffer */ diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 419819d6dab3..aaa1118bf01e 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -248,7 +248,7 @@ CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_EHCI_TT_NEWSCHED=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_PRINTER=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 4c311ddd973b..315b86106572 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -243,7 +243,7 @@ CONFIG_USB=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_TT_NEWSCHED is not set +CONFIG_USB_EHCI_TT_NEWSCHED=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_UHCI_HCD=y CONFIG_USB_PRINTER=y diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 54f60ab41c63..112cefacf2af 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -797,7 +797,9 @@ static int rfc4106_init(struct crypto_tfm *tfm) PTR_ALIGN((u8 *)crypto_tfm_ctx(tfm), AESNI_ALIGN); struct crypto_aead *cryptd_child; struct aesni_rfc4106_gcm_ctx *child_ctx; - cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni", 0, 0); + cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni", + CRYPTO_ALG_INTERNAL, + CRYPTO_ALG_INTERNAL); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); @@ -890,15 +892,12 @@ out_free_ablkcipher: return ret; } -static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, - unsigned int key_len) +static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key, + unsigned int key_len) { int ret = 0; - struct crypto_tfm *tfm = crypto_aead_tfm(parent); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); - struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); - struct aesni_rfc4106_gcm_ctx *child_ctx = - aesni_rfc4106_gcm_ctx_get(cryptd_child); + struct crypto_tfm *tfm = crypto_aead_tfm(aead); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(aead); u8 *new_key_align, *new_key_mem = NULL; if (key_len < 4) { @@ -943,20 +942,31 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, goto exit; } ret = rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); - memcpy(child_ctx, ctx, sizeof(*ctx)); exit: kfree(new_key_mem); return ret; } -/* This is the Integrity Check Value (aka the authentication tag length and can - * be 8, 12 or 16 bytes long. */ -static int rfc4106_set_authsize(struct crypto_aead *parent, - unsigned int authsize) +static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key, + unsigned int key_len) { struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); - struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); + struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm); + struct aesni_rfc4106_gcm_ctx *c_ctx = aesni_rfc4106_gcm_ctx_get(child); + struct cryptd_aead *cryptd_tfm = ctx->cryptd_tfm; + int ret; + ret = crypto_aead_setkey(child, key, key_len); + if (!ret) { + memcpy(ctx, c_ctx, sizeof(*ctx)); + ctx->cryptd_tfm = cryptd_tfm; + } + return ret; +} + +static int common_rfc4106_set_authsize(struct crypto_aead *aead, + unsigned int authsize) +{ switch (authsize) { case 8: case 12: @@ -965,51 +975,23 @@ static int rfc4106_set_authsize(struct crypto_aead *parent, default: return -EINVAL; } - crypto_aead_crt(parent)->authsize = authsize; - crypto_aead_crt(cryptd_child)->authsize = authsize; + crypto_aead_crt(aead)->authsize = authsize; return 0; } -static int rfc4106_encrypt(struct aead_request *req) -{ - int ret; - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - - if (!irq_fpu_usable()) { - struct aead_request *cryptd_req = - (struct aead_request *) aead_request_ctx(req); - memcpy(cryptd_req, req, sizeof(*req)); - aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); - return crypto_aead_encrypt(cryptd_req); - } else { - struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); - kernel_fpu_begin(); - ret = cryptd_child->base.crt_aead.encrypt(req); - kernel_fpu_end(); - return ret; - } -} - -static int rfc4106_decrypt(struct aead_request *req) +/* This is the Integrity Check Value (aka the authentication tag length and can + * be 8, 12 or 16 bytes long. */ +static int rfc4106_set_authsize(struct crypto_aead *parent, + unsigned int authsize) { + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(parent); + struct crypto_aead *child = cryptd_aead_child(ctx->cryptd_tfm); int ret; - struct crypto_aead *tfm = crypto_aead_reqtfm(req); - struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); - if (!irq_fpu_usable()) { - struct aead_request *cryptd_req = - (struct aead_request *) aead_request_ctx(req); - memcpy(cryptd_req, req, sizeof(*req)); - aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); - return crypto_aead_decrypt(cryptd_req); - } else { - struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm); - kernel_fpu_begin(); - ret = cryptd_child->base.crt_aead.decrypt(req); - kernel_fpu_end(); - return ret; - } + ret = crypto_aead_setauthsize(child, authsize); + if (!ret) + crypto_aead_crt(parent)->authsize = authsize; + return ret; } static int __driver_rfc4106_encrypt(struct aead_request *req) @@ -1185,6 +1167,78 @@ static int __driver_rfc4106_decrypt(struct aead_request *req) } return retval; } + +static int rfc4106_encrypt(struct aead_request *req) +{ + int ret; + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + + if (!irq_fpu_usable()) { + struct aead_request *cryptd_req = + (struct aead_request *) aead_request_ctx(req); + + memcpy(cryptd_req, req, sizeof(*req)); + aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + ret = crypto_aead_encrypt(cryptd_req); + } else { + kernel_fpu_begin(); + ret = __driver_rfc4106_encrypt(req); + kernel_fpu_end(); + } + return ret; +} + +static int rfc4106_decrypt(struct aead_request *req) +{ + int ret; + struct crypto_aead *tfm = crypto_aead_reqtfm(req); + struct aesni_rfc4106_gcm_ctx *ctx = aesni_rfc4106_gcm_ctx_get(tfm); + + if (!irq_fpu_usable()) { + struct aead_request *cryptd_req = + (struct aead_request *) aead_request_ctx(req); + + memcpy(cryptd_req, req, sizeof(*req)); + aead_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + ret = crypto_aead_decrypt(cryptd_req); + } else { + kernel_fpu_begin(); + ret = __driver_rfc4106_decrypt(req); + kernel_fpu_end(); + } + return ret; +} + +static int helper_rfc4106_encrypt(struct aead_request *req) +{ + int ret; + + if (unlikely(!irq_fpu_usable())) { + WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context"); + ret = -EINVAL; + } else { + kernel_fpu_begin(); + ret = __driver_rfc4106_encrypt(req); + kernel_fpu_end(); + } + return ret; +} + +static int helper_rfc4106_decrypt(struct aead_request *req) +{ + int ret; + + if (unlikely(!irq_fpu_usable())) { + WARN_ONCE(1, "__gcm-aes-aesni alg used in invalid context"); + ret = -EINVAL; + } else { + kernel_fpu_begin(); + ret = __driver_rfc4106_decrypt(req); + kernel_fpu_end(); + } + return ret; +} #endif static struct crypto_alg aesni_algs[] = { { @@ -1210,7 +1264,7 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__aes-aesni", .cra_driver_name = "__driver-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER | CRYPTO_ALG_INTERNAL, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1, @@ -1229,7 +1283,8 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__ecb-aes-aesni", .cra_driver_name = "__driver-ecb-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1, @@ -1249,7 +1304,8 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__cbc-aes-aesni", .cra_driver_name = "__driver-cbc-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1, @@ -1313,7 +1369,8 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__ctr-aes-aesni", .cra_driver_name = "__driver-ctr-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct crypto_aes_ctx) + AESNI_ALIGN - 1, @@ -1357,7 +1414,7 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__gcm-aes-aesni", .cra_driver_name = "__driver-gcm-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_AEAD, + .cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct aesni_rfc4106_gcm_ctx) + AESNI_ALIGN, @@ -1366,8 +1423,12 @@ static struct crypto_alg aesni_algs[] = { { .cra_module = THIS_MODULE, .cra_u = { .aead = { - .encrypt = __driver_rfc4106_encrypt, - .decrypt = __driver_rfc4106_decrypt, + .setkey = common_rfc4106_set_key, + .setauthsize = common_rfc4106_set_authsize, + .encrypt = helper_rfc4106_encrypt, + .decrypt = helper_rfc4106_decrypt, + .ivsize = 8, + .maxauthsize = 16, }, }, }, { @@ -1423,7 +1484,8 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__lrw-aes-aesni", .cra_driver_name = "__driver-lrw-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct aesni_lrw_ctx), .cra_alignmask = 0, @@ -1444,7 +1506,8 @@ static struct crypto_alg aesni_algs[] = { { .cra_name = "__xts-aes-aesni", .cra_driver_name = "__driver-xts-aes-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = AES_BLOCK_SIZE, .cra_ctxsize = sizeof(struct aesni_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index 9a07fafe3831..baf0ac21ace5 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -343,7 +343,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__ecb-camellia-aesni-avx2", .cra_driver_name = "__driver-ecb-camellia-aesni-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, @@ -362,7 +363,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__cbc-camellia-aesni-avx2", .cra_driver_name = "__driver-cbc-camellia-aesni-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, @@ -381,7 +383,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__ctr-camellia-aesni-avx2", .cra_driver_name = "__driver-ctr-camellia-aesni-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, @@ -401,7 +404,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__lrw-camellia-aesni-avx2", .cra_driver_name = "__driver-lrw-camellia-aesni-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_lrw_ctx), .cra_alignmask = 0, @@ -424,7 +428,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__xts-camellia-aesni-avx2", .cra_driver_name = "__driver-xts-camellia-aesni-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index ed38d959add6..78818a1e73e3 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -335,7 +335,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__ecb-camellia-aesni", .cra_driver_name = "__driver-ecb-camellia-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, @@ -354,7 +355,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__cbc-camellia-aesni", .cra_driver_name = "__driver-cbc-camellia-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, @@ -373,7 +375,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__ctr-camellia-aesni", .cra_driver_name = "__driver-ctr-camellia-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct camellia_ctx), .cra_alignmask = 0, @@ -393,7 +396,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__lrw-camellia-aesni", .cra_driver_name = "__driver-lrw-camellia-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_lrw_ctx), .cra_alignmask = 0, @@ -416,7 +420,8 @@ static struct crypto_alg cmll_algs[10] = { { .cra_name = "__xts-camellia-aesni", .cra_driver_name = "__driver-xts-camellia-aesni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAMELLIA_BLOCK_SIZE, .cra_ctxsize = sizeof(struct camellia_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 60ada677a928..236c80974457 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -341,7 +341,8 @@ static struct crypto_alg cast5_algs[6] = { { .cra_name = "__ecb-cast5-avx", .cra_driver_name = "__driver-ecb-cast5-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAST5_BLOCK_SIZE, .cra_ctxsize = sizeof(struct cast5_ctx), .cra_alignmask = 0, @@ -360,7 +361,8 @@ static struct crypto_alg cast5_algs[6] = { { .cra_name = "__cbc-cast5-avx", .cra_driver_name = "__driver-cbc-cast5-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAST5_BLOCK_SIZE, .cra_ctxsize = sizeof(struct cast5_ctx), .cra_alignmask = 0, @@ -379,7 +381,8 @@ static struct crypto_alg cast5_algs[6] = { { .cra_name = "__ctr-cast5-avx", .cra_driver_name = "__driver-ctr-cast5-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct cast5_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index 0160f68a57ff..f448810ca4ac 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -372,7 +372,8 @@ static struct crypto_alg cast6_algs[10] = { { .cra_name = "__ecb-cast6-avx", .cra_driver_name = "__driver-ecb-cast6-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAST6_BLOCK_SIZE, .cra_ctxsize = sizeof(struct cast6_ctx), .cra_alignmask = 0, @@ -391,7 +392,8 @@ static struct crypto_alg cast6_algs[10] = { { .cra_name = "__cbc-cast6-avx", .cra_driver_name = "__driver-cbc-cast6-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAST6_BLOCK_SIZE, .cra_ctxsize = sizeof(struct cast6_ctx), .cra_alignmask = 0, @@ -410,7 +412,8 @@ static struct crypto_alg cast6_algs[10] = { { .cra_name = "__ctr-cast6-avx", .cra_driver_name = "__driver-ctr-cast6-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct cast6_ctx), .cra_alignmask = 0, @@ -430,7 +433,8 @@ static struct crypto_alg cast6_algs[10] = { { .cra_name = "__lrw-cast6-avx", .cra_driver_name = "__driver-lrw-cast6-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAST6_BLOCK_SIZE, .cra_ctxsize = sizeof(struct cast6_lrw_ctx), .cra_alignmask = 0, @@ -453,7 +457,8 @@ static struct crypto_alg cast6_algs[10] = { { .cra_name = "__xts-cast6-avx", .cra_driver_name = "__driver-xts-cast6-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = CAST6_BLOCK_SIZE, .cra_ctxsize = sizeof(struct cast6_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 26d49ebae040..225be06edc80 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -178,7 +178,7 @@ continue_block: ## 2a) PROCESS FULL BLOCKS: ################################################################ full_block: - movq $128,%rax + movl $128,%eax lea 128*8*2(block_0), block_1 lea 128*8*3(block_0), block_2 add $128*8*1, block_0 diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 8253d85aa165..2079baf06bdd 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -154,7 +154,8 @@ static struct shash_alg ghash_alg = { .cra_name = "__ghash", .cra_driver_name = "__ghash-pclmulqdqni", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_flags = CRYPTO_ALG_TYPE_SHASH | + CRYPTO_ALG_INTERNAL, .cra_blocksize = GHASH_BLOCK_SIZE, .cra_ctxsize = sizeof(struct ghash_ctx), .cra_module = THIS_MODULE, @@ -261,7 +262,9 @@ static int ghash_async_init_tfm(struct crypto_tfm *tfm) struct cryptd_ahash *cryptd_tfm; struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm); - cryptd_tfm = cryptd_alloc_ahash("__ghash-pclmulqdqni", 0, 0); + cryptd_tfm = cryptd_alloc_ahash("__ghash-pclmulqdqni", + CRYPTO_ALG_INTERNAL, + CRYPTO_ALG_INTERNAL); if (IS_ERR(cryptd_tfm)) return PTR_ERR(cryptd_tfm); ctx->cryptd_tfm = cryptd_tfm; diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c index 432f1d76ceb8..6a85598931b5 100644 --- a/arch/x86/crypto/glue_helper.c +++ b/arch/x86/crypto/glue_helper.c @@ -232,7 +232,6 @@ static void glue_ctr_crypt_final_128bit(const common_glue_ctr_func_t fn_ctr, le128_to_be128((be128 *)walk->iv, &ctrblk); } -EXPORT_SYMBOL_GPL(glue_ctr_crypt_final_128bit); static unsigned int __glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx, struct blkcipher_desc *desc, diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 437e47a4d302..2f63dc89e7a9 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -309,7 +309,8 @@ static struct crypto_alg srp_algs[10] = { { .cra_name = "__ecb-serpent-avx2", .cra_driver_name = "__driver-ecb-serpent-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -329,7 +330,8 @@ static struct crypto_alg srp_algs[10] = { { .cra_name = "__cbc-serpent-avx2", .cra_driver_name = "__driver-cbc-serpent-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -349,7 +351,8 @@ static struct crypto_alg srp_algs[10] = { { .cra_name = "__ctr-serpent-avx2", .cra_driver_name = "__driver-ctr-serpent-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -370,7 +373,8 @@ static struct crypto_alg srp_algs[10] = { { .cra_name = "__lrw-serpent-avx2", .cra_driver_name = "__driver-lrw-serpent-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_lrw_ctx), .cra_alignmask = 0, @@ -394,7 +398,8 @@ static struct crypto_alg srp_algs[10] = { { .cra_name = "__xts-serpent-avx2", .cra_driver_name = "__driver-xts-serpent-avx2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index 7e217398b4eb..c8d478af8456 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -378,7 +378,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__ecb-serpent-avx", .cra_driver_name = "__driver-ecb-serpent-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -397,7 +398,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__cbc-serpent-avx", .cra_driver_name = "__driver-cbc-serpent-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -416,7 +418,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__ctr-serpent-avx", .cra_driver_name = "__driver-ctr-serpent-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -436,7 +439,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__lrw-serpent-avx", .cra_driver_name = "__driver-lrw-serpent-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_lrw_ctx), .cra_alignmask = 0, @@ -459,7 +463,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__xts-serpent-avx", .cra_driver_name = "__driver-xts-serpent-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c index bf025adaea01..3643dd508f45 100644 --- a/arch/x86/crypto/serpent_sse2_glue.c +++ b/arch/x86/crypto/serpent_sse2_glue.c @@ -387,7 +387,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__ecb-serpent-sse2", .cra_driver_name = "__driver-ecb-serpent-sse2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -406,7 +407,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__cbc-serpent-sse2", .cra_driver_name = "__driver-cbc-serpent-sse2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -425,7 +427,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__ctr-serpent-sse2", .cra_driver_name = "__driver-ctr-serpent-sse2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct serpent_ctx), .cra_alignmask = 0, @@ -445,7 +448,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__lrw-serpent-sse2", .cra_driver_name = "__driver-lrw-serpent-sse2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_lrw_ctx), .cra_alignmask = 0, @@ -468,7 +472,8 @@ static struct crypto_alg serpent_algs[10] = { { .cra_name = "__xts-serpent-sse2", .cra_driver_name = "__driver-xts-serpent-sse2", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SERPENT_BLOCK_SIZE, .cra_ctxsize = sizeof(struct serpent_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index fd9f6b035b16..e510b1c5d690 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -694,7 +694,8 @@ static struct shash_alg sha1_mb_shash_alg = { * use ASYNC flag as some buffers in multi-buffer * algo may not have completed before hashing thread sleep */ - .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_ASYNC, + .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_ASYNC | + CRYPTO_ALG_INTERNAL, .cra_blocksize = SHA1_BLOCK_SIZE, .cra_module = THIS_MODULE, .cra_list = LIST_HEAD_INIT(sha1_mb_shash_alg.base.cra_list), @@ -770,7 +771,9 @@ static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm) struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm); struct mcryptd_hash_ctx *mctx; - mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb", 0, 0); + mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb", + CRYPTO_ALG_INTERNAL, + CRYPTO_ALG_INTERNAL); if (IS_ERR(mcryptd_tfm)) return PTR_ERR(mcryptd_tfm); mctx = crypto_ahash_ctx(&mcryptd_tfm->base); @@ -828,7 +831,7 @@ static unsigned long sha1_mb_flusher(struct mcryptd_alg_cstate *cstate) while (!list_empty(&cstate->work_list)) { rctx = list_entry(cstate->work_list.next, struct mcryptd_hash_request_ctx, waiter); - if time_before(cur_time, rctx->tag.expire) + if (time_before(cur_time, rctx->tag.expire)) break; kernel_fpu_begin(); sha_ctx = (struct sha1_hash_ctx *) sha1_ctx_mgr_flush(cstate->mgr); diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c index 4ca7e166a2aa..822acb5b464c 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c +++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c @@ -56,7 +56,7 @@ void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state) { unsigned int j; - state->unused_lanes = 0xF76543210; + state->unused_lanes = 0xF76543210ULL; for (j = 0; j < 8; j++) { state->lens[j] = 0xFFFFFFFF; state->ldata[j].job_in_lane = NULL; diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 6c20fe04a738..33d1b9dc14cc 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -28,7 +28,7 @@ #include <linux/cryptohash.h> #include <linux/types.h> #include <crypto/sha.h> -#include <asm/byteorder.h> +#include <crypto/sha1_base.h> #include <asm/i387.h> #include <asm/xcr.h> #include <asm/xsave.h> @@ -44,132 +44,51 @@ asmlinkage void sha1_transform_avx(u32 *digest, const char *data, #define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, - unsigned int rounds); + unsigned int rounds); #endif -static asmlinkage void (*sha1_transform_asm)(u32 *, const char *, unsigned int); - - -static int sha1_ssse3_init(struct shash_desc *desc) -{ - struct sha1_state *sctx = shash_desc_ctx(desc); - - *sctx = (struct sha1_state){ - .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 }, - }; - - return 0; -} - -static int __sha1_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len, unsigned int partial) -{ - struct sha1_state *sctx = shash_desc_ctx(desc); - unsigned int done = 0; - - sctx->count += len; - - if (partial) { - done = SHA1_BLOCK_SIZE - partial; - memcpy(sctx->buffer + partial, data, done); - sha1_transform_asm(sctx->state, sctx->buffer, 1); - } - - if (len - done >= SHA1_BLOCK_SIZE) { - const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE; - - sha1_transform_asm(sctx->state, data + done, rounds); - done += rounds * SHA1_BLOCK_SIZE; - } - - memcpy(sctx->buffer, data + done, len - done); - - return 0; -} +static void (*sha1_transform_asm)(u32 *, const char *, unsigned int); static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct sha1_state *sctx = shash_desc_ctx(desc); - unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; - int res; - /* Handle the fast case right here */ - if (partial + len < SHA1_BLOCK_SIZE) { - sctx->count += len; - memcpy(sctx->buffer + partial, data, len); + if (!irq_fpu_usable() || + (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE) + return crypto_sha1_update(desc, data, len); - return 0; - } + /* make sure casting to sha1_block_fn() is safe */ + BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0); - if (!irq_fpu_usable()) { - res = crypto_sha1_update(desc, data, len); - } else { - kernel_fpu_begin(); - res = __sha1_ssse3_update(desc, data, len, partial); - kernel_fpu_end(); - } - - return res; -} - - -/* Add padding and return the message digest. */ -static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) -{ - struct sha1_state *sctx = shash_desc_ctx(desc); - unsigned int i, index, padlen; - __be32 *dst = (__be32 *)out; - __be64 bits; - static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, }; - - bits = cpu_to_be64(sctx->count << 3); - - /* Pad out to 56 mod 64 and append length */ - index = sctx->count % SHA1_BLOCK_SIZE; - padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index); - if (!irq_fpu_usable()) { - crypto_sha1_update(desc, padding, padlen); - crypto_sha1_update(desc, (const u8 *)&bits, sizeof(bits)); - } else { - kernel_fpu_begin(); - /* We need to fill a whole block for __sha1_ssse3_update() */ - if (padlen <= 56) { - sctx->count += padlen; - memcpy(sctx->buffer + index, padding, padlen); - } else { - __sha1_ssse3_update(desc, padding, padlen, index); - } - __sha1_ssse3_update(desc, (const u8 *)&bits, sizeof(bits), 56); - kernel_fpu_end(); - } - - /* Store state in digest */ - for (i = 0; i < 5; i++) - dst[i] = cpu_to_be32(sctx->state[i]); - - /* Wipe context */ - memset(sctx, 0, sizeof(*sctx)); + kernel_fpu_begin(); + sha1_base_do_update(desc, data, len, + (sha1_block_fn *)sha1_transform_asm); + kernel_fpu_end(); return 0; } -static int sha1_ssse3_export(struct shash_desc *desc, void *out) +static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - struct sha1_state *sctx = shash_desc_ctx(desc); + if (!irq_fpu_usable()) + return crypto_sha1_finup(desc, data, len, out); - memcpy(out, sctx, sizeof(*sctx)); + kernel_fpu_begin(); + if (len) + sha1_base_do_update(desc, data, len, + (sha1_block_fn *)sha1_transform_asm); + sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_transform_asm); + kernel_fpu_end(); - return 0; + return sha1_base_finish(desc, out); } -static int sha1_ssse3_import(struct shash_desc *desc, const void *in) +/* Add padding and return the message digest. */ +static int sha1_ssse3_final(struct shash_desc *desc, u8 *out) { - struct sha1_state *sctx = shash_desc_ctx(desc); - - memcpy(sctx, in, sizeof(*sctx)); - - return 0; + return sha1_ssse3_finup(desc, NULL, 0, out); } #ifdef CONFIG_AS_AVX2 @@ -186,13 +105,11 @@ static void sha1_apply_transform_avx2(u32 *digest, const char *data, static struct shash_alg alg = { .digestsize = SHA1_DIGEST_SIZE, - .init = sha1_ssse3_init, + .init = sha1_base_init, .update = sha1_ssse3_update, .final = sha1_ssse3_final, - .export = sha1_ssse3_export, - .import = sha1_ssse3_import, + .finup = sha1_ssse3_finup, .descsize = sizeof(struct sha1_state), - .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name= "sha1-ssse3", diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 642f15687a0a..92b3b5d75ba9 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -96,10 +96,10 @@ SHUF_DC00 = %xmm12 # shuffle xDxC -> DC00 BYTE_FLIP_MASK = %xmm13 NUM_BLKS = %rdx # 3rd arg -CTX = %rsi # 2nd arg -INP = %rdi # 1st arg +INP = %rsi # 2nd arg +CTX = %rdi # 1st arg -SRND = %rdi # clobbers INP +SRND = %rsi # clobbers INP c = %ecx d = %r8d e = %edx @@ -342,8 +342,8 @@ a = TMP_ ######################################################################## ## void sha256_transform_avx(void *input_data, UINT32 digest[8], UINT64 num_blks) -## arg 1 : pointer to input data -## arg 2 : pointer to digest +## arg 1 : pointer to digest +## arg 2 : pointer to input data ## arg 3 : Num blocks ######################################################################## .text diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 9e86944c539d..570ec5ec62d7 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -91,12 +91,12 @@ BYTE_FLIP_MASK = %ymm13 X_BYTE_FLIP_MASK = %xmm13 # XMM version of BYTE_FLIP_MASK NUM_BLKS = %rdx # 3rd arg -CTX = %rsi # 2nd arg -INP = %rdi # 1st arg +INP = %rsi # 2nd arg +CTX = %rdi # 1st arg c = %ecx d = %r8d e = %edx # clobbers NUM_BLKS -y3 = %edi # clobbers INP +y3 = %esi # clobbers INP TBL = %rbp @@ -523,8 +523,8 @@ STACK_SIZE = _RSP + _RSP_SIZE ######################################################################## ## void sha256_transform_rorx(void *input_data, UINT32 digest[8], UINT64 num_blks) -## arg 1 : pointer to input data -## arg 2 : pointer to digest +## arg 1 : pointer to digest +## arg 2 : pointer to input data ## arg 3 : Num blocks ######################################################################## .text diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index f833b74d902b..2cedc44e8121 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -88,10 +88,10 @@ SHUF_DC00 = %xmm11 # shuffle xDxC -> DC00 BYTE_FLIP_MASK = %xmm12 NUM_BLKS = %rdx # 3rd arg -CTX = %rsi # 2nd arg -INP = %rdi # 1st arg +INP = %rsi # 2nd arg +CTX = %rdi # 1st arg -SRND = %rdi # clobbers INP +SRND = %rsi # clobbers INP c = %ecx d = %r8d e = %edx @@ -348,8 +348,8 @@ a = TMP_ ######################################################################## ## void sha256_transform_ssse3(void *input_data, UINT32 digest[8], UINT64 num_blks) -## arg 1 : pointer to input data -## arg 2 : pointer to digest +## arg 1 : pointer to digest +## arg 2 : pointer to input data ## arg 3 : Num blocks ######################################################################## .text diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 8fad72f4dfd2..ccc338881ee8 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -36,195 +36,74 @@ #include <linux/cryptohash.h> #include <linux/types.h> #include <crypto/sha.h> -#include <asm/byteorder.h> +#include <crypto/sha256_base.h> #include <asm/i387.h> #include <asm/xcr.h> #include <asm/xsave.h> #include <linux/string.h> -asmlinkage void sha256_transform_ssse3(const char *data, u32 *digest, - u64 rounds); +asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, + u64 rounds); #ifdef CONFIG_AS_AVX -asmlinkage void sha256_transform_avx(const char *data, u32 *digest, +asmlinkage void sha256_transform_avx(u32 *digest, const char *data, u64 rounds); #endif #ifdef CONFIG_AS_AVX2 -asmlinkage void sha256_transform_rorx(const char *data, u32 *digest, - u64 rounds); +asmlinkage void sha256_transform_rorx(u32 *digest, const char *data, + u64 rounds); #endif -static asmlinkage void (*sha256_transform_asm)(const char *, u32 *, u64); - - -static int sha256_ssse3_init(struct shash_desc *desc) -{ - struct sha256_state *sctx = shash_desc_ctx(desc); - - sctx->state[0] = SHA256_H0; - sctx->state[1] = SHA256_H1; - sctx->state[2] = SHA256_H2; - sctx->state[3] = SHA256_H3; - sctx->state[4] = SHA256_H4; - sctx->state[5] = SHA256_H5; - sctx->state[6] = SHA256_H6; - sctx->state[7] = SHA256_H7; - sctx->count = 0; - - return 0; -} - -static int __sha256_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len, unsigned int partial) -{ - struct sha256_state *sctx = shash_desc_ctx(desc); - unsigned int done = 0; - - sctx->count += len; - - if (partial) { - done = SHA256_BLOCK_SIZE - partial; - memcpy(sctx->buf + partial, data, done); - sha256_transform_asm(sctx->buf, sctx->state, 1); - } - - if (len - done >= SHA256_BLOCK_SIZE) { - const unsigned int rounds = (len - done) / SHA256_BLOCK_SIZE; - - sha256_transform_asm(data + done, sctx->state, (u64) rounds); - - done += rounds * SHA256_BLOCK_SIZE; - } - - memcpy(sctx->buf, data + done, len - done); - - return 0; -} +static void (*sha256_transform_asm)(u32 *, const char *, u64); static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct sha256_state *sctx = shash_desc_ctx(desc); - unsigned int partial = sctx->count % SHA256_BLOCK_SIZE; - int res; - /* Handle the fast case right here */ - if (partial + len < SHA256_BLOCK_SIZE) { - sctx->count += len; - memcpy(sctx->buf + partial, data, len); + if (!irq_fpu_usable() || + (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE) + return crypto_sha256_update(desc, data, len); - return 0; - } - - if (!irq_fpu_usable()) { - res = crypto_sha256_update(desc, data, len); - } else { - kernel_fpu_begin(); - res = __sha256_ssse3_update(desc, data, len, partial); - kernel_fpu_end(); - } - - return res; -} + /* make sure casting to sha256_block_fn() is safe */ + BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0); - -/* Add padding and return the message digest. */ -static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) -{ - struct sha256_state *sctx = shash_desc_ctx(desc); - unsigned int i, index, padlen; - __be32 *dst = (__be32 *)out; - __be64 bits; - static const u8 padding[SHA256_BLOCK_SIZE] = { 0x80, }; - - bits = cpu_to_be64(sctx->count << 3); - - /* Pad out to 56 mod 64 and append length */ - index = sctx->count % SHA256_BLOCK_SIZE; - padlen = (index < 56) ? (56 - index) : ((SHA256_BLOCK_SIZE+56)-index); - - if (!irq_fpu_usable()) { - crypto_sha256_update(desc, padding, padlen); - crypto_sha256_update(desc, (const u8 *)&bits, sizeof(bits)); - } else { - kernel_fpu_begin(); - /* We need to fill a whole block for __sha256_ssse3_update() */ - if (padlen <= 56) { - sctx->count += padlen; - memcpy(sctx->buf + index, padding, padlen); - } else { - __sha256_ssse3_update(desc, padding, padlen, index); - } - __sha256_ssse3_update(desc, (const u8 *)&bits, - sizeof(bits), 56); - kernel_fpu_end(); - } - - /* Store state in digest */ - for (i = 0; i < 8; i++) - dst[i] = cpu_to_be32(sctx->state[i]); - - /* Wipe context */ - memset(sctx, 0, sizeof(*sctx)); + kernel_fpu_begin(); + sha256_base_do_update(desc, data, len, + (sha256_block_fn *)sha256_transform_asm); + kernel_fpu_end(); return 0; } -static int sha256_ssse3_export(struct shash_desc *desc, void *out) +static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - struct sha256_state *sctx = shash_desc_ctx(desc); + if (!irq_fpu_usable()) + return crypto_sha256_finup(desc, data, len, out); - memcpy(out, sctx, sizeof(*sctx)); + kernel_fpu_begin(); + if (len) + sha256_base_do_update(desc, data, len, + (sha256_block_fn *)sha256_transform_asm); + sha256_base_do_finalize(desc, (sha256_block_fn *)sha256_transform_asm); + kernel_fpu_end(); - return 0; + return sha256_base_finish(desc, out); } -static int sha256_ssse3_import(struct shash_desc *desc, const void *in) -{ - struct sha256_state *sctx = shash_desc_ctx(desc); - - memcpy(sctx, in, sizeof(*sctx)); - - return 0; -} - -static int sha224_ssse3_init(struct shash_desc *desc) -{ - struct sha256_state *sctx = shash_desc_ctx(desc); - - sctx->state[0] = SHA224_H0; - sctx->state[1] = SHA224_H1; - sctx->state[2] = SHA224_H2; - sctx->state[3] = SHA224_H3; - sctx->state[4] = SHA224_H4; - sctx->state[5] = SHA224_H5; - sctx->state[6] = SHA224_H6; - sctx->state[7] = SHA224_H7; - sctx->count = 0; - - return 0; -} - -static int sha224_ssse3_final(struct shash_desc *desc, u8 *hash) +/* Add padding and return the message digest. */ +static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) { - u8 D[SHA256_DIGEST_SIZE]; - - sha256_ssse3_final(desc, D); - - memcpy(hash, D, SHA224_DIGEST_SIZE); - memzero_explicit(D, SHA256_DIGEST_SIZE); - - return 0; + return sha256_ssse3_finup(desc, NULL, 0, out); } static struct shash_alg algs[] = { { .digestsize = SHA256_DIGEST_SIZE, - .init = sha256_ssse3_init, + .init = sha256_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, - .export = sha256_ssse3_export, - .import = sha256_ssse3_import, + .finup = sha256_ssse3_finup, .descsize = sizeof(struct sha256_state), - .statesize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", .cra_driver_name = "sha256-ssse3", @@ -235,13 +114,11 @@ static struct shash_alg algs[] = { { } }, { .digestsize = SHA224_DIGEST_SIZE, - .init = sha224_ssse3_init, + .init = sha224_base_init, .update = sha256_ssse3_update, - .final = sha224_ssse3_final, - .export = sha256_ssse3_export, - .import = sha256_ssse3_import, + .final = sha256_ssse3_final, + .finup = sha256_ssse3_finup, .descsize = sizeof(struct sha256_state), - .statesize = sizeof(struct sha256_state), .base = { .cra_name = "sha224", .cra_driver_name = "sha224-ssse3", diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 974dde9bc6cd..565274d6a641 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -54,9 +54,9 @@ # Virtual Registers # ARG1 -msg = %rdi +digest = %rdi # ARG2 -digest = %rsi +msg = %rsi # ARG3 msglen = %rdx T1 = %rcx @@ -271,7 +271,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE .endm ######################################################################## -# void sha512_transform_avx(const void* M, void* D, u64 L) +# void sha512_transform_avx(void* D, const void* M, u64 L) # Purpose: Updates the SHA512 digest stored at D with the message stored in M. # The size of the message pointed to by M must be an integer multiple of SHA512 # message blocks. diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 568b96105f5c..a4771dcd1fcf 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -70,9 +70,9 @@ XFER = YTMP0 BYTE_FLIP_MASK = %ymm9 # 1st arg -INP = %rdi +CTX = %rdi # 2nd arg -CTX = %rsi +INP = %rsi # 3rd arg NUM_BLKS = %rdx @@ -562,7 +562,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE .endm ######################################################################## -# void sha512_transform_rorx(const void* M, void* D, uint64_t L)# +# void sha512_transform_rorx(void* D, const void* M, uint64_t L)# # Purpose: Updates the SHA512 digest stored at D with the message stored in M. # The size of the message pointed to by M must be an integer multiple of SHA512 # message blocks. diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index fb56855d51f5..e610e29cbc81 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -53,9 +53,9 @@ # Virtual Registers # ARG1 -msg = %rdi +digest = %rdi # ARG2 -digest = %rsi +msg = %rsi # ARG3 msglen = %rdx T1 = %rcx @@ -269,7 +269,7 @@ frame_size = frame_GPRSAVE + GPRSAVE_SIZE .endm ######################################################################## -# void sha512_transform_ssse3(const void* M, void* D, u64 L)# +# void sha512_transform_ssse3(void* D, const void* M, u64 L)# # Purpose: Updates the SHA512 digest stored at D with the message stored in M. # The size of the message pointed to by M must be an integer multiple of SHA512 # message blocks. diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index 0b6af26832bf..d9fa4c1e063f 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -34,205 +34,75 @@ #include <linux/cryptohash.h> #include <linux/types.h> #include <crypto/sha.h> -#include <asm/byteorder.h> +#include <crypto/sha512_base.h> #include <asm/i387.h> #include <asm/xcr.h> #include <asm/xsave.h> #include <linux/string.h> -asmlinkage void sha512_transform_ssse3(const char *data, u64 *digest, - u64 rounds); +asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data, + u64 rounds); #ifdef CONFIG_AS_AVX -asmlinkage void sha512_transform_avx(const char *data, u64 *digest, +asmlinkage void sha512_transform_avx(u64 *digest, const char *data, u64 rounds); #endif #ifdef CONFIG_AS_AVX2 -asmlinkage void sha512_transform_rorx(const char *data, u64 *digest, - u64 rounds); +asmlinkage void sha512_transform_rorx(u64 *digest, const char *data, + u64 rounds); #endif -static asmlinkage void (*sha512_transform_asm)(const char *, u64 *, u64); - - -static int sha512_ssse3_init(struct shash_desc *desc) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - sctx->state[0] = SHA512_H0; - sctx->state[1] = SHA512_H1; - sctx->state[2] = SHA512_H2; - sctx->state[3] = SHA512_H3; - sctx->state[4] = SHA512_H4; - sctx->state[5] = SHA512_H5; - sctx->state[6] = SHA512_H6; - sctx->state[7] = SHA512_H7; - sctx->count[0] = sctx->count[1] = 0; - - return 0; -} +static void (*sha512_transform_asm)(u64 *, const char *, u64); -static int __sha512_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len, unsigned int partial) +static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, + unsigned int len) { struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int done = 0; - - sctx->count[0] += len; - if (sctx->count[0] < len) - sctx->count[1]++; - if (partial) { - done = SHA512_BLOCK_SIZE - partial; - memcpy(sctx->buf + partial, data, done); - sha512_transform_asm(sctx->buf, sctx->state, 1); - } - - if (len - done >= SHA512_BLOCK_SIZE) { - const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE; + if (!irq_fpu_usable() || + (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE) + return crypto_sha512_update(desc, data, len); - sha512_transform_asm(data + done, sctx->state, (u64) rounds); - - done += rounds * SHA512_BLOCK_SIZE; - } + /* make sure casting to sha512_block_fn() is safe */ + BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0); - memcpy(sctx->buf, data + done, len - done); + kernel_fpu_begin(); + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_transform_asm); + kernel_fpu_end(); return 0; } -static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data, - unsigned int len) +static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; - int res; - - /* Handle the fast case right here */ - if (partial + len < SHA512_BLOCK_SIZE) { - sctx->count[0] += len; - if (sctx->count[0] < len) - sctx->count[1]++; - memcpy(sctx->buf + partial, data, len); - - return 0; - } + if (!irq_fpu_usable()) + return crypto_sha512_finup(desc, data, len, out); - if (!irq_fpu_usable()) { - res = crypto_sha512_update(desc, data, len); - } else { - kernel_fpu_begin(); - res = __sha512_ssse3_update(desc, data, len, partial); - kernel_fpu_end(); - } + kernel_fpu_begin(); + if (len) + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_transform_asm); + sha512_base_do_finalize(desc, (sha512_block_fn *)sha512_transform_asm); + kernel_fpu_end(); - return res; + return sha512_base_finish(desc, out); } - /* Add padding and return the message digest. */ static int sha512_ssse3_final(struct shash_desc *desc, u8 *out) { - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int i, index, padlen; - __be64 *dst = (__be64 *)out; - __be64 bits[2]; - static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, }; - - /* save number of bits */ - bits[1] = cpu_to_be64(sctx->count[0] << 3); - bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); - - /* Pad out to 112 mod 128 and append length */ - index = sctx->count[0] & 0x7f; - padlen = (index < 112) ? (112 - index) : ((128+112) - index); - - if (!irq_fpu_usable()) { - crypto_sha512_update(desc, padding, padlen); - crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits)); - } else { - kernel_fpu_begin(); - /* We need to fill a whole block for __sha512_ssse3_update() */ - if (padlen <= 112) { - sctx->count[0] += padlen; - if (sctx->count[0] < padlen) - sctx->count[1]++; - memcpy(sctx->buf + index, padding, padlen); - } else { - __sha512_ssse3_update(desc, padding, padlen, index); - } - __sha512_ssse3_update(desc, (const u8 *)&bits, - sizeof(bits), 112); - kernel_fpu_end(); - } - - /* Store state in digest */ - for (i = 0; i < 8; i++) - dst[i] = cpu_to_be64(sctx->state[i]); - - /* Wipe context */ - memset(sctx, 0, sizeof(*sctx)); - - return 0; -} - -static int sha512_ssse3_export(struct shash_desc *desc, void *out) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - memcpy(out, sctx, sizeof(*sctx)); - - return 0; -} - -static int sha512_ssse3_import(struct shash_desc *desc, const void *in) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - memcpy(sctx, in, sizeof(*sctx)); - - return 0; -} - -static int sha384_ssse3_init(struct shash_desc *desc) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - sctx->state[0] = SHA384_H0; - sctx->state[1] = SHA384_H1; - sctx->state[2] = SHA384_H2; - sctx->state[3] = SHA384_H3; - sctx->state[4] = SHA384_H4; - sctx->state[5] = SHA384_H5; - sctx->state[6] = SHA384_H6; - sctx->state[7] = SHA384_H7; - - sctx->count[0] = sctx->count[1] = 0; - - return 0; -} - -static int sha384_ssse3_final(struct shash_desc *desc, u8 *hash) -{ - u8 D[SHA512_DIGEST_SIZE]; - - sha512_ssse3_final(desc, D); - - memcpy(hash, D, SHA384_DIGEST_SIZE); - memzero_explicit(D, SHA512_DIGEST_SIZE); - - return 0; + return sha512_ssse3_finup(desc, NULL, 0, out); } static struct shash_alg algs[] = { { .digestsize = SHA512_DIGEST_SIZE, - .init = sha512_ssse3_init, + .init = sha512_base_init, .update = sha512_ssse3_update, .final = sha512_ssse3_final, - .export = sha512_ssse3_export, - .import = sha512_ssse3_import, + .finup = sha512_ssse3_finup, .descsize = sizeof(struct sha512_state), - .statesize = sizeof(struct sha512_state), .base = { .cra_name = "sha512", .cra_driver_name = "sha512-ssse3", @@ -243,13 +113,11 @@ static struct shash_alg algs[] = { { } }, { .digestsize = SHA384_DIGEST_SIZE, - .init = sha384_ssse3_init, + .init = sha384_base_init, .update = sha512_ssse3_update, - .final = sha384_ssse3_final, - .export = sha512_ssse3_export, - .import = sha512_ssse3_import, + .final = sha512_ssse3_final, + .finup = sha512_ssse3_finup, .descsize = sizeof(struct sha512_state), - .statesize = sizeof(struct sha512_state), .base = { .cra_name = "sha384", .cra_driver_name = "sha384-ssse3", diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S index a039d21986a2..a350c990dc86 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64.S @@ -264,7 +264,7 @@ ENTRY(twofish_enc_blk) movq R1, 8(%rsi) popq R1 - movq $1,%rax + movl $1,%eax ret ENDPROC(twofish_enc_blk) @@ -316,6 +316,6 @@ ENTRY(twofish_dec_blk) movq R1, 8(%rsi) popq R1 - movq $1,%rax + movl $1,%eax ret ENDPROC(twofish_dec_blk) diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 1ac531ea9bcc..b5e2d5651851 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -340,7 +340,8 @@ static struct crypto_alg twofish_algs[10] = { { .cra_name = "__ecb-twofish-avx", .cra_driver_name = "__driver-ecb-twofish-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = TF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct twofish_ctx), .cra_alignmask = 0, @@ -359,7 +360,8 @@ static struct crypto_alg twofish_algs[10] = { { .cra_name = "__cbc-twofish-avx", .cra_driver_name = "__driver-cbc-twofish-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = TF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct twofish_ctx), .cra_alignmask = 0, @@ -378,7 +380,8 @@ static struct crypto_alg twofish_algs[10] = { { .cra_name = "__ctr-twofish-avx", .cra_driver_name = "__driver-ctr-twofish-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = 1, .cra_ctxsize = sizeof(struct twofish_ctx), .cra_alignmask = 0, @@ -398,7 +401,8 @@ static struct crypto_alg twofish_algs[10] = { { .cra_name = "__lrw-twofish-avx", .cra_driver_name = "__driver-lrw-twofish-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = TF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct twofish_lrw_ctx), .cra_alignmask = 0, @@ -421,7 +425,8 @@ static struct crypto_alg twofish_algs[10] = { { .cra_name = "__xts-twofish-avx", .cra_driver_name = "__driver-xts-twofish-avx", .cra_priority = 0, - .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER | + CRYPTO_ALG_INTERNAL, .cra_blocksize = TF_BLOCK_SIZE, .cra_ctxsize = sizeof(struct twofish_xts_ctx), .cra_alignmask = 0, diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index e785b422b766..bb635c641869 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,7 +3,6 @@ # obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_signal.o -obj-$(CONFIG_IA32_EMULATION) += nosyscall.o syscall_ia32.o obj-$(CONFIG_IA32_AOUT) += ia32_aout.o diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index d0165c9a2932..c81d35e6c7f1 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -161,8 +161,7 @@ int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from) } static int ia32_restore_sigcontext(struct pt_regs *regs, - struct sigcontext_ia32 __user *sc, - unsigned int *pax) + struct sigcontext_ia32 __user *sc) { unsigned int tmpflags, err = 0; void __user *buf; @@ -184,7 +183,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, RELOAD_SEG(es); COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); + COPY(dx); COPY(cx); COPY(ip); COPY(ax); /* Don't touch extended registers */ COPY_SEG_CPL3(cs); @@ -197,12 +196,12 @@ static int ia32_restore_sigcontext(struct pt_regs *regs, get_user_ex(tmp, &sc->fpstate); buf = compat_ptr(tmp); - - get_user_ex(*pax, &sc->ax); } get_user_catch(err); err |= restore_xstate_sig(buf, 1); + force_iret(); + return err; } @@ -211,7 +210,6 @@ asmlinkage long sys32_sigreturn(void) struct pt_regs *regs = current_pt_regs(); struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); sigset_t set; - unsigned int ax; if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) goto badframe; @@ -224,9 +222,9 @@ asmlinkage long sys32_sigreturn(void) set_current_blocked(&set); - if (ia32_restore_sigcontext(regs, &frame->sc, &ax)) + if (ia32_restore_sigcontext(regs, &frame->sc)) goto badframe; - return ax; + return regs->ax; badframe: signal_fault(regs, frame, "32bit sigreturn"); @@ -238,7 +236,6 @@ asmlinkage long sys32_rt_sigreturn(void) struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_ia32 __user *frame; sigset_t set; - unsigned int ax; frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4); @@ -249,13 +246,13 @@ asmlinkage long sys32_rt_sigreturn(void) set_current_blocked(&set); - if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) + if (ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; - return ax; + return regs->ax; badframe: signal_fault(regs, frame, "32bit rt sigreturn"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 156ebcab4ada..a821b1cd4fa7 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -30,24 +30,13 @@ .section .entry.text, "ax" - .macro IA32_ARG_FIXUP noebp=0 - movl %edi,%r8d - .if \noebp - .else - movl %ebp,%r9d - .endif - xchg %ecx,%esi - movl %ebx,%edi - movl %edx,%edx /* zero extension */ - .endm - - /* clobbers %eax */ - .macro CLEAR_RREGS offset=0, _r9=rax + /* clobbers %rax */ + .macro CLEAR_RREGS _r9=rax xorl %eax,%eax - movq %rax,\offset+R11(%rsp) - movq %rax,\offset+R10(%rsp) - movq %\_r9,\offset+R9(%rsp) - movq %rax,\offset+R8(%rsp) + movq %rax,R11(%rsp) + movq %rax,R10(%rsp) + movq %\_r9,R9(%rsp) + movq %rax,R8(%rsp) .endm /* @@ -60,14 +49,14 @@ * If it's -1 to make us punt the syscall, then (u32)-1 is still * an appropriately invalid value. */ - .macro LOAD_ARGS32 offset, _r9=0 + .macro LOAD_ARGS32 _r9=0 .if \_r9 - movl \offset+16(%rsp),%r9d + movl R9(%rsp),%r9d .endif - movl \offset+40(%rsp),%ecx - movl \offset+48(%rsp),%edx - movl \offset+56(%rsp),%esi - movl \offset+64(%rsp),%edi + movl RCX(%rsp),%ecx + movl RDX(%rsp),%edx + movl RSI(%rsp),%esi + movl RDI(%rsp),%edi movl %eax,%eax /* zero extension */ .endm @@ -99,54 +88,69 @@ ENDPROC(native_irq_enable_sysexit) /* * 32bit SYSENTER instruction entry. * + * SYSENTER loads ss, rsp, cs, and rip from previously programmed MSRs. + * IF and VM in rflags are cleared (IOW: interrupts are off). + * SYSENTER does not save anything on the stack, + * and does not save old rip (!!!) and rflags. + * * Arguments: - * %eax System call number. - * %ebx Arg1 - * %ecx Arg2 - * %edx Arg3 - * %esi Arg4 - * %edi Arg5 - * %ebp user stack - * 0(%ebp) Arg6 - * - * Interrupts off. - * + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp user stack + * 0(%ebp) arg6 + * * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. Set up a complete hardware stack frame to share code + * path below. We set up a complete hardware stack frame to share code * with the int 0x80 path. - */ + */ ENTRY(ia32_sysenter_target) CFI_STARTPROC32 simple CFI_SIGNAL_FRAME CFI_DEF_CFA rsp,0 CFI_REGISTER rsp,rbp - SWAPGS_UNSAFE_STACK - movq PER_CPU_VAR(kernel_stack), %rsp - addq $(KERNEL_STACK_OFFSET),%rsp + /* - * No need to follow this irqs on/off section: the syscall - * disabled irqs, here we enable it straight after entry: + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. */ + SWAPGS_UNSAFE_STACK + movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp ENABLE_INTERRUPTS(CLBR_NONE) - movl %ebp,%ebp /* zero extension */ - pushq_cfi $__USER32_DS - /*CFI_REL_OFFSET ss,0*/ - pushq_cfi %rbp - CFI_REL_OFFSET rsp,0 - pushfq_cfi - /*CFI_REL_OFFSET rflags,0*/ - movl TI_sysenter_return+THREAD_INFO(%rsp,3*8-KERNEL_STACK_OFFSET),%r10d - CFI_REGISTER rip,r10 - pushq_cfi $__USER32_CS - /*CFI_REL_OFFSET cs,0*/ + + /* Zero-extending 32-bit regs, do not remove */ + movl %ebp, %ebp movl %eax, %eax - pushq_cfi %r10 - CFI_REL_OFFSET rip,0 - pushq_cfi %rax + + movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d + CFI_REGISTER rip,r10 + + /* Construct struct pt_regs on stack */ + pushq_cfi $__USER32_DS /* pt_regs->ss */ + pushq_cfi %rbp /* pt_regs->sp */ + CFI_REL_OFFSET rsp,0 + pushfq_cfi /* pt_regs->flags */ + pushq_cfi $__USER32_CS /* pt_regs->cs */ + pushq_cfi %r10 /* pt_regs->ip = thread_info->sysenter_return */ + CFI_REL_OFFSET rip,0 + pushq_cfi_reg rax /* pt_regs->orig_ax */ + pushq_cfi_reg rdi /* pt_regs->di */ + pushq_cfi_reg rsi /* pt_regs->si */ + pushq_cfi_reg rdx /* pt_regs->dx */ + pushq_cfi_reg rcx /* pt_regs->cx */ + pushq_cfi_reg rax /* pt_regs->ax */ cld - SAVE_ARGS 0,1,0 - /* no need to do an access_ok check here because rbp has been - 32bit zero extended */ + sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ + CFI_ADJUST_CFA_OFFSET 10*8 + + /* + * no need to do an access_ok check here because rbp has been + * 32bit zero extended + */ ASM_STAC 1: movl (%rbp),%ebp _ASM_EXTABLE(1b,ia32_badarg) @@ -157,42 +161,80 @@ ENTRY(ia32_sysenter_target) * 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) + testl $X86_EFLAGS_NT,EFLAGS(%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) + orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) CFI_REMEMBER_STATE jnz sysenter_tracesys cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys sysenter_do_call: - IA32_ARG_FIXUP + /* 32bit syscall -> 64bit C ABI argument conversion */ + movl %edi,%r8d /* arg5 */ + movl %ebp,%r9d /* arg6 */ + xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ + movl %ebx,%edi /* arg1 */ + movl %edx,%edx /* arg3 (zero extension) */ sysenter_dispatch: call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX-ARGOFFSET(%rsp) + movq %rax,RAX(%rsp) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jnz sysexit_audit sysexit_from_sys_call: - andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) - /* clear IF, that popfq doesn't enable interrupts early */ - andl $~0x200,EFLAGS-ARGOFFSET(%rsp) - movl RIP-ARGOFFSET(%rsp),%edx /* User %eip */ - CFI_REGISTER rip,rdx - RESTORE_ARGS 0,24,0,0,0,0 + /* + * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an + * NMI between STI and SYSEXIT has poorly specified behavior, + * and and NMI followed by an IRQ with usergs is fatal. So + * we just pretend we're using SYSEXIT but we really use + * SYSRETL instead. + * + * This code path is still called 'sysexit' because it pairs + * with 'sysenter' and it uses the SYSENTER calling convention. + */ + andl $~TS_COMPAT,ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + movl RIP(%rsp),%ecx /* User %eip */ + CFI_REGISTER rip,rcx + RESTORE_RSI_RDI + xorl %edx,%edx /* avoid info leaks */ xorq %r8,%r8 xorq %r9,%r9 xorq %r10,%r10 - xorq %r11,%r11 - popfq_cfi + movl EFLAGS(%rsp),%r11d /* User eflags */ /*CFI_RESTORE rflags*/ - popq_cfi %rcx /* User %esp */ - CFI_REGISTER rsp,rcx TRACE_IRQS_ON - ENABLE_INTERRUPTS_SYSEXIT32 + + /* + * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT, + * since it avoids a dicey window with interrupts enabled. + */ + movl RSP(%rsp),%esp + + /* + * USERGS_SYSRET32 does: + * gsbase = user's gs base + * eip = ecx + * rflags = r11 + * cs = __USER32_CS + * ss = __USER_DS + * + * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does: + * + * pop %ebp + * pop %edx + * pop %ecx + * + * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to + * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's + * address (already known to user code), and R12-R15 are + * callee-saved and therefore don't contain any interesting + * kernel data. + */ + USERGS_SYSRET32 CFI_RESTORE_STATE @@ -205,18 +247,18 @@ sysexit_from_sys_call: movl %ebx,%esi /* 2nd arg: 1st syscall arg */ movl %eax,%edi /* 1st arg: syscall number */ call __audit_syscall_entry - movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */ + movl RAX(%rsp),%eax /* reload syscall number */ cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys movl %ebx,%edi /* reload 1st syscall arg */ - movl RCX-ARGOFFSET(%rsp),%esi /* reload 2nd syscall arg */ - movl RDX-ARGOFFSET(%rsp),%edx /* reload 3rd syscall arg */ - movl RSI-ARGOFFSET(%rsp),%ecx /* reload 4th syscall arg */ - movl RDI-ARGOFFSET(%rsp),%r8d /* reload 5th syscall arg */ + movl RCX(%rsp),%esi /* reload 2nd syscall arg */ + movl RDX(%rsp),%edx /* reload 3rd syscall arg */ + movl RSI(%rsp),%ecx /* reload 4th syscall arg */ + movl RDI(%rsp),%r8d /* reload 5th syscall arg */ .endm .macro auditsys_exit exit - testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jnz ia32_ret_from_sys_call TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) @@ -227,13 +269,13 @@ sysexit_from_sys_call: 1: setbe %al /* 1 if error, 0 if not */ movzbl %al,%edi /* zero-extend that into %edi */ call __audit_syscall_exit - movq RAX-ARGOFFSET(%rsp),%rax /* reload syscall return value */ + movq RAX(%rsp),%rax /* reload syscall return value */ movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl %edi,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jz \exit - CLEAR_RREGS -ARGOFFSET + CLEAR_RREGS jmp int_with_check .endm @@ -253,16 +295,16 @@ sysenter_fix_flags: sysenter_tracesys: #ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jz sysenter_auditsys #endif - SAVE_REST + SAVE_EXTRA_REGS CLEAR_RREGS movq $-ENOSYS,RAX(%rsp)/* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ - RESTORE_REST + LOAD_ARGS32 /* reload args from stack in case ptrace changed it */ + RESTORE_EXTRA_REGS cmpq $(IA32_NR_syscalls-1),%rax ja int_ret_from_sys_call /* sysenter_tracesys has set RAX(%rsp) */ jmp sysenter_do_call @@ -272,94 +314,128 @@ ENDPROC(ia32_sysenter_target) /* * 32bit SYSCALL instruction entry. * + * 32bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * then loads new ss, cs, and rip from previously programmed MSRs. + * rflags gets masked by a value from another MSR (so CLD and CLAC + * are not needed). SYSCALL does not save anything on the stack + * and does not change rsp. + * + * Note: rflags saving+masking-with-MSR happens only in Long mode + * (in legacy 32bit mode, IF, RF and VM bits are cleared and that's it). + * Don't get confused: rflags saving+masking depends on Long Mode Active bit + * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes + * or target CS descriptor's L bit (SYSCALL does not read segment descriptors). + * * Arguments: - * %eax System call number. - * %ebx Arg1 - * %ecx return EIP - * %edx Arg3 - * %esi Arg4 - * %edi Arg5 - * %ebp Arg2 [note: not saved in the stack frame, should not be touched] - * %esp user stack - * 0(%esp) Arg6 - * - * Interrupts off. - * + * eax system call number + * ecx return address + * ebx arg1 + * ebp arg2 (note: not saved in the stack frame, should not be touched) + * edx arg3 + * esi arg4 + * edi arg5 + * esp user stack + * 0(%esp) arg6 + * * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. Set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ + * path below. We set up a complete hardware stack frame to share code + * with the int 0x80 path. + */ ENTRY(ia32_cstar_target) CFI_STARTPROC32 simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET + CFI_DEF_CFA rsp,0 CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ + + /* + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ SWAPGS_UNSAFE_STACK movl %esp,%r8d CFI_REGISTER rsp,r8 movq PER_CPU_VAR(kernel_stack),%rsp - /* - * No need to follow this irqs on/off section: the syscall - * disabled irqs and here we enable it straight after entry: - */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8,0,0 - movl %eax,%eax /* zero extension */ - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) - movq %rcx,RIP-ARGOFFSET(%rsp) - CFI_REL_OFFSET rip,RIP-ARGOFFSET - movq %rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */ + + /* Zero-extending 32-bit regs, do not remove */ + movl %eax,%eax + + /* Construct struct pt_regs on stack */ + pushq_cfi $__USER32_DS /* pt_regs->ss */ + pushq_cfi %r8 /* pt_regs->sp */ + CFI_REL_OFFSET rsp,0 + pushq_cfi %r11 /* pt_regs->flags */ + pushq_cfi $__USER32_CS /* pt_regs->cs */ + pushq_cfi %rcx /* pt_regs->ip */ + CFI_REL_OFFSET rip,0 + pushq_cfi_reg rax /* pt_regs->orig_ax */ + pushq_cfi_reg rdi /* pt_regs->di */ + pushq_cfi_reg rsi /* pt_regs->si */ + pushq_cfi_reg rdx /* pt_regs->dx */ + pushq_cfi_reg rbp /* pt_regs->cx */ movl %ebp,%ecx - movq $__USER32_CS,CS-ARGOFFSET(%rsp) - movq $__USER32_DS,SS-ARGOFFSET(%rsp) - movq %r11,EFLAGS-ARGOFFSET(%rsp) - /*CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/ - movq %r8,RSP-ARGOFFSET(%rsp) - CFI_REL_OFFSET rsp,RSP-ARGOFFSET - /* no need to do an access_ok check here because r8 has been - 32bit zero extended */ - /* hardware stack frame is complete now */ + pushq_cfi_reg rax /* pt_regs->ax */ + sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ + CFI_ADJUST_CFA_OFFSET 10*8 + + /* + * no need to do an access_ok check here because r8 has been + * 32bit zero extended + */ ASM_STAC 1: movl (%r8),%r9d _ASM_EXTABLE(1b,ia32_badarg) ASM_CLAC - orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) CFI_REMEMBER_STATE jnz cstar_tracesys cmpq $IA32_NR_syscalls-1,%rax ja ia32_badsys cstar_do_call: - IA32_ARG_FIXUP 1 + /* 32bit syscall -> 64bit C ABI argument conversion */ + movl %edi,%r8d /* arg5 */ + /* r9 already loaded */ /* arg6 */ + xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ + movl %ebx,%edi /* arg1 */ + movl %edx,%edx /* arg3 (zero extension) */ cstar_dispatch: call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX-ARGOFFSET(%rsp) + movq %rax,RAX(%rsp) DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jnz sysretl_audit sysretl_from_sys_call: - andl $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) - RESTORE_ARGS 0,-ARG_SKIP,0,0,0 - movl RIP-ARGOFFSET(%rsp),%ecx + andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + RESTORE_RSI_RDI_RDX + movl RIP(%rsp),%ecx CFI_REGISTER rip,rcx - movl EFLAGS-ARGOFFSET(%rsp),%r11d + movl EFLAGS(%rsp),%r11d /*CFI_REGISTER rflags,r11*/ xorq %r10,%r10 xorq %r9,%r9 xorq %r8,%r8 TRACE_IRQS_ON - movl RSP-ARGOFFSET(%rsp),%esp + movl RSP(%rsp),%esp CFI_RESTORE rsp + /* + * 64bit->32bit SYSRET restores eip from ecx, + * eflags from r11 (but RF and VM bits are forced to 0), + * cs and ss are loaded from MSRs. + * (Note: 32bit->32bit SYSRET is different: since r11 + * does not exist, it merely sets eflags.IF=1). + */ USERGS_SYSRET32 - + #ifdef CONFIG_AUDITSYSCALL cstar_auditsys: CFI_RESTORE_STATE - movl %r9d,R9-ARGOFFSET(%rsp) /* register to be clobbered by call */ + movl %r9d,R9(%rsp) /* register to be clobbered by call */ auditsys_entry_common - movl R9-ARGOFFSET(%rsp),%r9d /* reload 6th syscall arg */ + movl R9(%rsp),%r9d /* reload 6th syscall arg */ jmp cstar_dispatch sysretl_audit: @@ -368,17 +444,17 @@ sysretl_audit: cstar_tracesys: #ifdef CONFIG_AUDITSYSCALL - testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jz cstar_auditsys #endif xchgl %r9d,%ebp - SAVE_REST - CLEAR_RREGS 0, r9 + SAVE_EXTRA_REGS + CLEAR_RREGS r9 movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS32 ARGOFFSET, 1 /* reload args from stack in case ptrace changed it */ - RESTORE_REST + LOAD_ARGS32 1 /* reload args from stack in case ptrace changed it */ + RESTORE_EXTRA_REGS xchgl %ebp,%r9d cmpq $(IA32_NR_syscalls-1),%rax ja int_ret_from_sys_call /* cstar_tracesys has set RAX(%rsp) */ @@ -391,78 +467,94 @@ ia32_badarg: jmp ia32_sysret CFI_ENDPROC -/* - * Emulated IA32 system calls via int 0x80. +/* + * Emulated IA32 system calls via int 0x80. * - * Arguments: - * %eax System call number. - * %ebx Arg1 - * %ecx Arg2 - * %edx Arg3 - * %esi Arg4 - * %edi Arg5 - * %ebp Arg6 [note: not saved in the stack frame, should not be touched] + * Arguments: + * eax system call number + * ebx arg1 + * ecx arg2 + * edx arg3 + * esi arg4 + * edi arg5 + * ebp arg6 (note: not saved in the stack frame, should not be touched) * * Notes: - * Uses the same stack frame as the x86-64 version. - * All registers except %eax must be saved (but ptrace may violate that) + * Uses the same stack frame as the x86-64 version. + * All registers except eax must be saved (but ptrace may violate that). * Arguments are zero extended. For system calls that want sign extension and * take long arguments a wrapper is needed. Most calls can just be called * directly. - * Assumes it is only called from user space and entered with interrupts off. - */ + * Assumes it is only called from user space and entered with interrupts off. + */ ENTRY(ia32_syscall) CFI_STARTPROC32 simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,SS+8-RIP - /*CFI_REL_OFFSET ss,SS-RIP*/ - CFI_REL_OFFSET rsp,RSP-RIP - /*CFI_REL_OFFSET rflags,EFLAGS-RIP*/ - /*CFI_REL_OFFSET cs,CS-RIP*/ - CFI_REL_OFFSET rip,RIP-RIP - PARAVIRT_ADJUST_EXCEPTION_FRAME - SWAPGS + CFI_DEF_CFA rsp,5*8 + /*CFI_REL_OFFSET ss,4*8 */ + CFI_REL_OFFSET rsp,3*8 + /*CFI_REL_OFFSET rflags,2*8 */ + /*CFI_REL_OFFSET cs,1*8 */ + CFI_REL_OFFSET rip,0*8 + /* - * No need to follow this irqs on/off section: the syscall - * disabled irqs and here we enable it straight after entry: + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. */ + PARAVIRT_ADJUST_EXCEPTION_FRAME + SWAPGS ENABLE_INTERRUPTS(CLBR_NONE) - movl %eax,%eax - pushq_cfi %rax + + /* Zero-extending 32-bit regs, do not remove */ + movl %eax,%eax + + /* Construct struct pt_regs on stack (iret frame is already on stack) */ + pushq_cfi_reg rax /* pt_regs->orig_ax */ + pushq_cfi_reg rdi /* pt_regs->di */ + pushq_cfi_reg rsi /* pt_regs->si */ + pushq_cfi_reg rdx /* pt_regs->dx */ + pushq_cfi_reg rcx /* pt_regs->cx */ + pushq_cfi_reg rax /* pt_regs->ax */ cld - /* note the registers are not zero extended to the sf. - this could be a problem. */ - SAVE_ARGS 0,1,0 - orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET) - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + sub $(10*8),%rsp /* pt_regs->r8-11,bp,bx,r12-15 not saved */ + CFI_ADJUST_CFA_OFFSET 10*8 + + orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS) + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jnz ia32_tracesys cmpq $(IA32_NR_syscalls-1),%rax ja ia32_badsys ia32_do_call: - IA32_ARG_FIXUP + /* 32bit syscall -> 64bit C ABI argument conversion */ + movl %edi,%r8d /* arg5 */ + movl %ebp,%r9d /* arg6 */ + xchg %ecx,%esi /* rsi:arg2, rcx:arg4 */ + movl %ebx,%edi /* arg1 */ + movl %edx,%edx /* arg3 (zero extension) */ call *ia32_sys_call_table(,%rax,8) # xxx: rip relative ia32_sysret: - movq %rax,RAX-ARGOFFSET(%rsp) + movq %rax,RAX(%rsp) ia32_ret_from_sys_call: - CLEAR_RREGS -ARGOFFSET - jmp int_ret_from_sys_call + CLEAR_RREGS + jmp int_ret_from_sys_call -ia32_tracesys: - SAVE_REST +ia32_tracesys: + SAVE_EXTRA_REGS CLEAR_RREGS movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */ movq %rsp,%rdi /* &pt_regs -> arg1 */ call syscall_trace_enter - LOAD_ARGS32 ARGOFFSET /* reload args from stack in case ptrace changed it */ - RESTORE_REST + LOAD_ARGS32 /* reload args from stack in case ptrace changed it */ + RESTORE_EXTRA_REGS cmpq $(IA32_NR_syscalls-1),%rax ja int_ret_from_sys_call /* ia32_tracesys has set RAX(%rsp) */ jmp ia32_do_call END(ia32_syscall) ia32_badsys: - movq $0,ORIG_RAX-ARGOFFSET(%rsp) + movq $0,ORIG_RAX(%rsp) movq $-ENOSYS,%rax jmp ia32_sysret @@ -479,8 +571,6 @@ GLOBAL(\label) PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn PTREGSCALL stub32_sigreturn, sys32_sigreturn - PTREGSCALL stub32_execve, compat_sys_execve - PTREGSCALL stub32_execveat, compat_sys_execveat PTREGSCALL stub32_fork, sys_fork PTREGSCALL stub32_vfork, sys_vfork @@ -492,24 +582,23 @@ GLOBAL(stub32_clone) ALIGN ia32_ptregs_common: - popq %r11 CFI_ENDPROC CFI_STARTPROC32 simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,SS+8-ARGOFFSET - CFI_REL_OFFSET rax,RAX-ARGOFFSET - CFI_REL_OFFSET rcx,RCX-ARGOFFSET - CFI_REL_OFFSET rdx,RDX-ARGOFFSET - CFI_REL_OFFSET rsi,RSI-ARGOFFSET - CFI_REL_OFFSET rdi,RDI-ARGOFFSET - CFI_REL_OFFSET rip,RIP-ARGOFFSET -/* CFI_REL_OFFSET cs,CS-ARGOFFSET*/ -/* CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/ - CFI_REL_OFFSET rsp,RSP-ARGOFFSET -/* CFI_REL_OFFSET ss,SS-ARGOFFSET*/ - SAVE_REST + CFI_DEF_CFA rsp,SIZEOF_PTREGS + CFI_REL_OFFSET rax,RAX + CFI_REL_OFFSET rcx,RCX + CFI_REL_OFFSET rdx,RDX + CFI_REL_OFFSET rsi,RSI + CFI_REL_OFFSET rdi,RDI + CFI_REL_OFFSET rip,RIP +/* CFI_REL_OFFSET cs,CS*/ +/* CFI_REL_OFFSET rflags,EFLAGS*/ + CFI_REL_OFFSET rsp,RSP +/* CFI_REL_OFFSET ss,SS*/ + SAVE_EXTRA_REGS 8 call *%rax - RESTORE_REST - jmp ia32_sysret /* misbalances the return cache */ + RESTORE_EXTRA_REGS 8 + ret CFI_ENDPROC END(ia32_ptregs_common) diff --git a/arch/x86/ia32/nosyscall.c b/arch/x86/ia32/nosyscall.c deleted file mode 100644 index 51ecd5b4e787..000000000000 --- a/arch/x86/ia32/nosyscall.c +++ /dev/null @@ -1,7 +0,0 @@ -#include <linux/kernel.h> -#include <linux/errno.h> - -long compat_ni_syscall(void) -{ - return -ENOSYS; -} diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 8e0ceecdc957..719cd702b0a4 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -201,20 +201,6 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high, advice); } -long sys32_vm86_warning(void) -{ - struct task_struct *me = current; - static char lastcomm[sizeof(me->comm)]; - - if (strncmp(lastcomm, me->comm, sizeof(lastcomm))) { - compat_printk(KERN_INFO - "%s: vm86 mode not supported on 64 bit kernel\n", - me->comm); - strncpy(lastcomm, me->comm, sizeof(lastcomm)); - } - return -ENOSYS; -} - asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi, size_t count) { diff --git a/arch/x86/ia32/syscall_ia32.c b/arch/x86/ia32/syscall_ia32.c deleted file mode 100644 index 4754ba0f5d9f..000000000000 --- a/arch/x86/ia32/syscall_ia32.c +++ /dev/null @@ -1,25 +0,0 @@ -/* System call table for ia32 emulation. */ - -#include <linux/linkage.h> -#include <linux/sys.h> -#include <linux/cache.h> -#include <asm/asm-offsets.h> - -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void compat(void) ; -#include <asm/syscalls_32.h> -#undef __SYSCALL_I386 - -#define __SYSCALL_I386(nr, sym, compat) [nr] = compat, - -typedef void (*sys_call_ptr_t)(void); - -extern void compat_ni_syscall(void); - -const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { - /* - * Smells like a compiler bug -- it doesn't work - * when the & below is removed. - */ - [0 ... __NR_ia32_syscall_max] = &compat_ni_syscall, -#include <asm/syscalls_32.h> -}; diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h index 372231c22a47..bdf02eeee765 100644 --- a/arch/x86/include/asm/alternative-asm.h +++ b/arch/x86/include/asm/alternative-asm.h @@ -18,12 +18,63 @@ .endm #endif -.macro altinstruction_entry orig alt feature orig_len alt_len +.macro altinstruction_entry orig alt feature orig_len alt_len pad_len .long \orig - . .long \alt - . .word \feature .byte \orig_len .byte \alt_len + .byte \pad_len +.endm + +.macro ALTERNATIVE oldinstr, newinstr, feature +140: + \oldinstr +141: + .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr +144: + .popsection +.endm + +#define old_len 141b-140b +#define new_len1 144f-143f +#define new_len2 145f-144f + +/* + * max without conditionals. Idea adapted from: + * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + */ +#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) + +.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 +140: + \oldinstr +141: + .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \ + (alt_max_short(new_len1, new_len2) - (old_len)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b + altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr1 +144: + \newinstr2 +145: + .popsection .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 473bdbee378a..ba32af062f61 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -48,8 +48,9 @@ struct alt_instr { s32 repl_offset; /* offset to replacement instruction */ u16 cpuid; /* cpuid bit set for replacement */ u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction, <= instrlen */ -}; + u8 replacementlen; /* length of new instruction */ + u8 padlen; /* length of build-time padding */ +} __packed; extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); @@ -76,50 +77,69 @@ static inline int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ -#define OLDINSTR(oldinstr) "661:\n\t" oldinstr "\n662:\n" +#define b_replacement(num) "664"#num +#define e_replacement(num) "665"#num -#define b_replacement(number) "663"#number -#define e_replacement(number) "664"#number +#define alt_end_marker "663" +#define alt_slen "662b-661b" +#define alt_pad_len alt_end_marker"b-662b" +#define alt_total_slen alt_end_marker"b-661b" +#define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f" -#define alt_slen "662b-661b" -#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f" +#define __OLDINSTR(oldinstr, num) \ + "661:\n\t" oldinstr "\n662:\n" \ + ".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * " \ + "((" alt_rlen(num) ")-(" alt_slen ")),0x90\n" -#define ALTINSTR_ENTRY(feature, number) \ +#define OLDINSTR(oldinstr, num) \ + __OLDINSTR(oldinstr, num) \ + alt_end_marker ":\n" + +/* + * max without conditionals. Idea adapted from: + * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas works with s32s. + */ +#define alt_max_short(a, b) "((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") - (" b ")))))" + +/* + * Pad the second replacement alternative with additional NOPs if it is + * additionally longer than the first replacement alternative. + */ +#define OLDINSTR_2(oldinstr, num1, num2) \ + "661:\n\t" oldinstr "\n662:\n" \ + ".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * " \ + "(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \ + alt_end_marker ":\n" + +#define ALTINSTR_ENTRY(feature, num) \ " .long 661b - .\n" /* label */ \ - " .long " b_replacement(number)"f - .\n" /* new instruction */ \ + " .long " b_replacement(num)"f - .\n" /* new instruction */ \ " .word " __stringify(feature) "\n" /* feature bit */ \ - " .byte " alt_slen "\n" /* source len */ \ - " .byte " alt_rlen(number) "\n" /* replacement len */ - -#define DISCARD_ENTRY(number) /* rlen <= slen */ \ - " .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n" + " .byte " alt_total_slen "\n" /* source len */ \ + " .byte " alt_rlen(num) "\n" /* replacement len */ \ + " .byte " alt_pad_len "\n" /* pad len */ -#define ALTINSTR_REPLACEMENT(newinstr, feature, number) /* replacement */ \ - b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t" +#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \ + b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t" /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, newinstr, feature) \ - OLDINSTR(oldinstr) \ + OLDINSTR(oldinstr, 1) \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature, 1) \ ".popsection\n" \ - ".pushsection .discard,\"aw\",@progbits\n" \ - DISCARD_ENTRY(1) \ - ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ ".popsection" #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ - OLDINSTR(oldinstr) \ + OLDINSTR_2(oldinstr, 1, 2) \ ".pushsection .altinstructions,\"a\"\n" \ ALTINSTR_ENTRY(feature1, 1) \ ALTINSTR_ENTRY(feature2, 2) \ ".popsection\n" \ - ".pushsection .discard,\"aw\",@progbits\n" \ - DISCARD_ENTRY(1) \ - DISCARD_ENTRY(2) \ - ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ @@ -146,6 +166,9 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alternative(oldinstr, newinstr, feature) \ asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory") +#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ + asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory") + /* * Alternative inline assembly with input. * diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index efc3b22d896e..976b86a325e5 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -91,7 +91,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) { volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg); - alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP, + alternative_io("movl %0, %P1", "xchgl %0, %P1", X86_BUG_11AP, ASM_OUTPUT2("=r" (v), "=m" (*addr)), ASM_OUTPUT2("0" (v), "m" (*addr))); } @@ -204,7 +204,6 @@ extern void clear_local_APIC(void); extern void disconnect_bsp_APIC(int virt_wire_setup); extern void disable_local_APIC(void); extern void lapic_shutdown(void); -extern int verify_local_APIC(void); extern void sync_Arb_IDs(void); extern void init_bsp_APIC(void); extern void setup_local_APIC(void); diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 2ab1eb33106e..959e45b81fe2 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -95,13 +95,11 @@ do { \ * Stop RDTSC speculation. This is needed when you need to use RDTSC * (or get_cycles or vread that possibly accesses the TSC) in a defined * code region. - * - * (Could use an alternative three way for this if there was one.) */ static __always_inline void rdtsc_barrier(void) { - alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); - alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); + alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, + "lfence", X86_FEATURE_LFENCE_RDTSC); } #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h index 1f1297b46f83..1c8b50edb2db 100644 --- a/arch/x86/include/asm/calling.h +++ b/arch/x86/include/asm/calling.h @@ -55,143 +55,157 @@ For 32-bit we have the following conventions - kernel is built with * for assembly code: */ -#define R15 0 -#define R14 8 -#define R13 16 -#define R12 24 -#define RBP 32 -#define RBX 40 - -/* arguments: interrupts/non tracing syscalls only save up to here: */ -#define R11 48 -#define R10 56 -#define R9 64 -#define R8 72 -#define RAX 80 -#define RCX 88 -#define RDX 96 -#define RSI 104 -#define RDI 112 -#define ORIG_RAX 120 /* + error_code */ -/* end of arguments */ - -/* cpu exception frame or undefined in case of fast syscall: */ -#define RIP 128 -#define CS 136 -#define EFLAGS 144 -#define RSP 152 -#define SS 160 - -#define ARGOFFSET R11 - - .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0 - subq $9*8+\addskip, %rsp - CFI_ADJUST_CFA_OFFSET 9*8+\addskip - movq_cfi rdi, 8*8 - movq_cfi rsi, 7*8 - movq_cfi rdx, 6*8 - - .if \save_rcx - movq_cfi rcx, 5*8 - .endif +/* The layout forms the "struct pt_regs" on the stack: */ +/* + * C ABI says these regs are callee-preserved. They aren't saved on kernel entry + * unless syscall needs a complete, fully filled "struct pt_regs". + */ +#define R15 0*8 +#define R14 1*8 +#define R13 2*8 +#define R12 3*8 +#define RBP 4*8 +#define RBX 5*8 +/* These regs are callee-clobbered. Always saved on kernel entry. */ +#define R11 6*8 +#define R10 7*8 +#define R9 8*8 +#define R8 9*8 +#define RAX 10*8 +#define RCX 11*8 +#define RDX 12*8 +#define RSI 13*8 +#define RDI 14*8 +/* + * On syscall entry, this is syscall#. On CPU exception, this is error code. + * On hw interrupt, it's IRQ number: + */ +#define ORIG_RAX 15*8 +/* Return frame for iretq */ +#define RIP 16*8 +#define CS 17*8 +#define EFLAGS 18*8 +#define RSP 19*8 +#define SS 20*8 + +#define SIZEOF_PTREGS 21*8 + + .macro ALLOC_PT_GPREGS_ON_STACK addskip=0 + subq $15*8+\addskip, %rsp + CFI_ADJUST_CFA_OFFSET 15*8+\addskip + .endm - .if \rax_enosys - movq $-ENOSYS, 4*8(%rsp) - .else - movq_cfi rax, 4*8 + .macro SAVE_C_REGS_HELPER offset=0 rax=1 rcx=1 r8910=1 r11=1 + .if \r11 + movq_cfi r11, 6*8+\offset .endif - - .if \save_r891011 - movq_cfi r8, 3*8 - movq_cfi r9, 2*8 - movq_cfi r10, 1*8 - movq_cfi r11, 0*8 + .if \r8910 + movq_cfi r10, 7*8+\offset + movq_cfi r9, 8*8+\offset + movq_cfi r8, 9*8+\offset + .endif + .if \rax + movq_cfi rax, 10*8+\offset + .endif + .if \rcx + movq_cfi rcx, 11*8+\offset .endif + movq_cfi rdx, 12*8+\offset + movq_cfi rsi, 13*8+\offset + movq_cfi rdi, 14*8+\offset + .endm + .macro SAVE_C_REGS offset=0 + SAVE_C_REGS_HELPER \offset, 1, 1, 1, 1 + .endm + .macro SAVE_C_REGS_EXCEPT_RAX_RCX offset=0 + SAVE_C_REGS_HELPER \offset, 0, 0, 1, 1 + .endm + .macro SAVE_C_REGS_EXCEPT_R891011 + SAVE_C_REGS_HELPER 0, 1, 1, 0, 0 + .endm + .macro SAVE_C_REGS_EXCEPT_RCX_R891011 + SAVE_C_REGS_HELPER 0, 1, 0, 0, 0 + .endm + .macro SAVE_C_REGS_EXCEPT_RAX_RCX_R11 + SAVE_C_REGS_HELPER 0, 0, 0, 1, 0 + .endm + + .macro SAVE_EXTRA_REGS offset=0 + movq_cfi r15, 0*8+\offset + movq_cfi r14, 1*8+\offset + movq_cfi r13, 2*8+\offset + movq_cfi r12, 3*8+\offset + movq_cfi rbp, 4*8+\offset + movq_cfi rbx, 5*8+\offset + .endm + .macro SAVE_EXTRA_REGS_RBP offset=0 + movq_cfi rbp, 4*8+\offset + .endm + .macro RESTORE_EXTRA_REGS offset=0 + movq_cfi_restore 0*8+\offset, r15 + movq_cfi_restore 1*8+\offset, r14 + movq_cfi_restore 2*8+\offset, r13 + movq_cfi_restore 3*8+\offset, r12 + movq_cfi_restore 4*8+\offset, rbp + movq_cfi_restore 5*8+\offset, rbx .endm -#define ARG_SKIP (9*8) + .macro ZERO_EXTRA_REGS + xorl %r15d, %r15d + xorl %r14d, %r14d + xorl %r13d, %r13d + xorl %r12d, %r12d + xorl %ebp, %ebp + xorl %ebx, %ebx + .endm - .macro RESTORE_ARGS rstor_rax=1, addskip=0, rstor_rcx=1, rstor_r11=1, \ - rstor_r8910=1, rstor_rdx=1 + .macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1 .if \rstor_r11 - movq_cfi_restore 0*8, r11 + movq_cfi_restore 6*8, r11 .endif - .if \rstor_r8910 - movq_cfi_restore 1*8, r10 - movq_cfi_restore 2*8, r9 - movq_cfi_restore 3*8, r8 + movq_cfi_restore 7*8, r10 + movq_cfi_restore 8*8, r9 + movq_cfi_restore 9*8, r8 .endif - .if \rstor_rax - movq_cfi_restore 4*8, rax + movq_cfi_restore 10*8, rax .endif - .if \rstor_rcx - movq_cfi_restore 5*8, rcx + movq_cfi_restore 11*8, rcx .endif - .if \rstor_rdx - movq_cfi_restore 6*8, rdx - .endif - - movq_cfi_restore 7*8, rsi - movq_cfi_restore 8*8, rdi - - .if ARG_SKIP+\addskip > 0 - addq $ARG_SKIP+\addskip, %rsp - CFI_ADJUST_CFA_OFFSET -(ARG_SKIP+\addskip) + movq_cfi_restore 12*8, rdx .endif + movq_cfi_restore 13*8, rsi + movq_cfi_restore 14*8, rdi .endm - - .macro LOAD_ARGS offset, skiprax=0 - movq \offset(%rsp), %r11 - movq \offset+8(%rsp), %r10 - movq \offset+16(%rsp), %r9 - movq \offset+24(%rsp), %r8 - movq \offset+40(%rsp), %rcx - movq \offset+48(%rsp), %rdx - movq \offset+56(%rsp), %rsi - movq \offset+64(%rsp), %rdi - .if \skiprax - .else - movq \offset+72(%rsp), %rax - .endif + .macro RESTORE_C_REGS + RESTORE_C_REGS_HELPER 1,1,1,1,1 .endm - -#define REST_SKIP (6*8) - - .macro SAVE_REST - subq $REST_SKIP, %rsp - CFI_ADJUST_CFA_OFFSET REST_SKIP - movq_cfi rbx, 5*8 - movq_cfi rbp, 4*8 - movq_cfi r12, 3*8 - movq_cfi r13, 2*8 - movq_cfi r14, 1*8 - movq_cfi r15, 0*8 + .macro RESTORE_C_REGS_EXCEPT_RAX + RESTORE_C_REGS_HELPER 0,1,1,1,1 .endm - - .macro RESTORE_REST - movq_cfi_restore 0*8, r15 - movq_cfi_restore 1*8, r14 - movq_cfi_restore 2*8, r13 - movq_cfi_restore 3*8, r12 - movq_cfi_restore 4*8, rbp - movq_cfi_restore 5*8, rbx - addq $REST_SKIP, %rsp - CFI_ADJUST_CFA_OFFSET -(REST_SKIP) + .macro RESTORE_C_REGS_EXCEPT_RCX + RESTORE_C_REGS_HELPER 1,0,1,1,1 .endm - - .macro SAVE_ALL - SAVE_ARGS - SAVE_REST + .macro RESTORE_C_REGS_EXCEPT_R11 + RESTORE_C_REGS_HELPER 1,1,0,1,1 + .endm + .macro RESTORE_C_REGS_EXCEPT_RCX_R11 + RESTORE_C_REGS_HELPER 1,0,0,1,1 + .endm + .macro RESTORE_RSI_RDI + RESTORE_C_REGS_HELPER 0,0,0,0,0 + .endm + .macro RESTORE_RSI_RDI_RDX + RESTORE_C_REGS_HELPER 0,0,0,0,1 .endm - .macro RESTORE_ALL addskip=0 - RESTORE_REST - RESTORE_ARGS 1, \addskip + .macro REMOVE_PT_GPREGS_FROM_STACK addskip=0 + addq $15*8+\addskip, %rsp + CFI_ADJUST_CFA_OFFSET -(15*8+\addskip) .endm .macro icebp @@ -210,37 +224,23 @@ For 32-bit we have the following conventions - kernel is built with */ .macro SAVE_ALL - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ebp - CFI_REL_OFFSET ebp, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 + pushl_cfi_reg eax + pushl_cfi_reg ebp + pushl_cfi_reg edi + pushl_cfi_reg esi + pushl_cfi_reg edx + pushl_cfi_reg ecx + pushl_cfi_reg ebx .endm .macro RESTORE_ALL - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %ecx - CFI_RESTORE ecx - popl_cfi %edx - CFI_RESTORE edx - popl_cfi %esi - CFI_RESTORE esi - popl_cfi %edi - CFI_RESTORE edi - popl_cfi %ebp - CFI_RESTORE ebp - popl_cfi %eax - CFI_RESTORE eax + popl_cfi_reg ebx + popl_cfi_reg ecx + popl_cfi_reg edx + popl_cfi_reg esi + popl_cfi_reg edi + popl_cfi_reg ebp + popl_cfi_reg eax .endm #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h index 59c6c401f79f..acdee09228b3 100644 --- a/arch/x86/include/asm/compat.h +++ b/arch/x86/include/asm/compat.h @@ -301,7 +301,7 @@ static inline void __user *arch_compat_alloc_user_space(long len) sp = task_pt_regs(current)->sp; } else { /* -128 for the x32 ABI redzone */ - sp = this_cpu_read(old_rsp) - 128; + sp = task_pt_regs(current)->sp - 128; } return (void __user *)round_down(sp - len, 16); diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index d2b12988d2ed..bf2caa1dedc5 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -34,8 +34,6 @@ extern int _debug_hotplug_cpu(int cpu, int action); #endif #endif -DECLARE_PER_CPU(int, cpu_state); - int mwait_usable(const struct cpuinfo_x86 *); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 90a54851aedc..7ee9b94d9921 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include <asm/disabled-features.h> #endif -#define NCAPINTS 11 /* N 32-bit words worth of info */ +#define NCAPINTS 13 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -195,6 +195,7 @@ #define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ #define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ +#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ @@ -226,12 +227,15 @@ #define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ #define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ #define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ #define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ #define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ #define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ #define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ @@ -242,6 +246,12 @@ #define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ #define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ + /* * BUG word(s) */ @@ -418,6 +428,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) " .word %P0\n" /* 1: do replace */ " .byte 2b - 1b\n" /* source len */ " .byte 0\n" /* replacement len */ + " .byte 0\n" /* pad len */ ".previous\n" /* skipping size check since replacement size = 0 */ : : "i" (X86_FEATURE_ALWAYS) : : t_warn); @@ -432,6 +443,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) " .word %P0\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 0\n" /* replacement len */ + " .byte 0\n" /* pad len */ ".previous\n" /* skipping size check since replacement size = 0 */ : : "i" (bit) : : t_no); @@ -457,6 +469,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) " .word %P1\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 4f - 3f\n" /* replacement len */ + " .byte 0\n" /* pad len */ ".previous\n" ".section .discard,\"aw\",@progbits\n" " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ @@ -483,31 +496,30 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) static __always_inline __pure bool _static_cpu_has_safe(u16 bit) { #ifdef CC_HAVE_ASM_GOTO -/* - * We need to spell the jumps to the compiler because, depending on the offset, - * the replacement jump can be bigger than the original jump, and this we cannot - * have. Thus, we force the jump to the widest, 4-byte, signed relative - * offset even though the last would often fit in less bytes. - */ - asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n" + asm_volatile_goto("1: jmp %l[t_dynamic]\n" "2:\n" + ".skip -(((5f-4f) - (2b-1b)) > 0) * " + "((5f-4f) - (2b-1b)),0x90\n" + "3:\n" ".section .altinstructions,\"a\"\n" " .long 1b - .