diff options
Diffstat (limited to 'arch/x86')
107 files changed, 3082 insertions, 1447 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 178084b4377..32a1918e1b8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -51,6 +51,7 @@ config X86 select HAVE_KERNEL_LZMA select HAVE_HW_BREAKPOINT select HAVE_ARCH_KMEMCHECK + select HAVE_USER_RETURN_NOTIFIER config OUTPUT_FORMAT string @@ -1331,7 +1332,9 @@ config MATH_EMULATION kernel, it won't hurt. config MTRR - bool "MTRR (Memory Type Range Register) support" + bool + default y + prompt "MTRR (Memory Type Range Register) support" if EMBEDDED ---help--- On Intel P6 family processors (Pentium Pro, Pentium II and later) the Memory Type Range Registers (MTRRs) may be used to control @@ -1397,7 +1400,8 @@ config MTRR_SANITIZER_SPARE_REG_NR_DEFAULT config X86_PAT bool - prompt "x86 PAT support" + default y + prompt "x86 PAT support" if EMBEDDED depends on MTRR ---help--- Use PAT attributes to setup page level cache control. @@ -1603,7 +1607,7 @@ config COMPAT_VDSO depends on X86_32 || IA32_EMULATION ---help--- Map the 32-bit VDSO to the predictable old-style address too. - ---help--- + Say N here if you are running a sufficiently recent glibc version (2.3.3 or later), to remove the high-mapped VDSO mapping and to exclusively use the randomized VDSO. diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 5e99762eb5c..08e442bc3ab 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -301,15 +301,11 @@ config X86_CPU # # Define implied options from the CPU selection here -config X86_L1_CACHE_BYTES +config X86_INTERNODE_CACHE_SHIFT int - default "128" if MPSC - default "64" if GENERIC_CPU || MK8 || MCORE2 || MATOM || X86_32 - -config X86_INTERNODE_CACHE_BYTES - int - default "4096" if X86_VSMP - default X86_L1_CACHE_BYTES if !X86_VSMP + default "12" if X86_VSMP + default "7" if NUMA + default X86_L1_CACHE_SHIFT config X86_CMPXCHG def_bool X86_64 || (X86_32 && !M386) @@ -317,9 +313,9 @@ config X86_CMPXCHG config X86_L1_CACHE_SHIFT int default "7" if MPENTIUM4 || MPSC + default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU default "4" if X86_ELAN || M486 || M386 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU config X86_XADD def_bool y diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index cbf0776dbec..1255d953c65 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -46,6 +46,13 @@ cflags-$(CONFIG_MGEODE_LX) += $(call cc-option,-march=geode,-march=pentium-mmx) # cpu entries cflags-$(CONFIG_X86_GENERIC) += $(call tune,generic,$(call tune,i686)) +# Work around the pentium-mmx code generator madness of gcc4.4.x which +# does stack alignment by generating horrible code _before_ the mcount +# prologue (push %ebp, mov %esp, %ebp) which breaks the function graph +# tracer assumptions. For i686, generic, core2 this is set by the +# compiler anyway +cflags-$(CONFIG_FUNCTION_GRAPH_TRACER) += $(call cc-option,-maccumulate-outgoing-args) + # Bug fix for binutils: this option is required in order to keep # binutils from generating NOPL instructions against our will. ifneq ($(CONFIG_X86_P6_NOP),y) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 077e1b69198..faff0dc9c06 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -107,8 +107,7 @@ ENTRY(startup_32) lgdt gdt(%ebp) /* Enable PAE mode */ - xorl %eax, %eax - orl $(X86_CR4_PAE), %eax + movl $(X86_CR4_PAE), %eax movl %eax, %cr4 /* diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index f4193bb4878..a6f1a59a5b0 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -4,6 +4,7 @@ OUTPUT_FORMAT(CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT, CONFIG_OUTPUT_FORMAT) #undef i386 +#include <asm/cache.h> #include <asm/page_types.h> #ifdef CONFIG_X86_64 @@ -46,7 +47,7 @@ SECTIONS *(.data.*) _edata = . ; } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .bss : { _bss = . ; *(.bss) diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c index d42da380249..f767164cd5d 100644 --- a/arch/x86/boot/video.c +++ b/arch/x86/boot/video.c @@ -27,6 +27,12 @@ static void store_cursor_position(void) boot_params.screen_info.orig_x = oreg.dl; boot_params.screen_info.orig_y = oreg.dh; + + if (oreg.ch & 0x20) + boot_params.screen_info.flags |= VIDEO_FLAGS_NOCURSOR; + + if ((oreg.ch & 0x1f) > (oreg.cl & 0x1f)) + boot_params.screen_info.flags |= VIDEO_FLAGS_NOCURSOR; } static void store_video_mode(void) diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index cfb0010fa94..1a58ad89fdf 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o +obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o obj-$(CONFIG_CRYPTO_CRC32C_INTEL) += crc32c-intel.o @@ -24,3 +25,5 @@ twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o + +ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index eb0566e8331..20bb0e1ac68 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -16,6 +16,7 @@ */ #include <linux/linkage.h> +#include <asm/inst.h> .text @@ -122,103 +123,72 @@ ENTRY(aesni_set_key) movups 0x10(%rsi), %xmm2 # other user key movaps %xmm2, (%rcx) add $0x10, %rcx - # aeskeygenassist $0x1, %xmm2, %xmm1 # round 1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x01 + AESKEYGENASSIST 0x1 %xmm2 %xmm1 # round 1 call _key_expansion_256a - # aeskeygenassist $0x1, %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + AESKEYGENASSIST 0x1 %xmm0 %xmm1 call _key_expansion_256b - # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + AESKEYGENASSIST 0x2 %xmm2 %xmm1 # round 2 call _key_expansion_256a - # aeskeygenassist $0x2, %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + AESKEYGENASSIST 0x2 %xmm0 %xmm1 call _key_expansion_256b - # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + AESKEYGENASSIST 0x4 %xmm2 %xmm1 # round 3 call _key_expansion_256a - # aeskeygenassist $0x4, %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + AESKEYGENASSIST 0x4 %xmm0 %xmm1 call _key_expansion_256b - # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + AESKEYGENASSIST 0x8 %xmm2 %xmm1 # round 4 call _key_expansion_256a - # aeskeygenassist $0x8, %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + AESKEYGENASSIST 0x8 %xmm0 %xmm1 call _key_expansion_256b - # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + AESKEYGENASSIST 0x10 %xmm2 %xmm1 # round 5 call _key_expansion_256a - # aeskeygenassist $0x10, %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + AESKEYGENASSIST 0x10 %xmm0 %xmm1 call _key_expansion_256b - # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + AESKEYGENASSIST 0x20 %xmm2 %xmm1 # round 6 call _key_expansion_256a - # aeskeygenassist $0x20, %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + AESKEYGENASSIST 0x20 %xmm0 %xmm1 call _key_expansion_256b - # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + AESKEYGENASSIST 0x40 %xmm2 %xmm1 # round 7 call _key_expansion_256a jmp .Ldec_key .Lenc_key192: movq 0x10(%rsi), %xmm2 # other user key - # aeskeygenassist $0x1, %xmm2, %xmm1 # round 1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x01 + AESKEYGENASSIST 0x1 %xmm2 %xmm1 # round 1 call _key_expansion_192a - # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + AESKEYGENASSIST 0x2 %xmm2 %xmm1 # round 2 call _key_expansion_192b - # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + AESKEYGENASSIST 0x4 %xmm2 %xmm1 # round 3 call _key_expansion_192a - # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + AESKEYGENASSIST 0x8 %xmm2 %xmm1 # round 4 call _key_expansion_192b - # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + AESKEYGENASSIST 0x10 %xmm2 %xmm1 # round 5 call _key_expansion_192a - # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + AESKEYGENASSIST 0x20 %xmm2 %xmm1 # round 6 call _key_expansion_192b - # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + AESKEYGENASSIST 0x40 %xmm2 %xmm1 # round 7 call _key_expansion_192a - # aeskeygenassist $0x80, %xmm2, %xmm1 # round 8 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x80 + AESKEYGENASSIST 0x80 %xmm2 %xmm1 # round 8 call _key_expansion_192b jmp .Ldec_key .Lenc_key128: - # aeskeygenassist $0x1, %xmm0, %xmm1 # round 1 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + AESKEYGENASSIST 0x1 %xmm0 %xmm1 # round 1 call _key_expansion_128 - # aeskeygenassist $0x2, %xmm0, %xmm1 # round 2 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + AESKEYGENASSIST 0x2 %xmm0 %xmm1 # round 2 call _key_expansion_128 - # aeskeygenassist $0x4, %xmm0, %xmm1 # round 3 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + AESKEYGENASSIST 0x4 %xmm0 %xmm1 # round 3 call _key_expansion_128 - # aeskeygenassist $0x8, %xmm0, %xmm1 # round 4 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + AESKEYGENASSIST 0x8 %xmm0 %xmm1 # round 4 call _key_expansion_128 - # aeskeygenassist $0x10, %xmm0, %xmm1 # round 5 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + AESKEYGENASSIST 0x10 %xmm0 %xmm1 # round 5 call _key_expansion_128 - # aeskeygenassist $0x20, %xmm0, %xmm1 # round 6 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + AESKEYGENASSIST 0x20 %xmm0 %xmm1 # round 6 call _key_expansion_128 - # aeskeygenassist $0x40, %xmm0, %xmm1 # round 7 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x40 + AESKEYGENASSIST 0x40 %xmm0 %xmm1 # round 7 call _key_expansion_128 - # aeskeygenassist $0x80, %xmm0, %xmm1 # round 8 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x80 + AESKEYGENASSIST 0x80 %xmm0 %xmm1 # round 8 call _key_expansion_128 - # aeskeygenassist $0x1b, %xmm0, %xmm1 # round 9 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x1b + AESKEYGENASSIST 0x1b %xmm0 %xmm1 # round 9 call _key_expansion_128 - # aeskeygenassist $0x36, %xmm0, %xmm1 # round 10 - .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x36 + AESKEYGENASSIST 0x36 %xmm0 %xmm1 # round 10 call _key_expansion_128 .Ldec_key: sub $0x10, %rcx @@ -231,8 +201,7 @@ ENTRY(aesni_set_key) .align 4 .Ldec_key_loop: movaps (%rdi), %xmm0 - # aesimc %xmm0, %xmm1 - .byte 0x66, 0x0f, 0x38, 0xdb, 0xc8 + AESIMC %xmm0 %xmm1 movaps %xmm1, (%rsi) add $0x10, %rdi sub $0x10, %rsi @@ -274,51 +243,37 @@ _aesni_enc1: je .Lenc192 add $0x20, TKEYP movaps -0x60(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps -0x50(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE .align 4 .Lenc192: movaps -0x40(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps -0x30(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE .align 4 .Lenc128: movaps -0x20(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps -0x10(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps (TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x10(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x20(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x30(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x40(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x50(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x60(TKEYP), KEY - # aesenc KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + AESENC KEY STATE movaps 0x70(TKEYP), KEY - # aesenclast KEY, STATE # last round - .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 + AESENCLAST KEY STATE ret /* @@ -353,135 +308,79 @@ _aesni_enc4: je .L4enc192 add $0x20, TKEYP movaps -0x60(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps -0x50(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 #.align 4 .L4enc192: movaps -0x40(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps -0x30(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 #.align 4 .L4enc128: movaps -0x20(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps -0x10(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps (TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x10(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x20(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x30(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x40(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x50(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x60(TKEYP), KEY - # aesenc KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 - # aesenc KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xe2 - # aesenc KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xea - # aesenc KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdc, 0xf2 + AESENC KEY STATE1 + AESENC KEY STATE2 + AESENC KEY STATE3 + AESENC KEY STATE4 movaps 0x70(TKEYP), KEY - # aesenclast KEY, STATE1 # last round - .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 - # aesenclast KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdd, 0xe2 - # aesenclast KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdd, 0xea - # aesenclast KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdd, 0xf2 + AESENCLAST KEY STATE1 # last round + AESENCLAST KEY STATE2 + AESENCLAST KEY STATE3 + AESENCLAST KEY STATE4 ret /* @@ -518,51 +417,37 @@ _aesni_dec1: je .Ldec192 add $0x20, TKEYP movaps -0x60(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps -0x50(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE .align 4 .Ldec192: movaps -0x40(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps -0x30(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE .align 4 .Ldec128: movaps -0x20(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps -0x10(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps (TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x10(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x20(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x30(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x40(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x50(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x60(TKEYP), KEY - # aesdec KEY, STATE - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + AESDEC KEY STATE movaps 0x70(TKEYP), KEY - # aesdeclast KEY, STATE # last round - .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 + AESDECLAST KEY STATE ret /* @@ -597,135 +482,79 @@ _aesni_dec4: je .L4dec192 add $0x20, TKEYP movaps -0x60(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps -0x50(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 .align 4 .L4dec192: movaps -0x40(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps -0x30(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 .align 4 .L4dec128: movaps -0x20(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps -0x10(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps (TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x10(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x20(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x30(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x40(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x50(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x60(TKEYP), KEY - # aesdec KEY, STATE1 - .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 - # aesdec KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xde, 0xe2 - # aesdec KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xde, 0xea - # aesdec KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xde, 0xf2 + AESDEC KEY STATE1 + AESDEC KEY STATE2 + AESDEC KEY STATE3 + AESDEC KEY STATE4 movaps 0x70(TKEYP), KEY - # aesdeclast KEY, STATE1 # last round - .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 - # aesdeclast KEY, STATE2 - .byte 0x66, 0x0f, 0x38, 0xdf, 0xe2 - # aesdeclast KEY, STATE3 - .byte 0x66, 0x0f, 0x38, 0xdf, 0xea - # aesdeclast KEY, STATE4 - .byte 0x66, 0x0f, 0x38, 0xdf, 0xf2 + AESDECLAST KEY STATE1 # last round + AESDECLAST KEY STATE2 + AESDECLAST KEY STATE3 + AESDECLAST KEY STATE4 ret /* diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S new file mode 100644 index 00000000000..1eb7f90cb7b --- /dev/null +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -0,0 +1,157 @@ +/* + * Accelerated GHASH implementation with Intel PCLMULQDQ-NI + * instructions. This file contains accelerated part of ghash + * implementation. More information about PCLMULQDQ can be found at: + * + * http://software.intel.com/en-us/articles/carry-less-multiplication-and-its-usage-for-computing-the-gcm-mode/ + * + * Copyright (c) 2009 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * Vinodh Gopal + * Erdinc Ozturk + * Deniz Karakoyunlu + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/inst.h> + +.data + +.align 16 +.Lbswap_mask: + .octa 0x000102030405060708090a0b0c0d0e0f +.Lpoly: + .octa 0xc2000000000000000000000000000001 +.Ltwo_one: + .octa 0x00000001000000000000000000000001 + +#define DATA %xmm0 +#define SHASH %xmm1 +#define T1 %xmm2 +#define T2 %xmm3 +#define T3 %xmm4 +#define BSWAP %xmm5 +#define IN1 %xmm6 + +.text + +/* + * __clmul_gf128mul_ble: internal ABI + * input: + * DATA: operand1 + * SHASH: operand2, hash_key << 1 mod poly + * output: + * DATA: operand1 * operand2 mod poly + * changed: + * T1 + * T2 + * T3 + */ +__clmul_gf128mul_ble: + movaps DATA, T1 + pshufd $0b01001110, DATA, T2 + pshufd $0b01001110, SHASH, T3 + pxor DATA, T2 + pxor SHASH, T3 + + PCLMULQDQ 0x00 SHASH DATA # DATA = a0 * b0 + PCLMULQDQ 0x11 SHASH T1 # T1 = a1 * b1 + PCLMULQDQ 0x00 T3 T2 # T2 = (a1 + a0) * (b1 + b0) + pxor DATA, T2 + pxor T1, T2 # T2 = a0 * b1 + a1 * b0 + + movaps T2, T3 + pslldq $8, T3 + psrldq $8, T2 + pxor T3, DATA + pxor T2, T1 # <T1:DATA> is result of + # carry-less multiplication + + # first phase of the reduction + movaps DATA, T3 + psllq $1, T3 + pxor DATA, T3 + psllq $5, T3 + pxor DATA, T3 + psllq $57, T3 + movaps T3, T2 + pslldq $8, T2 + psrldq $8, T3 + pxor T2, DATA + pxor T3, T1 + + # second phase of the reduction + movaps DATA, T2 + psrlq $5, T2 + pxor DATA, T2 + psrlq $1, T2 + pxor DATA, T2 + psrlq $1, T2 + pxor T2, T1 + pxor T1, DATA + ret + +/* void clmul_ghash_mul(char *dst, const be128 *shash) */ +ENTRY(clmul_ghash_mul) + movups (%rdi), DATA + movups (%rsi), SHASH + movaps .Lbswap_mask, BSWAP + PSHUFB_XMM BSWAP DATA + call __clmul_gf128mul_ble + PSHUFB_XMM BSWAP DATA + movups DATA, (%rdi) + ret + +/* + * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, + * const be128 *shash); + */ +ENTRY(clmul_ghash_update) + cmp $16, %rdx + jb .Lupdate_just_ret # check length + movaps .Lbswap_mask, BSWAP + movups (%rdi), DATA + movups (%rcx), SHASH + PSHUFB_XMM BSWAP DATA +.align 4 +.Lupdate_loop: + movups (%rsi), IN1 + PSHUFB_XMM BSWAP IN1 + pxor IN1, DATA + call __clmul_gf128mul_ble + sub $16, %rdx + add $16, %rsi + cmp $16, %rdx + jge .Lupdate_loop + PSHUFB_XMM BSWAP DATA + movups DATA, (%rdi) +.Lupdate_just_ret: + ret + +/* + * void clmul_ghash_setkey(be128 *shash, const u8 *key); + * + * Calculate hash_key << 1 mod poly + */ +ENTRY(clmul_ghash_setkey) + movaps .Lbswap_mask, BSWAP + movups (%rsi), %xmm0 + PSHUFB_XMM BSWAP %xmm0 + movaps %xmm0, %xmm1 + psllq $1, %xmm0 + psrlq $63, %xmm1 + movaps %xmm1, %xmm2 + pslldq $8, %xmm1 + psrldq $8, %xmm2 + por %xmm1, %xmm0 + # reduction + pshufd $0b00100100, %xmm2, %xmm1 + pcmpeqd .Ltwo_one, %xmm1 + pand .Lpoly, %xmm1 + pxor %xmm1, %xmm0 + movups %xmm0, (%rdi) + ret diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c new file mode 100644 index 00000000000..cbcc8d8ea93 --- /dev/null +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -0,0 +1,333 @@ +/* + * Accelerated GHASH implementation with Intel PCLMULQDQ-NI + * instructions. This file contains glue code. + * + * Copyright (c) 2009 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/crypto.h> +#include <crypto/algapi.h> +#include <crypto/cryptd.h> +#include <crypto/gf128mul.h> +#include <crypto/internal/hash.h> +#include <asm/i387.h> + +#define GHASH_BLOCK_SIZE 16 +#define GHASH_DIGEST_SIZE 16 + +void clmul_ghash_mul(char *dst, const be128 *shash); + +void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, + const be128 *shash); + +void clmul_ghash_setkey(be128 *shash, const u8 *key); + +struct ghash_async_ctx { + struct cryptd_ahash *cryptd_tfm; +}; + +struct ghash_ctx { + be128 shash; +}; + +struct ghash_desc_ctx { + u8 buffer[GHASH_BLOCK_SIZE]; + u32 bytes; +}; + +static int ghash_init(struct shash_desc *desc) +{ + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + memset(dctx, 0, sizeof(*dctx)); + + return 0; +} + +static int ghash_setkey(struct crypto_shash *tfm, + const u8 *key, unsigned int keylen) +{ + struct ghash_ctx *ctx = crypto_shash_ctx(tfm); + + if (keylen != GHASH_BLOCK_SIZE) { + crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + + clmul_ghash_setkey(&ctx->shash, key); + + return 0; +} + +static int ghash_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); + u8 *dst = dctx->buffer; + + kernel_fpu_begin(); + if (dctx->bytes) { + int n = min(srclen, dctx->bytes); + u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes); + + dctx->bytes -= n; + srclen -= n; + + while (n--) + *pos++ ^= *src++; + + if (!dctx->bytes) + clmul_ghash_mul(dst, &ctx->shash); + } + + clmul_ghash_update(dst, src, srclen, &ctx->shash); + kernel_fpu_end(); + + if (srclen & 0xf) { + src += srclen - (srclen & 0xf); + srclen &= 0xf; + dctx->bytes = GHASH_BLOCK_SIZE - srclen; + while (srclen--) + *dst++ ^= *src++; + } + + return 0; +} + +static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx) +{ + u8 *dst = dctx->buffer; + + if (dctx->bytes) { + u8 *tmp = dst + (GHASH_BLOCK_SIZE - dctx->bytes); + + while (dctx->bytes--) + *tmp++ ^= 0; + + kernel_fpu_begin(); + clmul_ghash_mul(dst, &ctx->shash); + kernel_fpu_end(); + } + + dctx->bytes = 0; +} + +static int ghash_final(struct shash_desc *desc, u8 *dst) +{ + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm); + u8 *buf = dctx->buffer; + + ghash_flush(ctx, dctx); + memcpy(dst, buf, GHASH_BLOCK_SIZE); + + return 0; +} + +static struct shash_alg ghash_alg = { + .digestsize = GHASH_DIGEST_SIZE, + .init = ghash_init, + .update = ghash_update, + .final = ghash_final, + .setkey = ghash_setkey, + .descsize = sizeof(struct ghash_desc_ctx), + .base = { + .cra_name = "__ghash", + .cra_driver_name = "__ghash-pclmulqdqni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = GHASH_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct ghash_ctx), + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ghash_alg.base.cra_list), + }, +}; + +static int ghash_async_init(struct ahash_request *req) +{ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm); + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm; + + if (!irq_fpu_usable()) { + memcpy(cryptd_req, req, sizeof(*req)); + ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base); + return crypto_ahash_init(cryptd_req); + } else { + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm); + + desc->tfm = child; + desc->flags = req->base.flags; + return crypto_shash_init(desc); + } +} + +static int ghash_async_update(struct ahash_request *req) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + + if (!irq_fpu_usable()) { + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm); + struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm; + + memcpy(cryptd_req, req, sizeof(*req)); + ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base); + return crypto_ahash_update(cryptd_req); + } else { + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + return shash_ahash_update(req, desc); + } +} + +static int ghash_async_final(struct ahash_request *req) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + + if (!irq_fpu_usable()) { + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm); + struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm; + + memcpy(cryptd_req, req, sizeof(*req)); + ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base); + return crypto_ahash_final(cryptd_req); + } else { + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + return crypto_shash_final(desc, req->result); + } +} + +static int ghash_async_digest(struct ahash_request *req) +{ + struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); + struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm); + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm; + + if (!irq_fpu_usable()) { + memcpy(cryptd_req, req, sizeof(*req)); + ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base); + return crypto_ahash_digest(cryptd_req); + } else { + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm); + + desc->tfm = child; + desc->flags = req->base.flags; + return shash_ahash_digest(req, desc); + } +} + +static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key, + unsigned int keylen) +{ + struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm); + struct crypto_ahash *child = &ctx->cryptd_tfm->base; + int err; + + crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK); + crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm) + & CRYPTO_TFM_REQ_MASK); + err = crypto_ahash_setkey(child, key, keylen); + crypto_ahash_set_flags(tfm, crypto_ahash_get_flags(child) + & CRYPTO_TFM_RES_MASK); + + return 0; +} + +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); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ctx->cryptd_tfm = cryptd_tfm; + crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm), + sizeof(struct ahash_request) + + crypto_ahash_reqsize(&cryptd_tfm->base)); + + return 0; +} + +static void ghash_async_exit_tfm(struct crypto_tfm *tfm) +{ + struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm); + + cryptd_free_ahash(ctx->cryptd_tfm); +} + +static struct ahash_alg ghash_async_alg = { + .init = ghash_async_init, + .update = ghash_async_update, + .final = ghash_async_final, + .setkey = ghash_async_setkey, + .digest = ghash_async_digest, + .halg = { + .digestsize = GHASH_DIGEST_SIZE, + .base = { + .cra_name = "ghash", + .cra_driver_name = "ghash-clmulni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC, + .cra_blocksize = GHASH_BLOCK_SIZE, + .cra_type = &crypto_ahash_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ghash_async_alg.halg.base.cra_list), + .cra_init = ghash_async_init_tfm, + .cra_exit = ghash_async_exit_tfm, + }, + }, +}; + +static int __init ghash_pclmulqdqni_mod_init(void) +{ + int err; + + if (!cpu_has_pclmulqdq) { + printk(KERN_INFO "Intel PCLMULQDQ-NI instructions are not" + " detected.