diff options
Diffstat (limited to 'arch/x86')
192 files changed, 6652 insertions, 3359 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 34bc3a8..c9086e6 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -34,12 +34,15 @@ config X86 select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE + select HAVE_FTRACE_SYSCALLS select HAVE_KVM select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK select HAVE_GENERIC_DMA_COHERENT if X86_32 select HAVE_EFFICIENT_UNALIGNED_ACCESS select USER_STACKTRACE_SUPPORT + select HAVE_DMA_API_DEBUG select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_LZMA @@ -164,6 +167,9 @@ config AUDIT_ARCH config ARCH_SUPPORTS_OPTIMIZED_INLINING def_bool y +config ARCH_SUPPORTS_DEBUG_PAGEALLOC + def_bool y + # Use the generic interrupt handling code in kernel/irq/: config GENERIC_HARDIRQS bool @@ -246,16 +252,13 @@ config SMP config X86_X2APIC bool "Support x2apic" - depends on X86_LOCAL_APIC && X86_64 + depends on X86_LOCAL_APIC && X86_64 && INTR_REMAP ---help--- This enables x2apic support on CPUs that have this feature. This allows 32-bit apic IDs (so it can support very large systems), and accesses the local apic via MSRs not via mmio. - ( On certain CPU models you may need to enable INTR_REMAP too, - to get functional x2apic mode. ) - If you don't know what to do here, say N. config SPARSE_IRQ @@ -350,6 +353,7 @@ config X86_UV bool "SGI Ultraviolet" depends on X86_64 depends on X86_EXTENDED_PLATFORM + depends on NUMA select X86_X2APIC ---help--- This option is needed in order to support SGI Ultraviolet systems. @@ -1140,7 +1144,7 @@ config NODES_SHIFT depends on NEED_MULTIPLE_NODES ---help--- Specify the maximum number of NUMA Nodes available on the target - system. Increases memory reserved to accomodate various tables. + system. Increases memory reserved to accommodate various tables. config HAVE_ARCH_BOOTMEM def_bool y @@ -1318,7 +1322,7 @@ config MTRR_SANITIZER add writeback entries. Can be disabled with disable_mtrr_cleanup on the kernel command line. - The largest mtrr entry size for a continous block can be set with + The largest mtrr entry size for a continuous block can be set with mtrr_chunk_size. If unsure, say Y. @@ -1833,8 +1837,8 @@ config PCI_MMCONFIG config DMAR bool "Support for DMA Remapping Devices (EXPERIMENTAL)" - depends on X86_64 && PCI_MSI && ACPI && EXPERIMENTAL - ---help--- + depends on PCI_MSI && ACPI && EXPERIMENTAL + help DMA remapping (DMAR) devices support enables independent address translations for Direct Memory Access (DMA) from devices. These DMA remapping devices are reported via ACPI tables @@ -1875,7 +1879,6 @@ config DMAR_FLOPPY_WA config INTR_REMAP bool "Support for Interrupt Remapping (EXPERIMENTAL)" depends on X86_64 && X86_IO_APIC && PCI_MSI && ACPI && EXPERIMENTAL - select X86_X2APIC ---help--- Supports Interrupt remapping for IO-APIC and MSI devices. To use x2apic mode in the CPU's which support x2APIC enhancements or diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 924e156..8130334 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -506,6 +506,7 @@ config X86_PTRACE_BTS bool "Branch Trace Store" default y depends on X86_DEBUGCTLMSR + depends on BROKEN ---help--- This adds a ptrace interface to the hardware's branch trace store. diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index fdb45df..d8359e7 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -72,14 +72,6 @@ config DEBUG_STACK_USAGE This option will slow down process creation somewhat. -config DEBUG_PAGEALLOC - bool "Debug page memory allocations" - depends on DEBUG_KERNEL - ---help--- - Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruptions. - config DEBUG_PER_CPU_MAPS bool "Debug access to per_cpu maps" depends on DEBUG_KERNEL diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index fb737ce..6633b6e 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -57,6 +57,7 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE # How to compile the 16-bit code. Note we always compile for -march=i386, # that way we can complain to the user if the CPU is insufficient. KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ + -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes \ -march=i386 -mregparm=3 \ -include $(srctree)/$(src)/code16gcc.h \ @@ -66,7 +67,7 @@ KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \ $(call cc-option, -fno-unit-at-a-time)) \ $(call cc-option, -fno-stack-protector) \ $(call cc-option, -mpreferred-stack-boundary=2) -KBUILD_CFLAGS += $(call cc-option,-m32) +KBUILD_CFLAGS += $(call cc-option, -m32) KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ $(obj)/bzImage: asflags-y := $(SVGA_MODE) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3ca4c19..65551c9 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -8,6 +8,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma h KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC +KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += $(call cc-option,-ffreestanding) diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 8c3c25f..5054c2d 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -2,6 +2,7 @@ * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright 2007 rPath, Inc. - All Rights Reserved + * Copyright 2009 Intel Corporation; author H. Peter Anvin * * This file is part of the Linux kernel, and is made available under * the terms of the GNU General Public License version 2. @@ -16,24 +17,38 @@ #define SMAP 0x534d4150 /* ASCII "SMAP" */ +struct e820_ext_entry { + struct e820entry std; + u32 ext_flags; +} __attribute__((packed)); + static int detect_memory_e820(void) { int count = 0; u32 next = 0; - u32 size, id; + u32 size, id, edi; u8 err; struct e820entry *desc = boot_params.e820_map; + static struct e820_ext_entry buf; /* static so it is zeroed */ + + /* + * Set this here so that if the BIOS doesn't change this field + * but still doesn't change %ecx, we're still okay... + */ + buf.ext_flags = 1; do { - size = sizeof(struct e820entry); + size = sizeof buf; - /* Important: %edx is clobbered by some BIOSes, - so it must be either used for the error output - or explicitly marked clobbered. */ - asm("int $0x15; setc %0" + /* Important: %edx and %esi are clobbered by some BIOSes, + so they must be either used for the error output + or explicitly marked clobbered. Given that, assume there + is something out there clobbering %ebp and %edi, too. */ + asm("pushl %%ebp; int $0x15; popl %%ebp; setc %0" : "=d" (err), "+b" (next), "=a" (id), "+c" (size), - "=m" (*desc) - : "D" (desc), "d" (SMAP), "a" (0xe820)); + "=D" (edi), "+m" (buf) + : "D" (&buf), "d" (SMAP), "a" (0xe820) + : "esi"); /* BIOSes which terminate the chain with CF = 1 as opposed to %ebx = 0 don't always report the SMAP signature on @@ -51,8 +66,14 @@ static int detect_memory_e820(void) break; } + /* ACPI 3.0 added the extended flags support. If bit 0 + in the extended flags is zero, we're supposed to simply + ignore the entry -- a backwards incompatible change! */ + if (size > 20 && !(buf.ext_flags & 1)) + continue; + + *desc++ = buf.std; count++; - desc++; } while (next && count < ARRAY_SIZE(boot_params.e820_map)); return boot_params.e820_entries = count; diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index 95d86ce..9e0587a 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -129,22 +129,18 @@ u16 vga_crtc(void) return (inb(0x3cc) & 1) ? 0x3d4 : 0x3b4; } -static void vga_set_480_scanlines(int lines) +static void vga_set_480_scanlines(void) { u16 crtc; /* CRTC base address */ u8 csel; /* CRTC miscellaneous output register */ - u8 ovfw; /* CRTC overflow register */ - int end = lines-1; crtc = vga_crtc(); - ovfw = 0x3c | ((end >> (8-1)) & 0x02) | ((end >> (9-6)) & 0x40); - out_idx(0x0c, crtc, 0x11); /* Vertical sync end, unlock CR0-7 */ out_idx(0x0b, crtc, 0x06); /* Vertical total */ - out_idx(ovfw, crtc, 0x07); /* Vertical overflow */ + out_idx(0x3e, crtc, 0x07); /* Vertical overflow */ out_idx(0xea, crtc, 0x10); /* Vertical sync start */ - out_idx(end, crtc, 0x12); /* Vertical display end */ + out_idx(0xdf, crtc, 0x12); /* Vertical display end */ out_idx(0xe7, crtc, 0x15); /* Vertical blank start */ out_idx(0x04, crtc, 0x16); /* Vertical blank end */ csel = inb(0x3cc); @@ -153,21 +149,38 @@ static void vga_set_480_scanlines(int lines) outb(csel, 0x3c2); } +static void vga_set_vertical_end(int lines) +{ + u16 crtc; /* CRTC base address */ + u8 ovfw; /* CRTC overflow register */ + int end = lines-1; + + crtc = vga_crtc(); + + ovfw = 0x3c | ((end >> (8-1)) & 0x02) | ((end >> (9-6)) & 0x40); + + out_idx(ovfw, crtc, 0x07); /* Vertical overflow */ + out_idx(end, crtc, 0x12); /* Vertical display end */ +} + static void vga_set_80x30(void) { - vga_set_480_scanlines(30*16); + vga_set_480_scanlines(); + vga_set_vertical_end(30*16); } static void vga_set_80x34(void) { + vga_set_480_scanlines(); vga_set_14font(); - vga_set_480_scanlines(34*14); + vga_set_vertical_end(34*14); } static void vga_set_80x60(void) { + vga_set_480_scanlines(); vga_set_8font(); - vga_set_480_scanlines(60*8); + vga_set_vertical_end(60*8); } static int vga_set_mode(struct mode_info *mode) diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 903de4a..ebe7dee 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o 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_CRC32C_INTEL) += crc32c-intel.o @@ -19,3 +20,5 @@ salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o 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 diff --git a/arch/x86/crypto/aes-i586-asm_32.S b/arch/x86/crypto/aes-i586-asm_32.S index e41b147..b949ec2 100644 --- a/arch/x86/crypto/aes-i586-asm_32.S +++ b/arch/x86/crypto/aes-i586-asm_32.S @@ -41,14 +41,14 @@ #define tlen 1024 // length of each of 4 'xor' arrays (256 32-bit words) /* offsets to parameters with one register pushed onto stack */ -#define tfm 8 +#define ctx 8 #define out_blk 12 #define in_blk 16 -/* offsets in crypto_tfm structure */ -#define klen (crypto_tfm_ctx_offset + 0) -#define ekey (crypto_tfm_ctx_offset + 4) -#define dkey (crypto_tfm_ctx_offset + 244) +/* offsets in crypto_aes_ctx structure */ +#define klen (480) +#define ekey (0) +#define dkey (240) // register mapping for encrypt and decrypt subroutines @@ -217,7 +217,7 @@ do_col (table, r5,r0,r1,r4, r2,r3); /* idx=r5 */ // AES (Rijndael) Encryption Subroutine -/* void aes_enc_blk(struct crypto_tfm *tfm, u8 *out_blk, const u8 *in_blk) */ +/* void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ .global aes_enc_blk @@ -228,7 +228,7 @@ aes_enc_blk: push %ebp - mov tfm(%esp),%ebp + mov ctx(%esp),%ebp // CAUTION: the order and the values used in these assigns // rely on the register mappings @@ -292,7 +292,7 @@ aes_enc_blk: ret // AES (Rijndael) Decryption Subroutine -/* void aes_dec_blk(struct crypto_tfm *tfm, u8 *out_blk, const u8 *in_blk) */ +/* void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out_blk, const u8 *in_blk) */ .global aes_dec_blk @@ -303,7 +303,7 @@ aes_enc_blk: aes_dec_blk: push %ebp - mov tfm(%esp),%ebp + mov ctx(%esp),%ebp // CAUTION: the order and the values used in these assigns // rely on the register mappings diff --git a/arch/x86/crypto/aes-x86_64-asm_64.S b/arch/x86/crypto/aes-x86_64-asm_64.S index a120f52..5b577d5 100644 --- a/arch/x86/crypto/aes-x86_64-asm_64.S +++ b/arch/x86/crypto/aes-x86_64-asm_64.S @@ -17,8 +17,6 @@ #include <asm/asm-offsets.h> -#define BASE crypto_tfm_ctx_offset - #define R1 %rax #define R1E %eax #define R1X %ax @@ -56,13 +54,13 @@ .align 8; \ FUNC: movq r1,r2; \ movq r3,r4; \ - leaq BASE+KEY+48+4(r8),r9; \ + leaq KEY+48(r8),r9; \ movq r10,r11; \ movl (r7),r5 ## E; \ movl 4(r7),r1 ## E; \ movl 8(r7),r6 ## E; \ movl 12(r7),r7 ## E; \ - movl BASE+0(r8),r10 ## E; \ + movl 480(r8),r10 ## E; \ xorl -48(r9),r5 ## E; \ xorl -44(r9),r1 ## E; \ xorl -40(r9),r6 ## E; \ diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c index 71f4578..49ae9fe 100644 --- a/arch/x86/crypto/aes_glue.c +++ b/arch/x86/crypto/aes_glue.c @@ -5,17 +5,29 @@ #include <crypto/aes.h> -asmlinkage void aes_enc_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in); -asmlinkage void aes_dec_blk(struct crypto_tfm *tfm, u8 *out, const u8 *in); +asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); +asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in); + +void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) +{ + aes_enc_blk(ctx, dst, src); +} +EXPORT_SYMBOL_GPL(crypto_aes_encrypt_x86); + +void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) +{ + aes_dec_blk(ctx, dst, src); +} +EXPORT_SYMBOL_GPL(crypto_aes_decrypt_x86); static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - aes_enc_blk(tfm, dst, src); + aes_enc_blk(crypto_tfm_ctx(tfm), dst, src); } static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) { - aes_dec_blk(tfm, dst, src); + aes_dec_blk(crypto_tfm_ctx(tfm), dst, src); } static struct crypto_alg aes_alg = { diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S new file mode 100644 index 0000000..caba996 --- /dev/null +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -0,0 +1,896 @@ +/* + * Implement AES algorithm in Intel AES-NI instructions. + * + * The white paper of AES-NI instructions can be downloaded from: + * http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf + * + * Copyright (C) 2008, Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * Vinodh Gopal <vinodh.gopal@intel.com> + * Kahraman Akdemir + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/linkage.h> + +.text + +#define STATE1 %xmm0 +#define STATE2 %xmm4 +#define STATE3 %xmm5 +#define STATE4 %xmm6 +#define STATE STATE1 +#define IN1 %xmm1 +#define IN2 %xmm7 +#define IN3 %xmm8 +#define IN4 %xmm9 +#define IN IN1 +#define KEY %xmm2 +#define IV %xmm3 + +#define KEYP %rdi +#define OUTP %rsi +#define INP %rdx +#define LEN %rcx +#define IVP %r8 +#define KLEN %r9d +#define T1 %r10 +#define TKEYP T1 +#define T2 %r11 + +_key_expansion_128: +_key_expansion_256a: + pshufd $0b11111111, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + movaps %xmm0, (%rcx) + add $0x10, %rcx + ret + +_key_expansion_192a: + pshufd $0b01010101, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + + movaps %xmm2, %xmm5 + movaps %xmm2, %xmm6 + pslldq $4, %xmm5 + pshufd $0b11111111, %xmm0, %xmm3 + pxor %xmm3, %xmm2 + pxor %xmm5, %xmm2 + + movaps %xmm0, %xmm1 + shufps $0b01000100, %xmm0, %xmm6 + movaps %xmm6, (%rcx) + shufps $0b01001110, %xmm2, %xmm1 + movaps %xmm1, 16(%rcx) + add $0x20, %rcx + ret + +_key_expansion_192b: + pshufd $0b01010101, %xmm1, %xmm1 + shufps $0b00010000, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + shufps $0b10001100, %xmm0, %xmm4 + pxor %xmm4, %xmm0 + pxor %xmm1, %xmm0 + + movaps %xmm2, %xmm5 + pslldq $4, %xmm5 + pshufd $0b11111111, %xmm0, %xmm3 + pxor %xmm3, %xmm2 + pxor %xmm5, %xmm2 + + movaps %xmm0, (%rcx) + add $0x10, %rcx + ret + +_key_expansion_256b: + pshufd $0b10101010, %xmm1, %xmm1 + shufps $0b00010000, %xmm2, %xmm4 + pxor %xmm4, %xmm2 + shufps $0b10001100, %xmm2, %xmm4 + pxor %xmm4, %xmm2 + pxor %xmm1, %xmm2 + movaps %xmm2, (%rcx) + add $0x10, %rcx + ret + +/* + * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + * unsigned int key_len) + */ +ENTRY(aesni_set_key) + movups (%rsi), %xmm0 # user key (first 16 bytes) + movaps %xmm0, (%rdi) + lea 0x10(%rdi), %rcx # key addr + movl %edx, 480(%rdi) + pxor %xmm4, %xmm4 # xmm4 is assumed 0 in _key_expansion_x + cmp $24, %dl + jb .Lenc_key128 + je .Lenc_key192 + 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 + call _key_expansion_256a + # aeskeygenassist $0x1, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + call _key_expansion_256b + # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + call _key_expansion_256a + # aeskeygenassist $0x2, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + call _key_expansion_256b + # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + call _key_expansion_256a + # aeskeygenassist $0x4, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + call _key_expansion_256b + # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + call _key_expansion_256a + # aeskeygenassist $0x8, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + call _key_expansion_256b + # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + call _key_expansion_256a + # aeskeygenassist $0x10, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + call _key_expansion_256b + # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + call _key_expansion_256a + # aeskeygenassist $0x20, %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + call _key_expansion_256b + # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + 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 + call _key_expansion_192a + # aeskeygenassist $0x2, %xmm2, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x02 + call _key_expansion_192b + # aeskeygenassist $0x4, %xmm2, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x04 + call _key_expansion_192a + # aeskeygenassist $0x8, %xmm2, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x08 + call _key_expansion_192b + # aeskeygenassist $0x10, %xmm2, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x10 + call _key_expansion_192a + # aeskeygenassist $0x20, %xmm2, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x20 + call _key_expansion_192b + # aeskeygenassist $0x40, %xmm2, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x40 + call _key_expansion_192a + # aeskeygenassist $0x80, %xmm2, %xmm1 # round 8 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xca, 0x80 + call _key_expansion_192b + jmp .Ldec_key +.Lenc_key128: + # aeskeygenassist $0x1, %xmm0, %xmm1 # round 1 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x01 + call _key_expansion_128 + # aeskeygenassist $0x2, %xmm0, %xmm1 # round 2 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x02 + call _key_expansion_128 + # aeskeygenassist $0x4, %xmm0, %xmm1 # round 3 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x04 + call _key_expansion_128 + # aeskeygenassist $0x8, %xmm0, %xmm1 # round 4 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x08 + call _key_expansion_128 + # aeskeygenassist $0x10, %xmm0, %xmm1 # round 5 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x10 + call _key_expansion_128 + # aeskeygenassist $0x20, %xmm0, %xmm1 # round 6 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x20 + call _key_expansion_128 + # aeskeygenassist $0x40, %xmm0, %xmm1 # round 7 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x40 + call _key_expansion_128 + # aeskeygenassist $0x80, %xmm0, %xmm1 # round 8 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x80 + call _key_expansion_128 + # aeskeygenassist $0x1b, %xmm0, %xmm1 # round 9 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x1b + call _key_expansion_128 + # aeskeygenassist $0x36, %xmm0, %xmm1 # round 10 + .byte 0x66, 0x0f, 0x3a, 0xdf, 0xc8, 0x36 + call _key_expansion_128 +.Ldec_key: + sub $0x10, %rcx + movaps (%rdi), %xmm0 + movaps (%rcx), %xmm1 + movaps %xmm0, 240(%rcx) + movaps %xmm1, 240(%rdi) + add $0x10, %rdi + lea 240-16(%rcx), %rsi +.align 4 +.Ldec_key_loop: + movaps (%rdi), %xmm0 + # aesimc %xmm0, %xmm1 + .byte 0x66, 0x0f, 0x38, 0xdb, 0xc8 + movaps %xmm1, (%rsi) + add $0x10, %rdi + sub $0x10, %rsi + cmp %rcx, %rdi + jb .Ldec_key_loop + xor %rax, %rax + ret + +/* + * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + */ +ENTRY(aesni_enc) + movl 480(KEYP), KLEN # key length + movups (INP), STATE # input + call _aesni_enc1 + movups STATE, (OUTP) # output + ret + +/* + * _aesni_enc1: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: round count + * STATE: initial state (input) + * output: + * STATE: finial state (output) + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_enc1: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE # round 0 + add $0x30, TKEYP + cmp $24, KLEN + jb .Lenc128 + lea 0x20(TKEYP), TKEYP + je .Lenc192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x50(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 +.align 4 +.Lenc192: + movaps -0x40(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x30(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 +.align 4 +.Lenc128: + movaps -0x20(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps -0x10(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps (TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x10(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x20(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x30(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x40(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x50(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x60(TKEYP), KEY + # aesenc KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xdc, 0xc2 + movaps 0x70(TKEYP), KEY + # aesenclast KEY, STATE # last round + .byte 0x66, 0x0f, 0x38, 0xdd, 0xc2 + ret + +/* + * _aesni_enc4: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: round count + * STATE1: initial state (input) + * STATE2 + * STATE3 + * STATE4 + * output: + * STATE1: finial state (output) + * STATE2 + * STATE3 + * STATE4 + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_enc4: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE1 # round 0 + pxor KEY, STATE2 + pxor KEY, STATE3 + pxor KEY, STATE4 + add $0x30, TKEYP + cmp $24, KLEN + jb .L4enc128 + lea 0x20(TKEYP), TKEYP + 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 + 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 +#.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 + 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 +#.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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 + ret + +/* + * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src) + */ +ENTRY(aesni_dec) + mov 480(KEYP), KLEN # key length + add $240, KEYP + movups (INP), STATE # input + call _aesni_dec1 + movups STATE, (OUTP) #output + ret + +/* + * _aesni_dec1: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: key length + * STATE: initial state (input) + * output: + * STATE: finial state (output) + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_dec1: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE # round 0 + add $0x30, TKEYP + cmp $24, KLEN + jb .Ldec128 + lea 0x20(TKEYP), TKEYP + je .Ldec192 + add $0x20, TKEYP + movaps -0x60(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x50(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 +.align 4 +.Ldec192: + movaps -0x40(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x30(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 +.align 4 +.Ldec128: + movaps -0x20(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps -0x10(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps (TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x10(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x20(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x30(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x40(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x50(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x60(TKEYP), KEY + # aesdec KEY, STATE + .byte 0x66, 0x0f, 0x38, 0xde, 0xc2 + movaps 0x70(TKEYP), KEY + # aesdeclast KEY, STATE # last round + .byte 0x66, 0x0f, 0x38, 0xdf, 0xc2 + ret + +/* + * _aesni_dec4: internal ABI + * input: + * KEYP: key struct pointer + * KLEN: key length + * STATE1: initial state (input) + * STATE2 + * STATE3 + * STATE4 + * output: + * STATE1: finial state (output) + * STATE2 + * STATE3 + * STATE4 + * changed: + * KEY + * TKEYP (T1) + */ +_aesni_dec4: + movaps (KEYP), KEY # key + mov KEYP, TKEYP + pxor KEY, STATE1 # round 0 + pxor KEY, STATE2 + pxor KEY, STATE3 + pxor KEY, STATE4 + add $0x30, TKEYP + cmp $24, KLEN + jb .L4dec128 + lea 0x20(TKEYP), TKEYP + 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 + 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 +.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 + 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 +.