\n" /* src offset */ - " .long 3f - .\n" /* repl offset */ + " .long 4f - .\n" /* repl offset */ " .word %P1\n" /* always replace */ - " .byte 2b - 1b\n" /* src len */ - " .byte 4f - 3f\n" /* repl len */ + " .byte 3b - 1b\n" /* src len */ + " .byte 5f - 4f\n" /* repl len */ + " .byte 3b - 2b\n" /* pad len */ ".previous\n" ".section .altinstr_replacement,\"ax\"\n" - "3: .byte 0xe9\n .long %l[t_no] - 2b\n" - "4:\n" + "4: jmp %l[t_no]\n" + "5:\n" ".previous\n" ".section .altinstructions,\"a\"\n" " .long 1b - .\n" /* src offset */ " .long 0\n" /* no replacement */ " .word %P0\n" /* feature bit */ - " .byte 2b - 1b\n" /* src len */ + " .byte 3b - 1b\n" /* src len */ " .byte 0\n" /* repl len */ + " .byte 0\n" /* pad len */ ".previous\n" : : "i" (bit), "i" (X86_FEATURE_ALWAYS) : : t_dynamic, t_no); @@ -527,6 +539,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) " .word %P2\n" /* always replace */ " .byte 2b - 1b\n" /* source len */ " .byte 4f - 3f\n" /* replacement len */ + " .byte 0\n" /* pad len */ ".previous\n" ".section .discard,\"aw\",@progbits\n" " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ @@ -541,6 +554,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) " .word %P1\n" /* feature bit */ " .byte 4b - 3b\n" /* src len */ " .byte 6f - 5f\n" /* repl len */ + " .byte 0\n" /* pad len */ ".previous\n" ".section .discard,\"aw\",@progbits\n" " .byte 0xff + (6f-5f) - (4b-3b)\n" /* size check */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index a94b82e8f156..a0bf89fd2647 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -376,11 +376,16 @@ static inline void _set_gate(int gate, unsigned type, void *addr, * Pentium F0 0F bugfix can have resulted in the mapped * IDT being write-protected. */ -#define set_intr_gate(n, addr) \ +#define set_intr_gate_notrace(n, addr) \ do { \ BUG_ON((unsigned)n > 0xFF); \ _set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0, \ __KERNEL_CS); \ + } while (0) + +#define set_intr_gate(n, addr) \ + do { \ + set_intr_gate_notrace(n, addr); \ _trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\ 0, 0, __KERNEL_CS); \ } while (0) diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index f6f15986df6c..de1cdaf4d743 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -86,11 +86,23 @@ CFI_ADJUST_CFA_OFFSET 8 .endm + .macro pushq_cfi_reg reg + pushq %\reg + CFI_ADJUST_CFA_OFFSET 8 + CFI_REL_OFFSET \reg, 0 + .endm + .macro popq_cfi reg popq \reg CFI_ADJUST_CFA_OFFSET -8 .endm + .macro popq_cfi_reg reg + popq %\reg + CFI_ADJUST_CFA_OFFSET -8 + CFI_RESTORE \reg + .endm + .macro pushfq_cfi pushfq CFI_ADJUST_CFA_OFFSET 8 @@ -116,11 +128,23 @@ CFI_ADJUST_CFA_OFFSET 4 .endm + .macro pushl_cfi_reg reg + pushl %\reg + CFI_ADJUST_CFA_OFFSET 4 + CFI_REL_OFFSET \reg, 0 + .endm + .macro popl_cfi reg popl \reg CFI_ADJUST_CFA_OFFSET -4 .endm + .macro popl_cfi_reg reg + popl %\reg + CFI_ADJUST_CFA_OFFSET -4 + CFI_RESTORE \reg + .endm + .macro pushfl_cfi pushfl CFI_ADJUST_CFA_OFFSET 4 diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 779c2efe2e97..3ab0537872fb 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -40,14 +40,6 @@ static inline void e820_mark_nosave_regions(unsigned long limit_pfn) } #endif -#ifdef CONFIG_MEMTEST -extern void early_memtest(unsigned long start, unsigned long end); -#else -static inline void early_memtest(unsigned long start, unsigned long end) -{ -} -#endif - extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); extern u64 early_reserve_e820(u64 sizet, u64 align); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 25bce45c6fc4..3738b138b843 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -2,6 +2,8 @@ #define _ASM_X86_EFI_H #include <asm/i387.h> +#include <asm/pgtable.h> + /* * We map the EFI regions needed for runtime services non-contiguously, * with preserved alignment on virtual addresses starting from -4G down @@ -89,8 +91,8 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, extern struct efi_scratch efi_scratch; extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); -extern void __init efi_call_phys_prolog(void); -extern void __init efi_call_phys_epilog(void); +extern pgd_t * __init efi_call_phys_prolog(void); +extern void __init efi_call_phys_epilog(pgd_t *save_pgd); extern void __init efi_unmap_memmap(void); extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index ca3347a9dab5..f161c189c27b 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -171,10 +171,11 @@ do { \ static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { - regs->ax = regs->bx = regs->cx = regs->dx = 0; - regs->si = regs->di = regs->bp = 0; + /* Commented-out registers are cleared in stub_execve */ + /*regs->ax = regs->bx =*/ regs->cx = regs->dx = 0; + regs->si = regs->di /*= regs->bp*/ = 0; regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; - regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; + /*regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;*/ t->fs = t->gs = 0; t->fsindex = t->gsindex = 0; t->ds = t->es = ds; @@ -338,9 +339,6 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); #define compat_arch_setup_additional_pages compat_arch_setup_additional_pages -extern unsigned long arch_randomize_brk(struct mm_struct *mm); -#define arch_randomize_brk arch_randomize_brk - /* * True on X86_32 or when emulating IA32 on X86_64 */ @@ -365,6 +363,7 @@ enum align_flags { struct va_alignment { int flags; unsigned long mask; + unsigned long bits; } ____cacheline_aligned; extern struct va_alignment va_align; diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 72ba21a8b5fc..da5e96756570 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -67,6 +67,34 @@ extern void finit_soft_fpu(struct i387_soft_struct *soft); static inline void finit_soft_fpu(struct i387_soft_struct *soft) {} #endif +/* + * Must be run with preemption disabled: this clears the fpu_owner_task, + * on this CPU. + * + * This will disable any lazy FPU state restore of the current FPU state, + * but if the current thread owns the FPU, it will still be saved by. + */ +static inline void __cpu_disable_lazy_restore(unsigned int cpu) +{ + per_cpu(fpu_owner_task, cpu) = NULL; +} + +/* + * Used to indicate that the FPU state in memory is newer than the FPU + * state in registers, and the FPU state should be reloaded next time the + * task is run. Only safe on the current task, or non-running tasks. + */ +static inline void task_disable_lazy_fpu_restore(struct task_struct *tsk) +{ + tsk->thread.fpu.last_cpu = ~0; +} + +static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) +{ + return new == this_cpu_read_stable(fpu_owner_task) && + cpu == new->thread.fpu.last_cpu; +} + static inline int is_ia32_compat_frame(void) { return config_enabled(CONFIG_IA32_EMULATION) && @@ -107,7 +135,6 @@ static __always_inline __pure bool use_fxsr(void) static inline void fx_finit(struct i387_fxsave_struct *fx) { - memset(fx, 0, xstate_size); fx->cwd = 0x37f; fx->mxcsr = MXCSR_DEFAULT; } @@ -351,8 +378,14 @@ static inline void __thread_fpu_begin(struct task_struct *tsk) __thread_set_has_fpu(tsk); } -static inline void __drop_fpu(struct task_struct *tsk) +static inline void drop_fpu(struct task_struct *tsk) { + /* + * Forget coprocessor state.. + */ + preempt_disable(); + tsk->thread.fpu_counter = 0; + if (__thread_has_fpu(tsk)) { /* Ignore delayed exceptions from user space */ asm volatile("1: fwait\n" @@ -360,30 +393,29 @@ static inline void __drop_fpu(struct task_struct *tsk) _ASM_EXTABLE(1b, 2b)); __thread_fpu_end(tsk); } -} -static inline void drop_fpu(struct task_struct *tsk) -{ - /* - * Forget coprocessor state.. - */ - preempt_disable(); - tsk->thread.fpu_counter = 0; - __drop_fpu(tsk); clear_stopped_child_used_math(tsk); preempt_enable(); } -static inline void drop_init_fpu(struct task_struct *tsk) +static inline void restore_init_xstate(void) +{ + if (use_xsave()) + xrstor_state(init_xstate_buf, -1); + else + fxrstor_checking(&init_xstate_buf->i387); +} + +/* + * Reset the FPU state in the eager case and drop it in the lazy case (later use + * will reinit it). + */ +static inline void fpu_reset_state(struct task_struct *tsk) { if (!use_eager_fpu()) drop_fpu(tsk); - else { - if (use_xsave()) - xrstor_state(init_xstate_buf, -1); - else - fxrstor_checking(&init_xstate_buf->i387); - } + else + restore_init_xstate(); } /* @@ -400,24 +432,6 @@ static inline void drop_init_fpu(struct task_struct *tsk) */ typedef struct { int preload; } fpu_switch_t; -/* - * Must be run with preemption disabled: this clears the fpu_owner_task, - * on this CPU. - * - * This will disable any lazy FPU state restore of the current FPU state, - * but if the current thread owns the FPU, it will still be saved by. - */ -static inline void __cpu_disable_lazy_restore(unsigned int cpu) -{ - per_cpu(fpu_owner_task, cpu) = NULL; -} - -static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) -{ - return new == this_cpu_read_stable(fpu_owner_task) && - cpu == new->thread.fpu.last_cpu; -} - static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu) { fpu_switch_t fpu; @@ -426,13 +440,17 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta * If the task has used the math, pre-load the FPU on xsave processors * or if the past 5 consecutive context-switches used math. */ - fpu.preload = tsk_used_math(new) && (use_eager_fpu() || - new->thread.fpu_counter > 5); + fpu.preload = tsk_used_math(new) && + (use_eager_fpu() || new->thread.fpu_counter > 5); + if (__thread_has_fpu(old)) { if (!__save_init_fpu(old)) - cpu = ~0; - old->thread.fpu.last_cpu = cpu; - old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */ + task_disable_lazy_fpu_restore(old); + else + old->thread.fpu.last_cpu = cpu; + + /* But leave fpu_owner_task! */ + old->thread.fpu.has_fpu = 0; /* Don't change CR0.TS if we just switch! */ if (fpu.preload) { @@ -443,10 +461,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta stts(); } else { old->thread.fpu_counter = 0; - old->thread.fpu.last_cpu = ~0; + task_disable_lazy_fpu_restore(old); if (fpu.preload) { new->thread.fpu_counter++; - if (!use_eager_fpu() && fpu_lazy_restore(new, cpu)) + if (fpu_lazy_restore(new, cpu)) fpu.preload = 0; else prefetch(new->thread.fpu.state); @@ -466,7 +484,7 @@ static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu) { if (fpu.preload) { if (unlikely(restore_fpu_checking(new))) - drop_init_fpu(new); + fpu_reset_state(new); } } @@ -495,10 +513,12 @@ static inline int restore_xstate_sig(void __user *buf, int ia32_frame) } /* - * Need to be preemption-safe. + * Needs to be preemption-safe. * * NOTE! user_fpu_begin() must be used only immediately before restoring - * it. This function does not do any save/restore on their own. + * the save state. It does not do any saving/restoring on its own. In + * lazy FPU mode, it is just an optimization to avoid a #NM exception, + * the task can lose the FPU right after preempt_enable(). */ static inline void user_fpu_begin(void) { @@ -520,24 +540,6 @@ static inline void __save_fpu(struct task_struct *tsk) } /* - * These disable preemption on their own and are safe - */ -static inline void save_init_fpu(struct task_struct *tsk) -{ - WARN_ON_ONCE(!__thread_has_fpu(tsk)); - - if (use_eager_fpu()) { - __save_fpu(tsk); - return; - } - - preempt_disable(); - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - preempt_enable(); -} - -/* * i387 state interaction */ static inline unsigned short get_fpu_cwd(struct task_struct *tsk) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 9662290e0b20..e9571ddabc4f 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -181,10 +181,9 @@ extern __visible void smp_call_function_single_interrupt(struct pt_regs *); extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif -extern void (*__initconst interrupt[FIRST_SYSTEM_VECTOR - - FIRST_EXTERNAL_VECTOR])(void); +extern char irq_entries_start[]; #ifdef CONFIG_TRACING -#define trace_interrupt interrupt +#define trace_irq_entries_start irq_entries_start #endif #define VECTOR_UNDEFINED (-1) diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 47f29b1d1846..e7814b74caf8 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -69,7 +69,7 @@ struct insn { const insn_byte_t *next_byte; }; -#define MAX_INSN_SIZE 16 +#define MAX_INSN_SIZE 15 #define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) #define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h index f42a04735a0a..e37d6b3ad983 100644 --- a/arch/x86/include/asm/iommu_table.h +++ b/arch/x86/include/asm/iommu_table.h @@ -79,11 +79,12 @@ struct iommu_table_entry { * d). Similar to the 'init', except that this gets called from pci_iommu_init * where we do have a memory allocator. * - * The standard vs the _FINISH differs in that the _FINISH variant will - * continue detecting other IOMMUs in the call list after the - * the detection routine returns a positive number. The _FINISH will - * stop the execution chain. Both will still call the 'init' and - * 'late_init' functions if they are set. + * The standard IOMMU_INIT differs from the IOMMU_INIT_FINISH variant + * in that the former will continue detecting other IOMMUs in the call + * list after the detection routine returns a positive number, while the + * latter will stop the execution chain upon first successful detection. + * Both variants will still call the 'init' and 'late_init' functions if + * they are set. */ #define IOMMU_INIT_FINISH(_detect, _depend, _init, _late_init) \ __IOMMU_INIT(_detect, _depend, _init, _late_init, 1) diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 0a8b519226b8..b77f5edb03b0 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -136,10 +136,6 @@ static inline notrace unsigned long arch_local_irq_save(void) #define USERGS_SYSRET32 \ swapgs; \ sysretl -#define ENABLE_INTERRUPTS_SYSEXIT32 \ - swapgs; \ - sti; \ - sysexit #else #define INTERRUPT_RETURN iret @@ -163,22 +159,27 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(flags); } +#endif /* !__ASSEMBLY__ */ +#ifdef __ASSEMBLY__ +#ifdef CONFIG_TRACE_IRQFLAGS +# define TRACE_IRQS_ON call trace_hardirqs_on_thunk; +# define TRACE_IRQS_OFF call trace_hardirqs_off_thunk; #else - -#ifdef CONFIG_X86_64 -#define ARCH_LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk -#define ARCH_LOCKDEP_SYS_EXIT_IRQ \ +# define TRACE_IRQS_ON +# define TRACE_IRQS_OFF +#endif +#ifdef CONFIG_DEBUG_LOCK_ALLOC +# ifdef CONFIG_X86_64 +# define LOCKDEP_SYS_EXIT call lockdep_sys_exit_thunk +# define LOCKDEP_SYS_EXIT_IRQ \ TRACE_IRQS_ON; \ sti; \ - SAVE_REST; \ - LOCKDEP_SYS_EXIT; \ - RESTORE_REST; \ + call lockdep_sys_exit_thunk; \ cli; \ TRACE_IRQS_OFF; - -#else -#define ARCH_LOCKDEP_SYS_EXIT \ +# else +# define LOCKDEP_SYS_EXIT \ pushl %eax; \ pushl %ecx; \ pushl %edx; \ @@ -186,24 +187,12 @@ static inline int arch_irqs_disabled(void) popl %edx; \ popl %ecx; \ popl %eax; - -#define ARCH_LOCKDEP_SYS_EXIT_IRQ -#endif - -#ifdef CONFIG_TRACE_IRQFLAGS -# define TRACE_IRQS_ON call trace_hardirqs_on_thunk; -# define TRACE_IRQS_OFF call trace_hardirqs_off_thunk; +# define LOCKDEP_SYS_EXIT_IRQ +# endif #else -# define TRACE_IRQS_ON -# define TRACE_IRQS_OFF -#endif -#ifdef CONFIG_DEBUG_LOCK_ALLOC -# define LOCKDEP_SYS_EXIT ARCH_LOCKDEP_SYS_EXIT -# define LOCKDEP_SYS_EXIT_IRQ ARCH_LOCKDEP_SYS_EXIT_IRQ -# else # define LOCKDEP_SYS_EXIT # define LOCKDEP_SYS_EXIT_IRQ -# endif - +#endif #endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 6a2cefb4395a..a4c1cf7e93f8 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ #include <linux/stringify.h> #include <linux/types.h> @@ -30,8 +30,6 @@ l_yes: return true; } -#endif /* __KERNEL__ */ - #ifdef CONFIG_X86_64 typedef u64 jump_label_t; #else @@ -44,4 +42,5 @@ struct jump_entry { jump_label_t key; }; +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a236e39cc385..dea2e7e962e3 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -81,11 +81,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) (base_gfn >> KVM_HPAGE_GFN_SHIFT(level)); } -#define SELECTOR_TI_MASK (1 << 2) -#define SELECTOR_RPL_MASK 0x03 - -#define IOPL_SHIFT 12 - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 #define KVM_MMU_HASH_SHIFT 10 @@ -345,6 +340,7 @@ struct kvm_pmu { enum { KVM_DEBUGREG_BP_ENABLED = 1, KVM_DEBUGREG_WONT_EXIT = 2, + KVM_DEBUGREG_RELOAD = 4, }; struct kvm_vcpu_arch { @@ -431,6 +427,9 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES]; + + int maxphyaddr; + /* emulate context */ struct x86_emulate_ctxt emulate_ctxt; @@ -550,11 +549,20 @@ struct kvm_arch_memory_slot { struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; +/* + * We use as the mode the number of bits allocated in the LDR for the + * logical processor ID. It happens that these are all powers of two. + * This makes it is very easy to detect cases where the APICs are + * configured for multiple modes; in that case, we cannot use the map and + * hence cannot use kvm_irq_delivery_to_apic_fast either. + */ +#define KVM_APIC_MODE_XAPIC_CLUSTER 4 +#define KVM_APIC_MODE_XAPIC_FLAT 8 +#define KVM_APIC_MODE_X2APIC 16 + struct kvm_apic_map { struct rcu_head rcu; - u8 ldr_bits; - /* fields bellow are used to decode ldr values in different modes */ - u32 cid_shift, cid_mask, lid_mask, broadcast; + u8 mode; struct kvm_lapic *phys_map[256]; /* first index is cluster id second is cpu id in a cluster */ struct kvm_lapic *logical_map[16][16]; @@ -859,6 +867,8 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask, void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, struct kvm_memory_slot *memslot); +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, + struct kvm_memory_slot *memslot); void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot); void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, @@ -933,6 +943,7 @@ struct x86_emulate_ctxt; int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); +int kvm_vcpu_halt(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -1128,7 +1139,6 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index e62cf897f781..c1adf33fdd0d 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -115,7 +115,7 @@ static inline void kvm_spinlock_init(void) static inline bool kvm_para_available(void) { - return 0; + return false; } static inline unsigned int kvm_arch_para_features(void) diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h index a455a53d789a..2d29197bd2fb 100644 --- a/arch/x86/include/asm/livepatch.h +++ b/arch/x86/include/asm/livepatch.h @@ -32,8 +32,8 @@ static inline int klp_check_compiler_support(void) #endif return 0; } -extern int klp_write_module_reloc(struct module *mod, unsigned long type, - unsigned long loc, unsigned long value); +int klp_write_module_reloc(struct module *mod, unsigned long type, + unsigned long loc, unsigned long value); static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) { diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 9b3de99dc004..1f5a86d518db 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -116,6 +116,12 @@ struct mca_config { u32 rip_msr; }; +struct mce_vendor_flags { + __u64 overflow_recov : 1, /* cpuid_ebx(80000007) */ + __reserved_0 : 63; +}; +extern struct mce_vendor_flags mce_flags; + extern struct mca_config mca_cfg; extern void mce_register_decode_chain(struct notifier_block *nb); extern void mce_unregister_decode_chain(struct notifier_block *nb); @@ -128,9 +134,11 @@ extern int mce_p5_enabled; #ifdef CONFIG_X86_MCE int mcheck_init(void); void mcheck_cpu_init(struct cpuinfo_x86 *c); +void mcheck_vendor_init_severity(void); #else static inline int mcheck_init(void) { return 0; } static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} +static inline void mcheck_vendor_init_severity(void) {} #endif #ifdef CONFIG_X86_ANCIENT_MCE @@ -183,11 +191,11 @@ typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); enum mcp_flags { - MCP_TIMESTAMP = (1 << 0), /* log time stamp */ - MCP_UC = (1 << 1), /* log uncorrected errors */ - MCP_DONTLOG = (1 << 2), /* only clear, don't log */ + MCP_TIMESTAMP = BIT(0), /* log time stamp */ + MCP_UC = BIT(1), /* log uncorrected errors */ + MCP_DONTLOG = BIT(2), /* only clear, don't log */ }; -void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); +bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b); int mce_notify_irq(void); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 201b520521ed..2fb20d6f7e23 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -75,6 +75,79 @@ static inline void __exit exit_amd_microcode(void) {} #ifdef CONFIG_MICROCODE_EARLY #define MAX_UCODE_COUNT 128 + +#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) +#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') +#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I') +#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l') +#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h') +#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i') +#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D') + +#define CPUID_IS(a, b, c, ebx, ecx, edx) \ + (!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c)))) + +/* + * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. + * x86_vendor() gets vendor id for BSP. + * + * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify + * coding, we still use x86_vendor() to get vendor id for AP. + * + * x86_vendor() gets vendor information directly from CPUID. + */ +static inline int x86_vendor(void) +{ + u32 eax = 0x00000000; + u32 ebx, ecx = 0, edx; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) + return X86_VENDOR_INTEL; + + if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx)) + return X86_VENDOR_AMD; + + return X86_VENDOR_UNKNOWN; +} + +static inline unsigned int __x86_family(unsigned int sig) +{ + unsigned int x86; + + x86 = (sig >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (sig >> 20) & 0xff; + + return x86; +} + +static inline unsigned int x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + return __x86_family(eax); +} + +static inline unsigned int x86_model(unsigned int sig) +{ + unsigned int x86, model; + + x86 = __x86_family(sig); + + model = (sig >> 4) & 0xf; + + if (x86 == 0x6 || x86 == 0xf) + model += ((sig >> 16) & 0xf) << 4; + + return model; +} + extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); extern int __init save_microcode_in_initrd(void); diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index dd4c20043ce7..2b9209c46ca9 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -56,12 +56,15 @@ struct extended_sigtable { #define exttable_size(et) ((et)->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE) -extern int -get_matching_microcode(unsigned int csig, int cpf, void *mc, int rev); +extern int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc); extern int microcode_sanity_check(void *mc, int print_err); -extern int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev); -extern int -update_match_revision(struct microcode_header_intel *mc_header, int rev); +extern int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc); + +static inline int +revision_is_newer(struct microcode_header_intel *mc_header, int rev) +{ + return (mc_header->rev <= rev) ? 0 : 1; +} #ifdef CONFIG_MICROCODE_INTEL_EARLY extern void __init load_ucode_intel_bsp(void); diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index a1410db38a1a..653dfa7662e1 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -30,6 +30,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx) :: "a" (eax), "c" (ecx)); } +static inline void __sti_mwait(unsigned long eax, unsigned long ecx) +{ + trace_hardirqs_on(); + /* "mwait %eax, %ecx;" */ + asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" + :: "a" (eax), "c" (ecx)); +} + /* * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, * which can obviate IPI to trigger checking of need_resched. diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index f97fbe3abb67..c7c712f2648b 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -40,8 +40,10 @@ #ifdef CONFIG_X86_64 #include <asm/page_64_types.h> +#define IOREMAP_MAX_ORDER (PUD_SHIFT) #else #include <asm/page_32_types.h> +#define IOREMAP_MAX_ORDER (PMD_SHIFT) #endif /* CONFIG_X86_64 */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 965c47d254aa..8957810ad7d1 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -545,7 +545,7 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val); } -#if PAGETABLE_LEVELS >= 3 +#if CONFIG_PGTABLE_LEVELS >= 3 static inline pmd_t __pmd(pmdval_t val) { pmdval_t ret; @@ -585,7 +585,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud) PVOP_VCALL2(pv_mmu_ops.set_pud, pudp, val); } -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 static inline pud_t __pud(pudval_t val) { pudval_t ret; @@ -636,9 +636,9 @@ static inline void pud_clear(pud_t *pudp) set_pud(pudp, __pud(0)); } -#endif /* PAGETABLE_LEVELS == 4 */ +#endif /* CONFIG_PGTABLE_LEVELS == 4 */ -#endif /* PAGETABLE_LEVELS >= 3 */ +#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ #ifdef CONFIG_X86_PAE /* Special-case pte-setting operations for PAE, which can't update a @@ -976,11 +976,6 @@ extern void default_banner(void); PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) - -#define ENABLE_INTERRUPTS_SYSEXIT32 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7549b8b369e4..f7b0b5c112f2 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -294,7 +294,7 @@ struct pv_mmu_ops { struct paravirt_callee_save pgd_val; struct paravirt_callee_save make_pgd; -#if PAGETABLE_LEVELS >= 3 +#if CONFIG_PGTABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); void (*pte_clear)(struct mm_struct *mm, unsigned long addr, @@ -308,13 +308,13 @@ struct pv_mmu_ops { struct paravirt_callee_save pmd_val; struct paravirt_callee_save make_pmd; -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 struct paravirt_callee_save pud_val; struct paravirt_callee_save make_pud; void (*set_pgd)(pgd_t *pudp, pgd_t pgdval); -#endif /* PAGETABLE_LEVELS == 4 */ -#endif /* PAGETABLE_LEVELS >= 3 */ +#endif /* CONFIG_PGTABLE_LEVELS == 4 */ +#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ struct pv_lazy_ops lazy_mode; diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index c4412e972bbd..bf7f8b55b0f9 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -77,7 +77,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #define pmd_pgtable(pmd) pmd_page(pmd) -#if PAGETABLE_LEVELS > 2 +#if CONFIG_PGTABLE_LEVELS > 2 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) { struct page *page; @@ -116,7 +116,7 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) } #endif /* CONFIG_X86_PAE */ -#if PAGETABLE_LEVELS > 3 +#if CONFIG_PGTABLE_LEVELS > 3 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) { paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); @@ -142,7 +142,7 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, ___pud_free_tlb(tlb, pud); } -#endif /* PAGETABLE_LEVELS > 3 */ -#endif /* PAGETABLE_LEVELS > 2 */ +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ #endif /* _ASM_X86_PGALLOC_H */ diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h index daacc23e3fb9..392576433e77 100644 --- a/arch/x86/include/asm/pgtable-2level_types.h +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -17,7 +17,6 @@ typedef union { #endif /* !__ASSEMBLY__ */ #define SHARED_KERNEL_PMD 0 -#define PAGETABLE_LEVELS 2 /* * traditional i386 two-level paging structure: diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h index 1bd5876c8649..bcc89625ebe5 100644 --- a/arch/x86/include/asm/pgtable-3level_types.h +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -24,8 +24,6 @@ typedef union { #define SHARED_KERNEL_PMD 1 #endif -#define PAGETABLE_LEVELS 3 - /* * PGDIR_SHIFT determines what a top-level page table entry can map */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a0c35bf6cb92..fe57e7a98839 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -551,7 +551,7 @@ static inline unsigned long pages_to_mb(unsigned long npg) return npg >> (20 - PAGE_SHIFT); } -#if PAGETABLE_LEVELS > 2 +#if CONFIG_PGTABLE_LEVELS > 2 static inline int pud_none(pud_t pud) { return native_pud_val(pud) == 0; @@ -594,9 +594,9 @@ static inline int pud_large(pud_t pud) { return 0; } -#endif /* PAGETABLE_LEVELS > 2 */ +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ -#if PAGETABLE_LEVELS > 3 +#if CONFIG_PGTABLE_LEVELS > 3 static inline int pgd_present(pgd_t pgd) { return pgd_flags(pgd) & _PAGE_PRESENT; @@ -633,7 +633,7 @@ static inline int pgd_none(pgd_t pgd) { return !native_pgd_val(pgd); } -#endif /* PAGETABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 602b6028c5b6..e6844dfb4471 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -20,7 +20,6 @@ typedef struct { pteval_t pte; } pte_t; #endif /* !__ASSEMBLY__ */ #define SHARED_KERNEL_PMD 0 -#define PAGETABLE_LEVELS 4 /* * PGDIR_SHIFT determines what a top-level page table entry can map diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 8c7c10802e9c..78f0c8cbe316 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -234,7 +234,7 @@ static inline pgdval_t pgd_flags(pgd_t pgd) return native_pgd_val(pgd) & PTE_FLAGS_MASK; } -#if PAGETABLE_LEVELS > 3 +#if CONFIG_PGTABLE_LEVELS > 3 typedef struct { pudval_t pud; } pud_t; static inline pud_t native_make_pud(pmdval_t val) @@ -255,7 +255,7 @@ static inline pudval_t native_pud_val(pud_t pud) } #endif -#if PAGETABLE_LEVELS > 2 +#if CONFIG_PGTABLE_LEVELS > 2 typedef struct { pmdval_t pmd; } pmd_t; static inline pmd_t native_make_pmd(pmdval_t val) diff --git a/arch/x86/include/asm/resume-trace.h b/arch/x86/include/asm/pm-trace.h index 3ff1c2cb1da5..7b7ac42c3661 100644 --- a/arch/x86/include/asm/resume-trace.h +++ b/arch/x86/include/asm/pm-trace.h @@ -1,5 +1,5 @@ -#ifndef _ASM_X86_RESUME_TRACE_H -#define _ASM_X86_RESUME_TRACE_H +#ifndef _ASM_X86_PM_TRACE_H +#define _ASM_X86_PM_TRACE_H #include <asm/asm.h> @@ -14,8 +14,10 @@ do { \ ".previous" \ :"=r" (tracedata) \ : "i" (__LINE__), "i" (__FILE__)); \ - generate_resume_trace(tracedata, user); \ + generate_pm_trace(tracedata, user); \ } \ } while (0) -#endif /* _ASM_X86_RESUME_TRACE_H */ +#define TRACE_SUSPEND(user) TRACE_RESUME(user) + +#endif /* _ASM_X86_PM_TRACE_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ec1c93588cef..23ba6765b718 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -109,6 +109,9 @@ struct cpuinfo_x86 { /* in KB - valid for CPUS which support this call: */ int x86_cache_size; int x86_cache_alignment; /* In bytes */ + /* Cache QoS architectural values: */ + int x86_cache_max_rmid; /* max index */ + int x86_cache_occ_scale; /* scale to bytes */ int x86_power; unsigned long loops_per_jiffy; /* cpuid returned max cores value: */ @@ -210,8 +213,23 @@ struct x86_hw_tss { unsigned long sp0; unsigned short ss0, __ss0h; unsigned long sp1; - /* ss1 caches MSR_IA32_SYSENTER_CS: */ - unsigned short ss1, __ss1h; + + /* + * We don't use ring 1, so ss1 is a convenient scratch space in + * the same cacheline as sp0. We use ss1 to cache the value in + * MSR_IA32_SYSENTER_CS. When we context switch + * MSR_IA32_SYSENTER_CS, we first check if the new value being + * written matches ss1, and, if it's not, then we wrmsr the new + * value and update ss1. + * + * The only reason we context switch MSR_IA32_SYSENTER_CS is + * that we set it to zero in vm86 tasks to avoid corrupting the + * stack if we were to go through the sysenter path from vm86 + * mode. + */ + unsigned short ss1; /* MSR_IA32_SYSENTER_CS */ + + unsigned short __ss1h; unsigned long sp2; unsigned short ss2, __ss2h; unsigned long __cr3; @@ -276,13 +294,17 @@ struct tss_struct { unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; /* - * .. and then another 0x100 bytes for the emergency kernel stack: + * Space for the temporary SYSENTER stack: */ - unsigned long stack[64]; + unsigned long SYSENTER_stack[64]; } ____cacheline_aligned; -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss); +DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); + +#ifdef CONFIG_X86_32 +DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); +#endif /* * Save the original ist values for checking stack pointers during debugging @@ -474,7 +496,6 @@ struct thread_struct { #ifdef CONFIG_X86_32 unsigned long sysenter_cs; #else - unsigned long usersp; /* Copy from PDA */ unsigned short es; unsigned short ds; unsigned short fsindex; @@ -564,6 +585,16 @@ static inline void native_swapgs(void) #endif } +static inline unsigned long current_top_of_stack(void) +{ +#ifdef CONFIG_X86_64 + return this_cpu_read_stable(cpu_tss.x86_tss.sp0); +#else + /* sp0 on x86_32 is special in and around vm86 mode. */ + return this_cpu_read_stable(cpu_current_top_of_stack); +#endif +} + #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else @@ -761,10 +792,10 @@ extern char ignore_fpu_irq; #define ARCH_HAS_SPINLOCK_PREFETCH #ifdef CONFIG_X86_32 -# define BASE_PREFETCH ASM_NOP4 +# define BASE_PREFETCH "" # define ARCH_HAS_PREFETCH #else -# define BASE_PREFETCH "prefetcht0 (%1)" +# define BASE_PREFETCH "prefetcht0 %P1" #endif /* @@ -775,10 +806,9 @@ extern char ignore_fpu_irq; */ static inline void prefetch(const void *x) { - alternative_input(BASE_PREFETCH, - "prefetchnta (%1)", + alternative_input(BASE_PREFETCH, "prefetchnta %P1", X86_FEATURE_XMM, - "r" (x)); + "m" (*(const char *)x)); } /* @@ -788,10 +818,9 @@ static inline void prefetch(const void *x) */ static inline void prefetchw(const void *x) { - alternative_input(BASE_PREFETCH, - "prefetchw (%1)", - X86_FEATURE_3DNOW, - "r" (x)); + alternative_input(BASE_PREFETCH, "prefetchw %P1", + X86_FEATURE_3DNOWPREFETCH, + "m" (*(const char *)x)); } static inline void spin_lock_prefetch(const void *x) @@ -799,6 +828,9 @@ static inline void spin_lock_prefetch(const void *x) prefetchw(x); } +#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ + TOP_OF_KERNEL_STACK_PADDING) + #ifdef CONFIG_X86_32 /* * User space process size: 3GB (default). @@ -809,39 +841,16 @@ static inline void spin_lock_prefetch(const void *x) #define STACK_TOP_MAX STACK_TOP #define INIT_THREAD { \ - .sp0 = sizeof(init_stack) + (long)&init_stack, \ + .sp0 = TOP_OF_INIT_STACK, \ .vm86_info = NULL, \ .sysenter_cs = __KERNEL_CS, \ .io_bitmap_ptr = NULL, \ } -/* - * Note that the .io_bitmap member must be extra-big. This is because - * the CPU will access an additional byte beyond the end of the IO - * permission bitmap. The extra byte must be all 1 bits, and must - * be within the limit. - */ -#define INIT_TSS { \ - .x86_tss = { \ - .sp0 = sizeof(init_stack) + (long)&init_stack, \ - .ss0 = __KERNEL_DS, \ - .ss1 = __KERNEL_CS, \ - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \ - }, \ - .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, \ -} - extern unsigned long thread_saved_pc(struct task_struct *tsk); -#define THREAD_SIZE_LONGS (THREAD_SIZE/sizeof(unsigned long)) -#define KSTK_TOP(info) \ -({ \ - unsigned long *__ptr = (unsigned long *)(info); \ - (unsigned long)(&__ptr[THREAD_SIZE_LONGS]); \ -}) - /* - * The below -8 is to reserve 8 bytes on top of the ring0 stack. + * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack. * This is necessary to guarantee that the entire "struct pt_regs" * is accessible even if the CPU haven't stored the SS/ESP registers * on the stack (interrupt gate does not save these registers @@ -850,11 +859,11 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); * "struct pt_regs" is possible, but they may contain the * completely wrong values. */ -#define task_pt_regs(task) \ -({ \ - struct pt_regs *__regs__; \ - __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \ - __regs__ - 1; \ +#define task_pt_regs(task) \ +({ \ + unsigned long __ptr = (unsigned long)task_stack_page(task); \ + __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ + ((struct pt_regs *)__ptr) - 1; \ }) #define KSTK_ESP(task) (task_pt_regs(task)->sp) @@ -886,11 +895,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define STACK_TOP_MAX TASK_SIZE_MAX #define INIT_THREAD { \ - .sp0 = (unsigned long)&init_stack + sizeof(init_stack) \ -} - -#define INIT_TSS { \ - .x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \ + .sp0 = TOP_OF_INIT_STACK \ } /* @@ -902,11 +907,6 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); -/* - * User space RSP while inside the SYSCALL fast path - */ -DECLARE_PER_CPU(unsigned long, old_rsp); - #endif /* CONFIG_X86_64 */ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index 86fc2bb82287..19507ffa5d28 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -31,13 +31,17 @@ struct pt_regs { #else /* __i386__ */ struct pt_regs { +/* + * C ABI says these regs are callee-preserved. They aren't saved on kernel entry + * unless syscall needs a complete, fully filled "struct pt_regs". + */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; -/* arguments: non interrupts/non tracing syscalls only save up to here*/ +/* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; @@ -47,9 +51,12 @@ struct pt_regs { unsigned long dx; unsigned long si; unsigned long di; +/* + * On syscall entry, this is syscall#. On CPU exception, this is error code. + * On hw interrupt, it's IRQ number: + */ unsigned long orig_ax; -/* end of arguments */ -/* cpu exception frame or undefined */ +/* Return frame for iretq */ unsigned long ip; unsigned long cs; unsigned long flags; @@ -89,11 +96,13 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) } /* - * user_mode_vm(regs) determines whether a register set came from user mode. - * This is true if V8086 mode was enabled OR if the register set was from - * protected mode with RPL-3 CS value. This tricky test checks that with - * one comparison. Many places in the kernel can bypass this full check - * if they have already ruled out V8086 mode, so user_mode(regs) can be used. + * user_mode(regs) determines whether a register set came from user + * mode. On x86_32, this is true if V8086 mode was enabled OR if the + * register set was from protected mode with RPL-3 CS value. This + * tricky test checks that with one comparison. + * + * On x86_64, vm86 mode is mercifully nonexistent, and we don't need + * the extra check. */ static inline int user_mode(struct pt_regs *regs) { @@ -104,16 +113,6 @@ static inline int user_mode(struct pt_regs *regs) #endif } -static inline int user_mode_vm(struct pt_regs *regs) -{ -#ifdef CONFIG_X86_32 - return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= - USER_RPL; -#else - return user_mode(regs); -#endif -} - static inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 @@ -138,12 +137,8 @@ static inline bool user_64bit_mode(struct pt_regs *regs) #endif } -#define current_user_stack_pointer() this_cpu_read(old_rsp) -/* ia32 vs. x32 difference */ -#define compat_user_stack_pointer() \ - (test_thread_flag(TIF_IA32) \ - ? current_pt_regs()->sp \ - : this_cpu_read(old_rsp)) +#define current_user_stack_pointer() current_pt_regs()->sp +#define compat_user_stack_pointer() current_pt_regs()->sp #endif #ifdef CONFIG_X86_32 @@ -248,7 +243,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, */ #define arch_ptrace_stop_needed(code, info) \ ({ \ - set_thread_flag(TIF_NOTIFY_RESUME); \ + force_iret(); \ false; \ }) diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index d6b078e9fa28..25b1cc07d496 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; + u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h index 0f3d7f099224..0c8c7c8861b4 100644 --- a/arch/x86/include/asm/seccomp.h +++ b/arch/x86/include/asm/seccomp.h @@ -1,5 +1,20 @@ +#ifndef _ASM_X86_SECCOMP_H +#define _ASM_X86_SECCOMP_H + +#include <asm/unistd.h> + #ifdef CONFIG_X86_32 -# include <asm/seccomp_32.h> -#else -# include <asm/seccomp_64.h> +#define __NR_seccomp_sigreturn __NR_sigreturn #endif + +#ifdef CONFIG_COMPAT +#include <asm/ia32_unistd.h> +#define __NR_seccomp_read_32 __NR_ia32_read +#define __NR_seccomp_write_32 __NR_ia32_write +#define __NR_seccomp_exit_32 __NR_ia32_exit +#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn +#endif + +#include <asm-generic/seccomp.h> + +#endif /* _ASM_X86_SECCOMP_H */ diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h deleted file mode 100644 index b811d6f5780c..000000000000 --- a/arch/x86/include/asm/seccomp_32.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_SECCOMP_32_H -#define _ASM_X86_SECCOMP_32_H - -#include <linux/unistd.h> - -#define __NR_seccomp_read __NR_read -#define __NR_seccomp_write __NR_write -#define __NR_seccomp_exit __NR_exit -#define __NR_seccomp_sigreturn __NR_sigreturn - -#endif /* _ASM_X86_SECCOMP_32_H */ diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h deleted file mode 100644 index 84ec1bd161a5..000000000000 --- a/arch/x86/include/asm/seccomp_64.h +++ /dev/null @@ -1,17 +0,0 @@ -#ifndef _ASM_X86_SECCOMP_64_H -#define _ASM_X86_SECCOMP_64_H - -#include <linux/unistd.h> -#include <asm/ia32_unistd.h> - -#define __NR_seccomp_read __NR_read -#define __NR_seccomp_write __NR_write -#define __NR_seccomp_exit __NR_exit -#define __NR_seccomp_sigreturn __NR_rt_sigreturn - -#define __NR_seccomp_read_32 __NR_ia32_read -#define __NR_seccomp_write_32 __NR_ia32_write -#define __NR_seccomp_exit_32 __NR_ia32_exit -#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn - -#endif /* _ASM_X86_SECCOMP_64_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index db257a58571f..5a9856eb12ba 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -3,8 +3,10 @@ #include <linux/const.h> -/* Constructor for a conventional segment GDT (or LDT) entry */ -/* This is a macro so it can be used in initializers */ +/* + * Constructor for a conventional segment GDT (or LDT) entry. + * This is a macro so it can be used in initializers. + */ #define GDT_ENTRY(flags, base, limit) \ ((((base) & _AC(0xff000000,ULL)) << (56-24)) | \ (((flags) & _AC(0x0000f0ff,ULL)) << 40) | \ @@ -12,198 +14,228 @@ (((base) & _AC(0x00ffffff,ULL)) << 16) | \ (((limit) & _AC(0x0000ffff,ULL)))) -/* Simple and small GDT entries for booting only */ +/* Simple and small GDT entries for booting only: */ #define GDT_ENTRY_BOOT_CS 2 -#define __BOOT_CS (GDT_ENTRY_BOOT_CS * 8) +#define GDT_ENTRY_BOOT_DS 3 +#define GDT_ENTRY_BOOT_TSS 4 +#define __BOOT_CS (GDT_ENTRY_BOOT_CS*8) +#define __BOOT_DS (GDT_ENTRY_BOOT_DS*8) +#define __BOOT_TSS (GDT_ENTRY_BOOT_TSS*8) + +/* + * Bottom two bits of selector give the ring + * privilege level + */ +#define SEGMENT_RPL_MASK 0x3 -#define GDT_ENTRY_BOOT_DS (GDT_ENTRY_BOOT_CS + 1) -#define __BOOT_DS (GDT_ENTRY_BOOT_DS * 8) +/* User mode is privilege level 3: */ +#define USER_RPL 0x3 -#define GDT_ENTRY_BOOT_TSS (GDT_ENTRY_BOOT_CS + 2) -#define __BOOT_TSS (GDT_ENTRY_BOOT_TSS * 8) +/* Bit 2 is Table Indicator (TI): selects between LDT or GDT */ +#define SEGMENT_TI_MASK 0x4 +/* LDT segment has TI set ... */ +#define SEGMENT_LDT 0x4 +/* ... GDT has it cleared */ +#define SEGMENT_GDT 0x0 -#define SEGMENT_RPL_MASK 0x3 /* - * Bottom two bits of selector give the ring - * privilege level - */ -#define SEGMENT_TI_MASK 0x4 /* Bit 2 is table indicator (LDT/GDT) */ -#define USER_RPL 0x3 /* User mode is privilege level 3 */ -#define SEGMENT_LDT 0x4 /* LDT segment has TI set... */ -#define SEGMENT_GDT 0x0 /* ... GDT has it cleared */ +#define GDT_ENTRY_INVALID_SEG 0 #ifdef CONFIG_X86_32 /* * The layout of the per-CPU GDT under Linux: * - * 0 - null + * 0 - null <=== cacheline #1 * 1 - reserved * 2 - reserved * 3 - reserved * - * 4 - unused <==== new cacheline + * 4 - unused <=== cacheline #2 * 5 - unused * * ------- start of TLS (Thread-Local Storage) segments: * * 6 - TLS segment #1 [ glibc's TLS segment ] * 7 - TLS segment #2 [ Wine's %fs Win32 segment ] - * 8 - TLS segment #3 + * 8 - TLS segment #3 <=== cacheline #3 * 9 - reserved * 10 - reserved * 11 - reserved * * ------- start of kernel segments: * - * 12 - kernel code segment <==== new cacheline + * 12 - kernel code segment <=== cacheline #4 * 13 - kernel data segment * 14 - default user CS * 15 - default user DS - * 16 - TSS + * 16 - TSS <=== cacheline #5 * 17 - LDT * 18 - PNPBIOS support (16->32 gate) * 19 - PNPBIOS support - * 20 - PNPBIOS support + * 20 - PNPBIOS support <=== cacheline #6 * 21 - PNPBIOS support * 22 - PNPBIOS support * 23 - APM BIOS support - * 24 - APM BIOS support + * 24 - APM BIOS support <=== cacheline #7 * 25 - APM BIOS support * * 26 - ESPFIX small SS * 27 - per-cpu [ offset to per-cpu data area ] - * 28 - stack_canary-20 [ for stack protector ] + * 28 - stack_canary-20 [ for stack protector ] <=== cacheline #8 * 29 - unused * 30 - unused * 31 - TSS for double fault handler */ -#define GDT_ENTRY_TLS_MIN 6 -#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) +#define GDT_ENTRY_TLS_MIN 6 +#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) +#define GDT_ENTRY_KERNEL_CS 12 +#define GDT_ENTRY_KERNEL_DS 13 #define GDT_ENTRY_DEFAULT_USER_CS 14 - #define GDT_ENTRY_DEFAULT_USER_DS 15 +#define GDT_ENTRY_TSS 16 +#define GDT_ENTRY_LDT 17 +#define GDT_ENTRY_PNPBIOS_CS32 18 +#define GDT_ENTRY_PNPBIOS_CS16 19 +#define GDT_ENTRY_PNPBIOS_DS 20 +#define GDT_ENTRY_PNPBIOS_TS1 21 +#define GDT_ENTRY_PNPBIOS_TS2 22 +#define GDT_ENTRY_APMBIOS_BASE 23 + +#define GDT_ENTRY_ESPFIX_SS 26 +#define GDT_ENTRY_PERCPU 27 +#define GDT_ENTRY_STACK_CANARY 28 + +#define GDT_ENTRY_DOUBLEFAULT_TSS 31 -#define GDT_ENTRY_KERNEL_BASE (12) +/* + * Number of entries in the GDT table: + */ +#define GDT_ENTRIES 32 -#define GDT_ENTRY_KERNEL_CS (GDT_ENTRY_KERNEL_BASE+0) +/* + * Segment selector values corresponding to the above entries: + */ -#define GDT_ENTRY_KERNEL_DS (GDT_ENTRY_KERNEL_BASE+1) +#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) +#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) +#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) +#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) +#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS*8) -#define GDT_ENTRY_TSS (GDT_ENTRY_KERNEL_BASE+4) -#define GDT_ENTRY_LDT (GDT_ENTRY_KERNEL_BASE+5) +/* segment for calling fn: */ +#define PNP_CS32 (GDT_ENTRY_PNPBIOS_CS32*8) +/* code segment for BIOS: */ +#define PNP_CS16 (GDT_ENTRY_PNPBIOS_CS16*8) -#define GDT_ENTRY_PNPBIOS_BASE (GDT_ENTRY_KERNEL_BASE+6) -#define GDT_ENTRY_APMBIOS_BASE (GDT_ENTRY_KERNEL_BASE+11) +/* "Is this PNP code selector (PNP_CS32 or PNP_CS16)?" */ +#define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == PNP_CS32) -#define GDT_ENTRY_ESPFIX_SS (GDT_ENTRY_KERNEL_BASE+14) -#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS*8) +/* data segment for BIOS: */ +#define PNP_DS (GDT_ENTRY_PNPBIOS_DS*8) +/* transfer data segment: */ +#define PNP_TS1 (GDT_ENTRY_PNPBIOS_TS1*8) +/* another data segment: */ +#define PNP_TS2 (GDT_ENTRY_PNPBIOS_TS2*8) -#define GDT_ENTRY_PERCPU (GDT_ENTRY_KERNEL_BASE+15) #ifdef CONFIG_SMP -#define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8) +# define __KERNEL_PERCPU (GDT_ENTRY_PERCPU*8) #else -#define __KERNEL_PERCPU 0 +# define __KERNEL_PERCPU 0 #endif -#define GDT_ENTRY_STACK_CANARY (GDT_ENTRY_KERNEL_BASE+16) #ifdef CONFIG_CC_STACKPROTECTOR -#define __KERNEL_STACK_CANARY (GDT_ENTRY_STACK_CANARY*8) +# define __KERNEL_STACK_CANARY (GDT_ENTRY_STACK_CANARY*8) #else -#define __KERNEL_STACK_CANARY 0 +# define __KERNEL_STACK_CANARY 0 #endif -#define GDT_ENTRY_DOUBLEFAULT_TSS 31 - -/* - * The GDT has 32 entries - */ -#define GDT_ENTRIES 32 +#else /* 64-bit: */ -/* The PnP BIOS entries in the GDT */ -#define GDT_ENTRY_PNPBIOS_CS32 (GDT_ENTRY_PNPBIOS_BASE + 0) -#define GDT_ENTRY_PNPBIOS_CS16 (GDT_ENTRY_PNPBIOS_BASE + 1) -#define GDT_ENTRY_PNPBIOS_DS (GDT_ENTRY_PNPBIOS_BASE + 2) -#define GDT_ENTRY_PNPBIOS_TS1 (GDT_ENTRY_PNPBIOS_BASE + 3) -#define GDT_ENTRY_PNPBIOS_TS2 (GDT_ENTRY_PNPBIOS_BASE + 4) - -/* The PnP BIOS selectors */ -#define PNP_CS32 (GDT_ENTRY_PNPBIOS_CS32 * 8) /* segment for calling fn */ -#define PNP_CS16 (GDT_ENTRY_PNPBIOS_CS16 * 8) /* code segment for BIOS */ -#define PNP_DS (GDT_ENTRY_PNPBIOS_DS * 8) /* data segment for BIOS */ -#define PNP_TS1 (GDT_ENTRY_PNPBIOS_TS1 * 8) /* transfer data segment */ -#define PNP_TS2 (GDT_ENTRY_PNPBIOS_TS2 * 8) /* another data segment */ +#include <asm/cache.h> +#define GDT_ENTRY_KERNEL32_CS 1 +#define GDT_ENTRY_KERNEL_CS 2 +#define GDT_ENTRY_KERNEL_DS 3 /* - * Matching rules for certain types of segments. + * We cannot use the same code segment descriptor for user and kernel mode, + * not even in long flat mode, because of different DPL. + * + * GDT layout to get 64-bit SYSCALL/SYSRET support right. SYSRET hardcodes + * selectors: + * + * if returning to 32-bit userspace: cs = STAR.SYSRET_CS, + * if returning to 64-bit userspace: cs = STAR.SYSRET_CS+16, + * + * ss = STAR.SYSRET_CS+8 (in either case) + * + * thus USER_DS should be between 32-bit and 64-bit code selectors: */ +#define GDT_ENTRY_DEFAULT_USER32_CS 4 +#define GDT_ENTRY_DEFAULT_USER_DS 5 +#define GDT_ENTRY_DEFAULT_USER_CS 6 -/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */ -#define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8) - +/* Needs two entries */ +#define GDT_ENTRY_TSS 8 +/* Needs two entries */ +#define GDT_ENTRY_LDT 10 -#else -#include <asm/cache.h> - -#define GDT_ENTRY_KERNEL32_CS 1 -#define GDT_ENTRY_KERNEL_CS 2 -#define GDT_ENTRY_KERNEL_DS 3 +#define GDT_ENTRY_TLS_MIN 12 +#define GDT_ENTRY_TLS_MAX 14 -#define __KERNEL32_CS (GDT_ENTRY_KERNEL32_CS * 8) +/* Abused to load per CPU data from limit */ +#define GDT_ENTRY_PER_CPU 15 /* - * we cannot use the same code segment descriptor for user and kernel - * -- not even in the long flat mode, because of different DPL /kkeil - * The segment offset needs to contain a RPL. Grr. -AK - * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets) + * Number of entries in the GDT table: */ -#define GDT_ENTRY_DEFAULT_USER32_CS 4 -#define GDT_ENTRY_DEFAULT_USER_DS 5 -#define GDT_ENTRY_DEFAULT_USER_CS 6 -#define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8+3) -#define __USER32_DS __USER_DS - -#define GDT_ENTRY_TSS 8 /* needs two entries */ -#define GDT_ENTRY_LDT 10 /* needs two entries */ -#define GDT_ENTRY_TLS_MIN 12 -#define GDT_ENTRY_TLS_MAX 14 - -#define GDT_ENTRY_PER_CPU 15 /* Abused to load per CPU data from limit */ -#define __PER_CPU_SEG (GDT_ENTRY_PER_CPU * 8 + 3) +#define GDT_ENTRIES 16 -/* TLS indexes for 64bit - hardcoded in arch_prctl */ -#define FS_TLS 0 -#define GS_TLS 1 - -#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3) -#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3) - -#define GDT_ENTRIES 16 +/* + * Segment selector values corresponding to the above entries: + * + * Note, selectors also need to have a correct RPL, + * expressed with the +3 value for user-space selectors: + */ +#define __KERNEL32_CS (GDT_ENTRY_KERNEL32_CS*8) +#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) +#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) +#define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8 + 3) +#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) +#define __USER32_DS __USER_DS +#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) +#define __PER_CPU_SEG (GDT_ENTRY_PER_CPU*8 + 3) + +/* TLS indexes for 64-bit - hardcoded in arch_prctl(): */ +#define FS_TLS 0 +#define GS_TLS 1 + +#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3) +#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3) #endif -#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) -#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) -#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8+3) -#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8+3) #ifndef CONFIG_PARAVIRT -#define get_kernel_rpl() 0 +# define get_kernel_rpl() 0 #endif -#define IDT_ENTRIES 256 -#define NUM_EXCEPTION_VECTORS 32 -/* Bitmask of exception vectors which push an error code on the stack */ -#define EXCEPTION_ERRCODE_MASK 0x00027d00 -#define GDT_SIZE (GDT_ENTRIES * 8) -#define GDT_ENTRY_TLS_ENTRIES 3 -#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) +#define IDT_ENTRIES 256 +#define NUM_EXCEPTION_VECTORS 32 + +/* Bitmask of exception vectors which push an error code on the stack: */ +#define EXCEPTION_ERRCODE_MASK 0x00027d00 + +#define GDT_SIZE (GDT_ENTRIES*8) +#define GDT_ENTRY_TLS_ENTRIES 3 +#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8) #ifdef __KERNEL__ #ifndef __ASSEMBLY__ + extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5]; #ifdef CONFIG_TRACING -#define trace_early_idt_handlers early_idt_handlers +# define trace_early_idt_handlers early_idt_handlers #endif /* @@ -228,37 +260,30 @@ do { \ } while (0) /* - * Save a segment register away + * Save a segment register away: */ #define savesegment(seg, value) \ asm("mov %%" #seg ",%0":"=r" (value) : : "memory") /* - * x86_32 user gs accessors. + * x86-32 user GS accessors: */ #ifdef CONFIG_X86_32 -#ifdef CONFIG_X86_32_LAZY_GS -#define get_user_gs(regs) (u16)({unsigned long v; savesegment(gs, v); v;}) -#define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) -#define task_user_gs(tsk) ((tsk)->thread.gs) -#define lazy_save_gs(v) savesegment(gs, (v)) -#define lazy_load_gs(v) loadsegment(gs, (v)) -#else /* X86_32_LAZY_GS */ -#define get_user_gs(regs) (u16)((regs)->gs) -#define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) -#define task_user_gs(tsk) (task_pt_regs(tsk)->gs) -#define lazy_save_gs(v) do { } while (0) -#define lazy_load_gs(v) do { } while (0) -#endif /* X86_32_LAZY_GS */ +# ifdef CONFIG_X86_32_LAZY_GS +# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; }) +# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v)) +# define task_user_gs(tsk) ((tsk)->thread.gs) +# define lazy_save_gs(v) savesegment(gs, (v)) +# define lazy_load_gs(v) loadsegment(gs, (v)) +# else /* X86_32_LAZY_GS */ +# define get_user_gs(regs) (u16)((regs)->gs) +# define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0) +# define task_user_gs(tsk) (task_pt_regs(tsk)->gs) +# define lazy_save_gs(v) do { } while (0) +# define lazy_load_gs(v) do { } while (0) +# endif /* X86_32_LAZY_GS */ #endif /* X86_32 */ -static inline unsigned long get_limit(unsigned long segment) -{ - unsigned long __limit; - asm("lsll %1,%0" : "=r" (__limit) : "r" (segment)); - return __limit + 1; -} - #endif /* !__ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ff4e7b236e21..f69e06b283fb 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -66,6 +66,11 @@ static inline void x86_ce4100_early_setup(void) { } */ extern struct boot_params boot_params; +static inline bool kaslr_enabled(void) +{ + return !!(boot_params.hdr.loadflags & KASLR_FLAG); +} + /* * Do NOT EVER look at the BIOS memory size location. * It does not work on many machines. diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index 9dfce4e0417d..6fe6b182c998 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -57,9 +57,9 @@ struct sigcontext { unsigned long ip; unsigned long flags; unsigned short cs; - unsigned short gs; - unsigned short fs; - unsigned short __pad0; + unsigned short __pad2; /* Was called gs, but was always zero. */ + unsigned short __pad1; /* Was called fs, but was always zero. */ + unsigned short ss; unsigned long err; unsigned long trapno; unsigned long oldmask; diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index 7a958164088c..89db46752a8f 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -13,9 +13,7 @@ X86_EFLAGS_CF | X86_EFLAGS_RF) void signal_fault(struct pt_regs *regs, void __user *frame, char *where); - -int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, - unsigned long *pax); +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc); int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask); diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 8d3120f4e270..ba665ebd17bb 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -27,23 +27,11 @@ #ifdef CONFIG_X86_SMAP -#define ASM_CLAC \ - 661: ASM_NOP3 ; \ - .pushsection .altinstr_replacement, "ax" ; \ - 662: __ASM_CLAC ; \ - .popsection ; \ - .pushsection .altinstructions, "a" ; \ - altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ; \ - .popsection - -#define ASM_STAC \ - 661: ASM_NOP3 ; \ - .pushsection .altinstr_replacement, "ax" ; \ - 662: __ASM_STAC ; \ - .popsection ; \ - .pushsection .altinstructions, "a" ; \ - altinstruction_entry 661b, 662b, X86_FEATURE_SMAP, 3, 3 ; \ - .popsection +#define ASM_CLAC \ + ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP + +#define ASM_STAC \ + ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP #else /* CONFIG_X86_SMAP */ @@ -61,20 +49,20 @@ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP); + alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP); + alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP); } /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE(ASM_NOP3, __stringify(__ASM_CLAC), X86_FEATURE_SMAP) + ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE(ASM_NOP3, __stringify(__ASM_STAC), X86_FEATURE_SMAP) + ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP) #else /* CONFIG_X86_SMAP */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 8cd1cc3bc835..17a8dced12da 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -150,12 +150,13 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) } void cpu_disable_common(void); -void cpu_die_common(unsigned int cpu); void native_smp_prepare_boot_cpu(void); void native_smp_prepare_cpus(unsigned int max_cpus); void native_smp_cpus_done(unsigned int max_cpus); +void common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_cpu_disable(void); +int common_cpu_die(unsigned int cpu); void native_cpu_die(unsigned int cpu); void native_play_dead(void); void play_dead_common(void); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 6a4b00fafb00..aeb4666e0c0a 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -4,6 +4,8 @@ #ifdef __KERNEL__ +#include <asm/nops.h> + static inline void native_clts(void) { asm volatile("clts"); @@ -199,6 +201,28 @@ static inline void clflushopt(volatile void *__p) "+m" (*(volatile char __force *)__p)); } +static inline void clwb(volatile void *__p) +{ + volatile struct { char x[64]; } *p = __p; + + asm volatile(ALTERNATIVE_2( + ".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])", + ".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */ + X86_FEATURE_CLFLUSHOPT, + ".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */ + X86_FEATURE_CLWB) + : [p] "+m" (*p) + : [pax] "a" (p)); +} + +static inline void pcommit_sfence(void) +{ + alternative(ASM_NOP7, + ".byte 0x66, 0x0f, 0xae, 0xf8\n\t" /* pcommit */ + "sfence", + X86_FEATURE_PCOMMIT); +} + #define nop() asm volatile ("nop") diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 1d4e4f279a32..b4bdec3e9523 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -13,19 +13,44 @@ #include <asm/types.h> /* + * TOP_OF_KERNEL_STACK_PADDING is a number of unused bytes that we + * reserve at the top of the kernel stack. We do it because of a nasty + * 32-bit corner case. On x86_32, the hardware stack frame is + * variable-length. Except for vm86 mode, struct pt_regs assumes a + * maximum-length frame. If we enter from CPL 0, the top 8 bytes of + * pt_regs don't actually exist. Ordinarily this doesn't matter, but it + * does in at least one case: + * + * If we take an NMI early enough in SYSENTER, then we can end up with + * pt_regs that extends above sp0. On the way out, in the espfix code, + * we can read the saved SS value, but that value will be above sp0. + * Without this offset, that can result in a page fault. (We are + * careful that, in this case, the value we read doesn't matter.) + * + * In vm86 mode, the hardware frame is much longer still, but we neither + * access the extra members from NMI context, nor do we write such a + * frame at sp0 at all. + * + * x86_64 has a fixed-length stack frame. + */ +#ifdef CONFIG_X86_32 +# define TOP_OF_KERNEL_STACK_PADDING 8 +#else +# define TOP_OF_KERNEL_STACK_PADDING 0 +#endif + +/* * low level task data that entry.S needs immediate access to * - this struct should fit entirely inside of one cache line * - this struct shares the supervisor stack pages */ #ifndef __ASSEMBLY__ struct task_struct; -struct exec_domain; #include <asm/processor.h> #include <linux/atomic.h> struct thread_info { struct task_struct *task; /* main task structure */ - struct exec_domain *exec_domain; /* execution domain */ __u32 flags; /* low level flags */ __u32 status; /* thread synchronous flags */ __u32 cpu; /* current CPU */ @@ -39,7 +64,6 @@ struct thread_info { #define INIT_THREAD_INFO(tsk) \ { \ .task = &tsk, \ - .exec_domain = &default_exec_domain, \ .flags = 0, \ .cpu = 0, \ .saved_preempt_count = INIT_PREEMPT_COUNT, \ @@ -145,7 +169,6 @@ struct thread_info { #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) #define STACK_WARN (THREAD_SIZE/8) -#define KERNEL_STACK_OFFSET (5*(BITS_PER_LONG/8)) /* * macros/functions for gaining access to the thread information structure @@ -158,10 +181,7 @@ DECLARE_PER_CPU(unsigned long, kernel_stack); static inline struct thread_info *current_thread_info(void) { - struct thread_info *ti; - ti = (void *)(this_cpu_read_stable(kernel_stack) + - KERNEL_STACK_OFFSET - THREAD_SIZE); - return ti; + return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); } static inline unsigned long current_stack_pointer(void) @@ -177,16 +197,37 @@ static inline unsigned long current_stack_pointer(void) #else /* !__ASSEMBLY__ */ -/* how to get the thread information struct from ASM */ +/* Load thread_info address into "reg" */ #define GET_THREAD_INFO(reg) \ _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \ - _ASM_SUB $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg ; + _ASM_SUB $(THREAD_SIZE),reg ; /* - * Same if PER_CPU_VAR(kernel_stack) is, perhaps with some offset, already in - * a certain register (to be used in assembler memory operands). + * ASM operand which evaluates to a 'thread_info' address of + * the current task, if it is known that "reg" is exactly "off" + * bytes below the top of the stack currently. + * + * ( The kernel stack's size is known at build time, it is usually + * 2 or 4 pages, and the bottom of the kernel stack contains + * the thread_info structure. So to access the thread_info very + * quickly from assembly code we can calculate down from the + * top of the kernel stack to the bottom, using constant, + * build-time calculations only. ) + * + * For example, to fetch the current thread_info->flags value into %eax + * on x86-64 defconfig kernels, in syscall entry code where RSP is + * currently at exactly SIZEOF_PTREGS bytes away from the top of the + * stack: + * + * mov ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS), %eax + * + * will translate to: + * + * 8b 84 24 b8 c0 ff ff mov -0x3f48(%rsp), %eax + * + * which is below the current RSP by almost 16K. */ -#define THREAD_INFO(reg, off) KERNEL_STACK_OFFSET+(off)-THREAD_SIZE(reg) +#define ASM_THREAD_INFO(field, reg, off) ((field)+(off)-THREAD_SIZE)(reg) #endif @@ -236,6 +277,16 @@ static inline bool is_ia32_task(void) #endif return false; } + +/* + * Force syscall return via IRET by making it look as if there was + * some work pending. IRET is our most capable (but slowest) syscall + * return path, which is able to restore modified SS, CS and certain + * EFLAGS values that other (fast) syscall return instructions + * are not able to restore properly. + */ +#define force_iret() set_thread_flag(TIF_NOTIFY_RESUME) + #endif /* !__ASSEMBLY__ */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 12a26b979bf1..f2f9b39b274a 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -231,6 +231,6 @@ __copy_from_user_inatomic_nocache(void *dst, const void __user *src, } unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest); +copy_user_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 225b0988043a..ab456dc233b5 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -15,6 +15,7 @@ /* loadflags */ #define LOADED_HIGH (1<<0) +#define KASLR_FLAG (1<<1) #define QUIET_FLAG (1<<5) #define KEEP_SEGMENTS (1<<6) #define CAN_USE_HEAP (1<<7) diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h index d993e33f5236..960a8a9dc4ab 100644 --- a/arch/x86/include/uapi/asm/e820.h +++ b/arch/x86/include/uapi/asm/e820.h @@ -33,6 +33,16 @@ #define E820_NVS 4 #define E820_UNUSABLE 5 +/* + * This is a non-standardized way to represent ADR or NVDIMM regions that + * persist over a reboot. The kernel will ignore their special capabilities + * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * + * ( Note that older platforms also used 6 for the same type of memory, + * but newer versions switched to 12 as 6 was assigned differently. Some + * time they will learn... ) + */ +#define E820_PRAM 12 /* * reserved RAM used by kernel itself diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h index 3ce079136c11..c469490db4a8 100644 --- a/arch/x86/include/uapi/asm/msr-index.h +++ b/arch/x86/include/uapi/asm/msr-index.h @@ -61,6 +61,9 @@ #define MSR_OFFCORE_RSP_1 0x000001a7 #define MSR_NHM_TURBO_RATIO_LIMIT 0x000001ad #define MSR_IVT_TURBO_RATIO_LIMIT 0x000001ae +#define MSR_TURBO_RATIO_LIMIT 0x000001ad +#define MSR_TURBO_RATIO_LIMIT1 0x000001ae +#define MSR_TURBO_RATIO_LIMIT2 0x000001af #define MSR_LBR_SELECT 0x000001c8 #define MSR_LBR_TOS 0x000001c9 @@ -74,6 +77,24 @@ #define MSR_IA32_PERF_CAPABILITIES 0x00000345 #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 +#define MSR_IA32_RTIT_CTL 0x00000570 +#define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_OS BIT(2) +#define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_CR3EN BIT(7) +#define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_TSC_EN BIT(10) +#define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_BRANCH_EN BIT(13) +#define MSR_IA32_RTIT_STATUS 0x00000571 +#define RTIT_STATUS_CONTEXTEN BIT(1) +#define RTIT_STATUS_TRIGGEREN BIT(2) +#define RTIT_STATUS_ERROR BIT(4) +#define RTIT_STATUS_STOPPED BIT(5) +#define MSR_IA32_RTIT_CR3_MATCH 0x00000572 +#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560 +#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561 + #define MSR_MTRRfix64K_00000 0x00000250 #define MSR_MTRRfix16K_80000 0x00000258 #define MSR_MTRRfix16K_A0000 0x00000259 @@ -147,6 +168,11 @@ #define MSR_PP1_ENERGY_STATUS 0x00000641 #define MSR_PP1_POLICY 0x00000642 +#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 +#define MSR_PKG_ANY_CORE_C0_RES 0x00000659 +#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A +#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B + #define MSR_CORE_C1_RES 0x00000660 #define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 diff --git a/arch/x86/include/uapi/asm/ptrace-abi.h b/arch/x86/include/uapi/asm/ptrace-abi.h index 7b0a55a88851..580aee3072e0 100644 --- a/arch/x86/include/uapi/asm/ptrace-abi.h +++ b/arch/x86/include/uapi/asm/ptrace-abi.h @@ -25,13 +25,17 @@ #else /* __i386__ */ #if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS) +/* + * C ABI says these regs are callee-preserved. They aren't saved on kernel entry + * unless syscall needs a complete, fully filled "struct pt_regs". + */ #define R15 0 #define R14 8 #define R13 16 #define R12 24 #define RBP 32 #define RBX 40 -/* arguments: interrupts/non tracing syscalls only save up to here*/ +/* These regs are callee-clobbered. Always saved on kernel entry. */ #define R11 48 #define R10 56 #define R9 64 @@ -41,15 +45,17 @@ #define RDX 96 #define RSI 104 #define RDI 112 -#define ORIG_RAX 120 /* = ERROR */ -/* end of arguments */ -/* cpu exception frame or undefined in case of fast syscall. */ +/* + * On syscall entry, this is syscall#. On CPU exception, this is error code. + * On hw interrupt, it's IRQ number: + */ +#define ORIG_RAX 120 +/* Return frame for iretq */ #define RIP 128 #define CS 136 #define EFLAGS 144 #define RSP 152 #define SS 160 -#define ARGOFFSET R11 #endif /* __ASSEMBLY__ */ /* top of stack page */ diff --git a/arch/x86/include/uapi/asm/ptrace.h b/arch/x86/include/uapi/asm/ptrace.h index ac4b9aa4d999..bc16115af39b 100644 --- a/arch/x86/include/uapi/asm/ptrace.h +++ b/arch/x86/include/uapi/asm/ptrace.h @@ -41,13 +41,17 @@ struct pt_regs { #ifndef __KERNEL__ struct pt_regs { +/* + * C ABI says these regs are callee-preserved. They aren't saved on kernel entry + * unless syscall needs a complete, fully filled "struct pt_regs". + */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long rbp; unsigned long rbx; -/* arguments: non interrupts/non tracing syscalls only save up to here*/ +/* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; @@ -57,9 +61,12 @@ struct pt_regs { unsigned long rdx; unsigned long rsi; unsigned long rdi; +/* + * On syscall entry, this is syscall#. On CPU exception, this is error code. + * On hw interrupt, it's IRQ number: + */ unsigned long orig_rax; -/* end of arguments */ -/* cpu exception frame or undefined */ +/* Return frame for iretq */ unsigned long rip; unsigned long cs; unsigned long eflags; diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index d8b9f9081e86..16dc4e8a2cd3 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -177,9 +177,24 @@ struct sigcontext { __u64 rip; __u64 eflags; /* RFLAGS */ __u16 cs; - __u16 gs; - __u16 fs; - __u16 __pad0; + + /* + * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"), + * Linux saved and restored fs and gs in these slots. This + * was counterproductive, as fsbase and gsbase were never + * saved, so arch_prctl was presumably unreliable. + * + * If these slots are ever needed for any other purpose, there + * is some risk that very old 64-bit binaries could get + * confused. I doubt that many such binaries still work, + * though, since the same patch in 2.5.64 also removed the + * 64-bit set_thread_area syscall, so it appears that there is + * no TLS API that works in both pre- and post-2.5.64 kernels. + */ + __u16 __pad2; /* Was gs. */ + __u16 __pad1; /* Was fs. */ + + __u16 ss; __u64 err; __u64 trapno; __u64 oldmask; diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index c5f1a1deb91a..1fe92181ee9e 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_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_INVEPT 50 +#define EXIT_REASON_RDTSCP 51 #define EXIT_REASON_PREEMPTION_TIMER 52 #define EXIT_REASON_INVVPID 53 #define EXIT_REASON_WBINVD 54 diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index cdb1b70ddad0..9bcd0b56ca17 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += mcount_64.o obj-y += syscall_$(BITS).o vsyscall_gtod.o +obj-$(CONFIG_IA32_EMULATION) += syscall_32.o obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o @@ -94,6 +95,7 @@ obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch_$(BITS).o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o +obj-$(CONFIG_X86_PMEM_LEGACY) += pmem.o obj-$(CONFIG_PCSPKR_PLATFORM) += pcspeaker.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 703130f469ec..aef653193160 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -52,10 +52,25 @@ static int __init setup_noreplace_paravirt(char *str) __setup("noreplace-paravirt", setup_noreplace_paravirt); #endif -#define DPRINTK(fmt, ...) \ -do { \ - if (debug_alternative) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ +#define DPRINTK(fmt, args...) \ +do { \ + if (debug_alternative) \ + printk(KERN_DEBUG "%s: " fmt "\n", __func__, ##args); \ +} while (0) + +#define DUMP_BYTES(buf, len, fmt, args...) \ +do { \ + if (unlikely(debug_alternative)) { \ + int j; \ + \ + if (!