\n"); + return -ENODEV; + } + + err = crypto_register_shash(&ghash_alg); + if (err) + goto err_out; + err = crypto_register_ahash(&ghash_async_alg); + if (err) + goto err_shash; + + return 0; + +err_shash: + crypto_unregister_shash(&ghash_alg); +err_out: + return err; +} + +static void __exit ghash_pclmulqdqni_mod_exit(void) +{ + crypto_unregister_ahash(&ghash_async_alg); + crypto_unregister_shash(&ghash_alg); +} + +module_init(ghash_pclmulqdqni_mod_init); +module_exit(ghash_pclmulqdqni_mod_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("GHASH Message Digest Algorithm, " + "acclerated by PCLMULQDQ-NI"); +MODULE_ALIAS("ghash"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 581b0568fe1..4eefdca9832 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -653,7 +653,7 @@ ia32_sys_call_table: .quad compat_sys_writev .quad sys_getsid .quad sys_fdatasync - .quad sys32_sysctl /* sysctl */ + .quad compat_sys_sysctl /* sysctl */ .quad sys_mlock /* 150 */ .quad sys_munlock .quad sys_mlockall @@ -841,4 +841,5 @@ ia32_sys_call_table: .quad compat_sys_pwritev .quad compat_sys_rt_tgsigqueueinfo /* 335 */ .quad sys_perf_event_open + .quad compat_sys_recvmmsg ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 9f552719882..df82c0e48de 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -434,62 +434,6 @@ asmlinkage long sys32_rt_sigqueueinfo(int pid, int sig, return ret; } -#ifdef CONFIG_SYSCTL_SYSCALL -struct sysctl_ia32 { - unsigned int name; - int nlen; - unsigned int oldval; - unsigned int oldlenp; - unsigned int newval; - unsigned int newlen; - unsigned int __unused[4]; -}; - - -asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *args32) -{ - struct sysctl_ia32 a32; - mm_segment_t old_fs = get_fs(); - void __user *oldvalp, *newvalp; - size_t oldlen; - int __user *namep; - long ret; - - if (copy_from_user(&a32, args32, sizeof(a32))) - return -EFAULT; - - /* - * We need to pre-validate these because we have to disable - * address checking before calling do_sysctl() because of - * OLDLEN but we can't run the risk of the user specifying bad - * addresses here. Well, since we're dealing with 32 bit - * addresses, we KNOW that access_ok() will always succeed, so - * this is an expensive NOP, but so what... - */ - namep = compat_ptr(a32.name); - oldvalp = compat_ptr(a32.oldval); - newvalp = compat_ptr(a32.newval); - - if ((oldvalp && get_user(oldlen, (int __user *)compat_ptr(a32.oldlenp))) - || !access_ok(VERIFY_WRITE, namep, 0) - || !access_ok(VERIFY_WRITE, oldvalp, 0) - || !access_ok(VERIFY_WRITE, newvalp, 0)) - return -EFAULT; - - set_fs(KERNEL_DS); - lock_kernel(); - ret = do_sysctl(namep, a32.nlen, oldvalp, (size_t __user *)&oldlen, - newvalp, (size_t) a32.newlen); - unlock_kernel(); - set_fs(old_fs); - - if (oldvalp && put_user(oldlen, (int __user *)compat_ptr(a32.oldlenp))) - return -EFAULT; - - return ret; -} -#endif - /* warning: next two assume little endian */ asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count, u32 poslo, u32 poshi) diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 4518dc50090..60d2b2db0bc 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -118,7 +118,7 @@ extern void acpi_restore_state_mem(void); extern unsigned long acpi_wakeup_address; /* early initialization routine */ -extern void acpi_reserve_bootmem(void); +extern void acpi_reserve_wakeup_memory(void); /* * Check if the CPU can handle C2 and deeper @@ -158,6 +158,7 @@ struct bootnode; #ifdef CONFIG_ACPI_NUMA extern int acpi_numa; +extern int acpi_get_nodes(struct bootnode *physnodes); extern int acpi_scan_nodes(unsigned long start, unsigned long end); #define NR_NODE_MEMBLKS (MAX_NUMNODES*2) extern void acpi_fake_nodes(const struct bootnode *fake_nodes, diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h index 549860d3be8..2f9047cfaac 100644 --- a/arch/x86/include/asm/cache.h +++ b/arch/x86/include/asm/cache.h @@ -9,12 +9,13 @@ #define __read_mostly __attribute__((__section__(".data.read_mostly"))) +#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT +#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT) + #ifdef CONFIG_X86_VSMP -/* vSMP Internode cacheline shift */ -#define INTERNODE_CACHE_SHIFT (12) #ifdef CONFIG_SMP #define __cacheline_aligned_in_smp \ - __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT)))) \ + __attribute__((__aligned__(INTERNODE_CACHE_BYTES))) \ __page_aligned_data #endif #endif diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index b54f6afe7ec..634c40a739a 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -12,6 +12,7 @@ static inline void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { } static inline void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn) { } +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 static inline void flush_dcache_page(struct page *page) { } static inline void flush_dcache_mmap_lock(struct address_space *mapping) { } static inline void flush_dcache_mmap_unlock(struct address_space *mapping) { } @@ -176,6 +177,7 @@ void clflush_cache_range(void *addr, unsigned int size); #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; +extern int kernel_set_to_readonly; void set_kernel_text_rw(void); void set_kernel_text_ro(void); #else diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 9cfc88b9774..613700f27a4 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -248,6 +248,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) +#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64) # define cpu_has_invlpg 1 diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 40b4e614fe7..761249e396f 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -61,6 +61,12 @@ struct e820map { struct e820entry map[E820_X_MAX]; }; +#define ISA_START_ADDRESS 0xa0000 +#define ISA_END_ADDRESS 0x100000 + +#define BIOS_BEGIN 0x000a0000 +#define BIOS_END 0x00100000 + #ifdef __KERNEL__ /* see comment in arch/x86/kernel/e820.c */ extern struct e820map e820; @@ -126,15 +132,18 @@ extern void e820_reserve_resources(void); extern void e820_reserve_resources_late(void); extern void setup_memory_map(void); extern char *default_machine_specific_memory_setup(void); -#endif /* __KERNEL__ */ -#endif /* __ASSEMBLY__ */ -#define ISA_START_ADDRESS 0xa0000 -#define ISA_END_ADDRESS 0x100000 -#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS) +/* + * Returns true iff the specified range [s,e) is completely contained inside + * the ISA region. + */ +static inline bool is_ISA_range(u64 s, u64 e) +{ + return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS; +} -#define BIOS_BEGIN 0x000a0000 -#define BIOS_END 0x00100000 +#endif /* __KERNEL__ */ +#endif /* __ASSEMBLY__ */ #ifdef __KERNEL__ #include <linux/ioport.h> diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 456a304b817..8a024babe5e 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -157,19 +157,6 @@ do { \ #define compat_elf_check_arch(x) elf_check_arch_ia32(x) -static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp) -{ - loadsegment(fs, 0); - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); - load_gs_index(0); - regs->ip = ip; - regs->sp = sp; - regs->flags = X86_EFLAGS_IF; - regs->cs = __USER32_CS; - regs->ss = __USER32_DS; -} - static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { @@ -191,11 +178,8 @@ do { \ #define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ elf_common_init(¤t->thread, regs, __USER_DS) -#define compat_start_thread(regs, ip, sp) \ -do { \ - start_ia32_thread(regs, ip, sp); \ - set_fs(USER_DS); \ -} while (0) +void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp); +#define compat_start_thread start_thread_ia32 #define COMPAT_SET_PERSONALITY(ex) \ do { \ diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index f5693c81a1d..8e8ec663a98 100644 --- a/arch/x86/include/asm/entry_arch.h +++ b/arch/x86/include/asm/entry_arch.h @@ -34,7 +34,7 @@ BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7, smp_invalidate_interrupt) #endif -BUILD_INTERRUPT(generic_interrupt, GENERIC_INTERRUPT_VECTOR) +BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR) /* * every pentium local APIC has two 'local interrupts', with a diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 108eb6fd1ae..0f8576427cf 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -12,7 +12,7 @@ typedef struct { unsigned int apic_timer_irqs; /* arch dependent */ unsigned int irq_spurious_count; #endif - unsigned int generic_irqs; /* arch dependent */ + unsigned int x86_platform_ipis; /* arch dependent */ unsigned int apic_perf_irqs; unsigned int apic_pending_irqs; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index 1c22cb05ad6..5d89fd2a369 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -65,11 +65,12 @@ /* hpet memory map physical address */ extern unsigned long hpet_address; extern unsigned long force_hpet_address; +extern u8 hpet_blockid; extern int hpet_force_user; extern int is_hpet_enabled(void); extern int hpet_enable(void); extern void hpet_disable(void); -extern unsigned long hpet_readl(unsigned long a); +extern unsigned int hpet_readl(unsigned int a); extern void force_hpet_resume(void); extern void hpet_msi_unmask(unsigned int irq); @@ -78,9 +79,9 @@ extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg); extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg); #ifdef CONFIG_PCI_MSI -extern int arch_setup_hpet_msi(unsigned int irq); +extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id); #else -static inline int arch_setup_hpet_msi(unsigned int irq) +static inline int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { return -EINVAL; } diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 6e124269fd4..08c48a81841 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -27,7 +27,7 @@ /* Interrupt handlers registered during init_IRQ */ extern void apic_timer_interrupt(void); -extern void generic_interrupt(void); +extern void x86_platform_ipi(void); extern void error_interrupt(void); extern void perf_pending_interrupt(void); @@ -119,7 +119,7 @@ extern void eisa_set_level_irq(unsigned int irq); /* SMP */ extern void smp_apic_timer_interrupt(struct pt_regs *); extern void smp_spurious_interrupt(struct pt_regs *); -extern void smp_generic_interrupt(struct pt_regs *); +extern void smp_x86_platform_ipi(struct pt_regs *); extern void smp_error_interrupt(struct pt_regs *); #ifdef CONFIG_X86_IO_APIC extern asmlinkage void smp_irq_move_cleanup_interrupt(void); diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 0b20bbb758f..ebfb8a9e11f 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -10,6 +10,8 @@ #ifndef _ASM_X86_I387_H #define _ASM_X86_I387_H +#ifndef __ASSEMBLY__ + #include <linux/sched.h> #include <linux/kernel_stat.h> #include <linux/regset.h> @@ -411,4 +413,9 @@ static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk) } } +#endif /* __ASSEMBLY__ */ + +#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5 +#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5 + #endif /* _ASM_X86_I387_H */ diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h new file mode 100644 index 00000000000..14cf526091f --- /dev/null +++ b/arch/x86/include/asm/inst.h @@ -0,0 +1,150 @@ +/* + * Generate .byte code for some instructions not supported by old + * binutils. + */ +#ifndef X86_ASM_INST_H +#define X86_ASM_INST_H + +#ifdef __ASSEMBLY__ + + .macro XMM_NUM opd xmm + .ifc \xmm,%xmm0 + \opd = 0 + .endif + .ifc \xmm,%xmm1 + \opd = 1 + .endif + .ifc \xmm,%xmm2 + \opd = 2 + .endif + .ifc \xmm,%xmm3 + \opd = 3 + .endif + .ifc \xmm,%xmm4 + \opd = 4 + .endif + .ifc \xmm,%xmm5 + \opd = 5 + .endif + .ifc \xmm,%xmm6 + \opd = 6 + .endif + .ifc \xmm,%xmm7 + \opd = 7 + .endif + .ifc \xmm,%xmm8 + \opd = 8 + .endif + .ifc \xmm,%xmm9 + \opd = 9 + .endif + .ifc \xmm,%xmm10 + \opd = 10 + .endif + .ifc \xmm,%xmm11 + \opd = 11 + .endif + .ifc \xmm,%xmm12 + \opd = 12 + .endif + .ifc \xmm,%xmm13 + \opd = 13 + .endif + .ifc \xmm,%xmm14 + \opd = 14 + .endif + .ifc \xmm,%xmm15 + \opd = 15 + .endif + .endm + + .macro PFX_OPD_SIZE + .byte 0x66 + .endm + + .macro PFX_REX opd1 opd2 + .if (\opd1 | \opd2) & 8 + .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) + .endif + .endm + + .macro MODRM mod opd1 opd2 + .byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3) + .endm + + .macro PSHUFB_XMM xmm1 xmm2 + XMM_NUM pshufb_opd1 \xmm1 + XMM_NUM pshufb_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX pshufb_opd1 pshufb_opd2 + .byte 0x0f, 0x38, 0x00 + MODRM 0xc0 pshufb_opd1 pshufb_opd2 + .endm + + .macro PCLMULQDQ imm8 xmm1 xmm2 + XMM_NUM clmul_opd1 \xmm1 + XMM_NUM clmul_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX clmul_opd1 clmul_opd2 + .byte 0x0f, 0x3a, 0x44 + MODRM 0xc0 clmul_opd1 clmul_opd2 + .byte \imm8 + .endm + + .macro AESKEYGENASSIST rcon xmm1 xmm2 + XMM_NUM aeskeygen_opd1 \xmm1 + XMM_NUM aeskeygen_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX aeskeygen_opd1 aeskeygen_opd2 + .byte 0x0f, 0x3a, 0xdf + MODRM 0xc0 aeskeygen_opd1 aeskeygen_opd2 + .byte \rcon + .endm + + .macro AESIMC xmm1 xmm2 + XMM_NUM aesimc_opd1 \xmm1 + XMM_NUM aesimc_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX aesimc_opd1 aesimc_opd2 + .byte 0x0f, 0x38, 0xdb + MODRM 0xc0 aesimc_opd1 aesimc_opd2 + .endm + + .macro AESENC xmm1 xmm2 + XMM_NUM aesenc_opd1 \xmm1 + XMM_NUM aesenc_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX aesenc_opd1 aesenc_opd2 + .byte 0x0f, 0x38, 0xdc + MODRM 0xc0 aesenc_opd1 aesenc_opd2 + .endm + + .macro AESENCLAST xmm1 xmm2 + XMM_NUM aesenclast_opd1 \xmm1 + XMM_NUM aesenclast_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX aesenclast_opd1 aesenclast_opd2 + .byte 0x0f, 0x38, 0xdd + MODRM 0xc0 aesenclast_opd1 aesenclast_opd2 + .endm + + .macro AESDEC xmm1 xmm2 + XMM_NUM aesdec_opd1 \xmm1 + XMM_NUM aesdec_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX aesdec_opd1 aesdec_opd2 + .byte 0x0f, 0x38, 0xde + MODRM 0xc0 aesdec_opd1 aesdec_opd2 + .endm + + .macro AESDECLAST xmm1 xmm2 + XMM_NUM aesdeclast_opd1 \xmm1 + XMM_NUM aesdeclast_opd2 \xmm2 + PFX_OPD_SIZE + PFX_REX aesdeclast_opd1 aesdeclast_opd2 + .byte 0x0f, 0x38, 0xdf + MODRM 0xc0 aesdeclast_opd1 aesdeclast_opd2 + .endm +#endif + +#endif diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index ffd700ff5dc..5458380b6ef 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -37,7 +37,7 @@ extern void fixup_irqs(void); extern void irq_force_complete_move(int); #endif -extern void (*generic_interrupt_extension)(void); +extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); extern bool handle_irq(unsigned irq, struct pt_regs *regs); diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 5b21f0ec3df..6a635bd3986 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -106,7 +106,7 @@ /* * Generic system vector for platform specific use */ -#define GENERIC_INTERRUPT_VECTOR 0xed +#define X86_PLATFORM_IPI_VECTOR 0xed /* * Performance monitoring pending work vector: diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h index c2d1f3b58e5..f70e60071fe 100644 --- a/arch/x86/include/asm/k8.h +++ b/arch/x86/include/asm/k8.h @@ -4,13 +4,16 @@ #include <linux/pci.h> extern struct pci_device_id k8_nb_ids[]; +struct bootnode; extern int early_is_k8_nb(u32 value); extern struct pci_dev **k8_northbridges; extern int num_k8_northbridges; extern int cache_k8_northbridges(void); extern void k8_flush_garts(void); -extern int k8_scan_nodes(unsigned long start, unsigned long end); +extern int k8_get_nodes(struct bootnode *nodes); +extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn); +extern int k8_scan_nodes(void); #ifdef CONFIG_K8_NB static inline struct pci_dev *node_to_k8_nb_misc(int node) diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 4a5fe914dc5..950df434763 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -19,6 +19,8 @@ #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 +#define __KVM_HAVE_XEN_HVM +#define __KVM_HAVE_VCPU_EVENTS /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -79,6 +81,7 @@ struct kvm_ioapic_state { #define KVM_IRQCHIP_PIC_MASTER 0 #define KVM_IRQCHIP_PIC_SLAVE 1 #define KVM_IRQCHIP_IOAPIC 2 +#define KVM_NR_IRQCHIPS 3 /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { @@ -250,4 +253,31 @@ struct kvm_reinject_control { __u8 pit_reinject; __u8 reserved[31]; }; + +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 injected; + __u8 nr; + __u8 has_error_code; + __u8 pad; + __u32 error_code; + } exception; + struct { + __u8 injected; + __u8 nr; + __u8 soft; + __u8 pad; + } interrupt; + struct { + __u8 injected; + __u8 pending; + __u8 masked; + __u8 pad; + } nmi; + __u32 sipi_vector; + __u32 flags; + __u32 reserved[10]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index b7ed2c42311..7c18e1230f5 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -129,7 +129,7 @@ struct decode_cache { u8 seg_override; unsigned int d; unsigned long regs[NR_VCPU_REGS]; - unsigned long eip; + unsigned long eip, eip_orig; /* modrm */ u8 modrm; u8 modrm_mod; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d83892226f7..4f865e8b854 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -354,7 +354,6 @@ struct kvm_vcpu_arch { unsigned int time_offset; struct page *time_page; - bool singlestep; /* guest is single stepped by KVM */ bool nmi_pending; bool nmi_injected; @@ -371,6 +370,10 @@ struct kvm_vcpu_arch { u64 mcg_status; u64 mcg_ctl; u64 *mce_banks; + + /* used for guest single stepping over the given code position */ + u16 singlestep_cs; + unsigned long singlestep_rip; }; struct kvm_mem_alias { @@ -397,7 +400,6 @@ struct kvm_arch{ struct kvm_pic *vpic; struct kvm_ioapic *vioapic; struct kvm_pit *vpit; - struct hlist_head irq_ack_notifier_list; int vapics_in_nmi_mode; unsigned int tss_addr; @@ -410,8 +412,10 @@ struct kvm_arch{ gpa_t ept_identity_map_addr; unsigned long irq_sources_bitmap; - unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; u64 vm_init_tsc; + s64 kvmclock_offset; + + struct kvm_xen_hvm_config xen_hvm_config; }; struct kvm_vm_stat { @@ -461,7 +465,7 @@ struct descriptor_table { struct kvm_x86_ops { int (*cpu_has_kvm_support)(void); /* __init */ int (*disabled_by_bios)(void); /* __init */ - void (*hardware_enable)(void *dummy); /* __init */ + int (*hardware_enable)(void *dummy); void (*hardware_disable)(void *dummy); void (*check_processor_compatibility)(void *rtn); int (*hardware_setup)(void); /* __init */ @@ -477,8 +481,8 @@ struct kvm_x86_ops { void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); void (*vcpu_put)(struct kvm_vcpu *vcpu); - int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_guest_debug *dbg); + void (*set_guest_debug)(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); @@ -506,8 +510,8 @@ struct kvm_x86_ops { void (*tlb_flush)(struct kvm_vcpu *vcpu); - void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run); - int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu); + void (*run)(struct kvm_vcpu *vcpu); + int (*handle_exit)(struct kvm_vcpu *vcpu); void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); @@ -519,6 +523,8 @@ struct kvm_x86_ops { bool has_error_code, u32 error_code); int (*interrupt_allowed)(struct kvm_vcpu *vcpu); int (*nmi_allowed)(struct kvm_vcpu *vcpu); + bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); + void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); @@ -568,7 +574,7 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run, +int emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, u16 error_code, int emulation_type); void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); @@ -585,9 +591,9 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); struct x86_emulate_ctxt; -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port); void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); @@ -616,6 +622,9 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu); +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); + void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2, @@ -802,4 +811,7 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); +void kvm_define_shared_msr(unsigned index, u32 msr); +void kvm_set_shared_msr(unsigned index, u64 val, u64 mask); + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index ef51b501e22..c24ca9a5645 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -12,6 +12,8 @@ struct device; enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; struct microcode_ops { + void (*init)(struct device *device); + void (*fini)(void); enum ucode_state (*request_microcode_user) (int cpu, const void __user *buf, size_t size); diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 61d90b1331c..d8bf23a88d0 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -71,12 +71,7 @@ static inline void early_get_smp_config(void) static inline void find_smp_config(void) { - x86_init.mpparse.find_smp_config(1); -} - -static inline void early_find_smp_config(void) -{ - x86_init.mpparse.find_smp_config(0); + x86_init.mpparse.find_smp_config(); } #ifdef CONFIG_X86_MPPARSE @@ -89,7 +84,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str); # else # define default_mpc_oem_bus_info NULL # endif -extern void default_find_smp_config(unsigned int reserve); +extern void default_find_smp_config(void); extern void default_get_smp_config(unsigned int early); #else static inline void early_reserve_e820_mpc_new(void) { } @@ -97,7 +92,7 @@ static inline void early_reserve_e820_mpc_new(void) { } #define default_mpc_apic_id NULL #define default_smp_read_mpc_oem NULL #define default_mpc_oem_bus_info NULL -#define default_find_smp_config x86_init_uint_noop +#define default_find_smp_config x86_init_noop #define default_get_smp_config x86_init_uint_noop #endif diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 6473f5ccff8..642fe34b36a 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -49,7 +49,8 @@ extern unsigned long max_pfn_mapped; extern unsigned long init_memory_mapping(unsigned long start, unsigned long end); -extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn); +extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn, + int acpi, int k8); extern void free_initmem(void); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index af6fd360ab3..a34c785c5a6 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -16,6 +16,8 @@ #ifndef __ASSEMBLY__ +#include <asm/x86_init.h> + /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. @@ -270,9 +272,9 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, unsigned long new_flags) { /* - * PAT type is always WB for ISA. So no need to check. + * PAT type is always WB for untracked ranges, so no need to check. */ - if (is_ISA_range(paddr, paddr + size - 1)) + if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) return 1; /* diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 621f56d7312..4009f6534f5 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -5,18 +5,19 @@ /* misc architecture specific prototypes */ -extern void early_idt_handler(void); +void early_idt_handler(void); -extern void system_call(void); -extern void syscall_init(void); +void system_call(void); +void syscall_init(void); -extern void ia32_syscall(void); -extern void ia32_cstar_target(void); -extern void ia32_sysenter_target(void); +void ia32_syscall(void); +void ia32_cstar_target(void); +void ia32_sysenter_target(void); -extern void syscall32_cpu_init(void); +void syscall32_cpu_init(void); -extern void check_efer(void); +void x86_configure_nx(void); +void x86_report_nx(void); extern int reboot_force; diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h index 1b7ee5d673c..0a524242865 100644 --- a/arch/x86/include/asm/sections.h +++ b/arch/x86/include/asm/sections.h @@ -2,7 +2,13 @@ #define _ASM_X86_SECTIONS_H #include <asm-generic/sections.h> +#include <asm/uaccess.h> extern char __brk_base[], __brk_limit[]; +extern struct exception_table_entry __stop___ex_table[]; + +#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +extern char __end_rodata_hpage_align[]; +#endif #endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 85574b7c1bc..1fecb7e6113 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -57,7 +57,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { u16 intercept_dr_write; u32 intercept_exceptions; u64 intercept; - u8 reserved_1[44]; + u8 reserved_1[42]; + u16 pause_filter_count; u64 iopm_base_pa; u64 msrpm_base_pa; u64 tsc_offset; diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 72a6dcd1299..9af9decb38c 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -51,11 +51,6 @@ asmlinkage long sys32_sched_rr_get_interval(compat_pid_t, asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *, compat_size_t); asmlinkage long sys32_rt_sigqueueinfo(int, int, compat_siginfo_t __user *); -#ifdef CONFIG_SYSCTL_SYSCALL -struct sysctl_ia32; -asmlinkage long sys32_sysctl(struct sysctl_ia32 __user *); -#endif - asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d27d0a2fec4..375c917c37d 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ #define TIF_MCE_NOTIFY 10 /* notify userspace of an MCE */ +#define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* 32bit process */ #define TIF_FORK 18 /* ret_from_fork */ @@ -107,6 +108,7 @@ struct thread_info { #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_MCE_NOTIFY (1 << TIF_MCE_NOTIFY) +#define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) @@ -142,13 +144,14 @@ struct thread_info { /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ - (_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME) + (_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \ + _TIF_USER_RETURN_NOTIFY) /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW \ (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC) -#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW +#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG) #define PREEMPT_ACTIVE 0x10000000 diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index 6fb3c209a7e..3baf379fa84 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -342,10 +342,11 @@ #define __NR_pwritev 334 #define __NR_rt_tgsigqueueinfo 335 #define __NR_perf_event_open 336 +#define __NR_recvmmsg 337 #ifdef __KERNEL__ -#define NR_syscalls 337 +#define NR_syscalls 338 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index 8d3ad0adbc6..4843f7ba754 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -661,6 +661,8 @@ __SYSCALL(__NR_pwritev, sys_pwritev) __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) #define __NR_perf_event_open 298 __SYSCALL(__NR_perf_event_open, sys_perf_event_open) +#define __NR_recvmmsg 299 +__SYSCALL(__NR_recvmmsg, sys_recvmmsg) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 272514c2d45..2b4945419a8 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -56,6 +56,7 @@ #define SECONDARY_EXEC_ENABLE_VPID 0x00000020 #define SECONDARY_EXEC_WBINVD_EXITING 0x00000040 #define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080 +#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -144,6 +145,8 @@ enum vmcs_field { VM_ENTRY_INSTRUCTION_LEN = 0x0000401a, TPR_THRESHOLD = 0x0000401c, SECONDARY_VM_EXEC_CONTROL = 0x0000401e, + PLE_GAP = 0x00004020, + PLE_WINDOW = 0x00004022, VM_INSTRUCTION_ERROR = 0x00004400, VM_EXIT_REASON = 0x00004402, VM_EXIT_INTR_INFO = 0x00004404, @@ -248,6 +251,7 @@ enum vmcs_field { #define EXIT_REASON_MSR_READ 31 #define EXIT_REASON_MSR_WRITE 32 #define EXIT_REASON_MWAIT_INSTRUCTION 36 +#define EXIT_REASON_PAUSE_INSTRUCTION 40 #define EXIT_REASON_MCE_DURING_VMENTRY 41 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43 #define EXIT_REASON_APIC_ACCESS 44 diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index d8e71459f02..ea0e8ea15e1 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -26,7 +26,7 @@ struct x86_init_mpparse { void (*smp_read_mpc_oem)(struct mpc_table *mpc); void (*mpc_oem_pci_bus)(struct mpc_bus *m); void (*mpc_oem_bus_info)(struct mpc_bus *m, char *name); - void (*find_smp_config)(unsigned int reserve); + void (*find_smp_config)(void); void (*get_smp_config)(unsigned int early); }; @@ -125,12 +125,14 @@ struct x86_cpuinit_ops { * @calibrate_tsc: calibrate TSC * @get_wallclock: get time from HW clock like RTC etc. * @set_wallclock: set time back to HW clock + * @is_untracked_pat_range exclude from PAT logic */ struct x86_platform_ops { unsigned long (*calibrate_tsc)(void); unsigned long (*get_wallclock)(void); int (*set_wallclock)(unsigned long nowtime); void (*iommu_shutdown)(void); + bool (*is_untracked_pat_range)(u64 start, u64 end); }; extern struct x86_init_ops x86_init; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 67e929b8987..87eee07da21 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -624,6 +624,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) } hpet_address = hpet_tbl->address.address; + hpet_blockid = hpet_tbl->sequence; /* * Some broken BIOSes advertise HPET at 0x0. We really do not diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ca93638ba43..82e508677b9 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -78,12 +78,9 @@ int acpi_save_state_mem(void) #ifndef CONFIG_64BIT store_gdt((struct desc_ptr *)&header->pmode_gdt); - header->pmode_efer_low = nx_enabled; - if (header->pmode_efer_low & 1) { - /* This is strange, why not save efer, always? */ - rdmsr(MSR_EFER, header->pmode_efer_low, - header->pmode_efer_high); - } + if (rdmsr_safe(MSR_EFER, &header->pmode_efer_low, + &header->pmode_efer_high)) + header->pmode_efer_low = header->pmode_efer_high = 0; #endif /* !CONFIG_64BIT */ header->pmode_cr0 = read_cr0(); @@ -119,29 +116,32 @@ void acpi_restore_state_mem(void) /** - * acpi_reserve_bootmem - do _very_ early ACPI initialisation + * acpi_reserve_wakeup_memory - do _very_ early ACPI initialisation * * We allocate a page from the first 1MB of memory for the wakeup * routine for when we come back from a sleep state. The * runtime allocator allows specification of <16MB pages, but not * <1MB pages. */ -void __init acpi_reserve_bootmem(void) +void __init acpi_reserve_wakeup_memory(void) { + unsigned long mem; + if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) { printk(KERN_ERR "ACPI: Wakeup code way too big, S3 disabled.