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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 + 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 + ret + +/* + * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len) + */ +ENTRY(aesni_ecb_enc) + test LEN, LEN # check length + jz .Lecb_enc_ret + mov 480(KEYP), KLEN + cmp $16, LEN + jb .Lecb_enc_ret + cmp $64, LEN + jb .Lecb_enc_loop1 +.align 4 +.Lecb_enc_loop4: + movups (INP), STATE1 + movups 0x10(INP), STATE2 + movups 0x20(INP), STATE3 + movups 0x30(INP), STATE4 + call _aesni_enc4 + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lecb_enc_loop4 + cmp $16, LEN + jb .Lecb_enc_ret +.align 4 +.Lecb_enc_loop1: + movups (INP), STATE1 + call _aesni_enc1 + movups STATE1, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lecb_enc_loop1 +.Lecb_enc_ret: + ret + +/* + * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len); + */ +ENTRY(aesni_ecb_dec) + test LEN, LEN + jz .Lecb_dec_ret + mov 480(KEYP), KLEN + add $240, KEYP + cmp $16, LEN + jb .Lecb_dec_ret + cmp $64, LEN + jb .Lecb_dec_loop1 +.align 4 +.Lecb_dec_loop4: + movups (INP), STATE1 + movups 0x10(INP), STATE2 + movups 0x20(INP), STATE3 + movups 0x30(INP), STATE4 + call _aesni_dec4 + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lecb_dec_loop4 + cmp $16, LEN + jb .Lecb_dec_ret +.align 4 +.Lecb_dec_loop1: + movups (INP), STATE1 + call _aesni_dec1 + movups STATE1, (OUTP) + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lecb_dec_loop1 +.Lecb_dec_ret: + ret + +/* + * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_cbc_enc) + cmp $16, LEN + jb .Lcbc_enc_ret + mov 480(KEYP), KLEN + movups (IVP), STATE # load iv as initial state +.align 4 +.Lcbc_enc_loop: + movups (INP), IN # load input + pxor IN, STATE + call _aesni_enc1 + movups STATE, (OUTP) # store output + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lcbc_enc_loop + movups STATE, (IVP) +.Lcbc_enc_ret: + ret + +/* + * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src, + * size_t len, u8 *iv) + */ +ENTRY(aesni_cbc_dec) + cmp $16, LEN + jb .Lcbc_dec_ret + mov 480(KEYP), KLEN + add $240, KEYP + movups (IVP), IV + cmp $64, LEN + jb .Lcbc_dec_loop1 +.align 4 +.Lcbc_dec_loop4: + movups (INP), IN1 + movaps IN1, STATE1 + movups 0x10(INP), IN2 + movaps IN2, STATE2 + movups 0x20(INP), IN3 + movaps IN3, STATE3 + movups 0x30(INP), IN4 + movaps IN4, STATE4 + call _aesni_dec4 + pxor IV, STATE1 + pxor IN1, STATE2 + pxor IN2, STATE3 + pxor IN3, STATE4 + movaps IN4, IV + movups STATE1, (OUTP) + movups STATE2, 0x10(OUTP) + movups STATE3, 0x20(OUTP) + movups STATE4, 0x30(OUTP) + sub $64, LEN + add $64, INP + add $64, OUTP + cmp $64, LEN + jge .Lcbc_dec_loop4 + cmp $16, LEN + jb .Lcbc_dec_ret +.align 4 +.Lcbc_dec_loop1: + movups (INP), IN + movaps IN, STATE + call _aesni_dec1 + pxor IV, STATE + movups STATE, (OUTP) + movaps IN, IV + sub $16, LEN + add $16, INP + add $16, OUTP + cmp $16, LEN + jge .Lcbc_dec_loop1 + movups IV, (IVP) +.Lcbc_dec_ret: + ret diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c new file mode 100644 index 0000000..02af0af --- /dev/null +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -0,0 +1,461 @@ +/* + * Support for Intel AES-NI instructions. This file contains glue + * code, the real AES implementation is in intel-aes_asm.S. + * + * Copyright (C) 2008, 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 as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/hardirq.h> +#include <linux/types.h> +#include <linux/crypto.h> +#include <linux/err.h> +#include <crypto/algapi.h> +#include <crypto/aes.h> +#include <crypto/cryptd.h> +#include <asm/i387.h> +#include <asm/aes.h> + +struct async_aes_ctx { + struct cryptd_ablkcipher *cryptd_tfm; +}; + +#define AESNI_ALIGN 16 +#define AES_BLOCK_MASK (~(AES_BLOCK_SIZE-1)) + +asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + unsigned int key_len); +asmlinkage void aesni_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in); +asmlinkage void aesni_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in); +asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len); +asmlinkage void aesni_ecb_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len); +asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); + +static inline int kernel_fpu_using(void) +{ + if (in_interrupt() && !(read_cr0() & X86_CR0_TS)) + return 1; + return 0; +} + +static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) +{ + unsigned long addr = (unsigned long)raw_ctx; + unsigned long align = AESNI_ALIGN; + + if (align <= crypto_tfm_ctx_alignment()) + align = 1; + return (struct crypto_aes_ctx *)ALIGN(addr, align); +} + +static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx, + const u8 *in_key, unsigned int key_len) +{ + struct crypto_aes_ctx *ctx = aes_ctx(raw_ctx); + u32 *flags = &tfm->crt_flags; + int err; + + if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && + key_len != AES_KEYSIZE_256) { + *flags |= CRYPTO_TFM_RES_BAD_KEY_LEN; + return -EINVAL; + } + + if (kernel_fpu_using()) + err = crypto_aes_expand_key(ctx, in_key, key_len); + else { + kernel_fpu_begin(); + err = aesni_set_key(ctx, in_key, key_len); + kernel_fpu_end(); + } + + return err; +} + +static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, + unsigned int key_len) +{ + return aes_set_key_common(tfm, crypto_tfm_ctx(tfm), in_key, key_len); +} + +static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + if (kernel_fpu_using()) + crypto_aes_encrypt_x86(ctx, dst, src); + else { + kernel_fpu_begin(); + aesni_enc(ctx, dst, src); + kernel_fpu_end(); + } +} + +static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm)); + + if (kernel_fpu_using()) + crypto_aes_decrypt_x86(ctx, dst, src); + else { + kernel_fpu_begin(); + aesni_dec(ctx, dst, src); + kernel_fpu_end(); + } +} + +static struct crypto_alg aesni_alg = { + .cra_name = "aes", + .cra_driver_name = "aes-aesni", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(aesni_alg.cra_list), + .cra_u = { + .cipher = { + .cia_min_keysize = AES_MIN_KEY_SIZE, + .cia_max_keysize = AES_MAX_KEY_SIZE, + .cia_setkey = aes_set_key, + .cia_encrypt = aes_encrypt, + .cia_decrypt = aes_decrypt + } + } +}; + +static int ecb_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static int ecb_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_ecb_alg = { + .cra_name = "__ecb-aes-aesni", + .cra_driver_name = "__driver-ecb-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_ecb_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aes_set_key, + .encrypt = ecb_encrypt, + .decrypt = ecb_decrypt, + }, + }, +}; + +static int cbc_encrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static int cbc_decrypt(struct blkcipher_desc *desc, + struct scatterlist *dst, struct scatterlist *src, + unsigned int nbytes) +{ + struct crypto_aes_ctx *ctx = aes_ctx(crypto_blkcipher_ctx(desc->tfm)); + struct blkcipher_walk walk; + int err; + + blkcipher_walk_init(&walk, dst, src, nbytes); + err = blkcipher_walk_virt(desc, &walk); + + kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); + nbytes &= AES_BLOCK_SIZE - 1; + err = blkcipher_walk_done(desc, &walk, nbytes); + } + kernel_fpu_end(); + + return err; +} + +static struct crypto_alg blk_cbc_alg = { + .cra_name = "__cbc-aes-aesni", + .cra_driver_name = "__driver-cbc-aes-aesni", + .cra_priority = 0, + .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx)+AESNI_ALIGN-1, + .cra_alignmask = 0, + .cra_type = &crypto_blkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(blk_cbc_alg.cra_list), + .cra_u = { + .blkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = aes_set_key, + .encrypt = cbc_encrypt, + .decrypt = cbc_decrypt, + }, + }, +}; + +static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key, + unsigned int key_len) +{ + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + return crypto_ablkcipher_setkey(&ctx->cryptd_tfm->base, key, key_len); +} + +static int ablk_encrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + if (kernel_fpu_using()) { + struct ablkcipher_request *cryptd_req = + ablkcipher_request_ctx(req); + memcpy(cryptd_req, req, sizeof(*req)); + ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + return crypto_ablkcipher_encrypt(cryptd_req); + } else { + struct blkcipher_desc desc; + desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm); + desc.info = req->info; + desc.flags = 0; + return crypto_blkcipher_crt(desc.tfm)->encrypt( + &desc, req->dst, req->src, req->nbytes); + } +} + +static int ablk_decrypt(struct ablkcipher_request *req) +{ + struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req); + struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm); + + if (kernel_fpu_using()) { + struct ablkcipher_request *cryptd_req = + ablkcipher_request_ctx(req); + memcpy(cryptd_req, req, sizeof(*req)); + ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base); + return crypto_ablkcipher_decrypt(cryptd_req); + } else { + struct blkcipher_desc desc; + desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm); + desc.info = req->info; + desc.flags = 0; + return crypto_blkcipher_crt(desc.tfm)->decrypt( + &desc, req->dst, req->src, req->nbytes); + } +} + +static void ablk_exit(struct crypto_tfm *tfm) +{ + struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm); + + cryptd_free_ablkcipher(ctx->cryptd_tfm); +} + +static void ablk_init_common(struct crypto_tfm *tfm, + struct cryptd_ablkcipher *cryptd_tfm) +{ + struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm); + + ctx->cryptd_tfm = cryptd_tfm; + tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) + + crypto_ablkcipher_reqsize(&cryptd_tfm->base); +} + +static int ablk_ecb_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-ecb-aes-aesni", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_ecb_alg = { + .cra_name = "ecb(aes)", + .cra_driver_name = "ecb-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_ecb_alg.cra_list), + .cra_init = ablk_ecb_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; + +static int ablk_cbc_init(struct crypto_tfm *tfm) +{ + struct cryptd_ablkcipher *cryptd_tfm; + + cryptd_tfm = cryptd_alloc_ablkcipher("__driver-cbc-aes-aesni", 0, 0); + if (IS_ERR(cryptd_tfm)) + return PTR_ERR(cryptd_tfm); + ablk_init_common(tfm, cryptd_tfm); + return 0; +} + +static struct crypto_alg ablk_cbc_alg = { + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-aesni", + .cra_priority = 400, + .cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER|CRYPTO_ALG_ASYNC, + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct async_aes_ctx), + .cra_alignmask = 0, + .cra_type = &crypto_ablkcipher_type, + .cra_module = THIS_MODULE, + .cra_list = LIST_HEAD_INIT(ablk_cbc_alg.cra_list), + .cra_init = ablk_cbc_init, + .cra_exit = ablk_exit, + .cra_u = { + .ablkcipher = { + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .setkey = ablk_set_key, + .encrypt = ablk_encrypt, + .decrypt = ablk_decrypt, + }, + }, +}; + +static int __init aesni_init(void) +{ + int err; + + if (!cpu_has_aes) { + printk(KERN_ERR "Intel AES-NI instructions are not detected.\n"); + return -ENODEV; + } + if ((err = crypto_register_alg(&aesni_alg))) + goto aes_err; + if ((err = crypto_register_alg(&blk_ecb_alg))) + goto blk_ecb_err; + if ((err = crypto_register_alg(&blk_cbc_alg))) + goto blk_cbc_err; + if ((err = crypto_register_alg(&ablk_ecb_alg))) + goto ablk_ecb_err; + if ((err = crypto_register_alg(&ablk_cbc_alg))) + goto ablk_cbc_err; + + return err; + +ablk_cbc_err: + crypto_unregister_alg(&ablk_ecb_alg); +ablk_ecb_err: + crypto_unregister_alg(&blk_cbc_alg); +blk_cbc_err: + crypto_unregister_alg(&blk_ecb_alg); +blk_ecb_err: + crypto_unregister_alg(&aesni_alg); +aes_err: + return err; +} + +static void __exit aesni_exit(void) +{ + crypto_unregister_alg(&ablk_cbc_alg); + crypto_unregister_alg(&ablk_ecb_alg); + crypto_unregister_alg(&blk_cbc_alg); + crypto_unregister_alg(&blk_ecb_alg); + crypto_unregister_alg(&aesni_alg); +} + +module_init(aesni_init); +module_exit(aesni_exit); + +MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("aes"); diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 097a6b6..a505202 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -557,7 +557,7 @@ ia32_sys_call_table: .quad sys32_olduname .quad sys_umask /* 60 */ .quad sys_chroot - .quad sys32_ustat + .quad compat_sys_ustat .quad sys_dup2 .quad sys_getppid .quad sys_getpgrp /* 65 */ @@ -828,4 +828,6 @@ ia32_sys_call_table: .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 + .quad compat_sys_preadv + .quad compat_sys_pwritev ia32_syscall_end: diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 6c0d7f6..efac92f 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -638,28 +638,6 @@ long sys32_uname(struct old_utsname __user *name) return err ? -EFAULT : 0; } -long sys32_ustat(unsigned dev, struct ustat32 __user *u32p) -{ - struct ustat u; - mm_segment_t seg; - int ret; - - seg = get_fs(); - set_fs(KERNEL_DS); - ret = sys_ustat(dev, (struct ustat __user *)&u); - set_fs(seg); - if (ret < 0) - return ret; - - if (!access_ok(VERIFY_WRITE, u32p, sizeof(struct ustat32)) || - __put_user((__u32) u.f_tfree, &u32p->f_tfree) || - __put_user((__u32) u.f_tinode, &u32p->f_tfree) || - __copy_to_user(&u32p->f_fname, u.f_fname, sizeof(u.f_fname)) || - __copy_to_user(&u32p->f_fpack, u.f_fpack, sizeof(u.f_fpack))) - ret = -EFAULT; - return ret; -} - asmlinkage long sys32_execve(char __user *name, compat_uptr_t __user *argv, compat_uptr_t __user *envp, struct pt_regs *regs) { diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/aes.h new file mode 100644 index 0000000..80545a1 --- /dev/null +++ b/arch/x86/include/asm/aes.h @@ -0,0 +1,11 @@ +#ifndef ASM_X86_AES_H +#define ASM_X86_AES_H + +#include <linux/crypto.h> +#include <crypto/aes.h> + +void crypto_aes_encrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, + const u8 *src); +void crypto_aes_decrypt_x86(struct crypto_aes_ctx *ctx, u8 *dst, + const u8 *src); +#endif diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 00f5962..42f2f83 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -75,7 +75,7 @@ static inline void default_inquire_remote_apic(int apicid) #define setup_secondary_clock setup_secondary_APIC_clock #endif -#ifdef CONFIG_X86_VSMP +#ifdef CONFIG_X86_64 extern int is_vsmp_box(void); #else static inline int is_vsmp_box(void) @@ -107,6 +107,9 @@ extern u32 native_safe_apic_wait_icr_idle(void); extern void native_apic_icr_write(u32 low, u32 id); extern u64 native_apic_icr_read(void); +#define EIM_8BIT_APIC_ID 0 +#define EIM_32BIT_APIC_ID 1 + #ifdef CONFIG_X86_X2APIC /* * Make previous memory operations globally visible before @@ -489,10 +492,19 @@ static inline int default_apic_id_registered(void) return physid_isset(read_apic_id(), phys_cpu_present_map); } +static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) +{ + return cpuid_apic >> index_msb; +} + +extern int default_apicid_to_node(int logical_apicid); + +#endif + static inline unsigned int default_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return cpumask_bits(cpumask)[0]; + return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; } static inline unsigned int @@ -506,15 +518,6 @@ default_cpu_mask_to_apicid_and(const struct cpumask *cpumask, return (unsigned int)(mask1 & mask2 & mask3); } -static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - -extern int default_apicid_to_node(int logical_apicid); - -#endif - static inline unsigned long default_check_apicid_used(physid_mask_t bitmap, int apicid) { return physid_isset(apicid, bitmap); diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h index b3894bf..e55dfc1 100644 --- a/arch/x86/include/asm/cacheflush.h +++ b/arch/x86/include/asm/cacheflush.h @@ -126,6 +126,11 @@ void clflush_cache_range(void *addr, unsigned int size); #ifdef CONFIG_DEBUG_RODATA void mark_rodata_ro(void); extern const int rodata_test_data; +void set_kernel_text_rw(void); +void set_kernel_text_ro(void); +#else +static inline void set_kernel_text_rw(void) { } +static inline void set_kernel_text_ro(void) { } #endif #ifdef CONFIG_DEBUG_RODATA_TEST diff --git a/arch/x86/include/asm/cpu_debug.h b/arch/x86/include/asm/cpu_debug.h index 2228020..2228020 100755..100644 --- a/arch/x86/include/asm/cpu_debug.h +++ b/arch/x86/include/asm/cpu_debug.h diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7301e60..bb83b1c 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -154,6 +154,7 @@ * CPUID levels like 0x6, 0xA etc */ #define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ /* Virtualization flags: Linux defined */ #define X86_FEATURE_TPR_SHADOW (8*32+ 0) /* Intel TPR Shadow */ @@ -213,6 +214,7 @@ extern const char * const x86_power_flags[32]; #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) #define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) +#define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) #define cpu_has_mp boot_cpu_has(X86_FEATURE_MP) #define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index a7f3c75..61c852f 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -3,8 +3,6 @@ #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -#ifdef CONFIG_X86_64 - extern cpumask_var_t cpu_callin_mask; extern cpumask_var_t cpu_callout_mask; extern cpumask_var_t cpu_initialized_mask; @@ -12,21 +10,5 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); -#else /* CONFIG_X86_32 */ - -extern cpumask_t cpu_callin_map; -extern cpumask_t cpu_callout_map; -extern cpumask_t cpu_initialized; -extern cpumask_t cpu_sibling_setup_map; - -#define cpu_callin_mask ((struct cpumask *)&cpu_callin_map) -#define cpu_callout_mask ((struct cpumask *)&cpu_callout_map) -#define cpu_initialized_mask ((struct cpumask *)&cpu_initialized) -#define cpu_sibling_setup_mask ((struct cpumask *)&cpu_sibling_setup_map) - -static inline void setup_cpu_local_masks(void) { } - -#endif /* CONFIG_X86_32 */ - #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 3c034f4..4994a20 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -6,7 +6,7 @@ struct dev_archdata { void *acpi_handle; #endif #ifdef CONFIG_X86_64 -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; #endif #ifdef CONFIG_DMAR void *iommu; /* hook for IOMMU specific extension */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index 132a134..f82fdc4 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -7,6 +7,8 @@ */ #include <linux/scatterlist.h> +#include <linux/dma-debug.h> +#include <linux/dma-attrs.h> #include <asm/io.h> #include <asm/swiotlb.h> #include <asm-generic/dma-coherent.h> @@ -16,47 +18,9 @@ extern int iommu_merge; extern struct device x86_dma_fallback_dev; extern int panic_on_overflow; -struct dma_mapping_ops { - int (*mapping_error)(struct device *dev, - dma_addr_t dma_addr); - void* (*alloc_coherent)(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp); - void (*free_coherent)(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - dma_addr_t (*map_single)(struct device *hwdev, phys_addr_t ptr, - size_t size, int direction); - void (*unmap_single)(struct device *dev, dma_addr_t addr, - size_t size, int direction); - void (*sync_single_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_for_device)(struct device *hwdev, - dma_addr_t dma_handle, size_t size, - int direction); - void (*sync_single_range_for_cpu)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_single_range_for_device)(struct device *hwdev, - dma_addr_t dma_handle, unsigned long offset, - size_t size, int direction); - void (*sync_sg_for_cpu)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - void (*sync_sg_for_device)(struct device *hwdev, - struct scatterlist *sg, int nelems, - int direction); - int (*map_sg)(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); - void (*unmap_sg)(struct device *hwdev, - struct scatterlist *sg, int nents, - int direction); - int (*dma_supported)(struct device *hwdev, u64 mask); - int is_phys; -}; - -extern struct dma_mapping_ops *dma_ops; - -static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) +extern struct dma_map_ops *dma_ops; + +static inline struct dma_map_ops *get_dma_ops(struct device *dev) { #ifdef CONFIG_X86_32 return dma_ops; @@ -71,7 +35,7 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev) /* Make sure we keep the same behaviour */ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); if (ops->mapping_error) return ops->mapping_error(dev, dma_addr); @@ -90,137 +54,167 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); - - BUG_ON(!valid_dma_direction(direction)); - return ops->map_single(hwdev, virt_to_phys(ptr), size, direction); + struct dma_map_ops *ops = get_dma_ops(hwdev); + dma_addr_t addr; + + BUG_ON(!valid_dma_direction(dir)); + addr = ops->map_page(hwdev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + dir, NULL); + debug_dma_map_page(hwdev, virt_to_page(ptr), + (unsigned long)ptr & ~PAGE_MASK, size, + dir, addr, true); + return addr; } static inline void dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); - BUG_ON(!valid_dma_direction(direction)); - if (ops->unmap_single) - ops->unmap_single(dev, addr, size, direction); + BUG_ON(!valid_dma_direction(dir)); + if (ops->unmap_page) + ops->unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, true); } static inline int dma_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction) + int nents, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); + int ents; + + BUG_ON(!valid_dma_direction(dir)); + ents = ops->map_sg(hwdev, sg, nents, dir, NULL); + debug_dma_map_sg(hwdev, sg, nents, ents, dir); - BUG_ON(!valid_dma_direction(direction)); - return ops->map_sg(hwdev, sg, nents, direction); + return ents; } static inline void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); + debug_dma_unmap_sg(hwdev, sg, nents, dir); if (ops->unmap_sg) - ops->unmap_sg(hwdev, sg, nents, direction); + ops->unmap_sg(hwdev, sg, nents, dir, NULL); } static inline void dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_cpu) - ops->sync_single_for_cpu(hwdev, dma_handle, size, direction); + ops->sync_single_for_cpu(hwdev, dma_handle, size, dir); + debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir); flush_write_buffers(); } static inline void dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_for_device) - ops->sync_single_for_device(hwdev, dma_handle, size, direction); + ops->sync_single_for_device(hwdev, dma_handle, size, dir); + debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir); flush_write_buffers(); } static inline void dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle, - unsigned long offset, size_t size, int direction) + unsigned long offset, size_t size, + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_range_for_cpu) ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, - size, direction); + size, dir); + debug_dma_sync_single_range_for_cpu(hwdev, dma_handle, + offset, size, dir); flush_write_buffers(); } static inline void dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle, unsigned long offset, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_single_range_for_device) ops->sync_single_range_for_device(hwdev, dma_handle, - offset, size, direction); + offset, size, dir); + debug_dma_sync_single_range_for_device(hwdev, dma_handle, + offset, size, dir); flush_write_buffers(); } static inline void dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_cpu) - ops->sync_sg_for_cpu(hwdev, sg, nelems, direction); + ops->sync_sg_for_cpu(hwdev, sg, nelems, dir); + debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir); flush_write_buffers(); } static inline void dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(hwdev); + struct dma_map_ops *ops = get_dma_ops(hwdev); - BUG_ON(!valid_dma_direction(direction)); + BUG_ON(!valid_dma_direction(dir)); if (ops->sync_sg_for_device) - ops->sync_sg_for_device(hwdev, sg, nelems, direction); + ops->sync_sg_for_device(hwdev, sg, nelems, dir); + debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir); flush_write_buffers(); } static inline dma_addr_t dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, - int direction) + enum dma_data_direction dir) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); + dma_addr_t addr; - BUG_ON(!valid_dma_direction(direction)); - return ops->map_single(dev, page_to_phys(page) + offset, - size, direction); + BUG_ON(!valid_dma_direction(dir)); + addr = ops->map_page(dev, page, offset, size, dir, NULL); + debug_dma_map_page(dev, page, offset, size, dir, addr, false); + + return addr; } static inline void dma_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, int direction) + size_t size, enum dma_data_direction dir) { - dma_unmap_single(dev, addr, size, direction); + struct dma_map_ops *ops = get_dma_ops(dev); + + BUG_ON(!valid_dma_direction(dir)); + if (ops->unmap_page) + ops->unmap_page(dev, addr, size, dir, NULL); + debug_dma_unmap_page(dev, addr, size, dir, false); } static inline void @@ -244,7 +238,7 @@ static inline unsigned long dma_alloc_coherent_mask(struct device *dev, dma_mask = dev->coherent_dma_mask; if (!dma_mask) - dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK; + dma_mask = (gfp & GFP_DMA) ? DMA_BIT_MASK(24) : DMA_BIT_MASK(32); return dma_mask; } @@ -253,10 +247,10 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp) { unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp); - if (dma_mask <= DMA_24BIT_MASK) + if (dma_mask <= DMA_BIT_MASK(24)) gfp |= GFP_DMA; #ifdef CONFIG_X86_64 - if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA)) + if (dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) gfp |= GFP_DMA32; #endif return gfp; @@ -266,7 +260,7 @@ static inline void * dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); void *memory; gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32); @@ -285,20 +279,24 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, if (!ops->alloc_coherent) return NULL; - return ops->alloc_coherent(dev, size, dma_handle, - dma_alloc_coherent_gfp_flags(dev, gfp)); + memory = ops->alloc_coherent(dev, size, dma_handle, + dma_alloc_coherent_gfp_flags(dev, gfp)); + debug_dma_alloc_coherent(dev, size, *dma_handle, memory); + + return memory; } static inline void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t bus) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); WARN_ON(irqs_disabled()); /* for portability */ if (dma_release_from_coherent(dev, get_order(size), vaddr)) return; + debug_dma_free_coherent(dev, size, vaddr, bus); if (ops->free_coherent) ops->free_coherent(dev, size, vaddr, bus); } diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 00d41ce..7ecba4d 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -72,7 +72,7 @@ extern int e820_all_mapped(u64 start, u64 end, unsigned type); extern void e820_add_region(u64 start, u64 size, int type); extern void e820_print_map(char *who); extern int -sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map); +sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); extern u64 e820_update_range(u64 start, u64 size, unsigned old_type, unsigned new_type); extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 63a79c7..2d81af3 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -111,6 +111,8 @@ enum fixed_addresses { #ifdef CONFIG_PARAVIRT FIX_PARAVIRT_BOOTMAP, #endif + FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */ + FIX_TEXT_POKE1, __end_of_permanent_fixed_addresses, #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT FIX_OHCI1394_BASE, @@ -149,11 +151,11 @@ extern pte_t *pkmap_page_table; void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); void native_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags); + phys_addr_t phys, pgprot_t flags); #ifndef CONFIG_PARAVIRT static inline void __set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { native_set_fixmap(idx, phys, flags); } diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index b55b4a7..bd2c651 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -28,6 +28,13 @@ #endif +/* FIXME: I don't want to stay hardcoded */ +#ifdef CONFIG_X86_64 +# define FTRACE_SYSCALL_MAX 296 +#else +# define FTRACE_SYSCALL_MAX 333 +#endif + #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_ADDR ((long)(mcount)) #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ @@ -55,29 +62,4 @@ struct dyn_arch_ftrace { #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - -#ifndef __ASSEMBLY__ - -/* - * Stack of return addresses for functions - * of a thread. - * Used in struct thread_info - */ -struct ftrace_ret_stack { - unsigned long ret; - unsigned long func; - unsigned long long calltime; -}; - -/* - * Primary handler of a function return. - * It relays on ftrace_return_to_handler. - * Defined in entry_32/64.S - */ -extern void return_to_handler(void); - -#endif /* __ASSEMBLY__ */ -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 50ca486..1f7e625 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -129,13 +129,6 @@ typedef struct compat_siginfo { } _sifields; } compat_siginfo_t; -struct ustat32 { - __u32 f_tfree; - compat_ino_t f_tinode; - char f_fname[6]; - char f_fpack[6]; -}; - #define IA32_STACK_TOP IA32_PAGE_OFFSET #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index e5383e3..7373932 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -193,8 +193,10 @@ extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); */ extern void early_ioremap_init(void); extern void early_ioremap_reset(void); -extern void __iomem *early_ioremap(unsigned long offset, unsigned long size); -extern void __iomem *early_memremap(unsigned long offset, unsigned long size); +extern void __iomem *early_ioremap(resource_size_t phys_addr, + unsigned long size); +extern void __iomem *early_memremap(resource_size_t phys_addr, + unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 373cc2b..9d826e4 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -162,10 +162,13 @@ extern int (*ioapic_renumber_irq)(int ioapic, int irq); extern void ioapic_init_mappings(void); #ifdef CONFIG_X86_64 -extern int save_IO_APIC_setup(void); -extern void mask_IO_APIC_setup(void); -extern void restore_IO_APIC_setup(void); -extern void reinit_intr_remapped_IO_APIC(int); +extern struct IO_APIC_route_entry **alloc_ioapic_entries(void); +extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries); +extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries); +extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries); +extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries); +extern void reinit_intr_remapped_IO_APIC(int intr_remapping, + struct IO_APIC_route_entry **ioapic_entries); #endif extern void probe_nr_irqs_gsi(void); diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index a6ee9e6..af326a2 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -3,7 +3,7 @@ extern void pci_iommu_shutdown(void); extern void no_iommu_init(void); -extern struct dma_mapping_ops nommu_dma_ops; +extern struct dma_map_ops nommu_dma_ops; extern int force_iommu, no_iommu; extern int iommu_detected; diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index 886c940..dc3f6cf 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -15,6 +15,7 @@ #define __KVM_HAVE_DEVICE_ASSIGNMENT #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI +#define __KVM_HAVE_GUEST_DEBUG /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -212,7 +213,30 @@ struct kvm_pit_channel_state { __s64 count_load_time; }; +struct kvm_debug_exit_arch { + __u32 exception; + __u32 pad; + __u64 pc; + __u64 dr6; + __u64 dr7; +}; + +#define KVM_GUESTDBG_USE_SW_BP 0x00010000 +#define KVM_GUESTDBG_USE_HW_BP 0x00020000 +#define KVM_GUESTDBG_INJECT_DB 0x00040000 +#define KVM_GUESTDBG_INJECT_BP 0x00080000 + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { + __u64 debugreg[8]; +}; + struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; + +struct kvm_reinject_control { + __u8 pit_reinject; + __u8 reserved[31]; +}; #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 730843d..f0faf58 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -22,6 +22,7 @@ #include <asm/pvclock-abi.h> #include <asm/desc.h> #include <asm/mtrr.h> +#include <asm/msr-index.h> #define KVM_MAX_VCPUS 16 #define KVM_MEMORY_SLOTS 32 @@ -134,11 +135,18 @@ enum { #define KVM_NR_MEM_OBJS 40 -struct kvm_guest_debug { - int enabled; - unsigned long bp[4]; - int singlestep; -}; +#define KVM_NR_DB_REGS 4 + +#define DR6_BD (1 << 13) +#define DR6_BS (1 << 14) +#define DR6_FIXED_1 0xffff0ff0 +#define DR6_VOLATILE 0x0000e00f + +#define DR7_BP_EN_MASK 0x000000ff +#define DR7_GE (1 << 9) +#define DR7_GD (1 << 13) +#define DR7_FIXED_1 0x00000400 +#define DR7_VOLATILE 0xffff23ff /* * We don't want allocation failures within the mmu code, so we preallocate @@ -162,7 +170,8 @@ struct kvm_pte_chain { * bits 0:3 - total guest paging levels (2-4, or zero for real mode) * bits 4:7 - page table level for this shadow (1-4) * bits 8:9 - page table quadrant for 2-level guests - * bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode) + * bit 16 - direct mapping of virtual to physical mapping at gfn + * used for real mode and two-dimensional paging * bits 17:19 - common access permissions for all ptes in this shadow page */ union kvm_mmu_page_role { @@ -172,9 +181,10 @@ union kvm_mmu_page_role { unsigned level:4; unsigned quadrant:2; unsigned pad_for_nice_hex_output:6; - unsigned metaphysical:1; + unsigned direct:1; unsigned access:3; unsigned invalid:1; + unsigned cr4_pge:1; }; }; @@ -218,6 +228,18 @@ struct kvm_pv_mmu_op_buffer { char buf[512] __aligned(sizeof(long)); }; +struct kvm_pio_request { + unsigned long count; + int cur_count; + gva_t guest_gva; + int in; + int port; + int size; + int string; + int down; + int rep; +}; + /* * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level * 32-bit). The kvm_mmu structure abstracts the details of the current mmu @@ -236,6 +258,7 @@ struct kvm_mmu { hpa_t root_hpa; int root_level; int shadow_root_level; + union kvm_mmu_page_role base_role; u64 *pae_root; }; @@ -258,6 +281,7 @@ struct kvm_vcpu_arch { unsigned long cr3; unsigned long cr4; unsigned long cr8; + u32 hflags; u64 pdptrs[4]; /* pae */ u64 shadow_efer; u64 apic_base; @@ -338,6 +362,15 @@ struct kvm_vcpu_arch { struct mtrr_state_type mtrr_state; u32 pat; + + int switch_db_regs; + unsigned long host_db[KVM_NR_DB_REGS]; + unsigned long host_dr6; + unsigned long host_dr7; + unsigned long db[KVM_NR_DB_REGS]; + unsigned long dr6; + unsigned long dr7; + unsigned long eff_db[KVM_NR_DB_REGS]; }; struct kvm_mem_alias { @@ -378,6 +411,7 @@ struct kvm_arch{ unsigned long irq_sources_bitmap; unsigned long irq_states[KVM_IOAPIC_NUM_PINS]; + u64 vm_init_tsc; }; struct kvm_vm_stat { @@ -446,8 +480,7 @@ struct kvm_x86_ops { void (*vcpu_put)(struct kvm_vcpu *vcpu); int (*set_guest_debug)(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg); - void (*guest_debug_pre)(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); @@ -583,16 +616,12 @@ 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, u32 error_code); -void kvm_pic_set_irq(void *opaque, int irq, int level); +int kvm_pic_set_irq(void *opaque, int irq, int level); void kvm_inject_nmi(struct kvm_vcpu *vcpu); void fx_init(struct kvm_vcpu *vcpu); -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); int emulator_write_emulated(unsigned long addr, const void *val, unsigned int bytes, @@ -737,6 +766,10 @@ enum { TASK_SWITCH_GATE = 3, }; +#define HF_GIF_MASK (1 << 0) +#define HF_HIF_MASK (1 << 1) +#define HF_VINTR_MASK (1 << 2) + /* * Hardware virtualization extension instructions may fault if a * reboot turns off virtualization while processes are running. diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 4389442..faae199 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -5,7 +5,6 @@ #define LHCALL_FLUSH_ASYNC 0 #define LHCALL_LGUEST_INIT 1 #define LHCALL_SHUTDOWN 2 -#define LHCALL_LOAD_GDT 3 #define LHCALL_NEW_PGTABLE 4 #define LHCALL_FLUSH_TLB 5 #define LHCALL_LOAD_IDT_ENTRY 6 @@ -17,6 +16,7 @@ #define LHCALL_SET_PMD 15 #define LHCALL_LOAD_TLS 16 #define LHCALL_NOTIFY 17 +#define LHCALL_LOAD_GDT_ENTRY 18 #define LGUEST_TRAP_ENTRY 0x1F @@ -26,36 +26,20 @@ #ifndef __ASSEMBLY__ #include <asm/hw_irq.h> +#include <asm/kvm_para.h> /*G:031 But first, how does our Guest contact the Host to ask for privileged * operations? There are two ways: the direct way is to make a "hypercall", * to make requests of the Host Itself. * - * Our hypercall mechanism uses the highest unused trap code (traps 32 and - * above are used by real hardware interrupts). Fifteen hypercalls are + * We use the KVM hypercall mechanism. Eighteen hypercalls are * available: the hypercall number is put in the %eax register, and the - * arguments (when required) are placed in %edx, %ebx and %ecx. If a return + * arguments (when required) are placed in %ebx, %ecx and %edx. If a return * value makes sense, it's returned in %eax. * * Grossly invalid calls result in Sudden Death at the hands of the vengeful * Host, rather than returning failure. This reflects Winston Churchill's * definition of a gentleman: "someone who is only rude intentionally". */ -static inline unsigned long -hcall(unsigned long call, - unsigned long arg1, unsigned long arg2, unsigned long arg3) -{ - /* "int" is the Intel instruction to trigger a trap. */ - asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY) - /* The call in %eax (aka "a") might be overwritten */ - : "=a"(call) - /* The arguments are in %eax, %edx, %ebx & %ecx */ - : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3) - /* "memory" means this might write somewhere in memory. - * This isn't true for all calls, but it's safe to tell - * gcc that it might happen so it doesn't get clever. */ - : "memory"); - return call; -} /*:*/ /* Can't use our min() macro here: needs to be a constant */ @@ -64,7 +48,7 @@ hcall(unsigned long call, #define LHCALL_RING_SIZE 64 struct hcall_args { /* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */ - unsigned long arg0, arg2, arg3, arg1; + unsigned long arg0, arg1, arg2, arg3; }; #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2dbd231..ec41fc1 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -18,11 +18,15 @@ #define _EFER_LME 8 /* Long mode enable */ #define _EFER_LMA 10 /* Long mode active (read-only) */ #define _EFER_NX 11 /* No execute enable */ +#define _EFER_SVME 12 /* Enable virtualization */ +#define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ #define EFER_SCE (1<<_EFER_SCE) #define EFER_LME (1<<_EFER_LME) #define EFER_LMA (1<<_EFER_LMA) #define EFER_NX (1<<_EFER_NX) +#define EFER_SVME (1<<_EFER_SVME) +#define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ #define MSR_IA32_PERFCTR0 0x000000c1 @@ -365,4 +369,9 @@ #define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b #define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c +/* AMD-V MSRs */ + +#define MSR_VM_CR 0xc0010114 +#define MSR_VM_HSAVE_PA 0xc0010117 + #endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7727aa8..378e369 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -347,7 +347,7 @@ struct pv_mmu_ops { /* Sometimes the physical address is a pfn, and sometimes its an mfn. We can tell which is which from the index. */ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, - unsigned long phys, pgprot_t flags); + phys_addr_t phys, pgprot_t flags); }; struct raw_spinlock; @@ -1432,7 +1432,7 @@ static inline void arch_leave_lazy_mmu_mode(void) void arch_flush_lazy_mmu_mode(void); static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { pv_mmu_ops.set_fixmap(idx, phys, flags); } diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h index 2cd07b9..7af14e5 100644 --- a/arch/x86/include/asm/pat.h +++ b/arch/x86/include/asm/pat.h @@ -18,9 +18,5 @@ extern int free_memtype(u64 start, u64 end); extern int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flag); -extern void map_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); -extern void unmap_devmem(unsigned long pfn, unsigned long size, - struct pgprot vma_prot); #endif /* _ASM_X86_PAT_H */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index a977de2..b51a1e8 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -86,12 +86,43 @@ static inline void early_quirks(void) { } extern void pci_iommu_alloc(void); -#endif /* __KERNEL__ */ +/* MSI arch hook */ +#define arch_setup_msi_irqs arch_setup_msi_irqs + +#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) + +#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG) + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) -#ifdef CONFIG_X86_32 -# include "pci_32.h" #else -# include "pci_64.h" + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; +#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) +#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + do { break; } while (pci_unmap_len(PTR, LEN_NAME)) + +#endif + +#endif /* __KERNEL__ */ + +#ifdef CONFIG_X86_64 +#include "pci_64.h" #endif /* implement the pci_ DMA API in terms of the generic device dma_ one */ @@ -109,11 +140,6 @@ static inline int __pcibus_to_node(const struct pci_bus *bus) return sd->node; } -static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus) -{ - return node_to_cpumask(__pcibus_to_node(bus)); -} - static inline const struct cpumask * cpumask_of_pcibus(const struct pci_bus *bus) { diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h deleted file mode 100644 index 6f1213a..0000000 --- a/arch/x86/include/asm/pci_32.h +++ /dev/null @@ -1,34 +0,0 @@ -#ifndef _ASM_X86_PCI_32_H -#define _ASM_X86_PCI_32_H - - -#ifdef __KERNEL__ - - -/* Dynamic DMA mapping stuff. - * i386 has everything mapped statically. - */ - -struct pci_dev; - -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions. - */ -#define PCI_DMA_BUS_IS_PHYS (1) - -/* pci_unmap_{page,single} is a nop so... */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) dma_addr_t ADDR_NAME[0]; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0]; -#define pci_unmap_addr(PTR, ADDR_NAME) sizeof((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - do { break; } while (pci_unmap_addr(PTR, ADDR_NAME)) -#define pci_unmap_len(PTR, LEN_NAME) sizeof((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - do { break; } while (pci_unmap_len(PTR, LEN_NAME)) - - -#endif /* __KERNEL__ */ - - -#endif /* _ASM_X86_PCI_32_H */ diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h index 4da2079..ae5e40f 100644 --- a/arch/x86/include/asm/pci_64.h +++ b/arch/x86/include/asm/pci_64.h @@ -24,28 +24,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn, extern void dma32_reserve_bootmem(void); -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions - * - * On AMD64 it mostly equals, but we set it to zero if a hardware - * IOMMU (gart) of sotware IOMMU (swiotlb) is available. - */ -#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - #endif /* __KERNEL__ */ #endif /* _ASM_X86_PCI_64_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ae85a8d..fcf4d92 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -94,7 +94,7 @@ struct cpuinfo_x86 { unsigned long loops_per_jiffy; #ifdef CONFIG_SMP /* cpus sharing the last level cache: */ - cpumask_t llc_shared_map; + cpumask_var_t llc_shared_map; #endif /* cpuid returned max cores value: */ u16 x86_max_cores; @@ -352,6 +352,11 @@ struct i387_soft_struct { u32 entry_eip; }; +struct ymmh_struct { + /* 16 * 16 bytes for each YMMH-reg = 256 bytes */ + u32 ymmh_space[64]; +}; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -361,6 +366,7 @@ struct xsave_hdr_struct { struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; + struct ymmh_struct ymmh; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); @@ -736,6 +742,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx) extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx); extern void select_idle_routine(const struct cpuinfo_x86 *c); +extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h index 8e0f8d1..8672303 100644 --- a/arch/x86/include/asm/ptrace-abi.h +++ b/arch/x86/include/asm/ptrace-abi.h @@ -80,8 +80,6 @@ #define PTRACE_SINGLEBLOCK 33 /* resume execution until next branch */ -#ifdef CONFIG_X86_PTRACE_BTS - #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -140,6 +138,5 @@ struct ptrace_bts_config { BTS records are read from oldest to newest. Returns number of BTS records drained. */ -#endif /* CONFIG_X86_PTRACE_BTS */ #endif /* _ASM_X86_PTRACE_ABI_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index d5cd6c5..a4737dd 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -50,7 +50,7 @@ #ifdef CONFIG_X86_64 #define NEED_PSE 0 #define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) -#define NEED_PGE (1<<(X86_FEATURE_PGE & 31)) +#define NEED_PGE 0 #define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) #define NEED_XMM (1<<(X86_FEATURE_XMM & 31)) #define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31)) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index fbf0521..bdc2ada 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -64,7 +64,7 @@ extern void x86_quirk_time_init(void); #include <asm/bootparam.h> /* Interrupt control for vSMPowered x86_64 systems */ -#ifdef CONFIG_X86_VSMP +#ifdef CONFIG_X86_64 void vsmp_init(void); #else static inline void vsmp_init(void) { } diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h index ec66649..72e5a44 100644 --- a/arch/x86/include/asm/sigcontext.h +++ b/arch/x86/include/asm/sigcontext.h @@ -269,6 +269,11 @@ struct _xsave_hdr { __u64 reserved2[5]; }; +struct _ymmh_state { + /* 16 * 16 bytes for each YMMH-reg */ + __u32 ymmh_space[64]; +}; + /* * Extended state pointed by the fpstate pointer in the sigcontext. * In addition to the fpstate, information encoded in the xstate_hdr @@ -278,6 +283,7 @@ struct _xsave_hdr { struct _xstate { struct _fpstate fpstate; struct _xsave_hdr xstate_hdr; + struct _ymmh_state ymmh; /* new processor state extensions go here */ }; diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 47d0e21..19e0d88 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,19 +21,19 @@ extern int smp_num_siblings; extern unsigned int num_processors; -DECLARE_PER_CPU(cpumask_t, cpu_sibling_map); -DECLARE_PER_CPU(cpumask_t, cpu_core_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map); +DECLARE_PER_CPU(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU(u16, cpu_llc_id); DECLARE_PER_CPU(int, cpu_number); static inline struct cpumask *cpu_sibling_mask(int cpu) { - return &per_cpu(cpu_sibling_map, cpu); + return per_cpu(cpu_sibling_map, cpu); } static inline struct cpumask *cpu_core_mask(int cpu) { - return &per_cpu(cpu_core_map, cpu); + return per_cpu(cpu_core_map, cpu); } DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid); @@ -121,9 +121,10 @@ static inline void arch_send_call_function_single_ipi(int cpu) smp_ops.send_call_func_single_ipi(cpu); } -static inline void arch_send_call_function_ipi(cpumask_t mask) +#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask +static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) { - smp_ops.send_call_func_ipi(&mask); + smp_ops.send_call_func_ipi(mask); } void cpu_disable_common(void); diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h index 8ab9cc8..ca8bf2c 100644 --- a/arch/x86/include/asm/socket.h +++ b/arch/x86/include/asm/socket.h @@ -54,4 +54,7 @@ #define SO_MARK 36 +#define SO_TIMESTAMPING 37 +#define SCM_TIMESTAMPING SO_TIMESTAMPING + #endif /* _ASM_X86_SOCKET_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 3a56966..e5e6caf 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -295,6 +295,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory"); } +#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock) +#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock) + #define _raw_spin_relax(lock) cpu_relax() #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index a5074bd..48dcfa6 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -24,28 +24,4 @@ struct saved_context { unsigned long return_address; } __attribute__((packed)); -#ifdef CONFIG_ACPI -extern unsigned long saved_eip; -extern unsigned long saved_esp; -extern unsigned long saved_ebp; -extern unsigned long saved_ebx; -extern unsigned long saved_esi; -extern unsigned long saved_edi; - -static inline void acpi_save_register_state(unsigned long return_point) -{ - saved_eip = return_point; - asm volatile("movl %%esp,%0" : "=m" (saved_esp)); - asm volatile("movl %%ebp,%0" : "=m" (saved_ebp)); - asm volatile("movl %%ebx,%0" : "=m" (saved_ebx)); - asm volatile("movl %%edi,%0" : "=m" (saved_edi)); - asm volatile("movl %%esi,%0" : "=m" (saved_esi)); -} - -#define acpi_restore_register_state() do {} while (0) - -/* routines for saving/restoring kernel state */ -extern int acpi_save_state_mem(void); -#endif - #endif /* _ASM_X86_SUSPEND_32_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 1b8afa7..82ada75 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -174,10 +174,6 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CPUID_FEATURE_SHIFT 2 #define SVM_CPUID_FUNC 0x8000000a -#define MSR_EFER_SVME_MASK (1ULL << 12) -#define MSR_VM_CR 0xc0010114 -#define MSR_VM_HSAVE_PA 0xc0010117ULL - #define SVM_VM_CR_SVM_DISABLE 4 #define SVM_SELECTOR_S_SHIFT 4 diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index ffb08be..72a6dcd 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -70,8 +70,6 @@ struct old_utsname; asmlinkage long sys32_olduname(struct oldold_utsname __user *); long sys32_uname(struct old_utsname __user *); -long sys32_ustat(unsigned, struct ustat32 __user *); - asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index df9d5f7..8820a73 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -94,6 +94,7 @@ struct thread_info { #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_DEBUGCTLMSR 25 /* uses thread_struct.debugctlmsr */ #define TIF_DS_AREA_MSR 26 /* uses thread_struct.ds_area_msr */ +#define TIF_SYSCALL_FTRACE 27 /* for ftrace syscall instrumentation */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) @@ -115,15 +116,17 @@ struct thread_info { #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_DEBUGCTLMSR (1 << TIF_DEBUGCTLMSR) #define _TIF_DS_AREA_MSR (1 << TIF_DS_AREA_MSR) +#define _TIF_SYSCALL_FTRACE (1 << TIF_SYSCALL_FTRACE) /* work to do in syscall_trace_enter() */ #define _TIF_WORK_SYSCALL_ENTRY \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \ + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE | \ _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP) /* work to do in syscall_trace_leave() */ #define _TIF_WORK_SYSCALL_EXIT \ - (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP) + (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP | \ + _TIF_SYSCALL_FTRACE) /* work to do on interrupt/exception return */ #define _TIF_WORK_MASK \ @@ -132,7 +135,7 @@ struct thread_info { _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU)) /* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP) +#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE) /* Only used for 64 bit */ #define _TIF_DO_NOTIFY_MASK \ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h index a81195e..bd37ed4 100644 --- a/arch/x86/include/asm/timer.h +++ b/arch/x86/include/asm/timer.h @@ -12,9 +12,9 @@ unsigned long native_calibrate_tsc(void); #ifdef CONFIG_X86_32 extern int timer_ack; -extern int recalibrate_cpu_khz(void); extern irqreturn_t timer_interrupt(int irq, void *dev_id); #endif /* CONFIG_X86_32 */ +extern int recalibrate_cpu_khz(void); extern int no_timer_check; diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 77cfb2c..892b119 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -44,9 +44,6 @@ #ifdef CONFIG_X86_32 -/* Mappings between node number and cpus on that node. */ -extern cpumask_t node_to_cpumask_map[]; - /* Mappings between logical cpu number and node number */ extern int cpu_to_node_map[]; @@ -57,30 +54,8 @@ static inline int cpu_to_node(int cpu) } #define early_cpu_to_node(cpu) cpu_to_node(cpu) -/* Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * cpumask_of_node function should be used whenever possible. - */ -static inline cpumask_t node_to_cpumask(int node) -{ - return node_to_cpumask_map[node]; -} - -/* Returns a bitmask of CPUs on Node 'node'. */ -static inline const struct cpumask *cpumask_of_node(int node) -{ - return &node_to_cpumask_map[node]; -} - -static inline void setup_node_to_cpumask_map(void) { } - #else /* CONFIG_X86_64 */ -/* Mappings between node number and cpus on that node. */ -extern cpumask_t *node_to_cpumask_map; - /* Mappings between logical cpu number and node number */ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); @@ -91,8 +66,6 @@ DECLARE_PER_CPU(int, node_number); #ifdef CONFIG_DEBUG_PER_CPU_MAPS extern int cpu_to_node(int cpu); extern int early_cpu_to_node(int cpu); -extern const cpumask_t *cpumask_of_node(int node); -extern cpumask_t node_to_cpumask(int node); #else /* !CONFIG_DEBUG_PER_CPU_MAPS */ @@ -108,42 +81,32 @@ static inline int early_cpu_to_node(int cpu) return early_per_cpu(x86_cpu_to_node_map, cpu); } -/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ -static inline const cpumask_t *cpumask_of_node(int node) -{ - return &node_to_cpumask_map[node]; -} +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +#endif /* CONFIG_X86_64 */ -/* Returns a bitmask of CPUs on Node 'node'. */ -static inline cpumask_t node_to_cpumask(int node) +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +extern const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) { return node_to_cpumask_map[node]; } - -#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ +#endif extern void setup_node_to_cpumask_map(void); /* - * Replace default node_to_cpumask_ptr with optimized version - * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" - */ -#define node_to_cpumask_ptr(v, node) \ - const cpumask_t *v = cpumask_of_node(node) - -#define node_to_cpumask_ptr_next(v, node) \ - v = cpumask_of_node(node) - -#endif /* CONFIG_X86_64 */ - -/* * Returns the number of the node containing Node 'node'. This * architecture is flat, so it is a pretty simple function! */ #define parent_node(node) (node) #define pcibus_to_node(bus) __pcibus_to_node(bus) -#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus) #ifdef CONFIG_X86_32 extern unsigned long node_start_pfn[]; @@ -209,52 +172,24 @@ static inline int early_cpu_to_node(int cpu) return 0; } -static inline const cpumask_t *cpumask_of_node(int node) -{ - return &cpu_online_map; -} -static inline cpumask_t node_to_cpumask(int node) -{ - return cpu_online_map; -} -static inline int node_to_first_cpu(int node) +static inline const struct cpumask *cpumask_of_node(int node) { - return first_cpu(cpu_online_map); + return cpu_online_mask; } static inline void setup_node_to_cpumask_map(void) { } -/* - * Replace default node_to_cpumask_ptr with optimized version - * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)" - */ -#define node_to_cpumask_ptr(v, node) \ - const cpumask_t *v = cpumask_of_node(node) - -#define node_to_cpumask_ptr_next(v, node) \ - v = cpumask_of_node(node) #endif #include <asm-generic/topology.h> -#ifdef CONFIG_NUMA -/* Returns the number of the first CPU on Node 'node'. */ -static inline int node_to_first_cpu(int node) -{ - return cpumask_first(cpumask_of_node(node)); -} -#endif - -extern cpumask_t cpu_coregroup_map(int cpu); extern const struct cpumask *cpu_coregroup_mask(int cpu); #ifdef ENABLE_TOPO_DEFINES #define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) -#define topology_core_siblings(cpu) (per_cpu(cpu_core_map, cpu)) -#define topology_thread_siblings(cpu) (per_cpu(cpu_sibling_map, cpu)) -#define topology_core_cpumask(cpu) (&per_cpu(cpu_core_map, cpu)) -#define topology_thread_cpumask(cpu) (&per_cpu(cpu_sibling_map, cpu)) +#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) /* indicates that pointers to the topology cpumask_t maps are valid */ #define arch_provides_topology_pointers yes @@ -268,7 +203,7 @@ struct pci_bus; void set_pci_bus_resources_arch_default(struct pci_bus *b); #ifdef CONFIG_SMP -#define mc_capable() (cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids) +#define mc_capable() (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids) #define smt_capable() (smp_num_siblings > 1) #endif diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index f2bba78..6e72d74 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -338,6 +338,8 @@ #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 +#define __NR_preadv 333 +#define __NR_pwritev 334 #ifdef __KERNEL__ diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index d2e415e..f818294 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3) __SYSCALL(__NR_pipe2, sys_pipe2) #define __NR_inotify_init1 294 __SYSCALL(__NR_inotify_init1, sys_inotify_init1) +#define __NR_preadv 295 +__SYSCALL(__NR_preadv, sys_preadv) +#define __NR_pwritev 296 +__SYSCALL(__NR_pwritev, sys_pwritev) #ifndef __NO_STUBS diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 9f4dfba..d3a98ea 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -11,11 +11,13 @@ #ifndef _ASM_X86_UV_UV_HUB_H #define _ASM_X86_UV_UV_HUB_H +#ifdef CONFIG_X86_64 #include <linux/numa.h> #include <linux/percpu.h> #include <linux/timer.h> #include <asm/types.h> #include <asm/percpu.h> +#include <asm/uv/uv_mmrs.h> /* @@ -397,6 +399,7 @@ static inline void uv_set_scir_bits(unsigned char value) uv_write_local_mmr8(uv_hub_info->scir.offset, value); } } + static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) { if (uv_cpu_hub_info(cpu)->scir.state != value) { @@ -405,4 +408,15 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value) } } +static inline void uv_hub_send_ipi(int pnode, int apicid, int vector) +{ + unsigned long val; + + val = (1UL << UVH_IPI_INT_SEND_SHFT) | + ((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) | + (vector << UVH_IPI_INT_VECTOR_SHFT); + uv_write_global_mmr64(pnode, UVH_IPI_INT, val); +} + +#endif /* CONFIG_X86_64 */ #endif /* _ASM_X86_UV_UV_HUB_H */ diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index dd62779..2cae46c 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -1,3 +1,4 @@ + /* * This file is subject to the terms and conditions of the GNU General Public * License. See the file "COPYING" in the main directory of this archive @@ -16,6 +17,11 @@ /* ========================================================================= */ /* UVH_BAU_DATA_CONFIG */ /* ========================================================================= */ +#define UVH_LB_BAU_MISC_CONTROL 0x320170UL +#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL +/* 1011 timebase 7 (168millisec) * 3 ticks -> 500ms */ #define UVH_BAU_DATA_CONFIG 0x61680UL #define UVH_BAU_DATA_CONFIG_32 0x0438 @@ -243,6 +249,158 @@ union uvh_event_occurred0_u { #define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0 /* ========================================================================= */ +/* UVH_GR0_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL + +#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR0_TLB_INT0_CONFIG_P_SHFT 13 +#define UVH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR0_TLB_INT0_CONFIG_T_SHFT 15 +#define UVH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR0_TLB_INT0_CONFIG_M_SHFT 16 +#define UVH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr0_tlb_int0_config_u { + unsigned long v; + struct uvh_gr0_tlb_int0_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR0_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL + +#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR0_TLB_INT1_CONFIG_P_SHFT 13 +#define UVH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR0_TLB_INT1_CONFIG_T_SHFT 15 +#define UVH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR0_TLB_INT1_CONFIG_M_SHFT 16 +#define UVH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr0_tlb_int1_config_u { + unsigned long v; + struct uvh_gr0_tlb_int1_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL + +#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR1_TLB_INT0_CONFIG_P_SHFT 13 +#define UVH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR1_TLB_INT0_CONFIG_T_SHFT 15 +#define UVH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR1_TLB_INT0_CONFIG_M_SHFT 16 +#define UVH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr1_tlb_int0_config_u { + unsigned long v; + struct uvh_gr1_tlb_int0_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL + +#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_GR1_TLB_INT1_CONFIG_P_SHFT 13 +#define UVH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_GR1_TLB_INT1_CONFIG_T_SHFT 15 +#define UVH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_GR1_TLB_INT1_CONFIG_M_SHFT 16 +#define UVH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + +union uvh_gr1_tlb_int1_config_u { + unsigned long v; + struct uvh_gr1_tlb_int1_config_s { + unsigned long vector_ : 8; /* RW */ + unsigned long dm : 3; /* RW */ + unsigned long destmode : 1; /* RW */ + unsigned long status : 1; /* RO */ + unsigned long p : 1; /* RO */ + unsigned long rsvd_14 : 1; /* */ + unsigned long t : 1; /* RO */ + unsigned long m : 1; /* RW */ + unsigned long rsvd_17_31: 15; /* */ + unsigned long apic_id : 32; /* RW */ + } s; +}; + +/* ========================================================================= */ /* UVH_INT_CMPB */ /* ========================================================================= */ #define UVH_INT_CMPB 0x22080UL diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 5936362..e0f9aa1 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -118,7 +118,7 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~MSR_EFER_SVME_MASK); + wrmsrl(MSR_EFER, efer & ~EFER_SVME); } /** Makes sure SVM is disabled, if it is supported on the CPU diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index d0238e6..498f944 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -270,8 +270,9 @@ enum vmcs_field { #define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ #define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ -#define INTR_TYPE_EXCEPTION (3 << 8) /* processor exception */ +#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ #define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ +#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 @@ -311,7 +312,7 @@ enum vmcs_field { #define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */ #define TYPE_MOV_TO_DR (0 << 4) #define TYPE_MOV_FROM_DR (1 << 4) -#define DEBUG_REG_ACCESS_REG 0xf00 /* 11:8, general purpose reg. */ +#define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ /* segment AR */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 1a918dd..018a0a4 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -124,7 +124,8 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) /* VIRT <-> MACHINE conversion */ #define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) -#define virt_to_mfn(v) (pfn_to_mfn(PFN_DOWN(__pa(v)))) +#define virt_to_pfn(v) (PFN_DOWN(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) #define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) static inline unsigned long pte_mfn(pte_t pte) diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 08e9a1a..727acc1 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -7,6 +7,7 @@ #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 #define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) @@ -15,7 +16,7 @@ /* * These are the features that the OS can handle currently. */ -#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE) +#define XCNTXT_MASK (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 339ce35..145cce7 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -66,11 +66,11 @@ obj-$(CONFIG_X86_MPPARSE) += mpparse.o obj-y += apic/ obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups_32.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o -obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o +obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_KEXEC) += machine_kexec_$(BITS).o obj-$(CONFIG_KEXEC) += relocate_kernel_$(BITS).o crash.o obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o -obj-$(CONFIG_X86_VSMP) += vsmp_64.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_MODULES) += module_$(BITS).o obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o @@ -106,7 +106,7 @@ obj-$(CONFIG_MICROCODE) += microcode.o obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o -obj-$(CONFIG_SWIOTLB) += pci-swiotlb_64.o # NB rename without _64 +obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o ### # 64 bit specific files @@ -120,4 +120,5 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_AMD_IOMMU) += amd_iommu_init.o amd_iommu.o obj-$(CONFIG_PCI_MMCONFIG) += mmconf-fam10h_64.o + obj-y += vsmp_64.o endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index a18eb7c..723989d 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -230,6 +230,35 @@ static void __cpuinit acpi_register_lapic(int id, u8 enabled) } static int __init +acpi_parse_x2apic(struct acpi_subtable_header *header, const unsigned long end) +{ + struct acpi_madt_local_x2apic *processor = NULL; + + processor = (struct acpi_madt_local_x2apic *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + +#ifdef CONFIG_X86_X2APIC + /* + * We need to register disabled CPU as well to permit + * counting disabled CPUs. This allows us to size + * cpus_possible_map more accurately, to permit + * to not preallocating memory for all NR_CPUS + * when we use CPU hotplug. + */ + acpi_register_lapic(processor->local_apic_id, /* APIC ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); +#else + printk(KERN_WARNING PREFIX "x2apic entry ignored\n"); +#endif + + return 0; +} + +static int __init acpi_parse_lapic(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_local_apic *processor = NULL; @@ -289,6 +318,25 @@ acpi_parse_lapic_addr_ovr(struct acpi_subtable_header * header, } static int __init +acpi_parse_x2apic_nmi(struct acpi_subtable_header *header, + const unsigned long end) +{ + struct acpi_madt_local_x2apic_nmi *x2apic_nmi = NULL; + + x2apic_nmi = (struct acpi_madt_local_x2apic_nmi *)header; + + if (BAD_MADT_ENTRY(x2apic_nmi, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + if (x2apic_nmi->lint != 1) + printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + + return 0; +} + +static int __init acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long end) { struct acpi_madt_local_apic_nmi *lapic_nmi = NULL; @@ -793,6 +841,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) static int __init acpi_parse_madt_lapic_entries(void) { int count; + int x2count = 0; if (!cpu_has_apic) return -ENODEV; @@ -816,22 +865,28 @@ static int __init acpi_parse_madt_lapic_entries(void) count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, acpi_parse_sapic, MAX_APICS); - if (!count) + if (!count) { + x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, + acpi_parse_x2apic, MAX_APICS); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_parse_lapic, MAX_APICS); - if (!count) { + } + if (!count && !x2count) { printk(KERN_ERR PREFIX "No LAPIC entries present\n"); /* TBD: Cleanup to allow fallback to MPS */ return -ENODEV; - } else if (count < 0) { + } else if (count < 0 || x2count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; } + x2count = + acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC_NMI, + acpi_parse_x2apic_nmi, 0); count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0); - if (count < 0) { + if (count < 0 || x2count < 0) { printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); /* TBD: Cleanup to allow fallback to MPS */ return count; @@ -1470,7 +1525,7 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d) /* * If your system is blacklisted here, but you find that acpi=force - * works for you, please contact acpi-devel@sourceforge.net + * works for you, please contact linux-acpi@vger.kernel.org */ static struct dmi_system_id __initdata acpi_dmi_table[] = { /* diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4c80f15..f576587 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -5,6 +5,7 @@ #include <linux/kprobes.h> #include <linux/mm.h> #include <linux/vmalloc.h> +#include <linux/memory.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -12,7 +13,9 @@ #include <asm/nmi.h> #include <asm/vsyscall.h> #include <asm/cacheflush.h> +#include <asm/tlbflush.h> #include <asm/io.h> +#include <asm/fixmap.h> #define MAX_PATCH_LEN (255-1) @@ -226,6 +229,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) { u8 **ptr; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -234,6 +238,7 @@ static void alternatives_smp_lock(u8 **start, u8 **end, u8 *text, u8 *text_end) /* turn DS segment override prefix into lock prefix */ text_poke(*ptr, ((unsigned char []){0xf0}), 1); }; + mutex_unlock(&text_mutex); } static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end) @@ -243,6 +248,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end if (noreplace_smp) return; + mutex_lock(&text_mutex); for (ptr = start; ptr < end; ptr++) { if (*ptr < text) continue; @@ -251,6 +257,7 @@ static void alternatives_smp_unlock(u8 **start, u8 **end, u8 *text, u8 *text_end /* turn lock prefix into DS segment override prefix */ text_poke(*ptr, ((unsigned char []){0x3E}), 1); }; + mutex_unlock(&text_mutex); } struct smp_alt_module { @@ -500,15 +507,16 @@ void *text_poke_early(void *addr, const void *opcode, size_t len) * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. + * + * Note: Must be called under text_mutex. */ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) { + unsigned long flags; char *vaddr; - int nr_pages = 2; struct page *pages[2]; int i; - might_sleep(); if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -518,18 +526,21 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) pages[1] = virt_to_page(addr + PAGE_SIZE); } BUG_ON(!pages[0]); - if (!pages[1]) - nr_pages = 1; - vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); - BUG_ON(!vaddr); - local_irq_disable(); + local_irq_save(flags); + set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0])); + if (pages[1]) + set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1])); + vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0); memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len); - local_irq_enable(); - vunmap(vaddr); + clear_fixmap(FIX_TEXT_POKE0); + if (pages[1]) + clear_fixmap(FIX_TEXT_POKE1); + local_flush_tlb(); sync_core(); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ for (i = 0; i < len; i++) BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]); + local_irq_restore(flags); return addr; } diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 5113c08..a97db99 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -22,10 +22,9 @@ #include <linux/bitops.h> #include <linux/debugfs.h> #include <linux/scatterlist.h> +#include <linux/dma-mapping.h> #include <linux/iommu-helper.h> -#ifdef CONFIG_IOMMU_API #include <linux/iommu.h> -#endif #include <asm/proto.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -1297,8 +1296,10 @@ static void __unmap_single(struct amd_iommu *iommu, /* * The exported map_single function for dma_ops. */ -static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, - size_t size, int dir) +static dma_addr_t map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1306,6 +1307,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr, u16 devid; dma_addr_t addr; u64 dma_mask; + phys_addr_t paddr = page_to_phys(page) + offset; INC_STATS_COUNTER(cnt_map_single); @@ -1340,8 +1342,8 @@ out: /* * The exported unmap_single function for dma_ops. */ -static void unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, int dir) +static void unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size, + enum dma_data_direction dir, struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1390,7 +1392,8 @@ static int map_sg_no_iommu(struct device *dev, struct scatterlist *sglist, * lists). */ static int map_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1457,7 +1460,8 @@ unmap: * lists). */ static void unmap_sg(struct device *dev, struct scatterlist *sglist, - int nelems, int dir) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long flags; struct amd_iommu *iommu; @@ -1644,11 +1648,11 @@ static void prealloc_protection_domains(void) } } -static struct dma_mapping_ops amd_iommu_dma_ops = { +static struct dma_map_ops amd_iommu_dma_ops = { .alloc_coherent = alloc_coherent, .free_coherent = free_coherent, - .map_single = map_single, - .unmap_single = unmap_single, + .map_page = map_page, + .unmap_page = unmap_page, .map_sg = map_sg, .unmap_sg = unmap_sg, .dma_supported = amd_iommu_dma_supported, @@ -1924,6 +1928,12 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, return paddr; } +static int amd_iommu_domain_has_cap(struct iommu_domain *domain, + unsigned long cap) +{ + return 0; +} + static struct iommu_ops amd_iommu_ops = { .domain_init = amd_iommu_domain_init, .domain_destroy = amd_iommu_domain_destroy, @@ -1932,5 +1942,6 @@ static struct iommu_ops amd_iommu_ops = { .map = amd_iommu_map_range, .unmap = amd_iommu_unmap_range, .iova_to_phys = amd_iommu_iova_to_phys, + .domain_has_cap = amd_iommu_domain_has_cap, }; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 85eb8e1..f287092 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -431,6 +431,12 @@ static void __cpuinit setup_APIC_timer(void) { struct clock_event_device *levt = &__get_cpu_var(lapic_events); + if (cpu_has(¤t_cpu_data, X86_FEATURE_ARAT)) { + lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP; + /* Make LAPIC timer preferrable over percpu HPET */ + lapic_clockevent.rating = 150; + } + memcpy(levt, &lapic_clockevent, sizeof(*levt)); levt->cpumask = cpumask_of(smp_processor_id()); @@ -1304,6 +1310,7 @@ void __init enable_IR_x2apic(void) #ifdef CONFIG_INTR_REMAP int ret; unsigned long flags; + struct IO_APIC_route_entry **ioapic_entries = NULL; if (!cpu_has_x2apic) return; @@ -1334,17 +1341,23 @@ void __init enable_IR_x2apic(void) return; } - ret = save_IO_APIC_setup(); + ioapic_entries = alloc_ioapic_entries(); + if (!ioapic_entries) { + pr_info("Allocate ioapic_entries failed: %d\n", ret); + goto end; + } + + ret = save_IO_APIC_setup(ioapic_entries); if (ret) { pr_info("Saving IO-APIC state failed: %d\n", ret); goto end; } local_irq_save(flags); - mask_IO_APIC_setup(); + mask_IO_APIC_setup(ioapic_entries); mask_8259A(); - ret = enable_intr_remapping(1); + ret = enable_intr_remapping(EIM_32BIT_APIC_ID); if (ret && x2apic_preenabled) { local_irq_restore(flags); @@ -1364,9 +1377,9 @@ end_restore: /* * IR enabling failed */ - restore_IO_APIC_setup(); + restore_IO_APIC_setup(ioapic_entries); else - reinit_intr_remapped_IO_APIC(x2apic_preenabled); + reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries); unmask_8259A(); local_irq_restore(flags); @@ -1379,6 +1392,8 @@ end: pr_info("Enabled Interrupt-remapping\n"); } else pr_err("Failed to enable Interrupt-remapping and x2apic\n"); + if (ioapic_entries) + free_ioapic_entries(ioapic_entries); #else if (!cpu_has_x2apic) return; @@ -1954,6 +1969,10 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state) local_irq_save(flags); disable_local_APIC(); +#ifdef CONFIG_INTR_REMAP + if (intr_remapping_enabled) + disable_intr_remapping(); +#endif local_irq_restore(flags); return 0; } @@ -1964,15 +1983,41 @@ static int lapic_resume(struct sys_device *dev) unsigned long flags; int maxlvt; +#ifdef CONFIG_INTR_REMAP + int ret; + struct IO_APIC_route_entry **ioapic_entries = NULL; + if (!apic_pm_state.active) return 0; - maxlvt = lapic_get_maxlvt(); - local_irq_save(flags); + if (x2apic) { + ioapic_entries = alloc_ioapic_entries(); + if (!ioapic_entries) { + WARN(1, "Alloc ioapic_entries in lapic resume failed."); + return -ENOMEM; + } + + ret = save_IO_APIC_setup(ioapic_entries); + if (ret) { + WARN(1, "Saving IO-APIC state failed: %d\n", ret); + free_ioapic_entries(ioapic_entries); + return ret; + } + + mask_IO_APIC_setup(ioapic_entries); + mask_8259A(); + enable_x2apic(); + } +#else + if (!apic_pm_state.active) + return 0; + local_irq_save(flags); if (x2apic) enable_x2apic(); +#endif + else { /* * Make sure the APICBASE points to the right address @@ -1986,6 +2031,7 @@ static int lapic_resume(struct sys_device *dev) wrmsr(MSR_IA32_APICBASE, l, h); } + maxlvt = lapic_get_maxlvt(); apic_write(APIC_LVTERR, ERROR_APIC_VECTOR | APIC_LVT_MASKED); apic_write(APIC_ID, apic_pm_state.apic_id); apic_write(APIC_DFR, apic_pm_state.apic_dfr); @@ -2009,8 +2055,20 @@ static int lapic_resume(struct sys_device *dev) apic_write(APIC_ESR, 0); apic_read(APIC_ESR); +#ifdef CONFIG_INTR_REMAP + if (intr_remapping_enabled) + reenable_intr_remapping(EIM_32BIT_APIC_ID); + + if (x2apic) { + unmask_8259A(); + restore_IO_APIC_setup(ioapic_entries); + free_ioapic_entries(ioapic_entries); + } +#endif + local_irq_restore(flags); + return 0; } @@ -2048,7 +2106,9 @@ static int __init init_lapic_sysfs(void) error = sysdev_register(&device_lapic); return error; } -device_initcall(init_lapic_sysfs); + +/* local apic needs to resume before other devices access its registers. */ +core_initcall(init_lapic_sysfs); #else /* CONFIG_PM */ diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f933822..306e5e8 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -159,20 +159,6 @@ static int flat_apic_id_registered(void) return physid_isset(read_xapic_id(), phys_cpu_present_map); } -static unsigned int flat_cpu_mask_to_apicid(const struct cpumask *cpumask) -{ - return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; -} - -static unsigned int flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask, - const struct cpumask *andmask) -{ - unsigned long mask1 = cpumask_bits(cpumask)[0] & APIC_ALL_CPUS; - unsigned long mask2 = cpumask_bits(andmask)[0] & APIC_ALL_CPUS; - - return mask1 & mask2; -} - static int flat_phys_pkg_id(int initial_apic_id, int index_msb) { return hard_smp_processor_id() >> index_msb; @@ -213,8 +199,8 @@ struct apic apic_flat = { .set_apic_id = set_apic_id, .apic_id_mask = 0xFFu << 24, - .cpu_mask_to_apicid = flat_cpu_mask_to_apicid, - .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .cpu_mask_to_apicid = default_cpu_mask_to_apicid, + .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, @@ -226,7 +212,7 @@ struct apic apic_flat = { .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, .smp_callin_clear_local_apic = NULL, - .inquire_remote_apic = NULL, + .