(len)) \ + break; \ + \ + printk(KERN_DEBUG fmt, ##args); \ + for (j = 0; j < (len) - 1; j++) \ + printk(KERN_CONT "%02hhx ", buf[j]); \ + printk(KERN_CONT "%02hhx\n", buf[j]); \ + } \ } while (0) /* @@ -243,12 +258,89 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void *text_poke_early(void *addr, const void *opcode, size_t len); -/* Replace instructions with better alternatives for this CPU type. - This runs before SMP is initialized to avoid SMP problems with - self modifying code. This implies that asymmetric systems where - APs have less capabilities than the boot processor are not handled. - Tough. Make sure you disable such features by hand. */ +/* + * Are we looking at a near JMP with a 1 or 4-byte displacement. + */ +static inline bool is_jmp(const u8 opcode) +{ + return opcode == 0xeb || opcode == 0xe9; +} + +static void __init_or_module +recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insnbuf) +{ + u8 *next_rip, *tgt_rip; + s32 n_dspl, o_dspl; + int repl_len; + + if (a->replacementlen != 5) + return; + + o_dspl = *(s32 *)(insnbuf + 1); + + /* next_rip of the replacement JMP */ + next_rip = repl_insn + a->replacementlen; + /* target rip of the replacement JMP */ + tgt_rip = next_rip + o_dspl; + n_dspl = tgt_rip - orig_insn; + + DPRINTK("target RIP: %p, new_displ: 0x%x", tgt_rip, n_dspl); + + if (tgt_rip - orig_insn >= 0) { + if (n_dspl - 2 <= 127) + goto two_byte_jmp; + else + goto five_byte_jmp; + /* negative offset */ + } else { + if (((n_dspl - 2) & 0xff) == (n_dspl - 2)) + goto two_byte_jmp; + else + goto five_byte_jmp; + } + +two_byte_jmp: + n_dspl -= 2; + + insnbuf[0] = 0xeb; + insnbuf[1] = (s8)n_dspl; + add_nops(insnbuf + 2, 3); + + repl_len = 2; + goto done; + +five_byte_jmp: + n_dspl -= 5; + + insnbuf[0] = 0xe9; + *(s32 *)&insnbuf[1] = n_dspl; + repl_len = 5; + +done: + + DPRINTK("final displ: 0x%08x, JMP 0x%lx", + n_dspl, (unsigned long)orig_insn + n_dspl + repl_len); +} + +static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr) +{ + if (instr[0] != 0x90) + return; + + add_nops(instr + (a->instrlen - a->padlen), a->padlen); + + DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ", + instr, a->instrlen - a->padlen, a->padlen); +} + +/* + * Replace instructions with better alternatives for this CPU type. This runs + * before SMP is initialized to avoid SMP problems with self modifying code. + * This implies that asymmetric systems where APs have less capabilities than + * the boot processor are not handled. Tough. Make sure you disable such + * features by hand. + */ void __init_or_module apply_alternatives(struct alt_instr *start, struct alt_instr *end) { @@ -256,10 +348,10 @@ void __init_or_module apply_alternatives(struct alt_instr *start, u8 *instr, *replacement; u8 insnbuf[MAX_PATCH_LEN]; - DPRINTK("%s: alt table %p -> %p\n", __func__, start, end); + DPRINTK("alt table %p -> %p", start, end); /* * The scan order should be from start to end. A later scanned - * alternative code can overwrite a previous scanned alternative code. + * alternative code can overwrite previously scanned alternative code. * Some kernel functions (e.g. memcpy, memset, etc) use this order to * patch code. * @@ -267,29 +359,54 @@ void __init_or_module apply_alternatives(struct alt_instr *start, * order. */ for (a = start; a < end; a++) { + int insnbuf_sz = 0; + instr = (u8 *)&a->instr_offset + a->instr_offset; replacement = (u8 *)&a->repl_offset + a->repl_offset; - BUG_ON(a->replacementlen > a->instrlen); BUG_ON(a->instrlen > sizeof(insnbuf)); BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); - if (!boot_cpu_has(a->cpuid)) + if (!boot_cpu_has(a->cpuid)) { + if (a->padlen > 1) + optimize_nops(a, instr); + continue; + } + + DPRINTK("feat: %d*32+%d, old: (%p, len: %d), repl: (%p, len: %d), pad: %d", + a->cpuid >> 5, + a->cpuid & 0x1f, + instr, a->instrlen, + replacement, a->replacementlen, a->padlen); + + DUMP_BYTES(instr, a->instrlen, "%p: old_insn: ", instr); + DUMP_BYTES(replacement, a->replacementlen, "%p: rpl_insn: ", replacement); memcpy(insnbuf, replacement, a->replacementlen); + insnbuf_sz = a->replacementlen; /* 0xe8 is a relative jump; fix the offset. */ - if (*insnbuf == 0xe8 && a->replacementlen == 5) - *(s32 *)(insnbuf + 1) += replacement - instr; + if (*insnbuf == 0xe8 && a->replacementlen == 5) { + *(s32 *)(insnbuf + 1) += replacement - instr; + DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx", + *(s32 *)(insnbuf + 1), + (unsigned long)instr + *(s32 *)(insnbuf + 1) + 5); + } + + if (a->replacementlen && is_jmp(replacement[0])) + recompute_jump(a, instr, replacement, insnbuf); - add_nops(insnbuf + a->replacementlen, - a->instrlen - a->replacementlen); + if (a->instrlen > a->replacementlen) { + add_nops(insnbuf + a->replacementlen, + a->instrlen - a->replacementlen); + insnbuf_sz += a->instrlen - a->replacementlen; + } + DUMP_BYTES(insnbuf, insnbuf_sz, "%p: final_insn: ", instr); - text_poke_early(instr, insnbuf, a->instrlen); + text_poke_early(instr, insnbuf, insnbuf_sz); } } #ifdef CONFIG_SMP - static void alternatives_smp_lock(const s32 *start, const s32 *end, u8 *text, u8 *text_end) { @@ -371,8 +488,8 @@ void __init_or_module alternatives_smp_module_add(struct module *mod, smp->locks_end = locks_end; smp->text = text; smp->text_end = text_end; - DPRINTK("%s: locks %p -> %p, text %p -> %p, name %s\n", - __func__, smp->locks, smp->locks_end, + DPRINTK("locks %p -> %p, text %p -> %p, name %s\n", + smp->locks, smp->locks_end, smp->text, smp->text_end, smp->name); list_add_tail(&smp->next, &smp_alt_modules); @@ -440,7 +557,7 @@ int alternatives_text_reserved(void *start, void *end) return 0; } -#endif +#endif /* CONFIG_SMP */ #ifdef CONFIG_PARAVIRT void __init_or_module apply_paravirt(struct paravirt_patch_site *start, @@ -601,7 +718,7 @@ int poke_int3_handler(struct pt_regs *regs) if (likely(!bp_patching_in_progress)) return 0; - if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr) + if (user_mode(regs) || regs->ip != (unsigned long)bp_int3_addr) return 0; /* set up the specified breakpoint handler */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ad3639ae1b9b..dcb52850a28f 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1084,67 +1084,6 @@ void lapic_shutdown(void) local_irq_restore(flags); } -/* - * This is to verify that we're looking at a real local APIC. - * Check these against your board if the CPUs aren't getting - * started for no apparent reason. - */ -int __init verify_local_APIC(void) -{ - unsigned int reg0, reg1; - - /* - * The version register is read-only in a real APIC. - */ - reg0 = apic_read(APIC_LVR); - apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg0); - apic_write(APIC_LVR, reg0 ^ APIC_LVR_MASK); - reg1 = apic_read(APIC_LVR); - apic_printk(APIC_DEBUG, "Getting VERSION: %x\n", reg1); - - /* - * The two version reads above should print the same - * numbers. If the second one is different, then we - * poke at a non-APIC. - */ - if (reg1 != reg0) - return 0; - - /* - * Check if the version looks reasonably. - */ - reg1 = GET_APIC_VERSION(reg0); - if (reg1 == 0x00 || reg1 == 0xff) - return 0; - reg1 = lapic_get_maxlvt(); - if (reg1 < 0x02 || reg1 == 0xff) - return 0; - - /* - * The ID register is read/write in a real APIC. - */ - reg0 = apic_read(APIC_ID); - apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg0); - apic_write(APIC_ID, reg0 ^ apic->apic_id_mask); - reg1 = apic_read(APIC_ID); - apic_printk(APIC_DEBUG, "Getting ID: %x\n", reg1); - apic_write(APIC_ID, reg0); - if (reg1 != (reg0 ^ apic->apic_id_mask)) - return 0; - - /* - * The next two are just to see if we have sane values. - * They're only really relevant if we're in Virtual Wire - * compatibility mode, but most boxes are anymore. - */ - reg0 = apic_read(APIC_LVT0); - apic_printk(APIC_DEBUG, "Getting LVT0: %x\n", reg0); - reg1 = apic_read(APIC_LVT1); - apic_printk(APIC_DEBUG, "Getting LVT1: %x\n", reg1); - - return 1; -} - /** * sync_Arb_IDs - synchronize APIC bus arbitration IDs */ @@ -2283,7 +2222,6 @@ int __init APIC_init_uniprocessor(void) disable_ioapic_support(); default_setup_apic_routing(); - verify_local_APIC(); apic_bsp_setup(true); return 0; } diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index e658f21681c8..d9d0bd2faaf4 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -135,12 +135,12 @@ static void init_x2apic_ldr(void) per_cpu(x86_cpu_to_logical_apicid, this_cpu) = apic_read(APIC_LDR); - __cpu_set(this_cpu, per_cpu(cpus_in_cluster, this_cpu)); + cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, this_cpu)); for_each_online_cpu(cpu) { if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu)) continue; - __cpu_set(this_cpu, per_cpu(cpus_in_cluster, cpu)); - __cpu_set(cpu, per_cpu(cpus_in_cluster, this_cpu)); + cpumask_set_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu)); + cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu)); } } @@ -195,7 +195,7 @@ static int x2apic_init_cpu_notifier(void) BUG_ON(!per_cpu(cpus_in_cluster, cpu) || !per_cpu(ipi_mask, cpu)); - __cpu_set(cpu, per_cpu(cpus_in_cluster, cpu)); + cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); register_hotcpu_notifier(&x2apic_cpu_notifier); return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 8e9dcfd630e4..c8d92950bc04 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -144,33 +144,60 @@ static void __init uv_set_apicid_hibit(void) static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { - int pnodeid, is_uv1, is_uv2, is_uv3; - - is_uv1 = !strcmp(oem_id, "SGI"); - is_uv2 = !strcmp(oem_id, "SGI2"); - is_uv3 = !strncmp(oem_id, "SGI3", 4); /* there are varieties of UV3 */ - if (is_uv1 || is_uv2 || is_uv3) { - uv_hub_info->hub_revision = - (is_uv1 ? UV1_HUB_REVISION_BASE : - (is_uv2 ? UV2_HUB_REVISION_BASE : - UV3_HUB_REVISION_BASE)); - pnodeid = early_get_pnodeid(); - early_get_apic_pnode_shift(); - x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; - x86_platform.nmi_init = uv_nmi_init; - if (!strcmp(oem_table_id, "UVL")) - uv_system_type = UV_LEGACY_APIC; - else if (!strcmp(oem_table_id, "UVX")) - uv_system_type = UV_X2APIC; - else if (!strcmp(oem_table_id, "UVH")) { - __this_cpu_write(x2apic_extra_bits, - pnodeid << uvh_apicid.s.pnode_shift); - uv_system_type = UV_NON_UNIQUE_APIC; - uv_set_apicid_hibit(); - return 1; - } + int pnodeid; + int uv_apic; + + if (strncmp(oem_id, "SGI", 3) != 0) + return 0; + + /* + * Determine UV arch type. + * SGI: UV100/1000 + * SGI2: UV2000/3000 + * SGI3: UV300 (truncated to 4 chars because of different varieties) + */ + uv_hub_info->hub_revision = + !strncmp(oem_id, "SGI3", 4) ? UV3_HUB_REVISION_BASE : + !strcmp(oem_id, "SGI2") ? UV2_HUB_REVISION_BASE : + !strcmp(oem_id, "SGI") ? UV1_HUB_REVISION_BASE : 0; + + if (uv_hub_info->hub_revision == 0) + goto badbios; + + pnodeid = early_get_pnodeid(); + early_get_apic_pnode_shift(); + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; + x86_platform.nmi_init = uv_nmi_init; + + if (!strcmp(oem_table_id, "UVX")) { /* most common */ + uv_system_type = UV_X2APIC; + uv_apic = 0; + + } else if (!strcmp(oem_table_id, "UVH")) { /* only UV1 systems */ + uv_system_type = UV_NON_UNIQUE_APIC; + __this_cpu_write(x2apic_extra_bits, + pnodeid << uvh_apicid.s.pnode_shift); + uv_set_apicid_hibit(); + uv_apic = 1; + + } else if (!strcmp(oem_table_id, "UVL")) { /* only used for */ + uv_system_type = UV_LEGACY_APIC; /* very small systems */ + uv_apic = 0; + + } else { + goto badbios; } - return 0; + + pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", + oem_id, oem_table_id, uv_system_type, + uv_min_hub_revision_id, uv_apic); + + return uv_apic; + +badbios: + pr_err("UV: OEM_ID:%s OEM_TABLE_ID:%s\n", oem_id, oem_table_id); + pr_err("Current BIOS not supported, update kernel and/or BIOS\n"); + BUG(); } enum uv_system_type get_uv_system_type(void) @@ -854,10 +881,14 @@ void __init uv_system_init(void) unsigned long mmr_base, present, paddr; unsigned short pnode_mask; unsigned char n_lshift; - char *hub = (is_uv1_hub() ? "UV1" : - (is_uv2_hub() ? "UV2" : - "UV3")); + char *hub = (is_uv1_hub() ? "UV100/1000" : + (is_uv2_hub() ? "UV2000/3000" : + (is_uv3_hub() ? "UV300" : NULL))); + if (!hub) { + pr_err("UV: Unknown/unsupported UV hub\n"); + return; + } pr_info("UV: Found %s hub\n", hub); map_low_mmrs(); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 3b3b9d33ac1d..47703aed74cf 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -68,7 +68,7 @@ void foo(void) /* Offset from the sysenter stack to tss.sp0 */ DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - - sizeof(struct tss_struct)); + offsetofend(struct tss_struct, SYSENTER_stack)); #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index fdcbb4d27c9f..5ce6f2da8763 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -81,6 +81,7 @@ int main(void) #undef ENTRY OFFSET(TSS_ist, tss_struct, x86_tss.ist); + OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); BLANK(); DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 80091ae54c2b..9bff68798836 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,8 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o endif obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o -obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o perf_event_intel_cqm.o +obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_pt.o perf_event_intel_bts.o obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \ perf_event_intel_uncore_snb.o \ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a220239cea65..fd470ebf924e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -5,6 +5,7 @@ #include <linux/io.h> #include <linux/sched.h> +#include <linux/random.h> #include <asm/processor.h> #include <asm/apic.h> #include <asm/cpu.h> @@ -488,6 +489,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) va_align.mask = (upperbit - 1) & PAGE_MASK; va_align.flags = ALIGN_VA_32 | ALIGN_VA_64; + + /* A random value per boot for bit slice [12:upper_bit) */ + va_align.bits = get_random_int() & va_align.mask; } } @@ -711,6 +715,11 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); + + /* 3DNow or LM implies PREFETCHW */ + if (!cpu_has(c, X86_FEATURE_3DNOWPREFETCH)) + if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM)) + set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2346c95c6ab1..a62cf04dac8a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -646,6 +646,30 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[10] = eax; } + /* Additional Intel-defined flags: level 0x0000000F */ + if (c->cpuid_level >= 0x0000000F) { + u32 eax, ebx, ecx, edx; + + /* QoS sub-leaf, EAX=0Fh, ECX=0 */ + cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); + c->x86_capability[11] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { + /* will be overridden if occupancy monitoring exists */ + c->x86_cache_max_rmid = ebx; + + /* QoS sub-leaf, EAX=0Fh, ECX=1 */ + cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); + c->x86_capability[12] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { + c->x86_cache_max_rmid = ecx; + c->x86_cache_occ_scale = ebx; + } + } else { + c->x86_cache_max_rmid = -1; + c->x86_cache_occ_scale = -1; + } + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; @@ -834,6 +858,20 @@ static void generic_identify(struct cpuinfo_x86 *c) detect_nopl(c); } +static void x86_init_cache_qos(struct cpuinfo_x86 *c) +{ + /* + * The heavy lifting of max_rmid and cache_occ_scale are handled + * in get_cpu_cap(). Here we just set the max_rmid for the boot_cpu + * in case CQM bits really aren't there in this CPU. + */ + if (c != &boot_cpu_data) { + boot_cpu_data.x86_cache_max_rmid = + min(boot_cpu_data.x86_cache_max_rmid, + c->x86_cache_max_rmid); + } +} + /* * This does the hard work of actually picking apart the CPU stuff... */ @@ -923,6 +961,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) init_hypervisor(c); x86_init_rdrand(c); + x86_init_cache_qos(c); /* * Clear/Set all flags overriden by options, need do it @@ -959,38 +998,37 @@ static void identify_cpu(struct cpuinfo_x86 *c) #endif } -#ifdef CONFIG_X86_64 -#ifdef CONFIG_IA32_EMULATION -/* May not be __init: called during resume */ -static void syscall32_cpu_init(void) -{ - /* Load these always in case some future AMD CPU supports - SYSENTER from compat mode too. */ - wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - - wrmsrl(MSR_CSTAR, ia32_cstar_target); -} -#endif /* CONFIG_IA32_EMULATION */ -#endif /* CONFIG_X86_64 */ - +/* + * Set up the CPU state needed to execute SYSENTER/SYSEXIT instructions + * on 32-bit kernels: + */ #ifdef CONFIG_X86_32 void enable_sep_cpu(void) { - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); + struct tss_struct *tss; + int cpu; - if (!boot_cpu_has(X86_FEATURE_SEP)) { - put_cpu(); - return; - } + cpu = get_cpu(); + tss = &per_cpu(cpu_tss, cpu); + + if (!boot_cpu_has(X86_FEATURE_SEP)) + goto out; + + /* + * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- + * see the big comment in struct x86_hw_tss's definition. + */ tss->x86_tss.ss1 = __KERNEL_CS; - tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss; - wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); - wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0); - wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0); + wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); + + wrmsr(MSR_IA32_SYSENTER_ESP, + (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), + 0); + + wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)ia32_sysenter_target, 0); + +out: put_cpu(); } #endif @@ -1118,7 +1156,7 @@ static __init int setup_disablecpuid(char *arg) __setup("clearcpuid=", setup_disablecpuid); DEFINE_PER_CPU(unsigned long, kernel_stack) = - (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE; + (unsigned long)&init_thread_union + THREAD_SIZE; EXPORT_PER_CPU_SYMBOL(kernel_stack); #ifdef CONFIG_X86_64 @@ -1130,8 +1168,8 @@ DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; /* - * The following four percpu variables are hot. Align current_task to - * cacheline size such that all four fall in the same cacheline. + * The following percpu variables are hot. Align current_task to + * cacheline size such that they fall in the same cacheline. */ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = &init_task; @@ -1171,10 +1209,23 @@ void syscall_init(void) */ wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); wrmsrl(MSR_LSTAR, system_call); - wrmsrl(MSR_CSTAR, ignore_sysret); #ifdef CONFIG_IA32_EMULATION - syscall32_cpu_init(); + wrmsrl(MSR_CSTAR, ia32_cstar_target); + /* + * This only works on Intel CPUs. + * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. + * This does not cause SYSENTER to jump to the wrong location, because + * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). + */ + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); +#else + wrmsrl(MSR_CSTAR, ignore_sysret); + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); #endif /* Flags to clear on syscall */ @@ -1226,6 +1277,15 @@ DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); +/* + * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find + * the top of the kernel stack. Use an extra percpu variable to track the + * top of the kernel stack directly. + */ +DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = + (unsigned long)&init_thread_union + THREAD_SIZE; +EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack); + #ifdef CONFIG_CC_STACKPROTECTOR DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif @@ -1307,7 +1367,7 @@ void cpu_init(void) */ load_ucode_ap(); - t = &per_cpu(init_tss, cpu); + t = &per_cpu(cpu_tss, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1391,7 +1451,7 @@ void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(init_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss, cpu); struct thread_struct *thread = &curr->thread; wait_for_master_cpu(cpu); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 659643376dbf..edcb0e28c336 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -7,16 +7,14 @@ * Andi Kleen / Andreas Herrmann : CPUID4 emulation on AMD. */ -#include <linux/init.h> #include <linux/slab.h> -#include <linux/device.h> -#include <linux/compiler.h> +#include <linux/cacheinfo.h> #include <linux/cpu.h> #include <linux/sched.h> +#include <linux/sysfs.h> #include <linux/pci.h> #include <asm/processor.h> -#include <linux/smp.h> #include <asm/amd_nb.h> #include <asm/smp.h> @@ -116,10 +114,10 @@ static const struct _cache_table cache_table[] = enum _cache_type { - CACHE_TYPE_NULL = 0, - CACHE_TYPE_DATA = 1, - CACHE_TYPE_INST = 2, - CACHE_TYPE_UNIFIED = 3 + CTYPE_NULL = 0, + CTYPE_DATA = 1, + CTYPE_INST = 2, + CTYPE_UNIFIED = 3 }; union _cpuid4_leaf_eax { @@ -159,11 +157,6 @@ struct _cpuid4_info_regs { struct amd_northbridge *nb; }; -struct _cpuid4_info { - struct _cpuid4_info_regs base; - DECLARE_BITMAP(shared_cpu_map, NR_CPUS); -}; - unsigned short num_cache_leaves; /* AMD doesn't have CPUID4. Emulate it here to report the same @@ -220,6 +213,13 @@ static const unsigned short assocs[] = { static const unsigned char levels[] = { 1, 1, 2, 3 }; static const unsigned char types[] = { 1, 2, 3, 3 }; +static const enum cache_type cache_type_map[] = { + [CTYPE_NULL] = CACHE_TYPE_NOCACHE, + [CTYPE_DATA] = CACHE_TYPE_DATA, + [CTYPE_INST] = CACHE_TYPE_INST, + [CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED, +}; + static void amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, union _cpuid4_leaf_ebx *ebx, @@ -291,14 +291,8 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, (ebx->split.ways_of_associativity + 1) - 1; } -struct _cache_attr { - struct attribute attr; - ssize_t (*show)(struct _cpuid4_info *, char *, unsigned int); - ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count, - unsigned int); -}; - #if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS) + /* * L3 cache descriptors */ @@ -325,20 +319,6 @@ static void amd_calc_l3_indices(struct amd_northbridge *nb) l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1; } -static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) -{ - int node; - - /* only for L3, and not in virtualized environments */ - if (index < 3) - return; - - node = amd_get_nb_id(smp_processor_id()); - this_leaf->nb = node_to_amd_nb(node); - if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) - amd_calc_l3_indices(this_leaf->nb); -} - /* * check whether a slot used for disabling an L3 index is occupied. * @l3: L3 cache descriptor @@ -359,15 +339,13 @@ int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot) return -1; } -static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, +static ssize_t show_cache_disable(struct cacheinfo *this_leaf, char *buf, unsigned int slot) { int index; + struct amd_northbridge *nb = this_leaf->priv; - if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) - return -EINVAL; - - index = amd_get_l3_disable_slot(this_leaf->base.nb, slot); + index = amd_get_l3_disable_slot(nb, slot); if (index >= 0) return sprintf(buf, "%d\n", index); @@ -376,9 +354,10 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf, #define SHOW_CACHE_DISABLE(slot) \ static ssize_t \ -show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf, \ - unsigned int cpu) \ +cache_disable_##slot##_show(struct device *dev, \ + struct device_attribute *attr, char *buf) \ { \ + struct cacheinfo *this_leaf = dev_get_drvdata(dev); \ return show_cache_disable(this_leaf, buf, slot); \ } SHOW_CACHE_DISABLE(0) @@ -446,25 +425,23 @@ int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot, return 0; } -static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, - const char *buf, size_t count, - unsigned int slot) +static ssize_t store_cache_disable(struct cacheinfo *this_leaf, + const char *buf, size_t count, + unsigned int slot) { unsigned long val = 0; int cpu, err = 0; + struct amd_northbridge *nb = this_leaf->priv; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) - return -EINVAL; - - cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map)); + cpu = cpumask_first(&this_leaf->shared_cpu_map); if (kstrtoul(buf, 10, &val) < 0) return -EINVAL; - err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val); + err = amd_set_l3_disable_slot(nb, cpu, slot, val); if (err) { if (err == -EEXIST) pr_warning("L3 slot %d in use/index already disabled!\n", @@ -476,41 +453,36 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf, #define STORE_CACHE_DISABLE(slot) \ static ssize_t \ -store_cache_disable_##slot(struct _cpuid4_info *this_leaf, \ - const char *buf, size_t count, \ - unsigned int cpu) \ +cache_disable_##slot##_store(struct device *dev, \ + struct device_attribute *attr, \ + const char *buf, size_t count) \ { \ + struct cacheinfo *this_leaf = dev_get_drvdata(dev); \ return store_cache_disable(this_leaf, buf, count, slot); \ } STORE_CACHE_DISABLE(0) STORE_CACHE_DISABLE(1) -static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644, - show_cache_disable_0, store_cache_disable_0); -static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644, - show_cache_disable_1, store_cache_disable_1); - -static ssize_t -show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu) +static ssize_t subcaches_show(struct device *dev, + struct device_attribute *attr, char *buf) { - if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) - return -EINVAL; + struct cacheinfo *this_leaf = dev_get_drvdata(dev); + int cpu = cpumask_first(&this_leaf->shared_cpu_map); return sprintf(buf, "%x\n", amd_get_subcaches(cpu)); } -static ssize_t -store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, - unsigned int cpu) +static ssize_t subcaches_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) { + struct cacheinfo *this_leaf = dev_get_drvdata(dev); + int cpu = cpumask_first(&this_leaf->shared_cpu_map); unsigned long val; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) - return -EINVAL; - if (kstrtoul(buf, 16, &val) < 0) return -EINVAL; @@ -520,9 +492,92 @@ store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count, return count; } -static struct _cache_attr subcaches = - __ATTR(subcaches, 0644, show_subcaches, store_subcaches); +static DEVICE_ATTR_RW(cache_disable_0); +static DEVICE_ATTR_RW(cache_disable_1); +static DEVICE_ATTR_RW(subcaches); + +static umode_t +cache_private_attrs_is_visible(struct kobject *kobj, + struct attribute *attr, int unused) +{ + struct device *dev = kobj_to_dev(kobj); + struct cacheinfo *this_leaf = dev_get_drvdata(dev); + umode_t mode = attr->mode; + + if (!this_leaf->priv) + return 0; + + if ((attr == &dev_attr_subcaches.attr) && + amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + return mode; + + if ((attr == &dev_attr_cache_disable_0.attr || + attr == &dev_attr_cache_disable_1.attr) && + amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) + return mode; + + return 0; +} + +static struct attribute_group cache_private_group = { + .is_visible = cache_private_attrs_is_visible, +}; + +static void init_amd_l3_attrs(void) +{ + int n = 1; + static struct attribute **amd_l3_attrs; + + if (amd_l3_attrs) /* already initialized */ + return; + + if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) + n += 2; + if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + n += 1; + + amd_l3_attrs = kcalloc(n, sizeof(*amd_l3_attrs), GFP_KERNEL); + if (!amd_l3_attrs) + return; + + n = 0; + if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) { + amd_l3_attrs[n++] = &dev_attr_cache_disable_0.attr; + amd_l3_attrs[n++] = &dev_attr_cache_disable_1.attr; + } + if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) + amd_l3_attrs[n++] = &dev_attr_subcaches.attr; + cache_private_group.attrs = amd_l3_attrs; +} + +const struct attribute_group * +cache_get_priv_group(struct cacheinfo *this_leaf) +{ + struct amd_northbridge *nb = this_leaf->priv; + + if (this_leaf->level < 3 || !nb) + return NULL; + + if (nb && nb->l3_cache.indices) + init_amd_l3_attrs(); + + return &cache_private_group; +} + +static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) +{ + int node; + + /* only for L3, and not in virtualized environments */ + if (index < 3) + return; + + node = amd_get_nb_id(smp_processor_id()); + this_leaf->nb = node_to_amd_nb(node); + if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) + amd_calc_l3_indices(this_leaf->nb); +} #else #define amd_init_l3_cache(x, y) #endif /* CONFIG_AMD_NB && CONFIG_SYSFS */ @@ -546,7 +601,7 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx); } - if (eax.split.type == CACHE_TYPE_NULL) + if (eax.split.type == CTYPE_NULL) return -EIO; /* better error ? */ this_leaf->eax = eax; @@ -575,7 +630,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) /* Do cpuid(op) loop to find out num_cache_leaves */ cpuid_count(op, i, &eax, &ebx, &ecx, &edx); cache_eax.full = eax; - } while (cache_eax.split.type != CACHE_TYPE_NULL); + } while (cache_eax.split.type != CTYPE_NULL); return i; } @@ -626,9 +681,9 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) switch (this_leaf.eax.split.level) { case 1: - if (this_leaf.eax.split.type == CACHE_TYPE_DATA) + if (this_leaf.eax.split.type == CTYPE_DATA) new_l1d = this_leaf.size/1024; - else if (this_leaf.eax.split.type == CACHE_TYPE_INST) + else if (this_leaf.eax.split.type == CTYPE_INST) new_l1i = this_leaf.size/1024; break; case 2: @@ -747,55 +802,52 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c) return l2; } -#ifdef CONFIG_SYSFS - -/* pointer to _cpuid4_info array (for each cache leaf) */ -static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info); -#define CPUID4_INFO_IDX(x, y) (&((per_cpu(ici_cpuid4_info, x))[y])) - -#ifdef CONFIG_SMP - -static int cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) +static int __cache_amd_cpumap_setup(unsigned int cpu, int index, + struct _cpuid4_info_regs *base) { - struct _cpuid4_info *this_leaf; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf; int i, sibling; if (cpu_has_topoext) { unsigned int apicid, nshared, first, last; - if (!per_cpu(ici_cpuid4_info, cpu)) - return 0; - - this_leaf = CPUID4_INFO_IDX(cpu, index); - nshared = this_leaf->base.eax.split.num_threads_sharing + 1; + this_leaf = this_cpu_ci->info_list + index; + nshared = base->eax.split.num_threads_sharing + 1; apicid = cpu_data(cpu).apicid; first = apicid - (apicid % nshared); last = first + nshared - 1; for_each_online_cpu(i) { + this_cpu_ci = get_cpu_cacheinfo(i); + if (!this_cpu_ci->info_list) + continue; + apicid = cpu_data(i).apicid; if ((apicid < first) || (apicid > last)) continue; - if (!per_cpu(ici_cpuid4_info, i)) - continue; - this_leaf = CPUID4_INFO_IDX(i, index); + + this_leaf = this_cpu_ci->info_list + index; for_each_online_cpu(sibling) { apicid = cpu_data(sibling).apicid; if ((apicid < first) || (apicid > last)) continue; - set_bit(sibling, this_leaf->shared_cpu_map); + cpumask_set_cpu(sibling, + &this_leaf->shared_cpu_map); } } } else if (index == 3) { for_each_cpu(i, cpu_llc_shared_mask(cpu)) { - if (!per_cpu(ici_cpuid4_info, i)) + this_cpu_ci = get_cpu_cacheinfo(i); + if (!this_cpu_ci->info_list) continue; - this_leaf = CPUID4_INFO_IDX(i, index); + this_leaf = this_cpu_ci->info_list + index; for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) { if (!cpu_online(sibling)) continue; - set_bit(sibling, this_leaf->shared_cpu_map); + cpumask_set_cpu(sibling, + &this_leaf->shared_cpu_map); } } } else @@ -804,457 +856,86 @@ static int cache_shared_amd_cpu_map_setup(unsigned int cpu, int index) return 1; } -static void cache_shared_cpu_map_setup(unsigned int cpu, int index) +static void __cache_cpumap_setup(unsigned int cpu, int index, + struct _cpuid4_info_regs *base) { - struct _cpuid4_info *this_leaf, *sibling_leaf; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf, *sibling_leaf; unsigned long num_threads_sharing; int index_msb, i; struct cpuinfo_x86 *c = &cpu_data(cpu); if (c->x86_vendor == X86_VENDOR_AMD) { - if (cache_shared_amd_cpu_map_setup(cpu, index)) + if (__cache_amd_cpumap_setup(cpu, index, base)) return; } - this_leaf = CPUID4_INFO_IDX(cpu, index); - num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing; + this_leaf = this_cpu_ci->info_list + index; + num_threads_sharing = 1 + base->eax.split.num_threads_sharing; + cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map); if (num_threads_sharing == 1) - cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map)); - else { - index_msb = get_count_order(num_threads_sharing); - - for_each_online_cpu(i) { - if (cpu_data(i).apicid >> index_msb == - c->apicid >> index_msb) { - cpumask_set_cpu(i, - to_cpumask(this_leaf->shared_cpu_map)); - if (i != cpu && per_cpu(ici_cpuid4_info, i)) { - sibling_leaf = - CPUID4_INFO_IDX(i, index); - cpumask_set_cpu(cpu, to_cpumask( - sibling_leaf->shared_cpu_map)); - } - } - } - } -} -static void cache_remove_shared_cpu_map(unsigned int cpu, int index) -{ - struct _cpuid4_info *this_leaf, *sibling_leaf; - int sibling; - - this_leaf = CPUID4_INFO_IDX(cpu, index); - for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) { - sibling_leaf = CPUID4_INFO_IDX(sibling, index); - cpumask_clear_cpu(cpu, - to_cpumask(sibling_leaf->shared_cpu_map)); - } -} -#else -static void cache_shared_cpu_map_setup(unsigned int cpu, int index) -{ -} - -static void cache_remove_shared_cpu_map(unsigned int cpu, int index) -{ -} -#endif - -static void free_cache_attributes(unsigned int cpu) -{ - int i; - - for (i = 0; i < num_cache_leaves; i++) - cache_remove_shared_cpu_map(cpu, i); - - kfree(per_cpu(ici_cpuid4_info, cpu)); - per_cpu(ici_cpuid4_info, cpu) = NULL; -} - -static void get_cpu_leaves(void *_retval) -{ - int j, *retval = _retval, cpu = smp_processor_id(); + return; - /* Do cpuid and store the results */ - for (j = 0; j < num_cache_leaves; j++) { - struct _cpuid4_info *this_leaf = CPUID4_INFO_IDX(cpu, j); + index_msb = get_count_order(num_threads_sharing); - *retval = cpuid4_cache_lookup_regs(j, &this_leaf->base); - if (unlikely(*retval < 0)) { - int i; + for_each_online_cpu(i) + if (cpu_data(i).apicid >> index_msb == c->apicid >> index_msb) { + struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i); - for (i = 0; i < j; i++) - cache_remove_shared_cpu_map(cpu, i); - break; + if (i == cpu || !sib_cpu_ci->info_list) + continue;/* skip if itself or no cacheinfo */ + sibling_leaf = sib_cpu_ci->info_list + index; + cpumask_set_cpu(i, &this_leaf->shared_cpu_map); + cpumask_set_cpu(cpu, &sibling_leaf->shared_cpu_map); } - cache_shared_cpu_map_setup(cpu, j); - } } -static int detect_cache_attributes(unsigned int cpu) +static void ci_leaf_init(struct cacheinfo *this_leaf, + struct _cpuid4_info_regs *base) { - int retval; - - if (num_cache_leaves == 0) - return -ENOENT; - - per_cpu(ici_cpuid4_info, cpu) = kzalloc( - sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL); - if (per_cpu(ici_cpuid4_info, cpu) == NULL) - return -ENOMEM; - - smp_call_function_single(cpu, get_cpu_leaves, &retval, true); - if (retval) { - kfree(per_cpu(ici_cpuid4_info, cpu)); - per_cpu(ici_cpuid4_info, cpu) = NULL; - } - - return retval; + this_leaf->level = base->eax.split.level; + this_leaf->type = cache_type_map[base->eax.split.type]; + this_leaf->coherency_line_size = + base->ebx.split.coherency_line_size + 1; + this_leaf->ways_of_associativity = + base->ebx.split.ways_of_associativity + 1; + this_leaf->size = base->size; + this_leaf->number_of_sets = base->ecx.split.number_of_sets + 1; + this_leaf->physical_line_partition = + base->ebx.split.physical_line_partition + 1; + this_leaf->priv = base->nb; } -#include <linux/kobject.h> -#include <linux/sysfs.h> -#include <linux/cpu.h> - -/* pointer to kobject for cpuX/cache */ -static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject); - -struct _index_kobject { - struct kobject kobj; - unsigned int cpu; - unsigned short index; -}; - -/* pointer to array of kobjects for cpuX/cache/indexY */ -static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject); -#define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(ici_index_kobject, x))[y])) - -#define show_one_plus(file_name, object, val) \ -static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \ - unsigned int cpu) \ -{ \ - return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \ -} - -show_one_plus(level, base.eax.split.level, 0); -show_one_plus(coherency_line_size, base.ebx.split.coherency_line_size, 1); -show_one_plus(physical_line_partition, base.ebx.split.physical_line_partition, 1); -show_one_plus(ways_of_associativity, base.ebx.split.ways_of_associativity, 1); -show_one_plus(number_of_sets, base.ecx.split.number_of_sets, 1); - -static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf, - unsigned int cpu) -{ - return sprintf(buf, "%luK\n", this_leaf->base.size / 1024); -} - -static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf, - int type, char *buf) -{ - const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map); - int ret; - - if (type) - ret = scnprintf(buf, PAGE_SIZE - 1, "%*pbl", - cpumask_pr_args(mask)); - else - ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb", - cpumask_pr_args(mask)); - buf[ret++] = '\n'; - buf[ret] = '\0'; - return ret; -} - -static inline ssize_t show_shared_cpu_map(struct _cpuid4_info *leaf, char *buf, - unsigned int cpu) +static int __init_cache_level(unsigned int cpu) { - return show_shared_cpu_map_func(leaf, 0, buf); -} - -static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf, - unsigned int cpu) -{ - return show_shared_cpu_map_func(leaf, 1, buf); -} + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); -static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf, - unsigned int cpu) -{ - switch (this_leaf->base.eax.split.type) { - case CACHE_TYPE_DATA: - return sprintf(buf, "Data\n"); - case CACHE_TYPE_INST: - return sprintf(buf, "Instruction\n"); - case CACHE_TYPE_UNIFIED: - return sprintf(buf, "Unified\n"); - default: - return sprintf(buf, "Unknown\n"); - } -} - -#define to_object(k) container_of(k, struct _index_kobject, kobj) -#define to_attr(a) container_of(a, struct _cache_attr, attr) - -#define define_one_ro(_name) \ -static struct _cache_attr _name = \ - __ATTR(_name, 0444, show_##_name, NULL) - -define_one_ro(level); -define_one_ro(type); -define_one_ro(coherency_line_size); -define_one_ro(physical_line_partition); -define_one_ro(ways_of_associativity); -define_one_ro(number_of_sets); -define_one_ro(size); -define_one_ro(shared_cpu_map); -define_one_ro(shared_cpu_list); - -static struct attribute *default_attrs[] = { - &type.attr, - &level.attr, - &coherency_line_size.attr, - &physical_line_partition.attr, - &ways_of_associativity.attr, - &number_of_sets.attr, - &size.attr, - &shared_cpu_map.attr, - &shared_cpu_list.attr, - NULL -}; - -#ifdef CONFIG_AMD_NB -static struct attribute **amd_l3_attrs(void) -{ - static struct attribute **attrs; - int n; - - if (attrs) - return attrs; - - n = ARRAY_SIZE(default_attrs); - - if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) - n += 2; - - if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) - n += 1; - - attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL); - if (attrs == NULL) - return attrs = default_attrs; - - for (n = 0; default_attrs[n]; n++) - attrs[n] = default_attrs[n]; - - if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) { - attrs[n++] = &cache_disable_0.attr; - attrs[n++] = &cache_disable_1.attr; - } - - if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) - attrs[n++] = &subcaches.attr; - - return attrs; -} -#endif - -static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) -{ - struct _cache_attr *fattr = to_attr(attr); - struct _index_kobject *this_leaf = to_object(kobj); - ssize_t ret; - - ret = fattr->show ? - fattr->show(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index), - buf, this_leaf->cpu) : - 0; - return ret; -} - -static ssize_t store(struct kobject *kobj, struct attribute *attr, - const char *buf, size_t count) -{ - struct _cache_attr *fattr = to_attr(attr); - struct _index_kobject *this_leaf = to_object(kobj); - ssize_t ret; - - ret = fattr->store ? - fattr->store(CPUID4_INFO_IDX(this_leaf->cpu, this_leaf->index), - buf, count, this_leaf->cpu) : - 0; - return ret; -} - -static const struct sysfs_ops sysfs_ops = { - .show = show, - .store = store, -}; - -static struct kobj_type ktype_cache = { - .sysfs_ops = &sysfs_ops, - .default_attrs = default_attrs, -}; - -static struct kobj_type ktype_percpu_entry = { - .sysfs_ops = &sysfs_ops, -}; - -static void cpuid4_cache_sysfs_exit(unsigned int cpu) -{ - kfree(per_cpu(ici_cache_kobject, cpu)); - kfree(per_cpu(ici_index_kobject, cpu)); - per_cpu(ici_cache_kobject, cpu) = NULL; - per_cpu(ici_index_kobject, cpu) = NULL; - free_cache_attributes(cpu); -} - -static int cpuid4_cache_sysfs_init(unsigned int cpu) -{ - int err; - - if (num_cache_leaves == 0) + if (!num_cache_leaves) return -ENOENT; - - err = detect_cache_attributes(cpu); - if (err) - return err; - - /* Allocate all required memory */ - per_cpu(ici_cache_kobject, cpu) = - kzalloc(sizeof(struct kobject), GFP_KERNEL); - if (unlikely(per_cpu(ici_cache_kobject, cpu) == NULL)) - goto err_out; - - per_cpu(ici_index_kobject, cpu) = kzalloc( - sizeof(struct _index_kobject) * num_cache_leaves, GFP_KERNEL); - if (unlikely(per_cpu(ici_index_kobject, cpu) == NULL)) - goto err_out; - + if (!this_cpu_ci) + return -EINVAL; + this_cpu_ci->num_levels = 3; + this_cpu_ci->num_leaves = num_cache_leaves; return 0; - -err_out: - cpuid4_cache_sysfs_exit(cpu); - return -ENOMEM; } -static DECLARE_BITMAP(cache_dev_map, NR_CPUS); - -/* Add/Remove cache interface for CPU device */ -static int cache_add_dev(struct device *dev) +static int __populate_cache_leaves(unsigned int cpu) { - unsigned int cpu = dev->id; - unsigned long i, j; - struct _index_kobject *this_object; - struct _cpuid4_info *this_leaf; - int retval; - - retval = cpuid4_cache_sysfs_init(cpu); - if (unlikely(retval < 0)) - return retval; - - retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu), - &ktype_percpu_entry, - &dev->kobj, "%s", "cache"); - if (retval < 0) { - cpuid4_cache_sysfs_exit(cpu); - return retval; - } + unsigned int idx, ret; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf = this_cpu_ci->info_list; + struct _cpuid4_info_regs id4_regs = {}; - for (i = 0; i < num_cache_leaves; i++) { - this_object = INDEX_KOBJECT_PTR(cpu, i); - this_object->cpu = cpu; - this_object->index = i; - - this_leaf = CPUID4_INFO_IDX(cpu, i); - - ktype_cache.default_attrs = default_attrs; -#ifdef CONFIG_AMD_NB - if (this_leaf->base.nb) - ktype_cache.default_attrs = amd_l3_attrs(); -#endif - retval = kobject_init_and_add(&(this_object->kobj), - &ktype_cache, - per_cpu(ici_cache_kobject, cpu), - "index%1lu", i); - if (unlikely(retval)) { - for (j = 0; j < i; j++) - kobject_put(&(INDEX_KOBJECT_PTR(cpu, j)->kobj)); - kobject_put(per_cpu(ici_cache_kobject, cpu)); - cpuid4_cache_sysfs_exit(cpu); - return retval; - } - kobject_uevent(&(this_object->kobj), KOBJ_ADD); + for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) { + ret = cpuid4_cache_lookup_regs(idx, &id4_regs); + if (ret) + return ret; + ci_leaf_init(this_leaf++, &id4_regs); + __cache_cpumap_setup(cpu, idx, &id4_regs); } - cpumask_set_cpu(cpu, to_cpumask(cache_dev_map)); - - kobject_uevent(per_cpu(ici_cache_kobject, cpu), KOBJ_ADD); return 0; } -static void cache_remove_dev(struct device *dev) -{ - unsigned int cpu = dev->id; - unsigned long i; - - if (per_cpu(ici_cpuid4_info, cpu) == NULL) - return; - if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map))) - return; - cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map)); - - for (i = 0; i < num_cache_leaves; i++) - kobject_put(&(INDEX_KOBJECT_PTR(cpu, i)->kobj)); - kobject_put(per_cpu(ici_cache_kobject, cpu)); - cpuid4_cache_sysfs_exit(cpu); -} - -static int cacheinfo_cpu_callback(struct notifier_block *nfb, - unsigned long action, void *hcpu) -{ - unsigned int cpu = (unsigned long)hcpu; - struct device *dev; - - dev = get_cpu_device(cpu); - switch (action) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - cache_add_dev(dev); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - cache_remove_dev(dev); - break; - } - return NOTIFY_OK; -} - -static struct notifier_block cacheinfo_cpu_notifier = { - .notifier_call = cacheinfo_cpu_callback, -}; - -static int __init cache_sysfs_init(void) -{ - int i, err = 0; - - if (num_cache_leaves == 0) - return 0; - - cpu_notifier_register_begin(); - for_each_online_cpu(i) { - struct device *dev = get_cpu_device(i); - - err = cache_add_dev(dev); - if (err) - goto out; - } - __register_hotcpu_notifier(&cacheinfo_cpu_notifier); - -out: - cpu_notifier_register_done(); - return err; -} - -device_initcall(cache_sysfs_init); - -#endif +DEFINE_SMP_CALL_CACHE_FUNCTION(init_cache_level) +DEFINE_SMP_CALL_CACHE_FUNCTION(populate_cache_leaves) diff --git a/arch/x86/kernel/cpu/intel_pt.h b/arch/x86/kernel/cpu/intel_pt.h new file mode 100644 index 000000000000..1c338b0eba05 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_pt.h @@ -0,0 +1,131 @@ +/* + * Intel(R) Processor Trace PMU driver for perf + * Copyright (c) 2013-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * Intel PT is specified in the Intel Architecture Instruction Set Extensions + * Programming Reference: + * http://software.intel.com/en-us/intel-isa-extensions + */ + +#ifndef __INTEL_PT_H__ +#define __INTEL_PT_H__ + +/* + * Single-entry ToPA: when this close to region boundary, switch + * buffers to avoid losing data. + */ +#define TOPA_PMI_MARGIN 512 + +/* + * Table of Physical Addresses bits + */ +enum topa_sz { + TOPA_4K = 0, + TOPA_8K, + TOPA_16K, + TOPA_32K, + TOPA_64K, + TOPA_128K, + TOPA_256K, + TOPA_512K, + TOPA_1MB, + TOPA_2MB, + TOPA_4MB, + TOPA_8MB, + TOPA_16MB, + TOPA_32MB, + TOPA_64MB, + TOPA_128MB, + TOPA_SZ_END, +}; + +static inline unsigned int sizes(enum topa_sz tsz) +{ + return 1 << (tsz + 12); +}; + +struct topa_entry { + u64 end : 1; + u64 rsvd0 : 1; + u64 intr : 1; + u64 rsvd1 : 1; + u64 stop : 1; + u64 rsvd2 : 1; + u64 size : 4; + u64 rsvd3 : 2; + u64 base : 36; + u64 rsvd4 : 16; +}; + +#define TOPA_SHIFT 12 +#define PT_CPUID_LEAVES 2 + +enum pt_capabilities { + PT_CAP_max_subleaf = 0, + PT_CAP_cr3_filtering, + PT_CAP_topa_output, + PT_CAP_topa_multiple_entries, + PT_CAP_payloads_lip, +}; + +struct pt_pmu { + struct pmu pmu; + u32 caps[4 * PT_CPUID_LEAVES]; +}; + +/** + * struct pt_buffer - buffer configuration; one buffer per task_struct or + * cpu, depending on perf event configuration + * @cpu: cpu for per-cpu allocation + * @tables: list of ToPA tables in this buffer + * @first: shorthand for first topa table + * @last: shorthand for last topa table + * @cur: current topa table + * @nr_pages: buffer size in pages + * @cur_idx: current output region's index within @cur table + * @output_off: offset within the current output region + * @data_size: running total of the amount of data in this buffer + * @lost: if data was lost/truncated + * @head: logical write offset inside the buffer + * @snapshot: if this is for a snapshot/overwrite counter + * @stop_pos: STOP topa entry in the buffer + * @intr_pos: INT topa entry in the buffer + * @data_pages: array of pages from perf + * @topa_index: table of topa entries indexed by page offset + */ +struct pt_buffer { + int cpu; + struct list_head tables; + struct topa *first, *last, *cur; + unsigned int cur_idx; + size_t output_off; + unsigned long nr_pages; + local_t data_size; + local_t lost; + local64_t head; + bool snapshot; + unsigned long stop_pos, intr_pos; + void **data_pages; + struct topa_entry *topa_index[0]; +}; + +/** + * struct pt - per-cpu pt context + * @handle: perf output handle + * @handle_nmi: do handle PT PMI on this cpu, there's an active event + */ +struct pt { + struct perf_output_handle handle; + int handle_nmi; +}; + +#endif /* __INTEL_PT_H__ */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 10b46906767f..fe32074b865b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -14,6 +14,7 @@ enum severity_level { }; #define ATTR_LEN 16 +#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ /* One object for each MCE bank, shared by all CPUs */ struct mce_bank { @@ -23,20 +24,20 @@ struct mce_bank { char attrname[ATTR_LEN]; /* attribute name */ }; -int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp); +extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; extern mce_banks_t mce_banks_ce_disabled; #ifdef CONFIG_X86_MCE_INTEL -unsigned long mce_intel_adjust_timer(unsigned long interval); -void mce_intel_cmci_poll(void); +unsigned long cmci_intel_adjust_timer(unsigned long interval); +bool mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); void cmci_disable_bank(int bank); #else -# define mce_intel_adjust_timer mce_adjust_timer_default -static inline void mce_intel_cmci_poll(void) { } +# define cmci_intel_adjust_timer mce_adjust_timer_default +static inline bool mce_intel_cmci_poll(void) { return false; } static inline void mce_intel_hcpu_update(unsigned long cpu) { } static inline void cmci_disable_bank(int bank) { } #endif diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index 8bb433043a7f..9c682c222071 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -186,7 +186,61 @@ static int error_context(struct mce *m) return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL; } -int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) +/* + * See AMD Error Scope Hierarchy table in a newer BKDG. For example + * 49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features" + */ +static int mce_severity_amd(struct mce *m, int tolerant, char **msg, bool is_excp) +{ + enum context ctx = error_context(m); + + /* Processor Context Corrupt, no need to fumble too much, die! */ + if (m->status & MCI_STATUS_PCC) + return MCE_PANIC_SEVERITY; + + if (m->status & MCI_STATUS_UC) { + + /* + * On older systems where overflow_recov flag is not present, we + * should simply panic if an error overflow occurs. If + * overflow_recov flag is present and set, then software can try + * to at least kill process to prolong system operation. + */ + if (mce_flags.overflow_recov) { + /* software can try to contain */ + if (!(m->mcgstatus & MCG_STATUS_RIPV) && (ctx == IN_KERNEL)) + return MCE_PANIC_SEVERITY; + + /* kill current process */ + return MCE_AR_SEVERITY; + } else { + /* at least one error was not logged */ + if (m->status & MCI_STATUS_OVER) + return MCE_PANIC_SEVERITY; + } + + /* + * For any other case, return MCE_UC_SEVERITY so that we log the + * error and exit #MC handler. + */ + return MCE_UC_SEVERITY; + } + + /* + * deferred error: poll handler catches these and adds to mce_ring so + * memory-failure can take recovery actions. + */ + if (m->status & MCI_STATUS_DEFERRED) + return MCE_DEFERRED_SEVERITY; + + /* + * corrected error: poll handler catches these and passes responsibility + * of decoding the error to EDAC + */ + return MCE_KEEP_SEVERITY; +} + +static int mce_severity_intel(struct mce *m, int tolerant, char **msg, bool is_excp) { enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); enum context ctx = error_context(m); @@ -216,6 +270,16 @@ int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp) } } +/* Default to mce_severity_intel */ +int (*mce_severity)(struct mce *m, int tolerant, char **msg, bool is_excp) = + mce_severity_intel; + +void __init mcheck_vendor_init_severity(void) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + mce_severity = mce_severity_amd; +} + #ifdef CONFIG_DEBUG_FS static void *s_start(struct seq_file *f, loff_t *pos) { diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 3c036cb4a370..e535533d5ab8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,11 +60,12 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define CREATE_TRACE_POINTS #include <trace/events/mce.h> -#define SPINUNIT 100 /* 100ns */ +#define SPINUNIT 100 /* 100ns */ DEFINE_PER_CPU(unsigned, mce_exception_count); struct mce_bank *mce_banks __read_mostly; +struct mce_vendor_flags mce_flags __read_mostly; struct mca_config mca_cfg __read_mostly = { .bootlog = -1, @@ -89,9 +90,6 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); static DEFINE_PER_CPU(struct mce, mces_seen); static int cpu_missing; -/* CMCI storm detection filter */ -static DEFINE_PER_CPU(unsigned long, mce_polled_error); - /* * MCA banks polled by the period polling timer for corrected events. * With Intel CMCI, this only has MCA banks which do not support CMCI (if any). @@ -622,8 +620,9 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); * is already totally * confused. In this case it's likely it will * not fully execute the machine check handler either. */ -void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) +bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { + bool error_logged = false; struct mce m; int severity; int i; @@ -646,7 +645,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) if (!(m.status & MCI_STATUS_VAL)) continue; - this_cpu_write(mce_polled_error, 1); + /* * Uncorrected or signalled events are handled by the exception * handler when it is enabled, so don't process those here. @@ -679,8 +678,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { + error_logged = true; mce_log(&m); + } /* * Clear state for this bank. @@ -694,6 +695,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b) */ sync_core(); + + return error_logged; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -813,7 +816,7 @@ static void mce_reign(void) * other CPUs. */ if (m && global_worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Fatal Machine check", m, msg); + mce_panic("Fatal machine check", m, msg); /* * For UC somewhere we let the CPU who detects it handle it. @@ -826,7 +829,7 @@ static void mce_reign(void) * source or one CPU is hung. Panic. */ if (global_worst <= MCE_KEEP_SEVERITY && mca_cfg.tolerant < 3) - mce_panic("Machine check from unknown source", NULL, NULL); + mce_panic("Fatal machine check from unknown source", NULL, NULL); /* * Now clear all the mces_seen so that they don't reappear on @@ -1258,7 +1261,7 @@ void mce_log_therm_throt_event(__u64 status) * poller finds an MCE, poll 2x faster. When the poller finds no more * errors, poll 2x slower (up to check_interval seconds). */ -static unsigned long check_interval = 5 * 60; /* 5 minutes */ +static unsigned long check_interval = INITIAL_CHECK_INTERVAL; static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); @@ -1268,49 +1271,57 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) return interval; } -static unsigned long (*mce_adjust_timer)(unsigned long interval) = - mce_adjust_timer_default; +static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static int cmc_error_seen(void) +static void __restart_timer(struct timer_list *t, unsigned long interval) { - unsigned long *v = this_cpu_ptr(&mce_polled_error); + unsigned long when = jiffies + interval; + unsigned long flags; + + local_irq_save(flags); - return test_and_clear_bit(0, v); + if (timer_pending(t)) { + if (time_before(when, t->expires)) + mod_timer_pinned(t, when); + } else { + t->expires = round_jiffies(when); + add_timer_on(t, smp_processor_id()); + } + + local_irq_restore(flags); } static void mce_timer_fn(unsigned long data) { struct timer_list *t = this_cpu_ptr(&mce_timer); + int cpu = smp_processor_id(); unsigned long iv; - int notify; - WARN_ON(smp_processor_id() != data); + WARN_ON(cpu != data); + + iv = __this_cpu_read(mce_next_interval); if (mce_available(this_cpu_ptr(&cpu_info))) { - machine_check_poll(MCP_TIMESTAMP, - this_cpu_ptr(&mce_poll_banks)); - mce_intel_cmci_poll(); + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_poll_banks)); + + if (mce_intel_cmci_poll()) { + iv = mce_adjust_timer(iv); + goto done; + } } /* - * Alert userspace if needed. If we logged an MCE, reduce the - * polling interval, otherwise increase the polling interval. + * Alert userspace if needed. If we logged an MCE, reduce the polling + * interval, otherwise increase the polling interval. */ - iv = __this_cpu_read(mce_next_interval); - notify = mce_notify_irq(); - notify |= cmc_error_seen(); - if (notify) { + if (mce_notify_irq()) iv = max(iv / 2, (unsigned long) HZ/100); - } else { + else iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); - iv = mce_adjust_timer(iv); - } + +done: __this_cpu_write(mce_next_interval, iv); - /* Might have become 0 after CMCI storm subsided */ - if (iv) { - t->expires = jiffies + iv; - add_timer_on(t, smp_processor_id()); - } + __restart_timer(t, iv); } /* @@ -1319,16 +1330,10 @@ static void mce_timer_fn(unsigned long data) void mce_timer_kick(unsigned long interval) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned long when = jiffies + interval; unsigned long iv = __this_cpu_read(mce_next_interval); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer_pinned(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + __restart_timer(t, interval); + if (interval < iv) __this_cpu_write(mce_next_interval, interval); } @@ -1525,45 +1530,46 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) * Various K7s with broken bank 0 around. Always disable * by default. */ - if (c->x86 == 6 && cfg->banks > 0) + if (c->x86 == 6 && cfg->banks > 0) mce_banks[0].ctl = 0; - /* - * Turn off MC4_MISC thresholding banks on those models since - * they're not supported there. - */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { - int i; - u64 val, hwcr; - bool need_toggle; - u32 msrs[] = { + /* + * overflow_recov is supported for F15h Models 00h-0fh + * even though we don't have a CPUID bit for it. + */ + if (c->x86 == 0x15 && c->x86_model <= 0xf) + mce_flags.overflow_recov = 1; + + /* + * Turn off MC4_MISC thresholding banks on those models since + * they're not supported there. + */ + if (c->x86 == 0x15 && + (c->x86_model >= 0x10 && c->x86_model <= 0x1f)) { + int i; + u64 hwcr; + bool need_toggle; + u32 msrs[] = { 0x00000413, /* MC4_MISC0 */ 0xc0000408, /* MC4_MISC1 */ - }; + }; - rdmsrl(MSR_K7_HWCR, hwcr); + rdmsrl(MSR_K7_HWCR, hwcr); - /* McStatusWrEn has to be set */ - need_toggle = !(hwcr & BIT(18)); + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); - for (i = 0; i < ARRAY_SIZE(msrs); i++) { - rdmsrl(msrs[i], val); + /* Clear CntP bit safely */ + for (i = 0; i < ARRAY_SIZE(msrs); i++) + msr_clear_bit(msrs[i], 62); - /* CntP bit set? */ - if (val & BIT_64(62)) { - val &= ~BIT_64(62); - wrmsrl(msrs[i], val); - } - } - - /* restore old settings */ - if (need_toggle) - wrmsrl(MSR_K7_HWCR, hwcr); - } + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); + } } if (c->x86_vendor == X86_VENDOR_INTEL) { @@ -1629,10 +1635,11 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); - mce_adjust_timer = mce_intel_adjust_timer; + mce_adjust_timer = cmci_intel_adjust_timer; break; case X86_VENDOR_AMD: mce_amd_feature_init(c); + mce_flags.overflow_recov = cpuid_ebx(0x80000007) & 0x1; break; default: break; @@ -2017,6 +2024,7 @@ __setup("mce", mcheck_enable); int __init mcheck_init(void) { mcheck_intel_therm_init(); + mcheck_vendor_init_severity(); return 0; } diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index f1c3769bbd64..55ad9b37cae8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -79,7 +79,7 @@ static inline bool is_shared_bank(int bank) return (bank == 4); } -static const char * const bank4_names(struct threshold_block *b) +static const char *bank4_names(const struct threshold_block *b) { switch (b->address) { /* MSR4_MISC0 */ @@ -250,6 +250,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) if (!b.interrupt_capable) goto init; + b.interrupt_enable = 1; new = (high & MASK_LVTOFF_HI) >> 20; offset = setup_APIC_mce(offset, new); @@ -322,6 +323,8 @@ static void amd_threshold_interrupt(void) log: mce_setup(&m); rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status); + if (!(m.status & MCI_STATUS_VAL)) + return; m.misc = ((u64)high << 32) | low; m.bank = bank; mce_log(&m); @@ -497,10 +500,12 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank, b->interrupt_capable = lvt_interrupt_supported(bank, high); b->threshold_limit = THRESHOLD_MAX; - if (b->interrupt_capable) + if (b->interrupt_capable) { threshold_ktype.default_attrs[2] = &interrupt_enable.attr; - else + b->interrupt_enable = 1; + } else { threshold_ktype.default_attrs[2] = NULL; + } INIT_LIST_HEAD(&b->miscj); diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index b3c97bafc123..b4a41cf030ed 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -39,6 +39,15 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); /* + * CMCI storm detection backoff counter + * + * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've + * encountered an error. If not, we decrement it by one. We signal the end of + * the CMCI storm when it reaches 0. + */ +static DEFINE_PER_CPU(int, cmci_backoff_cnt); + +/* * cmci_discover_lock protects against parallel discovery attempts * which could race against each other. */ @@ -46,7 +55,7 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); #define CMCI_THRESHOLD 1 #define CMCI_POLL_INTERVAL (30 * HZ) -#define CMCI_STORM_INTERVAL (1 * HZ) +#define CMCI_STORM_INTERVAL (HZ) #define CMCI_STORM_THRESHOLD 15 static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); @@ -82,11 +91,21 @@ static int cmci_supported(int *banks) return !!(cap & MCG_CMCI_P); } -void mce_intel_cmci_poll(void) +bool mce_intel_cmci_poll(void) { if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) - return; - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); + return false; + + /* + * Reset the counter if we've logged an error in the last poll + * during the storm. + */ + if (machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned))) + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + else + this_cpu_dec(cmci_backoff_cnt); + + return true; } void mce_intel_hcpu_update(unsigned long cpu) @@ -97,31 +116,32 @@ void mce_intel_hcpu_update(unsigned long cpu) per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; } -unsigned long mce_intel_adjust_timer(unsigned long interval) +unsigned long cmci_intel_adjust_timer(unsigned long interval) { - int r; - - if (interval < CMCI_POLL_INTERVAL) - return interval; + if ((this_cpu_read(cmci_backoff_cnt) > 0) && + (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) { + mce_notify_irq(); + return CMCI_STORM_INTERVAL; + } switch (__this_cpu_read(cmci_storm_state)) { case CMCI_STORM_ACTIVE: + /* * We switch back to interrupt mode once the poll timer has - * silenced itself. That means no events recorded and the - * timer interval is back to our poll interval. + * silenced itself. That means no events recorded and the timer + * interval is back to our poll interval. */ __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); - r = atomic_sub_return(1, &cmci_storm_on_cpus); - if (r == 0) + if (!atomic_sub_return(1, &cmci_storm_on_cpus)) pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + /* FALLTHROUGH */ case CMCI_STORM_SUBSIDED: /* - * We wait for all cpus to go back to SUBSIDED - * state. When that happens we switch back to - * interrupt mode. + * We wait for all CPUs to go back to SUBSIDED state. When that + * happens we switch back to interrupt mode. */ if (!atomic_read(&cmci_storm_on_cpus)) { __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); @@ -130,10 +150,8 @@ unsigned long mce_intel_adjust_timer(unsigned long interval) } return CMCI_POLL_INTERVAL; default: - /* - * We have shiny weather. Let the poll do whatever it - * thinks. - */ + + /* We have shiny weather. Let the poll do whatever it thinks. */ return interval; } } @@ -178,7 +196,8 @@ static bool cmci_storm_detect(void) cmci_storm_disable_banks(); __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); r = atomic_add_return(1, &cmci_storm_on_cpus); - mce_timer_kick(CMCI_POLL_INTERVAL); + mce_timer_kick(CMCI_STORM_INTERVAL); + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); if (r == 1) pr_notice("CMCI storm detected: switching to poll mode\n"); @@ -195,6 +214,7 @@ static void intel_threshold_interrupt(void) { if (cmci_storm_detect()) return; + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); mce_notify_irq(); } @@ -286,6 +306,7 @@ void cmci_recheck(void) if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) return; + local_irq_save(flags); machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); local_irq_restore(flags); diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index bfbbe6195e2d..12829c3ced3c 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -21,7 +21,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/firmware.h> -#include <linux/pci_ids.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/kernel.h> diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index d45df4bd16ab..a413a69cbd74 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -23,57 +23,6 @@ #include <asm/processor.h> #include <asm/cmdline.h> -#define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) -#define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') -#define CPUID_INTEL2 QCHAR('i', 'n', 'e', 'I') -#define CPUID_INTEL3 QCHAR('n', 't', 'e', 'l') -#define CPUID_AMD1 QCHAR('A', 'u', 't', 'h') -#define CPUID_AMD2 QCHAR('e', 'n', 't', 'i') -#define CPUID_AMD3 QCHAR('c', 'A', 'M', 'D') - -#define CPUID_IS(a, b, c, ebx, ecx, edx) \ - (!((ebx ^ (a))|(edx ^ (b))|(ecx ^ (c)))) - -/* - * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. - * x86_vendor() gets vendor id for BSP. - * - * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify - * coding, we still use x86_vendor() to get vendor id for AP. - * - * x86_vendor() gets vendor information directly through cpuid. - */ -static int x86_vendor(void) -{ - u32 eax = 0x00000000; - u32 ebx, ecx = 0, edx; - - native_cpuid(&eax, &ebx, &ecx, &edx); - - if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) - return X86_VENDOR_INTEL; - - if (CPUID_IS(CPUID_AMD1, CPUID_AMD2, CPUID_AMD3, ebx, ecx, edx)) - return X86_VENDOR_AMD; - - return X86_VENDOR_UNKNOWN; -} - -static int x86_family(void) -{ - u32 eax = 0x00000001; - u32 ebx, ecx = 0, edx; - int x86; - - native_cpuid(&eax, &ebx, &ecx, &edx); - - x86 = (eax >> 8) & 0xf; - if (x86 == 15) - x86 += (eax >> 20) & 0xff; - - return x86; -} - static bool __init check_loader_disabled_bsp(void) { #ifdef CONFIG_X86_32 @@ -96,7 +45,7 @@ static bool __init check_loader_disabled_bsp(void) void __init load_ucode_bsp(void) { - int vendor, x86; + int vendor, family; if (check_loader_disabled_bsp()) return; @@ -105,15 +54,15 @@ void __init load_ucode_bsp(void) return; vendor = x86_vendor(); - x86 = x86_family(); + family = x86_family(); switch (vendor) { case X86_VENDOR_INTEL: - if (x86 >= 6) + if (family >= 6) load_ucode_intel_bsp(); break; case X86_VENDOR_AMD: - if (x86 >= 0x10) + if (family >= 0x10) load_ucode_amd_bsp(); break; default: @@ -132,7 +81,7 @@ static bool check_loader_disabled_ap(void) void load_ucode_ap(void) { - int vendor, x86; + int vendor, family; if (check_loader_disabled_ap()) return; @@ -141,15 +90,15 @@ void load_ucode_ap(void) return; vendor = x86_vendor(); - x86 = x86_family(); + family = x86_family(); switch (vendor) { case X86_VENDOR_INTEL: - if (x86 >= 6) + if (family >= 6) load_ucode_intel_ap(); break; case X86_VENDOR_AMD: - if (x86 >= 0x10) + if (family >= 0x10) load_ucode_amd_ap(); break; default: @@ -179,18 +128,18 @@ int __init save_microcode_in_initrd(void) void reload_early_microcode(void) { - int vendor, x86; + int vendor, family; vendor = x86_vendor(); - x86 = x86_family(); + family = x86_family(); switch (vendor) { case X86_VENDOR_INTEL: - if (x86 >= 6) + if (family >= 6) reload_ucode_intel(); break; case X86_VENDOR_AMD: - if (x86 >= 0x10) + if (family >= 0x10) reload_ucode_amd(); break; default: diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 746e7fd08aad..a41beadb3db9 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -124,7 +124,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu) cpf = cpu_sig.pf; crev = cpu_sig.rev; - return get_matching_microcode(csig, cpf, mc_intel, crev); + return get_matching_microcode(csig, cpf, crev, mc_intel); } static int apply_microcode_intel(int cpu) @@ -226,7 +226,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, csig = uci->cpu_sig.sig; cpf = uci->cpu_sig.pf; - if (get_matching_microcode(csig, cpf, mc, new_rev)) { + if (get_matching_microcode(csig, cpf, new_rev, mc)) { vfree(new_mc); new_rev = mc_header.rev; new_mc = mc; diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c index 420eb933189c..2f49ab4ac0ae 100644 --- a/arch/x86/kernel/cpu/microcode/intel_early.c +++ b/arch/x86/kernel/cpu/microcode/intel_early.c @@ -16,6 +16,14 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ + +/* + * This needs to be before all headers so that pr_debug in printk.h doesn't turn + * printk calls into no_printk(). + * + *#define DEBUG + */ + #include <linux/module.h> #include <linux/mm.h> #include <linux/slab.h> @@ -28,6 +36,9 @@ #include <asm/tlbflush.h> #include <asm/setup.h> +#undef pr_fmt +#define pr_fmt(fmt) "microcode: " fmt + static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT]; static struct mc_saved_data { unsigned int mc_saved_count; @@ -35,50 +46,45 @@ static struct mc_saved_data { } mc_saved_data; static enum ucode_state -generic_load_microcode_early(struct microcode_intel **mc_saved_p, - unsigned int mc_saved_count, - struct ucode_cpu_info *uci) +load_microcode_early(struct microcode_intel **saved, + unsigned int num_saved, struct ucode_cpu_info *uci) { struct microcode_intel *ucode_ptr, *new_mc = NULL; - int new_rev = uci->cpu_sig.rev; - enum ucode_state state = UCODE_OK; - unsigned int mc_size; - struct microcode_header_intel *mc_header; - unsigned int csig = uci->cpu_sig.sig; - unsigned int cpf = uci->cpu_sig.pf; - int i; + struct microcode_header_intel *mc_hdr; + int new_rev, ret, i; - for (i = 0; i < mc_saved_count; i++) { - ucode_ptr = mc_saved_p[i]; + new_rev = uci->cpu_sig.rev; - mc_header = (struct microcode_header_intel *)ucode_ptr; - mc_size = get_totalsize(mc_header); - if (get_matching_microcode(csig, cpf, ucode_ptr, new_rev)) { - new_rev = mc_header->rev; - new_mc = ucode_ptr; - } - } + for (i = 0; i < num_saved; i++) { + ucode_ptr = saved[i]; + mc_hdr = (struct microcode_header_intel *)ucode_ptr; - if (!new_mc) { - state = UCODE_NFOUND; - goto out; + ret = get_matching_microcode(uci->cpu_sig.sig, + uci->cpu_sig.pf, + new_rev, + ucode_ptr); + if (!ret) + continue; + + new_rev = mc_hdr->rev; + new_mc = ucode_ptr; } + if (!new_mc) + return UCODE_NFOUND; + uci->mc = (struct microcode_intel *)new_mc; -out: - return state; + return UCODE_OK; } -static void -microcode_pointer(struct microcode_intel **mc_saved, - unsigned long *mc_saved_in_initrd, - unsigned long initrd_start, int mc_saved_count) +static inline void +copy_initrd_ptrs(struct microcode_intel **mc_saved, unsigned long *initrd, + unsigned long off, int num_saved) { int i; - for (i = 0; i < mc_saved_count; i++) - mc_saved[i] = (struct microcode_intel *) - (mc_saved_in_initrd[i] + initrd_start); + for (i = 0; i < num_saved; i++) + mc_saved[i] = (struct microcode_intel *)(initrd[i] + off); } #ifdef CONFIG_X86_32 @@ -102,55 +108,27 @@ microcode_phys(struct microcode_intel **mc_saved_tmp, #endif static enum ucode_state -load_microcode(struct mc_saved_data *mc_saved_data, - unsigned long *mc_saved_in_initrd, - unsigned long initrd_start, - struct ucode_cpu_info *uci) +load_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, + unsigned long initrd_start, struct ucode_cpu_info *uci) { struct microcode_intel *mc_saved_tmp[MAX_UCODE_COUNT]; unsigned int count = mc_saved_data->mc_saved_count; if (!mc_saved_data->mc_saved) { - microcode_pointer(mc_saved_tmp, mc_saved_in_initrd, - initrd_start, count); + copy_initrd_ptrs(mc_saved_tmp, initrd, initrd_start, count); - return generic_load_microcode_early(mc_saved_tmp, count, uci); + return load_microcode_early(mc_saved_tmp, count, uci); } else { #ifdef CONFIG_X86_32 microcode_phys(mc_saved_tmp, mc_saved_data); - return generic_load_microcode_early(mc_saved_tmp, count, uci); + return load_microcode_early(mc_saved_tmp, count, uci); #else - return generic_load_microcode_early(mc_saved_data->mc_saved, + return load_microcode_early(mc_saved_data->mc_saved, count, uci); #endif } } -static u8 get_x86_family(unsigned long sig) -{ - u8 x86; - - x86 = (sig >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (sig >> 20) & 0xff; - - return x86; -} - -static u8 get_x86_model(unsigned long sig) -{ - u8 x86, x86_model; - - x86 = get_x86_family(sig); - x86_model = (sig >> 4) & 0xf; - - if (x86 == 0x6 || x86 == 0xf) - x86_model += ((sig >> 16) & 0xf) << 4; - - return x86_model; -} - /* * Given CPU signature and a microcode patch, this function finds if the * microcode patch has matching family and model with the CPU. @@ -159,42 +137,40 @@ static enum ucode_state matching_model_microcode(struct microcode_header_intel *mc_header, unsigned long sig) { - u8 x86, x86_model; - u8 x86_ucode, x86_model_ucode; + unsigned int fam, model; + unsigned int fam_ucode, model_ucode; struct extended_sigtable *ext_header; unsigned long total_size = get_totalsize(mc_header); unsigned long data_size = get_datasize(mc_header); int ext_sigcount, i; struct extended_signature *ext_sig; - x86 = get_x86_family(sig); - x86_model = get_x86_model(sig); + fam = __x86_family(sig); + model = x86_model(sig); - x86_ucode = get_x86_family(mc_header->sig); - x86_model_ucode = get_x86_model(mc_header->sig); + fam_ucode = __x86_family(mc_header->sig); + model_ucode = x86_model(mc_header->sig); - if (x86 == x86_ucode && x86_model == x86_model_ucode) + if (fam == fam_ucode && model == model_ucode) return UCODE_OK; /* Look for ext. headers: */ if (total_size <= data_size + MC_HEADER_SIZE) return UCODE_NFOUND; - ext_header = (struct extended_sigtable *) - mc_header + data_size + MC_HEADER_SIZE; + ext_header = (void *) mc_header + data_size + MC_HEADER_SIZE; + ext_sig = (void *)ext_header + EXT_HEADER_SIZE; ext_sigcount = ext_header->count; - ext_sig = (void *)ext_header + EXT_HEADER_SIZE; for (i = 0; i < ext_sigcount; i++) { - x86_ucode = get_x86_family(ext_sig->sig); - x86_model_ucode = get_x86_model(ext_sig->sig); + fam_ucode = __x86_family(ext_sig->sig); + model_ucode = x86_model(ext_sig->sig); - if (x86 == x86_ucode && x86_model == x86_model_ucode) + if (fam == fam_ucode && model == model_ucode) return UCODE_OK; ext_sig++; } - return UCODE_NFOUND; } @@ -204,7 +180,7 @@ save_microcode(struct mc_saved_data *mc_saved_data, unsigned int mc_saved_count) { int i, j; - struct microcode_intel **mc_saved_p; + struct microcode_intel **saved_ptr; int ret; if (!mc_saved_count) @@ -213,39 +189,45 @@ save_microcode(struct mc_saved_data *mc_saved_data, /* * Copy new microcode data. */ - mc_saved_p = kmalloc(mc_saved_count*sizeof(struct microcode_intel *), - GFP_KERNEL); - if (!mc_saved_p) + saved_ptr = kcalloc(mc_saved_count, sizeof(struct microcode_intel *), GFP_KERNEL); + if (!saved_ptr) return -ENOMEM; for (i = 0; i < mc_saved_count; i++) { - struct microcode_intel *mc = mc_saved_src[i]; - struct microcode_header_intel *mc_header = &mc->hdr; - unsigned long mc_size = get_totalsize(mc_header); - mc_saved_p[i] = kmalloc(mc_size, GFP_KERNEL); - if (!mc_saved_p[i]) { - ret = -ENOMEM; - goto err; - } + struct microcode_header_intel *mc_hdr; + struct microcode_intel *mc; + unsigned long size; + if (!mc_saved_src[i]) { ret = -EINVAL; goto err; } - memcpy(mc_saved_p[i], mc, mc_size); + + mc = mc_saved_src[i]; + mc_hdr = &mc->hdr; + size = get_totalsize(mc_hdr); + + saved_ptr[i] = kmalloc(size, GFP_KERNEL); + if (!saved_ptr[i]) { + ret = -ENOMEM; + goto err; + } + + memcpy(saved_ptr[i], mc, size); } /* * Point to newly saved microcode. */ - mc_saved_data->mc_saved = mc_saved_p; + mc_saved_data->mc_saved = saved_ptr; mc_saved_data->mc_saved_count = mc_saved_count; return 0; err: for (j = 0; j <= i; j++) - kfree(mc_saved_p[j]); - kfree(mc_saved_p); + kfree(saved_ptr[j]); + kfree(saved_ptr); return ret; } @@ -257,48 +239,45 @@ err: * - or if it is a newly discovered microcode patch. * * The microcode patch should have matching model with CPU. + * + * Returns: The updated number @num_saved of saved microcode patches. */ -static void _save_mc(struct microcode_intel **mc_saved, u8 *ucode_ptr, - unsigned int *mc_saved_count_p) +static unsigned int _save_mc(struct microcode_intel **mc_saved, + u8 *ucode_ptr, unsigned int num_saved) { - int i; - int found = 0; - unsigned int mc_saved_count = *mc_saved_count_p; - struct microcode_header_intel *mc_header; + struct microcode_header_intel *mc_hdr, *mc_saved_hdr; + unsigned int sig, pf, new_rev; + int found = 0, i; + + mc_hdr = (struct microcode_header_intel *)ucode_ptr; + + for (i = 0; i < num_saved; i++) { + mc_saved_hdr = (struct microcode_header_intel *)mc_saved[i]; + sig = mc_saved_hdr->sig; + pf = mc_saved_hdr->pf; + new_rev = mc_hdr->rev; + + if (!get_matching_sig(sig, pf, new_rev, ucode_ptr)) + continue; + + found = 1; + + if (!revision_is_newer(mc_hdr, new_rev)) + continue; - mc_header = (struct microcode_header_intel *)ucode_ptr; - for (i = 0; i < mc_saved_count; i++) { - unsigned int sig, pf; - unsigned int new_rev; - struct microcode_header_intel *mc_saved_header = - (struct microcode_header_intel *)mc_saved[i]; - sig = mc_saved_header->sig; - pf = mc_saved_header->pf; - new_rev = mc_header->rev; - - if (get_matching_sig(sig, pf, ucode_ptr, new_rev)) { - found = 1; - if (update_match_revision(mc_header, new_rev)) { - /* - * Found an older ucode saved before. - * Replace the older one with this newer - * one. - */ - mc_saved[i] = - (struct microcode_intel *)ucode_ptr; - break; - } - } - } - if (i >= mc_saved_count && !found) /* - * This ucode is first time discovered in ucode file. - * Save it to memory. + * Found an older ucode saved earlier. Replace it with + * this newer one. */ - mc_saved[mc_saved_count++] = - (struct microcode_intel *)ucode_ptr; + mc_saved[i] = (struct microcode_intel *)ucode_ptr; + break; + } + + /* Newly detected microcode, save it to memory. */ + if (i >= num_saved && !found) + mc_saved[num_saved++] = (struct microcode_intel *)ucode_ptr; - *mc_saved_count_p = mc_saved_count; + return num_saved; } /* @@ -346,7 +325,7 @@ get_matching_model_microcode(int cpu, unsigned long start, continue; } - _save_mc(mc_saved_tmp, ucode_ptr, &mc_saved_count); + mc_saved_count = _save_mc(mc_saved_tmp, ucode_ptr, mc_saved_count); ucode_ptr += mc_size; } @@ -372,7 +351,7 @@ out: static int collect_cpu_info_early(struct ucode_cpu_info *uci) { unsigned int val[2]; - u8 x86, x86_model; + unsigned int family, model; struct cpu_signature csig; unsigned int eax, ebx, ecx, edx; @@ -387,10 +366,10 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_cpuid(&eax, &ebx, &ecx, &edx); csig.sig = eax; - x86 = get_x86_family(csig.sig); - x86_model = get_x86_model(csig.sig); + family = __x86_family(csig.sig); + model = x86_model(csig.sig); - if ((x86_model >= 5) || (x86 > 6)) { + if ((model >= 5) || (family > 6)) { /* get processor flags from MSR 0x17 */ native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); csig.pf = 1 << ((val[1] >> 18) & 7); @@ -429,8 +408,7 @@ static void __ref show_saved_mc(void) sig = uci.cpu_sig.sig; pf = uci.cpu_sig.pf; rev = uci.cpu_sig.rev; - pr_debug("CPU%d: sig=0x%x, pf=0x%x, rev=0x%x\n", - smp_processor_id(), sig, pf, rev); + pr_debug("CPU: sig=0x%x, pf=0x%x, rev=0x%x\n", sig, pf, rev); for (i = 0; i < mc_saved_data.mc_saved_count; i++) { struct microcode_header_intel *mc_saved_header; @@ -457,8 +435,7 @@ static void __ref show_saved_mc(void) if (total_size <= data_size + MC_HEADER_SIZE) continue; - ext_header = (struct extended_sigtable *) - mc_saved_header + data_size + MC_HEADER_SIZE; + ext_header = (void *) mc_saved_header + data_size + MC_HEADER_SIZE; ext_sigcount = ext_header->count; ext_sig = (void *)ext_header + EXT_HEADER_SIZE; @@ -515,8 +492,7 @@ int save_mc_for_early(u8 *mc) * Save the microcode patch mc in mc_save_tmp structure if it's a newer * version. */ - - _save_mc(mc_saved_tmp, mc, &mc_saved_count); + mc_saved_count = _save_mc(mc_saved_tmp, mc, mc_saved_count); /* * Save the mc_save_tmp in global mc_saved_data. @@ -548,12 +524,10 @@ EXPORT_SYMBOL_GPL(save_mc_for_early); static __initdata char ucode_name[] = "kernel/x86/microcode/GenuineIntel.bin"; static __init enum ucode_state -scan_microcode(unsigned long start, unsigned long end, - struct mc_saved_data *mc_saved_data, - unsigned long *mc_saved_in_initrd, - struct ucode_cpu_info *uci) +scan_microcode(struct mc_saved_data *mc_saved_data, unsigned long *initrd, + unsigned long start, unsigned long size, + struct ucode_cpu_info *uci) { - unsigned int size = end - start + 1; struct cpio_data cd; long offset = 0; #ifdef CONFIG_X86_32 @@ -569,10 +543,8 @@ scan_microcode(unsigned long start, unsigned long end, if (!cd.data) return UCODE_ERROR; - return get_matching_model_microcode(0, start, cd.data, cd.size, - mc_saved_data, mc_saved_in_initrd, - uci); + mc_saved_data, initrd, uci); } /* @@ -704,7 +676,7 @@ int __init save_microcode_in_initrd_intel(void) if (count == 0) return ret; - microcode_pointer(mc_saved, mc_saved_in_initrd, initrd_start, count); + copy_initrd_ptrs(mc_saved, mc_saved_in_initrd, initrd_start, count); ret = save_microcode(&mc_saved_data, mc_saved, count); if (ret) pr_err("Cannot save microcode patches from initrd.\n"); @@ -716,52 +688,44 @@ int __init save_microcode_in_initrd_intel(void) static void __init _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data, - unsigned long *mc_saved_in_initrd, - unsigned long initrd_start_early, - unsigned long initrd_end_early, - struct ucode_cpu_info *uci) + unsigned long *initrd, + unsigned long start, unsigned long size) { + struct ucode_cpu_info uci; enum ucode_state ret; - collect_cpu_info_early(uci); - scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data, - mc_saved_in_initrd, uci); + collect_cpu_info_early(&uci); - ret = load_microcode(mc_saved_data, mc_saved_in_initrd, - initrd_start_early, uci); + ret = scan_microcode(mc_saved_data, initrd, start, size, &uci); + if (ret != UCODE_OK) + return; - if (ret == UCODE_OK) - apply_microcode_early(uci, true); + ret = load_microcode(mc_saved_data, initrd, start, &uci); + if (ret != UCODE_OK) + return; + + apply_microcode_early(&uci, true); } -void __init -load_ucode_intel_bsp(void) +void __init load_ucode_intel_bsp(void) { - u64 ramdisk_image, ramdisk_size; - unsigned long initrd_start_early, initrd_end_early; - struct ucode_cpu_info uci; + u64 start, size; #ifdef CONFIG_X86_32 - struct boot_params *boot_params_p; + struct boot_params *p; - boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params); - ramdisk_image = boot_params_p->hdr.ramdisk_image; - ramdisk_size = boot_params_p->hdr.ramdisk_size; - initrd_start_early = ramdisk_image; - initrd_end_early = initrd_start_early + ramdisk_size; + p = (struct boot_params *)__pa_nodebug(&boot_params); + start = p->hdr.ramdisk_image; + size = p->hdr.ramdisk_size; _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), - (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), - initrd_start_early, initrd_end_early, &uci); + (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), + start, size); #else - ramdisk_image = boot_params.hdr.ramdisk_image; - ramdisk_size = boot_params.hdr.ramdisk_size; - initrd_start_early = ramdisk_image + PAGE_OFFSET; - initrd_end_early = initrd_start_early + ramdisk_size; - - _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, - initrd_start_early, initrd_end_early, - &uci); + start = boot_params.hdr.ramdisk_image + PAGE_OFFSET; + size = boot_params.hdr.ramdisk_size; + + _load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd, start, size); #endif } @@ -771,6 +735,7 @@ void load_ucode_intel_ap(void) struct ucode_cpu_info uci; unsigned long *mc_saved_in_initrd_p; unsigned long initrd_start_addr; + enum ucode_state ret; #ifdef CONFIG_X86_32 unsigned long *initrd_start_p; @@ -793,8 +758,12 @@ void load_ucode_intel_ap(void) return; collect_cpu_info_early(&uci); - load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, - initrd_start_addr, &uci); + ret = load_microcode(mc_saved_data_p, mc_saved_in_initrd_p, + initrd_start_addr, &uci); + + if (ret != UCODE_OK) + return; + apply_microcode_early(&uci, true); } @@ -808,8 +777,8 @@ void reload_ucode_intel(void) collect_cpu_info_early(&uci); - ret = generic_load_microcode_early(mc_saved_data.mc_saved, - mc_saved_data.mc_saved_count, &uci); + ret = load_microcode_early(mc_saved_data.mc_saved, + mc_saved_data.mc_saved_count, &uci); if (ret != UCODE_OK) return; diff --git a/arch/x86/kernel/cpu/microcode/intel_lib.c b/arch/x86/kernel/cpu/microcode/intel_lib.c index ce69320d0179..cd47a510a3f1 100644 --- a/arch/x86/kernel/cpu/microcode/intel_lib.c +++ b/arch/x86/kernel/cpu/microcode/intel_lib.c @@ -38,12 +38,6 @@ update_match_cpu(unsigned int csig, unsigned int cpf, return (!sigmatch(sig, csig, pf, cpf)) ? 0 : 1; } -int -update_match_revision(struct microcode_header_intel *mc_header, int rev) -{ - return (mc_header->rev <= rev) ? 