\n"); return; } - acpi_realmode = (unsigned long)alloc_bootmem_low(WAKEUP_SIZE); + mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE); - if (!acpi_realmode) { + if (mem == -1L) { printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n"); return; } - - acpi_wakeup_address = virt_to_phys((void *)acpi_realmode); + acpi_realmode = (unsigned long) phys_to_virt(mem); + acpi_wakeup_address = mem; + reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ad8c75b9e45..efb2b9cd132 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -647,7 +647,7 @@ static int __init calibrate_APIC_clock(void) calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS; apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta); - apic_printk(APIC_VERBOSE, "..... mult: %ld\n", lapic_clockevent.mult); + apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult); apic_printk(APIC_VERBOSE, "..... calibration result: %u\n", calibration_result); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index c0b4468683f..d5d498fbee4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3267,7 +3267,8 @@ void destroy_irq(unsigned int irq) * MSI message composition */ #ifdef CONFIG_PCI_MSI -static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg) +static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, + struct msi_msg *msg, u8 hpet_id) { struct irq_cfg *cfg; int err; @@ -3301,7 +3302,10 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms irte.dest_id = IRTE_DEST(dest); /* Set source-id of interrupt request */ - set_msi_sid(&irte, pdev); + if (pdev) + set_msi_sid(&irte, pdev); + else + set_hpet_sid(&irte, hpet_id); modify_irte(irq, &irte); @@ -3466,7 +3470,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(dev, irq, &msg); + ret = msi_compose_msg(dev, irq, &msg, -1); if (ret < 0) return ret; @@ -3599,7 +3603,7 @@ int arch_setup_dmar_msi(unsigned int irq) int ret; struct msi_msg msg; - ret = msi_compose_msg(NULL, irq, &msg); + ret = msi_compose_msg(NULL, irq, &msg, -1); if (ret < 0) return ret; dmar_msi_write(irq, &msg); @@ -3639,6 +3643,19 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask) #endif /* CONFIG_SMP */ +static struct irq_chip ir_hpet_msi_type = { + .name = "IR-HPET_MSI", + .unmask = hpet_msi_unmask, + .mask = hpet_msi_mask, +#ifdef CONFIG_INTR_REMAP + .ack = ir_ack_apic_edge, +#ifdef CONFIG_SMP + .set_affinity = ir_set_msi_irq_affinity, +#endif +#endif + .retrigger = ioapic_retrigger_irq, +}; + static struct irq_chip hpet_msi_type = { .name = "HPET_MSI", .unmask = hpet_msi_unmask, @@ -3650,20 +3667,36 @@ static struct irq_chip hpet_msi_type = { .retrigger = ioapic_retrigger_irq, }; -int arch_setup_hpet_msi(unsigned int irq) +int arch_setup_hpet_msi(unsigned int irq, unsigned int id) { int ret; struct msi_msg msg; struct irq_desc *desc = irq_to_desc(irq); - ret = msi_compose_msg(NULL, irq, &msg); + if (intr_remapping_enabled) { + struct intel_iommu *iommu = map_hpet_to_ir(id); + int index; + + if (!iommu) + return -1; + + index = alloc_irte(iommu, irq, 1); + if (index < 0) + return -1; + } + + ret = msi_compose_msg(NULL, irq, &msg, id); if (ret < 0) return ret; hpet_msi_write(irq, &msg); desc->status |= IRQ_MOVE_PCNTXT; - set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq, - "edge"); + if (irq_remapped(irq)) + set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type, + handle_edge_irq, "edge"); + else + set_irq_chip_and_handler_name(irq, &hpet_msi_type, + handle_edge_irq, "edge"); return 0; } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 07cdbdcd7a9..98c4665f251 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -264,11 +264,6 @@ static void __init smp_read_mpc_oem(struct mpc_table *mpc) static __init void early_check_numaq(void) { /* - * Find possible boot-time SMP configuration: - */ - early_find_smp_config(); - - /* * get boot-time SMP configuration: */ if (smp_found_config) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 130c4b93487..b684bb303cb 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -30,10 +30,22 @@ #include <asm/apic.h> #include <asm/ipi.h> #include <asm/smp.h> +#include <asm/x86_init.h> DEFINE_PER_CPU(int, x2apic_extra_bits); static enum uv_system_type uv_system_type; +static u64 gru_start_paddr, gru_end_paddr; + +static inline bool is_GRU_range(u64 start, u64 end) +{ + return start >= gru_start_paddr && end <= gru_end_paddr; +} + +static bool uv_is_untracked_pat_range(u64 start, u64 end) +{ + return is_ISA_range(start, end) || is_GRU_range(start, end); +} static int early_get_nodeid(void) { @@ -49,6 +61,7 @@ static int early_get_nodeid(void) static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { if (!strcmp(oem_id, "SGI")) { + x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; if (!strcmp(oem_table_id, "UVL")) uv_system_type = UV_LEGACY_APIC; else if (!strcmp(oem_table_id, "UVX")) @@ -385,8 +398,12 @@ static __init void map_gru_high(int max_pnode) int shift = UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT; gru.v = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR); - if (gru.s.enable) + if (gru.s.enable) { map_high("GRU", gru.s.base, shift, max_pnode, map_wb); + gru_start_paddr = ((u64)gru.s.base << shift); + gru_end_paddr = gru_start_paddr + (1UL << shift) * (max_pnode + 1); + + } } static __init void map_mmr_high(int max_pnode) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a4ec8b64754..c1afa990a6c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1136,7 +1136,7 @@ void __cpuinit cpu_init(void) wrmsrl(MSR_KERNEL_GS_BASE, 0); barrier(); - check_efer(); + x86_configure_nx(); if (cpu != 0) enable_x2apic(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 40e1835b35e..c900b73f922 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -263,8 +263,12 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) /* Don't do the funky fallback heuristics the AMD version employs for now. */ node = apicid_to_node[apicid]; - if (node == NUMA_NO_NODE || !node_online(node)) + if (node == NUMA_NO_NODE) node = first_node(node_online_map); + else if (!node_online(node)) { + /* reuse the value from init_cpu_to_node() */ + node = cpu_to_node(cpu); + } numa_set_node(cpu, node); printk(KERN_INFO "CPU %d/0x%x -> Node %d\n", cpu, apicid, node); diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 0df4c2b7107..6c40f6b5b34 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -94,7 +94,7 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0xd1, LVL_3, 1024 }, /* 4-way set assoc, 64 byte line size */ { 0xd2, LVL_3, 2048 }, /* 4-way set assoc, 64 byte line size */ { 0xd6, LVL_3, 1024 }, /* 8-way set assoc, 64 byte line size */ - { 0xd7, LVL_3, 2038 }, /* 8-way set assoc, 64 byte line size */ + { 0xd7, LVL_3, 2048 }, /* 8-way set assoc, 64 byte line size */ { 0xd8, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */ { 0xdc, LVL_3, 2048 }, /* 12-way set assoc, 64 byte line size */ { 0xdd, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */ @@ -102,6 +102,9 @@ static const struct _cache_table __cpuinitconst cache_table[] = { 0xe2, LVL_3, 2048 }, /* 16-way set assoc, 64 byte line size */ { 0xe3, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */ { 0xe4, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */ + { 0xea, LVL_3, 12288 }, /* 24-way set assoc, 64 byte line size */ + { 0xeb, LVL_3, 18432 }, /* 24-way set assoc, 64 byte line size */ + { 0xec, LVL_3, 24576 }, /* 24-way set assoc, 64 byte line size */ { 0x00, 0, 0} }; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 0bcaa387586..d7ebf25d10e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2016,9 +2016,11 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) break; case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - t->expires = round_jiffies(jiffies + + if (!mce_ignore_ce && check_interval) { + t->expires = round_jiffies(jiffies + __get_cpu_var(mce_next_interval)); - add_timer_on(t, cpu); + add_timer_on(t, cpu); + } smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); break; case CPU_POST_DEAD: diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 73c86db5acb..09b1698e046 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -170,6 +170,41 @@ static int __init cmp_range(const void *x1, const void *x2) return start1 - start2; } +static int __init clean_sort_range(struct res_range *range, int az) +{ + int i, j, k = az - 1, nr_range = 0; + + for (i = 0; i < k; i++) { + if (range[i].end) + continue; + for (j = k; j > i; j--) { + if (range[j].end) { + k = j; + break; + } + } + if (j == i) + break; + range[i].start = range[k].start; + range[i].end = range[k].end; + range[k].start = 0; + range[k].end = 0; + k--; + } + /* count it */ + for (i = 0; i < az; i++) { + if (!range[i].end) { + nr_range = i; + break; + } + } + + /* sort them */ + sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + + return nr_range; +} + #define BIOS_BUG_MSG KERN_WARNING \ "WARNING: BIOS bug: VAR MTRR %d contains strange UC entry under 1M, check with your system vendor!\n" @@ -223,22 +258,18 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range, subtract_range(range, extra_remove_base, extra_remove_base + extra_remove_size - 1); - /* get new range num */ - nr_range = 0; - for (i = 0; i < RANGE_NUM; i++) { - if (!range[i].end) - continue; - nr_range++; - } if (debug_print) { printk(KERN_DEBUG "After UC checking\n"); - for (i = 0; i < nr_range; i++) + for (i = 0; i < RANGE_NUM; i++) { + if (!range[i].end) + continue; printk(KERN_DEBUG "MTRR MAP PFN: %016lx - %016lx\n", range[i].start, range[i].end + 1); + } } /* sort the ranges */ - sort(range, nr_range, sizeof(struct res_range), cmp_range, NULL); + nr_range = clean_sort_range(range, RANGE_NUM); if (debug_print) { printk(KERN_DEBUG "After sorting\n"); for (i = 0; i < nr_range; i++) @@ -689,8 +720,6 @@ static int __init mtrr_need_cleanup(void) continue; if (!size) type = MTRR_NUM_TYPES; - if (type == MTRR_TYPE_WRPROT) - type = MTRR_TYPE_UNCACHABLE; num[type]++; } diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 4deb8fc849d..63bca794c8f 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -977,8 +977,8 @@ apicinterrupt UV_BAU_MESSAGE \ #endif apicinterrupt LOCAL_TIMER_VECTOR \ apic_timer_interrupt smp_apic_timer_interrupt -apicinterrupt GENERIC_INTERRUPT_VECTOR \ - generic_interrupt smp_generic_interrupt +apicinterrupt X86_PLATFORM_IPI_VECTOR \ + x86_platform_ipi smp_x86_platform_ipi #ifdef CONFIG_SMP apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 5a1b9758fd6..30968924543 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -189,9 +189,26 @@ static void wait_for_nmi(void) nmi_wait_count++; } +static inline int +within(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr < end; +} + static int do_ftrace_mod_code(unsigned long ip, void *new_code) { + /* + * On x86_64, kernel text mappings are mapped read-only with + * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead + * of the kernel text mapping to modify the kernel text. + * + * For 32bit kernels, these mappings are same and we can use + * kernel identity mapping to modify code. + */ + if (within(ip, (unsigned long)_text, (unsigned long)_etext)) + ip = (unsigned long)__va(__pa(ip)); + mod_code_ip = (void *)ip; mod_code_newcode = new_code; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 050c278481b..7fd318bac59 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -18,6 +18,8 @@ #include <asm/asm-offsets.h> #include <asm/setup.h> #include <asm/processor-flags.h> +#include <asm/msr-index.h> +#include <asm/cpufeature.h> #include <asm/percpu.h> /* Physical address */ @@ -297,25 +299,27 @@ ENTRY(startup_32_smp) orl %edx,%eax movl %eax,%cr4 - btl $5, %eax # check if PAE is enabled - jnc 6f + testb $X86_CR4_PAE, %al # check if PAE is enabled + jz 6f /* Check if extended functions are implemented */ movl $0x80000000, %eax cpuid - cmpl $0x80000000, %eax - jbe 6f + /* Value must be in the range 0x80000001 to 0x8000ffff */ + subl $0x80000001, %eax + cmpl $(0x8000ffff-0x80000001), %eax + ja 6f mov $0x80000001, %eax cpuid /* Execute Disable bit supported? */ - btl $20, %edx + btl $(X86_FEATURE_NX & 31), %edx jnc 6f /* Setup EFER (Extended Feature Enable Register) */ - movl $0xc0000080, %ecx + movl $MSR_EFER, %ecx rdmsr - btsl $11, %eax + btsl $_EFER_NX, %eax /* Make changes effective */ wrmsr diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 22db86a3764..2d8b5035371 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -262,11 +262,11 @@ ENTRY(secondary_startup_64) .quad x86_64_start_kernel ENTRY(initial_gs) .quad INIT_PER_CPU_VAR(irq_stack_union) - __FINITDATA ENTRY(stack_start) .quad init_thread_union+THREAD_SIZE-8 .word 0 + __FINITDATA bad_address: jmp bad_address @@ -340,6 +340,7 @@ ENTRY(name) i = i + 1 ; \ .endr + .data /* * This default setting generates an ident mapping at address 0x100000 * and a mapping for the kernel that precisely maps virtual address diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index dedc2bddf7a..ba6e6588460 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -33,6 +33,7 @@ * HPET address is set in acpi/boot.c, when an ACPI entry exists */ unsigned long hpet_address; +u8 hpet_blockid; /* OS timer block num */ #ifdef CONFIG_PCI_MSI static unsigned long hpet_num_timers; #endif @@ -47,12 +48,12 @@ struct hpet_dev { char name[10]; }; -unsigned long hpet_readl(unsigned long a) +inline unsigned int hpet_readl(unsigned int a) { return readl(hpet_virt_address + a); } -static inline void hpet_writel(unsigned long d, unsigned long a) +static inline void hpet_writel(unsigned int d, unsigned int a) { writel(d, hpet_virt_address + a); } @@ -167,7 +168,7 @@ do { \ static void hpet_reserve_msi_timers(struct hpet_data *hd); -static void hpet_reserve_platform_timers(unsigned long id) +static void hpet_reserve_platform_timers(unsigned int id) { struct hpet __iomem *hpet = hpet_virt_address; struct hpet_timer __iomem *timer = &hpet->hpet_timers[2]; @@ -205,7 +206,7 @@ static void hpet_reserve_platform_timers(unsigned long id) } #else -static void hpet_reserve_platform_timers(unsigned long id) { } +static void hpet_reserve_platform_timers(unsigned int id) { } #endif /* @@ -246,7 +247,7 @@ static void hpet_reset_counter(void) static void hpet_start_counter(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } @@ -271,7 +272,7 @@ static void hpet_resume_counter(void) static void hpet_enable_legacy_int(void) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_LEGACY; hpet_writel(cfg, HPET_CFG); @@ -314,7 +315,7 @@ static int hpet_setup_msi_irq(unsigned int irq); static void hpet_set_mode(enum clock_event_mode mode, struct clock_event_device *evt, int timer) { - unsigned long cfg, cmp, now; + unsigned int cfg, cmp, now; uint64_t delta; switch (mode) { @@ -323,7 +324,7 @@ static void hpet_set_mode(enum clock_event_mode mode, delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned long) delta; + cmp = now + (unsigned int) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; @@ -339,7 +340,7 @@ static void hpet_set_mode(enum clock_event_mode mode, * (See AMD-8111 HyperTransport I/O Hub Data Sheet, * Publication # 24674) */ - hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_writel((unsigned int) delta, HPET_Tn_CMP(timer)); hpet_start_counter(); hpet_print_config(); break; @@ -383,13 +384,24 @@ static int hpet_next_event(unsigned long delta, hpet_writel(cnt, HPET_Tn_CMP(timer)); /* - * We need to read back the CMP register to make sure that - * what we wrote hit the chip before we compare it to the - * counter. + * We need to read back the CMP register on certain HPET + * implementations (ATI chipsets) which seem to delay the + * transfer of the compare register into the internal compare + * logic. With small deltas this might actually be too late as + * the counter could already be higher than the compare value + * at that point and we would wait for the next hpet interrupt + * forever. We found out that reading the CMP register back + * forces the transfer so we can rely on the comparison with + * the counter register below. If the read back from the + * compare register does not match the value we programmed + * then we might have a real hardware problem. We can not do + * much about it here, but at least alert the user/admin with + * a prominent warning. */ - WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt); + WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt, + KERN_WARNING "hpet: compare register read back failed.\n"); - return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; + return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0; } static void hpet_legacy_set_mode(enum clock_event_mode mode, @@ -415,7 +427,7 @@ static struct hpet_dev *hpet_devs; void hpet_msi_unmask(unsigned int irq) { struct hpet_dev *hdev = get_irq_data(irq); - unsigned long cfg; + unsigned int cfg; /* unmask it */ cfg = hpet_readl(HPET_Tn_CFG(hdev->num)); @@ -425,7 +437,7 @@ void hpet_msi_unmask(unsigned int irq) void hpet_msi_mask(unsigned int irq) { - unsigned long cfg; + unsigned int cfg; struct hpet_dev *hdev = get_irq_data(irq); /* mask it */ @@ -467,7 +479,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { - if (arch_setup_hpet_msi(irq)) { + if (arch_setup_hpet_msi(irq, hpet_blockid)) { destroy_irq(irq); return -EINVAL; } @@ -584,6 +596,8 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) unsigned int num_timers_used = 0; int i; + if (boot_cpu_has(X86_FEATURE_ARAT)) + return; id = hpet_readl(HPET_ID); num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); @@ -598,7 +612,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) for (i = start_timer; i < num_timers - RESERVE_TIMERS; i++) { struct hpet_dev *hdev = &hpet_devs[num_timers_used]; - unsigned long cfg = hpet_readl(HPET_Tn_CFG(i)); + unsigned int cfg = hpet_readl(HPET_Tn_CFG(i)); /* Only consider HPET timer with MSI support */ if (!(cfg & HPET_TN_FSB_CAP)) @@ -813,7 +827,7 @@ static int hpet_clocksource_register(void) */ int __init hpet_enable(void) { - unsigned long id; + unsigned int id; int i; if (!is_hpet_capable()) @@ -872,10 +886,8 @@ int __init hpet_enable(void) if (id & HPET_ID_LEGSUP) { hpet_legacy_clockevent_register(); - hpet_msi_capability_lookup(2); return 1; } - hpet_msi_capability_lookup(0); return 0; out_nohpet: @@ -908,9 +920,17 @@ static __init int hpet_late_init(void) if (!hpet_virt_address) return -ENODEV; + if (hpet_readl(HPET_ID) & HPET_ID_LEGSUP) + hpet_msi_capability_lookup(2); + else + hpet_msi_capability_lookup(0); + hpet_reserve_platform_timers(hpet_readl(HPET_ID)); hpet_print_config(); + if (boot_cpu_has(X86_FEATURE_ARAT)) + return 0; + for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); } @@ -925,7 +945,7 @@ fs_initcall(hpet_late_init); void hpet_disable(void) { if (is_hpet_capable()) { - unsigned long cfg = hpet_readl(HPET_CFG); + unsigned int cfg = hpet_readl(HPET_CFG); if (hpet_legacy_int_enabled) { cfg &= ~HPET_CFG_LEGACY; @@ -965,8 +985,8 @@ static int hpet_prev_update_sec; static struct rtc_time hpet_alarm_time; static unsigned long hpet_pie_count; static u32 hpet_t1_cmp; -static unsigned long hpet_default_delta; -static unsigned long hpet_pie_delta; +static u32 hpet_default_delta; +static u32 hpet_pie_delta; static unsigned long hpet_pie_limit; static rtc_irq_handler irq_handler; @@ -1017,7 +1037,8 @@ EXPORT_SYMBOL_GPL(hpet_unregister_irq_handler); */ int hpet_rtc_timer_init(void) { - unsigned long cfg, cnt, delta, flags; + unsigned int cfg, cnt, delta; + unsigned long flags; if (!is_hpet_enabled()) return 0; @@ -1027,7 +1048,7 @@ int hpet_rtc_timer_init(void) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT; - hpet_default_delta = (unsigned long) clc; + hpet_default_delta = clc; } if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit) @@ -1113,7 +1134,7 @@ int hpet_set_periodic_freq(unsigned long freq) clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC; do_div(clc, freq); clc >>= hpet_clockevent.shift; - hpet_pie_delta = (unsigned long) clc; + hpet_pie_delta = clc; } return 1; } @@ -1127,7 +1148,7 @@ EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); static void hpet_rtc_timer_reinit(void) { - unsigned long cfg, delta; + unsigned int cfg, delta; int lost_ints = -1; if (unlikely(!hpet_rtc_flags)) { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index fee6cc2b207..664bcb7384a 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -18,7 +18,7 @@ atomic_t irq_err_count; /* Function pointer for generic interrupt vector handling */ -void (*generic_interrupt_extension)(void) = NULL; +void (*x86_platform_ipi_callback)(void) = NULL; /* * 'what should we do if we get a hw irq event on an illegal vector'. @@ -72,10 +72,10 @@ static int show_other_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs); seq_printf(p, " Performance pending work\n"); #endif - if (generic_interrupt_extension) { + if (x86_platform_ipi_callback) { seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->generic_irqs); + seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis); seq_printf(p, " Platform interrupts\n"); } #ifdef CONFIG_SMP @@ -187,8 +187,8 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->apic_perf_irqs; sum += irq_stats(cpu)->apic_pending_irqs; #endif - if (generic_interrupt_extension) - sum += irq_stats(cpu)->generic_irqs; + if (x86_platform_ipi_callback) + sum += irq_stats(cpu)->x86_platform_ipis; #ifdef CONFIG_SMP sum += irq_stats(cpu)->irq_resched_count; sum += irq_stats(cpu)->irq_call_count; @@ -251,9 +251,9 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) } /* - * Handler for GENERIC_INTERRUPT_VECTOR. + * Handler for X86_PLATFORM_IPI_VECTOR. */ -void smp_generic_interrupt(struct pt_regs *regs) +void smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -263,10 +263,10 @@ void smp_generic_interrupt(struct pt_regs *regs) irq_enter(); - inc_irq_stat(generic_irqs); + inc_irq_stat(x86_platform_ipis); - if (generic_interrupt_extension) - generic_interrupt_extension(); + if (x86_platform_ipi_callback) + x86_platform_ipi_callback(); irq_exit(); diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index 40f30773fb2..d5932226614 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -200,8 +200,8 @@ static void __init apic_intr_init(void) /* self generated IPI for local APIC timer */ alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt); - /* generic IPI for platform specific use */ - alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt); + /* IPI for X86 platform specific use */ + alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi); /* IPI vectors for APIC spurious and error interrupts */ alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index c843f8406da..a3fa43ba5d3 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -158,8 +158,7 @@ int machine_kexec_prepare(struct kimage *image) { int error; - if (nx_enabled) - set_pages_x(image->control_code_page, 1); + set_pages_x(image->control_code_page, 1); error = machine_kexec_alloc_page_tables(image); if (error) return error; @@ -173,8 +172,7 @@ int machine_kexec_prepare(struct kimage *image) */ void machine_kexec_cleanup(struct kimage *image) { - if (nx_enabled) - set_pages_nx(image->control_code_page, 1); + set_pages_nx(image->control_code_page, 1); machine_kexec_free_page_tables(image); } diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index f4c538b681c..63123d90210 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -33,6 +33,9 @@ MODULE_LICENSE("GPL v2"); #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 #define UCODE_UCODE_TYPE 0x00000001 +const struct firmware *firmware; +static int supported_cpu; + struct equiv_cpu_entry { u32 installed_cpu; u32 fixed_errata_mask; @@ -71,17 +74,14 @@ static struct equiv_cpu_entry *equiv_cpu_table; static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) { - struct cpuinfo_x86 *c = &cpu_data(cpu); u32 dummy; - memset(csig, 0, sizeof(*csig)); - if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) { - printk(KERN_WARNING "microcode: CPU%d: AMD CPU family 0x%x not " - "supported\n", cpu, c->x86); + if (!supported_cpu) return -1; - } + + memset(csig, 0, sizeof(*csig)); rdmsr(MSR_AMD64_PATCH_LEVEL, csig->rev, dummy); - printk(KERN_INFO "microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev); + pr_info("microcode: CPU%d: patch_level=0x%x\n", cpu, csig->rev); return 0; } @@ -103,22 +103,15 @@ static int get_matching_microcode(int cpu, void *mc, int rev) i++; } - if (!equiv_cpu_id) { - printk(KERN_WARNING "microcode: CPU%d: cpu revision " - "not listed in equivalent cpu table\n", cpu); + if (!equiv_cpu_id) return 0; - } - if (mc_header->processor_rev_id != equiv_cpu_id) { - printk(KERN_ERR "microcode: CPU%d: patch mismatch " - "(processor_rev_id: %x, equiv_cpu_id: %x)\n", - cpu, mc_header->processor_rev_id, equiv_cpu_id); + if (mc_header->processor_rev_id != equiv_cpu_id) return 0; - } /* ucode might be chipset specific -- currently we don't support this */ if (mc_header->nb_dev_id || mc_header->sb_dev_id) { - printk(KERN_ERR "microcode: CPU%d: loading of chipset " + pr_err(KERN_ERR "microcode: CPU%d: loading of chipset " "specific code not yet supported\n", cpu); return 0; } @@ -148,14 +141,12 @@ static int apply_microcode_amd(int cpu) /* check current patch id and patch's id for match */ if (rev != mc_amd->hdr.patch_id) { - printk(KERN_ERR "microcode: CPU%d: update failed " + pr_err("microcode: CPU%d: update failed " "(for patch_level=0x%x)\n", cpu, mc_amd->hdr.patch_id); return -1; } - printk(KERN_INFO "microcode: CPU%d: updated (new patch_level=0x%x)\n", - cpu, rev); - + pr_info("microcode: CPU%d: updated (new patch_level=0x%x)\n", cpu, rev); uci->cpu_sig.rev = rev; return 0; @@ -178,18 +169,15 @@ get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) return NULL; if (section_hdr[0] != UCODE_UCODE_TYPE) { - printk(KERN_ERR "microcode: error: invalid type field in " + pr_err("microcode: error: invalid type field in " "container file section header\n"); return NULL; } total_size = (unsigned long) (section_hdr[4] + (section_hdr[5] << 8)); - printk(KERN_DEBUG "microcode: size %u, total_size %u\n", - size, total_size); - if (total_size > size || total_size > UCODE_MAX_SIZE) { - printk(KERN_ERR "microcode: error: size mismatch\n"); + pr_err("microcode: error: size mismatch\n"); return NULL; } @@ -218,15 +206,14 @@ static int install_equiv_cpu_table(const u8 *buf) size = buf_pos[2]; if (buf_pos[1] != UCODE_EQUIV_CPU_TABLE_TYPE || !size) { - printk(KERN_ERR "microcode: error: invalid type field in " + pr_err("microcode: error: invalid type field in " "container file section header\n"); return 0; } equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size); if (!equiv_cpu_table) { - printk(KERN_ERR "microcode: failed to allocate " - "equivalent CPU table\n"); + pr_err("microcode: failed to allocate equivalent CPU table\n"); return 0; } @@ -259,8 +246,7 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) offset = install_equiv_cpu_table(ucode_ptr); if (!offset) { - printk(KERN_ERR "microcode: failed to create " - "equivalent cpu table\n"); + pr_err("microcode: failed to create equivalent cpu table\n"); return UCODE_ERROR; } @@ -308,33 +294,27 @@ generic_load_microcode(int cpu, const u8 *data, size_t size) static enum ucode_state request_microcode_fw(int cpu, struct device *device) { - const char *fw_name = "amd-ucode/microcode_amd.bin"; - const struct firmware *firmware; enum ucode_state ret; - if (request_firmware(&firmware, fw_name, device)) { - printk(KERN_ERR "microcode: failed to load file %s\n", fw_name); + if (firmware == NULL) return UCODE_NFOUND; - } if (*(u32 *)firmware->data != UCODE_MAGIC) { - printk(KERN_ERR "microcode: invalid UCODE_MAGIC (0x%08x)\n", + pr_err("microcode: invalid UCODE_MAGIC (0x%08x)\n", *(u32 *)firmware->data); return UCODE_ERROR; } ret = generic_load_microcode(cpu, firmware->data, firmware->size); - release_firmware(firmware); - return ret; } static enum ucode_state request_microcode_user(int cpu, const void __user *buf, size_t size) { - printk(KERN_INFO "microcode: AMD microcode update via " - "/dev/cpu/microcode not supported\n"); + pr_info("microcode: AMD microcode update via " + "/dev/cpu/microcode not supported\n"); return UCODE_ERROR; } @@ -346,7 +326,32 @@ static void microcode_fini_cpu_amd(int cpu) uci->mc = NULL; } +void init_microcode_amd(struct device *device) +{ + const char *fw_name = "amd-ucode/microcode_amd.bin"; + struct cpuinfo_x86 *c = &boot_cpu_data; + + WARN_ON(c->x86_vendor != X86_VENDOR_AMD); + + if (c->x86 < 0x10) { + pr_warning("microcode: AMD CPU family 0x%x not supported\n", + c->x86); + return; + } + supported_cpu = 1; + + if (request_firmware(&firmware, fw_name, device)) + pr_err("microcode: failed to load file %s\n", fw_name); +} + +void fini_microcode_amd(void) +{ + release_firmware(firmware); +} + static struct microcode_ops microcode_amd_ops = { + .init = init_microcode_amd, + .fini = fini_microcode_amd, .request_microcode_user = request_microcode_user, .request_microcode_fw = request_microcode_fw, .collect_cpu_info = collect_cpu_info_amd, diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index 2bcad3926ed..e68aae39786 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -391,7 +391,7 @@ static enum ucode_state microcode_update_cpu(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; enum ucode_state ustate; - if (uci->valid) + if (uci->valid && uci->mc) ustate = microcode_resume_cpu(cpu); else ustate = microcode_init_cpu(cpu); @@ -518,6 +518,9 @@ static int __init microcode_init(void) return PTR_ERR(microcode_pdev); } + if (microcode_ops->init) + microcode_ops->init(µcode_pdev->dev); + get_online_cpus(); mutex_lock(µcode_mutex); @@ -561,6 +564,9 @@ static void __exit microcode_exit(void) platform_device_unregister(microcode_pdev); + if (microcode_ops->fini) + microcode_ops->fini(); + microcode_ops = NULL; pr_info("Microcode Update Driver: v" MICROCODE_VERSION " removed.