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, .write = native_apic_mem_write, @@ -376,7 +362,7 @@ struct apic apic_physflat = { .trampoline_phys_high = DEFAULT_TRAMPOLINE_PHYS_HIGH, .wait_for_init_deassert = NULL, .smp_callin_clear_local_apic = NULL, - .inquire_remote_apic = NULL, + .inquire_remote_apic = default_inquire_remote_apic, .read = native_apic_mem_read, .write = native_apic_mem_write, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index d806eca..676cdac 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -26,12 +26,12 @@ static int bigsmp_apic_id_registered(void) return 1; } -static const cpumask_t *bigsmp_target_cpus(void) +static const struct cpumask *bigsmp_target_cpus(void) { #ifdef CONFIG_SMP - return &cpu_online_map; + return cpu_online_mask; #else - return &cpumask_of_cpu(0); + return cpumask_of(0); #endif } @@ -118,9 +118,9 @@ static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid) } /* As we are using single CPU as destination, pick only one CPU here */ -static unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask) { - return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask)); + return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask)); } static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask, @@ -188,10 +188,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = { { } /* NULL entry stops DMI scanning */ }; -static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask) { - cpus_clear(*retmask); - cpu_set(cpu, *retmask); + cpumask_clear(retmask); + cpumask_set_cpu(cpu, retmask); } static int probe_bigsmp(void) diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 19588f2..1c11b81 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -410,7 +410,7 @@ static void es7000_enable_apic_mode(void) WARN(1, "Command failed, status = %x\n", mip_status); } -static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -420,7 +420,8 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } @@ -455,14 +456,14 @@ static int es7000_apic_id_registered(void) return 1; } -static const cpumask_t *target_cpus_cluster(void) +static const struct cpumask *target_cpus_cluster(void) { - return &CPU_MASK_ALL; + return cpu_all_mask; } -static const cpumask_t *es7000_target_cpus(void) +static const struct cpumask *es7000_target_cpus(void) { - return &cpumask_of_cpu(smp_processor_id()); + return cpumask_of(smp_processor_id()); } static unsigned long @@ -517,7 +518,7 @@ static void es7000_setup_apic_routing(void) "Enabling APIC mode: %s. Using %d I/O APICs, target cpus %lx\n", (apic_version[apic] == 0x14) ? "Physical Cluster" : "Logical Cluster", - nr_ioapics, cpus_addr(*es7000_target_cpus())[0]); + nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); } static int es7000_apicid_to_node(int logical_apicid) @@ -572,7 +573,7 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid) return 1; } -static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask) { unsigned int round = 0; int cpu, uninitialized_var(apicid); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 86827d8..a2789e4 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -592,10 +592,12 @@ set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask) if (assign_irq_vector(irq, cfg, mask)) return BAD_APICID; - cpumask_and(desc->affinity, cfg->domain, mask); + /* check that before desc->addinity get updated */ set_extra_move_desc(desc, mask); - return apic->cpu_mask_to_apicid_and(desc->affinity, cpu_online_mask); + cpumask_copy(desc->affinity, mask); + + return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain); } static void @@ -849,63 +851,74 @@ __setup("pirq=", ioapic_pirq_setup); #endif /* CONFIG_X86_32 */ #ifdef CONFIG_INTR_REMAP -/* I/O APIC RTE contents at the OS boot up */ -static struct IO_APIC_route_entry *early_ioapic_entries[MAX_IO_APICS]; +struct IO_APIC_route_entry **alloc_ioapic_entries(void) +{ + int apic; + struct IO_APIC_route_entry **ioapic_entries; + + ioapic_entries = kzalloc(sizeof(*ioapic_entries) * nr_ioapics, + GFP_ATOMIC); + if (!ioapic_entries) + return 0; + + for (apic = 0; apic < nr_ioapics; apic++) { + ioapic_entries[apic] = + kzalloc(sizeof(struct IO_APIC_route_entry) * + nr_ioapic_registers[apic], GFP_ATOMIC); + if (!ioapic_entries[apic]) + goto nomem; + } + + return ioapic_entries; + +nomem: + while (--apic >= 0) + kfree(ioapic_entries[apic]); + kfree(ioapic_entries); + + return 0; +} /* * Saves all the IO-APIC RTE's */ -int save_IO_APIC_setup(void) +int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries) { - union IO_APIC_reg_01 reg_01; - unsigned long flags; int apic, pin; - /* - * The number of IO-APIC IRQ registers (== #pins): - */ - for (apic = 0; apic < nr_ioapics; apic++) { - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(apic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - nr_ioapic_registers[apic] = reg_01.bits.entries+1; - } + if (!ioapic_entries) + return -ENOMEM; for (apic = 0; apic < nr_ioapics; apic++) { - early_ioapic_entries[apic] = - kzalloc(sizeof(struct IO_APIC_route_entry) * - nr_ioapic_registers[apic], GFP_KERNEL); - if (!early_ioapic_entries[apic]) - goto nomem; - } + if (!ioapic_entries[apic]) + return -ENOMEM; - for (apic = 0; apic < nr_ioapics; apic++) for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) - early_ioapic_entries[apic][pin] = + ioapic_entries[apic][pin] = ioapic_read_entry(apic, pin); + } return 0; - -nomem: - while (apic >= 0) - kfree(early_ioapic_entries[apic--]); - memset(early_ioapic_entries, 0, - ARRAY_SIZE(early_ioapic_entries)); - - return -ENOMEM; } -void mask_IO_APIC_setup(void) +/* + * Mask all IO APIC entries. + */ +void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries) { int apic, pin; + if (!ioapic_entries) + return; + for (apic = 0; apic < nr_ioapics; apic++) { - if (!early_ioapic_entries[apic]) + if (!ioapic_entries[apic]) break; + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { struct IO_APIC_route_entry entry; - entry = early_ioapic_entries[apic][pin]; + entry = ioapic_entries[apic][pin]; if (!entry.mask) { entry.mask = 1; ioapic_write_entry(apic, pin, entry); @@ -914,22 +927,30 @@ void mask_IO_APIC_setup(void) } } -void restore_IO_APIC_setup(void) +/* + * Restore IO APIC entries which was saved in ioapic_entries. + */ +int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries) { int apic, pin; + if (!ioapic_entries) + return -ENOMEM; + for (apic = 0; apic < nr_ioapics; apic++) { - if (!early_ioapic_entries[apic]) - break; + if (!ioapic_entries[apic]) + return -ENOMEM; + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) ioapic_write_entry(apic, pin, - early_ioapic_entries[apic][pin]); - kfree(early_ioapic_entries[apic]); - early_ioapic_entries[apic] = NULL; + ioapic_entries[apic][pin]); } + return 0; } -void reinit_intr_remapped_IO_APIC(int intr_remapping) +void reinit_intr_remapped_IO_APIC(int intr_remapping, + struct IO_APIC_route_entry **ioapic_entries) + { /* * for now plain restore of previous settings. @@ -938,7 +959,17 @@ void reinit_intr_remapped_IO_APIC(int intr_remapping) * table entries. for now, do a plain restore, and wait for * the setup_IO_APIC_irqs() to do proper initialization. */ - restore_IO_APIC_setup(); + restore_IO_APIC_setup(ioapic_entries); +} + +void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries) +{ + int apic; + + for (apic = 0; apic < nr_ioapics; apic++) + kfree(ioapic_entries[apic]); + + kfree(ioapic_entries); } #endif @@ -1428,7 +1459,6 @@ void __setup_vector_irq(int cpu) static struct irq_chip ioapic_chip; static struct irq_chip ir_ioapic_chip; -static struct irq_chip msi_ir_chip; #define IOAPIC_AUTO -1 #define IOAPIC_EDGE 0 @@ -2494,7 +2524,6 @@ static void irq_complete_move(struct irq_desc **descp) static inline void irq_complete_move(struct irq_desc **descp) {} #endif -#ifdef CONFIG_INTR_REMAP static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg) { int apic, pin; @@ -2528,6 +2557,7 @@ eoi_ioapic_irq(struct irq_desc *desc) spin_unlock_irqrestore(&ioapic_lock, flags); } +#ifdef CONFIG_X86_X2APIC static void ack_x2apic_level(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); @@ -2539,7 +2569,6 @@ static void ack_x2apic_edge(unsigned int irq) { ack_x2APIC_irq(); } - #endif static void ack_apic_edge(unsigned int irq) @@ -2605,6 +2634,9 @@ static void ack_apic_level(unsigned int irq) */ ack_APIC_irq(); + if (irq_remapped(irq)) + eoi_ioapic_irq(desc); + /* Now we can move and renable the irq */ if (unlikely(do_unmask_irq)) { /* Only migrate the irq if the ack has been received. @@ -2650,6 +2682,26 @@ static void ack_apic_level(unsigned int irq) #endif } +#ifdef CONFIG_INTR_REMAP +static void ir_ack_apic_edge(unsigned int irq) +{ +#ifdef CONFIG_X86_X2APIC + if (x2apic_enabled()) + return ack_x2apic_edge(irq); +#endif + return ack_apic_edge(irq); +} + +static void ir_ack_apic_level(unsigned int irq) +{ +#ifdef CONFIG_X86_X2APIC + if (x2apic_enabled()) + return ack_x2apic_level(irq); +#endif + return ack_apic_level(irq); +} +#endif /* CONFIG_INTR_REMAP */ + static struct irq_chip ioapic_chip __read_mostly = { .name = "IO-APIC", .startup = startup_ioapic_irq, @@ -2663,20 +2715,20 @@ static struct irq_chip ioapic_chip __read_mostly = { .retrigger = ioapic_retrigger_irq, }; -#ifdef CONFIG_INTR_REMAP static struct irq_chip ir_ioapic_chip __read_mostly = { .name = "IR-IO-APIC", .startup = startup_ioapic_irq, .mask = mask_IO_APIC_irq, .unmask = unmask_IO_APIC_irq, - .ack = ack_x2apic_edge, - .eoi = ack_x2apic_level, +#ifdef CONFIG_INTR_REMAP + .ack = ir_ack_apic_edge, + .eoi = ir_ack_apic_level, #ifdef CONFIG_SMP .set_affinity = set_ir_ioapic_affinity_irq, #endif +#endif .retrigger = ioapic_retrigger_irq, }; -#endif static inline void init_IO_APIC_traps(void) { @@ -3391,18 +3443,18 @@ static struct irq_chip msi_chip = { .retrigger = ioapic_retrigger_irq, }; -#ifdef CONFIG_INTR_REMAP static struct irq_chip msi_ir_chip = { .name = "IR-PCI-MSI", .unmask = unmask_msi_irq, .mask = mask_msi_irq, - .ack = ack_x2apic_edge, +#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, }; -#endif /* * Map the PCI dev to the corresponding remapping hardware unit @@ -3467,6 +3519,10 @@ int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) struct intel_iommu *iommu = NULL; int index = 0; + /* x86 doesn't support multiple MSI yet */ + if (type == PCI_CAP_ID_MSI && nvec > 1) + return 1; + irq_want = nr_irqs_gsi; sub_handle = 0; list_for_each_entry(msidesc, &dev->msi_list, list) { diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c index bdfad80..d6bd624 100644 --- a/arch/x86/kernel/apic/nmi.c +++ b/arch/x86/kernel/apic/nmi.c @@ -39,7 +39,7 @@ int unknown_nmi_panic; int nmi_watchdog_enabled; -static cpumask_t backtrace_mask = CPU_MASK_NONE; +static cpumask_var_t backtrace_mask; /* nmi_active: * >0: the lapic NMI watchdog is active, but can be disabled @@ -138,6 +138,7 @@ int __init check_nmi_watchdog(void) if (!prev_nmi_count) goto error; + alloc_cpumask_var(&backtrace_mask, GFP_KERNEL); printk(KERN_INFO "Testing NMI watchdog ... "); #ifdef CONFIG_SMP @@ -413,14 +414,14 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason) touched = 1; } - if (cpu_isset(cpu, backtrace_mask)) { + if (cpumask_test_cpu(cpu, backtrace_mask)) { static DEFINE_SPINLOCK(lock); /* Serialise the printks */ spin_lock(&lock); printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu); dump_stack(); spin_unlock(&lock); - cpu_clear(cpu, backtrace_mask); + cpumask_clear_cpu(cpu, backtrace_mask); } /* Could check oops_in_progress here too, but it's safer not to */ @@ -554,10 +555,10 @@ void __trigger_all_cpu_backtrace(void) { int i; - backtrace_mask = cpu_online_map; + cpumask_copy(backtrace_mask, cpu_online_mask); /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { - if (cpus_empty(backtrace_mask)) + if (cpumask_empty(backtrace_mask)) break; mdelay(1); } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index ba2fc64..533e59c 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -334,9 +334,9 @@ static inline void numaq_smp_callin_clear_local_apic(void) clear_local_APIC(); } -static inline const cpumask_t *numaq_target_cpus(void) +static inline const struct cpumask *numaq_target_cpus(void) { - return &CPU_MASK_ALL; + return cpu_all_mask; } static inline unsigned long @@ -427,7 +427,7 @@ static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid) * We use physical apicids here, not logical, so just return the default * physical broadcast to stop people from breaking us */ -static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask) { return 0x0F; } @@ -462,7 +462,7 @@ static int probe_numaq(void) return found_numaq; } -static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -472,7 +472,8 @@ static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } static void numaq_setup_portio_remap(void) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 141c99a..01eda2a 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -83,7 +83,8 @@ static void default_vector_allocation_domain(int cpu, struct cpumask *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } /* should be called last. */ diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index aac52fa..9cfe1f4 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -53,23 +53,19 @@ static unsigned summit_get_apic_id(unsigned long x) return (x >> 24) & 0xFF; } -static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector) +static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector) { default_send_IPI_mask_sequence_logical(mask, vector); } static void summit_send_IPI_allbutself(int vector) { - cpumask_t mask = cpu_online_map; - cpu_clear(smp_processor_id(), mask); - - if (!cpus_empty(mask)) - summit_send_IPI_mask(&mask, vector); + default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector); } static void summit_send_IPI_all(int vector) { - summit_send_IPI_mask(&cpu_online_map, vector); + summit_send_IPI_mask(cpu_online_mask, vector); } #include <asm/tsc.h> @@ -186,13 +182,13 @@ static inline int is_WPEG(struct rio_detail *rio){ #define SUMMIT_APIC_DFR_VALUE (APIC_DFR_CLUSTER) -static const cpumask_t *summit_target_cpus(void) +static const struct cpumask *summit_target_cpus(void) { /* CPU_MASK_ALL (0xff) has undefined behaviour with * dest_LowestPrio mode logical clustered apic interrupt routing * Just start on cpu 0. IRQ balancing will spread load */ - return &cpumask_of_cpu(0); + return cpumask_of(0); } static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid) @@ -289,7 +285,7 @@ static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid) return 1; } -static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask) +static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask) { unsigned int round = 0; int cpu, apicid = 0; @@ -346,7 +342,7 @@ static int probe_summit(void) return 0; } -static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) +static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask) { /* Careful. Some cpus do not strictly honor the set of cpus * specified in the interrupt destination when using lowest @@ -356,7 +352,8 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask) * deliver interrupts to the wrong hyperthread when only one * hyperthread was specified in the interrupt desitination. */ - *retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } }; + cpumask_clear(retmask); + cpumask_bits(retmask)[0] = APIC_ALL_CPUS; } #ifdef CONFIG_X86_SUMMIT_NUMA diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1bd6da1..de1a50a 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -118,17 +118,12 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) static void uv_send_IPI_one(int cpu, int vector) { - unsigned long val, apicid; + unsigned long apicid; int pnode; apicid = per_cpu(x86_cpu_to_apicid, cpu); pnode = uv_apicid_to_pnode(apicid); - - val = (1UL << UVH_IPI_INT_SEND_SHFT) | - (apicid << UVH_IPI_INT_APIC_ID_SHFT) | - (vector << UVH_IPI_INT_VECTOR_SHFT); - - uv_write_global_mmr64(pnode, UVH_IPI_INT, val); + uv_hub_send_ipi(pnode, apicid, vector); } static void uv_send_IPI_mask(const struct cpumask *mask, int vector) @@ -554,7 +549,8 @@ void __init uv_system_init(void) unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size; int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val; int max_pnode = 0; - unsigned long mmr_base, present; + unsigned long mmr_base, present, paddr; + unsigned short pnode_mask; map_low_mmrs(); @@ -597,6 +593,7 @@ void __init uv_system_init(void) } } + pnode_mask = (1 << n_val) - 1; node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_upper = (((unsigned long)node_id.s.node_id) & ~((1 << n_val) - 1)) << m_val; @@ -620,7 +617,7 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->numa_blade_id = blade; uv_cpu_hub_info(cpu)->blade_processor_id = lcpu; uv_cpu_hub_info(cpu)->pnode = pnode; - uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1; + uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask; uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1; uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper; uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base; @@ -636,6 +633,16 @@ void __init uv_system_init(void) lcpu, blade); } + /* Add blade/pnode info for nodes without cpus */ + for_each_online_node(nid) { + if (uv_node_to_blade[nid] >= 0) + continue; + paddr = node_start_pfn(nid) << PAGE_SHIFT; + pnode = (paddr >> m_val) & pnode_mask; + blade = boot_pnode_to_blade(pnode); + uv_node_to_blade[nid] = blade; + } + map_gru_high(max_pnode); map_mmr_high(max_pnode); map_config_high(max_pnode); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 10033fe..49e0939 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -466,7 +466,7 @@ static const lookup_t error_table[] = { * @err: APM BIOS return code * * Write a meaningful log entry to the kernel log in the event of - * an APM error. + * an APM error. Note that this also handles (negative) kernel errors. */ static void apm_error(char *str, int err) @@ -478,43 +478,14 @@ static void apm_error(char *str, int err) break; if (i < ERROR_COUNT) printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg); + else if (err < 0) + printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err); else printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n", str, err); } /* - * Lock APM functionality to physical CPU 0 - */ - -#ifdef CONFIG_SMP - -static cpumask_t apm_save_cpus(void) -{ - cpumask_t x = current->cpus_allowed; - /* Some bioses don't like being called from CPU != 0 */ - set_cpus_allowed(current, cpumask_of_cpu(0)); - BUG_ON(smp_processor_id() != 0); - return x; -} - -static inline void apm_restore_cpus(cpumask_t mask) -{ - set_cpus_allowed(current, mask); -} - -#else - -/* - * No CPU lockdown needed on a uniprocessor - */ - -#define apm_save_cpus() (current->cpus_allowed) -#define apm_restore_cpus(x) (void)(x) - -#endif - -/* * These are the actual BIOS calls. Depending on APM_ZERO_SEGS and * apm_info.allow_ints, we are being really paranoid here! Not only * are interrupts disabled, but all the segment registers (except SS) @@ -568,16 +539,23 @@ static inline void apm_irq_restore(unsigned long flags) # define APM_DO_RESTORE_SEGS #endif +struct apm_bios_call { + u32 func; + /* In and out */ + u32 ebx; + u32 ecx; + /* Out only */ + u32 eax; + u32 edx; + u32 esi; + + /* Error: -ENOMEM, or bits 8-15 of eax */ + int err; +}; + /** - * apm_bios_call - Make an APM BIOS 32bit call - * @func: APM function to execute - * @ebx_in: EBX register for call entry - * @ecx_in: ECX register for call entry - * @eax: EAX register return - * @ebx: EBX register return - * @ecx: ECX register return - * @edx: EDX register return - * @esi: ESI register return + * __apm_bios_call - Make an APM BIOS 32bit call + * @_call: pointer to struct apm_bios_call. * * Make an APM call using the 32bit protected mode interface. The * caller is responsible for knowing if APM BIOS is configured and @@ -586,80 +564,142 @@ static inline void apm_irq_restore(unsigned long flags) * flag is loaded into AL. If there is an error, then the error * code is returned in AH (bits 8-15 of eax) and this function * returns non-zero. + * + * Note: this makes the call on the current CPU. */ - -static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in, - u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi) +static long __apm_bios_call(void *_call) { APM_DECL_SEGS unsigned long flags; - cpumask_t cpus; int cpu; struct desc_struct save_desc_40; struct desc_struct *gdt; - - cpus = apm_save_cpus(); + struct apm_bios_call *call = _call; cpu = get_cpu(); + BUG_ON(cpu != 0); gdt = get_cpu_gdt_table(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); APM_DO_SAVE_SEGS; - apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi); + apm_bios_call_asm(call->func, call->ebx, call->ecx, + &call->eax, &call->ebx, &call->ecx, &call->edx, + &call->esi); APM_DO_RESTORE_SEGS; apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); - apm_restore_cpus(cpus); - return *eax & 0xff; + return call->eax & 0xff; +} + +/* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */ +static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call) +{ + int ret; + + /* Don't bother with work_on_cpu in the common case, so we don't + * have to worry about OOM or overhead. */ + if (get_cpu() == 0) { + ret = fn(call); + put_cpu(); + } else { + put_cpu(); + ret = work_on_cpu(0, fn, call); + } + + /* work_on_cpu can fail with -ENOMEM */ + if (ret < 0) + call->err = ret; + else + call->err = (call->eax >> 8) & 0xff; + + return ret; } /** - * apm_bios_call_simple - make a simple APM BIOS 32bit call - * @func: APM function to invoke - * @ebx_in: EBX register value for BIOS call - * @ecx_in: ECX register value for BIOS call - * @eax: EAX register on return from the BIOS call + * apm_bios_call - Make an APM BIOS 32bit call (on CPU 0) + * @call: the apm_bios_call registers. + * + * If there is an error, it is returned in @call.err. + */ +static int apm_bios_call(struct apm_bios_call *call) +{ + return on_cpu0(__apm_bios_call, call); +} + +/** + * __apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0) + * @_call: pointer to struct apm_bios_call. * * Make a BIOS call that returns one value only, or just status. * If there is an error, then the error code is returned in AH - * (bits 8-15 of eax) and this function returns non-zero. This is - * used for simpler BIOS operations. This call may hold interrupts - * off for a long time on some laptops. + * (bits 8-15 of eax) and this function returns non-zero (it can + * also return -ENOMEM). This is used for simpler BIOS operations. + * This call may hold interrupts off for a long time on some laptops. + * + * Note: this makes the call on the current CPU. */ - -static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) +static long __apm_bios_call_simple(void *_call) { u8 error; APM_DECL_SEGS unsigned long flags; - cpumask_t cpus; int cpu; struct desc_struct save_desc_40; struct desc_struct *gdt; - - cpus = apm_save_cpus(); + struct apm_bios_call *call = _call; cpu = get_cpu(); + BUG_ON(cpu != 0); gdt = get_cpu_gdt_table(cpu); save_desc_40 = gdt[0x40 / 8]; gdt[0x40 / 8] = bad_bios_desc; apm_irq_save(flags); APM_DO_SAVE_SEGS; - error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax); + error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx, + &call->eax); APM_DO_RESTORE_SEGS; apm_irq_restore(flags); gdt[0x40 / 8] = save_desc_40; put_cpu(); - apm_restore_cpus(cpus); return error; } /** + * apm_bios_call_simple - make a simple APM BIOS 32bit call + * @func: APM function to invoke + * @ebx_in: EBX register value for BIOS call + * @ecx_in: ECX register value for BIOS call + * @eax: EAX register on return from the BIOS call + * @err: bits + * + * Make a BIOS call that returns one value only, or just status. + * If there is an error, then the error code is returned in @err + * and this function returns non-zero. This is used for simpler + * BIOS operations. This call may hold interrupts off for a long + * time on some laptops. + */ +static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax, + int *err) +{ + struct apm_bios_call call; + int ret; + + call.func = func; + call.ebx = ebx_in; + call.ecx = ecx_in; + + ret = on_cpu0(__apm_bios_call_simple, &call); + *eax = call.eax; + *err = call.err; + return ret; +} + +/** * apm_driver_version - APM driver version * @val: loaded with the APM version on return * @@ -678,9 +718,10 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) static int apm_driver_version(u_short *val) { u32 eax; + int err; - if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err)) + return err; *val = eax; return APM_SUCCESS; } @@ -701,22 +742,21 @@ static int apm_driver_version(u_short *val) * that APM 1.2 is in use. If no messges are pending the value 0x80 * is returned (No power management events pending). */ - static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) { - u32 eax; - u32 ebx; - u32 ecx; - u32 dummy; + struct apm_bios_call call; - if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx, - &dummy, &dummy)) - return (eax >> 8) & 0xff; - *event = ebx; + call.func = APM_FUNC_GET_EVENT; + call.ebx = call.ecx = 0; + + if (apm_bios_call(&call)) + return call.err; + + *event = call.ebx; if (apm_info.connection_version < 0x0102) *info = ~0; /* indicate info not valid */ else - *info = ecx; + *info = call.ecx; return APM_SUCCESS; } @@ -737,9 +777,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) static int set_power_state(u_short what, u_short state) { u32 eax; + int err; - if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err)) + return err; return APM_SUCCESS; } @@ -770,6 +811,7 @@ static int apm_do_idle(void) u8 ret = 0; int idled = 0; int polling; + int err; polling = !!