0 : 1; -} - int microcode_sanity_check(void *mc, int print_err) { unsigned long total_size, data_size, ext_table_size; @@ -128,10 +122,9 @@ int microcode_sanity_check(void *mc, int print_err) EXPORT_SYMBOL_GPL(microcode_sanity_check); /* - * return 0 - no update found - * return 1 - found update + * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev) +int get_matching_sig(unsigned int csig, int cpf, int rev, void *mc) { struct microcode_header_intel *mc_header = mc; struct extended_sigtable *ext_header; @@ -159,16 +152,15 @@ int get_matching_sig(unsigned int csig, int cpf, void *mc, int rev) } /* - * return 0 - no update found - * return 1 - found update + * Returns 1 if update has been found, 0 otherwise. */ -int get_matching_microcode(unsigned int csig, int cpf, void *mc, int rev) +int get_matching_microcode(unsigned int csig, int cpf, int rev, void *mc) { - struct microcode_header_intel *mc_header = mc; + struct microcode_header_intel *mc_hdr = mc; - if (!update_match_revision(mc_header, rev)) + if (!revision_is_newer(mc_hdr, rev)) return 0; - return get_matching_sig(csig, cpf, mc, rev); + return get_matching_sig(csig, cpf, rev, mc); } EXPORT_SYMBOL_GPL(get_matching_microcode); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index 36d99a337b49..3f20710a5b23 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -6,7 +6,7 @@ IN=$1 OUT=$2 -function dump_array() +dump_array() { ARRAY=$1 SIZE=$2 diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index a041e094b8b9..d76f13d6d8d6 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -404,11 +404,10 @@ static const struct file_operations mtrr_fops = { static int mtrr_seq_show(struct seq_file *seq, void *offset) { char factor; - int i, max, len; + int i, max; mtrr_type type; unsigned long base, size; - len = 0; max = num_var_ranges; for (i = 0; i < max; i++) { mtrr_if->get(i, &base, &size, &type); @@ -425,11 +424,10 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset) size >>= 20 - PAGE_SHIFT; } /* Base can be > 32bit */ - len += seq_printf(seq, "reg%02i: base=0x%06lx000 " - "(%5luMB), size=%5lu%cB, count=%d: %s\n", - i, base, base >> (20 - PAGE_SHIFT), size, - factor, mtrr_usage_table[i], - mtrr_attrib_to_str(type)); + seq_printf(seq, "reg%02i: base=0x%06lx000 (%5luMB), size=%5lu%cB, count=%d: %s\n", + i, base, base >> (20 - PAGE_SHIFT), + size, factor, + mtrr_usage_table[i], mtrr_attrib_to_str(type)); } return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index b71a7f86d68a..87848ebe2bb7 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -263,6 +263,14 @@ static void hw_perf_event_destroy(struct perf_event *event) } } +void hw_perf_lbr_event_destroy(struct perf_event *event) +{ + hw_perf_event_destroy(event); + + /* undo the lbr/bts event accounting */ + x86_del_exclusive(x86_lbr_exclusive_lbr); +} + static inline int x86_pmu_initialized(void) { return x86_pmu.handle_irq != NULL; @@ -302,6 +310,35 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) return x86_pmu_extra_regs(val, event); } +/* + * Check if we can create event of a certain type (that no conflicting events + * are present). + */ +int x86_add_exclusive(unsigned int what) +{ + int ret = -EBUSY, i; + + if (atomic_inc_not_zero(&x86_pmu.lbr_exclusive[what])) + return 0; + + mutex_lock(&pmc_reserve_mutex); + for (i = 0; i < ARRAY_SIZE(x86_pmu.lbr_exclusive); i++) + if (i != what && atomic_read(&x86_pmu.lbr_exclusive[i])) + goto out; + + atomic_inc(&x86_pmu.lbr_exclusive[what]); + ret = 0; + +out: + mutex_unlock(&pmc_reserve_mutex); + return ret; +} + +void x86_del_exclusive(unsigned int what) +{ + atomic_dec(&x86_pmu.lbr_exclusive[what]); +} + int x86_setup_perfctr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; @@ -346,6 +383,12 @@ int x86_setup_perfctr(struct perf_event *event) /* BTS is currently only allowed for user-mode. */ if (!attr->exclude_kernel) return -EOPNOTSUPP; + + /* disallow bts if conflicting events are present */ + if (x86_add_exclusive(x86_lbr_exclusive_lbr)) + return -EBUSY; + + event->destroy = hw_perf_lbr_event_destroy; } hwc->config |= config; @@ -399,39 +442,41 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip > precise) return -EOPNOTSUPP; - /* - * check that PEBS LBR correction does not conflict with - * whatever the user is asking with attr->branch_sample_type - */ - if (event->attr.precise_ip > 1 && - x86_pmu.intel_cap.pebs_format < 2) { - u64 *br_type = &event->attr.branch_sample_type; - - if (has_branch_stack(event)) { - if (!precise_br_compat(event)) - return -EOPNOTSUPP; - - /* branch_sample_type is compatible */ - - } else { - /* - * user did not specify branch_sample_type - * - * For PEBS fixups, we capture all - * the branches at the priv level of the - * event. - */ - *br_type = PERF_SAMPLE_BRANCH_ANY; - - if (!event->attr.exclude_user) - *br_type |= PERF_SAMPLE_BRANCH_USER; - - if (!event->attr.exclude_kernel) - *br_type |= PERF_SAMPLE_BRANCH_KERNEL; - } + } + /* + * check that PEBS LBR correction does not conflict with + * whatever the user is asking with attr->branch_sample_type + */ + if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format < 2) { + u64 *br_type = &event->attr.branch_sample_type; + + if (has_branch_stack(event)) { + if (!precise_br_compat(event)) + return -EOPNOTSUPP; + + /* branch_sample_type is compatible */ + + } else { + /* + * user did not specify branch_sample_type + * + * For PEBS fixups, we capture all + * the branches at the priv level of the + * event. + */ + *br_type = PERF_SAMPLE_BRANCH_ANY; + + if (!event->attr.exclude_user) + *br_type |= PERF_SAMPLE_BRANCH_USER; + + if (!event->attr.exclude_kernel) + *br_type |= PERF_SAMPLE_BRANCH_KERNEL; } } + if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK) + event->attach_state |= PERF_ATTACH_TASK_DATA; + /* * Generate PMC IRQs: * (keep 'enabled' bit clear for now) @@ -449,6 +494,12 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK; + if (event->attr.sample_period && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, event->attr.sample_period) > + event->attr.sample_period) + return -EINVAL; + } + return x86_setup_perfctr(event); } @@ -728,14 +779,17 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) struct event_constraint *c; unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; struct perf_event *e; - int i, wmin, wmax, num = 0; + int i, wmin, wmax, unsched = 0; struct hw_perf_event *hwc; bitmap_zero(used_mask, X86_PMC_IDX_MAX); + if (x86_pmu.start_scheduling) + x86_pmu.start_scheduling(cpuc); + for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) { hwc = &cpuc->event_list[i]->hw; - c = x86_pmu.get_event_constraints(cpuc, cpuc->event_list[i]); + c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]); hwc->constraint = c; wmin = min(wmin, c->weight); @@ -768,24 +822,30 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) /* slow path */ if (i != n) - num = perf_assign_events(cpuc->event_list, n, wmin, - wmax, assign); + unsched = perf_assign_events(cpuc->event_list, n, wmin, + wmax, assign); /* - * Mark the event as committed, so we do not put_constraint() - * in case new events are added and fail scheduling. + * In case of success (unsched = 0), mark events as committed, + * so we do not put_constraint() in case new events are added + * and fail to be scheduled + * + * We invoke the lower level commit callback to lock the resource + * + * We do not need to do all of this in case we are called to + * validate an event group (assign == NULL) */ - if (!num && assign) { + if (!unsched && assign) { for (i = 0; i < n; i++) { e = cpuc->event_list[i]; e->hw.flags |= PERF_X86_EVENT_COMMITTED; + if (x86_pmu.commit_scheduling) + x86_pmu.commit_scheduling(cpuc, e, assign[i]); } } - /* - * scheduling failed or is just a simulation, - * free resources if necessary - */ - if (!assign || num) { + + if (!assign || unsched) { + for (i = 0; i < n; i++) { e = cpuc->event_list[i]; /* @@ -795,11 +855,18 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) if ((e->hw.flags & PERF_X86_EVENT_COMMITTED)) continue; + /* + * release events that failed scheduling + */ if (x86_pmu.put_event_constraints) x86_pmu.put_event_constraints(cpuc, e); } } - return num ? -EINVAL : 0; + + if (x86_pmu.stop_scheduling) + x86_pmu.stop_scheduling(cpuc); + + return unsched ? -EINVAL : 0; } /* @@ -986,6 +1053,9 @@ int x86_perf_event_set_period(struct perf_event *event) if (left > x86_pmu.max_period) left = x86_pmu.max_period; + if (x86_pmu.limit_period) + left = x86_pmu.limit_period(event, left); + per_cpu(pmc_prev_left[idx], smp_processor_id()) = left; /* @@ -1033,7 +1103,6 @@ static int x86_pmu_add(struct perf_event *event, int flags) hwc = &event->hw; - perf_pmu_disable(event->pmu); n0 = cpuc->n_events; ret = n = collect_events(cpuc, event, false); if (ret < 0) @@ -1071,7 +1140,6 @@ done_collect: ret = 0; out: - perf_pmu_enable(event->pmu); return ret; } @@ -1103,7 +1171,7 @@ static void x86_pmu_start(struct perf_event *event, int flags) void perf_event_print_debug(void) { u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed; - u64 pebs; + u64 pebs, debugctl; struct cpu_hw_events *cpuc; unsigned long flags; int cpu, idx; @@ -1121,14 +1189,20 @@ void perf_event_print_debug(void) rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status); rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow); rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed); - rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); pr_info("\n"); pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl); pr_info("CPU#%d: status: %016llx\n", cpu, status); pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow); pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed); - pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); + if (x86_pmu.pebs_constraints) { + rdmsrl(MSR_IA32_PEBS_ENABLE, pebs); + pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs); + } + if (x86_pmu.lbr_nr) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + pr_info("CPU#%d: debugctl: %016llx\n", cpu, debugctl); + } } pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask); @@ -1321,11 +1395,12 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - int ret = NOTIFY_OK; + int i, ret = NOTIFY_OK; switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - cpuc->kfree_on_online = NULL; + for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) + cpuc->kfree_on_online[i] = NULL; if (x86_pmu.cpu_prepare) ret = x86_pmu.cpu_prepare(cpu); break; @@ -1336,7 +1411,10 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu) break; case CPU_ONLINE: - kfree(cpuc->kfree_on_online); + for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) { + kfree(cpuc->kfree_on_online[i]); + cpuc->kfree_on_online[i] = NULL; + } break; case CPU_DYING: @@ -1712,7 +1790,7 @@ static int validate_event(struct perf_event *event) if (IS_ERR(fake_cpuc)) return PTR_ERR(fake_cpuc); - c = x86_pmu.get_event_constraints(fake_cpuc, event); + c = x86_pmu.get_event_constraints(fake_cpuc, -1, event); if (!c || !c->weight) ret = -EINVAL; @@ -1914,10 +1992,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = { NULL, }; -static void x86_pmu_flush_branch_stack(void) +static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) { - if (x86_pmu.flush_branch_stack) - x86_pmu.flush_branch_stack(); + if (x86_pmu.sched_task) + x86_pmu.sched_task(ctx, sched_in); } void perf_check_microcode(void) @@ -1949,7 +2027,8 @@ static struct pmu pmu = { .commit_txn = x86_pmu_commit_txn, .event_idx = x86_pmu_event_idx, - .flush_branch_stack = x86_pmu_flush_branch_stack, + .sched_task = x86_pmu_sched_task, + .task_ctx_size = sizeof(struct x86_perf_task_context), }; void arch_perf_update_userpage(struct perf_event *event, @@ -1968,13 +2047,23 @@ void arch_perf_update_userpage(struct perf_event *event, data = cyc2ns_read_begin(); + /* + * Internal timekeeping for enabled/running/stopped times + * is always in the local_clock domain. + */ userpg->cap_user_time = 1; userpg->time_mult = data->cyc2ns_mul; userpg->time_shift = data->cyc2ns_shift; userpg->time_offset = data->cyc2ns_offset - now; - userpg->cap_user_time_zero = 1; - userpg->time_zero = data->cyc2ns_offset; + /* + * cap_user_time_zero doesn't make sense when we're using a different + * time base for the records. + */ + if (event->clock == &local_clock) { + userpg->cap_user_time_zero = 1; + userpg->time_zero = data->cyc2ns_offset; + } cyc2ns_read_end(data); } @@ -2147,24 +2236,24 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) static unsigned long code_segment_base(struct pt_regs *regs) { /* + * For IA32 we look at the GDT/LDT segment base to convert the + * effective IP to a linear address. + */ + +#ifdef CONFIG_X86_32 + /* * If we are in VM86 mode, add the segment offset to convert to a * linear address. */ if (regs->flags & X86_VM_MASK) return 0x10 * regs->cs; - /* - * For IA32 we look at the GDT/LDT segment base to convert the - * effective IP to a linear address. - */ -#ifdef CONFIG_X86_32 if (user_mode(regs) && regs->cs != __USER_CS) return get_segment_base(regs->cs); #else - if (test_thread_flag(TIF_IA32)) { - if (user_mode(regs) && regs->cs != __USER32_CS) - return get_segment_base(regs->cs); - } + if (user_mode(regs) && !user_64bit_mode(regs) && + regs->cs != __USER32_CS) + return get_segment_base(regs->cs); #endif return 0; } diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index df525d2be1e8..6ac5cb7a9e14 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -65,13 +65,15 @@ struct event_constraint { /* * struct hw_perf_event.flags flags */ -#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ -#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ -#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x40 /* grant rdpmc permission */ +#define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ +#define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ +#define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ +#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ struct amd_nb { @@ -123,8 +125,37 @@ struct intel_shared_regs { unsigned core_id; /* per-core: core id */ }; +enum intel_excl_state_type { + INTEL_EXCL_UNUSED = 0, /* counter is unused */ + INTEL_EXCL_SHARED = 1, /* counter can be used by both threads */ + INTEL_EXCL_EXCLUSIVE = 2, /* counter can be used by one thread only */ +}; + +struct intel_excl_states { + enum intel_excl_state_type init_state[X86_PMC_IDX_MAX]; + enum intel_excl_state_type state[X86_PMC_IDX_MAX]; + int num_alloc_cntrs;/* #counters allocated */ + int max_alloc_cntrs;/* max #counters allowed */ + bool sched_started; /* true if scheduling has started */ +}; + +struct intel_excl_cntrs { + raw_spinlock_t lock; + + struct intel_excl_states states[2]; + + int refcnt; /* per-core: #HT threads */ + unsigned core_id; /* per-core: core id */ +}; + #define MAX_LBR_ENTRIES 16 +enum { + X86_PERF_KFREE_SHARED = 0, + X86_PERF_KFREE_EXCL = 1, + X86_PERF_KFREE_MAX +}; + struct cpu_hw_events { /* * Generic x86 PMC bits @@ -179,6 +210,12 @@ struct cpu_hw_events { * used on Intel NHM/WSM/SNB */ struct intel_shared_regs *shared_regs; + /* + * manage exclusive counter access between hyperthread + */ + struct event_constraint *constraint_list; /* in enable order */ + struct intel_excl_cntrs *excl_cntrs; + int excl_thread_id; /* 0 or 1 */ /* * AMD specific bits @@ -187,7 +224,7 @@ struct cpu_hw_events { /* Inverted mask of bits to clear in the perf_ctr ctrl registers */ u64 perf_ctr_virt_mask; - void *kfree_on_online; + void *kfree_on_online[X86_PERF_KFREE_MAX]; }; #define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ @@ -202,6 +239,10 @@ struct cpu_hw_events { #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) +#define INTEL_EXCLEVT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ + 0, PERF_X86_EVENT_EXCL) + /* * The overlap flag marks event constraints with overlapping counter * masks. This is the case if the counter mask of such an event is not @@ -259,6 +300,10 @@ struct cpu_hw_events { #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) +#define INTEL_EXCLUEVT_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_EXCL) + #define INTEL_PLD_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) @@ -283,22 +328,40 @@ struct cpu_hw_events { /* Check flags and event code, and set the HSW load flag */ #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \ - __EVENT_CONSTRAINT(code, n, \ + __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, \ + PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL) + /* Check flags and event code/umask, and set the HSW store flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \ __EVENT_CONSTRAINT(code, n, \ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW) +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, \ + PERF_X86_EVENT_PEBS_ST_HSW|PERF_X86_EVENT_EXCL) + /* Check flags and event code/umask, and set the HSW load flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \ __EVENT_CONSTRAINT(code, n, \ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(code, n) \ + __EVENT_CONSTRAINT(code, n, \ + INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, \ + PERF_X86_EVENT_PEBS_LD_HSW|PERF_X86_EVENT_EXCL) + /* Check flags and event code/umask, and set the HSW N/A flag */ #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \ __EVENT_CONSTRAINT(code, n, \ @@ -408,6 +471,13 @@ union x86_pmu_config { #define X86_CONFIG(args...) ((union x86_pmu_config){.bits = {args}}).value +enum { + x86_lbr_exclusive_lbr, + x86_lbr_exclusive_bts, + x86_lbr_exclusive_pt, + x86_lbr_exclusive_max, +}; + /* * struct x86_pmu - generic x86 pmu */ @@ -443,14 +513,25 @@ struct x86_pmu { u64 max_period; struct event_constraint * (*get_event_constraints)(struct cpu_hw_events *cpuc, + int idx, struct perf_event *event); void (*put_event_constraints)(struct cpu_hw_events *cpuc, struct perf_event *event); + + void (*commit_scheduling)(struct cpu_hw_events *cpuc, + struct perf_event *event, + int cntr); + + void (*start_scheduling)(struct cpu_hw_events *cpuc); + + void (*stop_scheduling)(struct cpu_hw_events *cpuc); + struct event_constraint *event_constraints; struct x86_pmu_quirk *quirks; int perfctr_second_write; bool late_ack; + unsigned (*limit_period)(struct perf_event *event, unsigned l); /* * sysfs attrs @@ -472,7 +553,8 @@ struct x86_pmu { void (*cpu_dead)(int cpu); void (*check_microcode)(void); - void (*flush_branch_stack)(void); + void (*sched_task)(struct perf_event_context *ctx, + bool sched_in); /* * Intel Arch Perfmon v2+ @@ -504,10 +586,15 @@ struct x86_pmu { bool lbr_double_abort; /* duplicated lbr aborts */ /* + * Intel PT/LBR/BTS are exclusive + */ + atomic_t lbr_exclusive[x86_lbr_exclusive_max]; + + /* * Extra registers for events */ struct extra_reg *extra_regs; - unsigned int er_flags; + unsigned int flags; /* * Intel host/guest support (KVM) @@ -515,6 +602,13 @@ struct x86_pmu { struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr); }; +struct x86_perf_task_context { + u64 lbr_from[MAX_LBR_ENTRIES]; + u64 lbr_to[MAX_LBR_ENTRIES]; + int lbr_callstack_users; + int lbr_stack_state; +}; + #define x86_add_quirk(func_) \ do { \ static struct x86_pmu_quirk __quirk __initdata = { \ @@ -524,8 +618,13 @@ do { \ x86_pmu.quirks = &__quirk; \ } while (0) -#define ERF_NO_HT_SHARING 1 -#define ERF_HAS_RSP_1 2 +/* + * x86_pmu flags + */ +#define PMU_FL_NO_HT_SHARING 0x1 /* no hyper-threading resource sharing */ +#define PMU_FL_HAS_RSP_1 0x2 /* has 2 equivalent offcore_rsp regs */ +#define PMU_FL_EXCL_CNTRS 0x4 /* has exclusive counter requirements */ +#define PMU_FL_EXCL_ENABLED 0x8 /* exclusive counter active */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -546,6 +645,12 @@ static struct perf_pmu_events_attr event_attr_##v = { \ extern struct x86_pmu x86_pmu __read_mostly; +static inline bool x86_pmu_has_lbr_callstack(void) +{ + return x86_pmu.lbr_sel_map && + x86_pmu.lbr_sel_map[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] > 0; +} + DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); int x86_perf_event_set_period(struct perf_event *event); @@ -588,6 +693,12 @@ static inline int x86_pmu_rdpmc_index(int index) return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index; } +int x86_add_exclusive(unsigned int what); + +void x86_del_exclusive(unsigned int what); + +void hw_perf_lbr_event_destroy(struct perf_event *event); + int x86_setup_perfctr(struct perf_event *event); int x86_pmu_hw_config(struct perf_event *event); @@ -674,10 +785,34 @@ static inline int amd_pmu_init(void) #ifdef CONFIG_CPU_SUP_INTEL +static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) +{ + /* user explicitly requested branch sampling */ + if (has_branch_stack(event)) + return true; + + /* implicit branch sampling to correct PEBS skid */ + if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && + x86_pmu.intel_cap.pebs_format < 2) + return true; + + return false; +} + +static inline bool intel_pmu_has_bts(struct perf_event *event) +{ + if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && + !event->attr.freq && event->hw.sample_period == 1) + return true; + + return false; +} + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event); +x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event); struct intel_shared_regs *allocate_shared_regs(int cpu); @@ -727,13 +862,15 @@ void intel_pmu_pebs_disable_all(void); void intel_ds_init(void); +void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); + void intel_pmu_lbr_reset(void); void intel_pmu_lbr_enable(struct perf_event *event); void intel_pmu_lbr_disable(struct perf_event *event); -void intel_pmu_lbr_enable_all(void); +void intel_pmu_lbr_enable_all(bool pmi); void intel_pmu_lbr_disable_all(void); @@ -747,8 +884,18 @@ void intel_pmu_lbr_init_atom(void); void intel_pmu_lbr_init_snb(void); +void intel_pmu_lbr_init_hsw(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); +void intel_pt_interrupt(void); + +int intel_bts_interrupt(void); + +void intel_bts_enable_local(void); + +void intel_bts_disable_local(void); + int p4_pmu_init(void); int p6_pmu_init(void); @@ -758,6 +905,10 @@ int knc_pmu_init(void); ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); +static inline int is_ht_workaround_enabled(void) +{ + return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED); +} #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 28926311aac1..1cee5d2d7ece 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -382,6 +382,7 @@ static int amd_pmu_cpu_prepare(int cpu) static void amd_pmu_cpu_starting(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; struct amd_nb *nb; int i, nb_id; @@ -399,7 +400,7 @@ static void amd_pmu_cpu_starting(int cpu) continue; if (nb->nb_id == nb_id) { - cpuc->kfree_on_online = cpuc->amd_nb; + *onln = cpuc->amd_nb; cpuc->amd_nb = nb; break; } @@ -429,7 +430,8 @@ static void amd_pmu_cpu_dead(int cpu) } static struct event_constraint * -amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { /* * if not NB event or no NB, then no constraints @@ -537,7 +539,8 @@ static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); static struct event_constraint * -amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) +amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; unsigned int event_code = amd_get_event_code(hwc); diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index a61f5c6911da..989d3c215d2b 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -796,7 +796,7 @@ static int setup_ibs_ctl(int ibs_eilvt_off) * the IBS interrupt vector is handled by perf_ibs_cpu_notifier that * is using the new offset. */ -static int force_ibs_eilvt_setup(void) +static void force_ibs_eilvt_setup(void) { int offset; int ret; @@ -811,26 +811,24 @@ static int force_ibs_eilvt_setup(void) if (offset == APIC_EILVT_NR_MAX) { printk(KERN_DEBUG "No EILVT entry available\n"); - return -EBUSY; + return; } ret = setup_ibs_ctl(offset); if (ret) goto out; - if (!ibs_eilvt_valid()) { - ret = -EFAULT; + if (!ibs_eilvt_valid()) goto out; - } pr_info("IBS: LVT offset %d assigned\n", offset); - return 0; + return; out: preempt_disable(); put_eilvt(offset); preempt_enable(); - return ret; + return; } static void ibs_eilvt_setup(void) diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 258990688a5e..219d3fb423a1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/export.h> +#include <linux/watchdog.h> #include <asm/cpufeature.h> #include <asm/hardirq.h> @@ -113,6 +114,12 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -131,15 +138,12 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ - /* - * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT - * siblings; disable these events because they can corrupt unrelated - * counters. - */ - INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + EVENT_CONSTRAINT_END }; @@ -217,6 +221,21 @@ static struct event_constraint intel_hsw_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), + + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + + EVENT_CONSTRAINT_END +}; + +struct event_constraint intel_bdw_event_constraints[] = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ + INTEL_EVENT_CONSTRAINT(0xa3, 0x4), /* CYCLE_ACTIVITY.* */ EVENT_CONSTRAINT_END }; @@ -415,6 +434,202 @@ static __initconst const u64 snb_hw_cache_event_ids }; +/* + * Notes on the events: + * - data reads do not include code reads (comparable to earlier tables) + * - data counts include speculative execution (except L1 write, dtlb, bpu) + * - remote node access includes remote memory, remote cache, remote mmio. + * - prefetches are not included in the counts because they are not + * reliably counted. + */ + +#define HSW_DEMAND_DATA_RD BIT_ULL(0) +#define HSW_DEMAND_RFO BIT_ULL(1) +#define HSW_ANY_RESPONSE BIT_ULL(16) +#define HSW_SUPPLIER_NONE BIT_ULL(17) +#define HSW_L3_MISS_LOCAL_DRAM BIT_ULL(22) +#define HSW_L3_MISS_REMOTE_HOP0 BIT_ULL(27) +#define HSW_L3_MISS_REMOTE_HOP1 BIT_ULL(28) +#define HSW_L3_MISS_REMOTE_HOP2P BIT_ULL(29) +#define HSW_L3_MISS (HSW_L3_MISS_LOCAL_DRAM| \ + HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \ + HSW_L3_MISS_REMOTE_HOP2P) +#define HSW_SNOOP_NONE BIT_ULL(31) +#define HSW_SNOOP_NOT_NEEDED BIT_ULL(32) +#define HSW_SNOOP_MISS BIT_ULL(33) +#define HSW_SNOOP_HIT_NO_FWD BIT_ULL(34) +#define HSW_SNOOP_HIT_WITH_FWD BIT_ULL(35) +#define HSW_SNOOP_HITM BIT_ULL(36) +#define HSW_SNOOP_NON_DRAM BIT_ULL(37) +#define HSW_ANY_SNOOP (HSW_SNOOP_NONE| \ + HSW_SNOOP_NOT_NEEDED|HSW_SNOOP_MISS| \ + HSW_SNOOP_HIT_NO_FWD|HSW_SNOOP_HIT_WITH_FWD| \ + HSW_SNOOP_HITM|HSW_SNOOP_NON_DRAM) +#define HSW_SNOOP_DRAM (HSW_ANY_SNOOP & ~HSW_SNOOP_NON_DRAM) +#define HSW_DEMAND_READ HSW_DEMAND_DATA_RD +#define HSW_DEMAND_WRITE HSW_DEMAND_RFO +#define HSW_L3_MISS_REMOTE (HSW_L3_MISS_REMOTE_HOP0|\ + HSW_L3_MISS_REMOTE_HOP1|HSW_L3_MISS_REMOTE_HOP2P) +#define HSW_LLC_ACCESS HSW_ANY_RESPONSE + +#define BDW_L3_MISS_LOCAL BIT(26) +#define BDW_L3_MISS (BDW_L3_MISS_LOCAL| \ + HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \ + HSW_L3_MISS_REMOTE_HOP2P) + + +static __initconst const u64 hsw_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x151, /* L1D.REPLACEMENT */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x280, /* ICACHE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x81d0, /* MEM_UOPS_RETIRED.ALL_LOADS */ + [ C(RESULT_MISS) ] = 0x108, /* DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x82d0, /* MEM_UOPS_RETIRED.ALL_STORES */ + [ C(RESULT_MISS) ] = 0x149, /* DTLB_STORE_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x6085, /* ITLB_MISSES.STLB_HIT */ + [ C(RESULT_MISS) ] = 0x185, /* ITLB_MISSES.MISS_CAUSES_A_WALK */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0xc4, /* BR_INST_RETIRED.ALL_BRANCHES */ + [ C(RESULT_MISS) ] = 0xc5, /* BR_MISP_RETIRED.ALL_BRANCHES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + [ C(RESULT_MISS) ] = 0x1b7, /* OFFCORE_RESPONSE */ + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + +static __initconst const u64 hsw_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_READ| + HSW_LLC_ACCESS, + [ C(RESULT_MISS) ] = HSW_DEMAND_READ| + HSW_L3_MISS|HSW_ANY_SNOOP, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE| + HSW_LLC_ACCESS, + [ C(RESULT_MISS) ] = HSW_DEMAND_WRITE| + HSW_L3_MISS|HSW_ANY_SNOOP, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, + [ C(NODE) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_READ| + HSW_L3_MISS_LOCAL_DRAM| + HSW_SNOOP_DRAM, + [ C(RESULT_MISS) ] = HSW_DEMAND_READ| + HSW_L3_MISS_REMOTE| + HSW_SNOOP_DRAM, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = HSW_DEMAND_WRITE| + HSW_L3_MISS_LOCAL_DRAM| + HSW_SNOOP_DRAM, + [ C(RESULT_MISS) ] = HSW_DEMAND_WRITE| + HSW_L3_MISS_REMOTE| + HSW_SNOOP_DRAM, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0x0, + [ C(RESULT_MISS) ] = 0x0, + }, + }, +}; + static __initconst const u64 westmere_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] @@ -1029,21 +1244,10 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; -static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) -{ - /* user explicitly requested branch sampling */ - if (has_branch_stack(event)) - return true; - - /* implicit branch sampling to correct PEBS skid */ - if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1 && - x86_pmu.intel_cap.pebs_format < 2) - return true; - - return false; -} - -static void intel_pmu_disable_all(void) +/* + * Use from PMIs where the LBRs are already disabled. + */ +static void __intel_pmu_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1051,17 +1255,24 @@ static void intel_pmu_disable_all(void) if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); + else + intel_bts_disable_local(); intel_pmu_pebs_disable_all(); +} + +static void intel_pmu_disable_all(void) +{ + __intel_pmu_disable_all(); intel_pmu_lbr_disable_all(); } -static void intel_pmu_enable_all(int added) +static void __intel_pmu_enable_all(int added, bool pmi) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); intel_pmu_pebs_enable_all(); - intel_pmu_lbr_enable_all(); + intel_pmu_lbr_enable_all(pmi); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask); @@ -1073,7 +1284,13 @@ static void intel_pmu_enable_all(int added) return; intel_pmu_enable_bts(event->hw.config); - } + } else + intel_bts_enable_local(); +} + +static void intel_pmu_enable_all(int added) +{ + __intel_pmu_enable_all(added, false); } /* @@ -1207,7 +1424,7 @@ static void intel_pmu_disable_event(struct perf_event *event) * must disable before any actual event * because any event may be combined with LBR */ - if (intel_pmu_needs_lbr_smpl(event)) + if (needs_branch_stack(event)) intel_pmu_lbr_disable(event); if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) { @@ -1268,7 +1485,7 @@ static void intel_pmu_enable_event(struct perf_event *event) * must enabled before any actual event * because any event may be combined with LBR */ - if (intel_pmu_needs_lbr_smpl(event)) + if (needs_branch_stack(event)) intel_pmu_lbr_enable(event); if (event->attr.exclude_host) @@ -1334,6 +1551,18 @@ static void intel_pmu_reset(void) if (ds) ds->bts_index = ds->bts_buffer_base; + /* Ack all overflows and disable fixed counters */ + if (x86_pmu.version >= 2) { + intel_pmu_ack_status(intel_pmu_get_status()); + wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); + } + + /* Reset LBRs and LBR freezing */ + if (x86_pmu.lbr_nr) { + update_debugctlmsr(get_debugctlmsr() & + ~(DEBUGCTLMSR_FREEZE_LBRS_ON_PMI|DEBUGCTLMSR_LBR)); + } + local_irq_restore(flags); } @@ -1357,8 +1586,9 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) */ if (!x86_pmu.late_ack) apic_write(APIC_LVTPC, APIC_DM_NMI); - intel_pmu_disable_all(); + __intel_pmu_disable_all(); handled = intel_pmu_drain_bts_buffer(); + handled += intel_bts_interrupt(); status = intel_pmu_get_status(); if (!status) goto done; @@ -1399,6 +1629,14 @@ again: } /* + * Intel PT + */ + if (__test_and_clear_bit(55, (unsigned long *)&status)) { + handled++; + intel_pt_interrupt(); + } + + /* * Checkpointed counters can lead to 'spurious' PMIs because the * rollback caused by the PMI will have cleared the overflow status * bit. Therefore always force probe these counters. @@ -1433,7 +1671,7 @@ again: goto again; done: - intel_pmu_enable_all(0); + __intel_pmu_enable_all(0, true); /* * Only unmask the NMI after the overflow counters * have been reset. This avoids spurious NMIs on @@ -1464,7 +1702,7 @@ intel_bts_constraints(struct perf_event *event) static int intel_alt_er(int idx) { - if (!(x86_pmu.er_flags & ERF_HAS_RSP_1)) + if (!(x86_pmu.flags & PMU_FL_HAS_RSP_1)) return idx; if (idx == EXTRA_REG_RSP_0) @@ -1624,7 +1862,8 @@ intel_shared_regs_constraints(struct cpu_hw_events *cpuc, } struct event_constraint * -x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { struct event_constraint *c; @@ -1641,7 +1880,8 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) } static struct event_constraint * -intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +__intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { struct event_constraint *c; @@ -1657,7 +1897,278 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event if (c) return c; - return x86_get_event_constraints(cpuc, event); + return x86_get_event_constraints(cpuc, idx, event); +} + +static void +intel_start_scheduling(struct cpu_hw_events *cpuc) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xl, *xlo; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; /* sibling thread */ + + /* + * nothing needed if in group validation mode + */ + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + + /* + * no exclusion needed + */ + if (!excl_cntrs) + return; + + xlo = &excl_cntrs->states[o_tid]; + xl = &excl_cntrs->states[tid]; + + xl->sched_started = true; + xl->num_alloc_cntrs = 0; + /* + * lock shared state until we are done scheduling + * in stop_event_scheduling() + * makes scheduling appear as a transaction + */ + WARN_ON_ONCE(!irqs_disabled()); + raw_spin_lock(&excl_cntrs->lock); + + /* + * save initial state of sibling thread + */ + memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state)); +} + +static void +intel_stop_scheduling(struct cpu_hw_events *cpuc) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xl, *xlo; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; /* sibling thread */ + + /* + * nothing needed if in group validation mode + */ + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return; + /* + * no exclusion needed + */ + if (!excl_cntrs) + return; + + xlo = &excl_cntrs->states[o_tid]; + xl = &excl_cntrs->states[tid]; + + /* + * make new sibling thread state visible + */ + memcpy(xlo->state, xlo->init_state, sizeof(xlo->state)); + + xl->sched_started = false; + /* + * release shared state lock (acquired in intel_start_scheduling()) + */ + raw_spin_unlock(&excl_cntrs->lock); +} + +static struct event_constraint * +intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event, + int idx, struct event_constraint *c) +{ + struct event_constraint *cx; + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xl, *xlo; + int is_excl, i; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; /* alternate */ + + /* + * validating a group does not require + * enforcing cross-thread exclusion + */ + if (cpuc->is_fake || !is_ht_workaround_enabled()) + return c; + + /* + * no exclusion needed + */ + if (!excl_cntrs) + return c; + /* + * event requires exclusive counter access + * across HT threads + */ + is_excl = c->flags & PERF_X86_EVENT_EXCL; + + /* + * xl = state of current HT + * xlo = state of sibling HT + */ + xl = &excl_cntrs->states[tid]; + xlo = &excl_cntrs->states[o_tid]; + + /* + * do not allow scheduling of more than max_alloc_cntrs + * which is set to half the available generic counters. + * this helps avoid counter starvation of sibling thread + * by ensuring at most half the counters cannot be in + * exclusive mode. There is not designated counters for the + * limits. Any N/2 counters can be used. This helps with + * events with specifix counter constraints + */ + if (xl->num_alloc_cntrs++ == xl->max_alloc_cntrs) + return &emptyconstraint; + + cx = c; + + /* + * because we modify the constraint, we need + * to make a copy. Static constraints come + * from static const tables. + * + * only needed when constraint has not yet + * been cloned (marked dynamic) + */ + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) { + + /* sanity check */ + if (idx < 0) + return &emptyconstraint; + + /* + * grab pre-allocated constraint entry + */ + cx = &cpuc->constraint_list[idx]; + + /* + * initialize dynamic constraint + * with static constraint + */ + memcpy(cx, c, sizeof(*cx)); + + /* + * mark constraint as dynamic, so we + * can free it later on + */ + cx->flags |= PERF_X86_EVENT_DYNAMIC; + } + + /* + * From here on, the constraint is dynamic. + * Either it was just allocated above, or it + * was allocated during a earlier invocation + * of this function + */ + + /* + * Modify static constraint with current dynamic + * state of thread + * + * EXCLUSIVE: sibling counter measuring exclusive event + * SHARED : sibling counter measuring non-exclusive event + * UNUSED : sibling counter unused + */ + for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) { + /* + * exclusive event in sibling counter + * our corresponding counter cannot be used + * regardless of our event + */ + if (xl->state[i] == INTEL_EXCL_EXCLUSIVE) + __clear_bit(i, cx->idxmsk); + /* + * if measuring an exclusive event, sibling + * measuring non-exclusive, then counter cannot + * be used + */ + if (is_excl && xl->state[i] == INTEL_EXCL_SHARED) + __clear_bit(i, cx->idxmsk); + } + + /* + * recompute actual bit weight for scheduling algorithm + */ + cx->weight = hweight64(cx->idxmsk64); + + /* + * if we return an empty mask, then switch + * back to static empty constraint to avoid + * the cost of freeing later on + */ + if (cx->weight == 0) + cx = &emptyconstraint; + + return cx; +} + +static struct event_constraint * +intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct event_constraint *c1 = event->hw.constraint; + struct event_constraint *c2; + + /* + * first time only + * - static constraint: no change across incremental scheduling calls + * - dynamic constraint: handled by intel_get_excl_constraints() + */ + c2 = __intel_get_event_constraints(cpuc, idx, event); + if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) { + bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX); + c1->weight = c2->weight; + c2 = c1; + } + + if (cpuc->excl_cntrs) + return intel_get_excl_constraints(cpuc, event, idx, c2); + + return c2; +} + +static void intel_put_excl_constraints(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct intel_excl_states *xlo, *xl; + unsigned long flags = 0; /* keep compiler happy */ + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; + + /* + * nothing needed if in group validation mode + */ + if (cpuc->is_fake) + return; + + WARN_ON_ONCE(!excl_cntrs); + + if (!excl_cntrs) + return; + + xl = &excl_cntrs->states[tid]; + xlo = &excl_cntrs->states[o_tid]; + + /* + * put_constraint may be called from x86_schedule_events() + * which already has the lock held so here make locking + * conditional + */ + if (!xl->sched_started) + raw_spin_lock_irqsave(&excl_cntrs->lock, flags); + + /* + * if event was actually assigned, then mark the + * counter state as unused now + */ + if (hwc->idx >= 0) + xlo->state[hwc->idx] = INTEL_EXCL_UNUSED; + + if (!xl->sched_started) + raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags); } static void @@ -1678,7 +2189,57 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { + struct event_constraint *c = event->hw.constraint; + intel_put_shared_regs_event_constraints(cpuc, event); + + /* + * is PMU has exclusive counter restrictions, then + * all events are subject to and must call the + * put_excl_constraints() routine + */ + if (c && cpuc->excl_cntrs) + intel_put_excl_constraints(cpuc, event); + + /* cleanup dynamic constraint */ + if (c && (c->flags & PERF_X86_EVENT_DYNAMIC)) + event->hw.constraint = NULL; +} + +static void intel_commit_scheduling(struct cpu_hw_events *cpuc, + struct perf_event *event, int cntr) +{ + struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs; + struct event_constraint *c = event->hw.constraint; + struct intel_excl_states *xlo, *xl; + int tid = cpuc->excl_thread_id; + int o_tid = 1 - tid; + int is_excl; + + if (cpuc->is_fake || !c) + return; + + is_excl = c->flags & PERF_X86_EVENT_EXCL; + + if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) + return; + + WARN_ON_ONCE(!excl_cntrs); + + if (!excl_cntrs) + return; + + xl = &excl_cntrs->states[tid]; + xlo = &excl_cntrs->states[o_tid]; + + WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock)); + + if (cntr >= 0) { + if (is_excl) + xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE; + else + xlo->init_state[cntr] = INTEL_EXCL_SHARED; + } } static void intel_pebs_aliases_core2(struct perf_event *event) @@ -1747,10 +2308,21 @@ static int intel_pmu_hw_config(struct perf_event *event) if (event->attr.precise_ip && x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); - if (intel_pmu_needs_lbr_smpl(event)) { + if (needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); if (ret) return ret; + + /* + * BTS is set up earlier in this path, so don't account twice + */ + if (!intel_pmu_has_bts(event)) { + /* disallow lbr if conflicting events are present */ + if (x86_add_exclusive(x86_lbr_exclusive_lbr)) + return -EBUSY; + + event->destroy = hw_perf_lbr_event_destroy; + } } if (event->attr.type != PERF_TYPE_RAW) @@ -1891,9 +2463,12 @@ static struct event_constraint counter2_constraint = EVENT_CONSTRAINT(0, 0x4, 0); static struct event_constraint * -hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) +hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) { - struct event_constraint *c = intel_get_event_constraints(cpuc, event); + struct event_constraint *c; + + c = intel_get_event_constraints(cpuc, idx, event); /* Handle special quirk on in_tx_checkpointed only in counter 2 */ if (event->hw.config & HSW_IN_TX_CHECKPOINTED) { @@ -1905,6 +2480,32 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) return c; } +/* + * Broadwell: + * + * The INST_RETIRED.ALL period always needs to have lowest 6 bits cleared + * (BDM55) and it must not use a period smaller than 100 (BDM11). We combine + * the two to enforce a minimum period of 128 (the smallest value that has bits + * 0-5 cleared and >= 100). + * + * Because of how the code in x86_perf_event_set_period() works, the truncation + * of the lower 6 bits is 'harmless' as we'll occasionally add a longer period + * to make up for the 'lost' events due to carrying the 'error' in period_left. + * + * Therefore the effective (average) period matches the requested period, + * despite coarser hardware granularity. + */ +static unsigned bdw_limit_period(struct perf_event *event, unsigned left) +{ + if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (left < 128) + left = 128; + left &= ~0x3fu; + } + return left; +} + PMU_FORMAT_ATTR(event, "config:0-7" ); PMU_FORMAT_ATTR(umask, "config:8-15" ); PMU_FORMAT_ATTR(edge, "config:18" ); @@ -1979,16 +2580,52 @@ struct intel_shared_regs *allocate_shared_regs(int cpu) return regs; } +static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu) +{ + struct intel_excl_cntrs *c; + int i; + + c = kzalloc_node(sizeof(struct intel_excl_cntrs), + GFP_KERNEL, cpu_to_node(cpu)); + if (c) { + raw_spin_lock_init(&c->lock); + for (i = 0; i < X86_PMC_IDX_MAX; i++) { + c->states[0].state[i] = INTEL_EXCL_UNUSED; + c->states[0].init_state[i] = INTEL_EXCL_UNUSED; + + c->states[1].state[i] = INTEL_EXCL_UNUSED; + c->states[1].init_state[i] = INTEL_EXCL_UNUSED; + } + c->core_id = -1; + } + return c; +} + static int intel_pmu_cpu_prepare(int cpu) { struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); - if (!(x86_pmu.extra_regs || x86_pmu.lbr_sel_map)) - return NOTIFY_OK; + if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) { + cpuc->shared_regs = allocate_shared_regs(cpu); + if (!cpuc->shared_regs) + return NOTIFY_BAD; + } - cpuc->shared_regs = allocate_shared_regs(cpu); - if (!cpuc->shared_regs) - return NOTIFY_BAD; + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); + + cpuc->constraint_list = kzalloc(sz, GFP_KERNEL); + if (!cpuc->constraint_list) + return NOTIFY_BAD; + + cpuc->excl_cntrs = allocate_excl_cntrs(cpu); + if (!cpuc->excl_cntrs) { + kfree(cpuc->constraint_list); + kfree(cpuc->shared_regs); + return NOTIFY_BAD; + } + cpuc->excl_thread_id = 0; + } return NOTIFY_OK; } @@ -2010,13 +2647,15 @@ static void intel_pmu_cpu_starting(int cpu) if (!cpuc->shared_regs) return; - if (!(x86_pmu.er_flags & ERF_NO_HT_SHARING)) { + if (!(x86_pmu.flags & PMU_FL_NO_HT_SHARING)) { + void **onln = &cpuc->kfree_on_online[X86_PERF_KFREE_SHARED]; + for_each_cpu(i, topology_thread_cpumask(cpu)) { struct intel_shared_regs *pc; pc = per_cpu(cpu_hw_events, i).shared_regs; if (pc && pc->core_id == core_id) { - cpuc->kfree_on_online = cpuc->shared_regs; + *onln = cpuc->shared_regs; cpuc->shared_regs = pc; break; } @@ -2027,6 +2666,44 @@ static void intel_pmu_cpu_starting(int cpu) if (x86_pmu.lbr_sel_map) cpuc->lbr_sel = &cpuc->shared_regs->regs[EXTRA_REG_LBR]; + + if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) { + int h = x86_pmu.num_counters >> 1; + + for_each_cpu(i, topology_thread_cpumask(cpu)) { + struct intel_excl_cntrs *c; + + c = per_cpu(cpu_hw_events, i).excl_cntrs; + if (c && c->core_id == core_id) { + cpuc->kfree_on_online[1] = cpuc->excl_cntrs; + cpuc->excl_cntrs = c; + cpuc->excl_thread_id = 1; + break; + } + } + cpuc->excl_cntrs->core_id = core_id; + cpuc->excl_cntrs->refcnt++; + /* + * set hard limit to half the number of generic counters + */ + cpuc->excl_cntrs->states[0].max_alloc_cntrs = h; + cpuc->excl_cntrs->states[1].max_alloc_cntrs = h; + } +} + +static void free_excl_cntrs(int cpu) +{ + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + struct intel_excl_cntrs *c; + + c = cpuc->excl_cntrs; + if (c) { + if (c->core_id == -1 || --c->refcnt == 0) + kfree(c); + cpuc->excl_cntrs = NULL; + kfree(cpuc->constraint_list); + cpuc->constraint_list = NULL; + } } static void intel_pmu_cpu_dying(int cpu) @@ -2041,19 +2718,9 @@ static void intel_pmu_cpu_dying(int cpu) cpuc->shared_regs = NULL; } - fini_debug_store_on_cpu(cpu); -} + free_excl_cntrs(cpu); -static void intel_pmu_flush_branch_stack(void) -{ - /* - * Intel LBR does not tag entries with the - * PID of the current task, then we need to - * flush it on ctxsw - * For now, we simply reset it - */ - if (x86_pmu.lbr_nr) - intel_pmu_lbr_reset(); + fini_debug_store_on_cpu(cpu); } PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); @@ -2107,7 +2774,7 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .guest_get_msrs = intel_guest_get_msrs, - .flush_branch_stack = intel_pmu_flush_branch_stack, + .sched_task = intel_pmu_lbr_sched_task, }; static __init void intel_clovertown_quirk(void) @@ -2264,6 +2931,27 @@ static __init void intel_nehalem_quirk(void) } } +/* + * enable software workaround for errata: + * SNB: BJ122 + * IVB: BV98 + * HSW: HSD29 + * + * Only needed when HT is enabled. However detecting + * if HT is enabled is difficult (model specific). So instead, + * we enable the workaround in the early boot, and verify if + * it is needed in a later initcall phase once we have valid + * topology information to check if HT is actually enabled + */ +static __init void intel_ht_bug(void) +{ + x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED; + + x86_pmu.commit_scheduling = intel_commit_scheduling; + x86_pmu.start_scheduling = intel_start_scheduling; + x86_pmu.stop_scheduling = intel_stop_scheduling; +} + EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3"); EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82") @@ -2443,7 +3131,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_slm_event_constraints; x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; x86_pmu.extra_regs = intel_slm_extra_regs; - x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; pr_cont("Silvermont events, "); break; @@ -2461,7 +3149,7 @@ __init int intel_pmu_init(void) x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.pebs_constraints = intel_westmere_pebs_event_constraints; x86_pmu.extra_regs = intel_westmere_extra_regs; - x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.cpu_events = nhm_events_attrs; @@ -2478,6 +3166,7 @@ __init int intel_pmu_init(void) case 42: /* 32nm SandyBridge */ case 45: /* 32nm SandyBridge-E/EN/EP */ x86_add_quirk(intel_sandybridge_quirk); + x86_add_quirk(intel_ht_bug); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, @@ -2492,9 +3181,11 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_snbep_extra_regs; else x86_pmu.extra_regs = intel_snb_extra_regs; + + /* all extra regs are per-cpu when HT is on */ - x86_pmu.er_flags |= ERF_HAS_RSP_1; - x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.cpu_events = snb_events_attrs; @@ -2510,6 +3201,7 @@ __init int intel_pmu_init(void) case 58: /* 22nm IvyBridge */ case 62: /* 22nm IvyBridge-EP/EX */ + x86_add_quirk(intel_ht_bug); memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); /* dTLB-load-misses on IVB is different than SNB */ @@ -2528,8 +3220,8 @@ __init int intel_pmu_init(void) else x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ - x86_pmu.er_flags |= ERF_HAS_RSP_1; - x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.cpu_events = snb_events_attrs; @@ -2545,19 +3237,20 @@ __init int intel_pmu_init(void) case 63: /* 22nm Haswell Server */ case 69: /* 22nm Haswell ULT */ case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */ + x86_add_quirk(intel_ht_bug); x86_pmu.late_ack = true; - memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); - intel_pmu_lbr_init_snb(); + intel_pmu_lbr_init_hsw(); x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; /* all extra regs are per-cpu when HT is on */ - x86_pmu.er_flags |= ERF_HAS_RSP_1; - x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; @@ -2566,6 +3259,39 @@ __init int intel_pmu_init(void) pr_cont("Haswell events, "); break; + case 61: /* 14nm Broadwell Core-M */ + case 86: /* 14nm Broadwell Xeon D */ + x86_pmu.late_ack = true; + memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + + /* L3_MISS_LOCAL_DRAM is BIT(26) in Broadwell */ + hw_cache_extra_regs[C(LL)][C(OP_READ)][C(RESULT_MISS)] = HSW_DEMAND_READ | + BDW_L3_MISS|HSW_SNOOP_DRAM; + hw_cache_extra_regs[C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = HSW_DEMAND_WRITE|BDW_L3_MISS| + HSW_SNOOP_DRAM; + hw_cache_extra_regs[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = HSW_DEMAND_READ| + BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM; + hw_cache_extra_regs[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = HSW_DEMAND_WRITE| + BDW_L3_MISS_LOCAL|HSW_SNOOP_DRAM; + + intel_pmu_lbr_init_hsw(); + + x86_pmu.event_constraints = intel_bdw_event_constraints; + x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; + x86_pmu.extra_regs = intel_snbep_extra_regs; + x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + x86_pmu.hw_config = hsw_hw_config; + x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.cpu_events = hsw_events_attrs; + x86_pmu.limit_period = bdw_limit_period; + pr_cont("Broadwell events, "); + break; + default: switch (x86_pmu.version) { case 1: @@ -2651,3 +3377,47 @@ __init int intel_pmu_init(void) return 0; } + +/* + * HT bug: phase 2 init + * Called once we have valid topology information to check + * whether or not HT is enabled + * If HT is off, then we disable the workaround + */ +static __init int fixup_ht_bug(void) +{ + int cpu = smp_processor_id(); + int w, c; + /* + * problem not present on this CPU model, nothing to do + */ + if (!(x86_pmu.flags & PMU_FL_EXCL_ENABLED)) + return 0; + + w = cpumask_weight(topology_thread_cpumask(cpu)); + if (w > 1) { + pr_info("PMU erratum BJ122, BV98, HSD29 worked around, HT is on\n"); + return 0; + } + + watchdog_nmi_disable_all(); + + x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED); + + x86_pmu.commit_scheduling = NULL; + x86_pmu.start_scheduling = NULL; + x86_pmu.stop_scheduling = NULL; + + watchdog_nmi_enable_all(); + + get_online_cpus(); + + for_each_online_cpu(c) { + free_excl_cntrs(c); + } + + put_online_cpus(); + pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n"); + return 0; +} +subsys_initcall(fixup_ht_bug) diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c new file mode 100644 index 000000000000..ac1f0c55f379 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c @@ -0,0 +1,525 @@ +/* + * BTS PMU driver for perf + * Copyright (c) 2013-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#undef DEBUG + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/bitops.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/debugfs.h> +#include <linux/device.h> +#include <linux/coredump.h> + +#include <asm-generic/sizes.h> +#include <asm/perf_event.h> + +#include "perf_event.h" + +struct bts_ctx { + struct perf_output_handle handle; + struct debug_store ds_back; + int started; +}; + +static DEFINE_PER_CPU(struct bts_ctx, bts_ctx); + +#define BTS_RECORD_SIZE 24 +#define BTS_SAFETY_MARGIN 4080 + +struct bts_phys { + struct page *page; + unsigned long size; + unsigned long offset; + unsigned long displacement; +}; + +struct bts_buffer { + size_t real_size; /* multiple of BTS_RECORD_SIZE */ + unsigned int nr_pages; + unsigned int nr_bufs; + unsigned int cur_buf; + bool snapshot; + local_t data_size; + local_t lost; + local_t head; + unsigned long end; + void **data_pages; + struct bts_phys buf[0]; +}; + +struct pmu bts_pmu; + +void intel_pmu_enable_bts(u64 config); +void intel_pmu_disable_bts(void); + +static size_t buf_size(struct page *page) +{ + return 1 << (PAGE_SHIFT + page_private(page)); +} + +static void * +bts_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool overwrite) +{ + struct bts_buffer *buf; + struct page *page; + int node = (cpu == -1) ? cpu : cpu_to_node(cpu); + unsigned long offset; + size_t size = nr_pages << PAGE_SHIFT; + int pg, nbuf, pad; + + /* count all the high order buffers */ + for (pg = 0, nbuf = 0; pg < nr_pages;) { + page = virt_to_page(pages[pg]); + if (WARN_ON_ONCE(!PagePrivate(page) && nr_pages > 1)) + return NULL; + pg += 1 << page_private(page); + nbuf++; + } + + /* + * to avoid interrupts in overwrite mode, only allow one physical + */ + if (overwrite && nbuf > 1) + return NULL; + + buf = kzalloc_node(offsetof(struct bts_buffer, buf[nbuf]), GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->nr_pages = nr_pages; + buf->nr_bufs = nbuf; + buf->snapshot = overwrite; + buf->data_pages = pages; + buf->real_size = size - size % BTS_RECORD_SIZE; + + for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) { + unsigned int __nr_pages; + + page = virt_to_page(pages[pg]); + __nr_pages = PagePrivate(page) ? 1 << page_private(page) : 1; + buf->buf[nbuf].page = page; + buf->buf[nbuf].offset = offset; + buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0); + buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement; + pad = buf->buf[nbuf].size % BTS_RECORD_SIZE; + buf->buf[nbuf].size -= pad; + + pg += __nr_pages; + offset += __nr_pages << PAGE_SHIFT; + } + + return buf; +} + +static void bts_buffer_free_aux(void *data) +{ + kfree(data); +} + +static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx) +{ + return buf->buf[idx].offset + buf->buf[idx].displacement; +} + +static void +bts_config_buffer(struct bts_buffer *buf) +{ + int cpu = raw_smp_processor_id(); + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct bts_phys *phys = &buf->buf[buf->cur_buf]; + unsigned long index, thresh = 0, end = phys->size; + struct page *page = phys->page; + + index = local_read(&buf->head); + + if (!buf->snapshot) { + if (buf->end < phys->offset + buf_size(page)) + end = buf->end - phys->offset - phys->displacement; + + index -= phys->offset + phys->displacement; + + if (end - index > BTS_SAFETY_MARGIN) + thresh = end - BTS_SAFETY_MARGIN; + else if (end - index > BTS_RECORD_SIZE) + thresh = end - BTS_RECORD_SIZE; + else + thresh = end; + } + + ds->bts_buffer_base = (u64)(long)page_address(page) + phys->displacement; + ds->bts_index = ds->bts_buffer_base + index; + ds->bts_absolute_maximum = ds->bts_buffer_base + end; + ds->bts_interrupt_threshold = !buf->snapshot + ? ds->bts_buffer_base + thresh + : ds->bts_absolute_maximum + BTS_RECORD_SIZE; +} + +static void bts_buffer_pad_out(struct bts_phys *phys, unsigned long head) +{ + unsigned long index = head - phys->offset; + + memset(page_address(phys->page) + index, 0, phys->size - index); +} + +static bool bts_buffer_is_full(struct bts_buffer *buf, struct bts_ctx *bts) +{ + if (buf->snapshot) + return false; + + if (local_read(&buf->data_size) >= bts->handle.size || + bts->handle.size - local_read(&buf->data_size) < BTS_RECORD_SIZE) + return true; + + return false; +} + +static void bts_update(struct bts_ctx *bts) +{ + int cpu = raw_smp_processor_id(); + struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct bts_buffer *buf = perf_get_aux(&bts->handle); + unsigned long index = ds->bts_index - ds->bts_buffer_base, old, head; + + if (!buf) + return; + + head = index + bts_buffer_offset(buf, buf->cur_buf); + old = local_xchg(&buf->head, head); + + if (!buf->snapshot) { + if (old == head) + return; + + if (ds->bts_index >= ds->bts_absolute_maximum) + local_inc(&buf->lost); + + /* + * old and head are always in the same physical buffer, so we + * can subtract them to get the data size. + */ + local_add(head - old, &buf->data_size); + } else { + local_set(&buf->data_size, head); + } +} + +static void __bts_event_start(struct perf_event *event) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); + u64 config = 0; + + if (!buf || bts_buffer_is_full(buf, bts)) + return; + + event->hw.state = 0; + + if (!buf->snapshot) + config |= ARCH_PERFMON_EVENTSEL_INT; + if (!event->attr.exclude_kernel) + config |= ARCH_PERFMON_EVENTSEL_OS; + if (!event->attr.exclude_user) + config |= ARCH_PERFMON_EVENTSEL_USR; + + bts_config_buffer(buf); + + /* + * local barrier to make sure that ds configuration made it + * before we enable BTS + */ + wmb(); + + intel_pmu_enable_bts(config); +} + +static void bts_event_start(struct perf_event *event, int flags) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + __bts_event_start(event); + + /* PMI handler: this counter is running and likely generating PMIs */ + ACCESS_ONCE(bts->started) = 1; +} + +static void __bts_event_stop(struct perf_event *event) +{ + /* + * No extra synchronization is mandated by the documentation to have + * BTS data stores globally visible. + */ + intel_pmu_disable_bts(); + + if (event->hw.state & PERF_HES_STOPPED) + return; + + ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED; +} + +static void bts_event_stop(struct perf_event *event, int flags) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + /* PMI handler: don't restart this counter */ + ACCESS_ONCE(bts->started) = 0; + + __bts_event_stop(event); + + if (flags & PERF_EF_UPDATE) + bts_update(bts); +} + +void intel_bts_enable_local(void) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + if (bts->handle.event && bts->started) + __bts_event_start(bts->handle.event); +} + +void intel_bts_disable_local(void) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + + if (bts->handle.event) + __bts_event_stop(bts->handle.event); +} + +static int +bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle) +{ + unsigned long head, space, next_space, pad, gap, skip, wakeup; + unsigned int next_buf; + struct bts_phys *phys, *next_phys; + int ret; + + if (buf->snapshot) + return 0; + + head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1); + if (WARN_ON_ONCE(head != local_read(&buf->head))) + return -EINVAL; + + phys = &buf->buf[buf->cur_buf]; + space = phys->offset + phys->displacement + phys->size - head; + pad = space; + if (space > handle->size) { + space = handle->size; + space -= space % BTS_RECORD_SIZE; + } + if (space <= BTS_SAFETY_MARGIN) { + /* See if next phys buffer has more space */ + next_buf = buf->cur_buf + 1; + if (next_buf >= buf->nr_bufs) + next_buf = 0; + next_phys = &buf->buf[next_buf]; + gap = buf_size(phys->page) - phys->displacement - phys->size + + next_phys->displacement; + skip = pad + gap; + if (handle->size >= skip) { + next_space = next_phys->size; + if (next_space + skip > handle->size) { + next_space = handle->size - skip; + next_space -= next_space % BTS_RECORD_SIZE; + } + if (next_space > space || !space) { + if (pad) + bts_buffer_pad_out(phys, head); + ret = perf_aux_output_skip(handle, skip); + if (ret) + return ret; + /* Advance to next phys buffer */ + phys = next_phys; + space = next_space; + head = phys->offset + phys->displacement; + /* + * After this, cur_buf and head won't match ds + * anymore, so we must not be racing with + * bts_update(). + */ + buf->cur_buf = next_buf; + local_set(&buf->head, head); + } + } + } + + /* Don't go far beyond wakeup watermark */ + wakeup = BTS_SAFETY_MARGIN + BTS_RECORD_SIZE + handle->wakeup - + handle->head; + if (space > wakeup) { + space = wakeup; + space -= space % BTS_RECORD_SIZE; + } + + buf->end = head + space; + + /* + * If we have no space, the lost notification would have been sent when + * we hit absolute_maximum - see bts_update() + */ + if (!space) + return -ENOSPC; + + return 0; +} + +int intel_bts_interrupt(void) +{ + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct perf_event *event = bts->handle.event; + struct bts_buffer *buf; + s64 old_head; + int err; + + if (!event || !bts->started) + return 0; + + buf = perf_get_aux(&bts->handle); + /* + * Skip snapshot counters: they don't use the interrupt, but + * there's no other way of telling, because the pointer will + * keep moving + */ + if (!buf || buf->snapshot) + return 0; + + old_head = local_read(&buf->head); + bts_update(bts); + + /* no new data */ + if (old_head == local_read(&buf->head)) + return 0; + + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + return 1; + + err = bts_buffer_reset(buf, &bts->handle); + if (err) + perf_aux_output_end(&bts->handle, 0, false); + + return 1; +} + +static void bts_event_del(struct perf_event *event, int mode) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct bts_buffer *buf = perf_get_aux(&bts->handle); + + bts_event_stop(event, PERF_EF_UPDATE); + + if (buf) { + if (buf->snapshot) + bts->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0), + !!local_xchg(&buf->lost, 0)); + } + + cpuc->ds->bts_index = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_buffer_base = bts->ds_back.bts_buffer_base; + cpuc->ds->bts_absolute_maximum = bts->ds_back.bts_absolute_maximum; + cpuc->ds->bts_interrupt_threshold = bts->ds_back.bts_interrupt_threshold; +} + +static int bts_event_add(struct perf_event *event, int mode) +{ + struct bts_buffer *buf; + struct bts_ctx *bts = this_cpu_ptr(&bts_ctx); + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + int ret = -EBUSY; + + event->hw.state = PERF_HES_STOPPED; + + if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + return -EBUSY; + + if (bts->handle.event) + return -EBUSY; + + buf = perf_aux_output_begin(&bts->handle, event); + if (!buf) + return -EINVAL; + + ret = bts_buffer_reset(buf, &bts->handle); + if (ret) { + perf_aux_output_end(&bts->handle, 0, false); + return ret; + } + + bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base; + bts->ds_back.bts_absolute_maximum = cpuc->ds->bts_absolute_maximum; + bts->ds_back.bts_interrupt_threshold = cpuc->ds->bts_interrupt_threshold; + + if (mode & PERF_EF_START) { + bts_event_start(event, 0); + if (hwc->state & PERF_HES_STOPPED) { + bts_event_del(event, 0); + return -EBUSY; + } + } + + return 0; +} + +static void bts_event_destroy(struct perf_event *event) +{ + x86_del_exclusive(x86_lbr_exclusive_bts); +} + +static int bts_event_init(struct perf_event *event) +{ + if (event->attr.type != bts_pmu.type) + return -ENOENT; + + if (x86_add_exclusive(x86_lbr_exclusive_bts)) + return -EBUSY; + + event->destroy = bts_event_destroy; + + return 0; +} + +static void bts_event_read(struct perf_event *event) +{ +} + +static __init int bts_init(void) +{ + if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts) + return -ENODEV; + + bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE; + bts_pmu.task_ctx_nr = perf_sw_context; + bts_pmu.event_init = bts_event_init; + bts_pmu.add = bts_event_add; + bts_pmu.del = bts_event_del; + bts_pmu.start = bts_event_start; + bts_pmu.stop = bts_event_stop; + bts_pmu.read = bts_event_read; + bts_pmu.setup_aux = bts_buffer_setup_aux; + bts_pmu.free_aux = bts_buffer_free_aux; + + return perf_pmu_register(&bts_pmu, "intel_bts", -1); +} + +module_init(bts_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c new file mode 100644 index 000000000000..e4d1b8b738fa --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -0,0 +1,1379 @@ +/* + * Intel Cache Quality-of-Service Monitoring (CQM) support. + * + * Based very, very heavily on work by Peter Zijlstra. + */ + +#include <linux/perf_event.h> +#include <linux/slab.h> +#include <asm/cpu_device_id.h> +#include "perf_event.h" + +#define MSR_IA32_PQR_ASSOC 0x0c8f +#define MSR_IA32_QM_CTR 0x0c8e +#define MSR_IA32_QM_EVTSEL 0x0c8d + +static unsigned int cqm_max_rmid = -1; +static unsigned int cqm_l3_scale; /* supposedly cacheline size */ + +struct intel_cqm_state { + raw_spinlock_t lock; + int rmid; + int cnt; +}; + +static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); + +/* + * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. + * Also protects event->hw.cqm_rmid + * + * Hold either for stability, both for modification of ->hw.cqm_rmid. + */ +static DEFINE_MUTEX(cache_mutex); +static DEFINE_RAW_SPINLOCK(cache_lock); + +/* + * Groups of events that have the same target(s), one RMID per group. + */ +static LIST_HEAD(cache_groups); + +/* + * Mask of CPUs for reading CQM values. We only need one per-socket. + */ +static cpumask_t cqm_cpumask; + +#define RMID_VAL_ERROR (1ULL << 63) +#define RMID_VAL_UNAVAIL (1ULL << 62) + +#define QOS_L3_OCCUP_EVENT_ID (1 << 0) + +#define QOS_EVENT_MASK QOS_L3_OCCUP_EVENT_ID + +/* + * This is central to the rotation algorithm in __intel_cqm_rmid_rotate(). + * + * This rmid is always free and is guaranteed to have an associated + * near-zero occupancy value, i.e. no cachelines are tagged with this + * RMID, once __intel_cqm_rmid_rotate() returns. + */ +static unsigned int intel_cqm_rotation_rmid; + +#define INVALID_RMID (-1) + +/* + * Is @rmid valid for programming the hardware? + * + * rmid 0 is reserved by the hardware for all non-monitored tasks, which + * means that we should never come across an rmid with that value. + * Likewise, an rmid value of -1 is used to indicate "no rmid currently + * assigned" and is used as part of the rotation code. + */ +static inline bool __rmid_valid(unsigned int rmid) +{ + if (!rmid || rmid == INVALID_RMID) + return false; + + return true; +} + +static u64 __rmid_read(unsigned int rmid) +{ + u64 val; + + /* + * Ignore the SDM, this thing is _NOTHING_ like a regular perfcnt, + * it just says that to increase confusion. + */ + wrmsr(MSR_IA32_QM_EVTSEL, QOS_L3_OCCUP_EVENT_ID, rmid); + rdmsrl(MSR_IA32_QM_CTR, val); + + /* + * Aside from the ERROR and UNAVAIL bits, assume this thing returns + * the number of cachelines tagged with @rmid. + */ + return val; +} + +enum rmid_recycle_state { + RMID_YOUNG = 0, + RMID_AVAILABLE, + RMID_DIRTY, +}; + +struct cqm_rmid_entry { + unsigned int rmid; + enum rmid_recycle_state state; + struct list_head list; + unsigned long queue_time; +}; + +/* + * cqm_rmid_free_lru - A least recently used list of RMIDs. + * + * Oldest entry at the head, newest (most recently used) entry at the + * tail. This list is never traversed, it's only used to keep track of + * the lru order. That is, we only pick entries of the head or insert + * them on the tail. + * + * All entries on the list are 'free', and their RMIDs are not currently + * in use. To mark an RMID as in use, remove its entry from the lru + * list. + * + * + * cqm_rmid_limbo_lru - list of currently unused but (potentially) dirty RMIDs. + * + * This list is contains RMIDs that no one is currently using but that + * may have a non-zero occupancy value associated with them. The + * rotation worker moves RMIDs from the limbo list to the free list once + * the occupancy value drops below __intel_cqm_threshold. + * + * Both lists are protected by cache_mutex. + */ +static LIST_HEAD(cqm_rmid_free_lru); +static LIST_HEAD(cqm_rmid_limbo_lru); + +/* + * We use a simple array of pointers so that we can lookup a struct + * cqm_rmid_entry in O(1). This alleviates the callers of __get_rmid() + * and __put_rmid() from having to worry about dealing with struct + * cqm_rmid_entry - they just deal with rmids, i.e. integers. + * + * Once this array is initialized it is read-only. No locks are required + * to access it. + * + * All entries for all RMIDs can be looked up in the this array at all + * times. + */ +static struct cqm_rmid_entry **cqm_rmid_ptrs; + +static inline struct cqm_rmid_entry *__rmid_entry(int rmid) +{ + struct cqm_rmid_entry *entry; + + entry = cqm_rmid_ptrs[rmid]; + WARN_ON(entry->rmid != rmid); + + return entry; +} + +/* + * Returns < 0 on fail. + * + * We expect to be called with cache_mutex held. + */ +static int __get_rmid(void) +{ + struct cqm_rmid_entry *entry; + + lockdep_assert_held(&cache_mutex); + + if (list_empty(&cqm_rmid_free_lru)) + return INVALID_RMID; + + entry = list_first_entry(&cqm_rmid_free_lru, struct cqm_rmid_entry, list); + list_del(&entry->list); + + return entry->rmid; +} + +static void __put_rmid(unsigned int rmid) +{ + struct cqm_rmid_entry *entry; + + lockdep_assert_held(&cache_mutex); + + WARN_ON(!__rmid_valid(rmid)); + entry = __rmid_entry(rmid); + + entry->queue_time = jiffies; + entry->state = RMID_YOUNG; + + list_add_tail(&entry->list, &cqm_rmid_limbo_lru); +} + +static int intel_cqm_setup_rmid_cache(void) +{ + struct cqm_rmid_entry *entry; + unsigned int nr_rmids; + int r = 0; + + nr_rmids = cqm_max_rmid + 1; + cqm_rmid_ptrs = kmalloc(sizeof(struct cqm_rmid_entry *) * + nr_rmids, GFP_KERNEL); + if (!cqm_rmid_ptrs) + return -ENOMEM; + + for (; r <= cqm_max_rmid; r++) { + struct cqm_rmid_entry *entry; + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto fail; + + INIT_LIST_HEAD(&entry->list); + entry->rmid = r; + cqm_rmid_ptrs[r] = entry; + + list_add_tail(&entry->list, &cqm_rmid_free_lru); + } + + /* + * RMID 0 is special and is always allocated. It's used for all + * tasks that are not monitored. + */ + entry = __rmid_entry(0); + list_del(&entry->list); + + mutex_lock(&cache_mutex); + intel_cqm_rotation_rmid = __get_rmid(); + mutex_unlock(&cache_mutex); + + return 0; +fail: + while (r--) + kfree(cqm_rmid_ptrs[r]); + + kfree(cqm_rmid_ptrs); + return -ENOMEM; +} + +/* + * Determine if @a and @b measure the same set of tasks. + * + * If @a and @b measure the same set of tasks then we want to share a + * single RMID. + */ +static bool __match_event(struct perf_event *a, struct perf_event *b) +{ + /* Per-cpu and task events don't mix */ + if ((a->attach_state & PERF_ATTACH_TASK) != + (b->attach_state & PERF_ATTACH_TASK)) + return false; + +#ifdef CONFIG_CGROUP_PERF + if (a->cgrp != b->cgrp) + return false; +#endif + + /* If not task event, we're machine wide */ + if (!(b->attach_state & PERF_ATTACH_TASK)) + return true; + + /* + * Events that target same task are placed into the same cache group. + */ + if (a->hw.target == b->hw.target) + return true; + + /* + * Are we an inherited event? + */ + if (b->parent == a) + return true; + + return false; +} + +#ifdef CONFIG_CGROUP_PERF +static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) +{ + if (event->attach_state & PERF_ATTACH_TASK) + return perf_cgroup_from_task(event->hw.target); + + return event->cgrp; +} +#endif + +/* + * Determine if @a's tasks intersect with @b's tasks + * + * There are combinations of events that we explicitly prohibit, + * + * PROHIBITS + * system-wide -> cgroup and task + * cgroup -> system-wide + * -> task in cgroup + * task -> system-wide + * -> task in cgroup + * + * Call this function before allocating an RMID. + */ +static bool __conflict_event(struct perf_event *a, struct perf_event *b) +{ +#ifdef CONFIG_CGROUP_PERF + /* + * We can have any number of cgroups but only one system-wide + * event at a time. + */ + if (a->cgrp && b->cgrp) { + struct perf_cgroup *ac = a->cgrp; + struct perf_cgroup *bc = b->cgrp; + + /* + * This condition should have been caught in + * __match_event() and we should be sharing an RMID. + */ + WARN_ON_ONCE(ac == bc); + + if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || + cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) + return true; + + return false; + } + + if (a->cgrp || b->cgrp) { + struct perf_cgroup *ac, *bc; + + /* + * cgroup and system-wide events are mutually exclusive + */ + if ((a->cgrp && !(b->attach_state & PERF_ATTACH_TASK)) || + (b->cgrp && !(a->attach_state & PERF_ATTACH_TASK))) + return true; + + /* + * Ensure neither event is part of the other's cgroup + */ + ac = event_to_cgroup(a); + bc = event_to_cgroup(b); + if (ac == bc) + return true; + + /* + * Must have cgroup and non-intersecting task events. + */ + if (!ac || !bc) + return false; + + /* + * We have cgroup and task events, and the task belongs + * to a cgroup. Check for for overlap. + */ + if (cgroup_is_descendant(ac->css.cgroup, bc->css.cgroup) || + cgroup_is_descendant(bc->css.cgroup, ac->css.cgroup)) + return true; + + return false; + } +#endif + /* + * If one of them is not a task, same story as above with cgroups. + */ + if (!(a->attach_state & PERF_ATTACH_TASK) || + !(b->attach_state & PERF_ATTACH_TASK)) + return true; + + /* + * Must be non-overlapping. + */ + return false; +} + +struct rmid_read { + unsigned int rmid; + atomic64_t value; +}; + +static void __intel_cqm_event_count(void *info); + +/* + * Exchange the RMID of a group of events. + */ +static unsigned int +intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid) +{ + struct perf_event *event; + unsigned int old_rmid = group->hw.cqm_rmid; + struct list_head *head = &group->hw.cqm_group_entry; + + lockdep_assert_held(&cache_mutex); + + /* + * If our RMID is being deallocated, perform a read now. + */ + if (__rmid_valid(old_rmid) && !__rmid_valid(rmid)) { + struct rmid_read rr = { + .value = ATOMIC64_INIT(0), + .rmid = old_rmid, + }; + + on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, + &rr, 1); + local64_set(&group->count, atomic64_read(&rr.value)); + } + + raw_spin_lock_irq(&cache_lock); + + group->hw.cqm_rmid = rmid; + list_for_each_entry(event, head, hw.cqm_group_entry) + event->hw.cqm_rmid = rmid; + + raw_spin_unlock_irq(&cache_lock); + + return old_rmid; +} + +/* + * If we fail to assign a new RMID for intel_cqm_rotation_rmid because + * cachelines are still tagged with RMIDs in limbo, we progressively + * increment the threshold until we find an RMID in limbo with <= + * __intel_cqm_threshold lines tagged. This is designed to mitigate the + * problem where cachelines tagged with an RMID are not steadily being + * evicted. + * + * On successful rotations we decrease the threshold back towards zero. + * + * __intel_cqm_max_threshold provides an upper bound on the threshold, + * and is measured in bytes because it's exposed to userland. + */ +static unsigned int __intel_cqm_threshold; +static unsigned int __intel_cqm_max_threshold; + +/* + * Test whether an RMID has a zero occupancy value on this cpu. + */ +static void intel_cqm_stable(void *arg) +{ + struct cqm_rmid_entry *entry; + + list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { + if (entry->state != RMID_AVAILABLE) + break; + + if (__rmid_read(entry->rmid) > __intel_cqm_threshold) + entry->state = RMID_DIRTY; + } +} + +/* + * If we have group events waiting for an RMID that don't conflict with + * events already running, assign @rmid. + */ +static bool intel_cqm_sched_in_event(unsigned int rmid) +{ + struct perf_event *leader, *event; + + lockdep_assert_held(&cache_mutex); + + leader = list_first_entry(&cache_groups, struct perf_event, + hw.cqm_groups_entry); + event = leader; + + list_for_each_entry_continue(event, &cache_groups, + hw.cqm_groups_entry) { + if (__rmid_valid(event->hw.cqm_rmid)) + continue; + + if (__conflict_event(event, leader)) + continue; + + intel_cqm_xchg_rmid(event, rmid); + return true; + } + + return false; +} + +/* + * Initially use this constant for both the limbo queue time and the + * rotation timer interval, pmu::hrtimer_interval_ms. + * + * They don't need to be the same, but the two are related since if you + * rotate faster than you recycle RMIDs, you may run out of available + * RMIDs. + */ +#define RMID_DEFAULT_QUEUE_TIME 250 /* ms */ + +static unsigned int __rmid_queue_time_ms = RMID_DEFAULT_QUEUE_TIME; + +/* + * intel_cqm_rmid_stabilize - move RMIDs from limbo to free list + * @nr_available: number of freeable RMIDs on the limbo list + * + * Quiescent state; wait for all 'freed' RMIDs to become unused, i.e. no + * cachelines are tagged with those RMIDs. After this we can reuse them + * and know that the current set of active RMIDs is stable. + * + * Return %true or %false depending on whether stabilization needs to be + * reattempted. + * + * If we return %true then @nr_available is updated to indicate the + * number of RMIDs on the limbo list that have been queued for the + * minimum queue time (RMID_AVAILABLE), but whose data occupancy values + * are above __intel_cqm_threshold. + */ +static bool intel_cqm_rmid_stabilize(unsigned int *available) +{ + struct cqm_rmid_entry *entry, *tmp; + + lockdep_assert_held(&cache_mutex); + + *available = 0; + list_for_each_entry(entry, &cqm_rmid_limbo_lru, list) { + unsigned long min_queue_time; + unsigned long now = jiffies; + + /* + * We hold RMIDs placed into limbo for a minimum queue + * time. Before the minimum queue time has elapsed we do + * not recycle RMIDs. + * + * The reasoning is that until a sufficient time has + * passed since we stopped using an RMID, any RMID + * placed onto the limbo list will likely still have + * data tagged in the cache, which means we'll probably + * fail to recycle it anyway. + * + * We can save ourselves an expensive IPI by skipping + * any RMIDs that have not been queued for the minimum + * time. + */ + min_queue_time = entry->queue_time + + msecs_to_jiffies(__rmid_queue_time_ms); + + if (time_after(min_queue_time, now)) + break; + + entry->state = RMID_AVAILABLE; + (*available)++; + } + + /* + * Fast return if none of the RMIDs on the limbo list have been + * sitting on the queue for the minimum queue time. + */ + if (!*available) + return false; + + /* + * Test whether an RMID is free for each package. + */ + on_each_cpu_mask(&cqm_cpumask, intel_cqm_stable, NULL, true); + + list_for_each_entry_safe(entry, tmp, &cqm_rmid_limbo_lru, list) { + /* + * Exhausted all RMIDs that have waited min queue time. + */ + if (entry->state == RMID_YOUNG) + break; + + if (entry->state == RMID_DIRTY) + continue; + + list_del(&entry->list); /* remove from limbo */ + + /* + * The rotation RMID gets priority if it's + * currently invalid. In which case, skip adding + * the RMID to the the free lru. + */ + if (!__rmid_valid(intel_cqm_rotation_rmid)) { + intel_cqm_rotation_rmid = entry->rmid; + continue; + } + + /* + * If we have groups waiting for RMIDs, hand + * them one now provided they don't conflict. + */ + if (intel_cqm_sched_in_event(entry->rmid)) + continue; + + /* + * Otherwise place it onto the free list. + */ + list_add_tail(&entry->list, &cqm_rmid_free_lru); + } + + + return __rmid_valid(intel_cqm_rotation_rmid); +} + +/* + * Pick a victim group and move it to the tail of the group list. + * @next: The first group without an RMID + */ +static void __intel_cqm_pick_and_rotate(struct perf_event *next) +{ + struct perf_event *rotor; + unsigned int rmid; + + lockdep_assert_held(&cache_mutex); + + rotor = list_first_entry(&cache_groups, struct perf_event, + hw.cqm_groups_entry); + + /* + * The group at the front of the list should always have a valid + * RMID. If it doesn't then no groups have RMIDs assigned and we + * don't need to rotate the list. + */ + if (next == rotor) + return; + + rmid = intel_cqm_xchg_rmid(rotor, INVALID_RMID); + __put_rmid(rmid); + + list_rotate_left(&cache_groups); +} + +/* + * Deallocate the RMIDs from any events that conflict with @event, and + * place them on the back of the group list. + */ +static void intel_cqm_sched_out_conflicting_events(struct perf_event *event) +{ + struct perf_event *group, *g; + unsigned int rmid; + + lockdep_assert_held(&cache_mutex); + + list_for_each_entry_safe(group, g, &cache_groups, hw.cqm_groups_entry) { + if (group == event) + continue; + + rmid = group->hw.cqm_rmid; + + /* + * Skip events that don't have a valid RMID. + */ + if (!__rmid_valid(rmid)) + continue; + + /* + * No conflict? No problem! Leave the event alone. + */ + if (!__conflict_event(group, event)) + continue; + + intel_cqm_xchg_rmid(group, INVALID_RMID); + __put_rmid(rmid); + } +} + +/* + * Attempt to rotate the groups and assign new RMIDs. + * + * We rotate for two reasons, + * 1. To handle the scheduling of conflicting events + * 2. To recycle RMIDs + * + * Rotating RMIDs is complicated because the hardware doesn't give us + * any clues. + * + * There's problems with the hardware interface; when you change the + * task:RMID map cachelines retain their 'old' tags, giving a skewed + * picture. In order to work around this, we must always keep one free + * RMID - intel_cqm_rotation_rmid. + * + * Rotation works by taking away an RMID from a group (the old RMID), + * and assigning the free RMID to another group (the new RMID). We must + * then wait for the old RMID to not be used (no cachelines tagged). + * This ensure that all cachelines are tagged with 'active' RMIDs. At + * this point we can start reading values for the new RMID and treat the + * old RMID as the free RMID for the next rotation. + * + * Return %true or %false depending on whether we did any rotating. + */ +static bool __intel_cqm_rmid_rotate(void) +{ + struct perf_event *group, *start = NULL; + unsigned int threshold_limit; + unsigned int nr_needed = 0; + unsigned int nr_available; + bool rotated = false; + + mutex_lock(&cache_mutex); + +again: + /* + * Fast path through this function if there are no groups and no + * RMIDs that need cleaning. + */ + if (list_empty(&cache_groups) && list_empty(&cqm_rmid_limbo_lru)) + goto out; + + list_for_each_entry(group, &cache_groups, hw.cqm_groups_entry) { + if (!