\n"); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 5be95ef4ffe..35a57c963df 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -667,36 +667,18 @@ void __init default_get_smp_config(unsigned int early) */ } -static void __init smp_reserve_bootmem(struct mpf_intel *mpf) +static void __init smp_reserve_memory(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); -#ifdef CONFIG_X86_32 - /* - * We cannot access to MPC table to compute table size yet, - * as only few megabytes from the bottom is mapped now. - * PC-9800's MPC table places on the very last of physical - * memory; so that simply reserving PAGE_SIZE from mpf->physptr - * yields BUG() in reserve_bootmem. - * also need to make sure physptr is below than max_low_pfn - * we don't need reserve the area above max_low_pfn - */ - unsigned long end = max_low_pfn * PAGE_SIZE; - if (mpf->physptr < end) { - if (mpf->physptr + size > end) - size = end - mpf->physptr; - reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT); - } -#else - reserve_bootmem_generic(mpf->physptr, size, BOOTMEM_DEFAULT); -#endif + reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc"); } -static int __init smp_scan_config(unsigned long base, unsigned long length, - unsigned reserve) +static int __init smp_scan_config(unsigned long base, unsigned long length) { unsigned int *bp = phys_to_virt(base); struct mpf_intel *mpf; + unsigned long mem; apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n", bp, length); @@ -717,12 +699,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, printk(KERN_INFO "found SMP MP-table at [%p] %llx\n", mpf, (u64)virt_to_phys(mpf)); - if (!reserve) - return 1; - reserve_bootmem_generic(virt_to_phys(mpf), sizeof(*mpf), - BOOTMEM_DEFAULT); + mem = virt_to_phys(mpf); + reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf"); if (mpf->physptr) - smp_reserve_bootmem(mpf); + smp_reserve_memory(mpf); return 1; } @@ -732,7 +712,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length, return 0; } -void __init default_find_smp_config(unsigned int reserve) +void __init default_find_smp_config(void) { unsigned int address; @@ -744,9 +724,9 @@ void __init default_find_smp_config(unsigned int reserve) * 2) Scan the top 1K of base RAM * 3) Scan the 64K of bios */ - if (smp_scan_config(0x0, 0x400, reserve) || - smp_scan_config(639 * 0x400, 0x400, reserve) || - smp_scan_config(0xF0000, 0x10000, reserve)) + if (smp_scan_config(0x0, 0x400) || + smp_scan_config(639 * 0x400, 0x400) || + smp_scan_config(0xF0000, 0x10000)) return; /* * If it is an SMP machine we should know now, unless the @@ -767,7 +747,7 @@ void __init default_find_smp_config(unsigned int reserve) address = get_bios_ebda(); if (address) - smp_scan_config(address, 0x400, reserve); + smp_scan_config(address, 0x400); } #ifdef CONFIG_X86_IO_APIC diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 744508e7cfd..5e2ba634ea1 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -9,6 +9,7 @@ #include <linux/pm.h> #include <linux/clockchips.h> #include <linux/random.h> +#include <linux/user-return-notifier.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> #include <asm/system.h> @@ -209,6 +210,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, */ memset(tss->io_bitmap, 0xff, prev->io_bitmap_max); } + propagate_user_return_notify(prev_p, next_p); } int sys_fork(struct pt_regs *regs) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a98fe88fab6..c95c8f4e790 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -349,26 +349,42 @@ out: return err; } -void -start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +static void +start_thread_common(struct pt_regs *regs, unsigned long new_ip, + unsigned long new_sp, + unsigned int _cs, unsigned int _ss, unsigned int _ds) { loadsegment(fs, 0); - loadsegment(es, 0); - loadsegment(ds, 0); + loadsegment(es, _ds); + loadsegment(ds, _ds); load_gs_index(0); regs->ip = new_ip; regs->sp = new_sp; percpu_write(old_rsp, new_sp); - regs->cs = __USER_CS; - regs->ss = __USER_DS; - regs->flags = 0x200; + regs->cs = _cs; + regs->ss = _ss; + regs->flags = X86_EFLAGS_IF; set_fs(USER_DS); /* * Free the old FP and other extended state */ free_thread_xstate(current); } -EXPORT_SYMBOL_GPL(start_thread); + +void +start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) +{ + start_thread_common(regs, new_ip, new_sp, + __USER_CS, __USER_DS, 0); +} + +#ifdef CONFIG_IA32_EMULATION +void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) +{ + start_thread_common(regs, new_ip, new_sp, + __USER32_CS, __USER32_DS, __USER32_DS); +} +#endif /* * switch_to(x,y) should switch tasks from x to y. diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 6c3b2c6fd77..18093d7498f 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -499,6 +499,7 @@ static void __init quirk_amd_nb_node(struct pci_dev *dev) { struct pci_dev *nb_ht; unsigned int devfn; + u32 node; u32 val; devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0); @@ -507,7 +508,13 @@ static void __init quirk_amd_nb_node(struct pci_dev *dev) return; pci_read_config_dword(nb_ht, 0x60, &val); - set_dev_node(&dev->dev, val & 7); + node = val & 7; + /* + * Some hardware may return an invalid node ID, + * so check it first: + */ + if (node_online(node)) + set_dev_node(&dev->dev, node); pci_dev_put(nb_ht); } diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c index 61a837743fe..201eab63b05 100644 --- a/arch/x86/kernel/reboot_fixups_32.c +++ b/arch/x86/kernel/reboot_fixups_32.c @@ -80,6 +80,7 @@ void mach_reboot_fixups(void) continue; cur->reboot_fixup(dev); + pci_dev_put(dev); } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 82e88cdda9b..946a311a25c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -106,6 +106,7 @@ #include <asm/percpu.h> #include <asm/topology.h> #include <asm/apicdef.h> +#include <asm/k8.h> #ifdef CONFIG_X86_64 #include <asm/numa_64.h> #endif @@ -487,42 +488,11 @@ static void __init reserve_early_setup_data(void) #ifdef CONFIG_KEXEC -/** - * Reserve @size bytes of crashkernel memory at any suitable offset. - * - * @size: Size of the crashkernel memory to reserve. - * Returns the base address on success, and -1ULL on failure. - */ -static -unsigned long long __init find_and_reserve_crashkernel(unsigned long long size) -{ - const unsigned long long alignment = 16<<20; /* 16M */ - unsigned long long start = 0LL; - - while (1) { - int ret; - - start = find_e820_area(start, ULONG_MAX, size, alignment); - if (start == -1ULL) - return start; - - /* try to reserve it */ - ret = reserve_bootmem_generic(start, size, BOOTMEM_EXCLUSIVE); - if (ret >= 0) - return start; - - start += alignment; - } -} - static inline unsigned long long get_total_mem(void) { unsigned long long total; - total = max_low_pfn - min_low_pfn; -#ifdef CONFIG_HIGHMEM - total += highend_pfn - highstart_pfn; -#endif + total = max_pfn - min_low_pfn; return total << PAGE_SHIFT; } @@ -542,21 +512,25 @@ static void __init reserve_crashkernel(void) /* 0 means: find the address automatically */ if (crash_base <= 0) { - crash_base = find_and_reserve_crashkernel(crash_size); + const unsigned long long alignment = 16<<20; /* 16M */ + + crash_base = find_e820_area(alignment, ULONG_MAX, crash_size, + alignment); if (crash_base == -1ULL) { - pr_info("crashkernel reservation failed. " - "No suitable area found.\n"); + pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } } else { - ret = reserve_bootmem_generic(crash_base, crash_size, - BOOTMEM_EXCLUSIVE); - if (ret < 0) { - pr_info("crashkernel reservation failed - " - "memory is in use\n"); + unsigned long long start; + + start = find_e820_area(crash_base, ULONG_MAX, crash_size, + 1<<20); + if (start != crash_base) { + pr_info("crashkernel reservation failed - memory is in use.\n"); return; } } + reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL"); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -699,6 +673,9 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = { void __init setup_arch(char **cmdline_p) { + int acpi = 0; + int k8 = 0; + #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); visws_early_detect(); @@ -791,21 +768,18 @@ void __init setup_arch(char **cmdline_p) strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; -#ifdef CONFIG_X86_64 /* - * Must call this twice: Once just to detect whether hardware doesn't - * support NX (so that the early EHCI debug console setup can safely - * call set_fixmap(), and then again after parsing early parameters to - * honor the respective command line option. + * x86_configure_nx() is called before parse_early_param() to detect + * whether hardware doesn't support NX (so that the early EHCI debug + * console setup can safely call set_fixmap()). It may then be called + * again from within noexec_setup() during parsing early parameters + * to honor the respective command line option. */ - check_efer(); -#endif + x86_configure_nx(); parse_early_param(); -#ifdef CONFIG_X86_64 - check_efer(); -#endif + x86_report_nx(); /* Must be before kernel pagetables are setup */ vmi_activate(); @@ -901,6 +875,13 @@ void __init setup_arch(char **cmdline_p) reserve_brk(); +#ifdef CONFIG_ACPI_SLEEP + /* + * Reserve low memory region for sleep support. + * even before init_memory_mapping + */ + acpi_reserve_wakeup_memory(); +#endif init_gbpages(); /* max_pfn_mapped is updated here */ @@ -927,6 +908,8 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); + reserve_crashkernel(); + vsmp_init(); io_delay_init(); @@ -938,27 +921,24 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); + #ifdef CONFIG_ACPI_NUMA /* * Parse SRAT to discover nodes. */ - acpi_numa_init(); + acpi = acpi_numa_init(); #endif - initmem_init(0, max_pfn); - -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - */ - acpi_reserve_bootmem(); +#ifdef CONFIG_K8_NUMA + if (!acpi) + k8 = !k8_numa_init(0, max_pfn); #endif - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); - reserve_crashkernel(); + initmem_init(0, max_pfn, acpi, k8); #ifdef CONFIG_X86_64 /* diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index fbf3b07c856..74fe6d86dc5 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -19,6 +19,7 @@ #include <linux/stddef.h> #include <linux/personality.h> #include <linux/uaccess.h> +#include <linux/user-return-notifier.h> #include <asm/processor.h> #include <asm/ucontext.h> @@ -863,6 +864,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) if (current->replacement_session_keyring) key_replace_session_keyring(); } + if (thread_info_flags & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); #ifdef CONFIG_X86_32 clear_thread_flag(TIF_IRET); diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 0157cd26d7c..70c2125d55b 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -336,3 +336,4 @@ ENTRY(sys_call_table) .long sys_pwritev .long sys_rt_tgsigqueueinfo /* 335 */ .long sys_perf_event_open + .long sys_recvmmsg diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 1740c85e24b..364d015efeb 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -817,10 +817,8 @@ static int __init uv_init_blade(int blade) */ apicid = blade_to_first_apicid(blade); pa = uv_read_global_mmr64(pnode, UVH_BAU_DATA_CONFIG); - if ((pa & 0xff) != UV_BAU_MESSAGE) { - uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, + uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, ((apicid << 32) | UV_BAU_MESSAGE)); - } return 0; } diff --git a/arch/x86/kernel/uv_time.c b/arch/x86/kernel/uv_time.c index 583f11d5c48..3c84aa001c1 100644 --- a/arch/x86/kernel/uv_time.c +++ b/arch/x86/kernel/uv_time.c @@ -74,7 +74,7 @@ struct uv_rtc_timer_head { */ static struct uv_rtc_timer_head **blade_info __read_mostly; -static int uv_rtc_enable; +static int uv_rtc_evt_enable; /* * Hardware interface routines @@ -90,7 +90,7 @@ static void uv_rtc_send_IPI(int cpu) pnode = uv_apicid_to_pnode(apicid); val = (1UL << UVH_IPI_INT_SEND_SHFT) | (apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (GENERIC_INTERRUPT_VECTOR << UVH_IPI_INT_VECTOR_SHFT); + (X86_PLATFORM_IPI_VECTOR << UVH_IPI_INT_VECTOR_SHFT); uv_write_global_mmr64(pnode, UVH_IPI_INT, val); } @@ -115,7 +115,7 @@ static int uv_setup_intr(int cpu, u64 expires) uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS, UVH_EVENT_OCCURRED0_RTC1_MASK); - val = (GENERIC_INTERRUPT_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | + val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) | ((u64)cpu_physical_id(cpu) << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT); /* Set configuration */ @@ -123,7 +123,10 @@ static int uv_setup_intr(int cpu, u64 expires) /* Initialize comparator value */ uv_write_global_mmr64(pnode, UVH_INT_CMPB, expires); - return (expires < uv_read_rtc(NULL) && !uv_intr_pending(pnode)); + if (uv_read_rtc(NULL) <= expires) + return 0; + + return !uv_intr_pending(pnode); } /* @@ -223,6 +226,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires) next_cpu = head->next_cpu; *t = expires; + /* Will this one be next to go off? */ if (next_cpu < 0 || bcpu == next_cpu || expires < head->cpu[next_cpu].expires) { @@ -231,7 +235,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires) *t = ULLONG_MAX; uv_rtc_find_next_timer(head, pnode); spin_unlock_irqrestore(&head->lock, flags); - return 1; + return -ETIME; } } @@ -244,7 +248,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires) * * Returns 1 if this timer was pending. */ -static int uv_rtc_unset_timer(int cpu) +static int uv_rtc_unset_timer(int cpu, int force) { int pnode = uv_cpu_to_pnode(cpu); int bid = uv_cpu_to_blade_id(cpu); @@ -256,14 +260,15 @@ static int uv_rtc_unset_timer(int cpu) spin_lock_irqsave(&head->lock, flags); - if (head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) + if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force) rc = 1; - *t = ULLONG_MAX; - - /* Was the hardware setup for this timer? */ - if (head->next_cpu == bcpu) - uv_rtc_find_next_timer(head, pnode); + if (rc) { + *t = ULLONG_MAX; + /* Was the hardware setup for this timer? */ + if (head->next_cpu == bcpu) + uv_rtc_find_next_timer(head, pnode); + } spin_unlock_irqrestore(&head->lock, flags); @@ -310,32 +315,32 @@ static void uv_rtc_timer_setup(enum clock_event_mode mode, break; case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: - uv_rtc_unset_timer(ced_cpu); + uv_rtc_unset_timer(ced_cpu, 1); break; } } static void uv_rtc_interrupt(void) { - struct clock_event_device *ced = &__get_cpu_var(cpu_ced); int cpu = smp_processor_id(); + struct clock_event_device *ced = &per_cpu(cpu_ced, cpu); if (!ced || !ced->event_handler) return; - if (uv_rtc_unset_timer(cpu) != 1) + if (uv_rtc_unset_timer(cpu, 0) != 1) return; ced->event_handler(ced); } -static int __init uv_enable_rtc(char *str) +static int __init uv_enable_evt_rtc(char *str) { - uv_rtc_enable = 1; + uv_rtc_evt_enable = 1; return 1; } -__setup("uvrtc", uv_enable_rtc); +__setup("uvrtcevt", uv_enable_evt_rtc); static __init void uv_rtc_register_clockevents(struct work_struct *dummy) { @@ -350,27 +355,32 @@ static __init int uv_rtc_setup_clock(void) { int rc; - if (!uv_rtc_enable || !is_uv_system() || generic_interrupt_extension) + if (!is_uv_system()) return -ENODEV; - generic_interrupt_extension = uv_rtc_interrupt; - clocksource_uv.mult = clocksource_hz2mult(sn_rtc_cycles_per_second, clocksource_uv.shift); + /* If single blade, prefer tsc */ + if (uv_num_possible_blades() == 1) + clocksource_uv.rating = 250; + rc = clocksource_register(&clocksource_uv); - if (rc) { - generic_interrupt_extension = NULL; + if (rc) + printk(KERN_INFO "UV RTC clocksource failed rc %d\n", rc); + else + printk(KERN_INFO "UV RTC clocksource registered freq %lu MHz\n", + sn_rtc_cycles_per_second/(unsigned long)1E6); + + if (rc || !uv_rtc_evt_enable || x86_platform_ipi_callback) return rc; - } /* Setup and register clockevents */ rc = uv_rtc_allocate_timers(); - if (rc) { - clocksource_unregister(&clocksource_uv); - generic_interrupt_extension = NULL; - return rc; - } + if (rc) + goto error; + + x86_platform_ipi_callback = uv_rtc_interrupt; clock_event_device_uv.mult = div_sc(sn_rtc_cycles_per_second, NSEC_PER_SEC, clock_event_device_uv.shift); @@ -383,11 +393,19 @@ static __init int uv_rtc_setup_clock(void) rc = schedule_on_each_cpu(uv_rtc_register_clockevents); if (rc) { - clocksource_unregister(&clocksource_uv); - generic_interrupt_extension = NULL; + x86_platform_ipi_callback = NULL; uv_rtc_deallocate_timers(); + goto error; } + printk(KERN_INFO "UV RTC clockevents registered\n"); + + return 0; + +error: + clocksource_unregister(&clocksource_uv); + printk(KERN_INFO "UV RTC clockevents failed rc %d\n", rc); + return rc; } arch_initcall(uv_rtc_setup_clock); diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index abda6f53e71..34a279a7471 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -197,7 +197,7 @@ static void __init MP_processor_info(struct mpc_cpu *m) apic_version[m->apicid] = ver; } -static void __init visws_find_smp_config(unsigned int reserve) +static void __init visws_find_smp_config(void) { struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS); unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS)); diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 611b9e2360d..74c92bb194d 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -226,7 +226,7 @@ static void __devinit vmi_time_init_clockevent(void) evt->min_delta_ns = clockevent_delta2ns(1, evt); evt->cpumask = cpumask_of(cpu); - printk(KERN_WARNING "vmi: registering clock event %s. mult=%lu shift=%u\n", + printk(KERN_WARNING "vmi: registering clock event %s. mult=%u shift=%u\n", evt->name, evt->mult, evt->shift); clockevents_register_device(evt); } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3c68fe2d46c..f3f2104408d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -41,6 +41,32 @@ ENTRY(phys_startup_64) jiffies_64 = jiffies; #endif +#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) +/* + * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA + * we retain large page mappings for boundaries spanning kernel text, rodata + * and data sections. + * + * However, kernel identity mappings will have different RWX permissions + * to the pages mapping to text and to the pages padding (which are freed) the + * text section. Hence kernel identity mappings will be broken to smaller + * pages. For 64-bit, kernel text and kernel identity mappings are different, + * so we can enable protection checks that come with CONFIG_DEBUG_RODATA, + * as well as retain 2MB large page mappings for kernel text. + */ +#define X64_ALIGN_DEBUG_RODATA_BEGIN . = ALIGN(HPAGE_SIZE); + +#define X64_ALIGN_DEBUG_RODATA_END \ + . = ALIGN(HPAGE_SIZE); \ + __end_rodata_hpage_align = .; + +#else + +#define X64_ALIGN_DEBUG_RODATA_BEGIN +#define X64_ALIGN_DEBUG_RODATA_END + +#endif + PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(7); /* RWE */ @@ -90,7 +116,9 @@ SECTIONS EXCEPTION_TABLE(16) :text = 0x9090 + X64_ALIGN_DEBUG_RODATA_BEGIN RO_DATA(PAGE_SIZE) + X64_ALIGN_DEBUG_RODATA_END /* Data */ .data : AT(ADDR(.data) - LOAD_OFFSET) { @@ -107,13 +135,13 @@ SECTIONS PAGE_ALIGNED_DATA(PAGE_SIZE) - CACHELINE_ALIGNED_DATA(CONFIG_X86_L1_CACHE_BYTES) + CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) DATA_DATA CONSTRUCTORS /* rarely changed data like cpu maps */ - READ_MOSTLY_DATA(CONFIG_X86_INTERNODE_CACHE_BYTES) + READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES) /* End of data section */ _edata = .; @@ -137,12 +165,12 @@ SECTIONS *(.vsyscall_0) } :user - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .vsyscall_fn : AT(VLOAD(.vsyscall_fn)) { *(.vsyscall_fn) } - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .vsyscall_gtod_data : AT(VLOAD(.vsyscall_gtod_data)) { *(.vsyscall_gtod_data) } @@ -166,7 +194,7 @@ SECTIONS } vgetcpu_mode = VVIRT(.vgetcpu_mode); - . = ALIGN(CONFIG_X86_L1_CACHE_BYTES); + . = ALIGN(L1_CACHE_BYTES); .jiffies : AT(VLOAD(.jiffies)) { *(.jiffies) } diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8cb4974ff59..9055e5872ff 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -73,7 +73,8 @@ void update_vsyscall_tz(void) write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags); } -void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) +void update_vsyscall(struct timespec *wall_time, struct clocksource *clock, + u32 mult) { unsigned long flags; @@ -82,7 +83,7 @@ void update_vsyscall(struct timespec *wall_time, struct clocksource *clock) vsyscall_gtod_data.clock.vread = clock->vread; vsyscall_gtod_data.clock.cycle_last = clock->cycle_last; vsyscall_gtod_data.clock.mask = clock->mask; - vsyscall_gtod_data.clock.mult = clock->mult; + vsyscall_gtod_data.clock.mult = mult; vsyscall_gtod_data.clock.shift = clock->shift; vsyscall_gtod_data.wall_time_sec = wall_time->tv_sec; vsyscall_gtod_data.wall_time_nsec = wall_time->tv_nsec; @@ -237,7 +238,7 @@ static ctl_table kernel_table2[] = { }; static ctl_table kernel_root_table2[] = { - { .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, + { .procname = "kernel", .mode = 0555, .child = kernel_table2 }, {} }; diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index d11c5ff7c65..ccd179dec36 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -13,6 +13,7 @@ #include <asm/e820.h> #include <asm/time.h> #include <asm/irq.h> +#include <asm/pat.h> #include <asm/tsc.h> #include <asm/iommu.h> @@ -80,4 +81,5 @@ struct x86_platform_ops x86_platform = { .get_wallclock = mach_get_cmos_time, .set_wallclock = mach_set_rtc_mmss, .iommu_shutdown = iommu_shutdown_noop, + .is_untracked_pat_range = is_ISA_range, }; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b84e571f417..4cd49833246 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select HAVE_KVM_IRQCHIP select HAVE_KVM_EVENTFD select KVM_APIC_ARCHITECTURE + select USER_RETURN_NOTIFIER ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 0e7fe78d0f7..31a7035c4bd 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -6,7 +6,8 @@ CFLAGS_svm.o := -I. CFLAGS_vmx.o := -I. kvm-y += $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \ - coalesced_mmio.o irq_comm.o eventfd.o) + coalesced_mmio.o irq_comm.o eventfd.o \ + assigned-dev.o) kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1be5cd640e9..7e8faea4651 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -75,6 +75,8 @@ #define Group (1<<14) /* Bits 3:5 of modrm byte extend opcode */ #define GroupDual (1<<15) /* Alternate decoding of mod == 3 */ #define GroupMask 0xff /* Group number stored in bits 0:7 */ +/* Misc flags */ +#define No64 (1<<28) /* Source 2 operand type */ #define Src2None (0<<29) #define Src2CL (1<<29) @@ -92,19 +94,23 @@ static u32 opcode_table[256] = { /* 0x00 - 0x07 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x08 - 0x0F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - 0, 0, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, 0, /* 0x10 - 0x17 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x18 - 0x1F */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, - ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0, + ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, /* 0x20 - 0x27 */ ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM, @@ -133,7 +139,8 @@ static u32 opcode_table[256] = { DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack, /* 0x60 - 0x67 */ - 0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , + ImplicitOps | Stack | No64, ImplicitOps | Stack | No64, + 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ , 0, 0, 0, 0, /* 0x68 - 0x6F */ SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0, @@ -158,7 +165,7 @@ static u32 opcode_table[256] = { /* 0x90 - 0x97 */ DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, DstReg, /* 0x98 - 0x9F */ - 0, 0, SrcImm | Src2Imm16, 0, + 0, 0, SrcImm | Src2Imm16 | No64, 0, ImplicitOps | Stack, ImplicitOps | Stack, 0, 0, /* 0xA0 - 0xA7 */ ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs, @@ -185,7 +192,7 @@ static u32 opcode_table[256] = { ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, /* 0xC8 - 0xCF */ 0, 0, 0, ImplicitOps | Stack, - ImplicitOps, SrcImmByte, ImplicitOps, ImplicitOps, + ImplicitOps, SrcImmByte, ImplicitOps | No64, ImplicitOps, /* 0xD0 - 0xD7 */ ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, @@ -198,7 +205,7 @@ static u32 opcode_table[256] = { ByteOp | SrcImmUByte, SrcImmUByte, /* 0xE8 - 0xEF */ SrcImm | Stack, SrcImm | ImplicitOps, - SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps, + SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps, /* 0xF0 - 0xF7 */ @@ -244,11 +251,13 @@ static u32 twobyte_table[256] = { /* 0x90 - 0x9F */ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, /* 0xA0 - 0xA7 */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, + ImplicitOps | Stack, ImplicitOps | Stack, + 0, DstMem | SrcReg | ModRM | BitOp, DstMem | SrcReg | Src2ImmByte | ModRM, DstMem | SrcReg | Src2CL | ModRM, 0, 0, /* 0xA8 - 0xAF */ - 0, 0, 0, DstMem | SrcReg | ModRM | BitOp, + ImplicitOps | Stack, ImplicitOps | Stack, + 0, DstMem | SrcReg | ModRM | BitOp, DstMem | SrcReg | Src2ImmByte | ModRM, DstMem | SrcReg | Src2CL | ModRM, ModRM, 0, @@ -613,6 +622,9 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt, { int rc = 0; + /* x86 instructions are limited to 15 bytes. */ + if (eip + size - ctxt->decode.eip_orig > 15) + return X86EMUL_UNHANDLEABLE; eip += ctxt->cs_base; while (size--) { rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++); @@ -871,7 +883,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) /* Shadow copy of register state. Committed on successful emulation. */ memset(c, 0, sizeof(struct decode_cache)); - c->eip = kvm_rip_read(ctxt->vcpu); + c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu); ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS); memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs); @@ -962,6 +974,11 @@ done_prefixes: } } + if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) { + kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");; + return -1; + } + if (c->d & Group) { group = c->d & GroupMask; c->modrm = insn_fetch(u8, 1, c->eip); @@ -1186,6 +1203,69 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, return rc; } +static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg) +{ + struct decode_cache *c = &ctxt->decode; + struct kvm_segment segment; + + kvm_x86_ops->get_segment(ctxt->vcpu, &segment, seg); + + c->src.val = segment.selector; + emulate_push(ctxt); +} + +static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops, int seg) +{ + struct decode_cache *c = &ctxt->decode; + unsigned long selector; + int rc; + + rc = emulate_pop(ctxt, ops, &selector, c->op_bytes); + if (rc != 0) + return rc; + + rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, 1, seg); + return rc; +} + +static void emulate_pusha(struct x86_emulate_ctxt *ctxt) +{ + struct decode_cache *c = &ctxt->decode; + unsigned long old_esp = c->regs[VCPU_REGS_RSP]; + int reg = VCPU_REGS_RAX; + + while (reg <= VCPU_REGS_RDI) { + (reg == VCPU_REGS_RSP) ? + (c->src.val = old_esp) : (c->src.val = c->regs[reg]); + + emulate_push(ctxt); + ++reg; + } +} + +static int emulate_popa(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc = 0; + int reg = VCPU_REGS_RDI; + + while (reg >= VCPU_REGS_RAX) { + if (reg == VCPU_REGS_RSP) { + register_address_increment(c, &c->regs[VCPU_REGS_RSP], + c->op_bytes); + --reg; + } + + rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes); + if (rc != 0) + break; + --reg; + } + return rc; +} + static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1707,18 +1787,45 @@ special_insn: add: /* add */ emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags); break; + case 0x06: /* push es */ + emulate_push_sreg(ctxt, VCPU_SREG_ES); + break; + case 0x07: /* pop es */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES); + if (rc != 0) + goto done; + break; case 0x08 ... 0x0d: or: /* or */ emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags); break; + case 0x0e: /* push cs */ + emulate_push_sreg(ctxt, VCPU_SREG_CS); + break; case 0x10 ... 0x15: adc: /* adc */ emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags); break; + case 0x16: /* push ss */ + emulate_push_sreg(ctxt, VCPU_SREG_SS); + break; + case 0x17: /* pop ss */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS); + if (rc != 0) + goto done; + break; case 0x18 ... 0x1d: sbb: /* sbb */ emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags); break; + case 0x1e: /* push ds */ + emulate_push_sreg(ctxt, VCPU_SREG_DS); + break; + case 0x1f: /* pop ds */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS); + if (rc != 0) + goto done; + break; case 0x20 ... 