(current_thread_info()->status & TS_POLLING); if (polling) { @@ -782,7 +824,7 @@ static int apm_do_idle(void) } if (!need_resched()) { idled = 1; - ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax); + ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } if (polling) current_thread_info()->status |= TS_POLLING; @@ -797,8 +839,7 @@ static int apm_do_idle(void) * Only report the failure the first 5 times. */ if (++t < 5) { - printk(KERN_DEBUG "apm_do_idle failed (%d)\n", - (eax >> 8) & 0xff); + printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err); t = jiffies; } return -1; @@ -816,9 +857,10 @@ static int apm_do_idle(void) static void apm_do_busy(void) { u32 dummy; + int err; if (clock_slowed || ALWAYS_CALL_BUSY) { - (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy); + (void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err); clock_slowed = 0; } } @@ -937,7 +979,7 @@ static void apm_power_off(void) /* Some bioses don't like being called from CPU != 0 */ if (apm_info.realmode_power_off) { - (void)apm_save_cpus(); + set_cpus_allowed_ptr(current, cpumask_of(0)); machine_real_restart(po_bios_call, sizeof(po_bios_call)); } else { (void)set_system_power_state(APM_STATE_OFF); @@ -956,12 +998,13 @@ static void apm_power_off(void) static int apm_enable_power_management(int enable) { u32 eax; + int err; if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED)) return APM_NOT_ENGAGED; if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL, - enable, &eax)) - return (eax >> 8) & 0xff; + enable, &eax, &err)) + return err; if (enable) apm_info.bios.flags &= ~APM_BIOS_DISABLED; else @@ -986,24 +1029,23 @@ static int apm_enable_power_management(int enable) static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) { - u32 eax; - u32 ebx; - u32 ecx; - u32 edx; - u32 dummy; + struct apm_bios_call call; + + call.func = APM_FUNC_GET_STATUS; + call.ebx = APM_DEVICE_ALL; + call.ecx = 0; if (apm_info.get_power_status_broken) return APM_32_UNSUPPORTED; - if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0, - &eax, &ebx, &ecx, &edx, &dummy)) - return (eax >> 8) & 0xff; - *status = ebx; - *bat = ecx; + if (apm_bios_call(&call)) + return call.err; + *status = call.ebx; + *bat = call.ecx; if (apm_info.get_power_status_swabinminutes) { - *life = swab16((u16)edx); + *life = swab16((u16)call.edx); *life |= 0x8000; } else - *life = edx; + *life = call.edx; return APM_SUCCESS; } @@ -1048,12 +1090,14 @@ static int apm_get_battery_status(u_short which, u_short *status, static int apm_engage_power_management(u_short device, int enable) { u32 eax; + int err; if ((enable == 0) && (device == APM_DEVICE_ALL) && (apm_info.bios.flags & APM_BIOS_DISABLED)) return APM_DISABLED; - if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax)) - return (eax >> 8) & 0xff; + if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, + &eax, &err)) + return err; if (device == APM_DEVICE_ALL) { if (enable) apm_info.bios.flags &= ~APM_BIOS_DISENGAGED; @@ -1190,8 +1234,10 @@ static int suspend(int vetoable) struct apm_user *as; device_suspend(PMSG_SUSPEND); - local_irq_disable(); + device_power_down(PMSG_SUSPEND); + + local_irq_disable(); sysdev_suspend(PMSG_SUSPEND); local_irq_enable(); @@ -1209,9 +1255,12 @@ static int suspend(int vetoable) if (err != APM_SUCCESS) apm_error("suspend", err); err = (err == APM_SUCCESS) ? 0 : -EIO; + sysdev_resume(); - device_power_up(PMSG_RESUME); local_irq_enable(); + + device_power_up(PMSG_RESUME); + device_resume(PMSG_RESUME); queue_event(APM_NORMAL_RESUME, NULL); spin_lock(&user_list_lock); @@ -1228,8 +1277,9 @@ static void standby(void) { int err; - local_irq_disable(); device_power_down(PMSG_SUSPEND); + + local_irq_disable(); sysdev_suspend(PMSG_SUSPEND); local_irq_enable(); @@ -1239,8 +1289,9 @@ static void standby(void) local_irq_disable(); sysdev_resume(); - device_power_up(PMSG_RESUME); local_irq_enable(); + + device_power_up(PMSG_RESUME); } static apm_event_t get_event(void) @@ -1682,16 +1733,14 @@ static int apm(void *unused) char *power_stat; char *bat_stat; -#ifdef CONFIG_SMP /* 2002/08/01 - WT * This is to avoid random crashes at boot time during initialization * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D. * Some bioses don't like being called from CPU != 0. * Method suggested by Ingo Molnar. */ - set_cpus_allowed(current, cpumask_of_cpu(0)); + set_cpus_allowed_ptr(current, cpumask_of(0)); BUG_ON(smp_processor_id() != 0); -#endif if (apm_info.connection_version == 0) { apm_info.connection_version = apm_info.bios.version; diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index fbf2f33..5a6aa1c 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -18,6 +18,7 @@ #include <asm/thread_info.h> #include <asm/bootparam.h> #include <asm/elf.h> +#include <asm/suspend.h> #include <xen/interface/xen.h> diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 8793ab3..e72f062 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -16,6 +16,7 @@ #include <asm/thread_info.h> #include <asm/ia32.h> #include <asm/bootparam.h> +#include <asm/suspend.h> #include <xen/interface/xen.h> diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c index f638827..63a88e1 100644 --- a/arch/x86/kernel/bios_uv.c +++ b/arch/x86/kernel/bios_uv.c @@ -182,7 +182,8 @@ void uv_bios_init(void) memcpy(&uv_systab, tab, sizeof(struct uv_systab)); iounmap(tab); - printk(KERN_INFO "EFI UV System Table Revision %d\n", tab->revision); + printk(KERN_INFO "EFI UV System Table Revision %d\n", + uv_systab.revision); } #else /* !CONFIG_EFI */ diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 8220ae6..c965e52 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -31,6 +31,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) static const struct cpuid_bit __cpuinitconst cpuid_bits[] = { { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 }, + { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 }, { 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e2962cc..c4f6678 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -41,8 +41,6 @@ #include "cpu.h" -#ifdef CONFIG_X86_64 - /* all of these masks are initialized in setup_cpu_local_masks() */ cpumask_var_t cpu_initialized_mask; cpumask_var_t cpu_callout_mask; @@ -60,16 +58,6 @@ void __init setup_cpu_local_masks(void) alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask); } -#else /* CONFIG_X86_32 */ - -cpumask_t cpu_sibling_setup_map; -cpumask_t cpu_callout_map; -cpumask_t cpu_initialized; -cpumask_t cpu_callin_map; - -#endif /* CONFIG_X86_32 */ - - static const struct cpu_dev *this_cpu __cpuinitdata; DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { @@ -859,6 +847,7 @@ static void vgetcpu_set_mode(void) void __init identify_boot_cpu(void) { identify_cpu(&boot_cpu_data); + init_c1e_mask(); #ifdef CONFIG_X86_32 sysenter_setup(); enable_sep_cpu(); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 9469ecb..6de9a90 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -3,25 +3,25 @@ #define ARCH_X86_CPU_H struct cpu_model_info { - int vendor; - int family; - const char *model_names[16]; + int vendor; + int family; + const char *model_names[16]; }; /* attempt to consolidate cpu attributes */ struct cpu_dev { - const char * c_vendor; + const char *c_vendor; /* some have two possibilities for cpuid string */ - const char * c_ident[2]; + const char *c_ident[2]; struct cpu_model_info c_models[4]; - void (*c_early_init)(struct cpuinfo_x86 *c); - void (*c_init)(struct cpuinfo_x86 * c); - void (*c_identify)(struct cpuinfo_x86 * c); - unsigned int (*c_size_cache)(struct cpuinfo_x86 * c, unsigned int size); - int c_x86_vendor; + void (*c_early_init)(struct cpuinfo_x86 *); + void (*c_init)(struct cpuinfo_x86 *); + void (*c_identify)(struct cpuinfo_x86 *); + unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int); + int c_x86_vendor; }; #define cpu_dev_register(cpu_devX) \ diff --git a/arch/x86/kernel/cpu/cpu_debug.c b/arch/x86/kernel/cpu/cpu_debug.c index 46e29ab..46e29ab 100755..100644 --- a/arch/x86/kernel/cpu/cpu_debug.c +++ b/arch/x86/kernel/cpu/cpu_debug.c diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig index 65792c2..52c8398 100644 --- a/arch/x86/kernel/cpu/cpufreq/Kconfig +++ b/arch/x86/kernel/cpu/cpufreq/Kconfig @@ -87,30 +87,15 @@ config X86_POWERNOW_K7_ACPI config X86_POWERNOW_K8 tristate "AMD Opteron/Athlon64 PowerNow!" select CPU_FREQ_TABLE + depends on ACPI && ACPI_PROCESSOR help - This adds the CPUFreq driver for mobile AMD Opteron/Athlon64 processors. + This adds the CPUFreq driver for K8/K10 Opteron/Athlon64 processors. To compile this driver as a module, choose M here: the module will be called powernow-k8. For details, take a look at <file:Documentation/cpu-freq/>. - If in doubt, say N. - -config X86_POWERNOW_K8_ACPI - bool - prompt "ACPI Support" if X86_32 - depends on ACPI && X86_POWERNOW_K8 && ACPI_PROCESSOR - depends on !(X86_POWERNOW_K8 = y && ACPI_PROCESSOR = m) - default y - help - This provides access to the K8s Processor Performance States via ACPI. - This driver is probably required for CPUFreq to work with multi-socket and - SMP systems. It is not required on at least some single-socket yet - multi-core systems, even if SMP is enabled. - - It is safe to say Y here. - config X86_GX_SUSPMOD tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation" depends on X86_32 && PCI diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile index 560f776..509296d 100644 --- a/arch/x86/kernel/cpu/cpufreq/Makefile +++ b/arch/x86/kernel/cpu/cpufreq/Makefile @@ -1,6 +1,11 @@ +# Link order matters. K8 is preferred to ACPI because of firmware bugs in early +# K8 systems. ACPI is preferred to all other hardware-specific drivers. +# speedstep-* is preferred over p4-clockmod. + +obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o +obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o obj-$(CONFIG_X86_POWERNOW_K7) += powernow-k7.o -obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o obj-$(CONFIG_X86_LONGHAUL) += longhaul.o obj-$(CONFIG_X86_E_POWERSAVER) += e_powersaver.o obj-$(CONFIG_ELAN_CPUFREQ) += elanfreq.o @@ -10,7 +15,6 @@ obj-$(CONFIG_X86_GX_SUSPMOD) += gx-suspmod.o obj-$(CONFIG_X86_SPEEDSTEP_ICH) += speedstep-ich.o obj-$(CONFIG_X86_SPEEDSTEP_LIB) += speedstep-lib.o obj-$(CONFIG_X86_SPEEDSTEP_SMI) += speedstep-smi.o -obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO) += speedstep-centrino.o obj-$(CONFIG_X86_P4_CLOCKMOD) += p4-clockmod.o obj-$(CONFIG_X86_CPUFREQ_NFORCE2) += cpufreq-nforce2.o diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c index 22590cf..ecdb682 100644 --- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c +++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c @@ -1,5 +1,5 @@ /* - * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $) + * acpi-cpufreq.c - ACPI Processor P-States Driver * * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> @@ -33,19 +33,21 @@ #include <linux/cpufreq.h> #include <linux/compiler.h> #include <linux/dmi.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <linux/acpi.h> +#include <linux/io.h> +#include <linux/delay.h> +#include <linux/uaccess.h> + #include <acpi/processor.h> -#include <asm/io.h> #include <asm/msr.h> #include <asm/processor.h> #include <asm/cpufeature.h> -#include <asm/delay.h> -#include <asm/uaccess.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "acpi-cpufreq", msg) MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); @@ -66,10 +68,13 @@ struct acpi_cpufreq_data { unsigned int max_freq; unsigned int resume; unsigned int cpu_feature; + u64 saved_aperf, saved_mperf; }; static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data); +DEFINE_TRACE(power_mark); + /* acpi_perf_data is a pointer to percpu data. */ static struct acpi_processor_performance *acpi_perf_data; @@ -95,7 +100,7 @@ static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data) perf = data->acpi_data; - for (i=0; i<perf->state_count; i++) { + for (i = 0; i < perf->state_count; i++) { if (value == perf->states[i].status) return data->freq_table[i].frequency; } @@ -110,7 +115,7 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data) msr &= INTEL_MSR_RANGE; perf = data->acpi_data; - for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { + for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) { if (msr == perf->states[data->freq_table[i].index].status) return data->freq_table[i].frequency; } @@ -138,19 +143,18 @@ struct io_addr { u8 bit_width; }; -typedef union { - struct msr_addr msr; - struct io_addr io; -} drv_addr_union; - struct drv_cmd { unsigned int type; const struct cpumask *mask; - drv_addr_union addr; + union { + struct msr_addr msr; + struct io_addr io; + } addr; u32 val; }; -static long do_drv_read(void *_cmd) +/* Called via smp_call_function_single(), on the target CPU */ +static void do_drv_read(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 h; @@ -167,10 +171,10 @@ static long do_drv_read(void *_cmd) default: break; } - return 0; } -static long do_drv_write(void *_cmd) +/* Called via smp_call_function_many(), on the target CPUs */ +static void do_drv_write(void *_cmd) { struct drv_cmd *cmd = _cmd; u32 lo, hi; @@ -189,23 +193,24 @@ static long do_drv_write(void *_cmd) default: break; } - return 0; } static void drv_read(struct drv_cmd *cmd) { cmd->val = 0; - work_on_cpu(cpumask_any(cmd->mask), do_drv_read, cmd); + smp_call_function_single(cpumask_any(cmd->mask), do_drv_read, cmd, 1); } static void drv_write(struct drv_cmd *cmd) { - unsigned int i; + int this_cpu; - for_each_cpu(i, cmd->mask) { - work_on_cpu(i, do_drv_write, cmd); - } + this_cpu = get_cpu(); + if (cpumask_test_cpu(this_cpu, cmd->mask)) + do_drv_write(cmd); + smp_call_function_many(cmd->mask, do_drv_write, cmd, 1); + put_cpu(); } static u32 get_cur_val(const struct cpumask *mask) @@ -239,28 +244,23 @@ static u32 get_cur_val(const struct cpumask *mask) return cmd.val; } -struct perf_cur { +struct perf_pair { union { struct { u32 lo; u32 hi; } split; u64 whole; - } aperf_cur, mperf_cur; + } aperf, mperf; }; - -static long read_measured_perf_ctrs(void *_cur) +/* Called via smp_call_function_single(), on the target CPU */ +static void read_measured_perf_ctrs(void *_cur) { - struct perf_cur *cur = _cur; - - rdmsr(MSR_IA32_APERF, cur->aperf_cur.split.lo, cur->aperf_cur.split.hi); - rdmsr(MSR_IA32_MPERF, cur->mperf_cur.split.lo, cur->mperf_cur.split.hi); + struct perf_pair *cur = _cur; - wrmsr(MSR_IA32_APERF, 0, 0); - wrmsr(MSR_IA32_MPERF, 0, 0); - - return 0; + rdmsr(MSR_IA32_APERF, cur->aperf.split.lo, cur->aperf.split.hi); + rdmsr(MSR_IA32_MPERF, cur->mperf.split.lo, cur->mperf.split.hi); } /* @@ -279,52 +279,57 @@ static long read_measured_perf_ctrs(void *_cur) static unsigned int get_measured_perf(struct cpufreq_policy *policy, unsigned int cpu) { - struct perf_cur cur; + struct perf_pair readin, cur; unsigned int perf_percent; unsigned int retval; - if (!work_on_cpu(cpu, read_measured_perf_ctrs, &cur)) + if (smp_call_function_single(cpu, read_measured_perf_ctrs, &readin, 1)) return 0; + cur.aperf.whole = readin.aperf.whole - + per_cpu(drv_data, cpu)->saved_aperf; + cur.mperf.whole = readin.mperf.whole - + per_cpu(drv_data, cpu)->saved_mperf; + per_cpu(drv_data, cpu)->saved_aperf = readin.aperf.whole; + per_cpu(drv_data, cpu)->saved_mperf = readin.mperf.whole; + #ifdef __i386__ /* * We dont want to do 64 bit divide with 32 bit kernel * Get an approximate value. Return failure in case we cannot get * an approximate value. */ - if (unlikely(cur.aperf_cur.split.hi || cur.mperf_cur.split.hi)) { + if (unlikely(cur.aperf.split.hi || cur.mperf.split.hi)) { int shift_count; u32 h; - h = max_t(u32, cur.aperf_cur.split.hi, cur.mperf_cur.split.hi); + h = max_t(u32, cur.aperf.split.hi, cur.mperf.split.hi); shift_count = fls(h); - cur.aperf_cur.whole >>= shift_count; - cur.mperf_cur.whole >>= shift_count; + cur.aperf.whole >>= shift_count; + cur.mperf.whole >>= shift_count; } - if (((unsigned long)(-1) / 100) < cur.aperf_cur.split.lo) { + if (((unsigned long)(-1) / 100) < cur.aperf.split.lo) { int shift_count = 7; - cur.aperf_cur.split.lo >>= shift_count; - cur.mperf_cur.split.lo >>= shift_count; + cur.aperf.split.lo >>= shift_count; + cur.mperf.split.lo >>= shift_count; } - if (cur.aperf_cur.split.lo && cur.mperf_cur.split.lo) - perf_percent = (cur.aperf_cur.split.lo * 100) / - cur.mperf_cur.split.lo; + if (cur.aperf.split.lo && cur.mperf.split.lo) + perf_percent = (cur.aperf.split.lo * 100) / cur.mperf.split.lo; else perf_percent = 0; #else - if (unlikely(((unsigned long)(-1) / 100) < cur.aperf_cur.whole)) { + if (unlikely(((unsigned long)(-1) / 100) < cur.aperf.whole)) { int shift_count = 7; - cur.aperf_cur.whole >>= shift_count; - cur.mperf_cur.whole >>= shift_count; + cur.aperf.whole >>= shift_count; + cur.mperf.whole >>= shift_count; } - if (cur.aperf_cur.whole && cur.mperf_cur.whole) - perf_percent = (cur.aperf_cur.whole * 100) / - cur.mperf_cur.whole; + if (cur.aperf.whole && cur.mperf.whole) + perf_percent = (cur.aperf.whole * 100) / cur.mperf.whole; else perf_percent = 0; @@ -369,7 +374,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq, unsigned int cur_freq; unsigned int i; - for (i=0; i<100; i++) { + for (i = 0; i < 100; i++) { cur_freq = extract_freq(get_cur_val(mask), data); if (cur_freq == freq) return 1; @@ -494,7 +499,7 @@ acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu) unsigned long freq; unsigned long freqn = perf->states[0].core_frequency * 1000; - for (i=0; i<(perf->state_count-1); i++) { + for (i = 0; i < (perf->state_count-1); i++) { freq = freqn; freqn = perf->states[i+1].core_frequency * 1000; if ((2 * cpu_khz) > (freqn + freq)) { @@ -673,17 +678,29 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) /* detect transition latency */ policy->cpuinfo.transition_latency = 0; - for (i=0; i<perf->state_count; i++) { + for (i = 0; i < perf->state_count; i++) { if ((perf->states[i].transition_latency * 1000) > policy->cpuinfo.transition_latency) policy->cpuinfo.transition_latency = perf->states[i].transition_latency * 1000; } + /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */ + if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE && + policy->cpuinfo.transition_latency > 20 * 1000) { + static int print_once; + policy->cpuinfo.transition_latency = 20 * 1000; + if (!print_once) { + print_once = 1; + printk(KERN_INFO "Capping off P-state tranision latency" + " at 20 uS\n"); + } + } + data->max_freq = perf->states[0].core_frequency * 1000; /* table init */ - for (i=0; i<perf->state_count; i++) { - if (i>0 && perf->states[i].core_frequency >= + for (i = 0; i < perf->state_count; i++) { + if (i > 0 && perf->states[i].core_frequency >= data->freq_table[valid_states-1].frequency / 1000) continue; diff --git a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c index 965ea52..733093d 100644 --- a/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c +++ b/arch/x86/kernel/cpu/cpufreq/cpufreq-nforce2.c @@ -32,7 +32,7 @@ * nforce2_chipset: * FSB is changed using the chipset */ -static struct pci_dev *nforce2_chipset_dev; +static struct pci_dev *nforce2_dev; /* fid: * multiplier * 10 @@ -56,7 +56,9 @@ MODULE_PARM_DESC(fid, "CPU multiplier to use (11.5 = 115)"); MODULE_PARM_DESC(min_fsb, "Minimum FSB to use, if not defined: current FSB - 50"); -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "cpufreq-nforce2", msg) +#define PFX "cpufreq-nforce2: " +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "cpufreq-nforce2", msg) /** * nforce2_calc_fsb - calculate FSB @@ -118,11 +120,11 @@ static void nforce2_write_pll(int pll) int temp; /* Set the pll addr. to 0x00 */ - pci_write_config_dword(nforce2_chipset_dev, NFORCE2_PLLADR, 0); + pci_write_config_dword(nforce2_dev, NFORCE2_PLLADR, 0); /* Now write the value in all 64 registers */ for (temp = 0; temp <= 0x3f; temp++) - pci_write_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, pll); + pci_write_config_dword(nforce2_dev, NFORCE2_PLLREG, pll); return; } @@ -139,8 +141,8 @@ static unsigned int nforce2_fsb_read(int bootfsb) u32 fsb, temp = 0; /* Get chipset boot FSB from subdevice 5 (FSB at boot-time) */ - nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, - 0x01EF, PCI_ANY_ID, PCI_ANY_ID, NULL); + nforce2_sub5 = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, 0x01EF, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (!nforce2_sub5) return 0; @@ -148,13 +150,13 @@ static unsigned int nforce2_fsb_read(int bootfsb) fsb /= 1000000; /* Check if PLL register is already set */ - pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp); + pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp); if (bootfsb || !temp) return fsb; /* Use PLL register FSB value */ - pci_read_config_dword(nforce2_chipset_dev, NFORCE2_PLLREG, &temp); + pci_read_config_dword(nforce2_dev, NFORCE2_PLLREG, &temp); fsb = nforce2_calc_fsb(temp); return fsb; @@ -174,18 +176,18 @@ static int nforce2_set_fsb(unsigned int fsb) int pll = 0; if ((fsb > max_fsb) || (fsb < NFORCE2_MIN_FSB)) { - printk(KERN_ERR "cpufreq: FSB %d is out of range!\n", fsb); + printk(KERN_ERR PFX "FSB %d is out of range!\n", fsb); return -EINVAL; } tfsb = nforce2_fsb_read(0); if (!tfsb) { - printk(KERN_ERR "cpufreq: Error while reading the FSB\n"); + printk(KERN_ERR PFX "Error while reading the FSB\n"); return -EINVAL; } /* First write? Then set actual value */ - pci_read_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8 *)&temp); + pci_read_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8 *)&temp); if (!temp) { pll = nforce2_calc_pll(tfsb); @@ -197,7 +199,7 @@ static int nforce2_set_fsb(unsigned int fsb) /* Enable write access */ temp = 0x01; - pci_write_config_byte(nforce2_chipset_dev, NFORCE2_PLLENABLE, (u8)temp); + pci_write_config_byte(nforce2_dev, NFORCE2_PLLENABLE, (u8)temp); diff = tfsb - fsb; @@ -222,7 +224,7 @@ static int nforce2_set_fsb(unsigned int fsb) } temp = 0x40; - pci_write_config_byte(nforce2_chipset_dev, NFORCE2_PLLADR, (u8)temp); + pci_write_config_byte(nforce2_dev, NFORCE2_PLLADR, (u8)temp); return 0; } @@ -244,7 +246,8 @@ static unsigned int nforce2_get(unsigned int cpu) * nforce2_target - set a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * Sets a new CPUFreq policy. */ @@ -276,7 +279,7 @@ static int nforce2_target(struct cpufreq_policy *policy, /* local_irq_save(flags); */ if (nforce2_set_fsb(target_fsb) < 0) - printk(KERN_ERR "cpufreq: Changing FSB to %d failed\n", + printk(KERN_ERR PFX "Changing FSB to %d failed\n", target_fsb); else dprintk("Changed FSB successfully to %d\n", @@ -327,8 +330,8 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) /* FIX: Get FID from CPU */ if (!fid) { if (!cpu_khz) { - printk(KERN_WARNING - "cpufreq: cpu_khz not set, can't calculate multiplier!\n"); + printk(KERN_WARNING PFX + "cpu_khz not set, can't calculate multiplier!\n"); return -ENODEV; } @@ -343,7 +346,7 @@ static int nforce2_cpu_init(struct cpufreq_policy *policy) } } - printk(KERN_INFO "cpufreq: FSB currently at %i MHz, FID %d.%d\n", fsb, + printk(KERN_INFO PFX "FSB currently at %i MHz, FID %d.%d\n", fsb, fid / 10, fid % 10); /* Set maximum FSB to FSB at boot time */ @@ -392,17 +395,18 @@ static struct cpufreq_driver nforce2_driver = { */ static unsigned int nforce2_detect_chipset(void) { - nforce2_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, + nforce2_dev = pci_get_subsys(PCI_VENDOR_ID_NVIDIA, PCI_DEVICE_ID_NVIDIA_NFORCE2, PCI_ANY_ID, PCI_ANY_ID, NULL); - if (nforce2_chipset_dev == NULL) + if (nforce2_dev == NULL) return -ENODEV; - printk(KERN_INFO "cpufreq: Detected nForce2 chipset revision %X\n", - nforce2_chipset_dev->revision); - printk(KERN_INFO - "cpufreq: FSB changing is maybe unstable and can lead to crashes and data loss.\n"); + printk(KERN_INFO PFX "Detected nForce2 chipset revision %X\n", + nforce2_dev->revision); + printk(KERN_INFO PFX + "FSB changing is maybe unstable and can lead to " + "crashes and data loss.\n"); return 0; } @@ -420,7 +424,7 @@ static int __init nforce2_init(void) /* detect chipset */ if (nforce2_detect_chipset()) { - printk(KERN_ERR "cpufreq: No nForce2 chipset.\n"); + printk(KERN_INFO PFX "No nForce2 chipset.