__rmid_valid(group->hw.cqm_rmid)) { + if (!start) + start = group; + nr_needed++; + } + } + + /* + * We have some event groups, but they all have RMIDs assigned + * and no RMIDs need cleaning. + */ + if (!nr_needed && list_empty(&cqm_rmid_limbo_lru)) + goto out; + + if (!nr_needed) + goto stabilize; + + /* + * We have more event groups without RMIDs than available RMIDs, + * or we have event groups that conflict with the ones currently + * scheduled. + * + * We force deallocate the rmid of the group at the head of + * cache_groups. The first event group without an RMID then gets + * assigned intel_cqm_rotation_rmid. This ensures we always make + * forward progress. + * + * Rotate the cache_groups list so the previous head is now the + * tail. + */ + __intel_cqm_pick_and_rotate(start); + + /* + * If the rotation is going to succeed, reduce the threshold so + * that we don't needlessly reuse dirty RMIDs. + */ + if (__rmid_valid(intel_cqm_rotation_rmid)) { + intel_cqm_xchg_rmid(start, intel_cqm_rotation_rmid); + intel_cqm_rotation_rmid = __get_rmid(); + + intel_cqm_sched_out_conflicting_events(start); + + if (__intel_cqm_threshold) + __intel_cqm_threshold--; + } + + rotated = true; + +stabilize: + /* + * We now need to stablize the RMID we freed above (if any) to + * ensure that the next time we rotate we have an RMID with zero + * occupancy value. + * + * Alternatively, if we didn't need to perform any rotation, + * we'll have a bunch of RMIDs in limbo that need stabilizing. + */ + threshold_limit = __intel_cqm_max_threshold / cqm_l3_scale; + + while (intel_cqm_rmid_stabilize(&nr_available) && + __intel_cqm_threshold < threshold_limit) { + unsigned int steal_limit; + + /* + * Don't spin if nobody is actively waiting for an RMID, + * the rotation worker will be kicked as soon as an + * event needs an RMID anyway. + */ + if (!nr_needed) + break; + + /* Allow max 25% of RMIDs to be in limbo. */ + steal_limit = (cqm_max_rmid + 1) / 4; + + /* + * We failed to stabilize any RMIDs so our rotation + * logic is now stuck. In order to make forward progress + * we have a few options: + * + * 1. rotate ("steal") another RMID + * 2. increase the threshold + * 3. do nothing + * + * We do both of 1. and 2. until we hit the steal limit. + * + * The steal limit prevents all RMIDs ending up on the + * limbo list. This can happen if every RMID has a + * non-zero occupancy above threshold_limit, and the + * occupancy values aren't dropping fast enough. + * + * Note that there is prioritisation at work here - we'd + * rather increase the number of RMIDs on the limbo list + * than increase the threshold, because increasing the + * threshold skews the event data (because we reuse + * dirty RMIDs) - threshold bumps are a last resort. + */ + if (nr_available < steal_limit) + goto again; + + __intel_cqm_threshold++; + } + +out: + mutex_unlock(&cache_mutex); + return rotated; +} + +static void intel_cqm_rmid_rotate(struct work_struct *work); + +static DECLARE_DELAYED_WORK(intel_cqm_rmid_work, intel_cqm_rmid_rotate); + +static struct pmu intel_cqm_pmu; + +static void intel_cqm_rmid_rotate(struct work_struct *work) +{ + unsigned long delay; + + __intel_cqm_rmid_rotate(); + + delay = msecs_to_jiffies(intel_cqm_pmu.hrtimer_interval_ms); + schedule_delayed_work(&intel_cqm_rmid_work, delay); +} + +/* + * Find a group and setup RMID. + * + * If we're part of a group, we use the group's RMID. + */ +static void intel_cqm_setup_event(struct perf_event *event, + struct perf_event **group) +{ + struct perf_event *iter; + unsigned int rmid; + bool conflict = false; + + list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) { + rmid = iter->hw.cqm_rmid; + + if (__match_event(iter, event)) { + /* All tasks in a group share an RMID */ + event->hw.cqm_rmid = rmid; + *group = iter; + return; + } + + /* + * We only care about conflicts for events that are + * actually scheduled in (and hence have a valid RMID). + */ + if (__conflict_event(iter, event) && __rmid_valid(rmid)) + conflict = true; + } + + if (conflict) + rmid = INVALID_RMID; + else + rmid = __get_rmid(); + + event->hw.cqm_rmid = rmid; +} + +static void intel_cqm_event_read(struct perf_event *event) +{ + unsigned long flags; + unsigned int rmid; + u64 val; + + /* + * Task events are handled by intel_cqm_event_count(). + */ + if (event->cpu == -1) + return; + + raw_spin_lock_irqsave(&cache_lock, flags); + rmid = event->hw.cqm_rmid; + + if (!__rmid_valid(rmid)) + goto out; + + val = __rmid_read(rmid); + + /* + * Ignore this reading on error states and do not update the value. + */ + if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + goto out; + + local64_set(&event->count, val); +out: + raw_spin_unlock_irqrestore(&cache_lock, flags); +} + +static void __intel_cqm_event_count(void *info) +{ + struct rmid_read *rr = info; + u64 val; + + val = __rmid_read(rr->rmid); + + if (val & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) + return; + + atomic64_add(val, &rr->value); +} + +static inline bool cqm_group_leader(struct perf_event *event) +{ + return !list_empty(&event->hw.cqm_groups_entry); +} + +static u64 intel_cqm_event_count(struct perf_event *event) +{ + unsigned long flags; + struct rmid_read rr = { + .value = ATOMIC64_INIT(0), + }; + + /* + * We only need to worry about task events. System-wide events + * are handled like usual, i.e. entirely with + * intel_cqm_event_read(). + */ + if (event->cpu != -1) + return __perf_event_count(event); + + /* + * Only the group leader gets to report values. This stops us + * reporting duplicate values to userspace, and gives us a clear + * rule for which task gets to report the values. + * + * Note that it is impossible to attribute these values to + * specific packages - we forfeit that ability when we create + * task events. + */ + if (!cqm_group_leader(event)) + return 0; + + /* + * Notice that we don't perform the reading of an RMID + * atomically, because we can't hold a spin lock across the + * IPIs. + * + * Speculatively perform the read, since @event might be + * assigned a different (possibly invalid) RMID while we're + * busying performing the IPI calls. It's therefore necessary to + * check @event's RMID afterwards, and if it has changed, + * discard the result of the read. + */ + rr.rmid = ACCESS_ONCE(event->hw.cqm_rmid); + + if (!__rmid_valid(rr.rmid)) + goto out; + + on_each_cpu_mask(&cqm_cpumask, __intel_cqm_event_count, &rr, 1); + + raw_spin_lock_irqsave(&cache_lock, flags); + if (event->hw.cqm_rmid == rr.rmid) + local64_set(&event->count, atomic64_read(&rr.value)); + raw_spin_unlock_irqrestore(&cache_lock, flags); +out: + return __perf_event_count(event); +} + +static void intel_cqm_event_start(struct perf_event *event, int mode) +{ + struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); + unsigned int rmid = event->hw.cqm_rmid; + unsigned long flags; + + if (!(event->hw.cqm_state & PERF_HES_STOPPED)) + return; + + event->hw.cqm_state &= ~PERF_HES_STOPPED; + + raw_spin_lock_irqsave(&state->lock, flags); + + if (state->cnt++) + WARN_ON_ONCE(state->rmid != rmid); + else + WARN_ON_ONCE(state->rmid); + + state->rmid = rmid; + wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid); + + raw_spin_unlock_irqrestore(&state->lock, flags); +} + +static void intel_cqm_event_stop(struct perf_event *event, int mode) +{ + struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); + unsigned long flags; + + if (event->hw.cqm_state & PERF_HES_STOPPED) + return; + + event->hw.cqm_state |= PERF_HES_STOPPED; + + raw_spin_lock_irqsave(&state->lock, flags); + intel_cqm_event_read(event); + + if (!--state->cnt) { + state->rmid = 0; + wrmsrl(MSR_IA32_PQR_ASSOC, 0); + } else { + WARN_ON_ONCE(!state->rmid); + } + + raw_spin_unlock_irqrestore(&state->lock, flags); +} + +static int intel_cqm_event_add(struct perf_event *event, int mode) +{ + unsigned long flags; + unsigned int rmid; + + raw_spin_lock_irqsave(&cache_lock, flags); + + event->hw.cqm_state = PERF_HES_STOPPED; + rmid = event->hw.cqm_rmid; + + if (__rmid_valid(rmid) && (mode & PERF_EF_START)) + intel_cqm_event_start(event, mode); + + raw_spin_unlock_irqrestore(&cache_lock, flags); + + return 0; +} + +static void intel_cqm_event_del(struct perf_event *event, int mode) +{ + intel_cqm_event_stop(event, mode); +} + +static void intel_cqm_event_destroy(struct perf_event *event) +{ + struct perf_event *group_other = NULL; + + mutex_lock(&cache_mutex); + + /* + * If there's another event in this group... + */ + if (!list_empty(&event->hw.cqm_group_entry)) { + group_other = list_first_entry(&event->hw.cqm_group_entry, + struct perf_event, + hw.cqm_group_entry); + list_del(&event->hw.cqm_group_entry); + } + + /* + * And we're the group leader.. + */ + if (cqm_group_leader(event)) { + /* + * If there was a group_other, make that leader, otherwise + * destroy the group and return the RMID. + */ + if (group_other) { + list_replace(&event->hw.cqm_groups_entry, + &group_other->hw.cqm_groups_entry); + } else { + unsigned int rmid = event->hw.cqm_rmid; + + if (__rmid_valid(rmid)) + __put_rmid(rmid); + list_del(&event->hw.cqm_groups_entry); + } + } + + mutex_unlock(&cache_mutex); +} + +static int intel_cqm_event_init(struct perf_event *event) +{ + struct perf_event *group = NULL; + bool rotate = false; + + if (event->attr.type != intel_cqm_pmu.type) + return -ENOENT; + + if (event->attr.config & ~QOS_EVENT_MASK) + return -EINVAL; + + /* unsupported modes and filters */ + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest || + event->attr.sample_period) /* no sampling */ + return -EINVAL; + + INIT_LIST_HEAD(&event->hw.cqm_group_entry); + INIT_LIST_HEAD(&event->hw.cqm_groups_entry); + + event->destroy = intel_cqm_event_destroy; + + mutex_lock(&cache_mutex); + + /* Will also set rmid */ + intel_cqm_setup_event(event, &group); + + if (group) { + list_add_tail(&event->hw.cqm_group_entry, + &group->hw.cqm_group_entry); + } else { + list_add_tail(&event->hw.cqm_groups_entry, + &cache_groups); + + /* + * All RMIDs are either in use or have recently been + * used. Kick the rotation worker to clean/free some. + * + * We only do this for the group leader, rather than for + * every event in a group to save on needless work. + */ + if (!__rmid_valid(event->hw.cqm_rmid)) + rotate = true; + } + + mutex_unlock(&cache_mutex); + + if (rotate) + schedule_delayed_work(&intel_cqm_rmid_work, 0); + + return 0; +} + +EVENT_ATTR_STR(llc_occupancy, intel_cqm_llc, "event=0x01"); +EVENT_ATTR_STR(llc_occupancy.per-pkg, intel_cqm_llc_pkg, "1"); +EVENT_ATTR_STR(llc_occupancy.unit, intel_cqm_llc_unit, "Bytes"); +EVENT_ATTR_STR(llc_occupancy.scale, intel_cqm_llc_scale, NULL); +EVENT_ATTR_STR(llc_occupancy.snapshot, intel_cqm_llc_snapshot, "1"); + +static struct attribute *intel_cqm_events_attr[] = { + EVENT_PTR(intel_cqm_llc), + EVENT_PTR(intel_cqm_llc_pkg), + EVENT_PTR(intel_cqm_llc_unit), + EVENT_PTR(intel_cqm_llc_scale), + EVENT_PTR(intel_cqm_llc_snapshot), + NULL, +}; + +static struct attribute_group intel_cqm_events_group = { + .name = "events", + .attrs = intel_cqm_events_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-7"); +static struct attribute *intel_cqm_formats_attr[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group intel_cqm_format_group = { + .name = "format", + .attrs = intel_cqm_formats_attr, +}; + +static ssize_t +max_recycle_threshold_show(struct device *dev, struct device_attribute *attr, + char *page) +{ + ssize_t rv; + + mutex_lock(&cache_mutex); + rv = snprintf(page, PAGE_SIZE-1, "%u\n", __intel_cqm_max_threshold); + mutex_unlock(&cache_mutex); + + return rv; +} + +static ssize_t +max_recycle_threshold_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned int bytes, cachelines; + int ret; + + ret = kstrtouint(buf, 0, &bytes); + if (ret) + return ret; + + mutex_lock(&cache_mutex); + + __intel_cqm_max_threshold = bytes; + cachelines = bytes / cqm_l3_scale; + + /* + * The new maximum takes effect immediately. + */ + if (__intel_cqm_threshold > cachelines) + __intel_cqm_threshold = cachelines; + + mutex_unlock(&cache_mutex); + + return count; +} + +static DEVICE_ATTR_RW(max_recycle_threshold); + +static struct attribute *intel_cqm_attrs[] = { + &dev_attr_max_recycle_threshold.attr, + NULL, +}; + +static const struct attribute_group intel_cqm_group = { + .attrs = intel_cqm_attrs, +}; + +static const struct attribute_group *intel_cqm_attr_groups[] = { + &intel_cqm_events_group, + &intel_cqm_format_group, + &intel_cqm_group, + NULL, +}; + +static struct pmu intel_cqm_pmu = { + .hrtimer_interval_ms = RMID_DEFAULT_QUEUE_TIME, + .attr_groups = intel_cqm_attr_groups, + .task_ctx_nr = perf_sw_context, + .event_init = intel_cqm_event_init, + .add = intel_cqm_event_add, + .del = intel_cqm_event_del, + .start = intel_cqm_event_start, + .stop = intel_cqm_event_stop, + .read = intel_cqm_event_read, + .count = intel_cqm_event_count, +}; + +static inline void cqm_pick_event_reader(int cpu) +{ + int phys_id = topology_physical_package_id(cpu); + int i; + + for_each_cpu(i, &cqm_cpumask) { + if (phys_id == topology_physical_package_id(i)) + return; /* already got reader for this socket */ + } + + cpumask_set_cpu(cpu, &cqm_cpumask); +} + +static void intel_cqm_cpu_prepare(unsigned int cpu) +{ + struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + raw_spin_lock_init(&state->lock); + state->rmid = 0; + state->cnt = 0; + + WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); + WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); +} + +static void intel_cqm_cpu_exit(unsigned int cpu) +{ + int phys_id = topology_physical_package_id(cpu); + int i; + + /* + * Is @cpu a designated cqm reader? + */ + if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask)) + return; + + for_each_online_cpu(i) { + if (i == cpu) + continue; + + if (phys_id == topology_physical_package_id(i)) { + cpumask_set_cpu(i, &cqm_cpumask); + break; + } + } +} + +static int intel_cqm_cpu_notifier(struct notifier_block *nb, + unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + intel_cqm_cpu_prepare(cpu); + break; + case CPU_DOWN_PREPARE: + intel_cqm_cpu_exit(cpu); + break; + case CPU_STARTING: + cqm_pick_event_reader(cpu); + break; + } + + return NOTIFY_OK; +} + +static const struct x86_cpu_id intel_cqm_match[] = { + { .vendor = X86_VENDOR_INTEL, .feature = X86_FEATURE_CQM_OCCUP_LLC }, + {} +}; + +static int __init intel_cqm_init(void) +{ + char *str, scale[20]; + int i, cpu, ret; + + if (!x86_match_cpu(intel_cqm_match)) + return -ENODEV; + + cqm_l3_scale = boot_cpu_data.x86_cache_occ_scale; + + /* + * It's possible that not all resources support the same number + * of RMIDs. Instead of making scheduling much more complicated + * (where we have to match a task's RMID to a cpu that supports + * that many RMIDs) just find the minimum RMIDs supported across + * all cpus. + * + * Also, check that the scales match on all cpus. + */ + cpu_notifier_register_begin(); + + for_each_online_cpu(cpu) { + struct cpuinfo_x86 *c = &cpu_data(cpu); + + if (c->x86_cache_max_rmid < cqm_max_rmid) + cqm_max_rmid = c->x86_cache_max_rmid; + + if (c->x86_cache_occ_scale != cqm_l3_scale) { + pr_err("Multiple LLC scale values, disabling\n"); + ret = -EINVAL; + goto out; + } + } + + /* + * A reasonable upper limit on the max threshold is the number + * of lines tagged per RMID if all RMIDs have the same number of + * lines tagged in the LLC. + * + * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. + */ + __intel_cqm_max_threshold = + boot_cpu_data.x86_cache_size * 1024 / (cqm_max_rmid + 1); + + snprintf(scale, sizeof(scale), "%u", cqm_l3_scale); + str = kstrdup(scale, GFP_KERNEL); + if (!str) { + ret = -ENOMEM; + goto out; + } + + event_attr_intel_cqm_llc_scale.event_str = str; + + ret = intel_cqm_setup_rmid_cache(); + if (ret) + goto out; + + for_each_online_cpu(i) { + intel_cqm_cpu_prepare(i); + cqm_pick_event_reader(i); + } + + __perf_cpu_notifier(intel_cqm_cpu_notifier); + + ret = perf_pmu_register(&intel_cqm_pmu, "intel_cqm", -1); + if (ret) + pr_err("Intel CQM perf registration failed: %d\n", ret); + else + pr_info("Intel CQM monitoring enabled\n"); + +out: + cpu_notifier_register_done(); + + return ret; +} +device_initcall(intel_cqm_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 073983398364..813f75d71175 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -461,7 +461,8 @@ void intel_pmu_enable_bts(u64 config) debugctlmsr |= DEBUGCTLMSR_TR; debugctlmsr |= DEBUGCTLMSR_BTS; - debugctlmsr |= DEBUGCTLMSR_BTINT; + if (config & ARCH_PERFMON_EVENTSEL_INT) + debugctlmsr |= DEBUGCTLMSR_BTINT; if (!(config & ARCH_PERFMON_EVENTSEL_OS)) debugctlmsr |= DEBUGCTLMSR_BTS_OFF_OS; @@ -557,6 +558,8 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -564,6 +567,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -587,6 +592,8 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -602,6 +609,8 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ + /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -611,6 +620,10 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END @@ -622,6 +635,10 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EXCLEVT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END @@ -633,16 +650,16 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ - INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ - INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */ + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */ /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf), EVENT_CONSTRAINT_END diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 58f1a94beaf0..94e5b506caa6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -39,6 +39,7 @@ static enum { #define LBR_IND_JMP_BIT 6 /* do not capture indirect jumps */ #define LBR_REL_JMP_BIT 7 /* do not capture relative jumps */ #define LBR_FAR_BIT 8 /* do not capture far branches */ +#define LBR_CALL_STACK_BIT 9 /* enable call stack */ #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) @@ -49,6 +50,7 @@ static enum { #define LBR_REL_JMP (1 << LBR_REL_JMP_BIT) #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) +#define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -69,33 +71,31 @@ static enum { #define LBR_FROM_FLAG_IN_TX (1ULL << 62) #define LBR_FROM_FLAG_ABORT (1ULL << 61) -#define for_each_branch_sample_type(x) \ - for ((x) = PERF_SAMPLE_BRANCH_USER; \ - (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1) - /* * x86control flow change classification * x86control flow changes include branches, interrupts, traps, faults */ enum { - X86_BR_NONE = 0, /* unknown */ - - X86_BR_USER = 1 << 0, /* branch target is user */ - X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ - - X86_BR_CALL = 1 << 2, /* call */ - X86_BR_RET = 1 << 3, /* return */ - X86_BR_SYSCALL = 1 << 4, /* syscall */ - X86_BR_SYSRET = 1 << 5, /* syscall return */ - X86_BR_INT = 1 << 6, /* sw interrupt */ - X86_BR_IRET = 1 << 7, /* return from interrupt */ - X86_BR_JCC = 1 << 8, /* conditional */ - X86_BR_JMP = 1 << 9, /* jump */ - X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ - X86_BR_IND_CALL = 1 << 11,/* indirect calls */ - X86_BR_ABORT = 1 << 12,/* transaction abort */ - X86_BR_IN_TX = 1 << 13,/* in transaction */ - X86_BR_NO_TX = 1 << 14,/* not in transaction */ + X86_BR_NONE = 0, /* unknown */ + + X86_BR_USER = 1 << 0, /* branch target is user */ + X86_BR_KERNEL = 1 << 1, /* branch target is kernel */ + + X86_BR_CALL = 1 << 2, /* call */ + X86_BR_RET = 1 << 3, /* return */ + X86_BR_SYSCALL = 1 << 4, /* syscall */ + X86_BR_SYSRET = 1 << 5, /* syscall return */ + X86_BR_INT = 1 << 6, /* sw interrupt */ + X86_BR_IRET = 1 << 7, /* return from interrupt */ + X86_BR_JCC = 1 << 8, /* conditional */ + X86_BR_JMP = 1 << 9, /* jump */ + X86_BR_IRQ = 1 << 10,/* hw interrupt or trap or fault */ + X86_BR_IND_CALL = 1 << 11,/* indirect calls */ + X86_BR_ABORT = 1 << 12,/* transaction abort */ + X86_BR_IN_TX = 1 << 13,/* in transaction */ + X86_BR_NO_TX = 1 << 14,/* not in transaction */ + X86_BR_ZERO_CALL = 1 << 15,/* zero length call */ + X86_BR_CALL_STACK = 1 << 16,/* call stack */ }; #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL) @@ -112,13 +112,15 @@ enum { X86_BR_JMP |\ X86_BR_IRQ |\ X86_BR_ABORT |\ - X86_BR_IND_CALL) + X86_BR_IND_CALL |\ + X86_BR_ZERO_CALL) #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY) #define X86_BR_ANY_CALL \ (X86_BR_CALL |\ X86_BR_IND_CALL |\ + X86_BR_ZERO_CALL |\ X86_BR_SYSCALL |\ X86_BR_IRQ |\ X86_BR_INT) @@ -130,17 +132,32 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc); * otherwise it becomes near impossible to get a reliable stack. */ -static void __intel_pmu_lbr_enable(void) +static void __intel_pmu_lbr_enable(bool pmi) { - u64 debugctl; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 debugctl, lbr_select = 0, orig_debugctl; - if (cpuc->lbr_sel) - wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config); + /* + * No need to reprogram LBR_SELECT in a PMI, as it + * did not change. + */ + if (cpuc->lbr_sel && !pmi) { + lbr_select = cpuc->lbr_sel->config; + wrmsrl(MSR_LBR_SELECT, lbr_select); + } rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); - debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + orig_debugctl = debugctl; + debugctl |= DEBUGCTLMSR_LBR; + /* + * LBR callstack does not work well with FREEZE_LBRS_ON_PMI. + * If FREEZE_LBRS_ON_PMI is set, PMI near call/return instructions + * may cause superfluous increase/decrease of LBR_TOS. + */ + if (!(lbr_select & LBR_CALL_STACK)) + debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; + if (orig_debugctl != debugctl) + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); } static void __intel_pmu_lbr_disable(void) @@ -181,9 +198,116 @@ void intel_pmu_lbr_reset(void) intel_pmu_lbr_reset_64(); } +/* + * TOS = most recently recorded branch + */ +static inline u64 intel_pmu_lbr_tos(void) +{ + u64 tos; + + rdmsrl(x86_pmu.lbr_tos, tos); + return tos; +} + +enum { + LBR_NONE, + LBR_VALID, +}; + +static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx) +{ + int i; + unsigned lbr_idx, mask; + u64 tos; + + if (task_ctx->lbr_callstack_users == 0 || + task_ctx->lbr_stack_state == LBR_NONE) { + intel_pmu_lbr_reset(); + return; + } + + mask = x86_pmu.lbr_nr - 1; + tos = intel_pmu_lbr_tos(); + for (i = 0; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); + wrmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + } + task_ctx->lbr_stack_state = LBR_NONE; +} + +static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx) +{ + int i; + unsigned lbr_idx, mask; + u64 tos; + + if (task_ctx->lbr_callstack_users == 0) { + task_ctx->lbr_stack_state = LBR_NONE; + return; + } + + mask = x86_pmu.lbr_nr - 1; + tos = intel_pmu_lbr_tos(); + for (i = 0; i < x86_pmu.lbr_nr; i++) { + lbr_idx = (tos - i) & mask; + rdmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]); + rdmsrl(x86_pmu.lbr_to + lbr_idx, task_ctx->lbr_to[i]); + } + task_ctx->lbr_stack_state = LBR_VALID; +} + +void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_task_context *task_ctx; + + if (!x86_pmu.lbr_nr) + return; + + /* + * If LBR callstack feature is enabled and the stack was saved when + * the task was scheduled out, restore the stack. Otherwise flush + * the LBR stack. + */ + task_ctx = ctx ? ctx->task_ctx_data : NULL; + if (task_ctx) { + if (sched_in) { + __intel_pmu_lbr_restore(task_ctx); + cpuc->lbr_context = ctx; + } else { + __intel_pmu_lbr_save(task_ctx); + } + return; + } + + /* + * When sampling the branck stack in system-wide, it may be + * necessary to flush the stack on context switch. This happens + * when the branch stack does not tag its entries with the pid + * of the current task. Otherwise it becomes impossible to + * associate a branch entry with a task. This ambiguity is more + * likely to appear when the branch stack supports priv level + * filtering and the user sets it to monitor only at the user + * level (which could be a useful measurement in system-wide + * mode). In that case, the risk is high of having a branch + * stack with branch from multiple tasks. + */ + if (sched_in) { + intel_pmu_lbr_reset(); + cpuc->lbr_context = ctx; + } +} + +static inline bool branch_user_callstack(unsigned br_sel) +{ + return (br_sel & X86_BR_USER) && (br_sel & X86_BR_CALL_STACK); +} + void intel_pmu_lbr_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_task_context *task_ctx; if (!x86_pmu.lbr_nr) return; @@ -198,18 +322,33 @@ void intel_pmu_lbr_enable(struct perf_event *event) } cpuc->br_sel = event->hw.branch_reg.reg; + if (branch_user_callstack(cpuc->br_sel) && event->ctx && + event->ctx->task_ctx_data) { + task_ctx = event->ctx->task_ctx_data; + task_ctx->lbr_callstack_users++; + } + cpuc->lbr_users++; + perf_sched_cb_inc(event->ctx->pmu); } void intel_pmu_lbr_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_task_context *task_ctx; if (!x86_pmu.lbr_nr) return; + if (branch_user_callstack(cpuc->br_sel) && event->ctx && + event->ctx->task_ctx_data) { + task_ctx = event->ctx->task_ctx_data; + task_ctx->lbr_callstack_users--; + } + cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); + perf_sched_cb_dec(event->ctx->pmu); if (cpuc->enabled && !cpuc->lbr_users) { __intel_pmu_lbr_disable(); @@ -218,12 +357,12 @@ void intel_pmu_lbr_disable(struct perf_event *event) } } -void intel_pmu_lbr_enable_all(void) +void intel_pmu_lbr_enable_all(bool pmi) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->lbr_users) - __intel_pmu_lbr_enable(); + __intel_pmu_lbr_enable(pmi); } void intel_pmu_lbr_disable_all(void) @@ -234,18 +373,6 @@ void intel_pmu_lbr_disable_all(void) __intel_pmu_lbr_disable(); } -/* - * TOS = most recently recorded branch - */ -static inline u64 intel_pmu_lbr_tos(void) -{ - u64 tos; - - rdmsrl(x86_pmu.lbr_tos, tos); - - return tos; -} - static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) { unsigned long mask = x86_pmu.lbr_nr - 1; @@ -350,7 +477,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -387,11 +514,21 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_COND) mask |= X86_BR_JCC; + if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) { + if (!x86_pmu_has_lbr_callstack()) + return -EOPNOTSUPP; + if (mask & ~(X86_BR_USER | X86_BR_KERNEL)) + return -EINVAL; + mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET | + X86_BR_CALL_STACK; + } + /* * stash actual user request into reg, it may * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; + return 0; } /* @@ -403,14 +540,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) { struct hw_perf_event_extra *reg; u64 br_type = event->attr.branch_sample_type; - u64 mask = 0, m; - u64 v; + u64 mask = 0, v; + int i; - for_each_branch_sample_type(m) { - if (!(br_type & m)) + for (i = 0; i < PERF_SAMPLE_BRANCH_MAX_SHIFT; i++) { + if (!(br_type & (1ULL << i))) continue; - v = x86_pmu.lbr_sel_map[m]; + v = x86_pmu.lbr_sel_map[i]; if (v == LBR_NOT_SUPP) return -EOPNOTSUPP; @@ -420,8 +557,12 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; - /* LBR_SELECT operates in suppress mode so invert mask */ - reg->config = ~mask & x86_pmu.lbr_sel_mask; + /* + * The first 9 bits (LBR_SEL_MASK) in LBR_SELECT operate + * in suppress mode. So LBR_SELECT should be set to + * (~mask & LBR_SEL_MASK) | (mask & ~LBR_SEL_MASK) + */ + reg->config = mask ^ x86_pmu.lbr_sel_mask; return 0; } @@ -439,7 +580,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - intel_pmu_setup_sw_lbr_filter(event); + ret = intel_pmu_setup_sw_lbr_filter(event); + if (ret) + return ret; /* * setup HW LBR filter, if any @@ -568,6 +711,12 @@ static int branch_type(unsigned long from, unsigned long to, int abort) ret = X86_BR_INT; break; case 0xe8: /* call near rel */ + insn_get_immediate(&insn); + if (insn.immediate1.value == 0) { + /* zero length call */ + ret = X86_BR_ZERO_CALL; + break; + } case 0x9a: /* call far absolute */ ret = X86_BR_CALL; break; @@ -678,35 +827,49 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) /* * Map interface branch filters onto LBR filters */ -static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { - [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, - [PERF_SAMPLE_BRANCH_USER] = LBR_USER, - [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, - [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, - [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_REL_JMP - | LBR_IND_JMP | LBR_FAR, +static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_REL_JMP + | LBR_IND_JMP | LBR_FAR, /* * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches */ - [PERF_SAMPLE_BRANCH_ANY_CALL] = + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR, /* * NHM/WSM erratum: must include IND_JMP to capture IND_CALL */ - [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP, - [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, }; -static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { - [PERF_SAMPLE_BRANCH_ANY] = LBR_ANY, - [PERF_SAMPLE_BRANCH_USER] = LBR_USER, - [PERF_SAMPLE_BRANCH_KERNEL] = LBR_KERNEL, - [PERF_SAMPLE_BRANCH_HV] = LBR_IGN, - [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR, - [PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL - | LBR_FAR, - [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL, - [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, +static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL + | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, +}; + +static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = { + [PERF_SAMPLE_BRANCH_ANY_SHIFT] = LBR_ANY, + [PERF_SAMPLE_BRANCH_USER_SHIFT] = LBR_USER, + [PERF_SAMPLE_BRANCH_KERNEL_SHIFT] = LBR_KERNEL, + [PERF_SAMPLE_BRANCH_HV_SHIFT] = LBR_IGN, + [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT] = LBR_RETURN | LBR_FAR, + [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] = LBR_REL_CALL | LBR_IND_CALL + | LBR_FAR, + [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_COND_SHIFT] = LBR_JCC, + [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT] = LBR_REL_CALL | LBR_IND_CALL + | LBR_RETURN | LBR_CALL_STACK, }; /* core */ @@ -765,6 +928,20 @@ void __init intel_pmu_lbr_init_snb(void) pr_cont("16-deep LBR, "); } +/* haswell */ +void intel_pmu_lbr_init_hsw(void) +{ + x86_pmu.lbr_nr = 16; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = hsw_lbr_sel_map; + + pr_cont("16-deep LBR, "); +} + /* atom */ void __init intel_pmu_lbr_init_atom(void) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c new file mode 100644 index 000000000000..ffe666c2c6b5 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -0,0 +1,1100 @@ +/* + * Intel(R) Processor Trace PMU driver for perf + * Copyright (c) 2013-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * Intel PT is specified in the Intel Architecture Instruction Set Extensions + * Programming Reference: + * http://software.intel.com/en-us/intel-isa-extensions + */ + +#undef DEBUG + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/device.h> + +#include <asm/perf_event.h> +#include <asm/insn.h> +#include <asm/io.h> + +#include "perf_event.h" +#include "intel_pt.h" + +static DEFINE_PER_CPU(struct pt, pt_ctx); + +static struct pt_pmu pt_pmu; + +enum cpuid_regs { + CR_EAX = 0, + CR_ECX, + CR_EDX, + CR_EBX +}; + +/* + * Capabilities of Intel PT hardware, such as number of address bits or + * supported output schemes, are cached and exported to userspace as "caps" + * attribute group of pt pmu device + * (/sys/bus/event_source/devices/intel_pt/caps/) so that userspace can store + * relevant bits together with intel_pt traces. + * + * These are necessary for both trace decoding (payloads_lip, contains address + * width encoded in IP-related packets), and event configuration (bitmasks with + * permitted values for certain bit fields). + */ +#define PT_CAP(_n, _l, _r, _m) \ + [PT_CAP_ ## _n] = { .name = __stringify(_n), .leaf = _l, \ + .reg = _r, .mask = _m } + +static struct pt_cap_desc { + const char *name; + u32 leaf; + u8 reg; + u32 mask; +} pt_caps[] = { + PT_CAP(max_subleaf, 0, CR_EAX, 0xffffffff), + PT_CAP(cr3_filtering, 0, CR_EBX, BIT(0)), + PT_CAP(topa_output, 0, CR_ECX, BIT(0)), + PT_CAP(topa_multiple_entries, 0, CR_ECX, BIT(1)), + PT_CAP(payloads_lip, 0, CR_ECX, BIT(31)), +}; + +static u32 pt_cap_get(enum pt_capabilities cap) +{ + struct pt_cap_desc *cd = &pt_caps[cap]; + u32 c = pt_pmu.caps[cd->leaf * 4 + cd->reg]; + unsigned int shift = __ffs(cd->mask); + + return (c & cd->mask) >> shift; +} + +static ssize_t pt_cap_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *ea = + container_of(attr, struct dev_ext_attribute, attr); + enum pt_capabilities cap = (long)ea->var; + + return snprintf(buf, PAGE_SIZE, "%x\n", pt_cap_get(cap)); +} + +static struct attribute_group pt_cap_group = { + .name = "caps", +}; + +PMU_FORMAT_ATTR(tsc, "config:10" ); +PMU_FORMAT_ATTR(noretcomp, "config:11" ); + +static struct attribute *pt_formats_attr[] = { + &format_attr_tsc.attr, + &format_attr_noretcomp.attr, + NULL, +}; + +static struct attribute_group pt_format_group = { + .name = "format", + .attrs = pt_formats_attr, +}; + +static const struct attribute_group *pt_attr_groups[] = { + &pt_cap_group, + &pt_format_group, + NULL, +}; + +static int __init pt_pmu_hw_init(void) +{ + struct dev_ext_attribute *de_attrs; + struct attribute **attrs; + size_t size; + int ret; + long i; + + attrs = NULL; + ret = -ENODEV; + if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_INTEL_PT)) + goto fail; + + for (i = 0; i < PT_CPUID_LEAVES; i++) { + cpuid_count(20, i, + &pt_pmu.caps[CR_EAX + i*4], + &pt_pmu.caps[CR_EBX + i*4], + &pt_pmu.caps[CR_ECX + i*4], + &pt_pmu.caps[CR_EDX + i*4]); + } + + ret = -ENOMEM; + size = sizeof(struct attribute *) * (ARRAY_SIZE(pt_caps)+1); + attrs = kzalloc(size, GFP_KERNEL); + if (!attrs) + goto fail; + + size = sizeof(struct dev_ext_attribute) * (ARRAY_SIZE(pt_caps)+1); + de_attrs = kzalloc(size, GFP_KERNEL); + if (!de_attrs) + goto fail; + + for (i = 0; i < ARRAY_SIZE(pt_caps); i++) { + struct dev_ext_attribute *de_attr = de_attrs + i; + + de_attr->attr.attr.name = pt_caps[i].name; + + sysfs_attr_init(&de_attrs->attr.attr); + + de_attr->attr.attr.mode = S_IRUGO; + de_attr->attr.show = pt_cap_show; + de_attr->var = (void *)i; + + attrs[i] = &de_attr->attr.attr; + } + + pt_cap_group.attrs = attrs; + + return 0; + +fail: + kfree(attrs); + + return ret; +} + +#define PT_CONFIG_MASK (RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC) + +static bool pt_event_valid(struct perf_event *event) +{ + u64 config = event->attr.config; + + if ((config & PT_CONFIG_MASK) != config) + return false; + + return true; +} + +/* + * PT configuration helpers + * These all are cpu affine and operate on a local PT + */ + +static bool pt_is_running(void) +{ + u64 ctl; + + rdmsrl(MSR_IA32_RTIT_CTL, ctl); + + return !!(ctl & RTIT_CTL_TRACEEN); +} + +static void pt_config(struct perf_event *event) +{ + u64 reg; + + reg = RTIT_CTL_TOPA | RTIT_CTL_BRANCH_EN | RTIT_CTL_TRACEEN; + + if (!event->attr.exclude_kernel) + reg |= RTIT_CTL_OS; + if (!event->attr.exclude_user) + reg |= RTIT_CTL_USR; + + reg |= (event->attr.config & PT_CONFIG_MASK); + + wrmsrl(MSR_IA32_RTIT_CTL, reg); +} + +static void pt_config_start(bool start) +{ + u64 ctl; + + rdmsrl(MSR_IA32_RTIT_CTL, ctl); + if (start) + ctl |= RTIT_CTL_TRACEEN; + else + ctl &= ~RTIT_CTL_TRACEEN; + wrmsrl(MSR_IA32_RTIT_CTL, ctl); + + /* + * A wrmsr that disables trace generation serializes other PT + * registers and causes all data packets to be written to memory, + * but a fence is required for the data to become globally visible. + * + * The below WMB, separating data store and aux_head store matches + * the consumer's RMB that separates aux_head load and data load. + */ + if (!start) + wmb(); +} + +static void pt_config_buffer(void *buf, unsigned int topa_idx, + unsigned int output_off) +{ + u64 reg; + + wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, virt_to_phys(buf)); + + reg = 0x7f | ((u64)topa_idx << 7) | ((u64)output_off << 32); + + wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg); +} + +/* + * Keep ToPA table-related metadata on the same page as the actual table, + * taking up a few words from the top + */ + +#define TENTS_PER_PAGE (((PAGE_SIZE - 40) / sizeof(struct topa_entry)) - 1) + +/** + * struct topa - page-sized ToPA table with metadata at the top + * @table: actual ToPA table entries, as understood by PT hardware + * @list: linkage to struct pt_buffer's list of tables + * @phys: physical address of this page + * @offset: offset of the first entry in this table in the buffer + * @size: total size of all entries in this table + * @last: index of the last initialized entry in this table + */ +struct topa { + struct topa_entry table[TENTS_PER_PAGE]; + struct list_head list; + u64 phys; + u64 offset; + size_t size; + int last; +}; + +/* make -1 stand for the last table entry */ +#define TOPA_ENTRY(t, i) ((i) == -1 ? &(t)->table[(t)->last] : &(t)->table[(i)]) + +/** + * topa_alloc() - allocate page-sized ToPA table + * @cpu: CPU on which to allocate. + * @gfp: Allocation flags. + * + * Return: On success, return the pointer to ToPA table page. + */ +static struct topa *topa_alloc(int cpu, gfp_t gfp) +{ + int node = cpu_to_node(cpu); + struct topa *topa; + struct page *p; + + p = alloc_pages_node(node, gfp | __GFP_ZERO, 0); + if (!p) + return NULL; + + topa = page_address(p); + topa->last = 0; + topa->phys = page_to_phys(p); + + /* + * In case of singe-entry ToPA, always put the self-referencing END + * link as the 2nd entry in the table + */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) { + TOPA_ENTRY(topa, 1)->base = topa->phys >> TOPA_SHIFT; + TOPA_ENTRY(topa, 1)->end = 1; + } + + return topa; +} + +/** + * topa_free() - free a page-sized ToPA table + * @topa: Table to deallocate. + */ +static void topa_free(struct topa *topa) +{ + free_page((unsigned long)topa); +} + +/** + * topa_insert_table() - insert a ToPA table into a buffer + * @buf: PT buffer that's being extended. + * @topa: New topa table to be inserted. + * + * If it's the first table in this buffer, set up buffer's pointers + * accordingly; otherwise, add a END=1 link entry to @topa to the current + * "last" table and adjust the last table pointer to @topa. + */ +static void topa_insert_table(struct pt_buffer *buf, struct topa *topa) +{ + struct topa *last = buf->last; + + list_add_tail(&topa->list, &buf->tables); + + if (!buf->first) { + buf->first = buf->last = buf->cur = topa; + return; + } + + topa->offset = last->offset + last->size; + buf->last = topa; + + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + return; + + BUG_ON(last->last != TENTS_PER_PAGE - 1); + + TOPA_ENTRY(last, -1)->base = topa->phys >> TOPA_SHIFT; + TOPA_ENTRY(last, -1)->end = 1; +} + +/** + * topa_table_full() - check if a ToPA table is filled up + * @topa: ToPA table. + */ +static bool topa_table_full(struct topa *topa) +{ + /* single-entry ToPA is a special case */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + return !!topa->last; + + return topa->last == TENTS_PER_PAGE - 1; +} + +/** + * topa_insert_pages() - create a list of ToPA tables + * @buf: PT buffer being initialized. + * @gfp: Allocation flags. + * + * This initializes a list of ToPA tables with entries from + * the data_pages provided by rb_alloc_aux(). + * + * Return: 0 on success or error code. + */ +static int topa_insert_pages(struct pt_buffer *buf, gfp_t gfp) +{ + struct topa *topa = buf->last; + int order = 0; + struct page *p; + + p = virt_to_page(buf->data_pages[buf->nr_pages]); + if (PagePrivate(p)) + order = page_private(p); + + if (topa_table_full(topa)) { + topa = topa_alloc(buf->cpu, gfp); + if (!topa) + return -ENOMEM; + + topa_insert_table(buf, topa); + } + + TOPA_ENTRY(topa, -1)->base = page_to_phys(p) >> TOPA_SHIFT; + TOPA_ENTRY(topa, -1)->size = order; + if (!buf->snapshot && !pt_cap_get(PT_CAP_topa_multiple_entries)) { + TOPA_ENTRY(topa, -1)->intr = 1; + TOPA_ENTRY(topa, -1)->stop = 1; + } + + topa->last++; + topa->size += sizes(order); + + buf->nr_pages += 1ul << order; + + return 0; +} + +/** + * pt_topa_dump() - print ToPA tables and their entries + * @buf: PT buffer. + */ +static void pt_topa_dump(struct pt_buffer *buf) +{ + struct topa *topa; + + list_for_each_entry(topa, &buf->tables, list) { + int i; + + pr_debug("# table @%p (%016Lx), off %llx size %zx\n", topa->table, + topa->phys, topa->offset, topa->size); + for (i = 0; i < TENTS_PER_PAGE; i++) { + pr_debug("# entry @%p (%lx sz %u %c%c%c) raw=%16llx\n", + &topa->table[i], + (unsigned long)topa->table[i].base << TOPA_SHIFT, + sizes(topa->table[i].size), + topa->table[i].end ? 'E' : ' ', + topa->table[i].intr ? 'I' : ' ', + topa->table[i].stop ? 'S' : ' ', + *(u64 *)&topa->table[i]); + if ((pt_cap_get(PT_CAP_topa_multiple_entries) && + topa->table[i].stop) || + topa->table[i].end) + break; + } + } +} + +/** + * pt_buffer_advance() - advance to the next output region + * @buf: PT buffer. + * + * Advance the current pointers in the buffer to the next ToPA entry. + */ +static void pt_buffer_advance(struct pt_buffer *buf) +{ + buf->output_off = 0; + buf->cur_idx++; + + if (buf->cur_idx == buf->cur->last) { + if (buf->cur == buf->last) + buf->cur = buf->first; + else + buf->cur = list_entry(buf->cur->list.next, struct topa, + list); + buf->cur_idx = 0; + } +} + +/** + * pt_update_head() - calculate current offsets and sizes + * @pt: Per-cpu pt context. + * + * Update buffer's current write pointer position and data size. + */ +static void pt_update_head(struct pt *pt) +{ + struct pt_buffer *buf = perf_get_aux(&pt->handle); + u64 topa_idx, base, old; + + /* offset of the first region in this table from the beginning of buf */ + base = buf->cur->offset + buf->output_off; + + /* offset of the current output region within this table */ + for (topa_idx = 0; topa_idx < buf->cur_idx; topa_idx++) + base += sizes(buf->cur->table[topa_idx].size); + + if (buf->snapshot) { + local_set(&buf->data_size, base); + } else { + old = (local64_xchg(&buf->head, base) & + ((buf->nr_pages << PAGE_SHIFT) - 1)); + if (base < old) + base += buf->nr_pages << PAGE_SHIFT; + + local_add(base - old, &buf->data_size); + } +} + +/** + * pt_buffer_region() - obtain current output region's address + * @buf: PT buffer. + */ +static void *pt_buffer_region(struct pt_buffer *buf) +{ + return phys_to_virt(buf->cur->table[buf->cur_idx].base << TOPA_SHIFT); +} + +/** + * pt_buffer_region_size() - obtain current output region's size + * @buf: PT buffer. + */ +static size_t pt_buffer_region_size(struct pt_buffer *buf) +{ + return sizes(buf->cur->table[buf->cur_idx].size); +} + +/** + * pt_handle_status() - take care of possible status conditions + * @pt: Per-cpu pt context. + */ +static void pt_handle_status(struct pt *pt) +{ + struct pt_buffer *buf = perf_get_aux(&pt->handle); + int advance = 0; + u64 status; + + rdmsrl(MSR_IA32_RTIT_STATUS, status); + + if (status & RTIT_STATUS_ERROR) { + pr_err_ratelimited("ToPA ERROR encountered, trying to recover\n"); + pt_topa_dump(buf); + status &= ~RTIT_STATUS_ERROR; + } + + if (status & RTIT_STATUS_STOPPED) { + status &= ~RTIT_STATUS_STOPPED; + + /* + * On systems that only do single-entry ToPA, hitting STOP + * means we are already losing data; need to let the decoder + * know. + */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries) || + buf->output_off == sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) { + local_inc(&buf->lost); + advance++; + } + } + + /* + * Also on single-entry ToPA implementations, interrupt will come + * before the output reaches its output region's boundary. + */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries) && !buf->snapshot && + pt_buffer_region_size(buf) - buf->output_off <= TOPA_PMI_MARGIN) { + void *head = pt_buffer_region(buf); + + /* everything within this margin needs to be zeroed out */ + memset(head + buf->output_off, 0, + pt_buffer_region_size(buf) - + buf->output_off); + advance++; + } + + if (advance) + pt_buffer_advance(buf); + + wrmsrl(MSR_IA32_RTIT_STATUS, status); +} + +/** + * pt_read_offset() - translate registers into buffer pointers + * @buf: PT buffer. + * + * Set buffer's output pointers from MSR values. + */ +static void pt_read_offset(struct pt_buffer *buf) +{ + u64 offset, base_topa; + + rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, base_topa); + buf->cur = phys_to_virt(base_topa); + + rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, offset); + /* offset within current output region */ + buf->output_off = offset >> 32; + /* index of current output region within this table */ + buf->cur_idx = (offset & 0xffffff80) >> 7; +} + +/** + * pt_topa_next_entry() - obtain index of the first page in the next ToPA entry + * @buf: PT buffer. + * @pg: Page offset in the buffer. + * + * When advancing to the next output region (ToPA entry), given a page offset + * into the buffer, we need to find the offset of the first page in the next + * region. + */ +static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg) +{ + struct topa_entry *te = buf->topa_index[pg]; + + /* one region */ + if (buf->first == buf->last && buf->first->last == 1) + return pg; + + do { + pg++; + pg &= buf->nr_pages - 1; + } while (buf->topa_index[pg] == te); + + return pg; +} + +/** + * pt_buffer_reset_markers() - place interrupt and stop bits in the buffer + * @buf: PT buffer. + * @handle: Current output handle. + * + * Place INT and STOP marks to prevent overwriting old data that the consumer + * hasn't yet collected. + */ +static int pt_buffer_reset_markers(struct pt_buffer *buf, + struct perf_output_handle *handle) + +{ + unsigned long idx, npages, end; + + if (buf->snapshot) + return 0; + + /* can't stop in the middle of an output region */ + if (buf->output_off + handle->size + 1 < + sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size)) + return -EINVAL; + + + /* single entry ToPA is handled by marking all regions STOP=1 INT=1 */ + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + return 0; + + /* clear STOP and INT from current entry */ + buf->topa_index[buf->stop_pos]->stop = 0; + buf->topa_index[buf->intr_pos]->intr = 0; + + if (pt_cap_get(PT_CAP_topa_multiple_entries)) { + npages = (handle->size + 1) >> PAGE_SHIFT; + end = (local64_read(&buf->head) >> PAGE_SHIFT) + npages; + /*if (end > handle->wakeup >> PAGE_SHIFT) + end = handle->wakeup >> PAGE_SHIFT;*/ + idx = end & (buf->nr_pages - 1); + buf->stop_pos = idx; + idx = (local64_read(&buf->head) >> PAGE_SHIFT) + npages - 1; + idx &= buf->nr_pages - 1; + buf->intr_pos = idx; + } + + buf->topa_index[buf->stop_pos]->stop = 1; + buf->topa_index[buf->intr_pos]->intr = 1; + + return 0; +} + +/** + * pt_buffer_setup_topa_index() - build topa_index[] table of regions + * @buf: PT buffer. + * + * topa_index[] references output regions indexed by offset into the + * buffer for purposes of quick reverse lookup. + */ +static void pt_buffer_setup_topa_index(struct pt_buffer *buf) +{ + struct topa *cur = buf->first, *prev = buf->last; + struct topa_entry *te_cur = TOPA_ENTRY(cur, 0), + *te_prev = TOPA_ENTRY(prev, prev->last - 1); + int pg = 0, idx = 0, ntopa = 0; + + while (pg < buf->nr_pages) { + int tidx; + + /* pages within one topa entry */ + for (tidx = 0; tidx < 1 << te_cur->size; tidx++, pg++) + buf->topa_index[pg] = te_prev; + + te_prev = te_cur; + + if (idx == cur->last - 1) { + /* advance to next topa table */ + idx = 0; + cur = list_entry(cur->list.next, struct topa, list); + ntopa++; + } else + idx++; + te_cur = TOPA_ENTRY(cur, idx); + } + +} + +/** + * pt_buffer_reset_offsets() - adjust buffer's write pointers from aux_head + * @buf: PT buffer. + * @head: Write pointer (aux_head) from AUX buffer. + * + * Find the ToPA table and entry corresponding to given @head and set buffer's + * "current" pointers accordingly. + */ +static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head) +{ + int pg; + + if (buf->snapshot) + head &= (buf->nr_pages << PAGE_SHIFT) - 1; + + pg = (head >> PAGE_SHIFT) & (buf->nr_pages - 1); + pg = pt_topa_next_entry(buf, pg); + + buf->cur = (struct topa *)((unsigned long)buf->topa_index[pg] & PAGE_MASK); + buf->cur_idx = ((unsigned long)buf->topa_index[pg] - + (unsigned long)buf->cur) / sizeof(struct topa_entry); + buf->output_off = head & (sizes(buf->cur->table[buf->cur_idx].size) - 1); + + local64_set(&buf->head, head); + local_set(&buf->data_size, 0); +} + +/** + * pt_buffer_fini_topa() - deallocate ToPA structure of a buffer + * @buf: PT buffer. + */ +static void pt_buffer_fini_topa(struct pt_buffer *buf) +{ + struct topa *topa, *iter; + + list_for_each_entry_safe(topa, iter, &buf->tables, list) { + /* + * right now, this is in free_aux() path only, so + * no need to unlink this table from the list + */ + topa_free(topa); + } +} + +/** + * pt_buffer_init_topa() - initialize ToPA table for pt buffer + * @buf: PT buffer. + * @size: Total size of all regions within this ToPA. + * @gfp: Allocation flags. + */ +static int pt_buffer_init_topa(struct pt_buffer *buf, unsigned long nr_pages, + gfp_t gfp) +{ + struct topa *topa; + int err; + + topa = topa_alloc(buf->cpu, gfp); + if (!topa) + return -ENOMEM; + + topa_insert_table(buf, topa); + + while (buf->nr_pages < nr_pages) { + err = topa_insert_pages(buf, gfp); + if (err) { + pt_buffer_fini_topa(buf); + return -ENOMEM; + } + } + + pt_buffer_setup_topa_index(buf); + + /* link last table to the first one, unless we're double buffering */ + if (pt_cap_get(PT_CAP_topa_multiple_entries)) { + TOPA_ENTRY(buf->last, -1)->base = buf->first->phys >> TOPA_SHIFT; + TOPA_ENTRY(buf->last, -1)->end = 1; + } + + pt_topa_dump(buf); + return 0; +} + +/** + * pt_buffer_setup_aux() - set up topa tables for a PT buffer + * @cpu: Cpu on which to allocate, -1 means current. + * @pages: Array of pointers to buffer pages passed from perf core. + * @nr_pages: Number of pages in the buffer. + * @snapshot: If this is a snapshot/overwrite counter. + * + * This is a pmu::setup_aux callback that sets up ToPA tables and all the + * bookkeeping for an AUX buffer. + * + * Return: Our private PT buffer structure. + */ +static void * +pt_buffer_setup_aux(int cpu, void **pages, int nr_pages, bool snapshot) +{ + struct pt_buffer *buf; + int node, ret; + + if (!nr_pages) + return NULL; + + if (cpu == -1) + cpu = raw_smp_processor_id(); + node = cpu_to_node(cpu); + + buf = kzalloc_node(offsetof(struct pt_buffer, topa_index[nr_pages]), + GFP_KERNEL, node); + if (!buf) + return NULL; + + buf->cpu = cpu; + buf->snapshot = snapshot; + buf->data_pages = pages; + + INIT_LIST_HEAD(&buf->tables); + + ret = pt_buffer_init_topa(buf, nr_pages, GFP_KERNEL); + if (ret) { + kfree(buf); + return NULL; + } + + return buf; +} + +/** + * pt_buffer_free_aux() - perf AUX deallocation path callback + * @data: PT buffer. + */ +static void pt_buffer_free_aux(void *data) +{ + struct pt_buffer *buf = data; + + pt_buffer_fini_topa(buf); + kfree(buf); +} + +/** + * pt_buffer_is_full() - check if the buffer is full + * @buf: PT buffer. + * @pt: Per-cpu pt handle. + * + * If the user hasn't read data from the output region that aux_head + * points to, the buffer is considered full: the user needs to read at + * least this region and update aux_tail to point past it. + */ +static bool pt_buffer_is_full(struct pt_buffer *buf, struct pt *pt) +{ + if (buf->snapshot) + return false; + + if (local_read(&buf->data_size) >= pt->handle.size) + return true; + + return false; +} + +/** + * intel_pt_interrupt() - PT PMI handler + */ +void intel_pt_interrupt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf; + struct perf_event *event = pt->handle.event; + + /* + * There may be a dangling PT bit in the interrupt status register + * after PT has been disabled by pt_event_stop(). Make sure we don't + * do anything (particularly, re-enable) for this event here. + */ + if (!ACCESS_ONCE(pt->handle_nmi)) + return; + + pt_config_start(false); + + if (!event) + return; + + buf = perf_get_aux(&pt->handle); + if (!buf) + return; + + pt_read_offset(buf); + + pt_handle_status(pt); + + pt_update_head(pt); + + perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0), + local_xchg(&buf->lost, 0)); + + if (!event->hw.state) { + int ret; + + buf = perf_aux_output_begin(&pt->handle, event); + if (!buf) { + event->hw.state = PERF_HES_STOPPED; + return; + } + + pt_buffer_reset_offsets(buf, pt->handle.head); + ret = pt_buffer_reset_markers(buf, &pt->handle); + if (ret) { + perf_aux_output_end(&pt->handle, 0, true); + return; + } + + pt_config_buffer(buf->cur->table, buf->cur_idx, + buf->output_off); + wrmsrl(MSR_IA32_RTIT_STATUS, 0); + pt_config(event); + } +} + +/* + * PMU callbacks + */ + +static void pt_event_start(struct perf_event *event, int mode) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf = perf_get_aux(&pt->handle); + + if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) { + event->hw.state = PERF_HES_STOPPED; + return; + } + + ACCESS_ONCE(pt->handle_nmi) = 1; + event->hw.state = 0; + + pt_config_buffer(buf->cur->table, buf->cur_idx, + buf->output_off); + wrmsrl(MSR_IA32_RTIT_STATUS, 0); + pt_config(event); +} + +static void pt_event_stop(struct perf_event *event, int mode) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + /* + * Protect against the PMI racing with disabling wrmsr, + * see comment in intel_pt_interrupt(). + */ + ACCESS_ONCE(pt->handle_nmi) = 0; + pt_config_start(false); + + if (event->hw.state == PERF_HES_STOPPED) + return; + + event->hw.state = PERF_HES_STOPPED; + + if (mode & PERF_EF_UPDATE) { + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf = perf_get_aux(&pt->handle); + + if (!buf) + return; + + if (WARN_ON_ONCE(pt->handle.event != event)) + return; + + pt_read_offset(buf); + + pt_handle_status(pt); + + pt_update_head(pt); + } +} + +static void pt_event_del(struct perf_event *event, int mode) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct pt_buffer *buf; + + pt_event_stop(event, PERF_EF_UPDATE); + + buf = perf_get_aux(&pt->handle); + + if (buf) { + if (buf->snapshot) + pt->handle.head = + local_xchg(&buf->data_size, + buf->nr_pages << PAGE_SHIFT); + perf_aux_output_end(&pt->handle, local_xchg(&buf->data_size, 0), + local_xchg(&buf->lost, 0)); + } +} + +static int pt_event_add(struct perf_event *event, int mode) +{ + struct pt_buffer *buf; + struct pt *pt = this_cpu_ptr(&pt_ctx); + struct hw_perf_event *hwc = &event->hw; + int ret = -EBUSY; + + if (pt->handle.event) + goto fail; + + buf = perf_aux_output_begin(&pt->handle, event); + ret = -EINVAL; + if (!buf) + goto fail_stop; + + pt_buffer_reset_offsets(buf, pt->handle.head); + if (!buf->snapshot) { + ret = pt_buffer_reset_markers(buf, &pt->handle); + if (ret) + goto fail_end_stop; + } + + if (mode & PERF_EF_START) { + pt_event_start(event, 0); + ret = -EBUSY; + if (hwc->state == PERF_HES_STOPPED) + goto fail_end_stop; + } else { + hwc->state = PERF_HES_STOPPED; + } + + return 0; + +fail_end_stop: + perf_aux_output_end(&pt->handle, 0, true); +fail_stop: + hwc->state = PERF_HES_STOPPED; +fail: + return ret; +} + +static void pt_event_read(struct perf_event *event) +{ +} + +static void pt_event_destroy(struct perf_event *event) +{ + x86_del_exclusive(x86_lbr_exclusive_pt); +} + +static int pt_event_init(struct perf_event *event) +{ + if (event->attr.type != pt_pmu.pmu.type) + return -ENOENT; + + if (!pt_event_valid(event)) + return -EINVAL; + + if (x86_add_exclusive(x86_lbr_exclusive_pt)) + return -EBUSY; + + event->destroy = pt_event_destroy; + + return 0; +} + +static __init int pt_init(void) +{ + int ret, cpu, prior_warn = 0; + + BUILD_BUG_ON(sizeof(struct topa) > PAGE_SIZE); + get_online_cpus(); + for_each_online_cpu(cpu) { + u64 ctl; + + ret = rdmsrl_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl); + if (!ret && (ctl & RTIT_CTL_TRACEEN)) + prior_warn++; + } + put_online_cpus(); + + if (prior_warn) { + x86_add_exclusive(x86_lbr_exclusive_pt); + pr_warn("PT is enabled at boot time, doing nothing\n"); + + return -EBUSY; + } + + ret = pt_pmu_hw_init(); + if (ret) + return ret; + + if (!pt_cap_get(PT_CAP_topa_output)) { + pr_warn("ToPA output is not supported on this CPU\n"); + return -ENODEV; + } + + if (!pt_cap_get(PT_CAP_topa_multiple_entries)) + pt_pmu.pmu.capabilities = + PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; + + pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; + pt_pmu.pmu.attr_groups = pt_attr_groups; + pt_pmu.pmu.task_ctx_nr = perf_sw_context; + pt_pmu.pmu.event_init = pt_event_init; + pt_pmu.pmu.add = pt_event_add; + pt_pmu.pmu.del = pt_event_del; + pt_pmu.pmu.start = pt_event_start; + pt_pmu.pmu.stop = pt_event_stop; + pt_pmu.pmu.read = pt_event_read; + pt_pmu.pmu.setup_aux = pt_buffer_setup_aux; + pt_pmu.pmu.free_aux = pt_buffer_free_aux; + ret = perf_pmu_register(&pt_pmu.pmu, "intel_pt", -1); + + return ret; +} + +module_init(pt_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index c4bb8b8e5017..999289b94025 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -62,6 +62,14 @@ #define RAPL_IDX_PP1_NRG_STAT 3 /* gpu */ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ +#define NR_RAPL_DOMAINS 0x4 +static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { + "pp0-core", + "package", + "dram", + "pp1-gpu", +}; + /* Clients have PP0, PKG */ #define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\ 1<<RAPL_IDX_PKG_NRG_STAT|\ @@ -112,7 +120,6 @@ static struct perf_pmu_events_attr event_attr_##v = { \ struct rapl_pmu { spinlock_t lock; - int hw_unit; /* 1/2^hw_unit Joule */ int n_active; /* number of active events */ struct list_head active_list; struct pmu *pmu; /* pointer to rapl_pmu_class */ @@ -120,6 +127,7 @@ struct rapl_pmu { struct hrtimer hrtimer; }; +static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; /* 1/2^hw_unit Joule */ static struct pmu rapl_pmu_class; static cpumask_t rapl_cpu_mask; static int rapl_cntr_mask; @@ -127,6 +135,7 @@ static int rapl_cntr_mask; static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu); static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free); +static struct x86_pmu_quirk *rapl_quirks; static inline u64 rapl_read_counter(struct perf_event *event) { u64 raw; @@ -134,15 +143,28 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -static inline u64 rapl_scale(u64 v) +#define rapl_add_quirk(func_) \ +do { \ + static struct x86_pmu_quirk __quirk __initdata = { \ + .func = func_, \ + }; \ + __quirk.next = rapl_quirks; \ + rapl_quirks = &__quirk; \ +} while (0) + +static inline u64 rapl_scale(u64 v, int cfg) { + if (cfg > NR_RAPL_DOMAINS) { + pr_warn("invalid domain %d, failed to scale data\n", cfg); + return v; + } /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit); + return v << (32 - rapl_hw_unit[cfg - 1]); } static u64 rapl_event_update(struct perf_event *event) @@ -173,7 +195,7 @@ again: delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - sdelta = rapl_scale(delta); + sdelta = rapl_scale(delta, event->hw.config); local64_add(sdelta, &event->count); @@ -546,12 +568,22 @@ static void rapl_cpu_init(int cpu) cpumask_set_cpu(cpu, &rapl_cpu_mask); } +static __init void rapl_hsw_server_quirk(void) +{ + /* + * DRAM domain on HSW server has fixed energy unit which can be + * different than the unit from power unit MSR. + * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 + * of 2. Datasheet, September 2014, Reference Number: 330784-001 " + */ + rapl_hw_unit[RAPL_IDX_RAM_NRG_STAT] = 16; +} + 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; @@ -559,24 +591,13 @@ static int rapl_cpu_prepare(int cpu) if (phys_id < 0) return -1; - /* protect rdmsrl() to handle virtualization */ - 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; - spin_lock_init(&pmu->lock); INIT_LIST_HEAD(&pmu->active_list); - /* - * grab power unit as: 1/2^unit Joules - * - * we cache in local PMU instance - */ - pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; pmu->pmu = &rapl_pmu_class; /* @@ -586,8 +607,8 @@ static int rapl_cpu_prepare(int cpu) * divide interval by 2 to avoid lockstep (2 * 100) * if hw unit is 32, then we use 2 ms 1/200/2 */ - if (pmu->hw_unit < 32) - ms = (1000 / (2 * 100)) * (1ULL << (32 - pmu->hw_unit - 1)); + if (rapl_hw_unit[0] < 32) + ms = (1000 / (2 * 100)) * (1ULL << (32 - rapl_hw_unit[0] - 1)); else ms = 2; @@ -655,6 +676,20 @@ static int rapl_cpu_notifier(struct notifier_block *self, return NOTIFY_OK; } +static int rapl_check_hw_unit(void) +{ + u64 msr_rapl_power_unit_bits; + int i; + + /* protect rdmsrl() to handle virtualization */ + if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits)) + return -1; + for (i = 0; i < NR_RAPL_DOMAINS; i++) + rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + + return 0; +} + static const struct x86_cpu_id rapl_cpu_match[] = { [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 }, [1] = {}, @@ -664,6 +699,8 @@ static int __init rapl_pmu_init(void) { struct rapl_pmu *pmu; int cpu, ret; + struct x86_pmu_quirk *quirk; + int i; /* * check for Intel processor family 6 @@ -678,6 +715,11 @@ static int __init rapl_pmu_init(void) rapl_cntr_mask = RAPL_IDX_CLN; rapl_pmu_events_group.attrs = rapl_events_cln_attr; break; + case 63: /* Haswell-Server */ + rapl_add_quirk(rapl_hsw_server_quirk); + rapl_cntr_mask = RAPL_IDX_SRV; + rapl_pmu_events_group.attrs = rapl_events_srv_attr; + break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ rapl_cntr_mask = RAPL_IDX_HSW; @@ -693,7 +735,13 @@ static int __init rapl_pmu_init(void) /* unsupported */ return 0; } + ret = rapl_check_hw_unit(); + if (ret) + return ret; + /* run cpu model quirks */ + for (quirk = rapl_quirks; quirk; quirk = quirk->next) + quirk->func(); cpu_notifier_register_begin(); for_each_online_cpu(cpu) { @@ -714,14 +762,18 @@ static int __init rapl_pmu_init(void) pmu = __this_cpu_read(rapl_pmu); - pr_info("RAPL PMU detected, hw unit 2^-%d Joules," + pr_info("RAPL PMU detected," " API unit is 2^-32 Joules," " %d fixed counters" " %llu ms ovfl timer\n", - pmu->hw_unit, hweight32(rapl_cntr_mask), ktime_to_ms(pmu->timer_interval)); - + for (i = 0; i < NR_RAPL_DOMAINS; i++) { + if (rapl_cntr_mask & (1 << i)) { + pr_info("hw unit of domain %s 2^-%d Joules\n", + rapl_domain_names[i], rapl_hw_unit[i]); + } + } out: cpu_notifier_register_done(); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index 21af6149edf2..12d9548457e7 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -1132,8 +1132,7 @@ static int snbep_pci2phy_map_init(int devid) } } - if (ubox_dev) - pci_dev_put(ubox_dev); + pci_dev_put(ubox_dev); return err ? pcibios_err_to_errno(err) : 0; } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 60639093d536..3d423a101fae 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -41,6 +41,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, + { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index aceb2f90c716..c76d3e37c6e1 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -105,7 +105,7 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) #ifdef CONFIG_X86_32 struct pt_regs fixed_regs; - if (!user_mode_vm(regs)) { + if (!user_mode(regs)) { crash_fixup_ss_esp(&fixed_regs, regs); regs = &fixed_regs; } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 3d3503351242..6367a780cc8c 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -286,13 +286,13 @@ static void __init x86_flattree_get_config(void) initial_boot_params = dt = early_memremap(initial_dtb, map_len); size = of_get_flat_dt_size(); if (map_len < size) { - early_iounmap(dt, map_len); + early_memunmap(dt, map_len); initial_boot_params = dt = early_memremap(initial_dtb, size); map_len = size; } unflatten_and_copy_device_tree(); - early_iounmap(dt, map_len); + early_memunmap(dt, map_len); } #else static inline void x86_flattree_get_config(void) { } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index cf3df1d8d039..9c30acfadae2 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -25,10 +25,12 @@ unsigned int code_bytes = 64; int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; static int die_counter; -static void printk_stack_address(unsigned long address, int reliable) +static void printk_stack_address(unsigned long address, int reliable, + void *data) { - pr_cont(" [<%p>] %s%pB\n", - (void *)address, reliable ? "" : "? ", (void *)address); + printk("%s [<%p>] %s%pB\n", + (char *)data, (void *)address, reliable ? "" : "? ", + (void *)address); } void printk_address(unsigned long address) @@ -155,8 +157,7 @@ static int print_trace_stack(void *data, char *name) static void print_trace_address(void *data, unsigned long addr, int reliable) { touch_nmi_watchdog(); - printk(data); - printk_stack_address(addr, reliable); + printk_stack_address(addr, reliable, data); } static const struct stacktrace_ops print_trace_ops = { @@ -278,7 +279,7 @@ int __die(const char *str, struct pt_regs *regs, long err) print_modules(); show_regs(regs); #ifdef CONFIG_X86_32 - if (user_mode_vm(regs)) { + if (user_mode(regs)) { sp = regs->sp; ss = regs->ss & 0xffff; } else { @@ -307,7 +308,7 @@ void die(const char *str, struct pt_regs *regs, long err) unsigned long flags = oops_begin(); int sig = SIGSEGV; - if (!user_mode_vm(regs)) + if (!user_mode(regs)) report_bug(regs->ip, regs); if (__die(str, regs, err)) diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 5abd4cd4230c..464ffd69b92e 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -108,9 +108,12 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, for (i = 0; i < kstack_depth_to_print; i++) { if (kstack_end(stack)) break; - if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - pr_cont("\n"); - pr_cont(" %08lx", *stack++); + if ((i % STACKSLOTS_PER_LINE) == 0) { + if (i != 0) + pr_cont("\n"); + printk("%s %08lx", log_lvl, *stack++); + } else + pr_cont(" %08lx", *stack++); touch_nmi_watchdog(); } pr_cont("\n"); @@ -123,13 +126,13 @@ void show_regs(struct pt_regs *regs) int i; show_regs_print_info(KERN_EMERG); - __show_regs(regs, !user_mode_vm(regs)); + __show_regs(regs, !user_mode(regs)); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. */ - if (!user_mode_vm(regs)) { + if (!user_mode(regs)) { unsigned int code_prologue = code_bytes * 43 / 64; unsigned int code_len = code_bytes; unsigned char c; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index ff86f19b5758..5f1c6266eb30 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -280,12 +280,15 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, pr_cont(" <EOI> "); } } else { - if (((long) stack & (THREAD_SIZE-1)) == 0) + if (kstack_end(stack)) break; } - if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - pr_cont("\n"); - pr_cont(" %016lx", *stack++); + if ((i % STACKSLOTS_PER_LINE) == 0) { + if (i != 0) + pr_cont("\n"); + printk("%s %016lx", log_lvl, *stack++); + } else + pr_cont(" %016lx", *stack++); touch_nmi_watchdog(); } preempt_enable(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 46201deee923..e2ce85db2283 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -149,6 +149,9 @@ static void __init e820_print_type(u32 type) case E820_UNUSABLE: printk(KERN_CONT "unusable"); break; + case E820_PRAM: + printk(KERN_CONT "persistent (type %u)", type); + break; default: printk(KERN_CONT "type %u", type); break; @@ -343,7 +346,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, * continue building up new bios map based on this * information */ - if (current_type != last_type) { + if (current_type != last_type || current_type == E820_PRAM) { if (last_type != 0) { new_bios[new_bios_entry].size = change_point[chgidx]->addr - last_addr; @@ -661,7 +664,7 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len) extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); - early_iounmap(sdata, data_len); + early_memunmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); } @@ -688,6 +691,7 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn) register_nosave_region(pfn, PFN_UP(ei->addr)); pfn = PFN_DOWN(ei->addr + ei->size); + if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) register_nosave_region(PFN_UP(ei->addr), pfn); @@ -748,7 +752,7 @@ u64 __init early_reserve_e820(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +static unsigned long __init e820_end_pfn(unsigned long limit_pfn) { int i; unsigned long last_pfn = 0; @@ -759,7 +763,11 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) unsigned long start_pfn; unsigned long end_pfn; - if (ei->type != type) + /* + * Persistent memory is accounted as ram for purposes of + * establishing max_pfn and mem_map. + */ + if (ei->type != E820_RAM && ei->type != E820_PRAM) continue; start_pfn = ei->addr >> PAGE_SHIFT; @@ -784,12 +792,12 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) } unsigned long __init e820_end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); + return e820_end_pfn(MAX_ARCH_PFN); } unsigned long __init e820_end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM); + return e820_end_pfn(1UL << (32-PAGE_SHIFT)); } static void early_panic(char *msg) @@ -866,6 +874,9 @@ static int __init parse_memmap_one(char *p) } else if (*p == '$') { start_at = memparse(p+1, &p); e820_add_region(start_at, mem_size, E820_RESERVED); + } else if (*p == '!') { + start_at = memparse(p+1, &p); + e820_add_region(start_at, mem_size, E820_PRAM); } else e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); @@ -907,6 +918,7 @@ static inline const char *e820_type_to_string(int e820_type) case E820_ACPI: return "ACPI Tables"; case E820_NVS: return "ACPI Non-volatile Storage"; case E820_UNUSABLE: return "Unusable memory"; + case E820_PRAM: return "Persistent RAM"; default: return "reserved"; } } @@ -940,7 +952,9 @@ void __init e820_reserve_resources(void) * pci device BAR resource and insert them later in * pcibios_resource_survey() */ - if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) { + if (((e820.map[i].type != E820_RESERVED) && + (e820.map[i].type != E820_PRAM)) || + res->start < (1ULL<<20)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index a62536a1be88..49ff55ef9b26 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -95,20 +95,6 @@ static unsigned long early_serial_base = 0x3f8; /* ttyS0 */ #define DLL 0 /* Divisor Latch Low */ #define DLH 1 /* Divisor latch High */ -static void mem32_serial_out(unsigned long addr, int offset, int value) -{ - uint32_t *vaddr = (uint32_t *)addr; - /* shift implied by pointer type */ - writel(value, vaddr + offset); -} - -static unsigned int mem32_serial_in(unsigned long addr, int offset) -{ - uint32_t *vaddr = (uint32_t *)addr; - /* shift implied by pointer type */ - return readl(vaddr + offset); -} - static unsigned int io_serial_in(unsigned long addr, int offset) { return inb(addr + offset); @@ -205,6 +191,20 @@ static __init void early_serial_init(char *s) } #ifdef CONFIG_PCI +static void mem32_serial_out(unsigned long addr, int offset, int value) +{ + u32 *vaddr = (u32 *)addr; + /* shift implied by pointer type */ + writel(value, vaddr + offset); +} + +static unsigned int mem32_serial_in(unsigned long addr, int offset) +{ + u32 *vaddr = (u32 *)addr; + /* shift implied by pointer type */ + return readl(vaddr + offset); +} + /* * early_pci_serial_init() * @@ -217,8 +217,8 @@ static __init void early_pci_serial_init(char *s) unsigned divisor; unsigned long baud = DEFAULT_BAUD; u8 bus, slot, func; - uint32_t classcode, bar0; - uint16_t cmdreg; + u32 classcode, bar0; + u16 cmdreg; char *e; diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index 31e2d5bf3e38..1c309763e321 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -395,10 +395,13 @@ sysenter_past_esp: /*CFI_REL_OFFSET cs, 0*/ /* * Push current_thread_info()->sysenter_return to the stack. - * A tiny bit of offset fixup is necessary - 4*4 means the 4 words - * pushed above; +8 corresponds to copy_thread's esp0 setting. + * A tiny bit of offset fixup is necessary: TI_sysenter_return + * is relative to thread_info, which is at the bottom of the + * kernel stack page. 4*4 means the 4 words pushed above; + * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; + * and THREAD_SIZE takes us to the bottom. */ - pushl_cfi ((TI_sysenter_return)-THREAD_SIZE+8+4*4)(%esp) + pushl_cfi ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) CFI_REL_OFFSET eip, 0 pushl_cfi %eax @@ -432,7 +435,7 @@ sysenter_after_call: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $_TIF_ALLWORK_MASK, %ecx - jne sysexit_audit + jnz sysexit_audit sysenter_exit: /* if something modifies registers it must also disable sysexit */ movl PT_EIP(%esp), %edx @@ -460,7 +463,7 @@ sysenter_audit: sysexit_audit: testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jne syscall_exit_work + jnz syscall_exit_work TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_ANY) movl %eax,%edx /* second arg, syscall return value */ @@ -472,7 +475,7 @@ sysexit_audit: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx - jne syscall_exit_work + jnz syscall_exit_work movl PT_EAX(%esp),%eax /* reload syscall return value */ jmp sysenter_exit #endif @@ -510,7 +513,7 @@ syscall_exit: TRACE_IRQS_OFF movl TI_flags(%ebp), %ecx testl $_TIF_ALLWORK_MASK, %ecx # current->work - jne syscall_exit_work + jnz syscall_exit_work restore_all: TRACE_IRQS_IRET @@ -612,7 +615,7 @@ work_notifysig: # deal with pending signals and #ifdef CONFIG_VM86 testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) movl %esp, %eax - jne work_notifysig_v86 # returning to kernel-space or + jnz work_notifysig_v86 # returning to kernel-space or # vm86-space 1: #else @@ -720,43 +723,22 @@ END(sysenter_badsys) .endm /* - * Build the entry stubs and pointer table with some assembler magic. - * We pack 7 stubs into a single 32-byte chunk, which will fit in a - * single cache line on all modern x86 implementations. + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. */ -.section .init.rodata,"a" -ENTRY(interrupt) -.section .entry.text, "ax" - .p2align 5 - .p2align CONFIG_X86_L1_CACHE_SHIFT + .align 8 ENTRY(irq_entries_start) RING0_INT_FRAME -vector=FIRST_EXTERNAL_VECTOR -.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7 - .balign 32 - .rept 7 - .if vector < FIRST_SYSTEM_VECTOR - .if vector <> FIRST_EXTERNAL_VECTOR + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt CFI_ADJUST_CFA_OFFSET -4 - .endif -1: pushl_cfi $(~vector+0x80) /* Note: always in signed byte range */ - .