0x25: and: /* and */ emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags); @@ -1750,6 +1857,14 @@ special_insn: if (rc != 0) goto done; break; + case 0x60: /* pusha */ + emulate_pusha(ctxt); + break; + case 0x61: /* popa */ + rc = emulate_popa(ctxt, ops); + if (rc != 0) + goto done; + break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) goto cannot_emulate; @@ -1761,7 +1876,7 @@ special_insn: break; case 0x6c: /* insb */ case 0x6d: /* insw/insd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + if (kvm_emulate_pio_string(ctxt->vcpu, 1, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? @@ -1777,7 +1892,7 @@ special_insn: return 0; case 0x6e: /* outsb */ case 0x6f: /* outsw/outsd */ - if (kvm_emulate_pio_string(ctxt->vcpu, NULL, + if (kvm_emulate_pio_string(ctxt->vcpu, 0, (c->d & ByteOp) ? 1 : c->op_bytes, c->rep_prefix ? @@ -2070,7 +2185,7 @@ special_insn: case 0xef: /* out (e/r)ax,dx */ port = c->regs[VCPU_REGS_RDX]; io_dir_in = 0; - do_io: if (kvm_emulate_pio(ctxt->vcpu, NULL, io_dir_in, + do_io: if (kvm_emulate_pio(ctxt->vcpu, io_dir_in, (c->d & ByteOp) ? 1 : c->op_bytes, port) != 0) { c->eip = saved_eip; @@ -2297,6 +2412,14 @@ twobyte_insn: jmp_rel(c, c->src.val); c->dst.type = OP_NONE; break; + case 0xa0: /* push fs */ + emulate_push_sreg(ctxt, VCPU_SREG_FS); + break; + case 0xa1: /* pop fs */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS); + if (rc != 0) + goto done; + break; case 0xa3: bt: /* bt */ c->dst.type = OP_NONE; @@ -2308,6 +2431,14 @@ twobyte_insn: case 0xa5: /* shld cl, r, r/m */ emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags); break; + case 0xa8: /* push gs */ + emulate_push_sreg(ctxt, VCPU_SREG_GS); + break; + case 0xa9: /* pop gs */ + rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS); + if (rc != 0) + goto done; + break; case 0xab: bts: /* bts */ /* only subword offset */ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 144e7f60b5e..fab7440c9bb 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -688,10 +688,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm) struct kvm_vcpu *vcpu; int i; - mutex_lock(&kvm->irq_lock); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1); kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0); - mutex_unlock(&kvm->irq_lock); /* * Provides NMI watchdog support via Virtual Wire mode. diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 01f15168280..d057c0cbd24 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -38,7 +38,15 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq) s->isr_ack |= (1 << irq); if (s != &s->pics_state->pics[0]) irq += 8; + /* + * We are dropping lock while calling ack notifiers since ack + * notifier callbacks for assigned devices call into PIC recursively. + * Other interrupt may be delivered to PIC while lock is dropped but + * it should be safe since PIC state is already updated at this stage. + */ + spin_unlock(&s->pics_state->lock); kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq); + spin_lock(&s->pics_state->lock); } void kvm_pic_clear_isr_ack(struct kvm *kvm) @@ -176,16 +184,18 @@ int kvm_pic_set_irq(void *opaque, int irq, int level) static inline void pic_intack(struct kvm_kpic_state *s, int irq) { s->isr |= 1 << irq; - if (s->auto_eoi) { - if (s->rotate_on_auto_eoi) - s->priority_add = (irq + 1) & 7; - pic_clear_isr(s, irq); - } /* * We don't clear a level sensitive interrupt here */ if (!(s->elcr & (1 << irq))) s->irr &= ~(1 << irq); + + if (s->auto_eoi) { + if (s->rotate_on_auto_eoi) + s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); + } + } int kvm_pic_read_irq(struct kvm *kvm) @@ -225,22 +235,11 @@ int kvm_pic_read_irq(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, irqbase, n; + int irq; struct kvm *kvm = s->pics_state->irq_request_opaque; struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu; + u8 irr = s->irr, isr = s->imr; - if (s == &s->pics_state->pics[0]) - irqbase = 0; - else - irqbase = 8; - - for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { - if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) - if (s->irr & (1 << irq) || s->isr & (1 << irq)) { - n = irq + irqbase; - kvm_notify_acked_irq(kvm, SELECT_PIC(n), n); - } - } s->last_irr = 0; s->irr = 0; s->imr = 0; @@ -256,6 +255,13 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->rotate_on_auto_eoi = 0; s->special_fully_nested_mode = 0; s->init4 = 0; + + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { + if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) + if (irr & (1 << irq) || isr & (1 << irq)) { + pic_clear_isr(s, irq); + } + } } static void pic_ioport_write(void *opaque, u32 addr, u32 val) @@ -298,9 +304,9 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val) priority = get_priority(s, s->isr); if (priority != 8) { irq = (priority + s->priority_add) & 7; - pic_clear_isr(s, irq); if (cmd == 5) s->priority_add = (irq + 1) & 7; + pic_clear_isr(s, irq); pic_update_irq(s->pics_state); } break; diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 7d6058a2fd3..be399e207d5 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -71,6 +71,7 @@ struct kvm_pic { int output; /* intr from master PIC */ struct kvm_io_device dev; void (*ack_notifier)(void *opaque, int irq); + unsigned long irq_states[16]; }; struct kvm_pic *kvm_create_pic(struct kvm *kvm); @@ -85,7 +86,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) static inline int irqchip_in_kernel(struct kvm *kvm) { - return pic_irqchip(kvm) != NULL; + int ret; + + ret = (pic_irqchip(kvm) != NULL); + smp_rmb(); + return ret; } void kvm_pic_reset(struct kvm_kpic_state *s); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 23c217692ea..cd60c0bd1b3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -32,7 +32,6 @@ #include <asm/current.h> #include <asm/apicdef.h> #include <asm/atomic.h> -#include <asm/apicdef.h> #include "kvm_cache_regs.h" #include "irq.h" #include "trace.h" @@ -471,11 +470,8 @@ static void apic_set_eoi(struct kvm_lapic *apic) trigger_mode = IOAPIC_LEVEL_TRIG; else trigger_mode = IOAPIC_EDGE_TRIG; - if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) { - mutex_lock(&apic->vcpu->kvm->irq_lock); + if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode); - mutex_unlock(&apic->vcpu->kvm->irq_lock); - } } static void apic_send_ipi(struct kvm_lapic *apic) @@ -504,9 +500,7 @@ static void apic_send_ipi(struct kvm_lapic *apic) irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode, irq.vector); - mutex_lock(&apic->vcpu->kvm->irq_lock); kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq); - mutex_unlock(&apic->vcpu->kvm->irq_lock); } static u32 apic_get_tmcct(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 818b92ad82c..4c3e5b2314c 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2789,7 +2789,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) if (r) goto out; - er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0); + er = emulate_instruction(vcpu, cr2, error_code, 0); switch (er) { case EMULATE_DONE: @@ -2800,6 +2800,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code) case EMULATE_FAIL: vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; return 0; default: BUG(); diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 72558f8ff3f..a6017132fba 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -467,7 +467,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) level = iterator.level; sptep = iterator.sptep; - /* FIXME: properly handle invlpg on large guest pages */ if (level == PT_PAGE_TABLE_LEVEL || ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) || ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) { diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index c17404add91..3de0b37ec03 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -46,6 +46,7 @@ MODULE_LICENSE("GPL"); #define SVM_FEATURE_NPT (1 << 0) #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) +#define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ #define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */ @@ -53,15 +54,6 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) -/* Turn on to get debugging output*/ -/* #define NESTED_DEBUG */ - -#ifdef NESTED_DEBUG -#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args) -#else -#define nsvm_printk(fmt, args...) do {} while(0) -#endif - static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, @@ -85,6 +77,9 @@ struct nested_state { /* gpa pointers to the real vectors */ u64 vmcb_msrpm; + /* A VMEXIT is required but not yet emulated */ + bool exit_required; + /* cache for intercepts of the guest */ u16 intercept_cr_read; u16 intercept_cr_write; @@ -112,6 +107,8 @@ struct vcpu_svm { u32 *msrpm; struct nested_state nested; + + bool nmi_singlestep; }; /* enable NPT for AMD64 and X86 with PAE */ @@ -286,7 +283,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (!svm->next_rip) { - if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) != + if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -316,7 +313,7 @@ static void svm_hardware_disable(void *garbage) cpu_svm_disable(); } -static void svm_hardware_enable(void *garbage) +static int svm_hardware_enable(void *garbage) { struct svm_cpu_data *svm_data; @@ -325,16 +322,21 @@ static void svm_hardware_enable(void *garbage) struct desc_struct *gdt; int me = raw_smp_processor_id(); + rdmsrl(MSR_EFER, efer); + if (efer & EFER_SVME) + return -EBUSY; + if (!has_svm()) { - printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me); - return; + printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n", + me); + return -EINVAL; } svm_data = per_cpu(svm_data, me); if (!svm_data) { - printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n", + printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n", me); - return; + return -EINVAL; } svm_data->asid_generation = 1; @@ -345,11 +347,12 @@ static void svm_hardware_enable(void *garbage) gdt = (struct desc_struct *)gdt_descr.base; svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); - rdmsrl(MSR_EFER, efer); wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); + + return 0; } static void svm_cpu_uninit(int cpu) @@ -476,7 +479,7 @@ static __init int svm_hardware_setup(void) kvm_enable_efer_bits(EFER_SVME); } - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { r = svm_cpu_init(cpu); if (r) goto err; @@ -510,7 +513,7 @@ static __exit void svm_hardware_unsetup(void) { int cpu; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) svm_cpu_uninit(cpu); __free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER); @@ -625,11 +628,12 @@ static void init_vmcb(struct vcpu_svm *svm) save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; - /* - * cr0 val on cpu init should be 0x60000010, we enable cpu - * cache by default. the orderly way is to enable cache in bios. + /* This is the guest-visible cr0 value. + * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0. */ - save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP; + svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; + kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0); + save->cr4 = X86_CR4_PAE; /* rdx = ?? */ @@ -644,8 +648,6 @@ static void init_vmcb(struct vcpu_svm *svm) control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK| INTERCEPT_CR3_MASK); save->g_pat = 0x0007040600070406ULL; - /* enable caching because the QEMU Bios doesn't enable it */ - save->cr0 = X86_CR0_ET; save->cr3 = 0; save->cr4 = 0; } @@ -654,6 +656,11 @@ static void init_vmcb(struct vcpu_svm *svm) svm->nested.vmcb = 0; svm->vcpu.arch.hflags = 0; + if (svm_has(SVM_FEATURE_PAUSE_FILTER)) { + control->pause_filter_count = 3000; + control->intercept |= (1ULL << INTERCEPT_PAUSE); + } + enable_gif(svm); } @@ -758,14 +765,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) int i; if (unlikely(cpu != vcpu->cpu)) { - u64 tsc_this, delta; + u64 delta; /* * Make sure that the guest sees a monotonically * increasing TSC. */ - rdtscll(tsc_this); - delta = vcpu->arch.host_tsc - tsc_this; + delta = vcpu->arch.host_tsc - native_read_tsc(); svm->vmcb->control.tsc_offset += delta; if (is_nested(svm)) svm->nested.hsave->control.tsc_offset += delta; @@ -787,7 +793,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); - rdtscll(vcpu->arch.host_tsc); + vcpu->arch.host_tsc = native_read_tsc(); } static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) @@ -1045,7 +1051,7 @@ static void update_db_intercept(struct kvm_vcpu *vcpu) svm->vmcb->control.intercept_exceptions &= ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); - if (vcpu->arch.singlestep) + if (svm->nmi_singlestep) svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { @@ -1060,26 +1066,16 @@ static void update_db_intercept(struct kvm_vcpu *vcpu) vcpu->guest_debug = 0; } -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int old_debug = vcpu->guest_debug; struct vcpu_svm *svm = to_svm(vcpu); - vcpu->guest_debug = dbg->control; - - update_db_intercept(vcpu); - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) svm->vmcb->save.dr7 = dbg->arch.debugreg[7]; else svm->vmcb->save.dr7 = vcpu->arch.dr7; - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - - return 0; + update_db_intercept(vcpu); } static void load_host_msrs(struct kvm_vcpu *vcpu) @@ -1180,7 +1176,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, } } -static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int pf_interception(struct vcpu_svm *svm) { u64 fault_address; u32 error_code; @@ -1194,17 +1190,19 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); } -static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int db_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && - !svm->vcpu.arch.singlestep) { + !svm->nmi_singlestep) { kvm_queue_exception(&svm->vcpu, DB_VECTOR); return 1; } - if (svm->vcpu.arch.singlestep) { - svm->vcpu.arch.singlestep = false; + if (svm->nmi_singlestep) { + svm->nmi_singlestep = false; if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); @@ -1223,25 +1221,27 @@ static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int bp_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + kvm_run->exit_reason = KVM_EXIT_DEBUG; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = BP_VECTOR; return 0; } -static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int ud_interception(struct vcpu_svm *svm) { int er; - er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } -static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nm_interception(struct vcpu_svm *svm) { svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR); if (!(svm->vcpu.arch.cr0 & X86_CR0_TS)) @@ -1251,7 +1251,7 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int mc_interception(struct vcpu_svm *svm) { /* * On an #MC intercept the MCE handler is not called automatically in @@ -1264,8 +1264,10 @@ static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int shutdown_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + /* * VMCB is undefined after a SHUTDOWN intercept * so reinitialize it. @@ -1277,7 +1279,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 0; } -static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int io_interception(struct vcpu_svm *svm) { u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ int size, in, string; @@ -1291,7 +1293,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) if (string) { if (emulate_instruction(&svm->vcpu, - kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } @@ -1301,33 +1303,33 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; skip_emulated_instruction(&svm->vcpu); - return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); + return kvm_emulate_pio(&svm->vcpu, in, size, port); } -static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nmi_interception(struct vcpu_svm *svm) { return 1; } -static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int intr_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.irq_exits; return 1; } -static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int nop_on_interception(struct vcpu_svm *svm) { return 1; } -static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +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, struct kvm_run *kvm_run) +static int vmmcall_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; skip_emulated_instruction(&svm->vcpu); @@ -1378,8 +1380,15 @@ static inline int nested_svm_intr(struct vcpu_svm *svm) svm->vmcb->control.exit_code = SVM_EXIT_INTR; - if (nested_svm_exit_handled(svm)) { - nsvm_printk("VMexit -> INTR\n"); + if (svm->nested.intercept & 1ULL) { + /* + * The #vmexit can't be emulated here directly because this + * code path runs with irqs and preemtion disabled. A + * #vmexit emulation might sleep. Only signal request for + * the #vmexit here. + */ + svm->nested.exit_required = true; + trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip); return 1; } @@ -1390,10 +1399,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx) { struct page *page; - down_read(¤t->mm->mmap_sem); page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT); - up_read(¤t->mm->mmap_sem); - if (is_error_page(page)) goto error; @@ -1532,14 +1538,12 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm) } default: { u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); - nsvm_printk("exit code: 0x%x\n", exit_code); if (svm->nested.intercept & exit_bits) vmexit = NESTED_EXIT_DONE; } } if (vmexit == NESTED_EXIT_DONE) { - nsvm_printk("#VMEXIT reason=%04x\n", exit_code); nested_svm_vmexit(svm); } @@ -1584,6 +1588,12 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) struct vmcb *hsave = svm->nested.hsave; struct vmcb *vmcb = svm->vmcb; + trace_kvm_nested_vmexit_inject(vmcb->control.exit_code, + vmcb->control.exit_info_1, + vmcb->control.exit_info_2, + vmcb->control.exit_int_info, + vmcb->control.exit_int_info_err); + nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0); if (!nested_vmcb) return 1; @@ -1617,6 +1627,22 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2; nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info; nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err; + + /* + * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have + * to make sure that we do not lose injected events. So check event_inj + * here and copy it to exit_int_info if it is valid. + * Exit_int_info and event_inj can't be both valid because the case + * below only happens on a VMRUN instruction intercept which has + * no valid exit_int_info set. + */ + if (vmcb->control.event_inj & SVM_EVTINJ_VALID) { + struct vmcb_control_area *nc = &nested_vmcb->control; + + nc->exit_int_info = vmcb->control.event_inj; + nc->exit_int_info_err = vmcb->control.event_inj_err; + } + nested_vmcb->control.tlb_ctl = 0; nested_vmcb->control.event_inj = 0; nested_vmcb->control.event_inj_err = 0; @@ -1628,10 +1654,6 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) /* Restore the original control entries */ copy_vmcb_control_area(vmcb, hsave); - /* Kill any pending exceptions */ - if (svm->vcpu.arch.exception.pending == true) - nsvm_printk("WARNING: Pending Exception\n"); - kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -1702,6 +1724,12 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) /* nested_vmcb is our indicator if nested SVM is activated */ svm->nested.vmcb = svm->vmcb->save.rax; + trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb, + nested_vmcb->save.rip, + nested_vmcb->control.int_ctl, + nested_vmcb->control.event_inj, + nested_vmcb->control.nested_ctl); + /* Clear internal status */ kvm_clear_exception_queue(&svm->vcpu); kvm_clear_interrupt_queue(&svm->vcpu); @@ -1789,28 +1817,15 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->nested.intercept = nested_vmcb->control.intercept; force_new_asid(&svm->vcpu); - svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info; - svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err; svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; - if (nested_vmcb->control.int_ctl & V_IRQ_MASK) { - nsvm_printk("nSVM Injecting Interrupt: 0x%x\n", - nested_vmcb->control.int_ctl); - } if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; else svm->vcpu.arch.hflags &= ~HF_VINTR_MASK; - nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n", - nested_vmcb->control.exit_int_info, - nested_vmcb->control.int_state); - svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; svm->vmcb->control.int_state = nested_vmcb->control.int_state; svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset; - if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID) - nsvm_printk("Injecting Event: 0x%x\n", - nested_vmcb->control.event_inj); svm->vmcb->control.event_inj = nested_vmcb->control.event_inj; svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err; @@ -1837,7 +1852,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; } -static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmload_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -1857,7 +1872,7 @@ static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmsave_interception(struct vcpu_svm *svm) { struct vmcb *nested_vmcb; @@ -1877,10 +1892,8 @@ static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int vmrun_interception(struct vcpu_svm *svm) { - nsvm_printk("VMrun\n"); - if (nested_svm_check_permissions(svm)) return 1; @@ -1907,7 +1920,7 @@ failed: return 1; } -static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int stgi_interception(struct vcpu_svm *svm) { if (nested_svm_check_permissions(svm)) return 1; @@ -1920,7 +1933,7 @@ static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int clgi_interception(struct vcpu_svm *svm) { if (nested_svm_check_permissions(svm)) return 1; @@ -1937,10 +1950,12 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int invlpga_interception(struct vcpu_svm *svm) { struct kvm_vcpu *vcpu = &svm->vcpu; - nsvm_printk("INVLPGA\n"); + + trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX], + vcpu->arch.regs[VCPU_REGS_RAX]); /* Let's treat INVLPGA the same as INVLPG (can be optimized!) */ kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]); @@ -1950,15 +1965,21 @@ static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invalid_op_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int skinit_interception(struct vcpu_svm *svm) { + trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]); + kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; } -static int task_switch_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int invalid_op_interception(struct vcpu_svm *svm) +{ + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; +} + +static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; int reason; @@ -2008,14 +2029,14 @@ static int task_switch_interception(struct vcpu_svm *svm, return kvm_task_switch(&svm->vcpu, tss_selector, reason); } -static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int cpuid_interception(struct vcpu_svm *svm) { svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; kvm_emulate_cpuid(&svm->vcpu); return 1; } -static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int iret_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.nmi_window_exits; svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); @@ -2023,26 +2044,27 @@ static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int invlpg_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE) + if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } -static int emulate_on_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int emulate_on_interception(struct vcpu_svm *svm) { - if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE) + if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE) pr_unimpl(&svm->vcpu, "%s: failed\n", __func__); return 1; } -static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int cr8_write_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ - emulate_instruction(&svm->vcpu, NULL, 0, 0, 0); + emulate_instruction(&svm->vcpu, 0, 0, 0); if (irqchip_in_kernel(svm->vcpu.kvm)) { svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; return 1; @@ -2128,7 +2150,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) return 0; } -static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int rdmsr_interception(struct vcpu_svm *svm) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data; @@ -2221,7 +2243,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) return 0; } -static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int wrmsr_interception(struct vcpu_svm *svm) { u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) @@ -2237,17 +2259,18 @@ static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } -static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +static int msr_interception(struct vcpu_svm *svm) { if (svm->vmcb->control.exit_info_1) - return wrmsr_interception(svm, kvm_run); + return wrmsr_interception(svm); else - return rdmsr_interception(svm, kvm_run); + return rdmsr_interception(svm); } -static int interrupt_window_interception(struct vcpu_svm *svm, - struct kvm_run *kvm_run) +static int interrupt_window_interception(struct vcpu_svm *svm) { + struct kvm_run *kvm_run = svm->vcpu.run; + svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; /* @@ -2265,8 +2288,13 @@ static int interrupt_window_interception(struct vcpu_svm *svm, return 1; } -static int (*svm_exit_handlers[])(struct vcpu_svm *svm, - struct kvm_run *kvm_run) = { +static int pause_interception(struct vcpu_svm *svm) +{ + kvm_vcpu_on_spin(&(svm->vcpu)); + return 1; +} + +static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = emulate_on_interception, [SVM_EXIT_READ_CR3] = emulate_on_interception, [SVM_EXIT_READ_CR4] = emulate_on_interception, @@ -2301,6 +2329,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, [SVM_EXIT_INVLPGA] = invlpga_interception, @@ -2314,26 +2343,36 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_VMSAVE] = vmsave_interception, [SVM_EXIT_STGI] = stgi_interception, [SVM_EXIT_CLGI] = clgi_interception, - [SVM_EXIT_SKINIT] = invalid_op_interception, + [SVM_EXIT_SKINIT] = skinit_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, [SVM_EXIT_MWAIT] = invalid_op_interception, [SVM_EXIT_NPF] = pf_interception, }; -static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; trace_kvm_exit(exit_code, svm->vmcb->save.rip); + if (unlikely(svm->nested.exit_required)) { + nested_svm_vmexit(svm); + svm->nested.exit_required = false; + + return 1; + } + if (is_nested(svm)) { int vmexit; - nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n", - exit_code, svm->vmcb->control.exit_info_1, - svm->vmcb->control.exit_info_2, svm->vmcb->save.rip); + trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code, + svm->vmcb->control.exit_info_1, + svm->vmcb->control.exit_info_2, + svm->vmcb->control.exit_int_info, + svm->vmcb->control.exit_int_info_err); vmexit = nested_svm_exit_special(svm); @@ -2383,7 +2422,7 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) return 0; } - return svm_exit_handlers[exit_code](svm, kvm_run); + return svm_exit_handlers[exit_code](svm); } static void reload_tss(struct kvm_vcpu *vcpu) @@ -2460,20 +2499,47 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu) !(svm->vcpu.arch.hflags & HF_NMI_MASK); } +static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return !!(svm->vcpu.arch.hflags & HF_NMI_MASK); +} + +static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (masked) { + svm->vcpu.arch.hflags |= HF_NMI_MASK; + svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET); + } else { + svm->vcpu.arch.hflags &= ~HF_NMI_MASK; + svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET); + } +} + static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - return (vmcb->save.rflags & X86_EFLAGS_IF) && - !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) && - gif_set(svm) && - !(is_nested(svm) && (svm->vcpu.arch.hflags & HF_VINTR_MASK)); + int ret; + + if (!gif_set(svm) || + (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) + return 0; + + ret = !!(vmcb->save.rflags & X86_EFLAGS_IF); + + if (is_nested(svm)) + return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); + + return ret; } static void enable_irq_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - nsvm_printk("Trying to open IRQ window\n"); nested_svm_intr(svm); @@ -2498,7 +2564,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) /* Something prevents NMI from been injected. Single step over possible problem (IRET or exception injection or interrupt shadow) */ - vcpu->arch.singlestep = true; + svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); update_db_intercept(vcpu); } @@ -2588,13 +2654,20 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) #define R "e" #endif -static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); u16 fs_selector; u16 gs_selector; u16 ldt_selector; + /* + * A vmexit emulation is required before the vcpu can be executed + * again. + */ + if (unlikely(svm->nested.exit_required)) + return; + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; @@ -2893,6 +2966,8 @@ static struct kvm_x86_ops svm_x86_ops = { .queue_exception = svm_queue_exception, .interrupt_allowed = svm_interrupt_allowed, .nmi_allowed = svm_nmi_allowed, + .get_nmi_mask = svm_get_nmi_mask, + .set_nmi_mask = svm_set_nmi_mask, .