\n"); return -ENODEV; } diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c index 41ab3f0..35a257d 100644 --- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c +++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c @@ -12,12 +12,12 @@ #include <linux/cpufreq.h> #include <linux/ioport.h> #include <linux/slab.h> +#include <linux/timex.h> +#include <linux/io.h> +#include <linux/delay.h> #include <asm/msr.h> #include <asm/tsc.h> -#include <asm/timex.h> -#include <asm/io.h> -#include <asm/delay.h> #define EPS_BRAND_C7M 0 #define EPS_BRAND_C7 1 @@ -184,7 +184,7 @@ static int eps_cpu_init(struct cpufreq_policy *policy) break; } - switch(brand) { + switch (brand) { case EPS_BRAND_C7M: printk(KERN_CONT "C7-M\n"); break; @@ -218,17 +218,20 @@ static int eps_cpu_init(struct cpufreq_policy *policy) /* Print voltage and multiplier */ rdmsr(MSR_IA32_PERF_STATUS, lo, hi); current_voltage = lo & 0xff; - printk(KERN_INFO "eps: Current voltage = %dmV\n", current_voltage * 16 + 700); + printk(KERN_INFO "eps: Current voltage = %dmV\n", + current_voltage * 16 + 700); current_multiplier = (lo >> 8) & 0xff; printk(KERN_INFO "eps: Current multiplier = %d\n", current_multiplier); /* Print limits */ max_voltage = hi & 0xff; - printk(KERN_INFO "eps: Highest voltage = %dmV\n", max_voltage * 16 + 700); + printk(KERN_INFO "eps: Highest voltage = %dmV\n", + max_voltage * 16 + 700); max_multiplier = (hi >> 8) & 0xff; printk(KERN_INFO "eps: Highest multiplier = %d\n", max_multiplier); min_voltage = (hi >> 16) & 0xff; - printk(KERN_INFO "eps: Lowest voltage = %dmV\n", min_voltage * 16 + 700); + printk(KERN_INFO "eps: Lowest voltage = %dmV\n", + min_voltage * 16 + 700); min_multiplier = (hi >> 24) & 0xff; printk(KERN_INFO "eps: Lowest multiplier = %d\n", min_multiplier); @@ -318,7 +321,7 @@ static int eps_cpu_exit(struct cpufreq_policy *policy) return 0; } -static struct freq_attr* eps_attr[] = { +static struct freq_attr *eps_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -356,7 +359,7 @@ static void __exit eps_exit(void) cpufreq_unregister_driver(&eps_driver); } -MODULE_AUTHOR("Rafa³ Bilski <rafalbilski@interia.pl>"); +MODULE_AUTHOR("Rafal Bilski <rafalbilski@interia.pl>"); MODULE_DESCRIPTION("Enhanced PowerSaver driver for VIA C7 CPU's."); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/elanfreq.c b/arch/x86/kernel/cpu/cpufreq/elanfreq.c index fe613c9..006b278 100644 --- a/arch/x86/kernel/cpu/cpufreq/elanfreq.c +++ b/arch/x86/kernel/cpu/cpufreq/elanfreq.c @@ -184,7 +184,8 @@ static int elanfreq_target(struct cpufreq_policy *policy, { unsigned int newstate = 0; - if (cpufreq_frequency_table_target(policy, &elanfreq_table[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &elanfreq_table[0], + target_freq, relation, &newstate)) return -EINVAL; elanfreq_set_cpu_state(newstate); @@ -301,7 +302,8 @@ static void __exit elanfreq_exit(void) module_param(max_freq, int, 0444); MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Robert Schwebel <r.schwebel@pengutronix.de>, Sven Geggus <sven@geggus.net>"); +MODULE_AUTHOR("Robert Schwebel <r.schwebel@pengutronix.de>, " + "Sven Geggus <sven@geggus.net>"); MODULE_DESCRIPTION("cpufreq driver for AMD's Elan CPUs"); module_init(elanfreq_init); diff --git a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c index 9d9eae8..ac27ec2 100644 --- a/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c +++ b/arch/x86/kernel/cpu/cpufreq/gx-suspmod.c @@ -79,8 +79,9 @@ #include <linux/smp.h> #include <linux/cpufreq.h> #include <linux/pci.h> +#include <linux/errno.h> + #include <asm/processor-cyrix.h> -#include <asm/errno.h> /* PCI config registers, all at F0 */ #define PCI_PMER1 0x80 /* power management enable register 1 */ @@ -122,8 +123,8 @@ static struct gxfreq_params *gx_params; static int stock_freq; /* PCI bus clock - defaults to 30.000 if cpu_khz is not available */ -static int pci_busclk = 0; -module_param (pci_busclk, int, 0444); +static int pci_busclk; +module_param(pci_busclk, int, 0444); /* maximum duration for which the cpu may be suspended * (32us * MAX_DURATION). If no parameter is given, this defaults @@ -132,7 +133,7 @@ module_param (pci_busclk, int, 0444); * is suspended -- processing power is just 0.39% of what it used to be, * though. 781.25 kHz(!) for a 200 MHz processor -- wow. */ static int max_duration = 255; -module_param (max_duration, int, 0444); +module_param(max_duration, int, 0444); /* For the default policy, we want at least some processing power * - let's say 5%. (min = maxfreq / POLICY_MIN_DIV) @@ -140,7 +141,8 @@ module_param (max_duration, int, 0444); #define POLICY_MIN_DIV 20 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "gx-suspmod", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "gx-suspmod", msg) /** * we can detect a core multipiler from dir0_lsb @@ -166,12 +168,20 @@ static int gx_freq_mult[16] = { * Low Level chipset interface * ****************************************************************/ static struct pci_device_id gx_chipset_tbl[] __initdata = { - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, PCI_ANY_ID, PCI_ANY_ID }, - { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5530_LEGACY, + PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520, + PCI_ANY_ID, PCI_ANY_ID }, + { PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510, + PCI_ANY_ID, PCI_ANY_ID }, { 0, }, }; +static void gx_write_byte(int reg, int value) +{ + pci_write_config_byte(gx_params->cs55x0, reg, value); +} + /** * gx_detect_chipset: * @@ -200,7 +210,8 @@ static __init struct pci_dev *gx_detect_chipset(void) /** * gx_get_cpuspeed: * - * Finds out at which efficient frequency the Cyrix MediaGX/NatSemi Geode CPU runs. + * Finds out at which efficient frequency the Cyrix MediaGX/NatSemi + * Geode CPU runs. */ static unsigned int gx_get_cpuspeed(unsigned int cpu) { @@ -217,17 +228,18 @@ static unsigned int gx_get_cpuspeed(unsigned int cpu) * **/ -static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, u8 *off_duration) +static unsigned int gx_validate_speed(unsigned int khz, u8 *on_duration, + u8 *off_duration) { unsigned int i; u8 tmp_on, tmp_off; int old_tmp_freq = stock_freq; int tmp_freq; - *off_duration=1; - *on_duration=0; + *off_duration = 1; + *on_duration = 0; - for (i=max_duration; i>0; i--) { + for (i = max_duration; i > 0; i--) { tmp_off = ((khz * i) / stock_freq) & 0xff; tmp_on = i - tmp_off; tmp_freq = (stock_freq * tmp_off) / i; @@ -259,26 +271,34 @@ static void gx_set_cpuspeed(unsigned int khz) freqs.cpu = 0; freqs.old = gx_get_cpuspeed(0); - new_khz = gx_validate_speed(khz, &gx_params->on_duration, &gx_params->off_duration); + new_khz = gx_validate_speed(khz, &gx_params->on_duration, + &gx_params->off_duration); freqs.new = new_khz; cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); local_irq_save(flags); - if (new_khz != stock_freq) { /* if new khz == 100% of CPU speed, it is special case */ + + + if (new_khz != stock_freq) { + /* if new khz == 100% of CPU speed, it is special case */ switch (gx_params->cs55x0->device) { case PCI_DEVICE_ID_CYRIX_5530_LEGACY: pmer1 = gx_params->pci_pmer1 | IRQ_SPDUP | VID_SPDUP; /* FIXME: need to test other values -- Zwane,Miura */ - pci_write_config_byte(gx_params->cs55x0, PCI_IRQTC, 4); /* typical 2 to 4ms */ - pci_write_config_byte(gx_params->cs55x0, PCI_VIDTC, 100);/* typical 50 to 100ms */ - pci_write_config_byte(gx_params->cs55x0, PCI_PMER1, pmer1); - - if (gx_params->cs55x0->revision < 0x10) { /* CS5530(rev 1.2, 1.3) */ - suscfg = gx_params->pci_suscfg | SUSMOD; - } else { /* CS5530A,B.. */ - suscfg = gx_params->pci_suscfg | SUSMOD | PWRSVE; + /* typical 2 to 4ms */ + gx_write_byte(PCI_IRQTC, 4); + /* typical 50 to 100ms */ + gx_write_byte(PCI_VIDTC, 100); + gx_write_byte(PCI_PMER1, pmer1); + + if (gx_params->cs55x0->revision < 0x10) { + /* CS5530(rev 1.2, 1.3) */ + suscfg = gx_params->pci_suscfg|SUSMOD; + } else { + /* CS5530A,B.. */ + suscfg = gx_params->pci_suscfg|SUSMOD|PWRSVE; } break; case PCI_DEVICE_ID_CYRIX_5520: @@ -294,13 +314,13 @@ static void gx_set_cpuspeed(unsigned int khz) suscfg = gx_params->pci_suscfg & ~(SUSMOD); gx_params->off_duration = 0; gx_params->on_duration = 0; - dprintk("suspend modulation disabled: cpu runs 100 percent speed.\n"); + dprintk("suspend modulation disabled: cpu runs 100%% speed.\n"); } - pci_write_config_byte(gx_params->cs55x0, PCI_MODOFF, gx_params->off_duration); - pci_write_config_byte(gx_params->cs55x0, PCI_MODON, gx_params->on_duration); + gx_write_byte(PCI_MODOFF, gx_params->off_duration); + gx_write_byte(PCI_MODON, gx_params->on_duration); - pci_write_config_byte(gx_params->cs55x0, PCI_SUSCFG, suscfg); + gx_write_byte(PCI_SUSCFG, suscfg); pci_read_config_byte(gx_params->cs55x0, PCI_SUSCFG, &suscfg); local_irq_restore(flags); @@ -334,7 +354,8 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) return -EINVAL; policy->cpu = 0; - cpufreq_verify_within_limits(policy, (stock_freq / max_duration), stock_freq); + cpufreq_verify_within_limits(policy, (stock_freq / max_duration), + stock_freq); /* it needs to be assured that at least one supported frequency is * within policy->min and policy->max. If it is not, policy->max @@ -354,7 +375,8 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy) policy->max = tmp_freq; if (policy->max < policy->min) policy->max = policy->min; - cpufreq_verify_within_limits(policy, (stock_freq / max_duration), stock_freq); + cpufreq_verify_within_limits(policy, (stock_freq / max_duration), + stock_freq); return 0; } @@ -398,18 +420,18 @@ static int cpufreq_gx_cpu_init(struct cpufreq_policy *policy) return -ENODEV; /* determine maximum frequency */ - if (pci_busclk) { + if (pci_busclk) maxfreq = pci_busclk * gx_freq_mult[getCx86(CX86_DIR1) & 0x0f]; - } else if (cpu_khz) { + else if (cpu_khz) maxfreq = cpu_khz; - } else { + else maxfreq = 30000 * gx_freq_mult[getCx86(CX86_DIR1) & 0x0f]; - } + stock_freq = maxfreq; curfreq = gx_get_cpuspeed(0); dprintk("cpu max frequency is %d.\n", maxfreq); - dprintk("cpu current frequency is %dkHz.\n",curfreq); + dprintk("cpu current frequency is %dkHz.\n", curfreq); /* setup basic struct for cpufreq API */ policy->cpu = 0; @@ -447,7 +469,8 @@ static int __init cpufreq_gx_init(void) struct pci_dev *gx_pci; /* Test if we have the right hardware */ - if ((gx_pci = gx_detect_chipset()) == NULL) + gx_pci = gx_detect_chipset(); + if (gx_pci == NULL) return -ENODEV; /* check whether module parameters are sane */ @@ -468,9 +491,11 @@ static int __init cpufreq_gx_init(void) pci_read_config_byte(params->cs55x0, PCI_PMER1, &(params->pci_pmer1)); pci_read_config_byte(params->cs55x0, PCI_PMER2, &(params->pci_pmer2)); pci_read_config_byte(params->cs55x0, PCI_MODON, &(params->on_duration)); - pci_read_config_byte(params->cs55x0, PCI_MODOFF, &(params->off_duration)); + pci_read_config_byte(params->cs55x0, PCI_MODOFF, + &(params->off_duration)); - if ((ret = cpufreq_register_driver(&gx_suspmod_driver))) { + ret = cpufreq_register_driver(&gx_suspmod_driver); + if (ret) { kfree(params); return ret; /* register error! */ } @@ -485,9 +510,9 @@ static void __exit cpufreq_gx_exit(void) kfree(gx_params); } -MODULE_AUTHOR ("Hiroshi Miura <miura@da-cha.org>"); -MODULE_DESCRIPTION ("Cpufreq driver for Cyrix MediaGX and NatSemi Geode"); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Hiroshi Miura <miura@da-cha.org>"); +MODULE_DESCRIPTION("Cpufreq driver for Cyrix MediaGX and NatSemi Geode"); +MODULE_LICENSE("GPL"); module_init(cpufreq_gx_init); module_exit(cpufreq_gx_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.c b/arch/x86/kernel/cpu/cpufreq/longhaul.c index a4cff5d..ce2ed3e 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.c +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.c @@ -30,12 +30,11 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/delay.h> +#include <linux/timex.h> +#include <linux/io.h> +#include <linux/acpi.h> #include <asm/msr.h> -#include <asm/timex.h> -#include <asm/io.h> -#include <asm/acpi.h> -#include <linux/acpi.h> #include <acpi/processor.h> #include "longhaul.h" @@ -58,7 +57,7 @@ #define USE_NORTHBRIDGE (1 << 2) static int cpu_model; -static unsigned int numscales=16; +static unsigned int numscales = 16; static unsigned int fsb; static const struct mV_pos *vrm_mV_table; @@ -67,8 +66,8 @@ static const unsigned char *mV_vrm_table; static unsigned int highest_speed, lowest_speed; /* kHz */ static unsigned int minmult, maxmult; static int can_scale_voltage; -static struct acpi_processor *pr = NULL; -static struct acpi_processor_cx *cx = NULL; +static struct acpi_processor *pr; +static struct acpi_processor_cx *cx; static u32 acpi_regs_addr; static u8 longhaul_flags; static unsigned int longhaul_index; @@ -78,12 +77,13 @@ static int scale_voltage; static int disable_acpi_c3; static int revid_errata; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longhaul", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "longhaul", msg) /* Clock ratios multiplied by 10 */ -static int clock_ratio[32]; -static int eblcr_table[32]; +static int mults[32]; +static int eblcr[32]; static int longhaul_version; static struct cpufreq_frequency_table *longhaul_table; @@ -93,7 +93,7 @@ static char speedbuffer[8]; static char *print_speed(int speed) { if (speed < 1000) { - snprintf(speedbuffer, sizeof(speedbuffer),"%dMHz", speed); + snprintf(speedbuffer, sizeof(speedbuffer), "%dMHz", speed); return speedbuffer; } @@ -122,27 +122,28 @@ static unsigned int calc_speed(int mult) static int longhaul_get_cpu_mult(void) { - unsigned long invalue=0,lo, hi; + unsigned long invalue = 0, lo, hi; - rdmsr (MSR_IA32_EBL_CR_POWERON, lo, hi); - invalue = (lo & (1<<22|1<<23|1<<24|1<<25)) >>22; - if (longhaul_version==TYPE_LONGHAUL_V2 || longhaul_version==TYPE_POWERSAVER) { + rdmsr(MSR_IA32_EBL_CR_POWERON, lo, hi); + invalue = (lo & (1<<22|1<<23|1<<24|1<<25))>>22; + if (longhaul_version == TYPE_LONGHAUL_V2 || + longhaul_version == TYPE_POWERSAVER) { if (lo & (1<<27)) - invalue+=16; + invalue += 16; } - return eblcr_table[invalue]; + return eblcr[invalue]; } /* For processor with BCR2 MSR */ -static void do_longhaul1(unsigned int clock_ratio_index) +static void do_longhaul1(unsigned int mults_index) { union msr_bcr2 bcr2; rdmsrl(MSR_VIA_BCR2, bcr2.val); /* Enable software clock multiplier */ bcr2.bits.ESOFTBF = 1; - bcr2.bits.CLOCKMUL = clock_ratio_index & 0xff; + bcr2.bits.CLOCKMUL = mults_index & 0xff; /* Sync to timer tick */ safe_halt(); @@ -161,7 +162,7 @@ static void do_longhaul1(unsigned int clock_ratio_index) /* For processor with Longhaul MSR */ -static void do_powersaver(int cx_address, unsigned int clock_ratio_index, +static void do_powersaver(int cx_address, unsigned int mults_index, unsigned int dir) { union msr_longhaul longhaul; @@ -173,11 +174,11 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index, longhaul.bits.RevisionKey = longhaul.bits.RevisionID; else longhaul.bits.RevisionKey = 0; - longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf; - longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4; + longhaul.bits.SoftBusRatio = mults_index & 0xf; + longhaul.bits.SoftBusRatio4 = (mults_index & 0x10) >> 4; /* Setup new voltage */ if (can_scale_voltage) - longhaul.bits.SoftVID = (clock_ratio_index >> 8) & 0x1f; + longhaul.bits.SoftVID = (mults_index >> 8) & 0x1f; /* Sync to timer tick */ safe_halt(); /* Raise voltage if necessary */ @@ -240,14 +241,14 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index, /** * longhaul_set_cpu_frequency() - * @clock_ratio_index : bitpattern of the new multiplier. + * @mults_index : bitpattern of the new multiplier. * * Sets a new clock ratio. */ static void longhaul_setstate(unsigned int table_index) { - unsigned int clock_ratio_index; + unsigned int mults_index; int speed, mult; struct cpufreq_freqs freqs; unsigned long flags; @@ -256,9 +257,9 @@ static void longhaul_setstate(unsigned int table_index) u32 bm_timeout = 1000; unsigned int dir = 0; - clock_ratio_index = longhaul_table[table_index].index; + mults_index = longhaul_table[table_index].index; /* Safety precautions */ - mult = clock_ratio[clock_ratio_index & 0x1f]; + mult = mults[mults_index & 0x1f]; if (mult == -1) return; speed = calc_speed(mult); @@ -274,7 +275,7 @@ static void longhaul_setstate(unsigned int table_index) cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); - dprintk ("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", + dprintk("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n", fsb, mult/10, mult%10, print_speed(speed/1000)); retry_loop: preempt_disable(); @@ -282,8 +283,8 @@ retry_loop: pic2_mask = inb(0xA1); pic1_mask = inb(0x21); /* works on C3. save mask. */ - outb(0xFF,0xA1); /* Overkill */ - outb(0xFE,0x21); /* TMR0 only */ + outb(0xFF, 0xA1); /* Overkill */ + outb(0xFE, 0x21); /* TMR0 only */ /* Wait while PCI bus is busy. */ if (acpi_regs_addr && (longhaul_flags & USE_NORTHBRIDGE @@ -303,7 +304,7 @@ retry_loop: outb(3, 0x22); } else if ((pr != NULL) && pr->flags.bm_control) { /* Disable bus master arbitration */ - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1); + acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1); } switch (longhaul_version) { @@ -312,7 +313,7 @@ retry_loop: * Software controlled multipliers only. */ case TYPE_LONGHAUL_V1: - do_longhaul1(clock_ratio_index); + do_longhaul1(mults_index); break; /* @@ -326,10 +327,10 @@ retry_loop: case TYPE_POWERSAVER: if (longhaul_flags & USE_ACPI_C3) { /* Don't allow wakeup */ - acpi_set_register(ACPI_BITREG_BUS_MASTER_RLD, 0); - do_powersaver(cx->address, clock_ratio_index, dir); + acpi_write_bit_register(ACPI_BITREG_BUS_MASTER_RLD, 0); + do_powersaver(cx->address, mults_index, dir); } else { - do_powersaver(0, clock_ratio_index, dir); + do_powersaver(0, mults_index, dir); } break; } @@ -339,10 +340,10 @@ retry_loop: outb(0, 0x22); } else if ((pr != NULL) && pr->flags.bm_control) { /* Enable bus master arbitration */ - acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0); + acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0); } - outb(pic2_mask,0xA1); /* restore mask */ - outb(pic1_mask,0x21); + outb(pic2_mask, 0xA1); /* restore mask */ + outb(pic1_mask, 0x21); local_irq_restore(flags); preempt_enable(); @@ -392,7 +393,8 @@ retry_loop: cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); if (!bm_timeout) - printk(KERN_INFO PFX "Warning: Timeout while waiting for idle PCI bus.\n"); + printk(KERN_INFO PFX "Warning: Timeout while waiting for " + "idle PCI bus.\n"); } /* @@ -458,31 +460,32 @@ static int __init longhaul_get_ranges(void) break; } - dprintk ("MinMult:%d.%dx MaxMult:%d.%dx\n", + dprintk("MinMult:%d.%dx MaxMult:%d.%dx\n", minmult/10, minmult%10, maxmult/10, maxmult%10); highest_speed = calc_speed(maxmult); lowest_speed = calc_speed(minmult); - dprintk ("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb, + dprintk("FSB:%dMHz Lowest speed: %s Highest speed:%s\n", fsb, print_speed(lowest_speed/1000), print_speed(highest_speed/1000)); if (lowest_speed == highest_speed) { - printk (KERN_INFO PFX "highestspeed == lowest, aborting.\n"); + printk(KERN_INFO PFX "highestspeed == lowest, aborting.\n"); return -EINVAL; } if (lowest_speed > highest_speed) { - printk (KERN_INFO PFX "nonsense! lowest (%d > %d) !\n", + printk(KERN_INFO PFX "nonsense! lowest (%d > %d) !\n", lowest_speed, highest_speed); return -EINVAL; } - longhaul_table = kmalloc((numscales + 1) * sizeof(struct cpufreq_frequency_table), GFP_KERNEL); - if(!longhaul_table) + longhaul_table = kmalloc((numscales + 1) * sizeof(*longhaul_table), + GFP_KERNEL); + if (!longhaul_table) return -ENOMEM; for (j = 0; j < numscales; j++) { - ratio = clock_ratio[j]; + ratio = mults[j]; if (ratio == -1) continue; if (ratio > maxmult || ratio < minmult) @@ -507,13 +510,10 @@ static int __init longhaul_get_ranges(void) } } if (min_i != j) { - unsigned int temp; - temp = longhaul_table[j].frequency; - longhaul_table[j].frequency = longhaul_table[min_i].frequency; - longhaul_table[min_i].frequency = temp; - temp = longhaul_table[j].index; - longhaul_table[j].index = longhaul_table[min_i].index; - longhaul_table[min_i].index = temp; + swap(longhaul_table[j].frequency, + longhaul_table[min_i].frequency); + swap(longhaul_table[j].index, + longhaul_table[min_i].index); } } @@ -521,7 +521,7 @@ static int __init longhaul_get_ranges(void) /* Find index we are running on */ for (j = 0; j < k; j++) { - if (clock_ratio[longhaul_table[j].index & 0x1f] == mult) { + if (mults[longhaul_table[j].index & 0x1f] == mult) { longhaul_index = j; break; } @@ -559,20 +559,22 @@ static void __init longhaul_setup_voltagescaling(void) maxvid = vrm_mV_table[longhaul.bits.MaximumVID]; if (minvid.mV == 0 || maxvid.mV == 0 || minvid.mV > maxvid.mV) { - printk (KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. " + printk(KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. " "Voltage scaling disabled.\n", - minvid.mV/1000, minvid.mV%1000, maxvid.mV/1000, maxvid.mV%1000); + minvid.mV/1000, minvid.mV%1000, + maxvid.mV/1000, maxvid.mV%1000); return; } if (minvid.mV == maxvid.mV) { - printk (KERN_INFO PFX "Claims to support voltage scaling but min & max are " - "both %d.%03d. Voltage scaling disabled\n", + printk(KERN_INFO PFX "Claims to support voltage scaling but " + "min & max are both %d.%03d. " + "Voltage scaling disabled\n", maxvid.mV/1000, maxvid.mV%1000); return; } - /* How many voltage steps */ + /* How many voltage steps*/ numvscales = maxvid.pos - minvid.pos + 1; printk(KERN_INFO PFX "Max VID=%d.%03d " @@ -586,7 +588,7 @@ static void __init longhaul_setup_voltagescaling(void) j = longhaul.bits.MinMHzBR; if (longhaul.bits.MinMHzBR4) j += 16; - min_vid_speed = eblcr_table[j]; + min_vid_speed = eblcr[j]; if (min_vid_speed == -1) return; switch (longhaul.bits.MinMHzFSB) { @@ -617,7 +619,8 @@ static void __init longhaul_setup_voltagescaling(void) pos = minvid.pos; longhaul_table[j].index |= mV_vrm_table[pos] << 8; vid = vrm_mV_table[mV_vrm_table[pos]]; - printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n", speed, j, vid.mV); + printk(KERN_INFO PFX "f: %d kHz, index: %d, vid: %d mV\n", + speed, j, vid.mV); j++; } @@ -640,7 +643,8 @@ static int longhaul_target(struct cpufreq_policy *policy, unsigned int dir = 0; u8 vid, current_vid; - if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq, relation, &table_index)) + if (cpufreq_frequency_table_target(policy, longhaul_table, target_freq, + relation, &table_index)) return -EINVAL; /* Don't set same frequency again */ @@ -656,7 +660,8 @@ static int longhaul_target(struct cpufreq_policy *policy, * this in hardware, C3 is old and we need to do this * in software. */ i = longhaul_index; - current_vid = (longhaul_table[longhaul_index].index >> 8) & 0x1f; + current_vid = (longhaul_table[longhaul_index].index >> 8); + current_vid &= 0x1f; if (table_index > longhaul_index) dir = 1; while (i != table_index) { @@ -691,9 +696,9 @@ static acpi_status longhaul_walk_callback(acpi_handle obj_handle, { struct acpi_device *d; - if ( acpi_bus_get_device(obj_handle, &d) ) { + if (acpi_bus_get_device(obj_handle, &d)) return 0; - } + *return_value = acpi_driver_data(d); return 1; } @@ -750,7 +755,7 @@ static int longhaul_setup_southbridge(void) /* Find VT8235 southbridge */ dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL); if (dev == NULL) - /* Find VT8237 southbridge */ + /* Find VT8237 southbridge */ dev = pci_get_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8237, NULL); if (dev != NULL) { @@ -769,7 +774,8 @@ static int longhaul_setup_southbridge(void) if (pci_cmd & 1 << 7) { pci_read_config_dword(dev, 0x88, &acpi_regs_addr); acpi_regs_addr &= 0xff00; - printk(KERN_INFO PFX "ACPI I/O at 0x%x\n", acpi_regs_addr); + printk(KERN_INFO PFX "ACPI I/O at 0x%x\n", + acpi_regs_addr); } pci_dev_put(dev); @@ -781,7 +787,7 @@ static int longhaul_setup_southbridge(void) static int __init longhaul_cpu_init(struct cpufreq_policy *policy) { struct cpuinfo_x86 *c = &cpu_data(0); - char *cpuname=NULL; + char *cpuname = NULL; int ret; u32 lo, hi; @@ -791,8 +797,8 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpu_model = CPU_SAMUEL; cpuname = "C3 'Samuel' [C5A]"; longhaul_version = TYPE_LONGHAUL_V1; - memcpy (clock_ratio, samuel1_clock_ratio, sizeof(samuel1_clock_ratio)); - memcpy (eblcr_table, samuel1_eblcr, sizeof(samuel1_eblcr)); + memcpy(mults, samuel1_mults, sizeof(samuel1_mults)); + memcpy(eblcr, samuel1_eblcr, sizeof(samuel1_eblcr)); break; case 7: @@ -803,10 +809,8 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpuname = "C3 'Samuel 2' [C5B]"; /* Note, this is not a typo, early Samuel2's had * Samuel1 ratios. */ - memcpy(clock_ratio, samuel1_clock_ratio, - sizeof(samuel1_clock_ratio)); - memcpy(eblcr_table, samuel2_eblcr, - sizeof(samuel2_eblcr)); + memcpy(mults, samuel1_mults, sizeof(samuel1_mults)); + memcpy(eblcr, samuel2_eblcr, sizeof(samuel2_eblcr)); break; case 1 ... 15: longhaul_version = TYPE_LONGHAUL_V1; @@ -817,10 +821,8 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpu_model = CPU_EZRA; cpuname = "C3 'Ezra' [C5C]"; } - memcpy(clock_ratio, ezra_clock_ratio, - sizeof(ezra_clock_ratio)); - memcpy(eblcr_table, ezra_eblcr, - sizeof(ezra_eblcr)); + memcpy(mults, ezra_mults, sizeof(ezra_mults)); + memcpy(eblcr, ezra_eblcr, sizeof(ezra_eblcr)); break; } break; @@ -829,18 +831,16 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) cpu_model = CPU_EZRA_T; cpuname = "C3 'Ezra-T' [C5M]"; longhaul_version = TYPE_POWERSAVER; - numscales=32; - memcpy (clock_ratio, ezrat_clock_ratio, sizeof(ezrat_clock_ratio)); - memcpy (eblcr_table, ezrat_eblcr, sizeof(ezrat_eblcr)); + numscales = 32; + memcpy(mults, ezrat_mults, sizeof(ezrat_mults)); + memcpy(eblcr, ezrat_eblcr, sizeof(ezrat_eblcr)); break; case 9: longhaul_version = TYPE_POWERSAVER; numscales = 32; - memcpy(clock_ratio, - nehemiah_clock_ratio, - sizeof(nehemiah_clock_ratio)); - memcpy(eblcr_table, nehemiah_eblcr, sizeof(nehemiah_eblcr)); + memcpy(mults, nehemiah_mults, sizeof(nehemiah_mults)); + memcpy(eblcr, nehemiah_eblcr, sizeof(nehemiah_eblcr)); switch (c->x86_mask) { case 0 ... 1: cpu_model = CPU_NEHEMIAH; @@ -869,14 +869,14 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy) longhaul_version = TYPE_LONGHAUL_V1; } - printk (KERN_INFO PFX "VIA %s CPU detected. ", cpuname); + printk(KERN_INFO PFX "VIA %s CPU detected. ", cpuname); switch (longhaul_version) { case TYPE_LONGHAUL_V1: case TYPE_LONGHAUL_V2: - printk ("Longhaul v%d supported.\n", longhaul_version); + printk(KERN_CONT "Longhaul v%d supported.\n", longhaul_version); break; case TYPE_POWERSAVER: - printk ("Powersaver supported.\n"); + printk(KERN_CONT "Powersaver supported.\n"); break; }; @@ -940,7 +940,7 @@ static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy) return 0; } -static struct freq_attr* longhaul_attr[] = { +static struct freq_attr *longhaul_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -966,13 +966,15 @@ static int __init longhaul_init(void) #ifdef CONFIG_SMP if (num_online_cpus() > 1) { - printk(KERN_ERR PFX "More than 1 CPU detected, longhaul disabled.\n"); + printk(KERN_ERR PFX "More than 1 CPU detected, " + "longhaul disabled.\n"); return -ENODEV; } #endif #ifdef CONFIG_X86_IO_APIC if (cpu_has_apic) { - printk(KERN_ERR PFX "APIC detected. Longhaul is currently broken in this configuration.\n"); + printk(KERN_ERR PFX "APIC detected. Longhaul is currently " + "broken in this configuration.