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 - jmp 2f - .endif - .previous - .long 1b - .section .entry.text, "ax" -vector=vector+1 - .endif - .endr -2: jmp common_interrupt -.endr + .align 8 + .endr END(irq_entries_start) -.previous -END(interrupt) -.previous - /* * the CPU automatically disables interrupts when executing an IRQ vector, * so IRQ-flags tracing has to follow that: @@ -816,15 +798,9 @@ ENTRY(simd_coprocessor_error) pushl_cfi $0 #ifdef CONFIG_X86_INVD_BUG /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ -661: pushl_cfi $do_general_protection -662: -.section .altinstructions,"a" - altinstruction_entry 661b, 663f, X86_FEATURE_XMM, 662b-661b, 664f-663f -.previous -.section .altinstr_replacement,"ax" -663: pushl $do_simd_coprocessor_error -664: -.previous + ALTERNATIVE "pushl_cfi $do_general_protection", \ + "pushl $do_simd_coprocessor_error", \ + X86_FEATURE_XMM #else pushl_cfi $do_simd_coprocessor_error #endif @@ -1240,20 +1216,13 @@ error_code: /*CFI_REL_OFFSET es, 0*/ pushl_cfi %ds /*CFI_REL_OFFSET ds, 0*/ - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ebp - CFI_REL_OFFSET ebp, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 + pushl_cfi_reg eax + pushl_cfi_reg ebp + pushl_cfi_reg edi + pushl_cfi_reg esi + pushl_cfi_reg edx + pushl_cfi_reg ecx + pushl_cfi_reg ebx cld movl $(__KERNEL_PERCPU), %ecx movl %ecx, %fs diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index f0095a76c182..c7b238494b31 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -14,27 +14,14 @@ * NOTE: This code handles signal-recognition, which happens every time * after an interrupt and after each system call. * - * Normal syscalls and interrupts don't save a full stack frame, this is - * only done for syscall tracing, signals or fork/exec et.al. - * * A note on terminology: - * - top of stack: Architecture defined interrupt frame from SS to RIP + * - iret frame: Architecture defined interrupt frame from SS to RIP * at the top of the kernel process stack. - * - partial stack frame: partially saved registers up to R11. - * - full stack frame: Like partial stack frame, but all register saved. * * Some macro usage: * - CFI macros are used to generate dwarf2 unwind information for better * backtraces. They don't change any code. - * - SAVE_ALL/RESTORE_ALL - Save/restore all registers - * - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify. - * There are unfortunately lots of special cases where some registers - * not touched. The macro is a big mess that should be cleaned up. - * - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS. - * Gives a full stack frame. * - ENTRY/END Define functions in the symbol table. - * - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack - * frame that is otherwise undefined after a SYSCALL * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. * - idtentry - Define exception entry points. */ @@ -70,10 +57,6 @@ .section .entry.text, "ax" -#ifndef CONFIG_PREEMPT -#define retint_kernel retint_restore_args -#endif - #ifdef CONFIG_PARAVIRT ENTRY(native_usergs_sysret64) swapgs @@ -82,9 +65,9 @@ ENDPROC(native_usergs_sysret64) #endif /* CONFIG_PARAVIRT */ -.macro TRACE_IRQS_IRETQ offset=ARGOFFSET +.macro TRACE_IRQS_IRETQ #ifdef CONFIG_TRACE_IRQFLAGS - bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */ + bt $9,EFLAGS(%rsp) /* interrupts off? */ jnc 1f TRACE_IRQS_ON 1: @@ -116,8 +99,8 @@ ENDPROC(native_usergs_sysret64) call debug_stack_reset .endm -.macro TRACE_IRQS_IRETQ_DEBUG offset=ARGOFFSET - bt $9,EFLAGS-\offset(%rsp) /* interrupts off? */ +.macro TRACE_IRQS_IRETQ_DEBUG + bt $9,EFLAGS(%rsp) /* interrupts off? */ jnc 1f TRACE_IRQS_ON_DEBUG 1: @@ -130,34 +113,7 @@ ENDPROC(native_usergs_sysret64) #endif /* - * C code is not supposed to know about undefined top of stack. Every time - * a C function with an pt_regs argument is called from the SYSCALL based - * fast path FIXUP_TOP_OF_STACK is needed. - * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs - * manipulation. - */ - - /* %rsp:at FRAMEEND */ - .macro FIXUP_TOP_OF_STACK tmp offset=0 - movq PER_CPU_VAR(old_rsp),\tmp - movq \tmp,RSP+\offset(%rsp) - movq $__USER_DS,SS+\offset(%rsp) - movq $__USER_CS,CS+\offset(%rsp) - movq RIP+\offset(%rsp),\tmp /* get rip */ - movq \tmp,RCX+\offset(%rsp) /* copy it to rcx as sysret would do */ - movq R11+\offset(%rsp),\tmp /* get eflags */ - movq \tmp,EFLAGS+\offset(%rsp) - .endm - - .macro RESTORE_TOP_OF_STACK tmp offset=0 - movq RSP+\offset(%rsp),\tmp - movq \tmp,PER_CPU_VAR(old_rsp) - movq EFLAGS+\offset(%rsp),\tmp - movq \tmp,R11+\offset(%rsp) - .endm - -/* - * initial frame state for interrupts (and exceptions without error code) + * empty frame */ .macro EMPTY_FRAME start=1 offset=0 .if \start @@ -173,12 +129,12 @@ ENDPROC(native_usergs_sysret64) * initial frame state for interrupts (and exceptions without error code) */ .macro INTR_FRAME start=1 offset=0 - EMPTY_FRAME \start, SS+8+\offset-RIP - /*CFI_REL_OFFSET ss, SS+\offset-RIP*/ - CFI_REL_OFFSET rsp, RSP+\offset-RIP - /*CFI_REL_OFFSET rflags, EFLAGS+\offset-RIP*/ - /*CFI_REL_OFFSET cs, CS+\offset-RIP*/ - CFI_REL_OFFSET rip, RIP+\offset-RIP + EMPTY_FRAME \start, 5*8+\offset + /*CFI_REL_OFFSET ss, 4*8+\offset*/ + CFI_REL_OFFSET rsp, 3*8+\offset + /*CFI_REL_OFFSET rflags, 2*8+\offset*/ + /*CFI_REL_OFFSET cs, 1*8+\offset*/ + CFI_REL_OFFSET rip, 0*8+\offset .endm /* @@ -186,30 +142,23 @@ ENDPROC(native_usergs_sysret64) * with vector already pushed) */ .macro XCPT_FRAME start=1 offset=0 - INTR_FRAME \start, RIP+\offset-ORIG_RAX - .endm - -/* - * frame that enables calling into C. - */ - .macro PARTIAL_FRAME start=1 offset=0 - XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET - CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET - CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET - CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET - CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET - CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET - CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET - CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET - CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET - CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET + INTR_FRAME \start, 1*8+\offset .endm /* * frame that enables passing a complete pt_regs to a C function. */ .macro DEFAULT_FRAME start=1 offset=0 - PARTIAL_FRAME \start, R11+\offset-R15 + XCPT_FRAME \start, ORIG_RAX+\offset + CFI_REL_OFFSET rdi, RDI+\offset + CFI_REL_OFFSET rsi, RSI+\offset + CFI_REL_OFFSET rdx, RDX+\offset + CFI_REL_OFFSET rcx, RCX+\offset + CFI_REL_OFFSET rax, RAX+\offset + CFI_REL_OFFSET r8, R8+\offset + CFI_REL_OFFSET r9, R9+\offset + CFI_REL_OFFSET r10, R10+\offset + CFI_REL_OFFSET r11, R11+\offset CFI_REL_OFFSET rbx, RBX+\offset CFI_REL_OFFSET rbp, RBP+\offset CFI_REL_OFFSET r12, R12+\offset @@ -218,105 +167,30 @@ ENDPROC(native_usergs_sysret64) CFI_REL_OFFSET r15, R15+\offset .endm -ENTRY(save_paranoid) - XCPT_FRAME 1 RDI+8 - cld - movq %rdi, RDI+8(%rsp) - movq %rsi, RSI+8(%rsp) - movq_cfi rdx, RDX+8 - movq_cfi rcx, RCX+8 - movq_cfi rax, RAX+8 - movq %r8, R8+8(%rsp) - movq %r9, R9+8(%rsp) - movq %r10, R10+8(%rsp) - movq %r11, R11+8(%rsp) - movq_cfi rbx, RBX+8 - movq %rbp, RBP+8(%rsp) - movq %r12, R12+8(%rsp) - movq %r13, R13+8(%rsp) - movq %r14, R14+8(%rsp) - movq %r15, R15+8(%rsp) - movl $1,%ebx - movl $MSR_GS_BASE,%ecx - rdmsr - testl %edx,%edx - js 1f /* negative -> in kernel */ - SWAPGS - xorl %ebx,%ebx -1: ret - CFI_ENDPROC -END(save_paranoid) - /* - * A newly forked process directly context switches into this address. + * 64bit SYSCALL instruction entry. Up to 6 arguments in registers. * - * rdi: prev task we switched from - */ -ENTRY(ret_from_fork) - DEFAULT_FRAME - - LOCK ; btr $TIF_FORK,TI_flags(%r8) - - pushq_cfi $0x0002 - popfq_cfi # reset kernel eflags - - call schedule_tail # rdi: 'prev' task parameter - - GET_THREAD_INFO(%rcx) - - RESTORE_REST - - testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread? - jz 1f - - /* - * 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 - CFI_ADJUST_CFA_OFFSET REST_SKIP - movq %rbp, %rdi - call *%rbx - movl $0, RAX(%rsp) - RESTORE_REST - jmp int_ret_from_sys_call - CFI_ENDPROC -END(ret_from_fork) - -/* - * System call entry. Up to 6 arguments in registers are supported. + * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * then loads new ss, cs, and rip from previously programmed MSRs. + * rflags gets masked by a value from another MSR (so CLD and CLAC + * are not needed). SYSCALL does not save anything on the stack + * and does not change rsp. * - * SYSCALL does not save anything on the stack and does not change the - * stack pointer. However, it does mask the flags register for us, so - * CLD and CLAC are not needed. - */ - -/* - * Register setup: + * Registers on entry: * rax system call number + * rcx return address + * r11 saved rflags (note: r11 is callee-clobbered register in C ABI) * rdi arg0 - * rcx return address for syscall/sysret, C arg3 * rsi arg1 * rdx arg2 - * r10 arg3 (--> moved to rcx for C) + * r10 arg3 (needs to be moved to rcx to conform to C ABI) * r8 arg4 * r9 arg5 - * r11 eflags for syscall/sysret, temporary for C - * r12-r15,rbp,rbx saved by C code, not touched. + * (note: r12-r15,rbp,rbx are callee-preserved in C ABI) * - * Interrupts are off on entry. * Only called from user space. * - * XXX if we had a free scratch register we could save the RSP into the stack frame - * and report it properly in ps. Unfortunately we haven't. - * - * When user can change the frames always force IRET. That is because + * When user can change pt_regs->foo always force IRET. That is because * it deals with uncanonical addresses better. SYSRET has trouble * with them due to bugs in both AMD and Intel CPUs. */ @@ -324,9 +198,15 @@ END(ret_from_fork) ENTRY(system_call) CFI_STARTPROC simple CFI_SIGNAL_FRAME - CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET + CFI_DEF_CFA rsp,0 CFI_REGISTER rip,rcx /*CFI_REGISTER rflags,r11*/ + + /* + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ SWAPGS_UNSAFE_STACK /* * A hypervisor implementation might want to use a label @@ -335,18 +215,38 @@ ENTRY(system_call) */ GLOBAL(system_call_after_swapgs) - movq %rsp,PER_CPU_VAR(old_rsp) + movq %rsp,PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(kernel_stack),%rsp + + /* Construct struct pt_regs on stack */ + pushq_cfi $__USER_DS /* pt_regs->ss */ + pushq_cfi PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ /* - * No need to follow this irqs off/on section - it's straight - * and short: + * Re-enable interrupts. + * We use 'rsp_scratch' as a scratch space, hence irq-off block above + * must execute atomically in the face of possible interrupt-driven + * task preemption. We must enable interrupts only after we're done + * with using rsp_scratch: */ ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_ARGS 8, 0, rax_enosys=1 - movq_cfi rax,(ORIG_RAX-ARGOFFSET) - movq %rcx,RIP-ARGOFFSET(%rsp) - CFI_REL_OFFSET rip,RIP-ARGOFFSET - testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) + pushq_cfi %r11 /* pt_regs->flags */ + pushq_cfi $__USER_CS /* pt_regs->cs */ + pushq_cfi %rcx /* pt_regs->ip */ + CFI_REL_OFFSET rip,0 + pushq_cfi_reg rax /* pt_regs->orig_ax */ + pushq_cfi_reg rdi /* pt_regs->di */ + pushq_cfi_reg rsi /* pt_regs->si */ + pushq_cfi_reg rdx /* pt_regs->dx */ + pushq_cfi_reg rcx /* pt_regs->cx */ + pushq_cfi $-ENOSYS /* pt_regs->ax */ + pushq_cfi_reg r8 /* pt_regs->r8 */ + pushq_cfi_reg r9 /* pt_regs->r9 */ + pushq_cfi_reg r10 /* pt_regs->r10 */ + pushq_cfi_reg r11 /* pt_regs->r11 */ + sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */ + CFI_ADJUST_CFA_OFFSET 6*8 + + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) jnz tracesys system_call_fastpath: #if __SYSCALL_MASK == ~0 @@ -355,18 +255,21 @@ system_call_fastpath: andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja ret_from_sys_call /* and return regs->ax */ + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ movq %r10,%rcx - call *sys_call_table(,%rax,8) # XXX: rip relative - movq %rax,RAX-ARGOFFSET(%rsp) + call *sys_call_table(,%rax,8) + movq %rax,RAX(%rsp) +1: /* - * Syscall return path ending with SYSRET (fast path) - * Has incomplete stack frame and undefined top of stack. + * Syscall return path ending with SYSRET (fast path). + * Has incompletely filled pt_regs. */ -ret_from_sys_call: LOCKDEP_SYS_EXIT + /* + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ DISABLE_INTERRUPTS(CLBR_NONE) - TRACE_IRQS_OFF /* * We must check ti flags with interrupts (or at least preemption) @@ -376,72 +279,73 @@ ret_from_sys_call: * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is * very bad. */ - testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET) - jnz int_ret_from_sys_call_fixup /* Go the the slow path */ + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ CFI_REMEMBER_STATE - /* - * sysretq will re-enable interrupts: - */ - TRACE_IRQS_ON - movq RIP-ARGOFFSET(%rsp),%rcx + + RESTORE_C_REGS_EXCEPT_RCX_R11 + movq RIP(%rsp),%rcx CFI_REGISTER rip,rcx - RESTORE_ARGS 1,-ARG_SKIP,0 + movq EFLAGS(%rsp),%r11 /*CFI_REGISTER rflags,r11*/ - movq PER_CPU_VAR(old_rsp), %rsp + movq RSP(%rsp),%rsp + /* + * 64bit SYSRET restores rip from rcx, + * rflags from r11 (but RF and VM bits are forced to 0), + * cs and ss are loaded from MSRs. + * Restoration of rflags re-enables interrupts. + */ USERGS_SYSRET64 CFI_RESTORE_STATE -int_ret_from_sys_call_fixup: - FIXUP_TOP_OF_STACK %r11, -ARGOFFSET - jmp int_ret_from_sys_call_irqs_off - - /* Do syscall tracing */ + /* Do syscall entry tracing */ tracesys: - leaq -REST_SKIP(%rsp), %rdi - movq $AUDIT_ARCH_X86_64, %rsi + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi call syscall_trace_enter_phase1 test %rax, %rax jnz tracesys_phase2 /* if needed, run the slow path */ - LOAD_ARGS 0 /* else restore clobbered regs */ + RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ + movq ORIG_RAX(%rsp), %rax jmp system_call_fastpath /* and return to the fast path */ tracesys_phase2: - SAVE_REST - FIXUP_TOP_OF_STACK %rdi + SAVE_EXTRA_REGS movq %rsp, %rdi - movq $AUDIT_ARCH_X86_64, %rsi + movl $AUDIT_ARCH_X86_64, %esi movq %rax,%rdx call syscall_trace_enter_phase2 /* - * Reload arg registers from stack in case ptrace changed them. + * Reload registers from stack in case ptrace changed them. * We don't reload %rax because syscall_trace_entry_phase2() returned * the value it wants us to use in the table lookup. */ - LOAD_ARGS ARGOFFSET, 1 - RESTORE_REST + RESTORE_C_REGS_EXCEPT_RAX + RESTORE_EXTRA_REGS #if __SYSCALL_MASK == ~0 cmpq $__NR_syscall_max,%rax #else andl $__SYSCALL_MASK,%eax cmpl $__NR_syscall_max,%eax #endif - ja int_ret_from_sys_call /* RAX(%rsp) is already set */ + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ movq %r10,%rcx /* fixup for C */ call *sys_call_table(,%rax,8) - movq %rax,RAX-ARGOFFSET(%rsp) - /* Use IRET because user could have changed frame */ + movq %rax,RAX(%rsp) +1: + /* Use IRET because user could have changed pt_regs->foo */ /* * Syscall return path ending with IRET. - * Has correct top of stack, but partial stack frame. + * Has correct iret frame. */ GLOBAL(int_ret_from_sys_call) DISABLE_INTERRUPTS(CLBR_NONE) +int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */ TRACE_IRQS_OFF -int_ret_from_sys_call_irqs_off: movl $_TIF_ALLWORK_MASK,%edi /* edi: mask to check */ GLOBAL(int_with_check) @@ -450,8 +354,8 @@ GLOBAL(int_with_check) movl TI_flags(%rcx),%edx andl %edi,%edx jnz int_careful - andl $~TS_COMPAT,TI_status(%rcx) - jmp retint_swapgs + andl $~TS_COMPAT,TI_status(%rcx) + jmp syscall_return /* Either reschedule or signal or syscall exit tracking needed. */ /* First do a reschedule test. */ @@ -468,12 +372,11 @@ int_careful: TRACE_IRQS_OFF jmp int_with_check - /* handle signals and tracing -- both require a full stack frame */ + /* handle signals and tracing -- both require a full pt_regs */ int_very_careful: TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) -int_check_syscall_exit_work: - SAVE_REST + SAVE_EXTRA_REGS /* Check for syscall exit trace */ testl $_TIF_WORK_SYSCALL_EXIT,%edx jz int_signal @@ -492,86 +395,192 @@ int_signal: call do_notify_resume 1: movl $_TIF_WORK_MASK,%edi int_restore_rest: - RESTORE_REST + RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF jmp int_with_check + +syscall_return: + /* The IRETQ could re-enable interrupts: */ + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_IRETQ + + /* + * Try to use SYSRET instead of IRET if we're returning to + * a completely clean 64-bit userspace context. + */ + movq RCX(%rsp),%rcx + cmpq %rcx,RIP(%rsp) /* RCX == RIP */ + jne opportunistic_sysret_failed + + /* + * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP + * in kernel space. This essentially lets the user take over + * the kernel, since userspace controls RSP. It's not worth + * testing for canonicalness exactly -- this check detects any + * of the 17 high bits set, which is true for non-canonical + * or kernel addresses. (This will pessimize vsyscall=native. + * Big deal.) + * + * If virtual addresses ever become wider, this will need + * to be updated to remain correct on both old and new CPUs. + */ + .ifne __VIRTUAL_MASK_SHIFT - 47 + .error "virtual address width changed -- SYSRET checks need update" + .endif + shr $__VIRTUAL_MASK_SHIFT, %rcx + jnz opportunistic_sysret_failed + + cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */ + jne opportunistic_sysret_failed + + movq R11(%rsp),%r11 + cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */ + jne opportunistic_sysret_failed + + /* + * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, + * restoring TF results in a trap from userspace immediately after + * SYSRET. This would cause an infinite loop whenever #DB happens + * with register state that satisfies the opportunistic SYSRET + * conditions. For example, single-stepping this user code: + * + * movq $stuck_here,%rcx + * pushfq + * popq %r11 + * stuck_here: + * + * would never get past 'stuck_here'. + */ + testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 + jnz opportunistic_sysret_failed + + /* nothing to check for RSP */ + + cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */ + jne opportunistic_sysret_failed + + /* + * We win! This label is here just for ease of understanding + * perf profiles. Nothing jumps here. + */ +syscall_return_via_sysret: + CFI_REMEMBER_STATE + /* r11 is already restored (see code above) */ + RESTORE_C_REGS_EXCEPT_R11 + movq RSP(%rsp),%rsp + USERGS_SYSRET64 + CFI_RESTORE_STATE + +opportunistic_sysret_failed: + SWAPGS + jmp restore_c_regs_and_iret CFI_ENDPROC END(system_call) + .macro FORK_LIKE func ENTRY(stub_\func) CFI_STARTPROC - popq %r11 /* save return address */ - PARTIAL_FRAME 0 - SAVE_REST - pushq %r11 /* put it back on stack */ - FIXUP_TOP_OF_STACK %r11, 8 - DEFAULT_FRAME 0 8 /* offset 8: return address */ - call sys_\func - RESTORE_TOP_OF_STACK %r11, 8 - ret $REST_SKIP /* pop extended registers */ + DEFAULT_FRAME 0, 8 /* offset 8: return address */ + SAVE_EXTRA_REGS 8 + jmp sys_\func CFI_ENDPROC END(stub_\func) .endm - .macro FIXED_FRAME label,func -ENTRY(\label) - CFI_STARTPROC - PARTIAL_FRAME 0 8 /* offset 8: return address */ - FIXUP_TOP_OF_STACK %r11, 8-ARGOFFSET - call \func - RESTORE_TOP_OF_STACK %r11, 8-ARGOFFSET - ret - CFI_ENDPROC -END(\label) - .endm - FORK_LIKE clone FORK_LIKE fork FORK_LIKE vfork - FIXED_FRAME stub_iopl, sys_iopl ENTRY(stub_execve) CFI_STARTPROC - addq $8, %rsp - PARTIAL_FRAME 0 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 - call sys_execve - movq %rax,RAX(%rsp) - RESTORE_REST - jmp int_ret_from_sys_call + DEFAULT_FRAME 0, 8 + call sys_execve +return_from_execve: + testl %eax, %eax + jz 1f + /* exec failed, can use fast SYSRET code path in this case */ + ret +1: + /* must use IRET code path (pt_regs->cs may have changed) */ + addq $8, %rsp + CFI_ADJUST_CFA_OFFSET -8 + ZERO_EXTRA_REGS + movq %rax,RAX(%rsp) + jmp int_ret_from_sys_call CFI_ENDPROC END(stub_execve) - -ENTRY(stub_execveat) +/* + * Remaining execve stubs are only 7 bytes long. + * ENTRY() often aligns to 16 bytes, which in this case has no benefits. + */ + .align 8 +GLOBAL(stub_execveat) CFI_STARTPROC - addq $8, %rsp - PARTIAL_FRAME 0 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 - call sys_execveat - RESTORE_TOP_OF_STACK %r11 - movq %rax,RAX(%rsp) - RESTORE_REST - jmp int_ret_from_sys_call + DEFAULT_FRAME 0, 8 + call sys_execveat + jmp return_from_execve CFI_ENDPROC END(stub_execveat) +#ifdef CONFIG_X86_X32_ABI + .align 8 +GLOBAL(stub_x32_execve) + CFI_STARTPROC + DEFAULT_FRAME 0, 8 + call compat_sys_execve + jmp return_from_execve + CFI_ENDPROC +END(stub_x32_execve) + .align 8 +GLOBAL(stub_x32_execveat) + CFI_STARTPROC + DEFAULT_FRAME 0, 8 + call compat_sys_execveat + jmp return_from_execve + CFI_ENDPROC +END(stub_x32_execveat) +#endif + +#ifdef CONFIG_IA32_EMULATION + .align 8 +GLOBAL(stub32_execve) + CFI_STARTPROC + call compat_sys_execve + jmp return_from_execve + CFI_ENDPROC +END(stub32_execve) + .align 8 +GLOBAL(stub32_execveat) + CFI_STARTPROC + call compat_sys_execveat + jmp return_from_execve + CFI_ENDPROC +END(stub32_execveat) +#endif + /* * sigreturn is special because it needs to restore all registers on return. * This cannot be done with SYSRET, so use the IRET return path instead. */ ENTRY(stub_rt_sigreturn) CFI_STARTPROC - addq $8, %rsp - PARTIAL_FRAME 0 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 + DEFAULT_FRAME 0, 8 + /* + * SAVE_EXTRA_REGS result is not normally needed: + * sigreturn overwrites all pt_regs->GPREGS. + * But sigreturn can fail (!), and there is no easy way to detect that. + * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error, + * we SAVE_EXTRA_REGS here. + */ + SAVE_EXTRA_REGS 8 call sys_rt_sigreturn - movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer - RESTORE_REST +return_from_stub: + addq $8, %rsp + CFI_ADJUST_CFA_OFFSET -8 + RESTORE_EXTRA_REGS + movq %rax,RAX(%rsp) jmp int_ret_from_sys_call CFI_ENDPROC END(stub_rt_sigreturn) @@ -579,86 +588,70 @@ END(stub_rt_sigreturn) #ifdef CONFIG_X86_X32_ABI ENTRY(stub_x32_rt_sigreturn) CFI_STARTPROC - addq $8, %rsp - PARTIAL_FRAME 0 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 + DEFAULT_FRAME 0, 8 + SAVE_EXTRA_REGS 8 call sys32_x32_rt_sigreturn - movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer - RESTORE_REST - jmp int_ret_from_sys_call + jmp return_from_stub CFI_ENDPROC END(stub_x32_rt_sigreturn) +#endif -ENTRY(stub_x32_execve) - CFI_STARTPROC - addq $8, %rsp - PARTIAL_FRAME 0 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 - call compat_sys_execve - RESTORE_TOP_OF_STACK %r11 - movq %rax,RAX(%rsp) - RESTORE_REST - jmp int_ret_from_sys_call - CFI_ENDPROC -END(stub_x32_execve) +/* + * A newly forked process directly context switches into this address. + * + * rdi: prev task we switched from + */ +ENTRY(ret_from_fork) + DEFAULT_FRAME -ENTRY(stub_x32_execveat) - CFI_STARTPROC - addq $8, %rsp - PARTIAL_FRAME 0 - SAVE_REST - FIXUP_TOP_OF_STACK %r11 - call compat_sys_execveat - RESTORE_TOP_OF_STACK %r11 - movq %rax,RAX(%rsp) - RESTORE_REST + LOCK ; btr $TIF_FORK,TI_flags(%r8) + + pushq_cfi $0x0002 + popfq_cfi # reset kernel eflags + + call schedule_tail # rdi: 'prev' task parameter + + RESTORE_EXTRA_REGS + + testl $3,CS(%rsp) # from kernel_thread? + + /* + * 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 IRET code path to return, since it can safely handle + * all of the above. + */ + jnz int_ret_from_sys_call + + /* We came from kernel_thread */ + /* nb: we depend on RESTORE_EXTRA_REGS above */ + movq %rbp, %rdi + call *%rbx + movl $0, RAX(%rsp) + RESTORE_EXTRA_REGS jmp int_ret_from_sys_call CFI_ENDPROC -END(stub_x32_execveat) - -#endif +END(ret_from_fork) /* - * Build the entry stubs and pointer table with some assembler magic. - * We pack 7 stubs into a single 32-byte chunk, which will fit in a - * single cache line on all modern x86 implementations. + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. */ - .section .init.rodata,"a" -ENTRY(interrupt) - .section .entry.text - .p2align 5 - .p2align CONFIG_X86_L1_CACHE_SHIFT + .align 8 ENTRY(irq_entries_start) INTR_FRAME -vector=FIRST_EXTERNAL_VECTOR -.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7 - .balign 32 - .rept 7 - .if vector < FIRST_SYSTEM_VECTOR - .if vector <> FIRST_EXTERNAL_VECTOR + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt CFI_ADJUST_CFA_OFFSET -8 - .endif -1: pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */ - .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6 - jmp 2f - .endif - .previous - .quad 1b - .section .entry.text -vector=vector+1 - .endif - .endr -2: jmp common_interrupt -.endr + .align 8 + .endr CFI_ENDPROC END(irq_entries_start) -.previous -END(interrupt) -.previous - /* * Interrupt entry/exit. * @@ -669,47 +662,45 @@ END(interrupt) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func - /* reserve pt_regs for scratch regs and rbp */ - subq $ORIG_RAX-RBP, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP cld - /* start from rbp in pt_regs and jump over */ - movq_cfi rdi, (RDI-RBP) - movq_cfi rsi, (RSI-RBP) - movq_cfi rdx, (RDX-RBP) - movq_cfi rcx, (RCX-RBP) - movq_cfi rax, (RAX-RBP) - movq_cfi r8, (R8-RBP) - movq_cfi r9, (R9-RBP) - movq_cfi r10, (R10-RBP) - movq_cfi r11, (R11-RBP) - - /* Save rbp so that we can unwind from get_irq_regs() */ - movq_cfi rbp, 0 - - /* Save previous stack value */ - movq %rsp, %rsi + /* + * Since nothing in interrupt handling code touches r12...r15 members + * of "struct pt_regs", and since interrupts can nest, we can save + * four stack slots and simultaneously provide + * an unwind-friendly stack layout by saving "truncated" pt_regs + * exactly up to rbp slot, without these members. + */ + ALLOC_PT_GPREGS_ON_STACK -RBP + SAVE_C_REGS -RBP + /* this goes to 0(%rsp) for unwinder, not for saving the value: */ + SAVE_EXTRA_REGS_RBP -RBP - leaq -RBP(%rsp),%rdi /* arg1 for handler */ - testl $3, CS-RBP(%rsi) + leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */ + + testl $3, CS-RBP(%rsp) je 1f SWAPGS +1: /* + * Save previous stack pointer, optionally switch to interrupt stack. * irq_count is used to check if a CPU is already on an interrupt stack * or not. While this is essentially redundant with preempt_count it is * a little cheaper to use a separate counter in the PDA (short of * moving irq_enter into assembly, which would be too much work) */ -1: incl PER_CPU_VAR(irq_count) + movq %rsp, %rsi + incl PER_CPU_VAR(irq_count) cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp CFI_DEF_CFA_REGISTER rsi - - /* Store previous stack value */ pushq %rsi + /* + * For debugger: + * "CFA (Current Frame Address) is the value on stack + offset" + */ CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \ - 0x77 /* DW_OP_breg7 */, 0, \ + 0x77 /* DW_OP_breg7 (rsp) */, 0, \ 0x06 /* DW_OP_deref */, \ - 0x08 /* DW_OP_const1u */, SS+8-RBP, \ + 0x08 /* DW_OP_const1u */, SIZEOF_PTREGS-RBP, \ 0x22 /* DW_OP_plus */ /* We entered an interrupt context - irqs are off: */ TRACE_IRQS_OFF @@ -727,7 +718,7 @@ common_interrupt: ASM_CLAC addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ interrupt do_IRQ - /* 0(%rsp): old_rsp-ARGOFFSET */ + /* 0(%rsp): old RSP */ ret_from_intr: DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF @@ -735,19 +726,18 @@ ret_from_intr: /* Restore saved previous stack */ popq %rsi - CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */ - leaq ARGOFFSET-RBP(%rsi), %rsp + CFI_DEF_CFA rsi,SIZEOF_PTREGS-RBP /* reg/off reset after def_cfa_expr */ + /* return code expects complete pt_regs - adjust rsp accordingly: */ + leaq -RBP(%rsi),%rsp CFI_DEF_CFA_REGISTER rsp - CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET + CFI_ADJUST_CFA_OFFSET RBP -exit_intr: - GET_THREAD_INFO(%rcx) - testl $3,CS-ARGOFFSET(%rsp) + testl $3,CS(%rsp) je retint_kernel - /* Interrupt came from user space */ + + GET_THREAD_INFO(%rcx) /* - * Has a correct top of stack, but a partial stack frame * %rcx: thread info. Interrupts off. */ retint_with_reschedule: @@ -766,84 +756,34 @@ retint_swapgs: /* return to user-space */ DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_IRETQ - /* - * Try to use SYSRET instead of IRET if we're returning to - * a completely clean 64-bit userspace context. - */ - movq (RCX-R11)(%rsp), %rcx - cmpq %rcx,(RIP-R11)(%rsp) /* RCX == RIP */ - jne opportunistic_sysret_failed - - /* - * On Intel CPUs, sysret with non-canonical RCX/RIP will #GP - * in kernel space. This essentially lets the user take over - * the kernel, since userspace controls RSP. It's not worth - * testing for canonicalness exactly -- this check detects any - * of the 17 high bits set, which is true for non-canonical - * or kernel addresses. (This will pessimize vsyscall=native. - * Big deal.) - * - * If virtual addresses ever become wider, this will need - * to be updated to remain correct on both old and new CPUs. - */ - .ifne __VIRTUAL_MASK_SHIFT - 47 - .error "virtual address width changed -- sysret checks need update" - .endif - shr $__VIRTUAL_MASK_SHIFT, %rcx - jnz opportunistic_sysret_failed - - cmpq $__USER_CS,(CS-R11)(%rsp) /* CS must match SYSRET */ - jne opportunistic_sysret_failed - - movq (R11-ARGOFFSET)(%rsp), %r11 - cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp) /* R11 == RFLAGS */ - jne opportunistic_sysret_failed - - /* - * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, - * restoring TF results in a trap from userspace immediately after - * SYSRET. This would cause an infinite loop whenever #DB happens - * with register state that satisfies the opportunistic SYSRET - * conditions. For example, single-stepping this user code: - * - * movq $stuck_here,%rcx - * pushfq - * popq %r11 - * stuck_here: - * - * would never get past 'stuck_here'. - */ - testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz opportunistic_sysret_failed - - /* nothing to check for RSP */ - - cmpq $__USER_DS,(SS-ARGOFFSET)(%rsp) /* SS must match SYSRET */ - jne opportunistic_sysret_failed - - /* - * We win! This label is here just for ease of understanding - * perf profiles. Nothing jumps here. - */ -irq_return_via_sysret: - CFI_REMEMBER_STATE - RESTORE_ARGS 1,8,1 - movq (RSP-RIP)(%rsp),%rsp - USERGS_SYSRET64 - CFI_RESTORE_STATE - -opportunistic_sysret_failed: SWAPGS - jmp restore_args + jmp restore_c_regs_and_iret -retint_restore_args: /* return to kernel space */ - DISABLE_INTERRUPTS(CLBR_ANY) +/* Returning to kernel space */ +retint_kernel: +#ifdef CONFIG_PREEMPT + /* Interrupts are off */ + /* Check if we need preemption */ + bt $9,EFLAGS(%rsp) /* interrupts were off? */ + jnc 1f +0: cmpl $0,PER_CPU_VAR(__preempt_count) + jnz 1f + call preempt_schedule_irq + jmp 0b +1: +#endif /* * The iretq could re-enable interrupts: */ TRACE_IRQS_IRETQ -restore_args: - RESTORE_ARGS 1,8,1 + +/* + * At this label, code paths which return to kernel and to user, + * which come from interrupts/exception and from syscalls, merge. + */ +restore_c_regs_and_iret: + RESTORE_C_REGS + REMOVE_PT_GPREGS_FROM_STACK 8 irq_return: INTERRUPT_RETURN @@ -914,28 +854,17 @@ retint_signal: jz retint_swapgs TRACE_IRQS_ON ENABLE_INTERRUPTS(CLBR_NONE) - SAVE_REST + SAVE_EXTRA_REGS movq $-1,ORIG_RAX(%rsp) xorl %esi,%esi # oldset movq %rsp,%rdi # &pt_regs call do_notify_resume - RESTORE_REST + RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF GET_THREAD_INFO(%rcx) jmp retint_with_reschedule -#ifdef CONFIG_PREEMPT - /* Returning to kernel space. Check if we need preemption */ - /* rcx: threadinfo. interrupts off. */ -ENTRY(retint_kernel) - cmpl $0,PER_CPU_VAR(__preempt_count) - jnz retint_restore_args - bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ - jnc retint_restore_args - call preempt_schedule_irq - jmp exit_intr -#endif CFI_ENDPROC END(common_interrupt) @@ -1024,7 +953,7 @@ apicinterrupt IRQ_WORK_VECTOR \ /* * Exception entry points. */ -#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) @@ -1046,8 +975,7 @@ ENTRY(\sym) pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ .endif - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + ALLOC_PT_GPREGS_ON_STACK .if \paranoid .if \paranoid == 1 @@ -1055,10 +983,11 @@ ENTRY(\sym) testl $3, CS(%rsp) /* If coming from userspace, switch */ jnz 1f /* stacks. */ .endif - call save_paranoid + call paranoid_entry .else call error_entry .endif + /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ DEFAULT_FRAME 0 @@ -1080,19 +1009,20 @@ ENTRY(\sym) .endif .if \shift_ist != -1 - subq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist) + subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) .endif call \do_sym .if \shift_ist != -1 - addq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist) + addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) .endif + /* these procedures expect "no swapgs" flag in ebx */ .if \paranoid - jmp paranoid_exit /* %ebx: no swapgs flag */ + jmp paranoid_exit .else - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit .endif .if \paranoid == 1 @@ -1296,7 +1226,9 @@ ENTRY(xen_failsafe_callback) addq $0x30,%rsp CFI_ADJUST_CFA_OFFSET -0x30 pushq_cfi $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL + ALLOC_PT_GPREGS_ON_STACK + SAVE_C_REGS + SAVE_EXTRA_REGS jmp error_exit CFI_ENDPROC END(xen_failsafe_callback) @@ -1328,59 +1260,66 @@ idtentry async_page_fault do_async_page_fault has_error_code=1 idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) #endif - /* - * "Paranoid" exit path from exception stack. This is invoked - * only on return from non-NMI IST interrupts that came - * from kernel space. - * - * We may be returning to very strange contexts (e.g. very early - * in syscall entry), so checking for preemption here would - * be complicated. Fortunately, we there's no good reason - * to try to handle preemption here. - */ +/* + * Save all registers in pt_regs, and switch gs if needed. + * Use slow, but surefire "are we in kernel?" check. + * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + */ +ENTRY(paranoid_entry) + XCPT_FRAME 1 15*8 + cld + SAVE_C_REGS 8 + SAVE_EXTRA_REGS 8 + movl $1,%ebx + movl $MSR_GS_BASE,%ecx + rdmsr + testl %edx,%edx + js 1f /* negative -> in kernel */ + SWAPGS + xorl %ebx,%ebx +1: ret + CFI_ENDPROC +END(paranoid_entry) - /* ebx: no swapgs flag */ +/* + * "Paranoid" exit path from exception stack. This is invoked + * only on return from non-NMI IST interrupts that came + * from kernel space. + * + * We may be returning to very strange contexts (e.g. very early + * in syscall entry), so checking for preemption here would + * be complicated. Fortunately, we there's no good reason + * to try to handle preemption here. + */ +/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ ENTRY(paranoid_exit) DEFAULT_FRAME DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF_DEBUG testl %ebx,%ebx /* swapgs needed? */ - jnz paranoid_restore - TRACE_IRQS_IRETQ 0 + jnz paranoid_exit_no_swapgs + TRACE_IRQS_IRETQ SWAPGS_UNSAFE_STACK - RESTORE_ALL 8 - INTERRUPT_RETURN -paranoid_restore: - TRACE_IRQS_IRETQ_DEBUG 0 - RESTORE_ALL 8 + jmp paranoid_exit_restore +paranoid_exit_no_swapgs: + TRACE_IRQS_IRETQ_DEBUG +paranoid_exit_restore: + RESTORE_EXTRA_REGS + RESTORE_C_REGS + REMOVE_PT_GPREGS_FROM_STACK 8 INTERRUPT_RETURN CFI_ENDPROC END(paranoid_exit) /* - * Exception entry point. This expects an error code/orig_rax on the stack. - * returns in "no swapgs flag" in %ebx. + * Save all registers in pt_regs, and switch gs if needed. + * Return: ebx=0: need swapgs on exit, ebx=1: otherwise */ ENTRY(error_entry) - XCPT_FRAME - CFI_ADJUST_CFA_OFFSET 15*8 - /* oldrax contains error code */ + XCPT_FRAME 1 15*8 cld - movq %rdi, RDI+8(%rsp) - movq %rsi, RSI+8(%rsp) - movq %rdx, RDX+8(%rsp) - movq %rcx, RCX+8(%rsp) - movq %rax, RAX+8(%rsp) - movq %r8, R8+8(%rsp) - movq %r9, R9+8(%rsp) - movq %r10, R10+8(%rsp) - movq %r11, R11+8(%rsp) - movq_cfi rbx, RBX+8 - movq %rbp, RBP+8(%rsp) - movq %r12, R12+8(%rsp) - movq %r13, R13+8(%rsp) - movq %r14, R14+8(%rsp) - movq %r15, R15+8(%rsp) + SAVE_C_REGS 8 + SAVE_EXTRA_REGS 8 xorl %ebx,%ebx testl $3,CS+8(%rsp) je error_kernelspace @@ -1390,12 +1329,12 @@ error_sti: TRACE_IRQS_OFF ret -/* - * There are two places in the kernel that can potentially fault with - * usergs. Handle them here. B stepping K8s sometimes report a - * truncated RIP for IRET exceptions returning to compat mode. Check - * for these here too. - */ + /* + * There are two places in the kernel that can potentially fault with + * 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: CFI_REL_OFFSET rcx, RCX+8 incl %ebx @@ -1425,11 +1364,11 @@ error_bad_iret: END(error_entry) -/* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */ +/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ ENTRY(error_exit) DEFAULT_FRAME movl %ebx,%eax - RESTORE_REST + RESTORE_EXTRA_REGS DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF GET_THREAD_INFO(%rcx) @@ -1444,19 +1383,7 @@ ENTRY(error_exit) CFI_ENDPROC END(error_exit) -/* - * Test if a given stack is an NMI stack or not. - */ - .macro test_in_nmi reg stack nmi_ret normal_ret - cmpq %\reg, \stack - ja \normal_ret - subq $EXCEPTION_STKSZ, %\reg - cmpq %\reg, \stack - jb \normal_ret - jmp \nmi_ret - .endm - - /* runs on exception stack */ +/* Runs on exception stack */ ENTRY(nmi) INTR_FRAME PARAVIRT_ADJUST_EXCEPTION_FRAME @@ -1492,7 +1419,7 @@ ENTRY(nmi) * NMI. */ - /* Use %rdx as out temp variable throughout */ + /* Use %rdx as our temp variable throughout */ pushq_cfi %rdx CFI_REL_OFFSET rdx, 0 @@ -1517,8 +1444,17 @@ ENTRY(nmi) * We check the variable because the first NMI could be in a * breakpoint routine using a breakpoint stack. */ - lea 6*8(%rsp), %rdx - test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi + lea 6*8(%rsp), %rdx + /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */ + cmpq %rdx, 4*8(%rsp) + /* If the stack pointer is above the NMI stack, this is a normal NMI */ + ja first_nmi + subq $EXCEPTION_STKSZ, %rdx + cmpq %rdx, 4*8(%rsp) + /* If it is below the NMI stack, it is a normal NMI */ + jb first_nmi + /* Ah, it is within the NMI stack, treat it as nested */ + CFI_REMEMBER_STATE nested_nmi: @@ -1611,7 +1547,7 @@ first_nmi: .rept 5 pushq_cfi 11*8(%rsp) .endr - CFI_DEF_CFA_OFFSET SS+8-RIP + CFI_DEF_CFA_OFFSET 5*8 /* Everything up to here is safe from nested NMIs */ @@ -1639,7 +1575,7 @@ repeat_nmi: pushq_cfi -6*8(%rsp) .endr subq $(5*8), %rsp - CFI_DEF_CFA_OFFSET SS+8-RIP + CFI_DEF_CFA_OFFSET 5*8 end_repeat_nmi: /* @@ -1648,16 +1584,16 @@ end_repeat_nmi: * so that we repeat another NMI. */ pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + ALLOC_PT_GPREGS_ON_STACK + /* - * Use save_paranoid to handle SWAPGS, but no need to use paranoid_exit + * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit * as we should not be calling schedule in NMI context. * Even with normal interrupts enabled. An NMI should not be * setting NEED_RESCHED or anything that normal interrupts and * exceptions might do. */ - call save_paranoid + call paranoid_entry DEFAULT_FRAME 0 /* @@ -1688,8 +1624,10 @@ end_repeat_nmi: nmi_swapgs: SWAPGS_UNSAFE_STACK nmi_restore: + RESTORE_EXTRA_REGS + RESTORE_C_REGS /* Pop the extra iret frame at once */ - RESTORE_ALL 6*8 + REMOVE_PT_GPREGS_FROM_STACK 6*8 /* Clear the NMI executing stack variable */ movq $0, 5*8(%rsp) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index c4f8d4659070..2b55ee6db053 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -177,9 +177,6 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) - early_printk("Kernel alive\n"); - clear_page(init_level4_pgt); /* set init_level4_pgt kernel high mapping*/ init_level4_pgt[511] = early_level4_pgt[511]; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index f36bd42d6f0c..d031bad9e07e 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -22,6 +22,7 @@ #include <asm/cpufeature.h> #include <asm/percpu.h> #include <asm/nops.h> +#include <asm/bootparam.h> /* Physical address */ #define pa(X) ((X) - __PAGE_OFFSET) @@ -90,7 +91,7 @@ ENTRY(startup_32) /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ - testb $(1<<6), BP_loadflags(%esi) + testb $KEEP_SEGMENTS, BP_loadflags(%esi) jnz 2f /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6fd514d9f69a..ae6588b301c2 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -1,5 +1,5 @@ /* - * linux/arch/x86_64/kernel/head.S -- start in 32bit and switch to 64bit + * linux/arch/x86/kernel/head_64.S -- start in 32bit and switch to 64bit * * Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> @@ -56,7 +56,7 @@ startup_64: * %rsi holds a physical pointer to real_mode_data. * * We come here either directly from a 64bit bootloader, or from - * arch/x86_64/boot/compressed/head.S. + * arch/x86/boot/compressed/head_64.S. * * We only come here initially at boot nothing else comes here. * @@ -146,7 +146,7 @@ startup_64: leaq level2_kernel_pgt(%rip), %rdi leaq 4096(%rdi), %r8 /* See if it is a valid page table entry */ -1: testq $1, 0(%rdi) +1: testb $1, 0(%rdi) jz 2f addq %rbp, 0(%rdi) /* Go to the next page */ diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index d5651fce0b71..009183276bb7 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -42,8 +42,8 @@ void kernel_fpu_enable(void) * be set (so that the clts/stts pair does nothing that is * visible in the interrupted kernel thread). * - * Except for the eagerfpu case when we return 1 unless we've already - * been eager and saved the state in kernel_fpu_begin(). + * Except for the eagerfpu case when we return true; in the likely case + * the thread has FPU but we are not going to set/clear TS. */ static inline bool interrupted_kernel_fpu_idle(void) { @@ -51,7 +51,7 @@ static inline bool interrupted_kernel_fpu_idle(void) return false; if (use_eager_fpu()) - return __thread_has_fpu(current); + return true; return !__thread_has_fpu(current) && (read_cr0() & X86_CR0_TS); @@ -68,7 +68,7 @@ static inline bool interrupted_kernel_fpu_idle(void) static inline bool interrupted_user_mode(void) { struct pt_regs *regs = get_irq_regs(); - return regs && user_mode_vm(regs); + return regs && user_mode(regs); } /* @@ -94,9 +94,10 @@ void __kernel_fpu_begin(void) if (__thread_has_fpu(me)) { __save_init_fpu(me); - } else if (!use_eager_fpu()) { + } else { this_cpu_write(fpu_owner_task, NULL); - clts(); + if (!use_eager_fpu()) + clts(); } } EXPORT_SYMBOL(__kernel_fpu_begin); @@ -107,7 +108,7 @@ void __kernel_fpu_end(void) if (__thread_has_fpu(me)) { if (WARN_ON(restore_fpu_checking(me))) - drop_init_fpu(me); + fpu_reset_state(me); } else if (!use_eager_fpu()) { stts(); } @@ -120,10 +121,13 @@ void unlazy_fpu(struct task_struct *tsk) { preempt_disable(); if (__thread_has_fpu(tsk)) { - __save_init_fpu(tsk); - __thread_fpu_end(tsk); - } else - tsk->thread.fpu_counter = 0; + if (use_eager_fpu()) { + __save_fpu(tsk); + } else { + __save_init_fpu(tsk); + __thread_fpu_end(tsk); + } + } preempt_enable(); } EXPORT_SYMBOL(unlazy_fpu); @@ -221,11 +225,12 @@ void fpu_finit(struct fpu *fpu) return; } + memset(fpu->state, 0, xstate_size); + if (cpu_has_fxsr) { fx_finit(&fpu->state->fxsave); } else { struct i387_fsave_struct *fp = &fpu->state->fsave; - memset(fp, 0, xstate_size); fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; @@ -247,7 +252,7 @@ int init_fpu(struct task_struct *tsk) if (tsk_used_math(tsk)) { if (cpu_has_fpu && tsk == current) unlazy_fpu(tsk); - tsk->thread.fpu.last_cpu = ~0; + task_disable_lazy_fpu_restore(tsk); return 0; } @@ -336,6 +341,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + struct xsave_struct *xsave; int ret; if (!cpu_has_xsave) @@ -345,19 +351,19 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; + xsave = &target->thread.fpu.state->xsave; + /* * Copy the 48bytes defined by the software first into the xstate * memory layout in the thread struct, so that we can copy the entire * xstateregs to the user using one user_regset_copyout(). */ - memcpy(&target->thread.fpu.state->fxsave.sw_reserved, - xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); - + memcpy(&xsave->i387.sw_reserved, + xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); /* * Copy the xstate memory layout. */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->xsave, 0, -1); + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); return ret; } @@ -365,8 +371,8 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { + struct xsave_struct *xsave; int ret; - struct xsave_hdr_struct *xsave_hdr; if (!cpu_has_xsave) return -ENODEV; @@ -375,22 +381,18 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &target->thread.fpu.state->xsave, 0, -1); + xsave = &target->thread.fpu.state->xsave; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. */ - target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask; - - xsave_hdr = &target->thread.fpu.state->xsave.xsave_hdr; - - xsave_hdr->xstate_bv &= pcntxt_mask; + xsave->i387.mxcsr &= mxcsr_feature_mask; + xsave->xsave_hdr.xstate_bv &= pcntxt_mask; /* * These bits must be zero. */ - memset(xsave_hdr->reserved, 0, 48); - + memset(&xsave->xsave_hdr.reserved, 0, 48); return ret; } diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 4ddaf66ea35f..37dae792dbbe 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -54,7 +54,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * because the ->io_bitmap_max value must match the bitmap * contents: */ - tss = &per_cpu(init_tss, get_cpu()); + tss = &per_cpu(cpu_tss, get_cpu()); if (turn_on) bitmap_clear(t->io_bitmap_ptr, from, num); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 67b1cbe0093a..e5952c225532 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -295,7 +295,7 @@ int check_irq_vectors_for_cpu_disable(void) this_cpu = smp_processor_id(); cpumask_copy(&online_new, cpu_online_mask); - cpu_clear(this_cpu, online_new); + cpumask_clear_cpu(this_cpu, &online_new); this_count = 0; for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { @@ -307,7 +307,7 @@ int check_irq_vectors_for_cpu_disable(void) data = irq_desc_get_irq_data(desc); cpumask_copy(&affinity_new, data->affinity); - cpu_clear(this_cpu, affinity_new); + cpumask_clear_cpu(this_cpu, &affinity_new); /* Do not count inactive or per-cpu irqs. */ if (!irq_has_action(irq) || irqd_is_per_cpu(data)) diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 28d28f5eb8f4..f9fd86a7fcc7 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -165,7 +165,7 @@ bool handle_irq(unsigned irq, struct pt_regs *regs) if (unlikely(!desc)) return false; - if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) { + if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) { if (unlikely(overflow)) print_stack_overflow(); desc->handle_irq(irq, desc); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index e4b503d5558c..394e643d7830 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -44,7 +44,7 @@ static inline void stack_overflow_check(struct pt_regs *regs) u64 estack_top, estack_bottom; u64 curbase = (u64)task_stack_page(current); - if (user_mode_vm(regs)) + if (user_mode(regs)) return; if (regs->sp >= curbase + sizeof(struct thread_info) + diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 70e181ea1eac..cd10a6437264 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -178,7 +178,8 @@ void __init native_init_IRQ(void) #endif for_each_clear_bit_from(i, used_vectors, first_system_vector) { /* IA32_SYSCALL_VECTOR could be used in trap_init already. */ - set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); + set_intr_gate(i, irq_entries_start + + 8 * (i - FIRST_EXTERNAL_VECTOR)); } #ifdef CONFIG_X86_LOCAL_APIC for_each_clear_bit_from(i, used_vectors, NR_VECTORS) diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 25ecd56cefa8..d6178d9791db 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -126,11 +126,11 @@ char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) #ifdef CONFIG_X86_32 switch (regno) { case GDB_SS: - if (!user_mode_vm(regs)) + if (!user_mode(regs)) *(unsigned long *)mem = __KERNEL_DS; break; case GDB_SP: - if (!user_mode_vm(regs)) + if (!user_mode(regs)) *(unsigned long *)mem = kernel_stack_pointer(regs); break; case GDB_GS: diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 4e3d5a9621fe..1deffe6cc873 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -354,6 +354,7 @@ int __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; + int length; unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src); @@ -361,16 +362,18 @@ int __copy_instruction(u8 *dest, u8 *src) return 0; kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); + length = insn.length; + /* Another subsystem puts a breakpoint, failed to recover */ if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) return 0; - memcpy(dest, insn.kaddr, insn.length); + memcpy(dest, insn.kaddr, length); #ifdef CONFIG_X86_64 if (insn_rip_relative(&insn)) { s64 newdisp; u8 *disp; - kernel_insn_init(&insn, dest, insn.length); + kernel_insn_init(&insn, dest, length); insn_get_displacement(&insn); /* * The copied instruction uses the %rip-relative addressing @@ -394,7 +397,7 @@ int __copy_instruction(u8 *dest, u8 *src) *(s32 *) disp = (s32) newdisp; } #endif - return insn.length; + return length; } static int arch_copy_kprobe(struct kprobe *p) @@ -602,7 +605,7 @@ int kprobe_int3_handler(struct pt_regs *regs) struct kprobe *p; struct kprobe_ctlblk *kcb; - if (user_mode_vm(regs)) + if (user_mode(regs)) return 0; addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t)); @@ -1007,7 +1010,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, struct die_args *args = data; int ret = NOTIFY_DONE; - if (args->regs && user_mode_vm(args->regs)) + if (args->regs && user_mode(args->regs)) return ret; if (val == DIE_GPF) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index e354cc6446ab..9435620062df 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -513,7 +513,7 @@ void __init kvm_guest_init(void) * can get false positives too easily, for example if the host is * overcommitted. */ - watchdog_enable_hardlockup_detector(false); + hardlockup_detector_disable(); } static noinline uint32_t __kvm_cpuid_base(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index d1ac80b72c72..005c03e93fc5 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -33,6 +33,7 @@ #include <asm/page.h> #include <asm/pgtable.h> +#include <asm/setup.h> #if 0 #define DEBUGP(fmt, ...) \ @@ -47,21 +48,13 @@ do { \ #ifdef CONFIG_RANDOMIZE_BASE static unsigned long module_load_offset; -static int randomize_modules = 1; /* Mutex protects the module_load_offset. */ static DEFINE_MUTEX(module_kaslr_mutex); -static int __init parse_nokaslr(char *p) -{ - randomize_modules = 0; - return 0; -} -early_param("nokaslr", parse_nokaslr); - static unsigned long int get_module_load_offset(void) { - if (randomize_modules) { + if (kaslr_enabled()) { mutex_lock(&module_kaslr_mutex); /* * Calculate the module_load_offset the first time this diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 548d25f00c90..c614dd492f5f 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -443,7 +443,7 @@ struct pv_mmu_ops pv_mmu_ops = { .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, -#if PAGETABLE_LEVELS >= 3 +#if CONFIG_PGTABLE_LEVELS >= 3 #ifdef CONFIG_X86_PAE .set_pte_atomic = native_set_pte_atomic, .pte_clear = native_pte_clear, @@ -454,13 +454,13 @@ struct pv_mmu_ops pv_mmu_ops = { .pmd_val = PTE_IDENT, .make_pmd = PTE_IDENT, -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 .pud_val = PTE_IDENT, .make_pud = PTE_IDENT, .set_pgd = native_set_pgd, #endif -#endif /* PAGETABLE_LEVELS >= 3 */ +#endif /* CONFIG_PGTABLE_LEVELS >= 3 */ .pte_val = PTE_IDENT, .pgd_val = PTE_IDENT, diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index 781861cc5ee8..da8cb987b973 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -131,10 +131,11 @@ void perf_get_regs_user(struct perf_regs *regs_user, } /* - * RIP, flags, and the argument registers are usually saved. - * orig_ax is probably okay, too. + * These registers are always saved on 64-bit syscall entry. + * On 32-bit entry points, they are saved too except r8..r11. */ regs_user_copy->ip = user_regs->ip; + regs_user_copy->ax = user_regs->ax; regs_user_copy->cx = user_regs->cx; regs_user_copy->dx = user_regs->dx; regs_user_copy->si = user_regs->si; @@ -145,9 +146,12 @@ void perf_get_regs_user(struct perf_regs *regs_user, regs_user_copy->r11 = user_regs->r11; regs_user_copy->orig_ax = user_regs->orig_ax; regs_user_copy->flags = user_regs->flags; + regs_user_copy->sp = user_regs->sp; + regs_user_copy->cs = user_regs->cs; + regs_user_copy->ss = user_regs->ss; /* - * Don't even try to report the "rest" regs. + * Most system calls don't save these registers, don't report them. */ regs_user_copy->bx = -1; regs_user_copy->bp = -1; @@ -158,37 +162,13 @@ void perf_get_regs_user(struct perf_regs *regs_user, /* * For this to be at all useful, we need a reasonable guess for - * sp and the ABI. Be careful: we're in NMI context, and we're + * the ABI. Be careful: we're in NMI context, and we're * considering current to be the current task, so we should * be careful not to look at any other percpu variables that might * change during context switches. */ - if (IS_ENABLED(CONFIG_IA32_EMULATION) && - task_thread_info(current)->status & TS_COMPAT) { - /* Easy case: we're in a compat syscall. */ - regs_user->abi = PERF_SAMPLE_REGS_ABI_32; - regs_user_copy->sp = user_regs->sp; - regs_user_copy->cs = user_regs->cs; - regs_user_copy->ss = user_regs->ss; - } else if (user_regs->orig_ax != -1) { - /* - * We're probably in a 64-bit syscall. - * Warning: this code is severely racy. At least it's better - * than just blindly copying user_regs. - */ - regs_user->abi = PERF_SAMPLE_REGS_ABI_64; - regs_user_copy->sp = this_cpu_read(old_rsp); - regs_user_copy->cs = __USER_CS; - regs_user_copy->ss = __USER_DS; - regs_user_copy->cx = -1; /* usually contains garbage */ - } else { - /* We're probably in an interrupt or exception. */ - regs_user->abi = user_64bit_mode(user_regs) ? - PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32; - regs_user_copy->sp = user_regs->sp; - regs_user_copy->cs = user_regs->cs; - regs_user_copy->ss = user_regs->ss; - } + regs_user->abi = user_64bit_mode(user_regs) ? + PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32; regs_user->regs = regs_user_copy; } diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c new file mode 100644 index 000000000000..3420c874ddc5 --- /dev/null +++ b/arch/x86/kernel/pmem.c @@ -0,0 +1,53 @@ +/* + * Copyright (c) 2015, Christoph Hellwig. + */ +#include <linux/memblock.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <asm/e820.h> +#include <asm/page_types.h> +#include <asm/setup.h> + +static __init void register_pmem_device(struct resource *res) +{ + struct platform_device *pdev; + int error; + + pdev = platform_device_alloc("pmem", PLATFORM_DEVID_AUTO); + if (!pdev) + return; + + error = platform_device_add_resources(pdev, res, 1); + if (error) + goto out_put_pdev; + + error = platform_device_add(pdev); + if (error) + goto out_put_pdev; + return; + +out_put_pdev: + dev_warn(&pdev->dev, "failed to add 'pmem' (persistent memory) device!\n"); + platform_device_put(pdev); +} + +static __init int register_pmem_devices(void) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + if (ei->type == E820_PRAM) { + struct resource res = { + .flags = IORESOURCE_MEM, + .start = ei->addr, + .end = ei->addr + ei->size - 1, + }; + register_pmem_device(&res); + } + } + + return 0; +} +device_initcall(register_pmem_devices); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 046e2d620bbe..8213da62b1b7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -9,7 +9,7 @@ #include <linux/sched.h> #include <linux/module.h> #include <linux/pm.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <linux/random.h> #include <linux/user-return-notifier.h> #include <linux/dmi.h> @@ -24,6 +24,7 @@ #include <asm/syscalls.h> #include <asm/idle.h> #include <asm/uaccess.h> +#include <asm/mwait.h> #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/debugreg.h> @@ -37,7 +38,26 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { + .x86_tss = { + .sp0 = TOP_OF_INIT_STACK, +#ifdef CONFIG_X86_32 + .ss0 = __KERNEL_DS, + .ss1 = __KERNEL_CS, + .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, +#endif + }, +#ifdef CONFIG_X86_32 + /* + * Note that the .io_bitmap member must be extra-big. This is because + * the CPU will access an additional byte beyond the end of the IO + * permission bitmap. The extra byte must be all 1 bits, and must + * be within the limit. + */ + .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, +#endif +}; +EXPORT_PER_CPU_SYMBOL_GPL(cpu_tss); #ifdef CONFIG_X86_64 static DEFINE_PER_CPU(unsigned char, is_idle); @@ -69,8 +89,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) dst->thread.fpu_counter = 0; dst->thread.fpu.has_fpu = 0; - dst->thread.fpu.last_cpu = ~0; dst->thread.fpu.state = NULL; + task_disable_lazy_fpu_restore(dst); if (tsk_used_math(src)) { int err = fpu_alloc(&dst->thread.fpu); if (err) @@ -109,7 +129,7 @@ void exit_thread(void) unsigned long *bp = t->io_bitmap_ptr; if (bp) { - struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); + struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); t->io_bitmap_ptr = NULL; clear_thread_flag(TIF_IO_BITMAP); @@ -131,13 +151,18 @@ void flush_thread(void) flush_ptrace_hw_breakpoint(tsk); memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - drop_init_fpu(tsk); - /* - * Free the FPU state for non xsave platforms. They get reallocated - * lazily at the first use. - */ - if (!use_eager_fpu()) + + if (!use_eager_fpu()) { + /* FPU state will be reallocated lazily at the first use. */ + drop_fpu(tsk); free_thread_xstate(tsk); + } else if (!used_math()) { + /* kthread execs. TODO: cleanup this horror. */ + if (WARN_ON(init_fpu(tsk))) + force_sig(SIGKILL, tsk); + user_fpu_begin(); + restore_init_xstate(); + } } static void hard_disable_TSC(void) @@ -377,14 +402,11 @@ static void amd_e400_idle(void) if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) { cpumask_set_cpu(cpu, amd_e400_c1e_mask); - /* - * Force broadcast so ACPI can not interfere. - */ - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE, - &cpu); + /* Force broadcast so ACPI can not interfere. */ + tick_broadcast_force(); pr_info("Switch to broadcast mode on CPU%d\n", cpu); } - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu); + tick_broadcast_enter(); default_idle(); @@ -393,12 +415,59 @@ static void amd_e400_idle(void) * called with interrupts disabled. */ local_irq_disable(); - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu); + tick_broadcast_exit(); local_irq_enable(); } else default_idle(); } +/* + * Intel Core2 and older machines prefer MWAIT over HALT for C1. + * We can't rely on cpuidle installing MWAIT, because it will not load + * on systems that support only C1 -- so the boot default must be MWAIT. + * + * Some AMD machines are the opposite, they depend on using HALT. + * + * So for default C1, which is used during boot until cpuidle loads, + * use MWAIT-C1 on Intel HW that has it, else use HALT. + */ +static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +{ + if (c->x86_vendor != X86_VENDOR_INTEL) + return 0; + + if (!cpu_has(c, X86_FEATURE_MWAIT)) + return 0; + + return 1; +} + +/* + * MONITOR/MWAIT with no hints, used for default default C1 state. + * This invokes MWAIT with interrutps enabled and no flags, + * which is backwards compatible with the original MWAIT implementation. + */ + +static void mwait_idle(void) +{ + if (!current_set_polling_and_test()) { + if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) { + smp_mb(); /* quirk */ + clflush((void *)¤t_thread_info()->flags); + smp_mb(); /* quirk */ + } + + __monitor((void *)¤t_thread_info()->flags, 0, 0); + if (!need_resched()) + __sti_mwait(0, 0); + else + local_irq_enable(); + } else { + local_irq_enable(); + } + __current_clr_polling(); +} + void select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP @@ -412,6 +481,9 @@ void select_idle_routine(const struct cpuinfo_x86 *c) /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; + } else if (prefer_mwait_c1_over_halt(c)) { + pr_info("using mwait in idle threads\n"); + x86_idle = mwait_idle; } else x86_idle = default_idle; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 603c4f99cb5a..8ed2106b06da 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -73,7 +73,7 @@ void __show_regs(struct pt_regs *regs, int all) unsigned long sp; unsigned short ss, gs; - if (user_mode_vm(regs)) { + if (user_mode(regs)) { sp = regs->sp; ss = regs->ss & 0xffff; gs = get_user_gs(regs); @@ -206,11 +206,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->ip = new_ip; regs->sp = new_sp; regs->flags = X86_EFLAGS_IF; - /* - * force it to the iret return path by making it look as if there was - * some work pending. - */ - set_thread_flag(TIF_NOTIFY_RESUME); + force_iret(); } EXPORT_SYMBOL_GPL(start_thread); @@ -248,7 +244,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct thread_struct *prev = &prev_p->thread, *next = &next_p->thread; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss, cpu); fpu_switch_t fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ @@ -256,11 +252,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) fpu = switch_fpu_prepare(prev_p, next_p, cpu); /* - * Reload esp0. - */ - load_sp0(tss, next); - - /* * Save away %gs. No need to save %fs, as it was saved on the * stack on entry. No need to save %es and %ds, as those are * always kernel segments while inside the kernel. Doing this @@ -310,9 +301,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); + /* + * Reload esp0, kernel_stack, and current_top_of_stack. This changes + * current_thread_info(). + */ + load_sp0(tss, next); this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + - THREAD_SIZE - KERNEL_STACK_OFFSET); + (unsigned long)task_stack_page(next_p) + + THREAD_SIZE); + this_cpu_write(cpu_current_top_of_stack, + (unsigned long)task_stack_page(next_p) + + THREAD_SIZE); /* * Restore %gs if needed (which is common) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 67fcc43577d2..4baaa972f52a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ asmlinkage extern void ret_from_fork(void); -__visible DEFINE_PER_CPU(unsigned long, old_rsp); +__visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) @@ -161,7 +161,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; childregs = task_pt_regs(p); p->thread.sp = (unsigned long) childregs; - p->thread.usersp = me->thread.usersp; set_tsk_thread_flag(p, TIF_FORK); p->thread.io_bitmap_ptr = NULL; @@ -207,7 +206,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, */ if (clone_flags & CLONE_SETTLS) { #ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_IA32)) + if (is_ia32_task()) err = do_set_thread_area(p, -1, (struct user_desc __user *)childregs->si, 0); else @@ -235,13 +234,12 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, loadsegment(es, _ds); loadsegment(ds, _ds); load_gs_index(0); - current->thread.usersp = new_sp; regs->ip = new_ip; regs->sp = new_sp; - this_cpu_write(old_rsp, new_sp); regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; + force_iret(); } void @@ -277,15 +275,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss, cpu); unsigned fsindex, gsindex; fpu_switch_t fpu; fpu = switch_fpu_prepare(prev_p, next_p, cpu); - /* Reload esp0 and ss1. */ - load_sp0(tss, next); - /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). * @@ -401,8 +396,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Switch the PDA and FPU contexts. */ - prev->usersp = this_cpu_read(old_rsp); - this_cpu_write(old_rsp, next->usersp); this_cpu_write(current_task, next_p); /* @@ -413,9 +406,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count); this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count); + /* Reload esp0 and ss1. This changes current_thread_info(). */ + load_sp0(tss, next); + this_cpu_write(kernel_stack, - (unsigned long)task_stack_page(next_p) + - THREAD_SIZE - KERNEL_STACK_OFFSET); + (unsigned long)task_stack_page(next_p) + THREAD_SIZE); /* * Now maybe reload the debug registers and handle I/O bitmaps @@ -602,6 +597,5 @@ long sys_arch_prctl(int code, unsigned long addr) unsigned long KSTK_ESP(struct task_struct *task) { - return (test_tsk_thread_flag(task, TIF_IA32)) ? - (task_pt_regs(task)->sp) : ((task)->thread.usersp); + return task_pt_regs(task)->sp; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index e510618b2e91..a7bc79480719 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -364,18 +364,12 @@ static int set_segment_reg(struct task_struct *task, case offsetof(struct user_regs_struct,cs): if (unlikely(value == 0)) return -EIO; -#ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(task, TIF_IA32)) - task_pt_regs(task)->cs = value; -#endif + task_pt_regs(task)->cs = value; break; case offsetof(struct user_regs_struct,ss): if (unlikely(value == 0)) return -EIO; -#ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(task, TIF_IA32)) - task_pt_regs(task)->ss = value; -#endif + task_pt_regs(task)->ss = value; break; } @@ -1421,7 +1415,7 @@ static void fill_sigtrap_info(struct task_struct *tsk, memset(info, 0, sizeof(*info)); info->si_signo = SIGTRAP; info->si_code = si_code; - info->si_addr = user_mode_vm(regs) ? (void __user *)regs->ip : NULL; + info->si_addr = user_mode(regs) ? (void __user *)regs->ip : NULL; } void user_single_step_siginfo(struct task_struct *tsk, diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..e5ecd20e72dd 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } +static struct pvclock_vsyscall_time_info *pvclock_vdso_info; + +static struct pvclock_vsyscall_time_info * +pvclock_get_vsyscall_user_time_info(int cpu) +{ + if (!pvclock_vdso_info) { + BUG(); + return NULL; + } + + return &pvclock_vdso_info[cpu]; +} + +struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) +{ + return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; +} + #ifdef CONFIG_X86_64 +static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, + void *v) +{ + struct task_migration_notifier *mn = v; + struct pvclock_vsyscall_time_info *pvti; + + pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); + + /* this is NULL when pvclock vsyscall is not initialized */ + if (unlikely(pvti == NULL)) + return NOTIFY_DONE; + + pvti->migrate_count++; + + return NOTIFY_DONE; +} + +static struct notifier_block pvclock_migrate = { + .notifier_call = pvclock_task_migrate, +}; + /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); + pvclock_vdso_info = i; + for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } + + register_task_migration_notifier(&pvclock_migrate); + return 0; } #endif diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index e13f8e7c22a6..77630d57e7bf 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -226,23 +226,23 @@ swap_pages: movl (%ebx), %ecx addl $4, %ebx 1: - testl $0x1, %ecx /* is it a destination page */ + testb $0x1, %cl /* is it a destination page */ jz 2f movl %ecx, %edi andl $0xfffff000, %edi jmp 0b 2: - testl $0x2, %ecx /* is it an indirection page */ + testb $0x2, %cl /* is it an indirection page */ jz 2f movl %ecx, %ebx andl $0xfffff000, %ebx jmp 0b 2: - testl $0x4, %ecx /* is it the done indicator */ + testb $0x4, %cl /* is it the done indicator */ jz 2f jmp 3f 2: - testl $0x8, %ecx /* is it the source indicator */ + testb $0x8, %cl /* is it the source indicator */ jz 0b /* Ignore it otherwise */ movl %ecx, %esi /* For every source page do a copy */ andl $0xfffff000, %esi diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 3fd2c693e475..98111b38ebfd 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -123,7 +123,7 @@ identity_mapped: * Set cr4 to a known state: * - physical address extension enabled */ - movq $X86_CR4_PAE, %rax + movl $X86_CR4_PAE, %eax movq %rax, %cr4 jmp 1f @@ -221,23 +221,23 @@ swap_pages: movq (%rbx), %rcx addq $8, %rbx 1: - testq $0x1, %rcx /* is it a destination page? */ + testb $0x1, %cl /* is it a destination page? */ jz 2f movq %rcx, %rdi andq $0xfffffffffffff000, %rdi jmp 0b 2: - testq $0x2, %rcx /* is it an indirection page? */ + testb $0x2, %cl /* is it an indirection page? */ jz 2f movq %rcx, %rbx andq $0xfffffffffffff000, %rbx jmp 0b 2: - testq $0x4, %rcx /* is it the done indicator? */ + testb $0x4, %cl /* is it the done indicator? */ jz 2f jmp 3f 2: - testq $0x8, %rcx /* is it the source indicator? */ + testb $0x8, %cl /* is it the source indicator? */ jz 0b /* Ignore it otherwise */ movq %rcx, %rsi /* For ever source page do a copy */ andq $0xfffffffffffff000, %rsi @@ -246,17 +246,17 @@ swap_pages: movq %rsi, %rax movq %r10, %rdi - movq $512, %rcx + movl $512, %ecx rep ; movsq movq %rax, %rdi movq %rdx, %rsi - movq $512, %rcx + movl $512, %ecx rep ; movsq movq %rdx, %rdi movq %r10, %rsi - movq $512, %rcx + movl $512, %ecx rep ; movsq lea PAGE_SIZE(%rax), %rsi diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 0a2421cca01f..d74ac33290ae 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -354,7 +354,7 @@ static void __init relocate_initrd(void) mapaddr = ramdisk_image & PAGE_MASK; p = early_memremap(mapaddr, clen+slop); memcpy(q, p+slop, clen); - early_iounmap(p, clen+slop); + early_memunmap(p, clen+slop); q += clen; ramdisk_image += clen; ramdisk_size -= clen; @@ -438,7 +438,7 @@ static void __init parse_setup_data(void) data_len = data->len + sizeof(struct setup_data); data_type = data->type; pa_next = data->next; - early_iounmap(data, sizeof(*data)); + early_memunmap(data, sizeof(*data)); switch (data_type) { case SETUP_E820_EXT: @@ -470,7 +470,7 @@ static void __init e820_reserve_setup_data(void) E820_RAM, E820_RESERVED_KERN); found = 1; pa_data = data->next; - early_iounmap(data, sizeof(*data)); + early_memunmap(data, sizeof(*data)); } if (!found) return; @@ -491,7 +491,7 @@ static void __init memblock_x86_reserve_range_setup_data(void) data = early_memremap(pa_data, sizeof(*data)); memblock_reserve(pa_data, sizeof(*data) + data->len); pa_data = data->next; - early_iounmap(data, sizeof(*data)); + early_memunmap(data, sizeof(*data)); } } @@ -832,10 +832,15 @@ static void __init trim_low_memory_range(void) static int dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) { - pr_emerg("Kernel Offset: 0x%lx from 0x%lx " - "(relocation range: 0x%lx-0x%lx)\n", - (unsigned long)&_text - __START_KERNEL, __START_KERNEL, - __START_KERNEL_map, MODULES_VADDR-1); + if (kaslr_enabled()) { + pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n", + (unsigned long)&_text - __START_KERNEL, + __START_KERNEL, + __START_KERNEL_map, + MODULES_VADDR-1); + } else { + pr_emerg("Kernel Offset: disabled\n"); + } return 0; } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index e5042463c1bc..1ea14fd53933 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -61,8 +61,7 @@ regs->seg = GET_SEG(seg) | 3; \ } while (0) -int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, - unsigned long *pax) +int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) { void __user *buf; unsigned int tmpflags; @@ -81,7 +80,7 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, #endif /* CONFIG_X86_32 */ COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx); - COPY(dx); COPY(cx); COPY(ip); + COPY(dx); COPY(cx); COPY(ip); COPY(ax); #ifdef CONFIG_X86_64 COPY(r8); @@ -94,27 +93,20 @@ int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, COPY(r15); #endif /* CONFIG_X86_64 */ -#ifdef CONFIG_X86_32 COPY_SEG_CPL3(cs); COPY_SEG_CPL3(ss); -#else /* !CONFIG_X86_32 */ - /* Kernel saves and restores only the CS segment register on signals, - * which is the bare minimum needed to allow mixed 32/64-bit code. - * App's signal handler can save/restore other segments if needed. */ - COPY_SEG_CPL3(cs); -#endif /* CONFIG_X86_32 */ get_user_ex(tmpflags, &sc->flags); regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); regs->orig_ax = -1; /* disable syscall checks */ get_user_ex(buf, &sc->fpstate); - - get_user_ex(*pax, &sc->ax); } get_user_catch(err); err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32)); + force_iret(); + return err; } @@ -162,8 +154,9 @@ int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, #else /* !CONFIG_X86_32 */ put_user_ex(regs->flags, &sc->flags); put_user_ex(regs->cs, &sc->cs); - put_user_ex(0, &sc->gs); - put_user_ex(0, &sc->fs); + put_user_ex(0, &sc->__pad2); + put_user_ex(0, &sc->__pad1); + put_user_ex(regs->ss, &sc->ss); #endif /* CONFIG_X86_32 */ put_user_ex(fpstate, &sc->fpstate); @@ -457,9 +450,19 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, regs->sp = (unsigned long)frame; - /* Set up the CS register to run signal handlers in 64-bit mode, - even if the handler happens to be interrupting 32-bit code. */ + /* + * Set up the CS and SS registers to run signal handlers in + * 64-bit mode, even if the handler happens to be interrupting + * 32-bit or 16-bit code. + * + * SS is subtle. In 64-bit mode, we don't need any particular + * SS descriptor, but we do need SS to be valid. It's possible + * that the old SS is entirely bogus -- this can happen if the + * signal we're trying to deliver is #GP or #SS caused by a bad + * SS value. + */ regs->cs = __USER_CS; + regs->ss = __USER_DS; return 0; } @@ -539,7 +542,6 @@ asmlinkage unsigned long sys_sigreturn(void) { struct pt_regs *regs = current_pt_regs(); struct sigframe __user *frame; - unsigned long ax; sigset_t set; frame = (struct sigframe __user *)(regs->sp - 8); @@ -553,9 +555,9 @@ asmlinkage unsigned long sys_sigreturn(void) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->sc, &ax)) + if (restore_sigcontext(regs, &frame->sc)) goto badframe; - return ax; + return regs->ax; badframe: signal_fault(regs, frame, "sigreturn"); @@ -568,7 +570,6 @@ asmlinkage long sys_rt_sigreturn(void) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; - unsigned long ax; sigset_t set; frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); @@ -579,37 +580,23 @@ asmlinkage long sys_rt_sigreturn(void) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) + if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; if (restore_altstack(&frame->uc.uc_stack)) goto badframe; - return ax; + return regs->ax; badframe: signal_fault(regs, frame, "rt_sigreturn"); return 0; } -/* - * OK, we're invoking a handler: - */ -static int signr_convert(int sig) -{ -#ifdef CONFIG_X86_32 - struct thread_info *info = current_thread_info(); - - if (info->exec_domain && info->exec_domain->signal_invmap && sig < 32) - return info->exec_domain->signal_invmap[sig]; -#endif /* CONFIG_X86_32 */ - return sig; -} - static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { - int usig = signr_convert(ksig->sig); + int usig = ksig->sig; sigset_t *set = sigmask_to_save(); compat_sigset_t *cset = (compat_sigset_t *) set; @@ -629,7 +616,8 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { - bool failed; + bool stepping, failed; + /* Are we from a system call? */ if (syscall_get_nr(current, regs) >= 0) { /* If so, check system call restarting.. */ @@ -653,12 +641,13 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) } /* - * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF - * flag so that register information in the sigcontext is correct. + * If TF is set due to a debugger (TIF_FORCED_TF), clear TF now + * so that register information in the sigcontext is correct and + * then notify the tracer before entering the signal handler. */ - if (unlikely(regs->flags & X86_EFLAGS_TF) && - likely(test_and_clear_thread_flag(TIF_FORCED_TF))) - regs->flags &= ~X86_EFLAGS_TF; + stepping = test_thread_flag(TIF_SINGLESTEP); + if (stepping) + user_disable_single_step(current); failed = (setup_rt_frame(ksig, regs) < 0); if (!failed) { @@ -669,19 +658,17 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs) * it might disable possible debug exception from the * signal handler. * - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. + * Clear TF for the case when it wasn't set by debugger to + * avoid the recursive send_sigtrap() in SIGTRAP handler. */ 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); + fpu_reset_state(current); } - signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP)); + signal_setup_done(failed, ksig, stepping); } #ifdef CONFIG_X86_32 @@ -780,7 +767,6 @@ asmlinkage long sys32_x32_rt_sigreturn(void) struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_x32 __user *frame; sigset_t set; - unsigned long ax; frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); @@ -791,13 +777,13 @@ asmlinkage long sys32_x32_rt_sigreturn(void) set_current_blocked(&set); - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax)) + if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; if (compat_restore_altstack(&frame->uc.uc_stack)) goto badframe; - return ax; + return regs->ax; badframe: signal_fault(regs, frame, "x32 rt_sigreturn"); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index febc6aabc72e..50e547eac8cd 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -77,9 +77,6 @@ #include <asm/realmode.h> #include <asm/misc.h> -/* State of each CPU */ -DEFINE_PER_CPU(int, cpu_state) = { 0 }; - /* Number of siblings per CPU package */ int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); @@ -257,7 +254,7 @@ static void notrace start_secondary(void *unused) lock_vector_lock(); set_cpu_online(smp_processor_id(), true); unlock_vector_lock(); - per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE; + cpu_set_state_online(smp_processor_id()); x86_platform.nmi_init(); /* enable local interrupts */ @@ -779,6 +776,26 @@ out: return boot_error; } +void common_cpu_up(unsigned int cpu, struct task_struct *idle) +{ + /* Just in case we booted with a single CPU. */ + alternatives_enable_smp(); + + per_cpu(current_task, cpu) = idle; + +#ifdef CONFIG_X86_32 + /* Stack for startup_32 can be just as for start_secondary onwards */ + irq_ctx_init(cpu); + per_cpu(cpu_current_top_of_stack, cpu) = + (unsigned long)task_stack_page(idle) + THREAD_SIZE; +#else + clear_tsk_thread_flag(idle, TIF_FORK); + initial_gs = per_cpu_offset(cpu); +#endif + per_cpu(kernel_stack, cpu) = + (unsigned long)task_stack_page(idle) + THREAD_SIZE; +} + /* * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad * (ie clustered apic addressing mode), this is a LOGICAL apic ID. @@ -796,23 +813,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) int cpu0_nmi_registered = 0; unsigned long timeout; - /* Just in case we booted with a single CPU. */ - alternatives_enable_smp(); - idle->thread.sp = (unsigned long) (((struct pt_regs *) (THREAD_SIZE + task_stack_page(idle))) - 1); - per_cpu(current_task, cpu) = idle; -#ifdef CONFIG_X86_32 - /* Stack for startup_32 can be just as for start_secondary onwards */ - irq_ctx_init(cpu); -#else - clear_tsk_thread_flag(idle, TIF_FORK); - initial_gs = per_cpu_offset(cpu); -#endif - per_cpu(kernel_stack, cpu) = - (unsigned long)task_stack_page(idle) - - KERNEL_STACK_OFFSET + THREAD_SIZE; early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; stack_start = idle->thread.sp; @@ -948,11 +951,16 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) */ mtrr_save_state(); - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* x86 CPUs take themselves offline, so delayed offline is OK. */ + err = cpu_check_up_prepare(cpu); + if (err && err != -EBUSY) + return err; /* the FPU context is blank, nobody can own it */ __cpu_disable_lazy_restore(cpu); + common_cpu_up(cpu, tidle); + err = do_boot_cpu(apicid, cpu, tidle); if (err) { pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); @@ -1086,8 +1094,6 @@ static int __init smp_sanity_check(unsigned max_cpus) return SMP_NO_APIC; } - verify_local_APIC(); - /* * If SMP should be disabled, then really disable it! */ @@ -1191,7 +1197,7 @@ void __init native_smp_prepare_boot_cpu(void) switch_to_new_gdt(me); /* already set me in cpu_online_mask in boot_cpu_init() */ cpumask_set_cpu(me, cpu_callout_mask); - per_cpu(cpu_state, me) = CPU_ONLINE; + cpu_set_state_online(me); } void __init native_smp_cpus_done(unsigned int max_cpus) @@ -1318,14 +1324,10 @@ static void __ref remove_cpu_from_maps(int cpu) numa_remove_cpu(cpu); } -static DEFINE_PER_CPU(struct completion, die_complete); - void cpu_disable_common(void) { int cpu = smp_processor_id(); - init_completion(&per_cpu(die_complete, smp_processor_id())); - remove_siblinginfo(cpu); /* It's now safe to remove this processor from the online map */ @@ -1349,24 +1351,27 @@ int native_cpu_disable(void) return 0; } -void cpu_die_common(unsigned int cpu) +int common_cpu_die(unsigned int cpu) { - wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ); -} + int ret = 0; -void native_cpu_die(unsigned int cpu) -{ /* We don't do anything here: idle task is faking death itself. */ - cpu_die_common(cpu); - /* They ack this in play_dead() by setting CPU_DEAD */ - if (per_cpu(cpu_state, cpu) == CPU_DEAD) { + if (cpu_wait_death(cpu, 5)) { if (system_state == SYSTEM_RUNNING) pr_info("CPU %u is now offline\n", cpu); } else { pr_err("CPU %u didn't die...\n", cpu); + ret = -1; } + + return ret; +} + +void native_cpu_die(unsigned int cpu) +{ + common_cpu_die(cpu); } void play_dead_common(void) @@ -1375,10 +1380,8 @@ void play_dead_common(void) reset_lazy_tlbstate(); amd_e400_remove_cpu(raw_smp_processor_id()); - mb(); /* Ack it */ - __this_cpu_write(cpu_state, CPU_DEAD); - complete(&per_cpu(die_complete, smp_processor_id())); + (void)cpu_report_death(); /* * With physical CPU hotplug, we should halt the cpu diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 30277e27431a..10e0272d789a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -34,10 +34,26 @@ static unsigned long get_align_mask(void) return va_align.mask; } +/* + * To avoid aliasing in the I$ on AMD F15h, the bits defined by the + * va_align.bits, [12:upper_bit), are set to a random value instead of + * zeroing them. This random value is computed once per boot. This form + * of ASLR is known as "per-boot ASLR". + * + * To achieve this, the random value is added to the info.align_offset + * value before calling vm_unmapped_area() or ORed directly to the + * address. + */ +static unsigned long get_align_bits(void) +{ + return va_align.bits & get_align_mask(); +} + unsigned long align_vdso_addr(unsigned long addr) { unsigned long align_mask = get_align_mask(); - return (addr + align_mask) & ~align_mask; + addr = (addr + align_mask) & ~align_mask; + return addr | get_align_bits(); } static int __init control_va_addr_alignment(char *str) @@ -135,8 +151,12 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.length = len; info.low_limit = begin; info.high_limit = end; - info.align_mask = filp ? get_align_mask() : 0; + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; + if (filp) { + info.align_mask = get_align_mask(); + info.align_offset += get_align_bits(); + } return vm_unmapped_area(&info); } @@ -174,8 +194,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = mm->mmap_base; - info.align_mask = filp ? get_align_mask() : 0; + info.align_mask = 0; info.align_offset = pgoff << PAGE_SHIFT; + if (filp) { + info.align_mask = get_align_mask(); + info.align_offset += get_align_bits(); + } addr = vm_unmapped_area(&info); if (!