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 0d480e77eac..816e0449db0 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -349,6 +349,171 @@ TRACE_EVENT(kvm_apic_accept_irq, __entry->coalesced ? " (coalesced)" : "") ); +/* + * Tracepoint for nested VMRUN + */ +TRACE_EVENT(kvm_nested_vmrun, + TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl, + __u32 event_inj, bool npt), + TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u64, vmcb ) + __field( __u64, nested_rip ) + __field( __u32, int_ctl ) + __field( __u32, event_inj ) + __field( bool, npt ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->vmcb = vmcb; + __entry->nested_rip = nested_rip; + __entry->int_ctl = int_ctl; + __entry->event_inj = event_inj; + __entry->npt = npt; + ), + + TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x " + "event_inj: 0x%08x npt: %s\n", + __entry->rip, __entry->vmcb, __entry->nested_rip, + __entry->int_ctl, __entry->event_inj, + __entry->npt ? "on" : "off") +); + +/* + * Tracepoint for #VMEXIT while nested + */ +TRACE_EVENT(kvm_nested_vmexit, + TP_PROTO(__u64 rip, __u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err), + TP_ARGS(rip, exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->exit_code = exit_code; + __entry->exit_info1 = exit_info1; + __entry->exit_info2 = exit_info2; + __entry->exit_int_info = exit_int_info; + __entry->exit_int_info_err = exit_int_info_err; + ), + TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + __entry->rip, + ftrace_print_symbols_seq(p, __entry->exit_code, + kvm_x86_ops->exit_reasons_str), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +); + +/* + * Tracepoint for #VMEXIT reinjected to the guest + */ +TRACE_EVENT(kvm_nested_vmexit_inject, + TP_PROTO(__u32 exit_code, + __u64 exit_info1, __u64 exit_info2, + __u32 exit_int_info, __u32 exit_int_info_err), + TP_ARGS(exit_code, exit_info1, exit_info2, + exit_int_info, exit_int_info_err), + + TP_STRUCT__entry( + __field( __u32, exit_code ) + __field( __u64, exit_info1 ) + __field( __u64, exit_info2 ) + __field( __u32, exit_int_info ) + __field( __u32, exit_int_info_err ) + ), + + TP_fast_assign( + __entry->exit_code = exit_code; + __entry->exit_info1 = exit_info1; + __entry->exit_info2 = exit_info2; + __entry->exit_int_info = exit_int_info; + __entry->exit_int_info_err = exit_int_info_err; + ), + + TP_printk("reason: %s ext_inf1: 0x%016llx " + "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n", + ftrace_print_symbols_seq(p, __entry->exit_code, + kvm_x86_ops->exit_reasons_str), + __entry->exit_info1, __entry->exit_info2, + __entry->exit_int_info, __entry->exit_int_info_err) +); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_nested_intr_vmexit, + TP_PROTO(__u64 rip), + TP_ARGS(rip), + + TP_STRUCT__entry( + __field( __u64, rip ) + ), + + TP_fast_assign( + __entry->rip = rip + ), + + TP_printk("rip: 0x%016llx\n", __entry->rip) +); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_invlpga, + TP_PROTO(__u64 rip, int asid, u64 address), + TP_ARGS(rip, asid, address), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( int, asid ) + __field( __u64, address ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->asid = asid; + __entry->address = address; + ), + + TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n", + __entry->rip, __entry->asid, __entry->address) +); + +/* + * Tracepoint for nested #vmexit because of interrupt pending + */ +TRACE_EVENT(kvm_skinit, + TP_PROTO(__u64 rip, __u32 slb), + TP_ARGS(rip, slb), + + TP_STRUCT__entry( + __field( __u64, rip ) + __field( __u32, slb ) + ), + + TP_fast_assign( + __entry->rip = rip; + __entry->slb = slb; + ), + + TP_printk("rip: 0x%016llx slb: 0x%08x\n", + __entry->rip, __entry->slb) +); + #endif /* _TRACE_KVM_H */ /* This part must be outside protection */ diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index ed53b42caba..d4918d6fc92 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -61,12 +61,37 @@ module_param_named(unrestricted_guest, static int __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); +/* + * These 2 parameters are used to config the controls for Pause-Loop Exiting: + * ple_gap: upper bound on the amount of time between two successive + * executions of PAUSE in a loop. Also indicate if ple enabled. + * According to test, this time is usually small than 41 cycles. + * ple_window: upper bound on the amount of time a guest is allowed to execute + * in a PAUSE loop. Tests indicate that most spinlocks are held for + * less than 2^12 cycles + * Time is measured based on a counter that runs at the same rate as the TSC, + * refer SDM volume 3b section 21.6.13 & 22.1.3. + */ +#define KVM_VMX_DEFAULT_PLE_GAP 41 +#define KVM_VMX_DEFAULT_PLE_WINDOW 4096 +static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP; +module_param(ple_gap, int, S_IRUGO); + +static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; +module_param(ple_window, int, S_IRUGO); + struct vmcs { u32 revision_id; u32 abort; char data[0]; }; +struct shared_msr_entry { + unsigned index; + u64 data; + u64 mask; +}; + struct vcpu_vmx { struct kvm_vcpu vcpu; struct list_head local_vcpus_link; @@ -74,13 +99,12 @@ struct vcpu_vmx { int launched; u8 fail; u32 idt_vectoring_info; - struct kvm_msr_entry *guest_msrs; - struct kvm_msr_entry *host_msrs; + struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; - int msr_offset_efer; #ifdef CONFIG_X86_64 - int msr_offset_kernel_gs_base; + u64 msr_host_kernel_gs_base; + u64 msr_guest_kernel_gs_base; #endif struct vmcs *vmcs; struct { @@ -88,7 +112,6 @@ struct vcpu_vmx { u16 fs_sel, gs_sel, ldt_sel; int gs_ldt_reload_needed; int fs_reload_needed; - int guest_efer_loaded; } host_state; struct { int vm86_active; @@ -107,7 +130,6 @@ struct vcpu_vmx { } rmode; int vpid; bool emulation_required; - enum emulation_result invalid_state_emulation_result; /* Support for vnmi-less CPUs */ int soft_vnmi_blocked; @@ -176,6 +198,8 @@ static struct kvm_vmx_segment_field { VMX_SEGMENT_FIELD(LDTR), }; +static u64 host_efer; + static void ept_save_pdptrs(struct kvm_vcpu *vcpu); /* @@ -184,28 +208,12 @@ static void ept_save_pdptrs(struct kvm_vcpu *vcpu); */ static const u32 vmx_msr_index[] = { #ifdef CONFIG_X86_64 - MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, MSR_KERNEL_GS_BASE, + MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR, #endif MSR_EFER, MSR_K6_STAR, }; #define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index) -static void load_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - wrmsrl(e[i].index, e[i].data); -} - -static void save_msrs(struct kvm_msr_entry *e, int n) -{ - int i; - - for (i = 0; i < n; ++i) - rdmsrl(e[i].index, e[i].data); -} - static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | @@ -320,6 +328,12 @@ static inline int cpu_has_vmx_unrestricted_guest(void) SECONDARY_EXEC_UNRESTRICTED_GUEST; } +static inline int cpu_has_vmx_ple(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_PAUSE_LOOP_EXITING; +} + static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm) { return flexpriority_enabled && @@ -348,7 +362,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr) int i; for (i = 0; i < vmx->nmsrs; ++i) - if (vmx->guest_msrs[i].index == msr) + if (vmx_msr_index[vmx->guest_msrs[i].index] == msr) return i; return -1; } @@ -379,7 +393,7 @@ static inline void __invept(int ext, u64 eptp, gpa_t gpa) : : "a" (&operand), "c" (ext) : "cc", "memory"); } -static struct kvm_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) +static struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr) { int i; @@ -570,17 +584,12 @@ static void reload_tss(void) load_TR_desc(); } -static void load_transition_efer(struct vcpu_vmx *vmx) +static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset) { - int efer_offset = vmx->msr_offset_efer; - u64 host_efer; u64 guest_efer; u64 ignore_bits; - if (efer_offset < 0) - return; - host_efer = vmx->host_msrs[efer_offset].data; - guest_efer = vmx->guest_msrs[efer_offset].data; + guest_efer = vmx->vcpu.arch.shadow_efer; /* * NX is emulated; LMA and LME handled by hardware; SCE meaninless @@ -593,27 +602,17 @@ static void load_transition_efer(struct vcpu_vmx *vmx) if (guest_efer & EFER_LMA) ignore_bits &= ~(u64)EFER_SCE; #endif - if ((guest_efer & ~ignore_bits) == (host_efer & ~ignore_bits)) - return; - - vmx->host_state.guest_efer_loaded = 1; guest_efer &= ~ignore_bits; guest_efer |= host_efer & ignore_bits; - wrmsrl(MSR_EFER, guest_efer); - vmx->vcpu.stat.efer_reload++; -} - -static void reload_host_efer(struct vcpu_vmx *vmx) -{ - if (vmx->host_state.guest_efer_loaded) { - vmx->host_state.guest_efer_loaded = 0; - load_msrs(vmx->host_msrs + vmx->msr_offset_efer, 1); - } + vmx->guest_msrs[efer_offset].data = guest_efer; + vmx->guest_msrs[efer_offset].mask = ~ignore_bits; + return true; } static void vmx_save_host_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + int i; if (vmx->host_state.loaded) return; @@ -650,13 +649,15 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu) #endif #ifdef CONFIG_X86_64 - if (is_long_mode(&vmx->vcpu)) - save_msrs(vmx->host_msrs + - vmx->msr_offset_kernel_gs_base, 1); - + if (is_long_mode(&vmx->vcpu)) { + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + } #endif - load_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_transition_efer(vmx); + for (i = 0; i < vmx->save_nmsrs; ++i) + kvm_set_shared_msr(vmx->guest_msrs[i].index, + vmx->guest_msrs[i].data, + vmx->guest_msrs[i].mask); } static void __vmx_load_host_state(struct vcpu_vmx *vmx) @@ -684,9 +685,12 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx) local_irq_restore(flags); } reload_tss(); - save_msrs(vmx->guest_msrs, vmx->save_nmsrs); - load_msrs(vmx->host_msrs, vmx->save_nmsrs); - reload_host_efer(vmx); +#ifdef CONFIG_X86_64 + if (is_long_mode(&vmx->vcpu)) { + rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base); + wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base); + } +#endif } static void vmx_load_host_state(struct vcpu_vmx *vmx) @@ -877,19 +881,14 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, /* * Swap MSR entry in host/guest MSR entry array. */ -#ifdef CONFIG_X86_64 static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) { - struct kvm_msr_entry tmp; + struct shared_msr_entry tmp; tmp = vmx->guest_msrs[to]; vmx->guest_msrs[to] = vmx->guest_msrs[from]; vmx->guest_msrs[from] = tmp; - tmp = vmx->host_msrs[to]; - vmx->host_msrs[to] = vmx->host_msrs[from]; - vmx->host_msrs[from] = tmp; } -#endif /* * Set up the vmcs to automatically save and restore system @@ -898,15 +897,13 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to) */ static void setup_msrs(struct vcpu_vmx *vmx) { - int save_nmsrs; + int save_nmsrs, index; unsigned long *msr_bitmap; vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { - int index; - index = __find_msr_index(vmx, MSR_SYSCALL_MASK); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); @@ -916,9 +913,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) index = __find_msr_index(vmx, MSR_CSTAR); if (index >= 0) move_msr_up(vmx, index, save_nmsrs++); - index = __find_msr_index(vmx, MSR_KERNEL_GS_BASE); - if (index >= 0) - move_msr_up(vmx, index, save_nmsrs++); /* * MSR_K6_STAR is only needed on long mode guests, and only * if efer.sce is enabled. @@ -928,13 +922,11 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); } #endif - vmx->save_nmsrs = save_nmsrs; + index = __find_msr_index(vmx, MSR_EFER); + if (index >= 0 && update_transition_efer(vmx, index)) + move_msr_up(vmx, index, save_nmsrs++); -#ifdef CONFIG_X86_64 - vmx->msr_offset_kernel_gs_base = - __find_msr_index(vmx, MSR_KERNEL_GS_BASE); -#endif - vmx->msr_offset_efer = __find_msr_index(vmx, MSR_EFER); + vmx->save_nmsrs = save_nmsrs; if (cpu_has_vmx_msr_bitmap()) { if (is_long_mode(&vmx->vcpu)) @@ -976,7 +968,7 @@ static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) { u64 data; - struct kvm_msr_entry *msr; + struct shared_msr_entry *msr; if (!pdata) { printk(KERN_ERR "BUG: get_msr called with NULL pdata\n"); @@ -991,9 +983,13 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) case MSR_GS_BASE: data = vmcs_readl(GUEST_GS_BASE); break; + case MSR_KERNEL_GS_BASE: + vmx_load_host_state(to_vmx(vcpu)); + data = to_vmx(vcpu)->msr_guest_kernel_gs_base; + break; +#endif case MSR_EFER: return kvm_get_msr_common(vcpu, msr_index, pdata); -#endif case MSR_IA32_TSC: data = guest_read_tsc(); break; @@ -1007,6 +1003,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) data = vmcs_readl(GUEST_SYSENTER_ESP); break; default: + vmx_load_host_state(to_vmx(vcpu)); msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { vmx_load_host_state(to_vmx(vcpu)); @@ -1028,7 +1025,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr; + struct shared_msr_entry *msr; u64 host_tsc; int ret = 0; @@ -1044,6 +1041,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) case MSR_GS_BASE: vmcs_writel(GUEST_GS_BASE, data); break; + case MSR_KERNEL_GS_BASE: + vmx_load_host_state(vmx); + vmx->msr_guest_kernel_gs_base = data; + break; #endif case MSR_IA32_SYSENTER_CS: vmcs_write32(GUEST_SYSENTER_CS, data); @@ -1097,30 +1098,14 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - int old_debug = vcpu->guest_debug; - unsigned long flags; - - vcpu->guest_debug = dbg->control; - if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) - vcpu->guest_debug = 0; - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]); else vmcs_writel(GUEST_DR7, vcpu->arch.dr7); - flags = vmcs_readl(GUEST_RFLAGS); - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - else if (old_debug & KVM_GUESTDBG_SINGLESTEP) - flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - vmcs_writel(GUEST_RFLAGS, flags); - update_exception_bitmap(vcpu); - - return 0; } static __init int cpu_has_kvm_support(void) @@ -1139,12 +1124,15 @@ static __init int vmx_disabled_by_bios(void) /* locked but not enabled */ } -static void hardware_enable(void *garbage) +static int hardware_enable(void *garbage) { int cpu = raw_smp_processor_id(); u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); u64 old; + if (read_cr4() & X86_CR4_VMXE) + return -EBUSY; + INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu)); rdmsrl(MSR_IA32_FEATURE_CONTROL, old); if ((old & (FEATURE_CONTROL_LOCKED | @@ -1159,6 +1147,10 @@ static void hardware_enable(void *garbage) asm volatile (ASM_VMX_VMXON_RAX : : "a"(&phys_addr), "m"(phys_addr) : "memory", "cc"); + + ept_sync_global(); + + return 0; } static void vmclear_local_vcpus(void) @@ -1250,7 +1242,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) SECONDARY_EXEC_WBINVD_EXITING | SECONDARY_EXEC_ENABLE_VPID | SECONDARY_EXEC_ENABLE_EPT | - SECONDARY_EXEC_UNRESTRICTED_GUEST; + SECONDARY_EXEC_UNRESTRICTED_GUEST | + SECONDARY_EXEC_PAUSE_LOOP_EXITING; if (adjust_vmx_controls(min2, opt2, MSR_IA32_VMX_PROCBASED_CTLS2, &_cpu_based_2nd_exec_control) < 0) @@ -1344,15 +1337,17 @@ static void free_kvm_area(void) { int cpu; - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) { free_vmcs(per_cpu(vmxarea, cpu)); + per_cpu(vmxarea, cpu) = NULL; + } } static __init int alloc_kvm_area(void) { int cpu; - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { struct vmcs *vmcs; vmcs = alloc_vmcs_cpu(cpu); @@ -1394,6 +1389,9 @@ static __init int hardware_setup(void) if (enable_ept && !cpu_has_vmx_ept_2m_page()) kvm_disable_largepages(); + if (!cpu_has_vmx_ple()) + ple_gap = 0; + return alloc_kvm_area(); } @@ -1536,8 +1534,16 @@ continue_rmode: static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer) { struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER); + + if (!msr) + return; + /* + * Force kernel_gs_base reloading before EFER changes, as control + * of this msr depends on is_long_mode(). + */ + vmx_load_host_state(to_vmx(vcpu)); vcpu->arch.shadow_efer = efer; if (!msr) return; @@ -1727,6 +1733,7 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) vmcs_write64(EPT_POINTER, eptp); guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 : vcpu->kvm->arch.ept_identity_map_addr; + ept_load_pdptrs(vcpu); } vmx_flush_tlb(vcpu); @@ -2302,13 +2309,22 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; if (vmx->vpid == 0) exec_control &= ~SECONDARY_EXEC_ENABLE_VPID; - if (!enable_ept) + if (!enable_ept) { exec_control &= ~SECONDARY_EXEC_ENABLE_EPT; + enable_unrestricted_guest = 0; + } if (!enable_unrestricted_guest) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; + if (!ple_gap) + exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control); } + if (ple_gap) { + vmcs_write32(PLE_GAP, ple_gap); + vmcs_write32(PLE_WINDOW, ple_window); + } + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, !!bypass_guest_pf); vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, !!bypass_guest_pf); vmcs_write32(CR3_TARGET_COUNT, 0); /* 22.2.1 */ @@ -2376,10 +2392,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) if (wrmsr_safe(index, data_low, data_high) < 0) continue; data = data_low | ((u64)data_high << 32); - vmx->host_msrs[j].index = index; - vmx->host_msrs[j].reserved = 0; - vmx->host_msrs[j].data = data; - vmx->guest_msrs[j] = vmx->host_msrs[j]; + vmx->guest_msrs[j].index = i; + vmx->guest_msrs[j].data = 0; + vmx->guest_msrs[j].mask = -1ull; ++vmx->nmsrs; } @@ -2510,7 +2525,7 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) if (vmx->vpid != 0) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); - vmx->vcpu.arch.cr0 = 0x60000010; + vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; vmx_set_cr0(&vmx->vcpu, vmx->vcpu.arch.cr0); /* enter rmode */ vmx_set_cr4(&vmx->vcpu, 0); vmx_set_efer(&vmx->vcpu, 0); @@ -2627,6 +2642,34 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu) GUEST_INTR_STATE_NMI)); } +static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + if (!cpu_has_virtual_nmis()) + return to_vmx(vcpu)->soft_vnmi_blocked; + else + return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + GUEST_INTR_STATE_NMI); +} + +static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!cpu_has_virtual_nmis()) { + if (vmx->soft_vnmi_blocked != masked) { + vmx->soft_vnmi_blocked = masked; + vmx->vnmi_blocked_time = 0; + } + } else { + if (masked) + vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + else + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_NMI); + } +} + static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) && @@ -2659,7 +2702,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) - if (emulate_instruction(vcpu, NULL, 0, 0, 0) == EMULATE_DONE) + if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE) return 1; /* * Forward all other exceptions that are valid in real mode. @@ -2710,15 +2753,16 @@ static void kvm_machine_check(void) #endif } -static int handle_machine_check(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_machine_check(struct kvm_vcpu *vcpu) { /* already handled by vcpu_run */ return 1; } -static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_exception(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_run *kvm_run = vcpu->run; u32 intr_info, ex_no, error_code; unsigned long cr2, rip, dr6; u32 vect_info; @@ -2728,12 +2772,17 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) intr_info = vmcs_read32(VM_EXIT_INTR_INFO); if (is_machine_check(intr_info)) - return handle_machine_check(vcpu, kvm_run); + return handle_machine_check(vcpu); if ((vect_info & VECTORING_INFO_VALID_MASK) && - !is_page_fault(intr_info)) - printk(KERN_ERR "%s: unexpected, vectoring info 0x%x " - "intr info 0x%x\n", __func__, vect_info, intr_info); + !is_page_fault(intr_info)) { + 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.data[0] = vect_info; + vcpu->run->internal.data[1] = intr_info; + return 0; + } if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR) return 1; /* already handled by vmx_vcpu_run() */ @@ -2744,7 +2793,7 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } if (is_invalid_opcode(intr_info)) { - er = emulate_instruction(vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(vcpu, 0, 0, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(vcpu, UD_VECTOR); return 1; @@ -2803,20 +2852,19 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 0; } -static int handle_external_interrupt(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_external_interrupt(struct kvm_vcpu *vcpu) { ++vcpu->stat.irq_exits; return 1; } -static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_triple_fault(struct kvm_vcpu *vcpu) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; } -static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_io(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; int size, in, string; @@ -2827,8 +2875,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) string = (exit_qualification & 16) != 0; if (string) { - if (emulate_instruction(vcpu, - kvm_run, 0, 0, 0) == EMULATE_DO_MMIO) + if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO) return 0; return 1; } @@ -2838,7 +2885,7 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) port = exit_qualification >> 16; skip_emulated_instruction(vcpu); - return kvm_emulate_pio(vcpu, kvm_run, in, size, port); + return kvm_emulate_pio(vcpu, in, size, port); } static void @@ -2852,7 +2899,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xc1; } -static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_cr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification, val; int cr; @@ -2887,7 +2934,7 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; if (cr8_prev <= cr8) return 1; - kvm_run->exit_reason = KVM_EXIT_SET_TPR; + vcpu->run->exit_reason = KVM_EXIT_SET_TPR; return 0; } }; @@ -2922,13 +2969,13 @@ static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) default: break; } - kvm_run->exit_reason = 0; + vcpu->run->exit_reason = 0; pr_unimpl(vcpu, "unhandled control register: op %d cr %d\n", (int)(exit_qualification >> 4) & 3, cr); return 0; } -static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_dr(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; unsigned long val; @@ -2944,13 +2991,13 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - kvm_run->debug.arch.dr6 = vcpu->arch.dr6; - kvm_run->debug.arch.dr7 = dr; - kvm_run->debug.arch.pc = + vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; + vcpu->run->debug.arch.dr7 = dr; + vcpu->run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + vmcs_readl(GUEST_RIP); - kvm_run->debug.arch.exception = DB_VECTOR; - kvm_run->exit_reason = KVM_EXIT_DEBUG; + vcpu->run->debug.arch.exception = DB_VECTOR; + vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { vcpu->arch.dr7 &= ~DR7_GD; @@ -3016,13 +3063,13 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_cpuid(struct kvm_vcpu *vcpu) { kvm_emulate_cpuid(vcpu); return 1; } -static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_rdmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data; @@ -3041,7 +3088,7 @@ static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_wrmsr(struct kvm_vcpu *vcpu) { u32 ecx = vcpu->arch.regs[VCPU_REGS_RCX]; u64 data = (vcpu->arch.regs[VCPU_REGS_RAX] & -1u) @@ -3058,14 +3105,12 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_tpr_below_threshold(struct kvm_vcpu *vcpu) { return 1; } -static int handle_interrupt_window(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_interrupt_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; @@ -3081,34 +3126,34 @@ static int handle_interrupt_window(struct kvm_vcpu *vcpu, * possible */ if (!irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && !kvm_cpu_has_interrupt(vcpu)) { - kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; + vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; return 0; } return 1; } -static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +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, struct kvm_run *kvm_run) +static int handle_vmcall(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); kvm_emulate_hypercall(vcpu); return 1; } -static int handle_vmx_insn(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_vmx_insn(struct kvm_vcpu *vcpu) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } -static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_invlpg(struct kvm_vcpu *vcpu) { unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); @@ -3117,14 +3162,14 @@ static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_wbinvd(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_wbinvd(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); /* TODO: Add support for VT-d/pass-through device */ return 1; } -static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_apic_access(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; enum emulation_result er; @@ -3133,7 +3178,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) exit_qualification = vmcs_readl(EXIT_QUALIFICATION); offset = exit_qualification & 0xffful; - er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + er = emulate_instruction(vcpu, 0, 0, 0); if (er != EMULATE_DONE) { printk(KERN_ERR @@ -3144,7 +3189,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_task_switch(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long exit_qualification; @@ -3198,7 +3243,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_ept_violation(struct kvm_vcpu *vcpu) { unsigned long exit_qualification; gpa_t gpa; @@ -3219,8 +3264,8 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vmcs_readl(GUEST_LINEAR_ADDRESS)); printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", (long unsigned int)exit_qualification); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION; return 0; } @@ -3290,7 +3335,7 @@ static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte, } } -static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { u64 sptes[4]; int nr_sptes, i; @@ -3306,13 +3351,13 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i) ept_misconfig_inspect_spte(vcpu, sptes[i-1], i); - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG; return 0; } -static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int handle_nmi_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; @@ -3325,36 +3370,50 @@ static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } -static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); enum emulation_result err = EMULATE_DONE; - - local_irq_enable(); - preempt_enable(); + int ret = 1; while (!guest_state_valid(vcpu)) { - err = emulate_instruction(vcpu, kvm_run, 0, 0, 0); + err = emulate_instruction(vcpu, 0, 0, 0); - if (err == EMULATE_DO_MMIO) - break; + if (err == EMULATE_DO_MMIO) { + ret = 0; + goto out; + } if (err != EMULATE_DONE) { kvm_report_emulation_failure(vcpu, "emulation failure"); - break; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + ret = 0; + goto out; } if (signal_pending(current)) - break; + goto out; if (need_resched()) schedule(); } - preempt_disable(); - local_irq_disable(); + vmx->emulation_required = 0; +out: + return ret; +} - vmx->invalid_state_emulation_result = err; +/* + * Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE + * exiting, so only get here on cpu with PAUSE-Loop-Exiting. + */ +static int handle_pause(struct kvm_vcpu *vcpu) +{ + skip_emulated_instruction(vcpu); + kvm_vcpu_on_spin(vcpu); + + return 1; } /* @@ -3362,8 +3421,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, * may resume. Otherwise they set the kvm_run parameter to indicate what needs * to be done to userspace and return 0. */ -static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) = { +static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EXCEPTION_NMI] = handle_exception, [EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt, [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault, @@ -3394,6 +3452,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu, [EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check, [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, + [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, }; static const int kvm_vmx_max_exit_handlers = @@ -3403,7 +3462,7 @@ static const int kvm_vmx_max_exit_handlers = * The guest has exited. See if we can fix it or if we need userspace * assistance. */ -static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) +static int vmx_handle_exit(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exit_reason = vmx->exit_reason; @@ -3411,13 +3470,9 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) trace_kvm_exit(exit_reason, kvm_rip_read(vcpu)); - /* If we need to emulate an MMIO from handle_invalid_guest_state - * we just return 0 */ - if (vmx->emulation_required && emulate_invalid_guest_state) { - if (guest_state_valid(vcpu)) - vmx->emulation_required = 0; - return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO; - } + /* If guest state is invalid, start emulating */ + if (vmx->emulation_required && emulate_invalid_guest_state) + return handle_invalid_guest_state(vcpu); /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ @@ -3425,8 +3480,8 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) vcpu->arch.cr3 = vmcs_readl(GUEST_CR3); if (unlikely(vmx->fail)) { - kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY; - kvm_run->fail_entry.hardware_entry_failure_reason + vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY; + vcpu->run->fail_entry.hardware_entry_failure_reason = vmcs_read32(VM_INSTRUCTION_ERROR); return 0; } @@ -3459,10 +3514,10 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (exit_reason < kvm_vmx_max_exit_handlers && kvm_vmx_exit_handlers[exit_reason]) - return kvm_vmx_exit_handlers[exit_reason](vcpu, kvm_run); + return kvm_vmx_exit_handlers[exit_reason](vcpu); else { - kvm_run->exit_reason = KVM_EXIT_UNKNOWN; - kvm_run->hw.hardware_exit_reason = exit_reason; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; + vcpu->run->hw.hardware_exit_reason = exit_reason; } return 0; } @@ -3600,23 +3655,18 @@ static void fixup_rmode_irq(struct vcpu_vmx *vmx) #define Q "l" #endif -static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (enable_ept && is_paging(vcpu)) { - vmcs_writel(GUEST_CR3, vcpu->arch.cr3); - ept_load_pdptrs(vcpu); - } /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked)) vmx->entry_time = ktime_get(); - /* Handle invalid guest state instead of entering VMX */ - if (vmx->emulation_required && emulate_invalid_guest_state) { - handle_invalid_guest_state(vcpu, kvm_run); + /* Don't enter VMX if guest state is invalid, let the exit handler + start emulation until we arrive back to a valid state */ + if (vmx->emulation_required && emulate_invalid_guest_state) return; - } if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty)) vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]); @@ -3775,7 +3825,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) __clear_bit(vmx->vpid, vmx_vpid_bitmap); spin_unlock(&vmx_vpid_lock); vmx_free_vmcs(vcpu); - kfree(vmx->host_msrs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, vmx); @@ -3802,10 +3851,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto uninit_vcpu; } - vmx->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!vmx->host_msrs) - goto free_guest_msrs; - vmx->vmcs = alloc_vmcs(); if (!vmx->vmcs) goto free_msrs; @@ -3836,8 +3881,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) free_vmcs: free_vmcs(vmx->vmcs); free_msrs: - kfree(vmx->host_msrs); -free_guest_msrs: kfree(vmx->guest_msrs); uninit_vcpu: kvm_vcpu_uninit(&vmx->vcpu); @@ -3973,6 +4016,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .queue_exception = vmx_queue_exception, .interrupt_allowed = vmx_interrupt_allowed, .nmi_allowed = vmx_nmi_allowed, + .get_nmi_mask = vmx_get_nmi_mask, + .set_nmi_mask = vmx_set_nmi_mask, .