(addr & ~PAGE_MASK)) return addr; diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c index e9bcd57d8a9e..3777189c4a19 100644 --- a/arch/x86/kernel/syscall_32.c +++ b/arch/x86/kernel/syscall_32.c @@ -5,21 +5,29 @@ #include <linux/cache.h> #include <asm/asm-offsets.h> -#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ; +#ifdef CONFIG_IA32_EMULATION +#define SYM(sym, compat) compat +#else +#define SYM(sym, compat) sym +#define ia32_sys_call_table sys_call_table +#define __NR_ia32_syscall_max __NR_syscall_max +#endif + +#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ; #include <asm/syscalls_32.h> #undef __SYSCALL_I386 -#define __SYSCALL_I386(nr, sym, compat) [nr] = sym, +#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat), typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -__visible const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { +__visible const sys_call_ptr_t ia32_sys_call_table[__NR_ia32_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. */ - [0 ... __NR_syscall_max] = &sys_ni_syscall, + [0 ... __NR_ia32_syscall_max] = &sys_ni_syscall, #include <asm/syscalls_32.h> }; diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c index b79133abda48..5ecbfe5099da 100644 --- a/arch/x86/kernel/test_rodata.c +++ b/arch/x86/kernel/test_rodata.c @@ -57,7 +57,7 @@ int rodata_test(void) /* test 3: check the value hasn't changed */ /* If this test fails, we managed to overwrite the data */ if (!rodata_test_data) { - printk(KERN_ERR "rodata_test: Test 3 failes (end data)\n"); + printk(KERN_ERR "rodata_test: Test 3 fails (end data)\n"); return -ENODEV; } /* test 4: check if the rodata section is 4Kb aligned */ diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c index 25adc0e16eaa..d39c09119db6 100644 --- a/arch/x86/kernel/time.c +++ b/arch/x86/kernel/time.c @@ -30,7 +30,7 @@ unsigned long profile_pc(struct pt_regs *regs) { unsigned long pc = instruction_pointer(regs); - if (!user_mode_vm(regs) && in_lock_functions(pc)) { + if (!user_mode(regs) && in_lock_functions(pc)) { #ifdef CONFIG_FRAME_POINTER return *(unsigned long *)(regs->bp + sizeof(long)); #else diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 4ff5d162ff9f..324ab5247687 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -112,7 +112,7 @@ enum ctx_state ist_enter(struct pt_regs *regs) { enum ctx_state prev_state; - if (user_mode_vm(regs)) { + if (user_mode(regs)) { /* Other than that, we're just an exception. */ prev_state = exception_enter(); } else { @@ -123,7 +123,7 @@ enum ctx_state ist_enter(struct pt_regs *regs) * but we need to notify RCU. */ rcu_nmi_enter(); - prev_state = IN_KERNEL; /* the value is irrelevant. */ + prev_state = CONTEXT_KERNEL; /* the value is irrelevant. */ } /* @@ -146,7 +146,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) /* Must be before exception_exit. */ preempt_count_sub(HARDIRQ_OFFSET); - if (user_mode_vm(regs)) + if (user_mode(regs)) return exception_exit(prev_state); else rcu_nmi_exit(); @@ -158,7 +158,7 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) * * IST exception handlers normally cannot schedule. As a special * exception, if the exception interrupted userspace code (i.e. - * user_mode_vm(regs) would return true) and the exception was not + * user_mode(regs) would return true) and the exception was not * a double fault, it can be safe to schedule. ist_begin_non_atomic() * begins a non-atomic section within an ist_enter()/ist_exit() region. * Callers are responsible for enabling interrupts themselves inside @@ -167,15 +167,15 @@ void ist_exit(struct pt_regs *regs, enum ctx_state prev_state) */ void ist_begin_non_atomic(struct pt_regs *regs) { - BUG_ON(!user_mode_vm(regs)); + BUG_ON(!user_mode(regs)); /* * Sanity check: we need to be on the normal thread stack. This * will catch asm bugs and any attempt to use ist_preempt_enable * from double_fault. */ - BUG_ON(((current_stack_pointer() ^ this_cpu_read_stable(kernel_stack)) - & ~(THREAD_SIZE - 1)) != 0); + BUG_ON((unsigned long)(current_top_of_stack() - + current_stack_pointer()) >= THREAD_SIZE); preempt_count_sub(HARDIRQ_OFFSET); } @@ -194,8 +194,7 @@ static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, struct pt_regs *regs, long error_code) { -#ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) { + if (v8086_mode(regs)) { /* * Traps 0, 1, 3, 4, and 5 should be forwarded to vm86. * On nmi (interrupt 2), do_trap should not be called. @@ -207,7 +206,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, } return -1; } -#endif + if (!user_mode(regs)) { if (!fixup_exception(regs)) { tsk->thread.error_code = error_code; @@ -384,7 +383,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code) goto exit; conditional_sti(regs); - if (!user_mode_vm(regs)) + if (!user_mode(regs)) die("bounds", regs, error_code); if (!cpu_feature_enabled(X86_FEATURE_MPX)) { @@ -462,13 +461,11 @@ do_general_protection(struct pt_regs *regs, long error_code) prev_state = exception_enter(); conditional_sti(regs); -#ifdef CONFIG_X86_32 - if (regs->flags & X86_VM_MASK) { + if (v8086_mode(regs)) { local_irq_enable(); handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); goto exit; } -#endif tsk = current; if (!user_mode(regs)) { @@ -587,7 +584,7 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) /* 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)); + BUG_ON(!user_mode(&new_stack->regs)); return new_stack; } NOKPROBE_SYMBOL(fixup_bad_iret); @@ -637,7 +634,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) * then it's very likely the result of an icebp/int01 trap. * User wants a sigtrap for that. */ - if (!dr6 && user_mode_vm(regs)) + if (!dr6 && user_mode(regs)) user_icebp = 1; /* Catch kmemcheck conditions first of all! */ @@ -673,7 +670,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) /* It's safe to allow irq's after DR6 has been saved */ preempt_conditional_sti(regs); - if (regs->flags & X86_VM_MASK) { + if (v8086_mode(regs)) { handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, X86_TRAP_DB); preempt_conditional_cli(regs); @@ -721,7 +718,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) return; conditional_sti(regs); - if (!user_mode_vm(regs)) + if (!user_mode(regs)) { if (!fixup_exception(regs)) { task->thread.error_code = error_code; @@ -734,7 +731,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr) /* * Save the info for the exception handler and clear the error. */ - save_init_fpu(task); + unlazy_fpu(task); task->thread.trap_nr = trapnr; task->thread.error_code = error_code; info.si_signo = SIGFPE; @@ -863,7 +860,7 @@ void math_state_restore(void) kernel_fpu_disable(); __thread_fpu_begin(tsk); if (unlikely(restore_fpu_checking(tsk))) { - drop_init_fpu(tsk); + fpu_reset_state(tsk); force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); } else { tsk->thread.fpu_counter++; @@ -925,9 +922,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) /* Set of traps needed for early debugging. */ void __init early_trap_init(void) { - set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); + /* + * Don't use IST to set DEBUG_STACK as it doesn't work until TSS + * is ready in cpu_init() <-- trap_init(). Before trap_init(), + * CPU runs at ring 0 so it is impossible to hit an invalid + * stack. Using the original stack works well enough at this + * early stage. DEBUG_STACK will be equipped after cpu_init() in + * trap_init(). + * + * We don't need to set trace_idt_table like set_intr_gate(), + * since we don't have trace_debug and it will be reset to + * 'debug' in trap_init() by set_intr_gate_ist(). + */ + set_intr_gate_notrace(X86_TRAP_DB, debug); /* int3 can be called from all */ - set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + set_system_intr_gate(X86_TRAP_BP, &int3); #ifdef CONFIG_X86_32 set_intr_gate(X86_TRAP_PF, page_fault); #endif @@ -1005,6 +1014,15 @@ void __init trap_init(void) */ cpu_init(); + /* + * X86_TRAP_DB and X86_TRAP_BP have been set + * in early_trap_init(). However, ITS works only after + * cpu_init() loads TSS. See comments in early_trap_init(). + */ + set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK); + /* int3 can be called from all */ + set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK); + x86_init.irqs.trap_init(); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 81f8adb0679e..0b81ad67da07 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -912,7 +912,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, int ret = NOTIFY_DONE; /* We are only interested in userspace traps */ - if (regs && !user_mode_vm(regs)) + if (regs && !user_mode(regs)) return NOTIFY_DONE; switch (val) { diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index e8edcf52e069..fc9db6ef2a95 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -150,7 +150,7 @@ struct pt_regs *save_v86_state(struct kernel_vm86_regs *regs) do_exit(SIGSEGV); } - tss = &per_cpu(init_tss, get_cpu()); + tss = &per_cpu(cpu_tss, get_cpu()); current->thread.sp0 = current->thread.saved_sp0; current->thread.sysenter_cs = __KERNEL_CS; load_sp0(tss, ¤t->thread); @@ -318,7 +318,7 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk tsk->thread.saved_fs = info->regs32->fs; tsk->thread.saved_gs = get_user_gs(info->regs32); - tss = &per_cpu(init_tss, get_cpu()); + tss = &per_cpu(cpu_tss, get_cpu()); tsk->thread.sp0 = (unsigned long) &info->VM86_TSS_ESP0; if (cpu_has_sep) tsk->thread.sysenter_cs = 0; diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c index c7d791f32b98..51e330416995 100644 --- a/arch/x86/kernel/vsyscall_gtod.c +++ b/arch/x86/kernel/vsyscall_gtod.c @@ -31,30 +31,30 @@ void update_vsyscall(struct timekeeper *tk) gtod_write_begin(vdata); /* copy vsyscall data */ - vdata->vclock_mode = tk->tkr.clock->archdata.vclock_mode; - vdata->cycle_last = tk->tkr.cycle_last; - vdata->mask = tk->tkr.mask; - vdata->mult = tk->tkr.mult; - vdata->shift = tk->tkr.shift; + vdata->vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->cycle_last = tk->tkr_mono.cycle_last; + vdata->mask = tk->tkr_mono.mask; + vdata->mult = tk->tkr_mono.mult; + vdata->shift = tk->tkr_mono.shift; vdata->wall_time_sec = tk->xtime_sec; - vdata->wall_time_snsec = tk->tkr.xtime_nsec; + vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec; vdata->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - vdata->monotonic_time_snsec = tk->tkr.xtime_nsec + vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec - << tk->tkr.shift); + << tk->tkr_mono.shift); while (vdata->monotonic_time_snsec >= - (((u64)NSEC_PER_SEC) << tk->tkr.shift)) { + (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { vdata->monotonic_time_snsec -= - ((u64)NSEC_PER_SEC) << tk->tkr.shift; + ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; vdata->monotonic_time_sec++; } vdata->wall_time_coarse_sec = tk->xtime_sec; - vdata->wall_time_coarse_nsec = (long)(tk->tkr.xtime_nsec >> - tk->tkr.shift); + vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> + tk->tkr_mono.shift); vdata->monotonic_time_coarse_sec = vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index cdc6cf903078..87a815b85f3e 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -342,7 +342,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) config_enabled(CONFIG_IA32_EMULATION)); if (!buf) { - drop_init_fpu(tsk); + fpu_reset_state(tsk); return 0; } @@ -416,7 +416,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size) */ user_fpu_begin(); if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) { - drop_init_fpu(tsk); + fpu_reset_state(tsk); return -1; } } @@ -678,19 +678,13 @@ void xsave_init(void) this_func(); } -static inline void __init eager_fpu_init_bp(void) -{ - current->thread.fpu.state = - alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct)); - if (!init_xstate_buf) - setup_init_fpu_buf(); -} - -void eager_fpu_init(void) +/* + * setup_init_fpu_buf() is __init and it is OK to call it here because + * init_xstate_buf will be unset only once during boot. + */ +void __init_refok eager_fpu_init(void) { - static __refdata void (*boot_func)(void) = eager_fpu_init_bp; - - clear_used_math(); + WARN_ON(used_math()); current_thread_info()->status = 0; if (eagerfpu == ENABLE) @@ -701,21 +695,8 @@ void eager_fpu_init(void) return; } - if (boot_func) { - boot_func(); - boot_func = NULL; - } - - /* - * This is same as math_state_restore(). But use_xsave() is - * not yet patched to use math_state_restore(). - */ - init_fpu(current); - __thread_fpu_begin(current); - if (cpu_has_xsave) - xrstor_state(init_xstate_buf, -1); - else - fxrstor_checking(&init_xstate_buf->i387); + if (!init_xstate_buf) + setup_init_fpu_buf(); } /* diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 08f790dfadc9..16e8f962eaad 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,5 +1,5 @@ -ccflags-y += -Ivirt/kvm -Iarch/x86/kvm +ccflags-y += -Iarch/x86/kvm CFLAGS_x86.o := -I. CFLAGS_svm.o := -I. diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 8a80737ee6e6..59b69f6a2844 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -104,6 +104,9 @@ int kvm_update_cpuid(struct kvm_vcpu *vcpu) ((best->eax & 0xff00) >> 8) != 0) return -EINVAL; + /* Update physical-address width */ + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + kvm_pmu_cpuid_update(vcpu); return 0; } @@ -135,6 +138,21 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) } } +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best) + return best->eax & 0xff; +not_found: + return 36; +} +EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr); + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -757,21 +775,6 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); - if (!best || best->eax < 0x80000008) - goto not_found; - best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best) - return best->eax & 0xff; -not_found: - return 36; -} -EXPORT_SYMBOL_GPL(cpuid_maxphyaddr); - /* * If no match is found, check whether we exceed the vCPU's limit * and return the content of the highest valid _standard_ leaf instead. diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 4452eedfaedd..c3b1ad9fca81 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -20,13 +20,19 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 __user *entries); void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx); +int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); + +static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.maxphyaddr; +} static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; if (!static_cpu_has(X86_FEATURE_XSAVE)) - return 0; + return false; best = kvm_find_cpuid_entry(vcpu, 1, 0); return best && (best->ecx & bit(X86_FEATURE_XSAVE)); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 106c01557f2b..630bcb0d7a04 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -248,27 +248,7 @@ struct mode_dual { struct opcode mode64; }; -/* EFLAGS bit definitions. */ -#define EFLG_ID (1<<21) -#define EFLG_VIP (1<<20) -#define EFLG_VIF (1<<19) -#define EFLG_AC (1<<18) -#define EFLG_VM (1<<17) -#define EFLG_RF (1<<16) -#define EFLG_IOPL (3<<12) -#define EFLG_NT (1<<14) -#define EFLG_OF (1<<11) -#define EFLG_DF (1<<10) -#define EFLG_IF (1<<9) -#define EFLG_TF (1<<8) -#define EFLG_SF (1<<7) -#define EFLG_ZF (1<<6) -#define EFLG_AF (1<<4) -#define EFLG_PF (1<<2) -#define EFLG_CF (1<<0) - #define EFLG_RESERVED_ZEROS_MASK 0xffc0802a -#define EFLG_RESERVED_ONE_MASK 2 enum x86_transfer_type { X86_TRANSFER_NONE, @@ -317,7 +297,8 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) * These EFLAGS bits are restored from saved value during emulation, and * any changes are written back to the saved value after emulation. */ -#define EFLAGS_MASK (EFLG_OF|EFLG_SF|EFLG_ZF|EFLG_AF|EFLG_PF|EFLG_CF) +#define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\ + X86_EFLAGS_PF|X86_EFLAGS_CF) #ifdef CONFIG_X86_64 #define ON64(x) x @@ -478,6 +459,25 @@ static void assign_masked(ulong *dest, ulong src, ulong mask) *dest = (*dest & ~mask) | (src & mask); } +static void assign_register(unsigned long *reg, u64 val, int bytes) +{ + /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ + switch (bytes) { + case 1: + *(u8 *)reg = (u8)val; + break; + case 2: + *(u16 *)reg = (u16)val; + break; + case 4: + *reg = (u32)val; + break; /* 64b: zero-extend */ + case 8: + *reg = val; + break; + } +} + static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; @@ -943,6 +943,22 @@ FASTOP2(xadd); FASTOP2R(cmp, cmp_r); +static int em_bsf_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsf); +} + +static int em_bsr_c(struct x86_emulate_ctxt *ctxt) +{ + /* If src is zero, do not writeback, but update flags */ + if (ctxt->src.val == 0) + ctxt->dst.type = OP_NONE; + return fastop(ctxt, em_bsr); +} + static u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; @@ -1399,7 +1415,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, unsigned int in_page, n; unsigned int count = ctxt->rep_prefix ? address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1; - in_page = (ctxt->eflags & EFLG_DF) ? + in_page = (ctxt->eflags & X86_EFLAGS_DF) ? offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) : PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)); n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count); @@ -1412,7 +1428,7 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, } if (ctxt->rep_prefix && (ctxt->d & String) && - !(ctxt->eflags & EFLG_DF)) { + !(ctxt->eflags & X86_EFLAGS_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; @@ -1691,21 +1707,7 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, static void write_register_operand(struct operand *op) { - /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ - switch (op->bytes) { - case 1: - *(u8 *)op->addr.reg = (u8)op->val; - break; - case 2: - *(u16 *)op->addr.reg = (u16)op->val; - break; - case 4: - *op->addr.reg = (u32)op->val; - break; /* 64b: zero-extend */ - case 8: - *op->addr.reg = op->val; - break; - } + return assign_register(op->addr.reg, op->val, op->bytes); } static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) @@ -1792,32 +1794,34 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, { int rc; unsigned long val, change_mask; - int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &val, len); if (rc != X86EMUL_CONTINUE) return rc; - change_mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_OF - | EFLG_TF | EFLG_DF | EFLG_NT | EFLG_AC | EFLG_ID; + change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF | + X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT | + X86_EFLAGS_AC | X86_EFLAGS_ID; switch(ctxt->mode) { case X86EMUL_MODE_PROT64: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT16: if (cpl == 0) - change_mask |= EFLG_IOPL; + change_mask |= X86_EFLAGS_IOPL; if (cpl <= iopl) - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; case X86EMUL_MODE_VM86: if (iopl < 3) return emulate_gp(ctxt, 0); - change_mask |= EFLG_IF; + change_mask |= X86_EFLAGS_IF; break; default: /* real mode */ - change_mask |= (EFLG_IOPL | EFLG_IF); + change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF); break; } @@ -1918,7 +1922,7 @@ static int em_pusha(struct x86_emulate_ctxt *ctxt) static int em_pushf(struct x86_emulate_ctxt *ctxt) { - ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM; + ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM; return em_push(ctxt); } @@ -1926,6 +1930,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; + u32 val; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { @@ -1933,9 +1938,10 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) --reg; } - rc = emulate_pop(ctxt, reg_rmw(ctxt, reg), ctxt->op_bytes); + rc = emulate_pop(ctxt, &val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) break; + assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes); --reg; } return rc; @@ -1956,7 +1962,7 @@ static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq) if (rc != X86EMUL_CONTINUE) return rc; - ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC); + ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC); ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS); rc = em_push(ctxt); @@ -2022,10 +2028,14 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) unsigned long temp_eip = 0; unsigned long temp_eflags = 0; unsigned long cs = 0; - unsigned long mask = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF | EFLG_TF | - EFLG_IF | EFLG_DF | EFLG_OF | EFLG_IOPL | EFLG_NT | EFLG_RF | - EFLG_AC | EFLG_ID | (1 << 1); /* Last one is the reserved bit */ - unsigned long vm86_mask = EFLG_VM | EFLG_VIF | EFLG_VIP; + unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF | + X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF | + X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF | + X86_EFLAGS_AC | X86_EFLAGS_ID | + X86_EFLAGS_FIXED; + unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF | + X86_EFLAGS_VIP; /* TODO: Add stack limit check */ @@ -2054,7 +2064,6 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) ctxt->_eip = temp_eip; - if (ctxt->op_bytes == 4) ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask)); else if (ctxt->op_bytes == 2) { @@ -2063,7 +2072,7 @@ static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) } ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */ - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED; ctxt->ops->set_nmi_mask(ctxt, false); return rc; @@ -2145,12 +2154,12 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) { *reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0); *reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32); - ctxt->eflags &= ~EFLG_ZF; + ctxt->eflags &= ~X86_EFLAGS_ZF; } else { ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) | (u32) reg_read(ctxt, VCPU_REGS_RBX); - ctxt->eflags |= EFLG_ZF; + ctxt->eflags |= X86_EFLAGS_ZF; } return X86EMUL_CONTINUE; } @@ -2222,7 +2231,7 @@ static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) ctxt->src.val = ctxt->dst.orig_val; fastop(ctxt, em_cmp); - if (ctxt->eflags & EFLG_ZF) { + if (ctxt->eflags & X86_EFLAGS_ZF) { /* Success: write back to memory; no update of EAX */ ctxt->src.type = OP_NONE; ctxt->dst.val = ctxt->src.orig_val; @@ -2381,14 +2390,14 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt) ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~msr_data; - ctxt->eflags |= EFLG_RESERVED_ONE_MASK; + ctxt->eflags |= X86_EFLAGS_FIXED; #endif } else { /* legacy mode */ ops->get_msr(ctxt, MSR_STAR, &msr_data); ctxt->_eip = (u32)msr_data; - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } return X86EMUL_CONTINUE; @@ -2425,8 +2434,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); - ctxt->eflags &= ~(EFLG_VM | EFLG_IF); - cs_sel = (u16)msr_data & ~SELECTOR_RPL_MASK; + ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); + cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; if (efer & EFER_LMA) { cs.d = 0; @@ -2493,8 +2502,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) return emulate_gp(ctxt, 0); break; } - cs_sel |= SELECTOR_RPL_MASK; - ss_sel |= SELECTOR_RPL_MASK; + cs_sel |= SEGMENT_RPL_MASK; + ss_sel |= SEGMENT_RPL_MASK; ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); @@ -2512,7 +2521,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) return false; if (ctxt->mode == X86EMUL_MODE_VM86) return true; - iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT; + iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; return ctxt->ops->cpl(ctxt) > iopl; } @@ -2782,10 +2791,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, return ret; ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); - if (ret != X86EMUL_CONTINUE) - return ret; - return X86EMUL_CONTINUE; + return ret; } static int task_switch_32(struct x86_emulate_ctxt *ctxt, @@ -2954,7 +2961,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt, static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg, struct operand *op) { - int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count; + int df = (ctxt->eflags & X86_EFLAGS_DF) ? -op->count : op->count; register_address_increment(ctxt, reg, df * op->bytes); op->addr.mem.ea = register_address(ctxt, reg); @@ -3323,7 +3330,7 @@ static int em_clts(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_vmcall(struct x86_emulate_ctxt *ctxt) +static int em_hypercall(struct x86_emulate_ctxt *ctxt) { int rc = ctxt->ops->fix_hypercall(ctxt); @@ -3395,17 +3402,6 @@ static int em_lgdt(struct x86_emulate_ctxt *ctxt) return em_lgdt_lidt(ctxt, true); } -static int em_vmmcall(struct x86_emulate_ctxt *ctxt) -{ - int rc; - - rc = ctxt->ops->fix_hypercall(ctxt); - - /* Disable writeback. */ - ctxt->dst.type = OP_NONE; - return rc; -} - static int em_lidt(struct x86_emulate_ctxt *ctxt) { return em_lgdt_lidt(ctxt, false); @@ -3504,7 +3500,8 @@ static int em_sahf(struct x86_emulate_ctxt *ctxt) { u32 flags; - flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF; + flags = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | + X86_EFLAGS_SF; flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; ctxt->eflags &= ~0xffUL; @@ -3769,7 +3766,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) static const struct opcode group7_rm0[] = { N, - I(SrcNone | Priv | EmulateOnUD, em_vmcall), + I(SrcNone | Priv | EmulateOnUD, em_hypercall), N, N, N, N, N, N, }; @@ -3781,7 +3778,7 @@ static const struct opcode group7_rm1[] = { static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), - II(SrcNone | Prot | EmulateOnUD, em_vmmcall, vmmcall), + II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), @@ -4192,7 +4189,8 @@ static const struct opcode twobyte_table[256] = { N, N, G(BitOp, group8), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), - F(DstReg | SrcMem | ModRM, em_bsf), F(DstReg | SrcMem | ModRM, em_bsr), + I(DstReg | SrcMem | ModRM, em_bsf_c), + I(DstReg | SrcMem | ModRM, em_bsr_c), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), @@ -4759,9 +4757,9 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) if (((ctxt->b == 0xa6) || (ctxt->b == 0xa7) || (ctxt->b == 0xae) || (ctxt->b == 0xaf)) && (((ctxt->rep_prefix == REPE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == 0)) + ((ctxt->eflags & X86_EFLAGS_ZF) == 0)) || ((ctxt->rep_prefix == REPNE_PREFIX) && - ((ctxt->eflags & EFLG_ZF) == EFLG_ZF)))) + ((ctxt->eflags & X86_EFLAGS_ZF) == X86_EFLAGS_ZF)))) return true; return false; @@ -4913,7 +4911,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { ctxt->eip = ctxt->_eip; - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; goto done; } } @@ -4963,9 +4961,9 @@ special_insn: } if (ctxt->rep_prefix && (ctxt->d & String)) - ctxt->eflags |= EFLG_RF; + ctxt->eflags |= X86_EFLAGS_RF; else - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { if (ctxt->d & Fastop) { @@ -5014,7 +5012,7 @@ special_insn: rc = emulate_int(ctxt, ctxt->src.val); break; case 0xce: /* into */ - if (ctxt->eflags & EFLG_OF) + if (ctxt->eflags & X86_EFLAGS_OF) rc = emulate_int(ctxt, 4); break; case 0xe9: /* jmp rel */ @@ -5027,19 +5025,19 @@ special_insn: break; case 0xf5: /* cmc */ /* complement carry flag from eflags reg */ - ctxt->eflags ^= EFLG_CF; + ctxt->eflags ^= X86_EFLAGS_CF; break; case 0xf8: /* clc */ - ctxt->eflags &= ~EFLG_CF; + ctxt->eflags &= ~X86_EFLAGS_CF; break; case 0xf9: /* stc */ - ctxt->eflags |= EFLG_CF; + ctxt->eflags |= X86_EFLAGS_CF; break; case 0xfc: /* cld */ - ctxt->eflags &= ~EFLG_DF; + ctxt->eflags &= ~X86_EFLAGS_DF; break; case 0xfd: /* std */ - ctxt->eflags |= EFLG_DF; + ctxt->eflags |= X86_EFLAGS_DF; break; default: goto cannot_emulate; @@ -5100,7 +5098,7 @@ writeback: } goto done; /* skip rip writeback */ } - ctxt->eflags &= ~EFLG_RF; + ctxt->eflags &= ~X86_EFLAGS_RF; } ctxt->eip = ctxt->_eip; @@ -5137,8 +5135,7 @@ twobyte_insn: case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) ctxt->dst.val = ctxt->src.val; - else if (ctxt->mode != X86EMUL_MODE_PROT64 || - ctxt->op_bytes != 4) + else if (ctxt->op_bytes != 4) ctxt->dst.type = OP_NONE; /* no writeback */ break; case 0x80 ... 0x8f: /* jnz rel, etc*/ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 298781d4cfb4..4dce6f8b6129 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -443,7 +443,8 @@ static inline int pit_in_range(gpa_t addr) (addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH)); } -static int pit_ioport_write(struct kvm_io_device *this, +static int pit_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -519,7 +520,8 @@ static int pit_ioport_write(struct kvm_io_device *this, return 0; } -static int pit_ioport_read(struct kvm_io_device *this, +static int pit_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, void *data) { struct kvm_pit *pit = dev_to_pit(this); @@ -589,7 +591,8 @@ static int pit_ioport_read(struct kvm_io_device *this, return 0; } -static int speaker_ioport_write(struct kvm_io_device *this, +static int speaker_ioport_write(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, gpa_t addr, int len, const void *data) { struct kvm_pit *pit = speaker_to_pit(this); @@ -606,8 +609,9 @@ static int speaker_ioport_write(struct kvm_io_device *this, return 0; } -static int speaker_ioport_read(struct kvm_io_device *this, - gpa_t addr, int len, void *data) +static int speaker_ioport_read(struct kvm_vcpu *vcpu, + struct kvm_io_device *this, + gpa_t addr, int len, void *data) { struct kvm_pit *pit = speaker_to_pit(this); struct kvm_kpit_state *pit_state = &pit->pit_state; diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index dd1b16b611b0..c84990b42b5b 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -3,7 +3,7 @@ #include <linux/kthread.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm_kpit_channel_state { u32 count; /* can be 65536 */ diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 9541ba34126b..fef922ff2635 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -529,42 +529,42 @@ static int picdev_read(struct kvm_pic *s, return 0; } -static int picdev_master_write(struct kvm_io_device *dev, +static int picdev_master_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_master_read(struct kvm_io_device *dev, +static int picdev_master_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_master), addr, len, val); } -static int picdev_slave_write(struct kvm_io_device *dev, +static int picdev_slave_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_slave_read(struct kvm_io_device *dev, +static int picdev_slave_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_slave), addr, len, val); } -static int picdev_eclr_write(struct kvm_io_device *dev, +static int picdev_eclr_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { return picdev_write(container_of(dev, struct kvm_pic, dev_eclr), addr, len, val); } -static int picdev_eclr_read(struct kvm_io_device *dev, +static int picdev_eclr_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { return picdev_read(container_of(dev, struct kvm_pic, dev_eclr), diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 46d4449772bc..28146f03c514 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -206,6 +206,8 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, old_irr = ioapic->irr; ioapic->irr |= mask; + if (edge) + ioapic->irr_delivered &= ~mask; if ((edge && old_irr == ioapic->irr) || (!edge && entry.fields.remote_irr)) { ret = 0; @@ -349,7 +351,7 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status) irqe.shorthand = 0; if (irqe.trig_mode == IOAPIC_EDGE_TRIG) - ioapic->irr &= ~(1 << irq); + ioapic->irr_delivered |= 1 << irq; if (irq == RTC_GSI && line_status) { /* @@ -473,13 +475,6 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, } } -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) -{ - struct kvm_ioapic *ioapic = kvm->arch.vioapic; - smp_rmb(); - return test_bit(vector, ioapic->handled_vectors); -} - void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; @@ -500,8 +495,8 @@ static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr) (addr < ioapic->base_address + IOAPIC_MEM_LENGTH))); } -static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, - void *val) +static int ioapic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 result; @@ -543,8 +538,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len, return 0; } -static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len, - const void *val) +static int ioapic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, + gpa_t addr, int len, const void *val) { struct kvm_ioapic *ioapic = to_ioapic(this); u32 data; @@ -599,6 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS; ioapic->ioregsel = 0; ioapic->irr = 0; + ioapic->irr_delivered = 0; ioapic->id = 0; memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); rtc_irq_eoi_tracking_reset(ioapic); @@ -656,6 +652,7 @@ int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(state, ioapic, sizeof(struct kvm_ioapic_state)); + state->irr &= ~ioapic->irr_delivered; spin_unlock(&ioapic->lock); return 0; } @@ -669,6 +666,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state) spin_lock(&ioapic->lock); memcpy(ioapic, state, sizeof(struct kvm_ioapic_state)); ioapic->irr = 0; + ioapic->irr_delivered = 0; update_handled_vectors(ioapic); kvm_vcpu_request_scan_ioapic(kvm); kvm_ioapic_inject_all(ioapic, state->irr); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index c2e36d934af4..ca0b0b4e6256 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -3,7 +3,7 @@ #include <linux/kvm_host.h> -#include "iodev.h" +#include <kvm/iodev.h> struct kvm; struct kvm_vcpu; @@ -77,6 +77,7 @@ struct kvm_ioapic { struct rtc_status rtc_status; struct delayed_work eoi_inject; u32 irq_eoi[IOAPIC_NUM_PINS]; + u32 irr_delivered; }; #ifdef DEBUG @@ -97,13 +98,19 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } +static inline bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector) +{ + struct kvm_ioapic *ioapic = kvm->arch.vioapic; + smp_rmb(); + return test_bit(vector, ioapic->handled_vectors); +} + void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode); -bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector); int kvm_ioapic_init(struct kvm *kvm); void kvm_ioapic_destroy(struct kvm *kvm); int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id, diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 2d03568e9498..ad68c73008c5 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -27,7 +27,7 @@ #include <linux/kvm_host.h> #include <linux/spinlock.h> -#include "iodev.h" +#include <kvm/iodev.h> #include "ioapic.h" #include "lapic.h" diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4ee827d7bf36..d67206a7b99a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -133,6 +133,28 @@ static inline int kvm_apic_id(struct kvm_lapic *apic) return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; } +/* The logical map is definitely wrong if we have multiple + * modes at the same time. (Physical map is always right.) + */ +static inline bool kvm_apic_logical_map_valid(struct kvm_apic_map *map) +{ + return !(map->mode & (map->mode - 1)); +} + +static inline void +apic_logical_id(struct kvm_apic_map *map, u32 dest_id, u16 *cid, u16 *lid) +{ + unsigned lid_bits; + + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_CLUSTER != 4); + BUILD_BUG_ON(KVM_APIC_MODE_XAPIC_FLAT != 8); + BUILD_BUG_ON(KVM_APIC_MODE_X2APIC != 16); + lid_bits = map->mode; + + *cid = dest_id >> lid_bits; + *lid = dest_id & ((1 << lid_bits) - 1); +} + static void recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -146,48 +168,6 @@ static void recalculate_apic_map(struct kvm *kvm) if (!new) goto out; - new->ldr_bits = 8; - /* flat mode is default */ - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - new->broadcast = APIC_BROADCAST; - - kvm_for_each_vcpu(i, vcpu, kvm) { - struct kvm_lapic *apic = vcpu->arch.apic; - - if (!kvm_apic_present(vcpu)) - continue; - - if (apic_x2apic_mode(apic)) { - new->ldr_bits = 32; - new->cid_shift = 16; - new->cid_mask = new->lid_mask = 0xffff; - new->broadcast = X2APIC_BROADCAST; - } else if (kvm_apic_get_reg(apic, APIC_LDR)) { - if (kvm_apic_get_reg(apic, APIC_DFR) == - APIC_DFR_CLUSTER) { - new->cid_shift = 4; - new->cid_mask = 0xf; - new->lid_mask = 0xf; - } else { - new->cid_shift = 8; - new->cid_mask = 0; - new->lid_mask = 0xff; - } - } - - /* - * All APICs have to be configured in the same mode by an OS. - * We take advatage of this while building logical id loockup - * table. After reset APICs are in software disabled mode, so if - * we find apic with different setting we assume this is the mode - * OS wants all apics to be in; build lookup table accordingly. - */ - if (kvm_apic_sw_enabled(apic)) - break; - } - kvm_for_each_vcpu(i, vcpu, kvm) { struct kvm_lapic *apic = vcpu->arch.apic; u16 cid, lid; @@ -198,11 +178,25 @@ static void recalculate_apic_map(struct kvm *kvm) aid = kvm_apic_id(apic); ldr = kvm_apic_get_reg(apic, APIC_LDR); - cid = apic_cluster_id(new, ldr); - lid = apic_logical_id(new, ldr); if (aid < ARRAY_SIZE(new->phys_map)) new->phys_map[aid] = apic; + + if (apic_x2apic_mode(apic)) { + new->mode |= KVM_APIC_MODE_X2APIC; + } else if (ldr) { + ldr = GET_APIC_LOGICAL_ID(ldr); + if (kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + new->mode |= KVM_APIC_MODE_XAPIC_FLAT; + else + new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; + } + + if (!kvm_apic_logical_map_valid(new)) + continue; + + apic_logical_id(new, ldr, &cid, &lid); + if (lid && cid < ARRAY_SIZE(new->logical_map)) new->logical_map[cid][ffs(lid) - 1] = apic; } @@ -588,15 +582,23 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr) apic_update_ppr(apic); } -static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest) +static bool kvm_apic_broadcast(struct kvm_lapic *apic, u32 mda) { - return dest == (apic_x2apic_mode(apic) ? - X2APIC_BROADCAST : APIC_BROADCAST); + if (apic_x2apic_mode(apic)) + return mda == X2APIC_BROADCAST; + + return GET_APIC_DEST_FIELD(mda) == APIC_BROADCAST; } -static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest) +static bool kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 mda) { - return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest); + if (kvm_apic_broadcast(apic, mda)) + return true; + + if (apic_x2apic_mode(apic)) + return mda == kvm_apic_id(apic); + + return mda == SET_APIC_DEST_FIELD(kvm_apic_id(apic)); } static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) @@ -613,6 +615,7 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) && (logical_id & mda & 0xffff) != 0; logical_id = GET_APIC_LOGICAL_ID(logical_id); + mda = GET_APIC_DEST_FIELD(mda); switch (kvm_apic_get_reg(apic, APIC_DFR)) { case APIC_DFR_FLAT: @@ -627,10 +630,27 @@ static bool kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda) } } +/* KVM APIC implementation has two quirks + * - dest always begins at 0 while xAPIC MDA has offset 24, + * - IOxAPIC messages have to be delivered (directly) to x2APIC. + */ +static u32 kvm_apic_mda(unsigned int dest_id, struct kvm_lapic *source, + struct kvm_lapic *target) +{ + bool ipi = source != NULL; + bool x2apic_mda = apic_x2apic_mode(ipi ? source : target); + + if (!ipi && dest_id == APIC_BROADCAST && x2apic_mda) + return X2APIC_BROADCAST; + + return x2apic_mda ? dest_id : SET_APIC_DEST_FIELD(dest_id); +} + bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode) { struct kvm_lapic *target = vcpu->arch.apic; + u32 mda = kvm_apic_mda(dest, source, target); apic_debug("target %p, source %p, dest 0x%x, " "dest_mode 0x%x, short_hand 0x%x\n", @@ -640,9 +660,9 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, switch (short_hand) { case APIC_DEST_NOSHORT: if (dest_mode == APIC_DEST_PHYSICAL) - return kvm_apic_match_physical_addr(target, dest); + return kvm_apic_match_physical_addr(target, mda); else - return kvm_apic_match_logical_addr(target, dest); + return kvm_apic_match_logical_addr(target, mda); case APIC_DEST_SELF: return target == source; case APIC_DEST_ALLINC: @@ -664,6 +684,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic **dst; int i; bool ret = false; + bool x2apic_ipi = src && apic_x2apic_mode(src); *r = -1; @@ -675,15 +696,15 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, if (irq->shorthand) return false; + if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST)) + return false; + rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); if (!map) goto out; - if (irq->dest_id == map->broadcast) - goto out; - ret = true; if (irq->dest_mode == APIC_DEST_PHYSICAL) { @@ -692,16 +713,20 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, dst = &map->phys_map[irq->dest_id]; } else { - u32 mda = irq->dest_id << (32 - map->ldr_bits); - u16 cid = apic_cluster_id(map, mda); + u16 cid; + + if (!kvm_apic_logical_map_valid(map)) { + ret = false; + goto out; + } + + apic_logical_id(map, irq->dest_id, &cid, (u16 *)&bitmap); if (cid >= ARRAY_SIZE(map->logical_map)) goto out; dst = map->logical_map[cid]; - bitmap = apic_logical_id(map, mda); - if (irq->delivery_mode == APIC_DM_LOWEST) { int l = -1; for_each_set_bit(i, &bitmap, 16) { @@ -1037,7 +1062,7 @@ static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr) addr < apic->base_address + LAPIC_MMIO_LENGTH; } -static int apic_mmio_read(struct kvm_io_device *this, +static int apic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1357,7 +1382,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) return ret; } -static int apic_mmio_write(struct kvm_io_device *this, +static int apic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t address, int len, const void *data) { struct kvm_lapic *apic = to_lapic(this); @@ -1497,8 +1522,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) return; } - if (!kvm_vcpu_is_bsp(apic->vcpu)) - value &= ~MSR_IA32_APICBASE_BSP; vcpu->arch.apic_base = value; /* update jump label if enable bit changes */ diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 0bc6c656625b..9d28383fc1e7 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -1,7 +1,7 @@ #ifndef __KVM_X86_LAPIC_H #define __KVM_X86_LAPIC_H -#include "iodev.h" +#include <kvm/iodev.h> #include <linux/kvm_host.h> @@ -148,21 +148,6 @@ static inline bool kvm_apic_vid_enabled(struct kvm *kvm) return kvm_x86_ops->vm_has_apicv(kvm); } -static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr) -{ - u16 cid; - ldr >>= 32 - map->ldr_bits; - cid = (ldr >> map->cid_shift) & map->cid_mask; - - return cid; -} - -static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr) -{ - ldr >>= (32 - map->ldr_bits); - return ldr & map->lid_mask; -} - static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) { return vcpu->arch.apic->pending_events; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index cee759299a35..146f295ee322 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4465,6 +4465,79 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, kvm_flush_remote_tlbs(kvm); } +static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, + unsigned long *rmapp) +{ + u64 *sptep; + struct rmap_iterator iter; + int need_tlb_flush = 0; + pfn_t pfn; + struct kvm_mmu_page *sp; + + for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { + BUG_ON(!(*sptep & PT_PRESENT_MASK)); + + sp = page_header(__pa(sptep)); + pfn = spte_to_pfn(*sptep); + + /* + * Only EPT supported for now; otherwise, one would need to + * find out efficiently whether the guest page tables are + * also using huge pages. + */ + if (sp->role.direct && + !kvm_is_reserved_pfn(pfn) && + PageTransCompound(pfn_to_page(pfn))) { + drop_spte(kvm, sptep); + sptep = rmap_get_first(*rmapp, &iter); + need_tlb_flush = 1; + } else + sptep = rmap_get_next(&iter); + } + + return need_tlb_flush; +} + +void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, + struct kvm_memory_slot *memslot) +{ + bool flush = false; + unsigned long *rmapp; + unsigned long last_index, index; + gfn_t gfn_start, gfn_end; + + spin_lock(&kvm->mmu_lock); + + gfn_start = memslot->base_gfn; + gfn_end = memslot->base_gfn + memslot->npages - 1; + + if (gfn_start >= gfn_end) + goto out; + + rmapp = memslot->arch.rmap[0]; + last_index = gfn_to_index(gfn_end, memslot->base_gfn, + PT_PAGE_TABLE_LEVEL); + + for (index = 0; index <= last_index; ++index, ++rmapp) { + if (*rmapp) + flush |= kvm_mmu_zap_collapsible_spte(kvm, rmapp); + + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (flush) { + kvm_flush_remote_tlbs(kvm); + flush = false; + } + cond_resched_lock(&kvm->mmu_lock); + } + } + + if (flush) + kvm_flush_remote_tlbs(kvm); + +out: + spin_unlock(&kvm->mmu_lock); +} + void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, struct kvm_memory_slot *memslot) { diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 8e6b7d869d2f..29fbf9dfdc54 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -38,7 +38,7 @@ static struct kvm_arch_event_perf_mapping { }; /* mapping between fixed pmc index and arch_events array */ -int fixed_pmc_events[] = {1, 0, 7}; +static int fixed_pmc_events[] = {1, 0, 7}; static bool pmc_is_gp(struct kvm_pmc *pmc) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index cc618c882f90..ce741b8650f6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1261,7 +1261,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&svm->vcpu)) + if (kvm_vcpu_is_reset_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; svm_init_osvw(&svm->vcpu); @@ -1929,14 +1929,12 @@ static int nop_on_interception(struct vcpu_svm *svm) static int halt_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 1; - skip_emulated_instruction(&svm->vcpu); return kvm_emulate_halt(&svm->vcpu); } static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); kvm_emulate_hypercall(&svm->vcpu); return 1; } @@ -2757,11 +2755,11 @@ static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], - vcpu->arch.regs[VCPU_REGS_RAX]); + trace_kvm_invlpga(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RCX), + kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ - kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); + kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -2770,12 +2768,18 @@ static int invlpga_interception(struct vcpu_svm *svm) static int skinit_interception(struct vcpu_svm *svm) { - trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + trace_kvm_skinit(svm->vmcb->save.rip, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX)); kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } +static int wbinvd_interception(struct vcpu_svm *svm) +{ + kvm_emulate_wbinvd(&svm->vcpu); + return 1; +} + static int xsetbv_interception(struct vcpu_svm *svm) { u64 new_bv = kvm_read_edx_eax(&svm->vcpu); @@ -2902,7 +2906,8 @@ static int rdpmc_interception(struct vcpu_svm *svm) return 1; } -bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) +static bool check_selective_cr0_intercepted(struct vcpu_svm *svm, + unsigned long val) { unsigned long cr0 = svm->vcpu.arch.cr0; bool ret = false; @@ -2940,7 +2945,10 @@ static int cr_interception(struct vcpu_svm *svm) return emulate_on_interception(svm); reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; - cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; + if (svm->vmcb->control.exit_code == SVM_EXIT_CR0_SEL_WRITE) + cr = SVM_EXIT_WRITE_CR0 - SVM_EXIT_READ_CR0; + else + cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; err = 0; if (cr >= 16) { /* mov to cr */ @@ -3133,7 +3141,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) static int rdmsr_interception(struct vcpu_svm *svm) { - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); u64 data; if (svm_get_msr(&svm->vcpu, ecx, &data)) { @@ -3142,8 +3150,8 @@ static int rdmsr_interception(struct vcpu_svm *svm) } else { trace_kvm_msr_read(ecx, data); - svm->vcpu.arch.regs[VCPU_REGS_RAX] = data & 0xffffffff; - svm->vcpu.arch.regs[VCPU_REGS_RDX] = data >> 32; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, data & 0xffffffff); + kvm_register_write(&svm->vcpu, VCPU_REGS_RDX, data >> 32); svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; skip_emulated_instruction(&svm->vcpu); } @@ -3246,9 +3254,8 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) static int wrmsr_interception(struct vcpu_svm *svm) { struct msr_data msr; - u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; - u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) - | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + u32 ecx = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); + u64 data = kvm_read_edx_eax(&svm->vcpu); msr.data = data; msr.index = ecx; @@ -3325,7 +3332,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR3] = cr_interception, [SVM_EXIT_READ_CR4] = cr_interception, [SVM_EXIT_READ_CR8] = cr_interception, - [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, + [SVM_EXIT_CR0_SEL_WRITE] = cr_interception, [SVM_EXIT_WRITE_CR0] = cr_interception, [SVM_EXIT_WRITE_CR3] = cr_interception, [SVM_EXIT_WRITE_CR4] = cr_interception, @@ -3376,7 +3383,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, - [SVM_EXIT_WBINVD] = emulate_on_interception, + [SVM_EXIT_WBINVD] = wbinvd_interception, [SVM_EXIT_MONITOR] = monitor_interception, [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, @@ -3555,7 +3562,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) if (exit_code >= ARRAY_SIZE(svm_exit_handlers) || !svm_exit_handlers[exit_code]) { - WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code); + WARN_ONCE(1, "svm: unexpected exit reason 0x%x\n", exit_code); kvm_queue_exception(vcpu, UD_VECTOR); return 1; } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ae4f6d35d19c..f5e8dce8046c 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2470,6 +2470,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_secondary_ctls_low = 0; vmx->nested.nested_vmx_secondary_ctls_high &= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | @@ -3268,8 +3269,8 @@ static void fix_pmode_seg(struct kvm_vcpu *vcpu, int seg, * default value. */ if (seg == VCPU_SREG_CS || seg == VCPU_SREG_SS) - save->selector &= ~SELECTOR_RPL_MASK; - save->dpl = save->selector & SELECTOR_RPL_MASK; + save->selector &= ~SEGMENT_RPL_MASK; + save->dpl = save->selector & SEGMENT_RPL_MASK; save->s = 1; } vmx_set_segment(vcpu, save, seg); @@ -3842,7 +3843,7 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) unsigned int cs_rpl; vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); - cs_rpl = cs.selector & SELECTOR_RPL_MASK; + cs_rpl = cs.selector & SEGMENT_RPL_MASK; if (cs.unusable) return false; @@ -3870,7 +3871,7 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu) unsigned int ss_rpl; vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - ss_rpl = ss.selector & SELECTOR_RPL_MASK; + ss_rpl = ss.selector & SEGMENT_RPL_MASK; if (ss.unusable) return true; @@ -3892,7 +3893,7 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) unsigned int rpl; vmx_get_segment(vcpu, &var, seg); - rpl = var.selector & SELECTOR_RPL_MASK; + rpl = var.selector & SEGMENT_RPL_MASK; if (var.unusable) return true; @@ -3919,7 +3920,7 @@ static bool tr_valid(struct kvm_vcpu *vcpu) if (tr.unusable) return false; - if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (tr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; @@ -3937,7 +3938,7 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu) if (ldtr.unusable) return true; - if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */ + if (ldtr.selector & SEGMENT_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) return false; @@ -3954,8 +3955,8 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); - return ((cs.selector & SELECTOR_RPL_MASK) == - (ss.selector & SELECTOR_RPL_MASK)); + return ((cs.selector & SEGMENT_RPL_MASK) == + (ss.selector & SEGMENT_RPL_MASK)); } /* @@ -4711,7 +4712,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val(); kvm_set_cr8(&vmx->vcpu, 0); apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; - if (kvm_vcpu_is_bsp(&vmx->vcpu)) + if (kvm_vcpu_is_reset_bsp(&vmx->vcpu)) apic_base_msr.data |= MSR_IA32_APICBASE_BSP; apic_base_msr.host_initiated = true; kvm_set_apic_base(&vmx->vcpu, &apic_base_msr); @@ -5006,7 +5007,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); } return 1; } @@ -5071,6 +5072,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) } if (is_invalid_opcode(intr_info)) { + if (is_guest_mode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); @@ -5090,9 +5095,10 @@ static int handle_exception(struct kvm_vcpu *vcpu) !(is_page_fault(intr_info) && !(error_code & PFERR_RSVD_MASK))) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_SIMUL_EX; - vcpu->run->internal.ndata = 2; + vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vect_info; vcpu->run->internal.data[1] = intr_info; + vcpu->run->internal.data[2] = error_code; return 0; } @@ -5533,13 +5539,11 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu) static int handle_halt(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); return kvm_emulate_halt(vcpu); } static int handle_vmcall(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } @@ -5570,7 +5574,6 @@ static int handle_rdpmc(struct kvm_vcpu *vcpu) static int handle_wbinvd(struct kvm_vcpu *vcpu) { - skip_emulated_instruction(vcpu); kvm_emulate_wbinvd(vcpu); return 1; } @@ -5828,7 +5831,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { skip_emulated_instruction(vcpu); return 1; } @@ -5909,7 +5912,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; - ret = kvm_emulate_halt(vcpu); + ret = kvm_vcpu_halt(vcpu); goto out; } @@ -7318,21 +7321,21 @@ static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu, else if (port < 0x10000) bitmap = vmcs12->io_bitmap_b; else - return 1; + return true; bitmap += (port & 0x7fff) / 8; if (last_bitmap != bitmap) if (kvm_read_guest(vcpu->kvm, bitmap, &b, 1)) - return 1; + return true; if (b & (1 << (port & 7))) - return 1; + return true; port++; size--; last_bitmap = bitmap; } - return 0; + return false; } /* @@ -7348,7 +7351,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, gpa_t bitmap; if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS)) - return 1; + return true; /* * The MSR_BITMAP page is divided into four 1024-byte bitmaps, @@ -7367,10 +7370,10 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu, if (msr_index < 1024*8) { unsigned char b; if (kvm_read_guest(vcpu->kvm, bitmap + msr_index/8, &b, 1)) - return 1; + return true; return 1 & (b >> (msr_index & 7)); } else - return 1; /* let L1 handle the wrong parameter */ + return true; /* let L1 handle the wrong parameter */ } /* @@ -7392,7 +7395,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, case 0: if (vmcs12->cr0_guest_host_mask & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; break; case 3: if ((vmcs12->cr3_target_count >= 1 && @@ -7403,37 +7406,37 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, vmcs12->cr3_target_value2 == val) || (vmcs12->cr3_target_count >= 4 && vmcs12->cr3_target_value3 == val)) - return 0; + return false; if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING)) - return 1; + return true; break; case 4: if (vmcs12->cr4_guest_host_mask & (vmcs12->cr4_read_shadow ^ val)) - return 1; + return true; break; case 8: if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING)) - return 1; + return true; break; } break; case 2: /* clts */ if ((vmcs12->cr0_guest_host_mask & X86_CR0_TS) && (vmcs12->cr0_read_shadow & X86_CR0_TS)) - return 1; + return true; break; case 1: /* mov from cr */ switch (cr) { case 3: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR3_STORE_EXITING) - return 1; + return true; break; case 8: if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_CR8_STORE_EXITING) - return 1; + return true; break; } break; @@ -7444,14 +7447,14 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu, */ if (vmcs12->cr0_guest_host_mask & 0xe & (val ^ vmcs12->cr0_read_shadow)) - return 1; + return true; if ((vmcs12->cr0_guest_host_mask & 0x1) && !(vmcs12->cr0_read_shadow & 0x1) && (val & 0x1)) - return 1; + return true; break; } - return 0; + return false; } /* @@ -7474,48 +7477,48 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) KVM_ISA_VMX); if (vmx->nested.nested_run_pending) - return 0; + return false; if (unlikely(vmx->fail)) { pr_info_ratelimited("%s failed vm entry %x\n", __func__, vmcs_read32(VM_INSTRUCTION_ERROR)); - return 1; + return true; } switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: if (!is_exception(intr_info)) - return 0; + return false; else if (is_page_fault(intr_info)) return enable_ept; else if (is_no_device(intr_info) && !(vmcs12->guest_cr0 & X86_CR0_TS)) - return 0; + return false; return vmcs12->exception_bitmap & (1u << (intr_info & INTR_INFO_VECTOR_MASK)); case EXIT_REASON_EXTERNAL_INTERRUPT: - return 0; + return false; case EXIT_REASON_TRIPLE_FAULT: - return 1; + return true; case EXIT_REASON_PENDING_INTERRUPT: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING); case EXIT_REASON_NMI_WINDOW: return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING); case EXIT_REASON_TASK_SWITCH: - return 1; + return true; case EXIT_REASON_CPUID: if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa) - return 0; - return 1; + return false; + return true; case EXIT_REASON_HLT: return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING); case EXIT_REASON_INVD: - return 1; + return true; case EXIT_REASON_INVLPG: return nested_cpu_has(vmcs12, CPU_BASED_INVLPG_EXITING); case EXIT_REASON_RDPMC: return nested_cpu_has(vmcs12, CPU_BASED_RDPMC_EXITING); - case EXIT_REASON_RDTSC: + case EXIT_REASON_RDTSC: case EXIT_REASON_RDTSCP: return nested_cpu_has(vmcs12, CPU_BASED_RDTSC_EXITING); case EXIT_REASON_VMCALL: case EXIT_REASON_VMCLEAR: case EXIT_REASON_VMLAUNCH: case EXIT_REASON_VMPTRLD: @@ -7527,7 +7530,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! */ - return 1; + return true; case EXIT_REASON_CR_ACCESS: return nested_vmx_exit_handled_cr(vcpu, vmcs12); case EXIT_REASON_DR_ACCESS: @@ -7538,7 +7541,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_MSR_WRITE: return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason); case EXIT_REASON_INVALID_STATE: - return 1; + return true; case EXIT_REASON_MWAIT_INSTRUCTION: return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING); case EXIT_REASON_MONITOR_INSTRUCTION: @@ -7548,7 +7551,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) nested_cpu_has2(vmcs12, SECONDARY_EXEC_PAUSE_LOOP_EXITING); case EXIT_REASON_MCE_DURING_VMENTRY: - return 0; + return false; case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: @@ -7557,7 +7560,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_APIC_WRITE: case EXIT_REASON_EOI_INDUCED: /* apic_write and eoi_induced should exit unconditionally. */ - return 1; + return true; case EXIT_REASON_EPT_VIOLATION: /* * L0 always deals with the EPT violation. If nested EPT is @@ -7565,7 +7568,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * missing in the guest EPT table (EPT12), the EPT violation * will be injected with nested_ept_inject_page_fault() */ - return 0; + return false; case EXIT_REASON_EPT_MISCONFIG: /* * L2 never uses directly L1's EPT, but rather L0's own EPT @@ -7573,11 +7576,11 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) * (EPT on EPT). So any problems with the structure of the * table is L0's fault. */ - return 0; + return false; case EXIT_REASON_WBINVD: return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING); case EXIT_REASON_XSETBV: - return 1; + return true; case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS: /* * This should never happen, since it is not possible to @@ -7587,7 +7590,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) */ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES); default: - return 1; + return true; } } @@ -8522,6 +8525,9 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) exec_control); } } + if (nested && !vmx->rdtscp_enabled) + vmx->nested.nested_vmx_secondary_ctls_high &= + ~SECONDARY_EXEC_RDTSCP; } /* Exposing INVPCID only when PCID is exposed */ @@ -8622,10 +8628,11 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int maxphyaddr = cpuid_maxphyaddr(vcpu); if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - /* TODO: Also verify bits beyond physical address width are 0 */ - if (!PAGE_ALIGNED(vmcs12->apic_access_addr)) + if (!PAGE_ALIGNED(vmcs12->apic_access_addr) || + vmcs12->apic_access_addr >> maxphyaddr) return false; /* @@ -8641,8 +8648,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { - /* TODO: Also verify bits beyond physical address width are 0 */ - if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr)) + if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr) || + vmcs12->virtual_apic_page_addr >> maxphyaddr) return false; if (vmx->nested.virtual_apic_page) /* shouldn't happen */ @@ -8665,7 +8672,8 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, } if (nested_cpu_has_posted_intr(vmcs12)) { - if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64)) + if (!IS_ALIGNED(vmcs12->posted_intr_desc_addr, 64) || + vmcs12->posted_intr_desc_addr >> maxphyaddr) return false; if (vmx->nested.pi_desc_page) { /* shouldn't happen */ @@ -8864,9 +8872,9 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, unsigned long count_field, - unsigned long addr_field, - int maxphyaddr) + unsigned long addr_field) { + int maxphyaddr; u64 count, addr; if (vmcs12_read_any(vcpu, count_field, &count) || @@ -8876,6 +8884,7 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, } if (count == 0) return 0; + maxphyaddr = cpuid_maxphyaddr(vcpu); if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr || (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) { pr_warn_ratelimited( @@ -8889,19 +8898,16 @@ static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu, static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { - int maxphyaddr; - if (vmcs12->vm_exit_msr_load_count == 0 && vmcs12->vm_exit_msr_store_count == 0 && vmcs12->vm_entry_msr_load_count == 0) return 0; /* Fast path */ - maxphyaddr = cpuid_maxphyaddr(vcpu); if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT, - VM_EXIT_MSR_LOAD_ADDR, maxphyaddr) || + VM_EXIT_MSR_LOAD_ADDR) || nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT, - VM_EXIT_MSR_STORE_ADDR, maxphyaddr) || + VM_EXIT_MSR_STORE_ADDR) || nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT, - VM_ENTRY_MSR_LOAD_ADDR, maxphyaddr)) + VM_ENTRY_MSR_LOAD_ADDR)) return -EINVAL; return 0; } @@ -9151,8 +9157,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_RDTSCP | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | - SECONDARY_EXEC_APIC_REGISTER_VIRT); + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -9385,7 +9392,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) } if (!nested_get_vmcs12_pages(vcpu, vmcs12)) { - /*TODO: Also verify bits beyond physical address width are 0*/ nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); return 1; } @@ -9524,7 +9530,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) vmcs12->launch_state = 1; if (vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) - return kvm_emulate_halt(vcpu); + return kvm_vcpu_halt(vcpu); vmx->nested.nested_run_pending = 1; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 32bf19ef3115..e1a81267f3f6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -801,6 +801,17 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +static void kvm_update_dr0123(struct kvm_vcpu *vcpu) +{ + int i; + + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; + } +} + static void kvm_update_dr6(struct kvm_vcpu *vcpu) { if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) @@ -1070,19 +1081,19 @@ static void update_pvclock_gtod(struct timekeeper *tk) struct pvclock_gtod_data *vdata = &pvclock_gtod_data; u64 boot_ns; - boot_ns = ktime_to_ns(ktime_add(tk->tkr.base_mono, tk->offs_boot)); + boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); /* copy pvclock gtod data */ - vdata->clock.vclock_mode = tk->tkr.clock->archdata.vclock_mode; - vdata->clock.cycle_last = tk->tkr.cycle_last; - vdata->clock.mask = tk->tkr.mask; - vdata->clock.mult = tk->tkr.mult; - vdata->clock.shift = tk->tkr.shift; + vdata->clock.vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; + vdata->clock.cycle_last = tk->tkr_mono.cycle_last; + vdata->clock.mask = tk->tkr_mono.mask; + vdata->clock.mult = tk->tkr_mono.mult; + vdata->clock.shift = tk->tkr_mono.shift; vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr.xtime_nsec; + vdata->nsec_base = tk->tkr_mono.xtime_nsec; write_seqcount_end(&vdata->seq); } @@ -3149,6 +3160,7 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return -EINVAL; memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; kvm_update_dr6(vcpu); vcpu->arch.dr7 = dbgregs->dr7; @@ -4114,8 +4126,8 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_write(vcpu, &vcpu->arch.apic->dev, addr, n, v)) + && kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, n, v)) break; handled += n; addr += n; @@ -4134,8 +4146,9 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) do { n = min(len, 8); if (!(vcpu->arch.apic && - !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, n, v)) - && kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, n, v)) + !kvm_iodevice_read(vcpu, &vcpu->arch.apic->dev, + addr, n, v)) + && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); handled += n; @@ -4475,7 +4488,8 @@ mmio: return X86EMUL_CONTINUE; } -int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr, +static int emulator_read_write(struct x86_emulate_ctxt *ctxt, + unsigned long addr, void *val, unsigned int bytes, struct x86_exception *exception, const struct read_write_emulator_ops *ops) @@ -4538,7 +4552,7 @@ static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt, exception, &read_emultor); } -int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, +static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, const void *val, unsigned int bytes, @@ -4629,10 +4643,10 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) int r; if (vcpu->arch.pio.in) - r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, + r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); else - r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + r = kvm_io_bus_write(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); return r; @@ -4705,7 +4719,7 @@ static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) kvm_mmu_invlpg(emul_to_vcpu(ctxt), address); } -int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) { if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; @@ -4722,19 +4736,29 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) wbinvd(); return X86EMUL_CONTINUE; } + +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_emulate_wbinvd_noskip(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd); + + static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) { - kvm_emulate_wbinvd(emul_to_vcpu(ctxt)); + kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) +static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest) { return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) +static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long value) { return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); @@ -5816,7 +5840,7 @@ void kvm_arch_exit(void) free_percpu(shared_msrs); } -int kvm_emulate_halt(struct kvm_vcpu *vcpu) +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) { ++vcpu->stat.halt_exits; if (irqchip_in_kernel(vcpu->kvm)) { @@ -5827,6 +5851,13 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) return 0; } } +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); + +int kvm_emulate_halt(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->skip_emulated_instruction(vcpu); + return kvm_vcpu_halt(vcpu); +} EXPORT_SYMBOL_GPL(kvm_emulate_halt); int kvm_hv_hypercall(struct kvm_vcpu *vcpu) @@ -5903,7 +5934,7 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) lapic_irq.dest_id = apicid; lapic_irq.delivery_mode = APIC_DM_REMRD; - kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); + kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) @@ -5911,6 +5942,8 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit, r = 1; + kvm_x86_ops->skip_emulated_instruction(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) return kvm_hv_hypercall(vcpu); @@ -6164,7 +6197,7 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, } /* - * Returns 1 to let __vcpu_run() continue the guest execution loop without + * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. */ @@ -6301,6 +6334,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); set_debugreg(vcpu->arch.dr6, 6); + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } trace_kvm_entry(vcpu->vcpu_id); @@ -6382,42 +6416,47 @@ out: return r; } +static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) +{ + if (!kvm_arch_vcpu_runnable(vcpu)) { + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) + return 1; + } + + kvm_apic_accept_events(vcpu); + switch(vcpu->arch.mp_state) { + case KVM_MP_STATE_HALTED: + vcpu->arch.pv.pv_unhalted = false; + vcpu->arch.mp_state = + KVM_MP_STATE_RUNNABLE; + case KVM_MP_STATE_RUNNABLE: + vcpu->arch.apf.halted = false; + break; + case KVM_MP_STATE_INIT_RECEIVED: + break; + default: + return -EINTR; + break; + } + return 1; +} -static int __vcpu_run(struct kvm_vcpu *vcpu) +static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - r = 1; - while (r > 0) { + for (;;) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE && !vcpu->arch.apf.halted) r = vcpu_enter_guest(vcpu); - else { - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_check_request(KVM_REQ_UNHALT, vcpu)) { - kvm_apic_accept_events(vcpu); - switch(vcpu->arch.mp_state) { - case KVM_MP_STATE_HALTED: - vcpu->arch.pv.pv_unhalted = false; - vcpu->arch.mp_state = - KVM_MP_STATE_RUNNABLE; - case KVM_MP_STATE_RUNNABLE: - vcpu->arch.apf.halted = false; - break; - case KVM_MP_STATE_INIT_RECEIVED: - break; - default: - r = -EINTR; - break; - } - } - } - + else + r = vcpu_block(kvm, vcpu); if (r <= 0) break; @@ -6429,6 +6468,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; + break; } kvm_check_async_pf_completion(vcpu); @@ -6437,6 +6477,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) r = -EINTR; vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; + break; } if (need_resched()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); @@ -6568,7 +6609,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); - r = __vcpu_run(vcpu); + r = vcpu_run(vcpu); out: post_kvm_run_save(vcpu); @@ -7075,11 +7116,14 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu) kvm_clear_exception_queue(vcpu); memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_INIT; kvm_update_dr6(vcpu); vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); + vcpu->arch.cr2 = 0; + kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.apf.msr_val = 0; vcpu->arch.st.msr_val = 0; @@ -7240,7 +7284,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; - if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) + if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED; @@ -7288,6 +7332,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = 0; vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET; + vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + kvm_async_pf_hash_reset(vcpu); kvm_pmu_init(vcpu); @@ -7428,7 +7474,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) { - kvm_kvfree(free->arch.rmap[i]); + kvfree(free->arch.rmap[i]); free->arch.rmap[i] = NULL; } if (i == 0) @@ -7436,7 +7482,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, if (!dont || free->arch.lpage_info[i - 1] != dont->arch.lpage_info[i - 1]) { - kvm_kvfree(free->arch.lpage_info[i - 1]); + kvfree(free->arch.lpage_info[i - 1]); free->arch.lpage_info[i - 1] = NULL; } } @@ -7490,12 +7536,12 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, out_free: for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) { - kvm_kvfree(slot->arch.rmap[i]); + kvfree(slot->arch.rmap[i]); slot->arch.rmap[i] = NULL; if (i == 0) continue; - kvm_kvfree(slot->arch.lpage_info[i - 1]); + kvfree(slot->arch.lpage_info[i - 1]); slot->arch.lpage_info[i - 1] = NULL; } return -ENOMEM; @@ -7618,6 +7664,23 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, new = id_to_memslot(kvm->memslots, mem->slot); /* + * Dirty logging tracks sptes in 4k granularity, meaning that large + * sptes have to be split. If live migration is successful, the guest + * in the source machine will be destroyed and large sptes will be + * created in the destination. However, if the guest continues to run + * in the source machine (for example if live migration fails), small + * sptes will remain around and cause bad performance. + * + * Scan sptes if dirty logging has been stopped, dropping those + * which can be collapsed into a single large-page spte. Later + * page faults will create the large-page sptes. + */ + if ((change != KVM_MR_DELETE) && + (old->flags & KVM_MEM_LOG_DIRTY_PAGES) && + !(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) + kvm_mmu_zap_collapsible_sptes(kvm, new); + + /* * Set up write protection and/or dirty logging for the new slot. * * For KVM_MR_DELETE and KVM_MR_MOVE, the shadow pages of old slot have diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index ac4453d8520e..717908b16037 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -868,7 +868,8 @@ static void __init lguest_init_IRQ(void) /* Some systems map "vectors" to interrupts weirdly. Not us! */ __this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR); if (i != SYSCALL_VECTOR) - set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]); + set_intr_gate(i, irq_entries_start + + 8 * (i - FIRST_EXTERNAL_VECTOR)); } /* @@ -1076,6 +1077,7 @@ static void lguest_load_sp0(struct tss_struct *tss, { lazy_hcall3(LHCALL_SET_STACK, __KERNEL_DS | 0x1, thread->sp0, THREAD_SIZE / PAGE_SIZE); + tss->x86_tss.sp0 = thread->sp0; } /* Let's just say, I wouldn't do debugging under a Guest. */ diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index f5cc9eb1d51b..082a85167a5b 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -13,16 +13,6 @@ #include <asm/alternative-asm.h> #include <asm/dwarf2.h> -.macro SAVE reg - pushl_cfi %\reg - CFI_REL_OFFSET \reg, 0 -.endm - -.macro RESTORE reg - popl_cfi %\reg - CFI_RESTORE \reg -.endm - .macro read64 reg movl %ebx, %eax movl %ecx, %edx @@ -67,10 +57,10 @@ ENDPROC(atomic64_xchg_cx8) .macro addsub_return func ins insc ENTRY(atomic64_\func\()_return_cx8) CFI_STARTPROC - SAVE ebp - SAVE ebx - SAVE esi - SAVE edi + pushl_cfi_reg ebp + pushl_cfi_reg ebx + pushl_cfi_reg esi + pushl_cfi_reg edi movl %eax, %esi movl %edx, %edi @@ -89,10 +79,10 @@ ENTRY(atomic64_\func\()_return_cx8) 10: movl %ebx, %eax movl %ecx, %edx - RESTORE edi - RESTORE esi - RESTORE ebx - RESTORE ebp + popl_cfi_reg edi + popl_cfi_reg esi + popl_cfi_reg ebx + popl_cfi_reg ebp ret CFI_ENDPROC ENDPROC(atomic64_\func\()_return_cx8) @@ -104,7 +94,7 @@ addsub_return sub sub sbb .macro incdec_return func ins insc ENTRY(atomic64_\func\()_return_cx8) CFI_STARTPROC - SAVE ebx + pushl_cfi_reg ebx read64 %esi 1: @@ -119,7 +109,7 @@ ENTRY(atomic64_\func\()_return_cx8) 10: movl %ebx, %eax movl %ecx, %edx - RESTORE ebx + popl_cfi_reg ebx ret CFI_ENDPROC ENDPROC(atomic64_\func\()_return_cx8) @@ -130,7 +120,7 @@ incdec_return dec sub sbb ENTRY(atomic64_dec_if_positive_cx8) CFI_STARTPROC - SAVE ebx + pushl_cfi_reg ebx read64 %esi 1: @@ -146,18 +136,18 @@ ENTRY(atomic64_dec_if_positive_cx8) 2: movl %ebx, %eax movl %ecx, %edx - RESTORE ebx + popl_cfi_reg ebx ret CFI_ENDPROC ENDPROC(atomic64_dec_if_positive_cx8) ENTRY(atomic64_add_unless_cx8) CFI_STARTPROC - SAVE ebp - SAVE ebx + pushl_cfi_reg ebp + pushl_cfi_reg ebx /* these just push these two parameters on the stack */ - SAVE edi - SAVE ecx + pushl_cfi_reg edi + pushl_cfi_reg ecx movl %eax, %ebp movl %edx, %edi @@ -179,8 +169,8 @@ ENTRY(atomic64_add_unless_cx8) 3: addl $8, %esp CFI_ADJUST_CFA_OFFSET -8 - RESTORE ebx - RESTORE ebp + popl_cfi_reg ebx + popl_cfi_reg ebp ret 4: cmpl %edx, 4(%esp) @@ -192,7 +182,7 @@ ENDPROC(atomic64_add_unless_cx8) ENTRY(atomic64_inc_not_zero_cx8) CFI_STARTPROC - SAVE ebx + pushl_cfi_reg ebx read64 %esi 1: @@ -209,7 +199,7 @@ ENTRY(atomic64_inc_not_zero_cx8) movl $1, %eax 3: - RESTORE ebx + popl_cfi_reg ebx ret CFI_ENDPROC ENDPROC(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index e78b8eee6615..9bc944a91274 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -51,10 +51,8 @@ unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum) */ ENTRY(csum_partial) CFI_STARTPROC - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 + pushl_cfi_reg esi + pushl_cfi_reg ebx movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len movl 12(%esp),%esi # Function arg: unsigned char *buff @@ -127,14 +125,12 @@ ENTRY(csum_partial) 6: addl %ecx,%eax adcl $0, %eax 7: - testl $1, 12(%esp) + testb $1, 12(%esp) jz 8f roll $8, %eax 8: - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %esi - CFI_RESTORE esi + popl_cfi_reg ebx + popl_cfi_reg esi ret CFI_ENDPROC ENDPROC(csum_partial) @@ -145,10 +141,8 @@ ENDPROC(csum_partial) ENTRY(csum_partial) CFI_STARTPROC - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 + pushl_cfi_reg esi + pushl_cfi_reg ebx movl 20(%esp),%eax # Function arg: unsigned int sum movl 16(%esp),%ecx # Function arg: int len movl 12(%esp),%esi # Function arg: const unsigned char *buf @@ -251,14 +245,12 @@ ENTRY(csum_partial) addl %ebx,%eax adcl $0,%eax 80: - testl $1, 12(%esp) + testb $1, 12(%esp) jz 90f roll $8, %eax 90: - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %esi - CFI_RESTORE esi + popl_cfi_reg ebx + popl_cfi_reg esi ret CFI_ENDPROC ENDPROC(csum_partial) @@ -298,12 +290,9 @@ ENTRY(csum_partial_copy_generic) CFI_STARTPROC subl $4,%esp CFI_ADJUST_CFA_OFFSET 4 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 + pushl_cfi_reg edi + pushl_cfi_reg esi + pushl_cfi_reg ebx movl ARGBASE+16(%esp),%eax # sum movl ARGBASE+12(%esp),%ecx # len movl ARGBASE+4(%esp),%esi # src @@ -412,12 +401,9 @@ DST( movb %cl, (%edi) ) .previous - popl_cfi %ebx - CFI_RESTORE ebx - popl_cfi %esi - CFI_RESTORE esi - popl_cfi %edi - CFI_RESTORE edi + popl_cfi_reg ebx + popl_cfi_reg esi + popl_cfi_reg edi popl_cfi %ecx # equivalent to addl $4,%esp ret CFI_ENDPROC @@ -441,12 +427,9 @@ ENDPROC(csum_partial_copy_generic) ENTRY(csum_partial_copy_generic) CFI_STARTPROC - pushl_cfi %ebx - CFI_REL_OFFSET ebx, 0 - pushl_cfi %edi - CFI_REL_OFFSET edi, 0 - pushl_cfi %esi - CFI_REL_OFFSET esi, 0 + pushl_cfi_reg ebx + pushl_cfi_reg edi + pushl_cfi_reg esi movl ARGBASE+4(%esp),%esi #src movl ARGBASE+8(%esp),%edi #dst movl ARGBASE+12(%esp),%ecx #len @@ -506,12 +489,9 @@ DST( movb %dl, (%edi) ) jmp 7b .previous - popl_cfi %esi - CFI_RESTORE esi - popl_cfi %edi - CFI_RESTORE edi - popl_cfi %ebx - CFI_RESTORE ebx + popl_cfi_reg esi + popl_cfi_reg edi + popl_cfi_reg ebx ret CFI_ENDPROC ENDPROC(csum_partial_copy_generic) diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index f2145cfa12a6..e67e579c93bd 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,31 +1,35 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> +#include <asm/cpufeature.h> #include <asm/alternative-asm.h> /* - * Zero a page. - * rdi page - */ -ENTRY(clear_page_c) + * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is + * recommended to use this when possible and we do use them by default. + * If enhanced REP MOVSB/STOSB is not available, try to use fast string. + * Otherwise, use original. + */ + +/* + * Zero a page. + * %rdi - page + */ +ENTRY(clear_page) CFI_STARTPROC + + ALTERNATIVE_2 "jmp clear_page_orig", "", X86_FEATURE_REP_GOOD, \ + "jmp clear_page_c_e", X86_FEATURE_ERMS + movl $4096/8,%ecx xorl %eax,%eax rep stosq ret CFI_ENDPROC -ENDPROC(clear_page_c) +ENDPROC(clear_page) -ENTRY(clear_page_c_e) +ENTRY(clear_page_orig) CFI_STARTPROC - movl $4096,%ecx - xorl %eax,%eax - rep stosb - ret - CFI_ENDPROC -ENDPROC(clear_page_c_e) -ENTRY(clear_page) - CFI_STARTPROC xorl %eax,%eax movl $4096/64,%ecx .p2align 4 @@ -45,29 +49,13 @@ ENTRY(clear_page) nop ret CFI_ENDPROC -.Lclear_page_end: -ENDPROC(clear_page) - - /* - * Some CPUs support enhanced REP MOVSB/STOSB instructions. - * It is recommended to use this when possible. - * If enhanced REP MOVSB/STOSB is not available, try to use fast string. - * Otherwise, use original function. - * - */ +ENDPROC(clear_page_orig) -#include <asm/cpufeature.h> - - .section .altinstr_replacement,"ax" -1: .byte 0xeb /* jmp <disp8> */ - .byte (clear_page_c - clear_page) - (2f - 1b) /* offset */ -2: .byte 0xeb /* jmp <disp8> */ - .byte (clear_page_c_e - clear_page) - (3f - 2b) /* offset */ -3: - .previous - .section .altinstructions,"a" - altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\ - .Lclear_page_end-clear_page, 2b-1b - altinstruction_entry clear_page,2b,X86_FEATURE_ERMS, \ - .Lclear_page_end-clear_page,3b-2b - .previous +ENTRY(clear_page_c_e) + CFI_STARTPROC + movl $4096,%ecx + xorl %eax,%eax + rep stosb + ret + CFI_ENDPROC +ENDPROC(clear_page_c_e) diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 176cca67212b..8239dbcbf984 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -2,23 +2,26 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> +#include <asm/cpufeature.h> #include <asm/alternative-asm.h> +/* + * Some CPUs run faster using the string copy instructions (sane microcode). + * It is also a lot simpler. Use this when possible. But, don't use streaming + * copy unless the CPU indicates X86_FEATURE_REP_GOOD. Could vary the + * prefetch distance based on SMP/UP. + */ ALIGN -copy_page_rep: +ENTRY(copy_page) CFI_STARTPROC + ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq ret CFI_ENDPROC -ENDPROC(copy_page_rep) - -/* - * Don't use streaming copy unless the CPU indicates X86_FEATURE_REP_GOOD. - * Could vary the prefetch distance based on SMP/UP. -*/ +ENDPROC(copy_page) -ENTRY(copy_page) +ENTRY(copy_page_regs) CFI_STARTPROC subq $2*8, %rsp CFI_ADJUST_CFA_OFFSET 2*8 @@ -90,21 +93,5 @@ ENTRY(copy_page) addq $2*8, %rsp CFI_ADJUST_CFA_OFFSET -2*8 ret -.Lcopy_page_end: CFI_ENDPROC -ENDPROC(copy_page) - - /* Some CPUs run faster using the string copy instructions. - It is also a lot simpler. Use this when possible */ - -#include <asm/cpufeature.h> - - .section .altinstr_replacement,"ax" -1: .byte 0xeb /* jmp <disp8> */ - .byte (copy_page_rep - copy_page) - (2f - 1b) /* offset */ -2: - .previous - .section .altinstructions,"a" - altinstruction_entry copy_page, 1b, X86_FEATURE_REP_GOOD, \ - .Lcopy_page_end-copy_page, 2b-1b - .previous +ENDPROC(copy_page_regs) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index dee945d55594..fa997dfaef24 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -8,9 +8,6 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> - -#define FIX_ALIGNMENT 1 - #include <asm/current.h> #include <asm/asm-offsets.h> #include <asm/thread_info.h> @@ -19,33 +16,7 @@ #include <asm/asm.h> #include <asm/smap.h> -/* - * By placing feature2 after feature1 in altinstructions section, we logically - * implement: - * If CPU has feature2, jmp to alt2 is used - * else if CPU has feature1, jmp to alt1 is used - * else jmp to orig is used. - */ - .macro ALTERNATIVE_JUMP feature1,feature2,orig,alt1,alt2 -0: - .byte 0xe9 /* 32bit jump */ - .long \orig-1f /* by default jump to orig */ -1: - .section .altinstr_replacement,"ax" -2: .byte 0xe9 /* near jump with 32bit immediate */ - .long \alt1-1b /* offset */ /* or alternatively to alt1 */ -3: .byte 0xe9 /* near jump with 32bit immediate */ - .long \alt2-1b /* offset */ /* or alternatively to alt2 */ - .previous - - .section .altinstructions,"a" - altinstruction_entry 0b,2b,\feature1,5,5 - altinstruction_entry 0b,3b,\feature2,5,5 - .previous - .endm - .macro ALIGN_DESTINATION -#ifdef FIX_ALIGNMENT /* check for bad alignment of destination */ movl %edi,%ecx andl $7,%ecx @@ -67,7 +38,6 @@ _ASM_EXTABLE(100b,103b) _ASM_EXTABLE(101b,103b) -#endif .endm /* Standard copy_to_user with segment limit checking */ @@ -79,9 +49,11 @@ ENTRY(_copy_to_user) jc bad_to_user cmpq TI_addr_limit(%rax),%rcx ja bad_to_user - ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS, \ - copy_user_generic_unrolled,copy_user_generic_string, \ - copy_user_enhanced_fast_string + ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \ + "jmp copy_user_generic_string", \ + X86_FEATURE_REP_GOOD, \ + "jmp copy_user_enhanced_fast_string", \ + X86_FEATURE_ERMS CFI_ENDPROC ENDPROC(_copy_to_user) @@ -94,9 +66,11 @@ ENTRY(_copy_from_user) jc bad_from_user cmpq TI_addr_limit(%rax),%rcx ja bad_from_user - ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,X86_FEATURE_ERMS, \ - copy_user_generic_unrolled,copy_user_generic_string, \ - copy_user_enhanced_fast_string + ALTERNATIVE_2 "jmp copy_user_generic_unrolled", \ + "jmp copy_user_generic_string", \ + X86_FEATURE_REP_GOOD, \ + "jmp copy_user_enhanced_fast_string", \ + X86_FEATURE_ERMS CFI_ENDPROC ENDPROC(_copy_from_user) diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index 2419d5fefae3..9734182966f3 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -196,7 +196,7 @@ ENTRY(csum_partial_copy_generic) /* handle last odd byte */ .Lhandle_1: - testl $1, %r10d + testb $1, %r10b jz .Lende xorl %ebx, %ebx source diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 1313ae6b478b..8f72b334aea0 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -52,6 +52,13 @@ */ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) { + /* + * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid + * even if the input buffer is long enough to hold them. + */ + if (buf_len > MAX_INSN_SIZE) + buf_len = MAX_INSN_SIZE; + memset(insn, 0, sizeof(*insn)); insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; @@ -164,6 +171,12 @@ found: /* VEX.W overrides opnd_size */ insn->opnd_bytes = 8; } else { + /* + * For VEX2, fake VEX3-like byte#2. + * Makes it easier to decode vex.W, vex.vvvv, + * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0. + */ + insn->vex_prefix.bytes[2] = b2 & 0x7f; insn->vex_prefix.nbytes = 2; insn->next_byte += 2; } diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 89b53c9968e7..b046664f5a1c 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -1,12 +1,20 @@ /* Copyright 2002 Andi Kleen */ #include <linux/linkage.h> - #include <asm/cpufeature.h> #include <asm/dwarf2.h> #include <asm/alternative-asm.h> /* + * We build a jump to memcpy_orig by default which gets NOPped out on + * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which + * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs + * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. + */ + +.weak memcpy + +/* * memcpy - Copy a memory block. * * Input: @@ -17,15 +25,11 @@ * Output: * rax original destination */ +ENTRY(__memcpy) +ENTRY(memcpy) + ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ + "jmp memcpy_erms", X86_FEATURE_ERMS -/* - * memcpy_c() - fast string ops (REP MOVSQ) based variant. - * - * This gets patched over the unrolled variant (below) via the - * alternative instructions framework: - */ - .section .altinstr_replacement, "ax", @progbits -.Lmemcpy_c: movq %rdi, %rax movq %rdx, %rcx shrq $3, %rcx @@ -34,29 +38,21 @@ movl %edx, %ecx rep movsb ret -.Lmemcpy_e: - .previous +ENDPROC(memcpy) +ENDPROC(__memcpy) /* - * memcpy_c_e() - enhanced fast string memcpy. This is faster and simpler than - * memcpy_c. Use memcpy_c_e when possible. - * - * This gets patched over the unrolled variant (below) via the - * alternative instructions framework: + * memcpy_erms() - enhanced fast string memcpy. This is faster and + * simpler than memcpy. Use memcpy_erms when possible. */ - .section .altinstr_replacement, "ax", @progbits -.Lmemcpy_c_e: +ENTRY(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb ret -.Lmemcpy_e_e: - .previous - -.weak memcpy +ENDPROC(memcpy_erms) -ENTRY(__memcpy) -ENTRY(memcpy) +ENTRY(memcpy_orig) CFI_STARTPROC movq %rdi, %rax @@ -183,26 +179,4 @@ ENTRY(memcpy) .Lend: retq CFI_ENDPROC -ENDPROC(memcpy) -ENDPROC(__memcpy) - - /* - * Some CPUs are adding enhanced REP MOVSB/STOSB feature - * If the feature is supported, memcpy_c_e() is the first choice. - * If enhanced rep movsb copy is not available, use fast string copy - * memcpy_c() when possible. This is faster and code is simpler than - * original memcpy(). - * Otherwise, original memcpy() is used. - * In .altinstructions section, ERMS feature is placed after REG_GOOD - * feature to implement the right patch order. - * - * Replace only beginning, memcpy is used to apply alternatives, - * so it is silly to overwrite itself with nops - reboot is the - * only outcome... - */ - .section .altinstructions, "a" - altinstruction_entry __memcpy,.Lmemcpy_c,X86_FEATURE_REP_GOOD,\ - .Lmemcpy_e-.Lmemcpy_c,.Lmemcpy_e-.Lmemcpy_c - altinstruction_entry __memcpy,.Lmemcpy_c_e,X86_FEATURE_ERMS, \ - .Lmemcpy_e_e-.Lmemcpy_c_e,.Lmemcpy_e_e-.Lmemcpy_c_e - .previous +ENDPROC(memcpy_orig) diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 9c4b530575da..0f8a0d0331b9 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -5,7 +5,6 @@ * This assembly file is re-written from memmove_64.c file. * - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com> */ -#define _STRING_C #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/cpufeature.h> @@ -44,6 +43,8 @@ ENTRY(__memmove) jg 2f .Lmemmove_begin_forward: + ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS + /* * movsq instruction have many startup latency * so we handle small size by general register. @@ -207,21 +208,5 @@ ENTRY(__memmove) 13: retq CFI_ENDPROC - - .section .altinstr_replacement,"ax" -.Lmemmove_begin_forward_efs: - /* Forward moving data. */ - movq %rdx, %rcx - rep movsb - retq -.Lmemmove_end_forward_efs: - .previous - - .section .altinstructions,"a" - altinstruction_entry .Lmemmove_begin_forward, \ - .Lmemmove_begin_forward_efs,X86_FEATURE_ERMS, \ - .Lmemmove_end_forward-.Lmemmove_begin_forward, \ - .Lmemmove_end_forward_efs-.Lmemmove_begin_forward_efs - .previous ENDPROC(__memmove) ENDPROC(memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 6f44935c6a60..93118fb23976 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -5,19 +5,30 @@ #include <asm/cpufeature.h> #include <asm/alternative-asm.h> +.weak memset + /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is * simpler and shorter than the orignal function as well. - * + * * rdi destination - * rsi value (char) - * rdx count (bytes) - * + * rsi value (char) + * rdx count (bytes) + * * rax original destination - */ - .section .altinstr_replacement, "ax", @progbits -.Lmemset_c: + */ +ENTRY(memset) +ENTRY(__memset) + /* + * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended + * to use it when possible. If not available, use fast string instructions. + * + * Otherwise, use original memset function. + */ + ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ + "jmp memset_erms", X86_FEATURE_ERMS + movq %rdi,%r9 movq %rdx,%rcx andl $7,%edx @@ -31,8 +42,8 @@ rep stosb movq %r9,%rax ret -.Lmemset_e: - .previous +ENDPROC(memset) +ENDPROC(__memset) /* * ISO C memset - set a memory block to a byte value. This function uses @@ -45,21 +56,16 @@ * * rax original destination */ - .section .altinstr_replacement, "ax", @progbits -.Lmemset_c_e: +ENTRY(memset_erms) movq %rdi,%r9 movb %sil,%al movq %rdx,%rcx rep stosb movq %r9,%rax ret -.Lmemset_e_e: - .previous - -.weak memset +ENDPROC(memset_erms) -ENTRY(memset) -ENTRY(__memset) +ENTRY(memset_orig) CFI_STARTPROC movq %rdi,%r10 @@ -134,23 +140,4 @@ ENTRY(__memset) jmp .Lafter_bad_alignment .Lfinal: CFI_ENDPROC -ENDPROC(memset) -ENDPROC(__memset) - - /* Some CPUs support enhanced REP MOVSB/STOSB feature. - * It is recommended to use this when possible. - * - * If enhanced REP MOVSB/STOSB feature is not available, use fast string - * instructions. - * - * Otherwise, use original memset function. - * - * In .altinstructions section, ERMS feature is placed after REG_GOOD - * feature to implement the right patch order. - */ - .section .altinstructions,"a" - altinstruction_entry __memset,.Lmemset_c,X86_FEATURE_REP_GOOD,\ - .Lfinal-__memset,.Lmemset_e-.Lmemset_c - altinstruction_entry __memset,.Lmemset_c_e,X86_FEATURE_ERMS, \ - .Lfinal-__memset,.Lmemset_e_e-.Lmemset_c_e - .previous +ENDPROC(memset_orig) diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index f6d13eefad10..3ca5218fbece 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -14,8 +14,8 @@ .macro op_safe_regs op ENTRY(\op\()_safe_regs) CFI_STARTPROC - pushq_cfi %rbx - pushq_cfi %rbp + pushq_cfi_reg rbx + pushq_cfi_reg rbp movq %rdi, %r10 /* Save pointer */ xorl %r11d, %r11d /* Return value */ movl (%rdi), %eax @@ -35,8 +35,8 @@ ENTRY(\op\()_safe_regs) movl %ebp, 20(%r10) movl %esi, 24(%r10) movl %edi, 28(%r10) - popq_cfi %rbp - popq_cfi %rbx + popq_cfi_reg rbp + popq_cfi_reg rbx ret 3: CFI_RESTORE_STATE @@ -53,10 +53,10 @@ ENDPROC(\op\()_safe_regs) .macro op_safe_regs op ENTRY(\op\()_safe_regs) CFI_STARTPROC - pushl_cfi %ebx - pushl_cfi %ebp - pushl_cfi %esi - pushl_cfi %edi + pushl_cfi_reg ebx + pushl_cfi_reg ebp + pushl_cfi_reg esi + pushl_cfi_reg edi pushl_cfi $0 /* Return value */ pushl_cfi %eax movl 4(%eax), %ecx @@ -80,10 +80,10 @@ ENTRY(\op\()_safe_regs) movl %esi, 24(%eax) movl %edi, 28(%eax) popl_cfi %eax - popl_cfi %edi - popl_cfi %esi - popl_cfi %ebp - popl_cfi %ebx + popl_cfi_reg edi + popl_cfi_reg esi + popl_cfi_reg ebp + popl_cfi_reg ebx ret 3: CFI_RESTORE_STATE diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S index 5dff5f042468..2322abe4da3b 100644 --- a/arch/x86/lib/rwsem.S +++ b/arch/x86/lib/rwsem.S @@ -34,10 +34,10 @@ */ #define save_common_regs \ - pushl_cfi %ecx; CFI_REL_OFFSET ecx, 0 + pushl_cfi_reg ecx #define restore_common_regs \ - popl_cfi %ecx; CFI_RESTORE ecx + popl_cfi_reg ecx /* Avoid uglifying the argument copying x86-64 needs to do. */ .macro movq src, dst @@ -64,22 +64,22 @@ */ #define save_common_regs \ - pushq_cfi %rdi; CFI_REL_OFFSET rdi, 0; \ - pushq_cfi %rsi; CFI_REL_OFFSET rsi, 0; \ - pushq_cfi %rcx; CFI_REL_OFFSET rcx, 0; \ - pushq_cfi %r8; CFI_REL_OFFSET r8, 0; \ - pushq_cfi %r9; CFI_REL_OFFSET r9, 0; \ - pushq_cfi %r10; CFI_REL_OFFSET r10, 0; \ - pushq_cfi %r11; CFI_REL_OFFSET r11, 0 + pushq_cfi_reg rdi; \ + pushq_cfi_reg rsi; \ + pushq_cfi_reg rcx; \ + pushq_cfi_reg r8; \ + pushq_cfi_reg r9; \ + pushq_cfi_reg r10; \ + pushq_cfi_reg r11 #define restore_common_regs \ - popq_cfi %r11; CFI_RESTORE r11; \ - popq_cfi %r10; CFI_RESTORE r10; \ - popq_cfi %r9; CFI_RESTORE r9; \ - popq_cfi %r8; CFI_RESTORE r8; \ - popq_cfi %rcx; CFI_RESTORE rcx; \ - popq_cfi %rsi; CFI_RESTORE rsi; \ - popq_cfi %rdi; CFI_RESTORE rdi + popq_cfi_reg r11; \ + popq_cfi_reg r10; \ + popq_cfi_reg r9; \ + popq_cfi_reg r8; \ + popq_cfi_reg rcx; \ + popq_cfi_reg rsi; \ + popq_cfi_reg rdi #endif @@ -87,12 +87,10 @@ ENTRY(call_rwsem_down_read_failed) CFI_STARTPROC save_common_regs - __ASM_SIZE(push,_cfi) %__ASM_REG(dx) - CFI_REL_OFFSET __ASM_REG(dx), 0 + __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx) movq %rax,%rdi call rwsem_down_read_failed - __ASM_SIZE(pop,_cfi) %__ASM_REG(dx) - CFI_RESTORE __ASM_REG(dx) + __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx) restore_common_regs ret CFI_ENDPROC @@ -124,12 +122,10 @@ ENDPROC(call_rwsem_wake) ENTRY(call_rwsem_downgrade_wake) CFI_STARTPROC save_common_regs - __ASM_SIZE(push,_cfi) %__ASM_REG(dx) - CFI_REL_OFFSET __ASM_REG(dx), 0 + __ASM_SIZE(push,_cfi_reg) __ASM_REG(dx) movq %rax,%rdi call rwsem_downgrade_wake - __ASM_SIZE(pop,_cfi) %__ASM_REG(dx) - CFI_RESTORE __ASM_REG(dx) + __ASM_SIZE(pop,_cfi_reg) __ASM_REG(dx) restore_common_regs ret CFI_ENDPROC diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S index e28cdaf5ac2c..5eb715087b80 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/lib/thunk_32.S @@ -13,12 +13,9 @@ .globl \name \name: CFI_STARTPROC - pushl_cfi %eax - CFI_REL_OFFSET eax, 0 - pushl_cfi %ecx - CFI_REL_OFFSET ecx, 0 - pushl_cfi %edx - CFI_REL_OFFSET edx, 0 + pushl_cfi_reg eax + pushl_cfi_reg ecx + pushl_cfi_reg edx .if \put_ret_addr_in_eax /* Place EIP in the arg1 */ @@ -26,12 +23,9 @@ .endif call \func - popl_cfi %edx - CFI_RESTORE edx - popl_cfi %ecx - CFI_RESTORE ecx - popl_cfi %eax - CFI_RESTORE eax + popl_cfi_reg edx + popl_cfi_reg ecx + popl_cfi_reg eax ret CFI_ENDPROC _ASM_NOKPROBE(\name) diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index b30b5ebd614a..f89ba4e93025 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -17,9 +17,18 @@ CFI_STARTPROC /* this one pushes 9 elems, the next one would be %rIP */ - SAVE_ARGS + pushq_cfi_reg rdi + pushq_cfi_reg rsi + pushq_cfi_reg rdx + pushq_cfi_reg rcx + pushq_cfi_reg rax + pushq_cfi_reg r8 + pushq_cfi_reg r9 + pushq_cfi_reg r10 + pushq_cfi_reg r11 .if \put_ret_addr_in_rdi + /* 9*8(%rsp) is return addr on stack */ movq_cfi_restore 9*8, rdi .endif @@ -45,11 +54,22 @@ #endif #endif - /* SAVE_ARGS below is used only for the .cfi directives it contains. */ +#if defined(CONFIG_TRACE_IRQFLAGS) \ + || defined(CONFIG_DEBUG_LOCK_ALLOC) \ + || defined(CONFIG_PREEMPT) CFI_STARTPROC - SAVE_ARGS + CFI_ADJUST_CFA_OFFSET 9*8 restore: - RESTORE_ARGS + popq_cfi_reg r11 + popq_cfi_reg r10 + popq_cfi_reg r9 + popq_cfi_reg r8 + popq_cfi_reg rax + popq_cfi_reg rcx + popq_cfi_reg rdx + popq_cfi_reg rsi + popq_cfi_reg rdi ret CFI_ENDPROC _ASM_NOKPROBE(restore) +#endif diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index c905e89e19fe..1f33b3d1fd68 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -69,21 +69,20 @@ EXPORT_SYMBOL(copy_in_user); * it is not necessary to optimize tail handling. */ __visible unsigned long -copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) +copy_user_handle_tail(char *to, char *from, unsigned len) { - char c; - unsigned zero_len; - for (; len; --len, to++) { + char c; + if (__get_user_nocheck(c, from++, sizeof(char))) break; if (__put_user_nocheck(c, to, sizeof(char))) break; } - - for (c = 0, zero_len = len; zerorest && zero_len; --zero_len) - if (__put_user_nocheck(c, to++, sizeof(char))) - break; clac(); + + /* If the destination is a kernel buffer, we always clear the end */ + if ((unsigned long)to >= TASK_SIZE_MAX) + memset(to, 0, len); return len; } diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 1a2be7c6895d..816488c0b97e 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -273,6 +273,9 @@ dd: ESC de: ESC df: ESC # 0xe0 - 0xef +# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix +# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation +# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD. e0: LOOPNE/LOOPNZ Jb (f64) e1: LOOPE/LOOPZ Jb (f64) e2: LOOP Jb (f64) @@ -281,6 +284,10 @@ e4: IN AL,Ib e5: IN eAX,Ib e6: OUT Ib,AL e7: OUT Ib,eAX +# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset +# in "near" jumps and calls is 16-bit. For CALL, +# push of return address is 16-bit wide, RSP is decremented by 2 +# but is not truncated to 16 bits, unlike RIP. e8: CALL Jz (f64) e9: JMP-near Jz (f64) ea: JMP-far Ap (i64) @@ -456,6 +463,7 @@ AVXcode: 1 7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1) 7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqu Wx,Vx (F3) # 0x0f 0x80-0x8f +# Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 80: JO Jz (f64) 81: JNO Jz (f64) 82: JB/JC/JNAE Jz (f64) @@ -842,6 +850,7 @@ EndTable GrpTable: Grp5 0: INC Ev 1: DEC Ev +# Note: "forced64" is Intel CPU behavior (see comment about CALL insn). 2: CALLN Ev (f64) 3: CALLF Ep 4: JMPN Ev (f64) diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index c4cc74006c61..a482d105172b 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -32,6 +32,4 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_MEMTEST) += memtest.o - obj-$(CONFIG_X86_INTEL_MPX) += mpx.o diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ede025fb46f1..181c53bac3a7 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -59,7 +59,7 @@ static nokprobe_inline int kprobes_fault(struct pt_regs *regs) int ret = 0; /* kprobe_running() needs smp_processor_id() */ - if (kprobes_built_in() && !user_mode_vm(regs)) { + if (kprobes_built_in() && !user_mode(regs)) { preempt_disable(); if (kprobe_running() && kprobe_fault_handler(regs, 14)) ret = 1; @@ -148,7 +148,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; - if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE) + if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE_MAX) return 0; while (instr < max_instr) { @@ -1035,7 +1035,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) if (error_code & PF_USER) return false; - if (!user_mode_vm(regs) && (regs->flags & X86_EFLAGS_AC)) + if (!user_mode(regs) && (regs->flags & X86_EFLAGS_AC)) return false; return true; @@ -1140,7 +1140,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code, * User-mode registers count as a user access even for any * potential system fault or CPU buglet: */ - if (user_mode_vm(regs)) { + if (user_mode(regs)) { local_irq_enable(); error_code |= PF_USER; flags |= FAULT_FLAG_USER; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index a110efca6d06..1d553186c434 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -29,29 +29,33 @@ /* * Tables translating between page_cache_type_t and pte encoding. - * Minimal supported modes are defined statically, modified if more supported - * cache modes are available. - * Index into __cachemode2pte_tbl is the cachemode. - * Index into __pte2cachemode_tbl are the caching attribute bits of the pte - * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2. + * + * Minimal supported modes are defined statically, they are modified + * during bootup if more supported cache modes are available. + * + * Index into __cachemode2pte_tbl[] is the cachemode. + * + * Index into __pte2cachemode_tbl[] are the caching attribute bits of the pte + * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2. */ uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = { - [_PAGE_CACHE_MODE_WB] = 0, - [_PAGE_CACHE_MODE_WC] = _PAGE_PWT, - [_PAGE_CACHE_MODE_UC_MINUS] = _PAGE_PCD, - [_PAGE_CACHE_MODE_UC] = _PAGE_PCD | _PAGE_PWT, - [_PAGE_CACHE_MODE_WT] = _PAGE_PCD, - [_PAGE_CACHE_MODE_WP] = _PAGE_PCD, + [_PAGE_CACHE_MODE_WB ] = 0 | 0 , + [_PAGE_CACHE_MODE_WC ] = _PAGE_PWT | 0 , + [_PAGE_CACHE_MODE_UC_MINUS] = 0 | _PAGE_PCD, + [_PAGE_CACHE_MODE_UC ] = _PAGE_PWT | _PAGE_PCD, + [_PAGE_CACHE_MODE_WT ] = 0 | _PAGE_PCD, + [_PAGE_CACHE_MODE_WP ] = 0 | _PAGE_PCD, }; EXPORT_SYMBOL(__cachemode2pte_tbl); + uint8_t __pte2cachemode_tbl[8] = { - [__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC, - [__pte2cm_idx(_PAGE_PCD)] = _PAGE_CACHE_MODE_UC_MINUS, - [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD)] = _PAGE_CACHE_MODE_UC, - [__pte2cm_idx(_PAGE_PAT)] = _PAGE_CACHE_MODE_WB, - [__pte2cm_idx(_PAGE_PWT | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC, - [__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, + [__pte2cm_idx( 0 | 0 | 0 )] = _PAGE_CACHE_MODE_WB, + [__pte2cm_idx(_PAGE_PWT | 0 | 0 )] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx( 0 | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC_MINUS, + [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0 )] = _PAGE_CACHE_MODE_UC, + [__pte2cm_idx( 0 | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB, + [__pte2cm_idx(_PAGE_PWT | 0 | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC, + [__pte2cm_idx(0 | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS, [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC, }; EXPORT_SYMBOL(__pte2cachemode_tbl); @@ -131,21 +135,7 @@ void __init early_alloc_pgt_buf(void) int after_bootmem; -int direct_gbpages -#ifdef CONFIG_DIRECT_GBPAGES - = 1 -#endif -; - -static void __init init_gbpages(void) -{ -#ifdef CONFIG_X86_64 - if (direct_gbpages && cpu_has_gbpages) - printk(KERN_INFO "Using GB pages for direct mapping\n"); - else - direct_gbpages = 0; -#endif -} +early_param_on_off("gbpages", "nogbpages", direct_gbpages, CONFIG_X86_DIRECT_GBPAGES); struct map_range { unsigned long start; @@ -157,16 +147,12 @@ static int page_size_mask; static void __init probe_page_size_mask(void) { - init_gbpages(); - #if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK) /* * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ - if (direct_gbpages) - page_size_mask |= 1 << PG_LEVEL_1G; if (cpu_has_pse) page_size_mask |= 1 << PG_LEVEL_2M; #endif @@ -179,6 +165,15 @@ static void __init probe_page_size_mask(void) if (cpu_has_pge) { cr4_set_bits_and_update_boot(X86_CR4_PGE); __supported_pte_mask |= _PAGE_GLOBAL; + } else + __supported_pte_mask &= ~_PAGE_GLOBAL; + + /* Enable 1 GB linear kernel mappings if available: */ + if (direct_gbpages && cpu_has_gbpages) { + printk(KERN_INFO "Using GB pages for direct mapping\n"); + page_size_mask |= 1 << PG_LEVEL_1G; + } else { + direct_gbpages = 0; } } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 30eb05ae7061..3fba623e3ba5 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -130,20 +130,6 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, return 0; } -static int __init parse_direct_gbpages_off(char *arg) -{ - direct_gbpages = 0; - return 0; -} -early_param("nogbpages", parse_direct_gbpages_off); - -static int __init parse_direct_gbpages_on(char *arg) -{ - direct_gbpages = 1; - return 0; -} -early_param("gbpages", parse_direct_gbpages_on); - /* * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the * physical space so we can cache the place of the first one and move diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index fdf617c00e2f..5ead4d6cf3a7 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -67,8 +67,13 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, /* * Remap an arbitrary physical address space into the kernel virtual - * address space. Needed when the kernel wants to access high addresses - * directly. + * address space. It transparently creates kernel huge I/O mapping when + * the physical address is aligned by a huge page size (1GB or 2MB) and + * the requested size is at least the huge page size. + * + * NOTE: MTRRs can override PAT memory types with a 4KB granularity. + * Therefore, the mapping code falls back to use a smaller page toward 4KB + * when a mapping range is covered by non-WB type of MTRRs. * * NOTE! We need to allow non-page-aligned mappings too: we will obviously * have to convert them into an offset in a page-aligned mapping, but the @@ -326,6 +331,20 @@ void iounmap(volatile void __iomem *addr) } EXPORT_SYMBOL(iounmap); +int arch_ioremap_pud_supported(void) +{ +#ifdef CONFIG_X86_64 + return cpu_has_gbpages; +#else + return 0; +#endif +} + +int arch_ioremap_pmd_supported(void) +{ + return cpu_has_pse; +} + /* * Convert a physical pointer to a virtual kernel pointer for /dev/mem * access diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c deleted file mode 100644 index 1e9da795767a..000000000000 --- a/arch/x86/mm/memtest.c +++ /dev/null @@ -1,118 +0,0 @@ -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/pfn.h> -#include <linux/memblock.h> - -static u64 patterns[] __initdata = { - /* The first entry has to be 0 to leave memtest with zeroed memory */ - 0, - 0xffffffffffffffffULL, - 0x5555555555555555ULL, - 0xaaaaaaaaaaaaaaaaULL, - 0x1111111111111111ULL, - 0x2222222222222222ULL, - 0x4444444444444444ULL, - 0x8888888888888888ULL, - 0x3333333333333333ULL, - 0x6666666666666666ULL, - 0x9999999999999999ULL, - 0xccccccccccccccccULL, - 0x7777777777777777ULL, - 0xbbbbbbbbbbbbbbbbULL, - 0xddddddddddddddddULL, - 0xeeeeeeeeeeeeeeeeULL, - 0x7a6c7258554e494cULL, /* yeah ;-) */ -}; - -static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad) -{ - printk(KERN_INFO " %016llx bad mem addr %010llx - %010llx reserved\n", - (unsigned long long) pattern, - (unsigned long long) start_bad, - (unsigned long long) end_bad); - memblock_reserve(start_bad, end_bad - start_bad); -} - -static void __init memtest(u64 pattern, u64 start_phys, u64 size) -{ - u64 *p, *start, *end; - u64 start_bad, last_bad; - u64 start_phys_aligned; - const size_t incr = sizeof(pattern); - - start_phys_aligned = ALIGN(start_phys, incr); - start = __va(start_phys_aligned); - end = start + (size - (start_phys_aligned - start_phys)) / incr; - start_bad = 0; - last_bad = 0; - - for (p = start; p < end; p++) - *p = pattern; - - for (p = start; p < end; p++, start_phys_aligned += incr) { - if (*p == pattern) - continue; - if (start_phys_aligned == last_bad + incr) { - last_bad += incr; - continue; - } - if (start_bad) - reserve_bad_mem(pattern, start_bad, last_bad + incr); - start_bad = last_bad = start_phys_aligned; - } - if (start_bad) - reserve_bad_mem(pattern, start_bad, last_bad + incr); -} - -static void __init do_one_pass(u64 pattern, u64 start, u64 end) -{ - u64 i; - phys_addr_t this_start, this_end; - - for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) { - this_start = clamp_t(phys_addr_t, this_start, start, end); - this_end = clamp_t(phys_addr_t, this_end, start, end); - if (this_start < this_end) { - printk(KERN_INFO " %010llx - %010llx pattern %016llx\n", - (unsigned long long)this_start, - (unsigned long long)this_end, - (unsigned long long)cpu_to_be64(pattern)); - memtest(pattern, this_start, this_end - this_start); - } - } -} - -/* default is disabled */ -static int memtest_pattern __initdata; - -static int __init parse_memtest(char *arg) -{ - if (arg) - memtest_pattern = simple_strtoul(arg, NULL, 0); - else - memtest_pattern = ARRAY_SIZE(patterns); - - return 0; -} - -early_param("memtest", parse_memtest); - -void __init early_memtest(unsigned long start, unsigned long end) -{ - unsigned int i; - unsigned int idx = 0; - - if (!memtest_pattern) - return; - - printk(KERN_INFO "early_memtest: # of tests: %d\n", memtest_pattern); - for (i = memtest_pattern-1; i < UINT_MAX; --i) { - idx = i % ARRAY_SIZE(patterns); - do_one_pass(patterns[idx], start, end); - } -} diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index df4552bd239e..9d518d693b4b 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -65,24 +65,23 @@ static int mmap_is_legacy(void) return sysctl_legacy_va_layout; } -static unsigned long mmap_rnd(void) +unsigned long arch_mmap_rnd(void) { - unsigned long rnd = 0; + unsigned long rnd; /* - * 8 bits of randomness in 32bit mmaps, 20 address space bits - * 28 bits of randomness in 64bit mmaps, 40 address space bits - */ - if (current->flags & PF_RANDOMIZE) { - if (mmap_is_ia32()) - rnd = get_random_int() % (1<<8); - else - rnd = get_random_int() % (1<<28); - } + * 8 bits of randomness in 32bit mmaps, 20 address space bits + * 28 bits of randomness in 64bit mmaps, 40 address space bits + */ + if (mmap_is_ia32()) + rnd = (unsigned long)get_random_int() % (1<<8); + else + rnd = (unsigned long)get_random_int() % (1<<28); + return rnd << PAGE_SHIFT; } -static unsigned long mmap_base(void) +static unsigned long mmap_base(unsigned long rnd) { unsigned long gap = rlimit(RLIMIT_STACK); @@ -91,19 +90,19 @@ static unsigned long mmap_base(void) else if (gap > MAX_GAP) gap = MAX_GAP; - return PAGE_ALIGN(TASK_SIZE - gap - mmap_rnd()); + return PAGE_ALIGN(TASK_SIZE - gap - rnd); } /* * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 * does, but not when emulating X86_32 */ -static unsigned long mmap_legacy_base(void) +static unsigned long mmap_legacy_base(unsigned long rnd) { if (mmap_is_ia32()) return TASK_UNMAPPED_BASE; else - return TASK_UNMAPPED_BASE + mmap_rnd(); + return TASK_UNMAPPED_BASE + rnd; } /* @@ -112,13 +111,18 @@ static unsigned long mmap_legacy_base(void) */ void arch_pick_mmap_layout(struct mm_struct *mm) { - mm->mmap_legacy_base = mmap_legacy_base(); - mm->mmap_base = mmap_base(); + unsigned long random_factor = 0UL; + + if (current->flags & PF_RANDOMIZE) + random_factor = arch_mmap_rnd(); + + mm->mmap_legacy_base = mmap_legacy_base(random_factor); if (mmap_is_legacy()) { mm->mmap_base = mm->mmap_legacy_base; mm->get_unmapped_area = arch_get_unmapped_area; } else { + mm->mmap_base = mmap_base(random_factor); mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index cd4785bbacb9..4053bb58bf92 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -482,9 +482,16 @@ static void __init numa_clear_kernel_node_hotplug(void) &memblock.reserved, mb->nid); } - /* Mark all kernel nodes. */ + /* + * Mark all kernel nodes. + * + * When booting with mem=nn[kMG] or in a kdump kernel, numa_meminfo + * may not include all the memblock.reserved memory ranges because + * trim_snb_memory() reserves specific pages for Sandy Bridge graphics. + */ for_each_memblock(reserved, r) - node_set(r->nid, numa_kernel_nodes); + if (r->nid != MAX_NUMNODES) + node_set(r->nid, numa_kernel_nodes); /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ for (i = 0; i < numa_meminfo.nr_blks; i++) { diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 536ea2fb6e33..89af288ec674 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -81,11 +81,9 @@ void arch_report_meminfo(struct seq_file *m) seq_printf(m, "DirectMap4M: %8lu kB\n", direct_pages_count[PG_LEVEL_2M] << 12); #endif -#ifdef CONFIG_X86_64 if (direct_gbpages) seq_printf(m, "DirectMap1G: %8lu kB\n", direct_pages_count[PG_LEVEL_1G] << 20); -#endif } #else static inline void split_page_count(int level) { } @@ -1654,13 +1652,11 @@ int set_memory_ro(unsigned long addr, int numpages) { return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_RW), 0); } -EXPORT_SYMBOL_GPL(set_memory_ro); int set_memory_rw(unsigned long addr, int numpages) { return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_RW), 0); } -EXPORT_SYMBOL_GPL(set_memory_rw); int set_memory_np(unsigned long addr, int numpages) { diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 7ac68698406c..35af6771a95a 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -610,7 +610,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, } #ifdef CONFIG_STRICT_DEVMEM -/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM*/ +/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM */ static inline int range_is_allowed(unsigned long pfn, unsigned long size) { return 1; @@ -628,8 +628,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) while (cursor < to) { if (!devmem_is_allowed(pfn)) { - printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx]\n", - current->comm, from, to - 1); + printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx], PAT prevents it\n", + current->comm, from, to - 1); return 0; } cursor += PAGE_SIZE; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 7b22adaad4f1..0b97d2c75df3 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -4,6 +4,7 @@ #include <asm/pgtable.h> #include <asm/tlb.h> #include <asm/fixmap.h> +#include <asm/mtrr.h> #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO @@ -58,7 +59,7 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte) tlb_remove_page(tlb, pte); } -#if PAGETABLE_LEVELS > 2 +#if CONFIG_PGTABLE_LEVELS > 2 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) { struct page *page = virt_to_page(pmd); @@ -74,14 +75,14 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) tlb_remove_page(tlb, page); } -#if PAGETABLE_LEVELS > 3 +#if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); tlb_remove_page(tlb, virt_to_page(pud)); } -#endif /* PAGETABLE_LEVELS > 3 */ -#endif /* PAGETABLE_LEVELS > 2 */ +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ static inline void pgd_list_add(pgd_t *pgd) { @@ -117,9 +118,9 @@ static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd) /* If the pgd points to a shared pagetable level (either the ptes in non-PAE, or shared PMD in PAE), then just copy the references from swapper_pg_dir. */ - if (PAGETABLE_LEVELS == 2 || - (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || - PAGETABLE_LEVELS == 4) { + if (CONFIG_PGTABLE_LEVELS == 2 || + (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) || + CONFIG_PGTABLE_LEVELS == 4) { clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY, swapper_pg_dir + KERNEL_PGD_BOUNDARY, KERNEL_PGD_PTRS); @@ -275,12 +276,87 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) } } +/* + * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also + * assumes that pgd should be in one page. + * + * But kernel with PAE paging that is not running as a Xen domain + * only needs to allocate 32 bytes for pgd instead of one page. + */ +#ifdef CONFIG_X86_PAE + +#include <linux/slab.h> + +#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) +#define PGD_ALIGN 32 + +static struct kmem_cache *pgd_cache; + +static int __init pgd_cache_init(void) +{ + /* + * When PAE kernel is running as a Xen domain, it does not use + * shared kernel pmd. And this requires a whole page for pgd. + */ + if (!SHARED_KERNEL_PMD) + return 0; + + /* + * when PAE kernel is not running as a Xen domain, it uses + * shared kernel pmd. Shared kernel pmd does not require a whole + * page for pgd. We are able to just allocate a 32-byte for pgd. + * During boot time, we create a 32-byte slab for pgd table allocation. + */ + pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN, + SLAB_PANIC, NULL); + if (!pgd_cache) + return -ENOMEM; + + return 0; +} +core_initcall(pgd_cache_init); + +static inline pgd_t *_pgd_alloc(void) +{ + /* + * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain. + * We allocate one page for pgd. + */ + if (!SHARED_KERNEL_PMD) + return (pgd_t *)__get_free_page(PGALLOC_GFP); + + /* + * Now PAE kernel is not running as a Xen domain. We can allocate + * a 32-byte slab for pgd to save memory space. + */ + return kmem_cache_alloc(pgd_cache, PGALLOC_GFP); +} + +static inline void _pgd_free(pgd_t *pgd) +{ + if (!SHARED_KERNEL_PMD) + free_page((unsigned long)pgd); + else + kmem_cache_free(pgd_cache, pgd); +} +#else +static inline pgd_t *_pgd_alloc(void) +{ + return (pgd_t *)__get_free_page(PGALLOC_GFP); +} + +static inline void _pgd_free(pgd_t *pgd) +{ + free_page((unsigned long)pgd); +} +#endif /* CONFIG_X86_PAE */ + pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *pgd; pmd_t *pmds[PREALLOCATED_PMDS]; - pgd = (pgd_t *)__get_free_page(PGALLOC_GFP); + pgd = _pgd_alloc(); if (pgd == NULL) goto out; @@ -310,7 +386,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) out_free_pmds: free_pmds(mm, pmds); out_free_pgd: - free_page((unsigned long)pgd); + _pgd_free(pgd); out: return NULL; } @@ -320,7 +396,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) pgd_mop_up_pmds(mm, pgd); pgd_dtor(pgd); paravirt_pgd_free(mm, pgd); - free_page((unsigned long)pgd); + _pgd_free(pgd); } /* @@ -485,3 +561,67 @@ void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, { __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + u8 mtrr; + + /* + * Do not use a huge page when the range is covered by non-WB type + * of MTRRs. + */ + mtrr = mtrr_type_lookup(addr, addr + PUD_SIZE); + if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + return 0; + + prot = pgprot_4k_2_large(prot); + + set_pte((pte_t *)pud, pfn_pte( + (u64)addr >> PAGE_SHIFT, + __pgprot(pgprot_val(prot) | _PAGE_PSE))); + + return 1; +} + +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + u8 mtrr; + + /* + * Do not use a huge page when the range is covered by non-WB type + * of MTRRs. + */ + mtrr = mtrr_type_lookup(addr, addr + PMD_SIZE); + if ((mtrr != MTRR_TYPE_WRBACK) && (mtrr != 0xFF)) + return 0; + + prot = pgprot_4k_2_large(prot); + + set_pte((pte_t *)pmd, pfn_pte( + (u64)addr >> PAGE_SHIFT, + __pgprot(pgprot_val(prot) | _PAGE_PSE))); + + return 1; +} + +int pud_clear_huge(pud_t *pud) +{ + if (pud_large(*pud)) { + pud_clear(pud); + return 1; + } + + return 0; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + if (pmd_large(*pmd)) { + pmd_clear(pmd); + return 1; + } + + return 0; +} +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index 5d04be5efb64..4e664bdb535a 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -111,7 +111,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) { struct stack_frame *head = (struct stack_frame *)frame_pointer(regs); - if (!user_mode_vm(regs)) { + if (!user_mode(regs)) { unsigned long stack = kernel_stack_pointer(regs); if (depth) dump_trace(NULL, regs, (unsigned long *)stack, 0, diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2fb384724ebb..8fd6f44aee83 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -490,7 +490,9 @@ void pcibios_scan_root(int busnum) if (!bus) { pci_free_resource_list(&resources); kfree(sd); + return; } + pci_bus_add_devices(bus); } void __init pcibios_set_cache_line_size(void) diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index d143d216d52b..d7f997f7c26d 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/arch/x86/platform/efi/efi-bgrt.c @@ -67,7 +67,7 @@ void __init efi_bgrt_init(void) image = efi_lookup_mapped_addr(bgrt_tab->image_address); if (!image) { - image = early_memremap(bgrt_tab->image_address, + image = early_ioremap(bgrt_tab->image_address, sizeof(bmp_header)); ioremapped = true; if (!image) { @@ -89,7 +89,7 @@ void __init efi_bgrt_init(void) } if (ioremapped) { - image = early_memremap(bgrt_tab->image_address, + image = early_ioremap(bgrt_tab->image_address, bmp_header.size); if (!image) { pr_err("Ignoring BGRT: failed to map image memory\n"); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index dbc8627a5cdf..02744df576d5 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -85,12 +85,20 @@ static efi_status_t __init phys_efi_set_virtual_address_map( efi_memory_desc_t *virtual_map) { efi_status_t status; + unsigned long flags; + pgd_t *save_pgd; - efi_call_phys_prolog(); + save_pgd = efi_call_phys_prolog(); + + /* Disable interrupts around EFI calls: */ + local_irq_save(flags); status = efi_call_phys(efi_phys.set_virtual_address_map, memory_map_size, descriptor_size, descriptor_version, virtual_map); - efi_call_phys_epilog(); + local_irq_restore(flags); + + efi_call_phys_epilog(save_pgd); + return status; } @@ -491,7 +499,8 @@ void __init efi_init(void) if (efi_memmap_init()) return; - print_efi_memmap(); + if (efi_enabled(EFI_DBG)) + print_efi_memmap(); } void __init efi_late_init(void) @@ -939,6 +948,8 @@ static int __init arch_parse_efi_cmdline(char *str) { if (parse_option_str(str, "old_map")) set_bit(EFI_OLD_MEMMAP, &efi.flags); + if (parse_option_str(str, "debug")) + set_bit(EFI_DBG, &efi.flags); return 0; } diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 40e7cda52936..ed5b67338294 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -33,11 +33,10 @@ /* * To make EFI call EFI runtime service in physical addressing mode we need - * prolog/epilog before/after the invocation to disable interrupt, to - * claim EFI runtime service handler exclusively and to duplicate a memory in - * low memory space say 0 - 3G. + * prolog/epilog before/after the invocation to claim the EFI runtime service + * handler exclusively and to duplicate a memory mapping in low memory space, + * say 0 - 3G. */ -static unsigned long efi_rt_eflags; void efi_sync_low_kernel_mappings(void) {} void __init efi_dump_pagetable(void) {} @@ -57,21 +56,24 @@ void __init efi_map_region(efi_memory_desc_t *md) void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} -void __init efi_call_phys_prolog(void) +pgd_t * __init efi_call_phys_prolog(void) { struct desc_ptr gdt_descr; + pgd_t *save_pgd; - local_irq_save(efi_rt_eflags); - + /* Current pgd is swapper_pg_dir, we'll restore it later: */ + save_pgd = swapper_pg_dir; load_cr3(initial_page_table); __flush_tlb_all(); gdt_descr.address = __pa(get_cpu_gdt_table(0)); gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); + + return save_pgd; } -void __init efi_call_phys_epilog(void) +void __init efi_call_phys_epilog(pgd_t *save_pgd) { struct desc_ptr gdt_descr; @@ -79,10 +81,8 @@ void __init efi_call_phys_epilog(void) gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); - load_cr3(swapper_pg_dir); + load_cr3(save_pgd); __flush_tlb_all(); - - local_irq_restore(efi_rt_eflags); } void __init efi_runtime_mkexec(void) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 17e80d829df0..a0ac0f9c307f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -41,9 +41,6 @@ #include <asm/realmode.h> #include <asm/time.h> -static pgd_t *save_pgd __initdata; -static unsigned long efi_flags __initdata; - /* * We allocate runtime services regions bottom-up, starting from -4G, i.e. * 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G. @@ -78,17 +75,18 @@ static void __init early_code_mapping_set_exec(int executable) } } -void __init efi_call_phys_prolog(void) +pgd_t * __init efi_call_phys_prolog(void) { unsigned long vaddress; + pgd_t *save_pgd; + int pgd; int n_pgds; if (!efi_enabled(EFI_OLD_MEMMAP)) - return; + return NULL; early_code_mapping_set_exec(1); - local_irq_save(efi_flags); n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); save_pgd = kmalloc(n_pgds * sizeof(pgd_t), GFP_KERNEL); @@ -99,24 +97,29 @@ void __init efi_call_phys_prolog(void) set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress)); } __flush_tlb_all(); + + return save_pgd; } -void __init efi_call_phys_epilog(void) +void __init efi_call_phys_epilog(pgd_t *save_pgd) { /* * After the lock is released, the original page table is restored. */ - int pgd; - int n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + int pgd_idx; + int nr_pgds; - if (!efi_enabled(EFI_OLD_MEMMAP)) + if (!save_pgd) return; - for (pgd = 0; pgd < n_pgds; pgd++) - set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), save_pgd[pgd]); + nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE); + + for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) + set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]); + kfree(save_pgd); + __flush_tlb_all(); - local_irq_restore(efi_flags); early_code_mapping_set_exec(0); } diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index c9a0838890e2..278e4da4222f 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -11,6 +11,7 @@ */ #include <asm-generic/sections.h> +#include <asm/cpu_device_id.h> #include <asm/imr.h> #include <linux/init.h> #include <linux/mm.h> @@ -101,6 +102,12 @@ static void __init imr_self_test(void) } } +static const struct x86_cpu_id imr_ids[] __initconst = { + { X86_VENDOR_INTEL, 5, 9 }, /* Intel Quark SoC X1000. */ + {} +}; +MODULE_DEVICE_TABLE(x86cpu, imr_ids); + /** * imr_self_test_init - entry point for IMR driver. * @@ -108,7 +115,8 @@ static void __init imr_self_test(void) */ static int __init imr_self_test_init(void) { - imr_self_test(); + if (x86_match_cpu(imr_ids)) + imr_self_test(); return 0; } diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c index 9a2e590dd202..7fa8b3b53bc0 100644 --- a/arch/x86/platform/olpc/olpc-xo1-sci.c +++ b/arch/x86/platform/olpc/olpc-xo1-sci.c @@ -61,7 +61,7 @@ static void battery_status_changed(void) if (psy) { power_supply_changed(psy); - put_device(psy->dev); + power_supply_put(psy); } } @@ -71,7 +71,7 @@ static void ac_status_changed(void) if (psy) { power_supply_changed(psy); - put_device(psy->dev); + power_supply_put(psy); } } diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 08e350e757dc..55130846ac87 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -83,7 +83,7 @@ static void battery_status_changed(void) if (psy) { power_supply_changed(psy); - put_device(psy->dev); + power_supply_put(psy); } } @@ -93,7 +93,7 @@ static void ac_status_changed(void) if (psy) { power_supply_changed(psy); - put_device(psy->dev); + power_supply_put(psy); } } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 994798548b1a..3b6ec42718e4 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -415,7 +415,7 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp) struct reset_args reset_args; reset_args.sender = sender; - cpus_clear(*mask); + cpumask_clear(mask); /* find a single cpu for each uvhub in this distribution mask */ maskbits = sizeof(struct pnmask) * BITSPERBYTE; /* each bit is a pnode relative to the partition base pnode */ @@ -425,7 +425,7 @@ static void reset_with_ipi(struct pnmask *distribution, struct bau_control *bcp) continue; apnode = pnode + bcp->partition_base_pnode; cpu = pnode_to_first_cpu(apnode, smaster); - cpu_set(cpu, *mask); + cpumask_set_cpu(cpu, mask); } /* IPI all cpus; preemption is already disabled */ @@ -1126,7 +1126,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, /* don't actually do a shootdown of the local cpu */ cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); - if (cpu_isset(cpu, *cpumask)) + if (cpumask_test_cpu(cpu, cpumask)) stat->s_ntargself++; bau_desc = bcp->descriptor_base; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 3e32ed5648a0..757678fb26e1 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -134,7 +134,7 @@ static void do_fpu_end(void) static void fix_processor_context(void) { int cpu = smp_processor_id(); - struct tss_struct *t = &per_cpu(init_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 struct desc_struct *desc = get_cpu_gdt_table(cpu); tss_desc tss; diff --git a/arch/x86/syscalls/Makefile b/arch/x86/syscalls/Makefile index 3323c2745248..a55abb9f6c5e 100644 --- a/arch/x86/syscalls/Makefile +++ b/arch/x86/syscalls/Makefile @@ -19,6 +19,9 @@ quiet_cmd_syshdr = SYSHDR $@ quiet_cmd_systbl = SYSTBL $@ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@ +quiet_cmd_hypercalls = HYPERCALLS $@ + cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^) + syshdr_abi_unistd_32 := i386 $(uapi)/unistd_32.h: $(syscall32) $(syshdr) $(call if_changed,syshdr) @@ -47,10 +50,16 @@ $(out)/syscalls_32.h: $(syscall32) $(systbl) $(out)/syscalls_64.h: $(syscall64) $(systbl) $(call if_changed,systbl) +$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh + $(call if_changed,hypercalls) + +$(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h + uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h syshdr-y += syscalls_32.h syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h syshdr-$(CONFIG_X86_64) += syscalls_64.h +syshdr-$(CONFIG_XEN) += xen-hypercalls.h targets += $(uapisyshdr-y) $(syshdr-y) diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index b3560ece1c9f..ef8187f9d28d 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -119,7 +119,7 @@ 110 i386 iopl sys_iopl 111 i386 vhangup sys_vhangup 112 i386 idle -113 i386 vm86old sys_vm86old sys32_vm86_warning +113 i386 vm86old sys_vm86old sys_ni_syscall 114 i386 wait4 sys_wait4 compat_sys_wait4 115 i386 swapoff sys_swapoff 116 i386 sysinfo sys_sysinfo compat_sys_sysinfo @@ -172,7 +172,7 @@ 163 i386 mremap sys_mremap 164 i386 setresuid sys_setresuid16 165 i386 getresuid sys_getresuid16 -166 i386 vm86 sys_vm86 sys32_vm86_warning +166 i386 vm86 sys_vm86 sys_ni_syscall 167 i386 query_module 168 i386 poll sys_poll 169 i386 nfsservctl diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 8d656fbb57aa..9ef32d5f1b19 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -178,7 +178,7 @@ 169 common reboot sys_reboot 170 common sethostname sys_sethostname 171 common setdomainname sys_setdomainname -172 common iopl stub_iopl +172 common iopl sys_iopl 173 common ioperm sys_ioperm 174 64 create_module 175 common init_module sys_init_module diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index eafa324eb7a5..acb384d24669 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -21,7 +21,6 @@ obj-$(CONFIG_BINFMT_ELF) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o -subarch-$(CONFIG_HIGHMEM) += ../mm/highmem_32.o else diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h index 2d7d9a1f5b53..7e8a1a650435 100644 --- a/arch/x86/um/asm/barrier.h +++ b/arch/x86/um/asm/barrier.h @@ -36,22 +36,11 @@ #endif /* CONFIG_X86_PPRO_FENCE */ #define dma_wmb() barrier() -#ifdef CONFIG_SMP - -#define smp_mb() mb() -#define smp_rmb() dma_rmb() -#define smp_wmb() barrier() -#define set_mb(var, value) do { (void)xchg(&var, value); } while (0) - -#else /* CONFIG_SMP */ - #define smp_mb() barrier() #define smp_rmb() barrier() #define smp_wmb() barrier() #define set_mb(var, value) do { var = value; barrier(); } while (0) -#endif /* CONFIG_SMP */ - #define read_barrier_depends() do { } while (0) #define smp_read_barrier_depends() do { } while (0) @@ -64,8 +53,8 @@ */ static inline void rdtsc_barrier(void) { - alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); - alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); + alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, + "lfence", X86_FEATURE_LFENCE_RDTSC); } #endif diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index 25a1022dd793..0a656b727b1a 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -210,7 +210,7 @@ extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu); #define ELF_EXEC_PAGESIZE 4096 -#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3) +#define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) extern long elf_aux_hwcap; #define ELF_HWCAP (elf_aux_hwcap) diff --git a/arch/x86/um/ldt.c b/arch/x86/um/ldt.c index 8e08176f0bcb..5c0b711d2433 100644 --- a/arch/x86/um/ldt.c +++ b/arch/x86/um/ldt.c @@ -8,9 +8,7 @@ #include <linux/slab.h> #include <asm/unistd.h> #include <os.h> -#include <proc_mm.h> #include <skas.h> -#include <skas_ptrace.h> #include <sysdep/tls.h> extern int modify_ldt(int func, void *ptr, unsigned long bytecount); @@ -19,105 +17,20 @@ static long write_ldt_entry(struct mm_id *mm_idp, int func, struct user_desc *desc, void **addr, int done) { long res; - - if (proc_mm) { - /* - * This is a special handling for the case, that the mm to - * modify isn't current->active_mm. - * If this is called directly by modify_ldt, - * (current->active_mm->context.skas.u == mm_idp) - * will be true. So no call to __switch_mm(mm_idp) is done. - * If this is called in case of init_new_ldt or PTRACE_LDT, - * mm_idp won't belong to current->active_mm, but child->mm. - * So we need to switch child's mm into our userspace, then - * later switch back. - * - * Note: I'm unsure: should interrupts be disabled here? - */ - if (!current->active_mm || current->active_mm == &init_mm || - mm_idp != ¤t->active_mm->context.id) - __switch_mm(mm_idp); - } - - if (ptrace_ldt) { - struct ptrace_ldt ldt_op = (struct ptrace_ldt) { - .func = func, - .ptr = desc, - .bytecount = sizeof(*desc)}; - u32 cpu; - int pid; - - if (!proc_mm) - pid = mm_idp->u.pid; - else { - cpu = get_cpu(); - pid = userspace_pid[cpu]; - } - - res = os_ptrace_ldt(pid, 0, (unsigned long) &ldt_op); - - if (proc_mm) - put_cpu(); - } - else { - void *stub_addr; - res = syscall_stub_data(mm_idp, (unsigned long *)desc, - (sizeof(*desc) + sizeof(long) - 1) & - ~(sizeof(long) - 1), - addr, &stub_addr); - if (!res) { - unsigned long args[] = { func, - (unsigned long)stub_addr, - sizeof(*desc), - 0, 0, 0 }; - res = run_syscall_stub(mm_idp, __NR_modify_ldt, args, - 0, addr, done); - } + void *stub_addr; + res = syscall_stub_data(mm_idp, (unsigned long *)desc, + (sizeof(*desc) + sizeof(long) - 1) & + ~(sizeof(long) - 1), + addr, &stub_addr); + if (!res) { + unsigned long args[] = { func, + (unsigned long)stub_addr, + sizeof(*desc), + 0, 0, 0 }; + res = run_syscall_stub(mm_idp, __NR_modify_ldt, args, + 0, addr, done); } - if (proc_mm) { - /* - * This is the second part of special handling, that makes - * PTRACE_LDT possible to implement. - */ - if (current->active_mm && current->active_mm != &init_mm && - mm_idp != ¤t->active_mm->context.id) - __switch_mm(¤t->active_mm->context.id); - } - - return res; -} - -static long read_ldt_from_host(void __user * ptr, unsigned long bytecount) -{ - int res, n; - struct ptrace_ldt ptrace_ldt = (struct ptrace_ldt) { - .func = 0, - .bytecount = bytecount, - .ptr = kmalloc(bytecount, GFP_KERNEL)}; - u32 cpu; - - if (ptrace_ldt.ptr == NULL) - return -ENOMEM; - - /* - * This is called from sys_modify_ldt only, so userspace_pid gives - * us the right number - */ - - cpu = get_cpu(); - res = os_ptrace_ldt(userspace_pid[cpu], 0, (unsigned long) &ptrace_ldt); - put_cpu(); - if (res < 0) - goto out; - - n = copy_to_user(ptr, ptrace_ldt.ptr, res); - if (n != 0) - res = -EFAULT; - - out: - kfree(ptrace_ldt.ptr); - return res; } @@ -145,9 +58,6 @@ static int read_ldt(void __user * ptr, unsigned long bytecount) bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; err = bytecount; - if (ptrace_ldt) - return read_ldt_from_host(ptr, bytecount); - mutex_lock(&ldt->lock); if (ldt->entry_count <= LDT_DIRECT_ENTRIES) { size = LDT_ENTRY_SIZE*LDT_DIRECT_ENTRIES; @@ -229,17 +139,11 @@ static int write_ldt(void __user * ptr, unsigned long bytecount, int func) goto out; } - if (!ptrace_ldt) - mutex_lock(&ldt->lock); + mutex_lock(&ldt->lock); err = write_ldt_entry(mm_idp, func, &ldt_info, &addr, 1); if (err) goto out_unlock; - else if (ptrace_ldt) { - /* With PTRACE_LDT available, this is used as a flag only */ - ldt->entry_count = 1; - goto out; - } if (ldt_info.entry_number >= ldt->entry_count && ldt_info.entry_number >= LDT_DIRECT_ENTRIES) { @@ -393,91 +297,56 @@ long init_new_ldt(struct mm_context *new_mm, struct mm_context *from_mm) int i; long page, err=0; void *addr = NULL; - struct proc_mm_op copy; - if (!ptrace_ldt) - mutex_init(&new_mm->arch.ldt.lock); + mutex_init(&new_mm->arch.ldt.lock); if (!from_mm) { memset(&desc, 0, sizeof(desc)); /* - * We have to initialize a clean ldt. + * Now we try to retrieve info about the ldt, we + * inherited from the host. All ldt-entries found + * will be reset in the following loop */ - if (proc_mm) { - /* - * If the new mm was created using proc_mm, host's - * default-ldt currently is assigned, which normally - * contains the call-gates for lcall7 and lcall27. - * To remove these gates, we simply write an empty - * entry as number 0 to the host. - */ - err = write_ldt_entry(&new_mm->id, 1, &desc, &addr, 1); - } - else{ - /* - * Now we try to retrieve info about the ldt, we - * inherited from the host. All ldt-entries found - * will be reset in the following loop - */ - ldt_get_host_info(); - for (num_p=host_ldt_entries; *num_p != -1; num_p++) { - desc.entry_number = *num_p; - err = write_ldt_entry(&new_mm->id, 1, &desc, - &addr, *(num_p + 1) == -1); - if (err) - break; - } + ldt_get_host_info(); + for (num_p=host_ldt_entries; *num_p != -1; num_p++) { + desc.entry_number = *num_p; + err = write_ldt_entry(&new_mm->id, 1, &desc, + &addr, *(num_p + 1) == -1); + if (err) + break; } new_mm->arch.ldt.entry_count = 0; goto out; } - if (proc_mm) { - /* - * We have a valid from_mm, so we now have to copy the LDT of - * from_mm to new_mm, because using proc_mm an new mm with - * an empty/default LDT was created in new_mm() - */ - copy = ((struct proc_mm_op) { .op = MM_COPY_SEGMENTS, - .u = - { .copy_segments = - from_mm->id.u.mm_fd } } ); - i = os_write_file(new_mm->id.u.mm_fd, ©, sizeof(copy)); - if (i != sizeof(copy)) - printk(KERN_ERR "new_mm : /proc/mm copy_segments " - "failed, err = %d\n", -i); - } - - if (!ptrace_ldt) { - /* - * Our local LDT is used to supply the data for - * modify_ldt(READLDT), if PTRACE_LDT isn't available, - * i.e., we have to use the stub for modify_ldt, which - * can't handle the big read buffer of up to 64kB. - */ - mutex_lock(&from_mm->arch.ldt.lock); - if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES) - memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries, - sizeof(new_mm->arch.ldt.u.entries)); - else { - i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; - while (i-->0) { - page = __get_free_page(GFP_KERNEL|__GFP_ZERO); - if (!page) { - err = -ENOMEM; - break; - } - new_mm->arch.ldt.u.pages[i] = - (struct ldt_entry *) page; - memcpy(new_mm->arch.ldt.u.pages[i], - from_mm->arch.ldt.u.pages[i], PAGE_SIZE); + /* + * Our local LDT is used to supply the data for + * modify_ldt(READLDT), if PTRACE_LDT isn't available, + * i.e., we have to use the stub for modify_ldt, which + * can't handle the big read buffer of up to 64kB. + */ + mutex_lock(&from_mm->arch.ldt.lock); + if (from_mm->arch.ldt.entry_count <= LDT_DIRECT_ENTRIES) + memcpy(new_mm->arch.ldt.u.entries, from_mm->arch.ldt.u.entries, + sizeof(new_mm->arch.ldt.u.entries)); + else { + i = from_mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; + while (i-->0) { + page = __get_free_page(GFP_KERNEL|__GFP_ZERO); + if (!page) { + err = -ENOMEM; + break; } + new_mm->arch.ldt.u.pages[i] = + (struct ldt_entry *) page; + memcpy(new_mm->arch.ldt.u.pages[i], + from_mm->arch.ldt.u.pages[i], PAGE_SIZE); } - new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count; - mutex_unlock(&from_mm->arch.ldt.lock); } + new_mm->arch.ldt.entry_count = from_mm->arch.ldt.entry_count; + mutex_unlock(&from_mm->arch.ldt.lock); out: return err; @@ -488,7 +357,7 @@ void free_ldt(struct mm_context *mm) { int i; - if (!ptrace_ldt && mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) { + if (mm->arch.ldt.entry_count > LDT_DIRECT_ENTRIES) { i = mm->arch.ldt.entry_count / LDT_ENTRIES_PER_PAGE; while (i-- > 0) free_page((long) mm->arch.ldt.u.pages[i]); diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h index a26086b8a800..b6f2437ec29c 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_32.h +++ b/arch/x86/um/shared/sysdep/faultinfo_32.h @@ -27,9 +27,6 @@ struct faultinfo { /* This is Page Fault */ #define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14) -/* SKAS3 has no trap_no on i386, but get_skas_faultinfo() sets it to 0. */ -#define SEGV_MAYBE_FIXABLE(fi) ((fi)->trap_no == 0 && ptrace_faultinfo) - #define PTRACE_FULL_FAULTINFO 0 #endif diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h index f811cbe15d62..ee88f88974ea 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_64.h +++ b/arch/x86/um/shared/sysdep/faultinfo_64.h @@ -27,9 +27,6 @@ struct faultinfo { /* This is Page Fault */ #define SEGV_IS_FIXABLE(fi) ((fi)->trap_no == 14) -/* No broken SKAS API, which doesn't pass trap_no, here. */ -#define SEGV_MAYBE_FIXABLE(fi) 0 - #define PTRACE_FULL_FAULTINFO 1 #endif diff --git a/arch/x86/um/shared/sysdep/skas_ptrace.h b/arch/x86/um/shared/sysdep/skas_ptrace.h deleted file mode 100644 index 453febe98993..000000000000 --- a/arch/x86/um/shared/sysdep/skas_ptrace.h +++ /dev/null @@ -1,22 +0,0 @@ -/* - * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com) - * Licensed under the GPL - */ - -#ifndef __SYSDEP_X86_SKAS_PTRACE_H -#define __SYSDEP_X86_SKAS_PTRACE_H - -struct ptrace_faultinfo { - int is_write; - unsigned long addr; -}; - -struct ptrace_ldt { - int func; - void *ptr; - unsigned long bytecount; -}; - -#define PTRACE_LDT 54 - -#endif diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 0c8c32bfd792..592491d1d70d 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -549,13 +549,6 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, if (err) return err; - /* Set up registers for signal handler */ - { - struct exec_domain *ed = current_thread_info()->exec_domain; - if (unlikely(ed && ed->signal_invmap && sig < 32)) - sig = ed->signal_invmap[sig]; - } - PT_REGS_SP(regs) = (unsigned long) frame; PT_REGS_DI(regs) = sig; /* In case the signal handler was declared without prototypes */ diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c index 5cdfa9db2217..a75d8700472a 100644 --- a/arch/x86/um/sys_call_table_64.c +++ b/arch/x86/um/sys_call_table_64.c @@ -16,7 +16,7 @@ */ /* Not going to be implemented by UML, since we have no hardware. */ -#define stub_iopl sys_ni_syscall +#define sys_iopl sys_ni_syscall #define sys_ioperm sys_ni_syscall /* diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 7b9be9822724..275a3a8b78af 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -51,7 +51,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) -HOST_EXTRACFLAGS += -I$(srctree)/tools/include +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ @@ -206,4 +206,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE PHONY += vdso_install $(vdso_img_insttargets) vdso_install: $(vdso_img_insttargets) FORCE -clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* +clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 9793322751e0..40d2473836c9 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; + u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * Note: hypervisor must guarantee that: - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. - * 2. that per-CPU pvclock time info is updated if the - * underlying CPU changes. - * 3. that version is increased whenever underlying CPU - * changes. - * + * When looping to get a consistent (time-info, tsc) pair, we + * also need to deal with the possibility we can switch vcpus, + * so make sure we always re-fetch time-info for the current vcpu. */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -102,20 +99,27 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - pvti = get_pvti(cpu); + /* Make sure migrate_count will change if we leave the VCPU. */ + do { + pvti = get_pvti(cpu); + migrate_count = pvti->migrate_count; + + cpu1 = cpu; + cpu = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1)); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. + * - We must read TSC of pvti's VCPU. + * - KVM doesn't follow the versioning protocol, so data could + * change before version if we left the VCPU. */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); + smp_rmb(); + } while (unlikely((pvti->pvti.version & 1) || + pvti->pvti.version != version || + pvti->migrate_count != migrate_count)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/arch/x86/vdso/vdso32/syscall.S b/arch/x86/vdso/vdso32/syscall.S index 5415b5613d55..6b286bb5251c 100644 --- a/arch/x86/vdso/vdso32/syscall.S +++ b/arch/x86/vdso/vdso32/syscall.S @@ -19,8 +19,6 @@ __kernel_vsyscall: .Lpush_ebp: movl %ecx, %ebp syscall - movl $__USER32_DS, %ecx - movl %ecx, %ss movl %ebp, %ecx popl %ebp .Lpop_ebp: diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 7005ced5d1ad..70e060ad879a 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -7,6 +7,7 @@ #include <xen/xen.h> #include <xen/interface/physdev.h> #include "xen-ops.h" +#include "smp.h" static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) { @@ -28,7 +29,186 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) return 0xfd; } +static unsigned long xen_set_apic_id(unsigned int x) +{ + WARN_ON(1); + return x; +} + +static unsigned int xen_get_apic_id(unsigned long x) +{ + return ((x)>>24) & 0xFFu; +} + +static u32 xen_apic_read(u32 reg) +{ + struct xen_platform_op op = { + .cmd = XENPF_get_cpuinfo, + .interface_version = XENPF_INTERFACE_VERSION, + .u.pcpu_info.xen_cpuid = 0, + }; + int ret = 0; + + /* Shouldn't need this as APIC is turned off for PV, and we only + * get called on the bootup processor. But just in case. */ + if (!xen_initial_domain() || smp_processor_id()) + return 0; + + if (reg == APIC_LVR) + return 0x10; +#ifdef CONFIG_X86_32 + if (reg == APIC_LDR) + return SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); +#endif + if (reg != APIC_ID) + return 0; + + ret = HYPERVISOR_dom0_op(&op); + if (ret) + return 0; + + return op.u.pcpu_info.apic_id << 24; +} + +static void xen_apic_write(u32 reg, u32 val) +{ + /* Warn to see if there's any stray references */ + WARN(1,"register: %x, value: %x\n", reg, val); +} + +static u64 xen_apic_icr_read(void) +{ + return 0; +} + +static void xen_apic_icr_write(u32 low, u32 id) +{ + /* Warn to see if there's any stray references */ + WARN_ON(1); +} + +static u32 xen_safe_apic_wait_icr_idle(void) +{ + return 0; +} + +static int xen_apic_probe_pv(void) +{ + if (xen_pv_domain()) + return 1; + + return 0; +} + +static int xen_madt_oem_check(char *oem_id, char *oem_table_id) +{ + return xen_pv_domain(); +} + +static int xen_id_always_valid(int apicid) +{ + return 1; +} + +static int xen_id_always_registered(void) +{ + return 1; +} + +static int xen_phys_pkg_id(int initial_apic_id, int index_msb) +{ + return initial_apic_id >> index_msb; +} + +#ifdef CONFIG_X86_32 +static int xen_x86_32_early_logical_apicid(int cpu) +{ + /* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */ + return 1 << cpu; +} +#endif + +static void xen_noop(void) +{ +} + +static void xen_silent_inquire(int apicid) +{ +} + +static struct apic xen_pv_apic = { + .name = "Xen PV", + .probe = xen_apic_probe_pv, + .acpi_madt_oem_check = xen_madt_oem_check, + .apic_id_valid = xen_id_always_valid, + .apic_id_registered = xen_id_always_registered, + + /* .irq_delivery_mode - used in native_compose_msi_msg only */ + /* .irq_dest_mode - used in native_compose_msi_msg only */ + + .target_cpus = default_target_cpus, + .disable_esr = 0, + /* .dest_logical - default_send_IPI_ use it but we use our own. */ + .check_apicid_used = default_check_apicid_used, /* Used on 32-bit */ + + .vector_allocation_domain = flat_vector_allocation_domain, + .init_apic_ldr = xen_noop, /* setup_local_APIC calls it */ + + .ioapic_phys_id_map = default_ioapic_phys_id_map, /* Used on 32-bit */ + .setup_apic_routing = NULL, + .cpu_present_to_apicid = default_cpu_present_to_apicid, + .apicid_to_cpu_present = physid_set_mask_of_physid, /* Used on 32-bit */ + .check_phys_apicid_present = default_check_phys_apicid_present, /* smp_sanity_check needs it */ + .phys_pkg_id = xen_phys_pkg_id, /* detect_ht */ + + .get_apic_id = xen_get_apic_id, + .set_apic_id = xen_set_apic_id, /* Can be NULL on 32-bit. */ + .apic_id_mask = 0xFF << 24, /* Used by verify_local_APIC. Match with what xen_get_apic_id does. */ + + .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + +#ifdef CONFIG_SMP + .send_IPI_mask = xen_send_IPI_mask, + .send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself, + .send_IPI_allbutself = xen_send_IPI_allbutself, + .send_IPI_all = xen_send_IPI_all, + .send_IPI_self = xen_send_IPI_self, +#endif + /* .wait_for_init_deassert- used by AP bootup - smp_callin which we don't use */ + .inquire_remote_apic = xen_silent_inquire, + + .read = xen_apic_read, + .write = xen_apic_write, + .eoi_write = xen_apic_write, + + .icr_read = xen_apic_icr_read, + .icr_write = xen_apic_icr_write, + .wait_icr_idle = xen_noop, + .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle, + +#ifdef CONFIG_X86_32 + /* generic_processor_info and setup_local_APIC. */ + .x86_32_early_logical_apicid = xen_x86_32_early_logical_apicid, +#endif +}; + +static void __init xen_apic_check(void) +{ + if (apic == &xen_pv_apic) + return; + + pr_info("Switched APIC routing from %s to %s.\n", apic->name, + xen_pv_apic.name); + apic = &xen_pv_apic; +} void __init xen_init_apic(void) { x86_io_apic_ops.read = xen_io_apic_read; + /* On PV guests the APIC CPUID bit is disabled so none of the + * routines end up executing. */ + if (!xen_initial_domain()) + apic = &xen_pv_apic; + + x86_platform.apic_post_init = xen_apic_check; } +apic_driver(xen_pv_apic); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 5240f563076d..94578efd3067 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -912,6 +912,7 @@ static void xen_load_sp0(struct tss_struct *tss, mcs = xen_mc_entry(0); MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0); xen_mc_issue(PARAVIRT_LAZY_CPU); + tss->x86_tss.sp0 = thread->sp0; } static void xen_set_iopl_mask(unsigned mask) @@ -927,92 +928,6 @@ static void xen_io_delay(void) { } -#ifdef CONFIG_X86_LOCAL_APIC -static unsigned long xen_set_apic_id(unsigned int x) -{ - WARN_ON(1); - return x; -} -static unsigned int xen_get_apic_id(unsigned long x) -{ - return ((x)>>24) & 0xFFu; -} -static u32 xen_apic_read(u32 reg) -{ - struct xen_platform_op op = { - .cmd = XENPF_get_cpuinfo, - .interface_version = XENPF_INTERFACE_VERSION, - .u.pcpu_info.xen_cpuid = 0, - }; - int ret = 0; - - /* Shouldn't need this as APIC is turned off for PV, and we only - * get called on the bootup processor. But just in case. */ - if (!xen_initial_domain() || smp_processor_id()) - return 0; - - if (reg == APIC_LVR) - return 0x10; - - if (reg != APIC_ID) - return 0; - - ret = HYPERVISOR_dom0_op(&op); - if (ret) - return 0; - - return op.u.pcpu_info.apic_id << 24; -} - -static void xen_apic_write(u32 reg, u32 val) -{ - /* Warn to see if there's any stray references */ - WARN_ON(1); -} - -static u64 xen_apic_icr_read(void) -{ - return 0; -} - -static void xen_apic_icr_write(u32 low, u32 id) -{ - /* Warn to see if there's any stray references */ - WARN_ON(1); -} - -static void xen_apic_wait_icr_idle(void) -{ - return; -} - -static u32 xen_safe_apic_wait_icr_idle(void) -{ - return 0; -} - -static void set_xen_basic_apic_ops(void) -{ - apic->read = xen_apic_read; - apic->write = xen_apic_write; - apic->icr_read = xen_apic_icr_read; - apic->icr_write = xen_apic_icr_write; - apic->wait_icr_idle = xen_apic_wait_icr_idle; - apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle; - apic->set_apic_id = xen_set_apic_id; - apic->get_apic_id = xen_get_apic_id; - -#ifdef CONFIG_SMP - apic->send_IPI_allbutself = xen_send_IPI_allbutself; - apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself; - apic->send_IPI_mask = xen_send_IPI_mask; - apic->send_IPI_all = xen_send_IPI_all; - apic->send_IPI_self = xen_send_IPI_self; -#endif -} - -#endif - static void xen_clts(void) { struct multicall_space mcs; @@ -1618,7 +1533,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* * set up the basic apic ops. */ - set_xen_basic_apic_ops(); + xen_init_apic(); #endif if (xen_feature(XENFEAT_mmu_pt_update_preserve_ad)) { @@ -1731,8 +1646,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (HYPERVISOR_dom0_op(&op) == 0) boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; - xen_init_apic(); - /* Make sure ACS will be enabled */ pci_request_acs(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index adca9e2b6553..dd151b2045b0 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -502,7 +502,7 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 __visible pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); @@ -589,7 +589,7 @@ static void xen_set_pgd(pgd_t *ptr, pgd_t val) xen_mc_issue(PARAVIRT_LAZY_MMU); } -#endif /* PAGETABLE_LEVELS == 4 */ +#endif /* CONFIG_PGTABLE_LEVELS == 4 */ /* * (Yet another) pagetable walker. This one is intended for pinning a @@ -1628,7 +1628,7 @@ static void xen_release_pmd(unsigned long pfn) xen_release_ptpage(pfn, PT_PMD); } -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) { xen_alloc_ptpage(mm, pfn, PT_PUD); @@ -2046,7 +2046,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.set_pte = xen_set_pte; pv_mmu_ops.set_pmd = xen_set_pmd; pv_mmu_ops.set_pud = xen_set_pud; -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 pv_mmu_ops.set_pgd = xen_set_pgd; #endif @@ -2056,7 +2056,7 @@ static void __init xen_post_allocator_init(void) pv_mmu_ops.alloc_pmd = xen_alloc_pmd; pv_mmu_ops.release_pte = xen_release_pte; pv_mmu_ops.release_pmd = xen_release_pmd; -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 pv_mmu_ops.alloc_pud = xen_alloc_pud; pv_mmu_ops.release_pud = xen_release_pud; #endif @@ -2122,14 +2122,14 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), -#if PAGETABLE_LEVELS == 4 +#if CONFIG_PGTABLE_LEVELS == 4 .pud_val = PV_CALLEE_SAVE(xen_pud_val), .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_pgd = xen_set_pgd_hyper, .alloc_pud = xen_alloc_pmd_init, .release_pud = xen_release_pmd_init, -#endif /* PAGETABLE_LEVELS == 4 */ +#endif /* CONFIG_PGTABLE_LEVELS == 4 */ .activate_mm = xen_activate_mm, .dup_mmap = xen_dup_mmap, @@ -2436,99 +2436,11 @@ void __init xen_hvm_init_mmu_ops(void) } #endif -#ifdef CONFIG_XEN_PVH -/* - * Map foreign gfn (fgfn), to local pfn (lpfn). This for the user - * space creating new guest on pvh dom0 and needing to map domU pages. - */ -static int xlate_add_to_p2m(unsigned long lpfn, unsigned long fgfn, - unsigned int domid) -{ - int rc, err = 0; - xen_pfn_t gpfn = lpfn; - xen_ulong_t idx = fgfn; - - struct xen_add_to_physmap_range xatp = { - .domid = DOMID_SELF, - .foreign_domid = domid, - .size = 1, - .space = XENMAPSPACE_gmfn_foreign, - }; - set_xen_guest_handle(xatp.idxs, &idx); - set_xen_guest_handle(xatp.gpfns, &gpfn); - set_xen_guest_handle(xatp.errs, &err); - - rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp); - if (rc < 0) - return rc; - return err; -} - -static int xlate_remove_from_p2m(unsigned long spfn, int count) -{ - struct xen_remove_from_physmap xrp; - int i, rc; - - for (i = 0; i < count; i++) { - xrp.domid = DOMID_SELF; - xrp.gpfn = spfn+i; - rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp); - if (rc) - break; - } - return rc; -} - -struct xlate_remap_data { - unsigned long fgfn; /* foreign domain's gfn */ - pgprot_t prot; - domid_t domid; - int index; - struct page **pages; -}; - -static int xlate_map_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, - void *data) -{ - int rc; - struct xlate_remap_data *remap = data; - unsigned long pfn = page_to_pfn(remap->pages[remap->index++]); - pte_t pteval = pte_mkspecial(pfn_pte(pfn, remap->prot)); - - rc = xlate_add_to_p2m(pfn, remap->fgfn, remap->domid); - if (rc) - return rc; - native_set_pte(ptep, pteval); - - return 0; -} - -static int xlate_remap_gfn_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long mfn, - int nr, pgprot_t prot, unsigned domid, - struct page **pages) -{ - int err; - struct xlate_remap_data pvhdata; - - BUG_ON(!pages); - - pvhdata.fgfn = mfn; - pvhdata.prot = prot; - pvhdata.domid = domid; - pvhdata.index = 0; - pvhdata.pages = pages; - err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT, - xlate_map_pte_fn, &pvhdata); - flush_tlb_all(); - return err; -} -#endif - #define REMAP_BATCH_SIZE 16 struct remap_data { - unsigned long mfn; + xen_pfn_t *mfn; + bool contiguous; pgprot_t prot; struct mmu_update *mmu_update; }; @@ -2537,7 +2449,14 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct remap_data *rmd = data; - pte_t pte = pte_mkspecial(mfn_pte(rmd->mfn++, rmd->prot)); + pte_t pte = pte_mkspecial(mfn_pte(*rmd->mfn, rmd->prot)); + + /* If we have a contigious range, just update the mfn itself, + else update pointer to be "next mfn". */ + if (rmd->contiguous) + (*rmd->mfn)++; + else + rmd->mfn++; rmd->mmu_update->ptr = virt_to_machine(ptep).maddr; rmd->mmu_update->val = pte_val_ma(pte); @@ -2546,26 +2465,26 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, return 0; } -int xen_remap_domain_mfn_range(struct vm_area_struct *vma, - unsigned long addr, - xen_pfn_t mfn, int nr, - pgprot_t prot, unsigned domid, - struct page **pages) - +static int do_remap_mfn(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *mfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned domid, + struct page **pages) { + int err = 0; struct remap_data rmd; struct mmu_update mmu_update[REMAP_BATCH_SIZE]; - int batch; unsigned long range; - int err = 0; + int mapped = 0; BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO))); if (xen_feature(XENFEAT_auto_translated_physmap)) { #ifdef CONFIG_XEN_PVH /* We need to update the local page tables and the xen HAP */ - return xlate_remap_gfn_range(vma, addr, mfn, nr, prot, - domid, pages); + return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr, + prot, domid, pages); #else return -EINVAL; #endif @@ -2573,9 +2492,15 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, rmd.mfn = mfn; rmd.prot = prot; + /* We use the err_ptr to indicate if there we are doing a contigious + * mapping or a discontigious mapping. */ + rmd.contiguous = !err_ptr; while (nr) { - batch = min(REMAP_BATCH_SIZE, nr); + int index = 0; + int done = 0; + int batch = min(REMAP_BATCH_SIZE, nr); + int batch_left = batch; range = (unsigned long)batch << PAGE_SHIFT; rmd.mmu_update = mmu_update; @@ -2584,23 +2509,72 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, if (err) goto out; - err = HYPERVISOR_mmu_update(mmu_update, batch, NULL, domid); - if (err < 0) - goto out; + /* We record the error for each page that gives an error, but + * continue mapping until the whole set is done */ + do { + int i; + + err = HYPERVISOR_mmu_update(&mmu_update[index], + batch_left, &done, domid); + + /* + * @err_ptr may be the same buffer as @mfn, so + * only clear it after each chunk of @mfn is + * used. + */ + if (err_ptr) { + for (i = index; i < index + done; i++) + err_ptr[i] = 0; + } + if (err < 0) { + if (!err_ptr) + goto out; + err_ptr[i] = err; + done++; /* Skip failed frame. */ + } else + mapped += done; + batch_left -= done; + index += done; + } while (batch_left); nr -= batch; addr += range; + if (err_ptr) + err_ptr += batch; } - - err = 0; out: xen_flush_tlb_all(); - return err; + return err < 0 ? err : mapped; +} + +int xen_remap_domain_mfn_range(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t mfn, int nr, + pgprot_t prot, unsigned domid, + struct page **pages) +{ + return do_remap_mfn(vma, addr, &mfn, nr, NULL, prot, domid, pages); } EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range); +int xen_remap_domain_mfn_array(struct vm_area_struct *vma, + unsigned long addr, + xen_pfn_t *mfn, int nr, + int *err_ptr, pgprot_t prot, + unsigned domid, struct page **pages) +{ + /* We BUG_ON because it's a programmer error to pass a NULL err_ptr, + * and the consequences later is quite hard to detect what the actual + * cause of "wrong memory was mapped in". + */ + BUG_ON(err_ptr == NULL); + return do_remap_mfn(vma, addr, mfn, nr, err_ptr, prot, domid, pages); +} +EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array); + + /* Returns: 0 success */ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, int numpgs, struct page **pages) @@ -2609,22 +2583,7 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, return 0; #ifdef CONFIG_XEN_PVH - while (numpgs--) { - /* - * The mmu has already cleaned up the process mmu - * resources at this point (lookup_address will return - * NULL). - */ - unsigned long pfn = page_to_pfn(pages[numpgs]); - - xlate_remove_from_p2m(pfn, 1); - } - /* - * We don't need to flush tlbs because as part of - * xlate_remove_from_p2m, the hypervisor will do tlb flushes - * after removing the p2m entries from the EPT/NPT - */ - return 0; + return xen_xlate_unmap_gfn_range(vma, numpgs, pages); #else return -EINVAL; #endif diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 08e8489c47f1..86484384492e 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -90,14 +90,10 @@ static void cpu_bringup(void) set_cpu_online(cpu, true); - this_cpu_write(cpu_state, CPU_ONLINE); - - wmb(); + cpu_set_state_online(cpu); /* Implies full memory barrier. */ /* We can take interrupts now: we're officially "up". */ local_irq_enable(); - - wmb(); /* make sure everything is out */ } /* @@ -445,21 +441,19 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) { int rc; - per_cpu(current_task, cpu) = idle; -#ifdef CONFIG_X86_32 - irq_ctx_init(cpu); -#else - clear_tsk_thread_flag(idle, TIF_FORK); -#endif - per_cpu(kernel_stack, cpu) = - (unsigned long)task_stack_page(idle) - - KERNEL_STACK_OFFSET + THREAD_SIZE; + common_cpu_up(cpu, idle); xen_setup_runstate_info(cpu); xen_setup_timer(cpu); xen_init_lock_cpu(cpu); - per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* + * PV VCPUs are always successfully taken down (see 'while' loop + * in xen_cpu_die()), so -EBUSY is an error. + */ + rc = cpu_check_up_prepare(cpu); + if (rc) + return rc; /* make sure interrupts start blocked */ per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1; @@ -468,10 +462,6 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) if (rc) return rc; - if (num_online_cpus() == 1) - /* Just in case we booted with a single CPU. */ - alternatives_enable_smp(); - rc = xen_smp_intr_init(cpu); if (rc) return rc; @@ -479,10 +469,8 @@ static int xen_cpu_up(unsigned int cpu, struct task_struct *idle) rc = HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL); BUG_ON(rc); - while(per_cpu(cpu_state, cpu) != CPU_ONLINE) { + while (cpu_report_state(cpu) != CPU_ONLINE) HYPERVISOR_sched_op(SCHEDOP_yield, NULL); - barrier(); - } return 0; } @@ -511,11 +499,11 @@ static void xen_cpu_die(unsigned int cpu) schedule_timeout(HZ/10); } - cpu_die_common(cpu); - - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (common_cpu_die(cpu) == 0) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } static void xen_play_dead(void) /* used only with HOTPLUG_CPU */ @@ -747,6 +735,16 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc; + + /* + * This can happen if CPU was offlined earlier and + * offlining timed out in common_cpu_die(). + */ + if (cpu_report_state(cpu) == CPU_DEAD_FROZEN) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + } + /* * xen_smp_intr_init() needs to run before native_cpu_up() * so that IPI vectors are set up on the booting CPU before @@ -768,12 +766,6 @@ static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) return rc; } -static void xen_hvm_cpu_die(unsigned int cpu) -{ - xen_cpu_die(cpu); - native_cpu_die(cpu); -} - void __init xen_hvm_smp_init(void) { if (!xen_have_vector_callback) @@ -781,7 +773,7 @@ void __init xen_hvm_smp_init(void) smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; smp_ops.cpu_up = xen_hvm_cpu_up; - smp_ops.cpu_die = xen_hvm_cpu_die; + smp_ops.cpu_die = xen_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index c4df9dbd63b7..d9497698645a 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -1,5 +1,5 @@ #include <linux/types.h> -#include <linux/clockchips.h> +#include <linux/tick.h> #include <xen/interface/xen.h> #include <xen/grant_table.h> @@ -81,17 +81,14 @@ void xen_arch_post_suspend(int cancelled) static void xen_vcpu_notify_restore(void *data) { - unsigned long reason = (unsigned long)data; - /* Boot processor notified via generic timekeeping_resume() */ - if ( smp_processor_id() == 0) + if (smp_processor_id() == 0) return; - clockevents_notify(reason, NULL); + tick_resume_local(); } void xen_arch_resume(void) { - on_each_cpu(xen_vcpu_notify_restore, - (void *)CLOCK_EVT_NOTIFY_RESUME, 1); + on_each_cpu(xen_vcpu_notify_restore, NULL, 1); } diff --git a/arch/x86/xen/trace.c b/arch/x86/xen/trace.c index 520022d1a181..a702ec2f5931 100644 --- a/arch/x86/xen/trace.c +++ b/arch/x86/xen/trace.c @@ -1,54 +1,12 @@ #include <linux/ftrace.h> #include <xen/interface/xen.h> +#include <xen/interface/xen-mca.h> -#define N(x) [__HYPERVISOR_##x] = "("#x")" +#define HYPERCALL(x) [__HYPERVISOR_##x] = "("#x")", static const char *xen_hypercall_names[] = { - N(set_trap_table), - N(mmu_update), - N(set_gdt), - N(stack_switch), - N(set_callbacks), - N(fpu_taskswitch), - N(sched_op_compat), - N(dom0_op), - N(set_debugreg), - N(get_debugreg), - N(update_descriptor), - N(memory_op), - N(multicall), - N(update_va_mapping), - N(set_timer_op), - N(event_channel_op_compat), - N(xen_version), - N(console_io), - N(physdev_op_compat), - N(grant_table_op), - N(vm_assist), - N(update_va_mapping_otherdomain), - N(iret), - N(vcpu_op), - N(set_segment_base), - N(mmuext_op), - N(acm_op), - N(nmi_op), - N(sched_op), - N(callback_op), - N(xenoprof_op), - N(event_channel_op), - N(physdev_op), - N(hvm_op), - -/* Architecture-specific hypercall definitions. */ - N(arch_0), - N(arch_1), - N(arch_2), - N(arch_3), - N(arch_4), - N(arch_5), - N(arch_6), - N(arch_7), +#include <asm/xen-hypercalls.h> }; -#undef N +#undef HYPERCALL static const char *xen_hypercall_name(unsigned op) { diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 53adefda4275..985fc3ee0973 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -68,11 +68,11 @@ ENTRY(xen_sysret64) * We're already on the usermode stack at this point, but * still with the kernel gs, so we can easily switch back */ - movq %rsp, PER_CPU_VAR(old_rsp) + movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(kernel_stack), %rsp pushq $__USER_DS - pushq PER_CPU_VAR(old_rsp) + pushq PER_CPU_VAR(rsp_scratch) pushq %r11 pushq $__USER_CS pushq %rcx @@ -87,11 +87,11 @@ ENTRY(xen_sysret32) * We're already on the usermode stack at this point, but * still with the kernel gs, so we can easily switch back */ - movq %rsp, PER_CPU_VAR(old_rsp) + movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(kernel_stack), %rsp pushq $__USER32_DS - pushq PER_CPU_VAR(old_rsp) + pushq PER_CPU_VAR(rsp_scratch) pushq %r11 pushq $__USER32_CS pushq %rcx diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 674b222544b7..8afdfccf6086 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -12,6 +12,8 @@ #include <xen/interface/elfnote.h> #include <xen/interface/features.h> +#include <xen/interface/xen.h> +#include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> #ifdef CONFIG_XEN_PVH @@ -85,59 +87,14 @@ ENTRY(xen_pvh_early_cpu_init) .pushsection .text .balign PAGE_SIZE ENTRY(hypercall_page) -#define NEXT_HYPERCALL(x) \ - ENTRY(xen_hypercall_##x) \ - .skip 32 - -NEXT_HYPERCALL(set_trap_table) -NEXT_HYPERCALL(mmu_update) -NEXT_HYPERCALL(set_gdt) -NEXT_HYPERCALL(stack_switch) -NEXT_HYPERCALL(set_callbacks) -NEXT_HYPERCALL(fpu_taskswitch) -NEXT_HYPERCALL(sched_op_compat) -NEXT_HYPERCALL(platform_op) -NEXT_HYPERCALL(set_debugreg) -NEXT_HYPERCALL(get_debugreg) -NEXT_HYPERCALL(update_descriptor) -NEXT_HYPERCALL(ni) -NEXT_HYPERCALL(memory_op) -NEXT_HYPERCALL(multicall) -NEXT_HYPERCALL(update_va_mapping) -NEXT_HYPERCALL(set_timer_op) -NEXT_HYPERCALL(event_channel_op_compat) -NEXT_HYPERCALL(xen_version) -NEXT_HYPERCALL(console_io) -NEXT_HYPERCALL(physdev_op_compat) -NEXT_HYPERCALL(grant_table_op) -NEXT_HYPERCALL(vm_assist) -NEXT_HYPERCALL(update_va_mapping_otherdomain) -NEXT_HYPERCALL(iret) -NEXT_HYPERCALL(vcpu_op) -NEXT_HYPERCALL(set_segment_base) -NEXT_HYPERCALL(mmuext_op) -NEXT_HYPERCALL(xsm_op) -NEXT_HYPERCALL(nmi_op) -NEXT_HYPERCALL(sched_op) -NEXT_HYPERCALL(callback_op) -NEXT_HYPERCALL(xenoprof_op) -NEXT_HYPERCALL(event_channel_op) -NEXT_HYPERCALL(physdev_op) -NEXT_HYPERCALL(hvm_op) -NEXT_HYPERCALL(sysctl) -NEXT_HYPERCALL(domctl) -NEXT_HYPERCALL(kexec_op) -NEXT_HYPERCALL(tmem_op) /* 38 */ -ENTRY(xen_hypercall_rsvr) - .skip 320 -NEXT_HYPERCALL(mca) /* 48 */ -NEXT_HYPERCALL(arch_1) -NEXT_HYPERCALL(arch_2) -NEXT_HYPERCALL(arch_3) -NEXT_HYPERCALL(arch_4) -NEXT_HYPERCALL(arch_5) -NEXT_HYPERCALL(arch_6) - .balign PAGE_SIZE + .skip PAGE_SIZE + +#define HYPERCALL(n) \ + .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ + .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 +#include <asm/xen-hypercalls.h> +#undef HYPERCALL + .popsection ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") |