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, @@ -3987,7 +4032,12 @@ static struct kvm_x86_ops vmx_x86_ops = { static int __init vmx_init(void) { - int r; + int r, i; + + rdmsrl_safe(MSR_EFER, &host_efer); + + for (i = 0; i < NR_VMX_MSR; ++i) + kvm_define_shared_msr(i, vmx_msr_index[i]); vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_io_bitmap_a) @@ -4049,8 +4099,6 @@ static int __init vmx_init(void) if (bypass_guest_pf) kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull); - ept_sync_global(); - return 0; out3: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4fc80174191..9d068966fb2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -37,6 +37,7 @@ #include <linux/iommu.h> #include <linux/intel-iommu.h> #include <linux/cpufreq.h> +#include <linux/user-return-notifier.h> #include <trace/events/kvm.h> #undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS @@ -88,6 +89,25 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); int ignore_msrs = 0; module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +#define KVM_NR_SHARED_MSRS 16 + +struct kvm_shared_msrs_global { + int nr; + struct kvm_shared_msr { + u32 msr; + u64 value; + } msrs[KVM_NR_SHARED_MSRS]; +}; + +struct kvm_shared_msrs { + struct user_return_notifier urn; + bool registered; + u64 current_value[KVM_NR_SHARED_MSRS]; +}; + +static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; +static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs); + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -124,6 +144,72 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +static void kvm_on_user_return(struct user_return_notifier *urn) +{ + unsigned slot; + struct kvm_shared_msr *global; + struct kvm_shared_msrs *locals + = container_of(urn, struct kvm_shared_msrs, urn); + + for (slot = 0; slot < shared_msrs_global.nr; ++slot) { + global = &shared_msrs_global.msrs[slot]; + if (global->value != locals->current_value[slot]) { + wrmsrl(global->msr, global->value); + locals->current_value[slot] = global->value; + } + } + locals->registered = false; + user_return_notifier_unregister(urn); +} + +void kvm_define_shared_msr(unsigned slot, u32 msr) +{ + int cpu; + u64 value; + + if (slot >= shared_msrs_global.nr) + shared_msrs_global.nr = slot + 1; + shared_msrs_global.msrs[slot].msr = msr; + rdmsrl_safe(msr, &value); + shared_msrs_global.msrs[slot].value = value; + for_each_online_cpu(cpu) + per_cpu(shared_msrs, cpu).current_value[slot] = value; +} +EXPORT_SYMBOL_GPL(kvm_define_shared_msr); + +static void kvm_shared_msr_cpu_online(void) +{ + unsigned i; + struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs); + + for (i = 0; i < shared_msrs_global.nr; ++i) + locals->current_value[i] = shared_msrs_global.msrs[i].value; +} + +void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (((value ^ smsr->current_value[slot]) & mask) == 0) + return; + smsr->current_value[slot] = value; + wrmsrl(shared_msrs_global.msrs[slot].msr, value); + if (!smsr->registered) { + smsr->urn.on_user_return = kvm_on_user_return; + user_return_notifier_register(&smsr->urn); + smsr->registered = true; + } +} +EXPORT_SYMBOL_GPL(kvm_set_shared_msr); + +static void drop_user_return_notifiers(void *ignore) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (smsr->registered) + kvm_on_user_return(&smsr->urn); +} + unsigned long segment_base(u16 selector) { struct descriptor_table gdt; @@ -485,16 +571,19 @@ static inline u32 bit(int bitno) * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * * This list is modified at module load time to reflect the - * capabilities of the host cpu. + * capabilities of the host cpu. This capabilities test skips MSRs that are + * kvm-specific. Those are put in the beginning of the list. */ + +#define KVM_SAVE_MSRS_BEGIN 2 static u32 msrs_to_save[] = { + MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_K6_STAR, #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA + MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; static unsigned num_msrs_to_save; @@ -678,7 +767,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ vcpu->hv_clock.system_time = ts.tv_nsec + - (NSEC_PER_SEC * (u64)ts.tv_sec); + (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset; + /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -836,6 +926,38 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 0; } +static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + int lm = is_long_mode(vcpu); + u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 + : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + u8 *page; + int r; + + r = -E2BIG; + if (page_num >= blob_size) + goto out; + r = -ENOMEM; + page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!page) + goto out; + r = -EFAULT; + if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE)) + goto out_free; + if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) + goto out_free; + r = 0; +out_free: + kfree(page); +out: + return r; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -951,6 +1073,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) "0x%x data 0x%llx\n", msr, data); break; default: + if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) + return xen_hvm_config(vcpu, data); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -1225,6 +1349,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: + case KVM_CAP_XEN_HVM: + case KVM_CAP_ADJUST_CLOCK: + case KVM_CAP_VCPU_EVENTS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1239,8 +1366,8 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_NR_MEMSLOTS: r = KVM_MEMORY_SLOTS; break; - case KVM_CAP_PV_MMU: - r = !tdp_enabled; + case KVM_CAP_PV_MMU: /* obsolete */ + r = 0; break; case KVM_CAP_IOMMU: r = iommu_found(); @@ -1327,6 +1454,12 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); + if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) { + unsigned long khz = cpufreq_quick_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } kvm_request_guest_time_update(vcpu); } @@ -1760,6 +1893,61 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; } +static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_load(vcpu); + + events->exception.injected = vcpu->arch.exception.pending; + events->exception.nr = vcpu->arch.exception.nr; + events->exception.has_error_code = vcpu->arch.exception.has_error_code; + events->exception.error_code = vcpu->arch.exception.error_code; + + events->interrupt.injected = vcpu->arch.interrupt.pending; + events->interrupt.nr = vcpu->arch.interrupt.nr; + events->interrupt.soft = vcpu->arch.interrupt.soft; + + events->nmi.injected = vcpu->arch.nmi_injected; + events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + + events->sipi_vector = vcpu->arch.sipi_vector; + + events->flags = 0; + + vcpu_put(vcpu); +} + +static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + if (events->flags) + return -EINVAL; + + vcpu_load(vcpu); + + vcpu->arch.exception.pending = events->exception.injected; + vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.has_error_code = events->exception.has_error_code; + vcpu->arch.exception.error_code = events->exception.error_code; + + vcpu->arch.interrupt.pending = events->interrupt.injected; + vcpu->arch.interrupt.nr = events->interrupt.nr; + vcpu->arch.interrupt.soft = events->interrupt.soft; + if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) + kvm_pic_clear_isr_ack(vcpu->kvm); + + vcpu->arch.nmi_injected = events->nmi.injected; + vcpu->arch.nmi_pending = events->nmi.pending; + kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + + vcpu->arch.sipi_vector = events->sipi_vector; + + vcpu_put(vcpu); + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1770,6 +1958,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_GET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; @@ -1785,6 +1976,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; if (!lapic) @@ -1911,6 +2105,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); break; } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); + + r = -EFAULT; + if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) + break; + r = 0; + break; + } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + r = -EFAULT; + if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) + break; + + r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + break; + } default: r = -EINVAL; } @@ -2039,9 +2254,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2071,11 +2284,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: - mutex_lock(&kvm->irq_lock); - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - mutex_unlock(&kvm->irq_lock); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2183,7 +2392,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; /* * This union makes it completely explicit to gcc-3.x * that these two variables' stack usage should be @@ -2245,25 +2454,39 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) goto out; break; - case KVM_CREATE_IRQCHIP: + case KVM_CREATE_IRQCHIP: { + struct kvm_pic *vpic; + + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpic) + goto create_irqchip_unlock; r = -ENOMEM; - kvm->arch.vpic = kvm_create_pic(kvm); - if (kvm->arch.vpic) { + vpic = kvm_create_pic(kvm); + if (vpic) { r = kvm_ioapic_init(kvm); if (r) { - kfree(kvm->arch.vpic); - kvm->arch.vpic = NULL; - goto out; + kfree(vpic); + goto create_irqchip_unlock; } } else - goto out; + goto create_irqchip_unlock; + smp_wmb(); + kvm->arch.vpic = vpic; + smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { + mutex_lock(&kvm->irq_lock); kfree(kvm->arch.vpic); kfree(kvm->arch.vioapic); - goto out; + kvm->arch.vpic = NULL; + kvm->arch.vioapic = NULL; + mutex_unlock(&kvm->irq_lock); } + create_irqchip_unlock: + mutex_unlock(&kvm->lock); break; + } case KVM_CREATE_PIT: u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; @@ -2293,10 +2516,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, @@ -2422,6 +2643,55 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_XEN_HVM_CONFIG: { + r = -EFAULT; + if (copy_from_user(&kvm->arch.xen_hvm_config, argp, + sizeof(struct kvm_xen_hvm_config))) + goto out; + r = -EINVAL; + if (kvm->arch.xen_hvm_config.flags) + goto out; + r = 0; + break; + } + case KVM_SET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + s64 delta; + + r = -EFAULT; + if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + goto out; + + r = -EINVAL; + if (user_ns.flags) + goto out; + + r = 0; + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + delta = user_ns.clock - now_ns; + kvm->arch.kvmclock_offset = delta; + break; + } + case KVM_GET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + user_ns.clock = kvm->arch.kvmclock_offset + now_ns; + user_ns.flags = 0; + + r = -EFAULT; + if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + goto out; + r = 0; + break; + } + default: ; } @@ -2434,7 +2704,8 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { + /* skip the first msrs in the list. KVM-specific */ + for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; if (j < i) @@ -2758,13 +3029,13 @@ static void cache_all_regs(struct kvm_vcpu *vcpu) } int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, unsigned long cr2, u16 error_code, int emulation_type) { int r, shadow_mask; struct decode_cache *c; + struct kvm_run *run = vcpu->run; kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; @@ -2784,7 +3055,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); vcpu->arch.emulate_ctxt.mode = (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_REAL : cs_l @@ -2862,7 +3133,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); if (vcpu->mmio_is_write) { vcpu->mmio_needed = 0; @@ -2970,8 +3241,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu) return r; } -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) { unsigned long val; @@ -3000,7 +3270,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, } EXPORT_SYMBOL_GPL(kvm_emulate_pio); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port) { @@ -3073,9 +3343,6 @@ static void bounce_off(void *info) /* nothing */ } -static unsigned int ref_freq; -static unsigned long tsc_khz_ref; - static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -3084,14 +3351,11 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va struct kvm_vcpu *vcpu; int i, send_ipi = 0; - if (!ref_freq) - ref_freq = freq->old; - if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) return 0; if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) return 0; - per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); + per_cpu(cpu_tsc_khz, freq->cpu) = freq->new; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { @@ -3128,9 +3392,28 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = { .notifier_call = kvmclock_cpufreq_notifier }; +static void kvm_timer_init(void) +{ + int cpu; + + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + for_each_online_cpu(cpu) { + unsigned long khz = cpufreq_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } + } else { + for_each_possible_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + } +} + int kvm_arch_init(void *opaque) { - int r, cpu; + int r; struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; if (kvm_x86_ops) { @@ -3162,13 +3445,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); - for_each_possible_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { - tsc_khz_ref = tsc_khz; - cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); - } + kvm_timer_init(); return 0; @@ -3296,7 +3573,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long *rflags) { kvm_lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); } unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) @@ -3334,7 +3611,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, switch (cr) { case 0: kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); break; case 2: vcpu->arch.cr2 = val; @@ -3454,18 +3731,18 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); * * No need to exit to userspace if we already have an interrupt queued. */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && kvm_arch_interrupt_allowed(vcpu)); } -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static void post_kvm_run_save(struct kvm_vcpu *vcpu) { - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + struct kvm_run *kvm_run = vcpu->run; + + kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) @@ -3526,7 +3803,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { @@ -3562,11 +3839,11 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } -static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window; + vcpu->run->request_interrupt_window; if (vcpu->requests) if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) @@ -3587,12 +3864,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_x86_ops->tlb_flush(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; + vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; r = 0; goto out; } @@ -3616,7 +3893,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - inject_pending_event(vcpu, kvm_run); + inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) @@ -3642,7 +3919,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } trace_kvm_entry(vcpu->vcpu_id); - kvm_x86_ops->run(vcpu, kvm_run); + kvm_x86_ops->run(vcpu); /* * If the guest has used debug registers, at least dr7 @@ -3684,13 +3961,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); + r = kvm_x86_ops->handle_exit(vcpu); out: return r; } -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int __vcpu_run(struct kvm_vcpu *vcpu) { int r; @@ -3710,7 +3987,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) r = 1; while (r > 0) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) - r = vcpu_enter_guest(vcpu, kvm_run); + r = vcpu_enter_guest(vcpu); else { up_read(&vcpu->kvm->slots_lock); kvm_vcpu_block(vcpu); @@ -3738,14 +4015,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu, kvm_run)) { + if (dm_request_for_irq_injection(vcpu)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; } if (signal_pending(current)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } if (need_resched()) { @@ -3756,7 +4033,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } up_read(&vcpu->kvm->slots_lock); - post_kvm_run_save(vcpu, kvm_run); + post_kvm_run_save(vcpu); vapic_exit(vcpu); @@ -3789,15 +4066,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (r) goto out; } -#if CONFIG_HAS_IOMEM if (vcpu->mmio_needed) { memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; down_read(&vcpu->kvm->slots_lock); - r = emulate_instruction(vcpu, kvm_run, - vcpu->arch.mmio_fault_cr2, 0, + r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, EMULTYPE_NO_DECODE); up_read(&vcpu->kvm->slots_lock); if (r == EMULATE_DO_MMIO) { @@ -3808,12 +4083,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } } -#endif if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) kvm_register_write(vcpu, VCPU_REGS_RAX, kvm_run->hypercall.ret); - r = __vcpu_run(vcpu, kvm_run); + r = __vcpu_run(vcpu); out: if (vcpu->sigset_active) @@ -3847,13 +4121,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) #endif regs->rip = kvm_rip_read(vcpu); - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + regs->rflags = kvm_get_rflags(vcpu); vcpu_put(vcpu); @@ -3881,12 +4149,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); - #endif kvm_rip_write(vcpu, regs->rip); - kvm_x86_ops->set_rflags(vcpu, regs->rflags); - + kvm_set_rflags(vcpu, regs->rflags); vcpu->arch.exception.pending = false; @@ -4105,7 +4371,7 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) { return (seg != VCPU_SREG_LDTR) && (seg != VCPU_SREG_TR) && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM); + (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); } int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, @@ -4133,7 +4399,7 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu, { tss->cr3 = vcpu->arch.cr3; tss->eip = kvm_rip_read(vcpu); - tss->eflags = kvm_x86_ops->get_rflags(vcpu); + tss->eflags = kvm_get_rflags(vcpu); tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4157,7 +4423,7 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu, kvm_set_cr3(vcpu, tss->cr3); kvm_rip_write(vcpu, tss->eip); - kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2); + kvm_set_rflags(vcpu, tss->eflags | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); @@ -4195,7 +4461,7 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { tss->ip = kvm_rip_read(vcpu); - tss->flag = kvm_x86_ops->get_rflags(vcpu); + tss->flag = kvm_get_rflags(vcpu); tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4210,14 +4476,13 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); - tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR); } static int load_state_from_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { kvm_rip_write(vcpu, tss->ip); - kvm_x86_ops->set_rflags(vcpu, tss->flag | 2); + kvm_set_rflags(vcpu, tss->flag | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); @@ -4363,8 +4628,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); } /* set back link to prev task only if NT bit is set in eflags @@ -4372,11 +4637,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) old_tss_sel = 0xffff; - /* set back link to prev task only if NT bit is set in eflags - note that old_tss_sel is not used afetr this point */ - if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) - old_tss_sel = 0xffff; - if (nseg_desc.type & 8) ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel, old_tss_base, &nseg_desc); @@ -4385,8 +4645,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) old_tss_base, &nseg_desc); if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); } if (reason != TASK_SWITCH_IRET) { @@ -4438,8 +4698,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) + if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.cr3); + mmu_reset_needed = 1; + } if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); @@ -4480,12 +4742,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { + unsigned long rflags; int i, r; vcpu_load(vcpu); - if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) { + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { + r = -EBUSY; + if (vcpu->arch.exception.pending) + goto unlock_out; + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else + kvm_queue_exception(vcpu, BP_VECTOR); + } + + /* + * Read rflags as long as potentially injected trace flags are still + * filtered out. + */ + rflags = kvm_get_rflags(vcpu); + + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { for (i = 0; i < KVM_NR_DB_REGS; ++i) vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; vcpu->arch.switch_db_regs = @@ -4496,13 +4778,23 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + vcpu->arch.singlestep_cs = + get_segment_selector(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu); + } + + /* + * Trigger an rflags update that will inject or remove the trace + * flags. + */ + kvm_set_rflags(vcpu, rflags); + + kvm_x86_ops->set_guest_debug(vcpu, dbg); - if (dbg->control & KVM_GUESTDBG_INJECT_DB) - kvm_queue_exception(vcpu, DB_VECTOR); - else if (dbg->control & KVM_GUESTDBG_INJECT_BP) - kvm_queue_exception(vcpu, BP_VECTOR); + r = 0; +unlock_out: vcpu_put(vcpu); return r; @@ -4703,14 +4995,26 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) return kvm_x86_ops->vcpu_reset(vcpu); } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { - kvm_x86_ops->hardware_enable(garbage); + /* + * Since this may be called from a hotplug notifcation, + * we can't get the CPU frequency directly. + */ + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + int cpu = raw_smp_processor_id(); + per_cpu(cpu_tsc_khz, cpu) = 0; + } + + kvm_shared_msr_cpu_online(); + + return kvm_x86_ops->hardware_enable(garbage); } void kvm_arch_hardware_disable(void *garbage) { kvm_x86_ops->hardware_disable(garbage); + drop_user_return_notifiers(garbage); } int kvm_arch_hardware_setup(void) @@ -4948,8 +5252,36 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + vcpu->arch.singlestep_cs == + get_segment_selector(vcpu, VCPU_SREG_CS) && + vcpu->arch.singlestep_rip == kvm_rip_read(vcpu)) + rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_x86_ops->set_rflags(vcpu, rflags); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 73ffd5536f6..d406c523901 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -146,10 +146,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, use_gbpages = direct_gbpages; #endif - set_nx(); - if (nx_enabled) - printk(KERN_INFO "NX (Execute Disable) protection: active\n"); - /* Enable PSE if available */ if (cpu_has_pse) set_in_cr4(X86_CR4_PSE); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 30938c1d8d5..c973f8e2a6c 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -412,7 +412,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base) pkmap_page_table = pte; } -static void __init add_one_highpage_init(struct page *page, int pfn) +static void __init add_one_highpage_init(struct page *page) { ClearPageReserved(page); init_page_count(page); @@ -445,7 +445,7 @@ static int __init add_highpages_work_fn(unsigned long start_pfn, if (!pfn_valid(node_pfn)) continue; page = pfn_to_page(node_pfn); - add_one_highpage_init(page, node_pfn); + add_one_highpage_init(page); } return 0; @@ -703,8 +703,8 @@ void __init find_low_pfn_range(void) } #ifndef CONFIG_NEED_MULTIPLE_NODES -void __init initmem_init(unsigned long start_pfn, - unsigned long end_pfn) +void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, + int acpi, int k8) { #ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn; @@ -997,7 +997,7 @@ static noinline int do_test_wp_bit(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); -static int kernel_set_to_readonly; +int kernel_set_to_readonly __read_mostly; void set_kernel_text_rw(void) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 5a4398a6006..5198b9bb34e 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -568,7 +568,8 @@ kernel_physical_mapping_init(unsigned long start, } #ifndef CONFIG_NUMA -void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn) +void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, + int acpi, int k8) { unsigned long bootmap_size, bootmap; @@ -694,12 +695,12 @@ void __init mem_init(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); -static int kernel_set_to_readonly; +int kernel_set_to_readonly; void set_kernel_text_rw(void) { - unsigned long start = PFN_ALIGN(_stext); - unsigned long end = PFN_ALIGN(__start_rodata); + unsigned long start = PFN_ALIGN(_text); + unsigned long end = PFN_ALIGN(__stop___ex_table); if (!kernel_set_to_readonly) return; @@ -707,13 +708,18 @@ void set_kernel_text_rw(void) pr_debug("Set kernel text: %lx - %lx for read write\n", start, end); + /* + * Make the kernel identity mapping for text RW. Kernel text + * mapping will always be RO. Refer to the comment in + * static_protections() in pageattr.c + */ set_memory_rw(start, (end - start) >> PAGE_SHIFT); } void set_kernel_text_ro(void) { - unsigned long start = PFN_ALIGN(_stext); - unsigned long end = PFN_ALIGN(__start_rodata); + unsigned long start = PFN_ALIGN(_text); + unsigned long end = PFN_ALIGN(__stop___ex_table); if (!kernel_set_to_readonly) return; @@ -721,14 +727,21 @@ void set_kernel_text_ro(void) pr_debug("Set kernel text: %lx - %lx for read only\n", start, end); + /* + * Set the kernel identity mapping for text RO. + */ set_memory_ro(start, (end - start) >> PAGE_SHIFT); } void mark_rodata_ro(void) { - unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata); + unsigned long start = PFN_ALIGN(_text); unsigned long rodata_start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; + unsigned long end = (unsigned long) &__end_rodata_hpage_align; + unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table); + unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata); + unsigned long data_start = (unsigned long) &_sdata; printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); @@ -751,6 +764,14 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: again\n"); set_memory_ro(start, (end-start) >> PAGE_SHIFT); #endif + + free_init_pages("unused kernel memory", + (unsigned long) page_address(virt_to_page(text_end)), + (unsigned long) + page_address(virt_to_page(rodata_start))); + free_init_pages("unused kernel memory", + (unsigned long) page_address(virt_to_page(rodata_end)), + (unsigned long) page_address(virt_to_page(data_start))); } #endif diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 2feb9bdedaa..c246d259822 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -281,30 +281,6 @@ void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size) } EXPORT_SYMBOL(ioremap_cache); -static void __iomem *ioremap_default(resource_size_t phys_addr, - unsigned long size) -{ - unsigned long flags; - void __iomem *ret; - int err; - - /* - * - WB for WB-able memory and no other conflicting mappings - * - UC_MINUS for non-WB-able memory with no other conflicting mappings - * - Inherit from confliting mappings otherwise - */ - err = reserve_memtype(phys_addr, phys_addr + size, - _PAGE_CACHE_WB, &flags); - if (err < 0) - return NULL; - - ret = __ioremap_caller(phys_addr, size, flags, - __builtin_return_address(0)); - - free_memtype(phys_addr, phys_addr + size); - return ret; -} - void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size, unsigned long prot_val) { @@ -380,7 +356,7 @@ void *xlate_dev_mem_ptr(unsigned long phys) if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - addr = (void __force *)ioremap_default(start, PAGE_SIZE); + addr = (void __force *)ioremap_cache(start, PAGE_SIZE); if (addr) addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK)); diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c index 268f8255280..970ed579d4e 100644 --- a/arch/x86/mm/k8topology_64.c +++ b/arch/x86/mm/k8topology_64.c @@ -24,6 +24,9 @@ #include <asm/apic.h> #include <asm/k8.h> +static struct bootnode __initdata nodes[8]; +static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE; + static __init int find_northbridge(void) { int num; @@ -54,18 +57,6 @@ static __init void early_get_boot_cpu_id(void) * need to get boot_cpu_id so can use that to create apicid_to_node * in k8_scan_nodes() */ - /* - * Find possible boot-time SMP configuration: - */ -#ifdef CONFIG_X86_MPPARSE - early_find_smp_config(); -#endif -#ifdef CONFIG_ACPI - /* - * Read APIC information from ACPI tables. - */ - early_acpi_boot_init(); -#endif #ifdef CONFIG_X86_MPPARSE /* * get boot-time SMP configuration: @@ -76,12 +67,26 @@ static __init void early_get_boot_cpu_id(void) early_init_lapic_mapping(); } -int __init k8_scan_nodes(unsigned long start, unsigned long end) +int __init k8_get_nodes(struct bootnode *physnodes) { - unsigned numnodes, cores, bits, apicid_base; + int i; + int ret = 0; + + for_each_node_mask(i, nodes_parsed) { + physnodes[ret].start = nodes[i].start; + physnodes[ret].end = nodes[i].end; + ret++; + } + return ret; +} + +int __init k8_numa_init(unsigned long start_pfn, unsigned long end_pfn) +{ + unsigned long start = PFN_PHYS(start_pfn); + unsigned long end = PFN_PHYS(end_pfn); + unsigned numnodes; unsigned long prevbase; - struct bootnode nodes[8]; - int i, j, nb, found = 0; + int i, nb, found = 0; u32 nodeid, reg; if (!early_pci_allowed()) @@ -91,16 +96,15 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) if (nb < 0) return nb; - printk(KERN_INFO "Scanning NUMA topology in Northbridge %d\n", nb); + pr_info("Scanning NUMA topology in Northbridge %d\n", nb); reg = read_pci_config(0, nb, 0, 0x60); numnodes = ((reg >> 4) & 0xF) + 1; if (numnodes <= 1) return -1; - printk(KERN_INFO "Number of nodes %d\n", numnodes); + pr_info("Number of physical nodes %d\n", numnodes); - memset(&nodes, 0, sizeof(nodes)); prevbase = 0; for (i = 0; i < 8; i++) { unsigned long base, limit; @@ -111,28 +115,28 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) nodeid = limit & 7; if ((base & 3) == 0) { if (i < numnodes) - printk("Skipping disabled node %d\n", i); + pr_info("Skipping disabled node %d\n", i); continue; } if (nodeid >= numnodes) { - printk("Ignoring excess node %d (%lx:%lx)\n", nodeid, - base, limit); + pr_info("Ignoring excess node %d (%lx:%lx)\n", nodeid, + base, limit); continue; } if (!limit) { - printk(KERN_INFO "Skipping node entry %d (base %lx)\n", - i, base); + pr_info("Skipping node entry %d (base %lx)\n", + i, base); continue; } if ((base >> 8) & 3 || (limit >> 8) & 3) { - printk(KERN_ERR "Node %d using interleaving mode %lx/%lx\n", - nodeid, (base>>8)&3, (limit>>8) & 3); + pr_err("Node %d using interleaving mode %lx/%lx\n", + nodeid, (base >> 8) & 3, (limit >> 8) & 3); return -1; } - if (node_isset(nodeid, node_possible_map)) { - printk(KERN_INFO "Node %d already present. Skipping\n", - nodeid); + if (node_isset(nodeid, nodes_parsed)) { + pr_info("Node %d already present, skipping\n", + nodeid); continue; } @@ -141,8 +145,8 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) limit |= (1<<24)-1; limit++; - if (limit > max_pfn << PAGE_SHIFT) - limit = max_pfn << PAGE_SHIFT; + if (limit > end) + limit = end; if (limit <= base) continue; @@ -154,24 +158,24 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) if (limit > end) limit = end; if (limit == base) { - printk(KERN_ERR "Empty node %d\n", nodeid); + pr_err("Empty node %d\n", nodeid); continue; } if (limit < base) { - printk(KERN_ERR "Node %d bogus settings %lx-%lx.\n", + pr_err("Node %d bogus settings %lx-%lx.\n", nodeid, base, limit); continue; } /* Could sort here, but pun for now. Should not happen anyroads. */ if (prevbase > base) { - printk(KERN_ERR "Node map not sorted %lx,%lx\n", + pr_err("Node map not sorted %lx,%lx\n", prevbase, base); return -1; } - printk(KERN_INFO "Node %d MemBase %016lx Limit %016lx\n", - nodeid, base, limit); + pr_info("Node %d MemBase %016lx Limit %016lx\n", + nodeid, base, limit); found++; @@ -180,18 +184,29 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) prevbase = base; - node_set(nodeid, node_possible_map); + node_set(nodeid, nodes_parsed); } if (!found) return -1; + return 0; +} + +int __init k8_scan_nodes(void) +{ + unsigned int bits; + unsigned int cores; + unsigned int apicid_base; + int i; + BUG_ON(nodes_empty(nodes_parsed)); + node_possible_map = nodes_parsed; memnode_shift = compute_hash_shift(nodes, 8, NULL); if (memnode_shift < 0) { - printk(KERN_ERR "No NUMA node hash function found. Contact maintainer\n"); + pr_err("No NUMA node hash function found. Contact maintainer\n"); return -1; } - printk(KERN_INFO "Using node hash shift of %d\n", memnode_shift); + pr_info("Using node hash shift of %d\n", memnode_shift); /* use the coreid bits from early_identify_cpu */ bits = boot_cpu_data.x86_coreid_bits; @@ -200,14 +215,12 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end) /* need to get boot_cpu_id early for system with apicid lifting */ early_get_boot_cpu_id(); if (boot_cpu_physical_apicid > 0) { - printk(KERN_INFO "BSP APIC ID: %02x\n", - boot_cpu_physical_apicid); + pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid); apicid_base = boot_cpu_physical_apicid; } - for (i = 0; i < 8; i++) { - if (nodes[i].start == nodes[i].end) - continue; + for_each_node_mask(i, node_possible_map) { + int j; e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index d2530062fe0..b20760ca724 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -347,8 +347,8 @@ static void init_remap_allocator(int nid) (ulong) node_remap_end_vaddr[nid]); } -void __init initmem_init(unsigned long start_pfn, - unsigned long end_pfn) +void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, + int acpi, int k8) { int nid; long kva_target_pfn; diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 459913beac7..83bbc70d11b 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -239,8 +239,14 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) bootmap = early_node_mem(nodeid, bootmap_start, end, bootmap_pages<<PAGE_SHIFT, PAGE_SIZE); if (bootmap == NULL) { - if (nodedata_phys < start || nodedata_phys >= end) - free_bootmem(nodedata_phys, pgdat_size); + if (nodedata_phys < start || nodedata_phys >= end) { + /* + * only need to free it if it is from other node + * bootmem + */ + if (nid != nodeid) + free_bootmem(nodedata_phys, pgdat_size); + } node_data[nodeid] = NULL; return; } @@ -306,8 +312,71 @@ void __init numa_init_array(void) #ifdef CONFIG_NUMA_EMU /* Numa emulation */ +static struct bootnode nodes[MAX_NUMNODES] __initdata; +static struct bootnode physnodes[MAX_NUMNODES] __initdata; static char *cmdline __initdata; +static int __init setup_physnodes(unsigned long start, unsigned long end, + int acpi, int k8) +{ + int nr_nodes = 0; + int ret = 0; + int i; + +#ifdef CONFIG_ACPI_NUMA + if (acpi) + nr_nodes = acpi_get_nodes(physnodes); +#endif +#ifdef CONFIG_K8_NUMA + if (k8) + nr_nodes = k8_get_nodes(physnodes); +#endif + /* + * Basic sanity checking on the physical node map: there may be errors + * if the SRAT or K8 incorrectly reported the topology or the mem= + * kernel parameter is used. + */ + for (i = 0; i < nr_nodes; i++) { + if (physnodes[i].start == physnodes[i].end) + continue; + if (physnodes[i].start > end) { + physnodes[i].end = physnodes[i].start; + continue; + } + if (physnodes[i].end < start) { + physnodes[i].start = physnodes[i].end; + continue; + } + if (physnodes[i].start < start) + physnodes[i].start = start; + if (physnodes[i].end > end) + physnodes[i].end = end; + } + + /* + * Remove all nodes that have no memory or were truncated because of the + * limited address range. + */ + for (i = 0; i < nr_nodes; i++) { + if (physnodes[i].start == physnodes[i].end) + continue; + physnodes[ret].start = physnodes[i].start; + physnodes[ret].end = physnodes[i].end; + ret++; + } + + /* + * If no physical topology was detected, a single node is faked to cover + * the entire address space. + */ + if (!ret) { + physnodes[ret].start = start; + physnodes[ret].end = end; + ret = 1; + } + return ret; +} + /* * Setups up nid to range from addr to addr + size. If the end * boundary is greater than max_addr, then max_addr is used instead. @@ -315,11 +384,9 @@ static char *cmdline __initdata; * allocation past addr and -1 otherwise. addr is adjusted to be at * the end of the node. */ -static int __init setup_node_range(int nid, struct bootnode *nodes, u64 *addr, - u64 size, u64 max_addr) +static int __init setup_node_range(int nid, u64 *addr, u64 size, u64 max_addr) { int ret = 0; - nodes[nid].start = *addr; *addr += size; if (*addr >= max_addr) { @@ -335,12 +402,111 @@ static int __init setup_node_range(int nid, struct bootnode *nodes, u64 *addr, } /* + * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr + * to max_addr. The return value is the number of nodes allocated. + */ +static int __init split_nodes_interleave(u64 addr, u64 max_addr, + int nr_phys_nodes, int nr_nodes) +{ + nodemask_t physnode_mask = NODE_MASK_NONE; + u64 size; + int big; + int ret = 0; + int i; + + if (nr_nodes <= 0) + return -1; + if (nr_nodes > MAX_NUMNODES) { + pr_info("numa=fake=%d too large, reducing to %d\n", + nr_nodes, MAX_NUMNODES); + nr_nodes = MAX_NUMNODES; + } + + size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes; + /* + * Calculate the number of big nodes that can be allocated as a result + * of consolidating the remainder. + */ + big = ((size & ~FAKE_NODE_MIN_HASH_MASK) & nr_nodes) / + FAKE_NODE_MIN_SIZE; + + size &= FAKE_NODE_MIN_HASH_MASK; + if (!size) { + pr_err("Not enough memory for each node. " + "NUMA emulation disabled.\n"); + return -1; + } + + for (i = 0; i < nr_phys_nodes; i++) + if (physnodes[i].start != physnodes[i].end) + node_set(i, physnode_mask); + + /* + * Continue to fill physical nodes with fake nodes until there is no + * memory left on any of them. + */ + while (nodes_weight(physnode_mask)) { + for_each_node_mask(i, physnode_mask) { + u64 end = physnodes[i].start + size; + u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); + + if (ret < big) + end += FAKE_NODE_MIN_SIZE; + + /* + * Continue to add memory to this fake node if its + * non-reserved memory is less than the per-node size. + */ + while (end - physnodes[i].start - + e820_hole_size(physnodes[i].start, end) < size) { + end += FAKE_NODE_MIN_SIZE; + if (end > physnodes[i].end) { + end = physnodes[i].end; + break; + } + } + + /* + * If there won't be at least FAKE_NODE_MIN_SIZE of + * non-reserved memory in ZONE_DMA32 for the next node, + * this one must extend to the boundary. + */ + if (end < dma32_end && dma32_end - end - + e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + end = dma32_end; + + /* + * If there won't be enough non-reserved memory for the + * next node, this one must extend to the end of the + * physical node. + */ + if (physnodes[i].end - end - + e820_hole_size(end, physnodes[i].end) < size) + end = physnodes[i].end; + + /* + * Avoid allocating more nodes than requested, which can + * happen as a result of rounding down each node's size + * to FAKE_NODE_MIN_SIZE. + */ + if (nodes_weight(physnode_mask) + ret >= nr_nodes) + end = physnodes[i].end; + + if (setup_node_range(ret++, &physnodes[i].start, + end - physnodes[i].start, + physnodes[i].end) < 0) + node_clear(i, physnode_mask); + } + } + return ret; +} + +/* * Splits num_nodes nodes up equally starting at node_start. The return value * is the number of nodes split up and addr is adjusted to be at the end of the * last node allocated. */ -static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr, - u64 max_addr, int node_start, +static int __init split_nodes_equally(u64 *addr, u64 max_addr, int node_start, int num_nodes) { unsigned int big; @@ -388,7 +554,7 @@ static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr, break; } } - if (setup_node_range(i, nodes, addr, end - *addr, max_addr) < 0) + if (setup_node_range(i, addr, end - *addr, max_addr) < 0) break; } return i - node_start + 1; @@ -399,12 +565,12 @@ static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr, * always assigned to a final node and can be asymmetric. Returns the number of * nodes split. */ -static int __init split_nodes_by_size(struct bootnode *nodes, u64 *addr, - u64 max_addr, int node_start, u64 size) +static int __init split_nodes_by_size(u64 *addr, u64 max_addr, int node_start, + u64 size) { int i = node_start; size = (size << 20) & FAKE_NODE_MIN_HASH_MASK; - while (!setup_node_range(i++, nodes, addr, size, max_addr)) + while (!setup_node_range(i++, addr, size, max_addr)) ; return i - node_start; } @@ -413,15 +579,15 @@ static int __init split_nodes_by_size(struct bootnode *nodes, u64 *addr, * Sets up the system RAM area from start_pfn to last_pfn according to the * numa=fake command-line option. */ -static struct bootnode nodes[MAX_NUMNODES] __initdata; - -static int __init numa_emulation(unsigned long start_pfn, unsigned long last_pfn) +static int __init numa_emulation(unsigned long start_pfn, + unsigned long last_pfn, int acpi, int k8) { u64 size, addr = start_pfn << PAGE_SHIFT; u64 max_addr = last_pfn << PAGE_SHIFT; int num_nodes = 0, num = 0, coeff_flag, coeff = -1, i; + int num_phys_nodes; - memset(&nodes, 0, sizeof(nodes)); + num_phys_nodes = setup_physnodes(addr, max_addr, acpi, k8); /* * If the numa=fake command-line is just a single number N, split the * system RAM into N fake nodes. @@ -429,7 +595,8 @@ static int __init numa_emulation(unsigned long start_pfn, unsigned long last_pfn if (!strchr(cmdline, '*') && !strchr(cmdline, ',')) { long n = simple_strtol(cmdline, NULL, 0); - num_nodes = split_nodes_equally(nodes, &addr, max_addr, 0, n); + num_nodes = split_nodes_interleave(addr, max_addr, + num_phys_nodes, n); if (num_nodes < 0) return num_nodes; goto out; @@ -456,8 +623,8 @@ static int __init numa_emulation(unsigned long start_pfn, unsigned long last_pfn size = ((u64)num << 20) & FAKE_NODE_MIN_HASH_MASK; if (size) for (i = 0; i < coeff; i++, num_nodes++) - if (setup_node_range(num_nodes, nodes, - &addr, size, max_addr) < 0) + if (setup_node_range(num_nodes, &addr, + size, max_addr) < 0) goto done; if (!*cmdline) break; @@ -473,7 +640,7 @@ done: if (addr < max_addr) { if (coeff_flag && coeff < 0) { /* Split remaining nodes into num-sized chunks */ - num_nodes += split_nodes_by_size(nodes, &addr, max_addr, + num_nodes += split_nodes_by_size(&addr, max_addr, num_nodes, num); goto out; } @@ -482,7 +649,7 @@ done: /* Split remaining nodes into coeff chunks */ if (coeff <= 0) break; - num_nodes += split_nodes_equally(nodes, &addr, max_addr, + num_nodes += split_nodes_equally(&addr, max_addr, num_nodes, coeff); break; case ',': @@ -490,8 +657,8 @@ done: break; default: /* Give one final node */ - setup_node_range(num_nodes, nodes, &addr, - max_addr - addr, max_addr); + setup_node_range(num_nodes, &addr, max_addr - addr, + max_addr); num_nodes++; } } @@ -505,14 +672,10 @@ out: } /* - * We need to vacate all active ranges that may have been registered by - * SRAT and set acpi_numa to -1 so that srat_disabled() always returns - * true. NUMA emulation has succeeded so we will not scan ACPI nodes. + * We need to vacate all active ranges that may have been registered for + * the e820 memory map. */ remove_all_active_ranges(); -#ifdef CONFIG_ACPI_NUMA - acpi_numa = -1; -#endif for_each_node_mask(i, node_possible_map) { e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, nodes[i].end >> PAGE_SHIFT); @@ -524,7 +687,8 @@ out: } #endif /* CONFIG_NUMA_EMU */ -void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn) +void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn, + int acpi, int k8) { int i; @@ -532,23 +696,22 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn) nodes_clear(node_online_map); #ifdef CONFIG_NUMA_EMU - if (cmdline && !numa_emulation(start_pfn, last_pfn)) + if (cmdline && !numa_emulation(start_pfn, last_pfn, acpi, k8)) return; nodes_clear(node_possible_map); nodes_clear(node_online_map); #endif #ifdef CONFIG_ACPI_NUMA - if (!numa_off && !acpi_scan_nodes(start_pfn << PAGE_SHIFT, - last_pfn << PAGE_SHIFT)) + if (!numa_off && acpi && !acpi_scan_nodes(start_pfn << PAGE_SHIFT, + last_pfn << PAGE_SHIFT)) return; nodes_clear(node_possible_map); nodes_clear(node_online_map); #endif #ifdef CONFIG_K8_NUMA - if (!numa_off && !k8_scan_nodes(start_pfn<<PAGE_SHIFT, - last_pfn<<PAGE_SHIFT)) + if (!numa_off && k8 && !k8_scan_nodes()) return; nodes_clear(node_possible_map); nodes_clear(node_online_map); @@ -601,6 +764,25 @@ static __init int numa_setup(char *opt) early_param("numa", numa_setup); #ifdef CONFIG_NUMA + +static __init int find_near_online_node(int node) +{ + int n, val; + int min_val = INT_MAX; + int best_node = -1; + + for_each_online_node(n) { + val = node_distance(node, n); + + if (val < min_val) { + min_val = val; + best_node = n; + } + } + + return best_node; +} + /* * Setup early cpu_to_node. * @@ -632,7 +814,7 @@ void __init init_cpu_to_node(void) if (node == NUMA_NO_NODE) continue; if (!node_online(node)) - continue; + node = find_near_online_node(node); numa_set_node(cpu, node); } } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index dd38bfbefd1..1d4eb93d333 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -279,6 +279,22 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address, __pa((unsigned long)__end_rodata) >> PAGE_SHIFT)) pgprot_val(forbidden) |= _PAGE_RW; +#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA) + /* + * Once the kernel maps the text as RO (kernel_set_to_readonly is set), + * kernel text mappings for the large page aligned text, rodata sections + * will be always read-only. For the kernel identity mappings covering + * the holes caused by this alignment can be anything that user asks. + * + * This will preserve the large page mappings for kernel text/data + * at no extra cost. + */ + if (kernel_set_to_readonly && + within(address, (unsigned long)_text, + (unsigned long)__end_rodata_hpage_align)) + pgprot_val(forbidden) |= _PAGE_RW; +#endif + prot = __pgprot(pgprot_val(prot) & ~pgprot_val(forbidden)); return prot; @@ -1069,12 +1085,18 @@ EXPORT_SYMBOL(set_memory_array_wb); int set_memory_x(unsigned long addr, int numpages) { + if (!(__supported_pte_mask & _PAGE_NX)) + return 0; + return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_NX), 0); } EXPORT_SYMBOL(set_memory_x); int set_memory_nx(unsigned long addr, int numpages) { + if (!(__supported_pte_mask & _PAGE_NX)) + return 0; + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_NX), 0); } EXPORT_SYMBOL(set_memory_nx); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index e78cd0ec2bc..66b55d6e69e 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -20,6 +20,7 @@ #include <asm/cacheflush.h> #include <asm/processor.h> #include <asm/tlbflush.h> +#include <asm/x86_init.h> #include <asm/pgtable.h> #include <asm/fcntl.h> #include <asm/e820.h> @@ -355,9 +356,6 @@ static int free_ram_pages_type(u64 start, u64 end) * - _PAGE_CACHE_UC_MINUS * - _PAGE_CACHE_UC * - * req_type will have a special case value '-1', when requester want to inherit - * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS. - * * If new_type is NULL, function will return an error if it cannot reserve the * region with req_type. If new_type is non-NULL, function will return * available type in new_type in case of no error. In case of any error @@ -377,9 +375,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (!pat_enabled) { /* This is identical to page table setting without PAT */ if (new_type) { - if (req_type == -1) - *new_type = _PAGE_CACHE_WB; - else if (req_type == _PAGE_CACHE_WC) + if (req_type == _PAGE_CACHE_WC) *new_type = _PAGE_CACHE_UC_MINUS; else *new_type = req_type & _PAGE_CACHE_MASK; @@ -388,7 +384,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, } /* Low ISA region is always mapped WB in page table. No need to track */ - if (is_ISA_range(start, end - 1)) { + if (x86_platform.is_untracked_pat_range(start, end)) { if (new_type) *new_type = _PAGE_CACHE_WB; return 0; @@ -499,7 +495,7 @@ int free_memtype(u64 start, u64 end) return 0; /* Low ISA region is always mapped WB. No need to track */ - if (is_ISA_range(start, end - 1)) + if (x86_platform.is_untracked_pat_range(start, end)) return 0; is_range_ram = pat_pagerange_is_ram(start, end); @@ -582,7 +578,7 @@ static unsigned long lookup_memtype(u64 paddr) int rettype = _PAGE_CACHE_WB; struct memtype *entry; - if (is_ISA_range(paddr, paddr + PAGE_SIZE - 1)) + if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE)) return rettype; if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) { @@ -1018,8 +1014,10 @@ static const struct file_operations memtype_fops = { static int __init pat_memtype_list_init(void) { - debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir, - NULL, &memtype_fops); + if (pat_enabled) { + debugfs_create_file("pat_memtype_list", S_IRUSR, + arch_debugfs_dir, NULL, &memtype_fops); + } return 0; } diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 513d8ed5d2e..a3250aa3408 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -3,10 +3,8 @@ #include <linux/init.h> #include <asm/pgtable.h> +#include <asm/proto.h> -int nx_enabled; - -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static int disable_nx __cpuinitdata; /* @@ -22,48 +20,41 @@ static int __init noexec_setup(char *str) if (!str) return -EINVAL; if (!strncmp(str, "on", 2)) { - __supported_pte_mask |= _PAGE_NX; disable_nx = 0; } else if (!strncmp(str, "off", 3)) { disable_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; } + x86_configure_nx(); return 0; } early_param("noexec", noexec_setup); -#endif -#ifdef CONFIG_X86_PAE -void __init set_nx(void) +void __cpuinit x86_configure_nx(void) { - unsigned int v[4], l, h; - - if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { - cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); + if (cpu_has_nx && !disable_nx) + __supported_pte_mask |= _PAGE_NX; + else + __supported_pte_mask &= ~_PAGE_NX; +} - if ((v[3] & (1 << 20)) && !disable_nx) { - rdmsr(MSR_EFER, l, h); - l |= EFER_NX; - wrmsr(MSR_EFER, l, h); - nx_enabled = 1; - __supported_pte_mask |= _PAGE_NX; +void __init x86_report_nx(void) +{ + if (!cpu_has_nx) { + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "missing in CPU or disabled in BIOS!\n"); + } else { +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) + if (disable_nx) { + printk(KERN_INFO "NX (Execute Disable) protection: " + "disabled by kernel command line option\n"); + } else { + printk(KERN_INFO "NX (Execute Disable) protection: " + "active\n"); } - } -} #else -void set_nx(void) -{ -} + /* 32bit non-PAE kernel, NX cannot be used */ + printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " + "cannot be enabled: non-PAE kernel!\n"); #endif - -#ifdef CONFIG_X86_64 -void __cpuinit check_efer(void) -{ - unsigned long efer; - - rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || disable_nx) - __supported_pte_mask &= ~_PAGE_NX; + } } -#endif - diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 9d7ce96e5a5..d8907548966 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -290,8 +290,6 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm, start, end); - e820_register_active_regions(node, start >> PAGE_SHIFT, - end >> PAGE_SHIFT); if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) { update_nodes_add(node, start, end); @@ -338,6 +336,19 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) void __init acpi_numa_arch_fixup(void) {} +int __init acpi_get_nodes(struct bootnode *physnodes) +{ + int i; + int ret = 0; + + for_each_node_mask(i, nodes_parsed) { + physnodes[ret].start = nodes[i].start; + physnodes[ret].end = nodes[i].end; + ret++; + } + return ret; +} + /* Use the information discovered above to actually set up the nodes. */ int __init acpi_scan_nodes(unsigned long start, unsigned long end) { @@ -350,11 +361,6 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) for (i = 0; i < MAX_NUMNODES; i++) cutoff_node(i, start, end); - if (!nodes_cover_memory(nodes)) { - bad_srat(); - return -1; - } - memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks, memblk_nodeid); if (memnode_shift < 0) { @@ -364,6 +370,14 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) return -1; } + for_each_node_mask(i, nodes_parsed) + e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, + nodes[i].end >> PAGE_SHIFT); + if (!nodes_cover_memory(nodes)) { + bad_srat(); + return -1; + } + /* Account for nodes with cpus and no memory */ nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed); @@ -454,7 +468,6 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes) for (i = 0; i < num_nodes; i++) if (fake_nodes[i].start != fake_nodes[i].end) node_set(i, nodes_parsed); - WARN_ON(!nodes_cover_memory(fake_nodes)); } static int null_slit_node_compare(int a, int b) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 36fe08eeb5c..65b58e4b0b8 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -8,6 +8,7 @@ #include <asm/tlbflush.h> #include <asm/mmu_context.h> +#include <asm/cache.h> #include <asm/apic.h> #include <asm/uv/uv.h> @@ -43,7 +44,7 @@ union smp_flush_state { spinlock_t tlbstate_lock; DECLARE_BITMAP(flush_cpumask, NR_CPUS); }; - char pad[CONFIG_X86_INTERNODE_CACHE_BYTES]; + char pad[INTERNODE_CACHE_BYTES]; } ____cacheline_internodealigned_in_smp; /* State is put into the per CPU data section, but padded diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index 58bc00f68b1..02b442e9200 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -393,7 +393,6 @@ static ctl_table abi_table2[] = { static ctl_table abi_root_table2[] = { { - .ctl_name = CTL_ABI, .procname = "abi", .mode = 0555, .child = abi_table2 diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index dfbf70e6586..c462cea8ef0 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1093,10 +1093,8 @@ asmlinkage void __init xen_start_kernel(void) __supported_pte_mask |= _PAGE_IOMAP; -#ifdef CONFIG_X86_64 /* Work out if we support NX */ - check_efer(); -#endif + x86_configure_nx(); xen_setup_features(); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index fe03eeed7b4..738da0cb0d8 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -73,7 +73,7 @@ static __cpuinit void cpu_bringup(void) xen_setup_cpu_clockevents(); - cpu_set(cpu, cpu_online_map); + set_cpu_online(cpu, true); percpu_write(cpu_state, CPU_ONLINE); wmb(); |