\n"); return -ENODEV; } #endif @@ -993,8 +995,8 @@ static void __exit longhaul_exit(void) { int i; - for (i=0; i < numscales; i++) { - if (clock_ratio[i] == maxmult) { + for (i = 0; i < numscales; i++) { + if (mults[i] == maxmult) { longhaul_setstate(i); break; } @@ -1007,11 +1009,11 @@ static void __exit longhaul_exit(void) /* Even if BIOS is exporting ACPI C3 state, and it is used * with success when CPU is idle, this state doesn't * trigger frequency transition in some cases. */ -module_param (disable_acpi_c3, int, 0644); +module_param(disable_acpi_c3, int, 0644); MODULE_PARM_DESC(disable_acpi_c3, "Don't use ACPI C3 support"); /* Change CPU voltage with frequency. Very usefull to save * power, but most VIA C3 processors aren't supporting it. */ -module_param (scale_voltage, int, 0644); +module_param(scale_voltage, int, 0644); MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor"); /* Force revision key to 0 for processors which doesn't * support voltage scaling, but are introducing itself as @@ -1019,9 +1021,9 @@ MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor"); module_param(revid_errata, int, 0644); MODULE_PARM_DESC(revid_errata, "Ignore CPU Revision ID"); -MODULE_AUTHOR ("Dave Jones <davej@redhat.com>"); -MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dave Jones <davej@redhat.com>"); +MODULE_DESCRIPTION("Longhaul driver for VIA Cyrix processors."); +MODULE_LICENSE("GPL"); late_initcall(longhaul_init); module_exit(longhaul_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/longhaul.h b/arch/x86/kernel/cpu/cpufreq/longhaul.h index 4fcc320..e2360a4 100644 --- a/arch/x86/kernel/cpu/cpufreq/longhaul.h +++ b/arch/x86/kernel/cpu/cpufreq/longhaul.h @@ -49,14 +49,14 @@ union msr_longhaul { /* * Clock ratio tables. Div/Mod by 10 to get ratio. - * The eblcr ones specify the ratio read from the CPU. - * The clock_ratio ones specify what to write to the CPU. + * The eblcr values specify the ratio read from the CPU. + * The mults values specify what to write to the CPU. */ /* * VIA C3 Samuel 1 & Samuel 2 (stepping 0) */ -static const int __initdata samuel1_clock_ratio[16] = { +static const int __initdata samuel1_mults[16] = { -1, /* 0000 -> RESERVED */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -119,7 +119,7 @@ static const int __initdata samuel2_eblcr[16] = { /* * VIA C3 Ezra */ -static const int __initdata ezra_clock_ratio[16] = { +static const int __initdata ezra_mults[16] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -160,7 +160,7 @@ static const int __initdata ezra_eblcr[16] = { /* * VIA C3 (Ezra-T) [C5M]. */ -static const int __initdata ezrat_clock_ratio[32] = { +static const int __initdata ezrat_mults[32] = { 100, /* 0000 -> 10.0x */ 30, /* 0001 -> 3.0x */ 40, /* 0010 -> 4.0x */ @@ -235,7 +235,7 @@ static const int __initdata ezrat_eblcr[32] = { /* * VIA C3 Nehemiah */ -static const int __initdata nehemiah_clock_ratio[32] = { +static const int __initdata nehemiah_mults[32] = { 100, /* 0000 -> 10.0x */ -1, /* 0001 -> 16.0x */ 40, /* 0010 -> 4.0x */ diff --git a/arch/x86/kernel/cpu/cpufreq/longrun.c b/arch/x86/kernel/cpu/cpufreq/longrun.c index 777a7ff..da5f70f 100644 --- a/arch/x86/kernel/cpu/cpufreq/longrun.c +++ b/arch/x86/kernel/cpu/cpufreq/longrun.c @@ -11,12 +11,13 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/cpufreq.h> +#include <linux/timex.h> #include <asm/msr.h> #include <asm/processor.h> -#include <asm/timex.h> -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longrun", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "longrun", msg) static struct cpufreq_driver longrun_driver; @@ -51,7 +52,7 @@ static void __init longrun_get_policy(struct cpufreq_policy *policy) msr_lo &= 0x0000007F; msr_hi &= 0x0000007F; - if ( longrun_high_freq <= longrun_low_freq ) { + if (longrun_high_freq <= longrun_low_freq) { /* Assume degenerate Longrun table */ policy->min = policy->max = longrun_high_freq; } else { @@ -79,7 +80,7 @@ static int longrun_set_policy(struct cpufreq_policy *policy) if (!policy) return -EINVAL; - if ( longrun_high_freq <= longrun_low_freq ) { + if (longrun_high_freq <= longrun_low_freq) { /* Assume degenerate Longrun table */ pctg_lo = pctg_hi = 100; } else { @@ -152,7 +153,7 @@ static unsigned int longrun_get(unsigned int cpu) cpuid(0x80860007, &eax, &ebx, &ecx, &edx); dprintk("cpuid eax is %u\n", eax); - return (eax * 1000); + return eax * 1000; } /** @@ -196,7 +197,8 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, rdmsr(MSR_TMTA_LRTI_VOLT_MHZ, msr_lo, msr_hi); *high_freq = msr_lo * 1000; /* to kHz */ - dprintk("longrun table interface told %u - %u kHz\n", *low_freq, *high_freq); + dprintk("longrun table interface told %u - %u kHz\n", + *low_freq, *high_freq); if (*low_freq > *high_freq) *low_freq = *high_freq; @@ -219,7 +221,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, cpuid(0x80860007, &eax, &ebx, &ecx, &edx); /* try decreasing in 10% steps, some processors react only * on some barrier values */ - for (try_hi = 80; try_hi > 0 && ecx > 90; try_hi -=10) { + for (try_hi = 80; try_hi > 0 && ecx > 90; try_hi -= 10) { /* set to 0 to try_hi perf_pctg */ msr_lo &= 0xFFFFFF80; msr_hi &= 0xFFFFFF80; @@ -236,7 +238,7 @@ static unsigned int __init longrun_determine_freqs(unsigned int *low_freq, /* performance_pctg = (current_freq - low_freq)/(high_freq - low_freq) * eqals - * low_freq * ( 1 - perf_pctg) = (cur_freq - high_freq * perf_pctg) + * low_freq * (1 - perf_pctg) = (cur_freq - high_freq * perf_pctg) * * high_freq * perf_pctg is stored tempoarily into "ebx". */ @@ -317,9 +319,10 @@ static void __exit longrun_exit(void) } -MODULE_AUTHOR ("Dominik Brodowski <linux@brodo.de>"); -MODULE_DESCRIPTION ("LongRun driver for Transmeta Crusoe and Efficeon processors."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); +MODULE_DESCRIPTION("LongRun driver for Transmeta Crusoe and " + "Efficeon processors."); +MODULE_LICENSE("GPL"); module_init(longrun_init); module_exit(longrun_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c index 3178c3a..6ac55bd 100644 --- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c +++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c @@ -27,15 +27,17 @@ #include <linux/cpufreq.h> #include <linux/slab.h> #include <linux/cpumask.h> +#include <linux/timex.h> #include <asm/processor.h> #include <asm/msr.h> -#include <asm/timex.h> +#include <asm/timer.h> #include "speedstep-lib.h" #define PFX "p4-clockmod: " -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "p4-clockmod", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "p4-clockmod", msg) /* * Duty Cycle (3bits), note DC_DISABLE is not specified in @@ -58,7 +60,8 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) { u32 l, h; - if (!cpu_online(cpu) || (newstate > DC_DISABLE) || (newstate == DC_RESV)) + if (!cpu_online(cpu) || + (newstate > DC_DISABLE) || (newstate == DC_RESV)) return -EINVAL; rdmsr_on_cpu(cpu, MSR_IA32_THERM_STATUS, &l, &h); @@ -66,7 +69,8 @@ static int cpufreq_p4_setdc(unsigned int cpu, unsigned int newstate) if (l & 0x01) dprintk("CPU#%d currently thermal throttled\n", cpu); - if (has_N44_O17_errata[cpu] && (newstate == DC_25PT || newstate == DC_DFLT)) + if (has_N44_O17_errata[cpu] && + (newstate == DC_25PT || newstate == DC_DFLT)) newstate = DC_38PT; rdmsr_on_cpu(cpu, MSR_IA32_THERM_CONTROL, &l, &h); @@ -112,7 +116,8 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, struct cpufreq_freqs freqs; int i; - if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &p4clockmod_table[0], + target_freq, relation, &newstate)) return -EINVAL; freqs.old = cpufreq_p4_get(policy->cpu); @@ -127,7 +132,8 @@ static int cpufreq_p4_target(struct cpufreq_policy *policy, cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE); } - /* run on each logical CPU, see section 13.15.3 of IA32 Intel Architecture Software + /* run on each logical CPU, + * see section 13.15.3 of IA32 Intel Architecture Software * Developer's Manual, Volume 3 */ for_each_cpu(i, policy->cpus) @@ -153,28 +159,30 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) { if (c->x86 == 0x06) { if (cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Warning: EST-capable CPU detected. " - "The acpi-cpufreq module offers voltage scaling" - " in addition of frequency scaling. You should use " - "that instead of p4-clockmod, if possible.\n"); + printk(KERN_WARNING PFX "Warning: EST-capable CPU " + "detected. The acpi-cpufreq module offers " + "voltage scaling in addition of frequency " + "scaling. You should use that instead of " + "p4-clockmod, if possible.\n"); switch (c->x86_model) { case 0x0E: /* Core */ case 0x0F: /* Core Duo */ case 0x16: /* Celeron Core */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PCORE); + return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE); case 0x0D: /* Pentium M (Dothan) */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; /* fall through */ case 0x09: /* Pentium M (Banias) */ - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_PM); + return speedstep_get_frequency(SPEEDSTEP_CPU_PM); } } if (c->x86 != 0xF) { if (!cpu_has(c, X86_FEATURE_EST)) - printk(KERN_WARNING PFX "Unknown p4-clockmod-capable CPU. " - "Please send an e-mail to <cpufreq@vger.kernel.org>\n"); + printk(KERN_WARNING PFX "Unknown CPU. " + "Please send an e-mail to " + "<cpufreq@vger.kernel.org>\n"); return 0; } @@ -182,16 +190,16 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c) * throttling is active or not. */ p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS; - if (speedstep_detect_processor() == SPEEDSTEP_PROCESSOR_P4M) { + if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4M) { printk(KERN_WARNING PFX "Warning: Pentium 4-M detected. " "The speedstep-ich or acpi cpufreq modules offer " "voltage scaling in addition of frequency scaling. " "You should use either one instead of p4-clockmod, " "if possible.\n"); - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_P4M); + return speedstep_get_frequency(SPEEDSTEP_CPU_P4M); } - return speedstep_get_processor_frequency(SPEEDSTEP_PROCESSOR_P4D); + return speedstep_get_frequency(SPEEDSTEP_CPU_P4D); } @@ -203,7 +211,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) unsigned int i; #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif /* Errata workaround */ @@ -217,14 +225,20 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) dprintk("has errata -- disabling low frequencies\n"); } + if (speedstep_detect_processor() == SPEEDSTEP_CPU_P4D && + c->x86_model < 2) { + /* switch to maximum frequency and measure result */ + cpufreq_p4_setdc(policy->cpu, DC_DISABLE); + recalibrate_cpu_khz(); + } /* get max frequency */ stock_freq = cpufreq_p4_get_frequency(c); if (!stock_freq) return -EINVAL; /* table init */ - for (i=1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { - if ((i<2) && (has_N44_O17_errata[policy->cpu])) + for (i = 1; (p4clockmod_table[i].frequency != CPUFREQ_TABLE_END); i++) { + if ((i < 2) && (has_N44_O17_errata[policy->cpu])) p4clockmod_table[i].frequency = CPUFREQ_ENTRY_INVALID; else p4clockmod_table[i].frequency = (stock_freq * i)/8; @@ -232,7 +246,10 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy) cpufreq_frequency_table_get_attr(p4clockmod_table, policy->cpu); /* cpuinfo and default policy values */ - policy->cpuinfo.transition_latency = 1000000; /* assumed */ + + /* the transition latency is set to be 1 higher than the maximum + * transition latency of the ondemand governor */ + policy->cpuinfo.transition_latency = 10000001; policy->cur = stock_freq; return cpufreq_frequency_table_cpuinfo(policy, &p4clockmod_table[0]); @@ -258,12 +275,12 @@ static unsigned int cpufreq_p4_get(unsigned int cpu) l = DC_DISABLE; if (l != DC_DISABLE) - return (stock_freq * l / 8); + return stock_freq * l / 8; return stock_freq; } -static struct freq_attr* p4clockmod_attr[] = { +static struct freq_attr *p4clockmod_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -298,9 +315,10 @@ static int __init cpufreq_p4_init(void) ret = cpufreq_register_driver(&p4clockmod_driver); if (!ret) - printk(KERN_INFO PFX "P4/Xeon(TM) CPU On-Demand Clock Modulation available\n"); + printk(KERN_INFO PFX "P4/Xeon(TM) CPU On-Demand Clock " + "Modulation available\n"); - return (ret); + return ret; } @@ -310,9 +328,9 @@ static void __exit cpufreq_p4_exit(void) } -MODULE_AUTHOR ("Zwane Mwaikambo <zwane@commfireservices.com>"); -MODULE_DESCRIPTION ("cpufreq driver for Pentium(TM) 4/Xeon(TM)"); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Zwane Mwaikambo <zwane@commfireservices.com>"); +MODULE_DESCRIPTION("cpufreq driver for Pentium(TM) 4/Xeon(TM)"); +MODULE_LICENSE("GPL"); late_initcall(cpufreq_p4_init); module_exit(cpufreq_p4_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c index c1ac579..f10dea4 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k6.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k6.c @@ -1,6 +1,7 @@ /* * This file was based upon code in Powertweak Linux (http://powertweak.sf.net) - * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä, Dominik Brodowski. + * (C) 2000-2003 Dave Jones, Arjan van de Ven, Janne Pänkälä, + * Dominik Brodowski. * * Licensed under the terms of the GNU GPL License version 2. * @@ -13,14 +14,15 @@ #include <linux/cpufreq.h> #include <linux/ioport.h> #include <linux/slab.h> - -#include <asm/msr.h> #include <linux/timex.h> #include <linux/io.h> +#include <asm/msr.h> + #define POWERNOW_IOPORT 0xfff0 /* it doesn't matter where, as long as it is unused */ +#define PFX "powernow-k6: " static unsigned int busfreq; /* FSB, in 10 kHz */ static unsigned int max_multiplier; @@ -47,8 +49,8 @@ static struct cpufreq_frequency_table clock_ratio[] = { */ static int powernow_k6_get_cpu_multiplier(void) { - u64 invalue = 0; - u32 msrval; + u64 invalue = 0; + u32 msrval; msrval = POWERNOW_IOPORT + 0x1; wrmsr(MSR_K6_EPMR, msrval, 0); /* enable the PowerNow port */ @@ -68,12 +70,12 @@ static int powernow_k6_get_cpu_multiplier(void) */ static void powernow_k6_set_state(unsigned int best_i) { - unsigned long outvalue = 0, invalue = 0; - unsigned long msrval; - struct cpufreq_freqs freqs; + unsigned long outvalue = 0, invalue = 0; + unsigned long msrval; + struct cpufreq_freqs freqs; if (clock_ratio[best_i].index > max_multiplier) { - printk(KERN_ERR "cpufreq: invalid target frequency\n"); + printk(KERN_ERR PFX "invalid target frequency\n"); return; } @@ -119,7 +121,8 @@ static int powernow_k6_verify(struct cpufreq_policy *policy) * powernow_k6_setpolicy - sets a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * sets a new CPUFreq policy */ @@ -127,9 +130,10 @@ static int powernow_k6_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { - unsigned int newstate = 0; + unsigned int newstate = 0; - if (cpufreq_frequency_table_target(policy, &clock_ratio[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &clock_ratio[0], + target_freq, relation, &newstate)) return -EINVAL; powernow_k6_set_state(newstate); @@ -140,7 +144,7 @@ static int powernow_k6_target(struct cpufreq_policy *policy, static int powernow_k6_cpu_init(struct cpufreq_policy *policy) { - unsigned int i; + unsigned int i, f; int result; if (policy->cpu != 0) @@ -152,10 +156,11 @@ static int powernow_k6_cpu_init(struct cpufreq_policy *policy) /* table init */ for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) { - if (clock_ratio[i].index > max_multiplier) + f = clock_ratio[i].index; + if (f > max_multiplier) clock_ratio[i].frequency = CPUFREQ_ENTRY_INVALID; else - clock_ratio[i].frequency = busfreq * clock_ratio[i].index; + clock_ratio[i].frequency = busfreq * f; } /* cpuinfo and default policy values */ @@ -185,7 +190,9 @@ static int powernow_k6_cpu_exit(struct cpufreq_policy *policy) static unsigned int powernow_k6_get(unsigned int cpu) { - return busfreq * powernow_k6_get_cpu_multiplier(); + unsigned int ret; + ret = (busfreq * powernow_k6_get_cpu_multiplier()); + return ret; } static struct freq_attr *powernow_k6_attr[] = { @@ -221,7 +228,7 @@ static int __init powernow_k6_init(void) return -ENODEV; if (!request_region(POWERNOW_IOPORT, 16, "PowerNow!")) { - printk("cpufreq: PowerNow IOPORT region already used.\n"); + printk(KERN_INFO PFX "PowerNow IOPORT region already used.\n"); return -EIO; } @@ -246,7 +253,8 @@ static void __exit powernow_k6_exit(void) } -MODULE_AUTHOR("Arjan van de Ven, Dave Jones <davej@redhat.com>, Dominik Brodowski <linux@brodo.de>"); +MODULE_AUTHOR("Arjan van de Ven, Dave Jones <davej@redhat.com>, " + "Dominik Brodowski <linux@brodo.de>"); MODULE_DESCRIPTION("PowerNow! driver for AMD K6-2+ / K6-3+ processors."); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c index 1b446d7..3c28ccd 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k7.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k7.c @@ -6,10 +6,12 @@ * Licensed under the terms of the GNU GPL License version 2. * Based upon datasheets & sample CPUs kindly provided by AMD. * - * Errata 5: Processor may fail to execute a FID/VID change in presence of interrupt. - * - We cli/sti on stepping A0 CPUs around the FID/VID transition. - * Errata 15: Processors with half frequency multipliers may hang upon wakeup from disconnect. - * - We disable half multipliers if ACPI is used on A0 stepping CPUs. + * Errata 5: + * CPU may fail to execute a FID/VID change in presence of interrupt. + * - We cli/sti on stepping A0 CPUs around the FID/VID transition. + * Errata 15: + * CPU with half frequency multipliers may hang upon wakeup from disconnect. + * - We disable half multipliers if ACPI is used on A0 stepping CPUs. */ #include <linux/kernel.h> @@ -20,11 +22,11 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/dmi.h> +#include <linux/timex.h> +#include <linux/io.h> +#include <asm/timer.h> /* Needed for recalibrate_cpu_khz() */ #include <asm/msr.h> -#include <asm/timer.h> -#include <asm/timex.h> -#include <asm/io.h> #include <asm/system.h> #ifdef CONFIG_X86_POWERNOW_K7_ACPI @@ -58,9 +60,9 @@ struct pst_s { union powernow_acpi_control_t { struct { unsigned long fid:5, - vid:5, - sgtc:20, - res1:2; + vid:5, + sgtc:20, + res1:2; } bits; unsigned long val; }; @@ -94,14 +96,15 @@ static struct cpufreq_frequency_table *powernow_table; static unsigned int can_scale_bus; static unsigned int can_scale_vid; -static unsigned int minimum_speed=-1; +static unsigned int minimum_speed = -1; static unsigned int maximum_speed; static unsigned int number_scales; static unsigned int fsb; static unsigned int latency; static char have_a0; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "powernow-k7", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "powernow-k7", msg) static int check_fsb(unsigned int fsbspeed) { @@ -109,7 +112,7 @@ static int check_fsb(unsigned int fsbspeed) unsigned int f = fsb / 1000; delta = (fsbspeed > f) ? fsbspeed - f : f - fsbspeed; - return (delta < 5); + return delta < 5; } static int check_powernow(void) @@ -117,24 +120,26 @@ static int check_powernow(void) struct cpuinfo_x86 *c = &cpu_data(0); unsigned int maxei, eax, ebx, ecx, edx; - if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 !=6)) { + if ((c->x86_vendor != X86_VENDOR_AMD) || (c->x86 != 6)) { #ifdef MODULE - printk (KERN_INFO PFX "This module only works with AMD K7 CPUs\n"); + printk(KERN_INFO PFX "This module only works with " + "AMD K7 CPUs\n"); #endif return 0; } /* Get maximum capabilities */ - maxei = cpuid_eax (0x80000000); + maxei = cpuid_eax(0x80000000); if (maxei < 0x80000007) { /* Any powernow info ? */ #ifdef MODULE - printk (KERN_INFO PFX "No powernow capabilities detected\n"); + printk(KERN_INFO PFX "No powernow capabilities detected\n"); #endif return 0; } if ((c->x86_model == 6) && (c->x86_mask == 0)) { - printk (KERN_INFO PFX "K7 660[A0] core detected, enabling errata workarounds\n"); + printk(KERN_INFO PFX "K7 660[A0] core detected, " + "enabling errata workarounds\n"); have_a0 = 1; } @@ -144,37 +149,42 @@ static int check_powernow(void) if (!(edx & (1 << 1 | 1 << 2))) return 0; - printk (KERN_INFO PFX "PowerNOW! Technology present. Can scale: "); + printk(KERN_INFO PFX "PowerNOW! Technology present. Can scale: "); if (edx & 1 << 1) { - printk ("frequency"); - can_scale_bus=1; + printk("frequency"); + can_scale_bus = 1; } if ((edx & (1 << 1 | 1 << 2)) == 0x6) - printk (" and "); + printk(" and "); if (edx & 1 << 2) { - printk ("voltage"); - can_scale_vid=1; + printk("voltage"); + can_scale_vid = 1; } - printk (".\n"); + printk(".\n"); return 1; } +static void invalidate_entry(unsigned int entry) +{ + powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; +} -static int get_ranges (unsigned char *pst) +static int get_ranges(unsigned char *pst) { unsigned int j; unsigned int speed; u8 fid, vid; - powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * (number_scales + 1)), GFP_KERNEL); + powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * + (number_scales + 1)), GFP_KERNEL); if (!powernow_table) return -ENOMEM; - for (j=0 ; j < number_scales; j++) { + for (j = 0 ; j < number_scales; j++) { fid = *pst++; powernow_table[j].frequency = (fsb * fid_codes[fid]) / 10; @@ -182,10 +192,10 @@ static int get_ranges (unsigned char *pst) speed = powernow_table[j].frequency; - if ((fid_codes[fid] % 10)==5) { + if ((fid_codes[fid] % 10) == 5) { #ifdef CONFIG_X86_POWERNOW_K7_ACPI if (have_a0 == 1) - powernow_table[j].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(j); #endif } @@ -197,7 +207,7 @@ static int get_ranges (unsigned char *pst) vid = *pst++; powernow_table[j].index |= (vid << 8); /* upper 8 bits */ - dprintk (" FID: 0x%x (%d.%dx [%dMHz]) " + dprintk(" FID: 0x%x (%d.%dx [%dMHz]) " "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, fid_codes[fid] % 10, speed/1000, vid, mobile_vid_table[vid]/1000, @@ -214,13 +224,13 @@ static void change_FID(int fid) { union msr_fidvidctl fidvidctl; - rdmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + rdmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); if (fidvidctl.bits.FID != fid) { fidvidctl.bits.SGTC = latency; fidvidctl.bits.FID = fid; fidvidctl.bits.VIDC = 0; fidvidctl.bits.FIDC = 1; - wrmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + wrmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); } } @@ -229,18 +239,18 @@ static void change_VID(int vid) { union msr_fidvidctl fidvidctl; - rdmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + rdmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); if (fidvidctl.bits.VID != vid) { fidvidctl.bits.SGTC = latency; fidvidctl.bits.VID = vid; fidvidctl.bits.FIDC = 0; fidvidctl.bits.VIDC = 1; - wrmsrl (MSR_K7_FID_VID_CTL, fidvidctl.val); + wrmsrl(MSR_K7_FID_VID_CTL, fidvidctl.val); } } -static void change_speed (unsigned int index) +static void change_speed(unsigned int index) { u8 fid, vid; struct cpufreq_freqs freqs; @@ -257,7 +267,7 @@ static void change_speed (unsigned int index) freqs.cpu = 0; - rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val); + rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val); cfid = fidvidstatus.bits.CFID; freqs.old = fsb * fid_codes[cfid] / 10; @@ -321,12 +331,14 @@ static int powernow_acpi_init(void) goto err1; } - if (acpi_processor_perf->control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) { + if (acpi_processor_perf->control_register.space_id != + ACPI_ADR_SPACE_FIXED_HARDWARE) { retval = -ENODEV; goto err2; } - if (acpi_processor_perf->status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) { + if (acpi_processor_perf->status_register.space_id != + ACPI_ADR_SPACE_FIXED_HARDWARE) { retval = -ENODEV; goto err2; } @@ -338,7 +350,8 @@ static int powernow_acpi_init(void) goto err2; } - powernow_table = kzalloc((number_scales + 1) * (sizeof(struct cpufreq_frequency_table)), GFP_KERNEL); + powernow_table = kzalloc((sizeof(struct cpufreq_frequency_table) * + (number_scales + 1)), GFP_KERNEL); if (!powernow_table) { retval = -ENOMEM; goto err2; @@ -352,7 +365,7 @@ static int powernow_acpi_init(void) unsigned int speed, speed_mhz; pc.val = (unsigned long) state->control; - dprintk ("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n", + dprintk("acpi: P%d: %d MHz %d mW %d uS control %08x SGTC %d\n", i, (u32) state->core_frequency, (u32) state->power, @@ -381,12 +394,12 @@ static int powernow_acpi_init(void) if (speed % 1000 > 0) speed_mhz++; - if ((fid_codes[fid] % 10)==5) { + if ((fid_codes[fid] % 10) == 5) { if (have_a0 == 1) - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(i); } - dprintk (" FID: 0x%x (%d.%dx [%dMHz]) " + dprintk(" FID: 0x%x (%d.%dx [%dMHz]) " "VID: 0x%x (%d.%03dV)\n", fid, fid_codes[fid] / 10, fid_codes[fid] % 10, speed_mhz, vid, mobile_vid_table[vid]/1000, @@ -422,7 +435,8 @@ err1: err05: kfree(acpi_processor_perf); err0: - printk(KERN_WARNING PFX "ACPI perflib can not be used in this platform\n"); + printk(KERN_WARNING PFX "ACPI perflib can not be used on " + "this platform\n"); acpi_processor_perf = NULL; return retval; } @@ -435,7 +449,14 @@ static int powernow_acpi_init(void) } #endif -static int powernow_decode_bios (int maxfid, int startvid) +static void print_pst_entry(struct pst_s *pst, unsigned int j) +{ + dprintk("PST:%d (@%p)\n", j, pst); + dprintk(" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", + pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid); +} + +static int powernow_decode_bios(int maxfid, int startvid) { struct psb_s *psb; struct pst_s *pst; @@ -446,61 +467,67 @@ static int powernow_decode_bios (int maxfid, int startvid) etuple = cpuid_eax(0x80000001); - for (i=0xC0000; i < 0xffff0 ; i+=16) { + for (i = 0xC0000; i < 0xffff0 ; i += 16) { p = phys_to_virt(i); - if (memcmp(p, "AMDK7PNOW!", 10) == 0){ - dprintk ("Found PSB header at %p\n", p); + if (memcmp(p, "AMDK7PNOW!", 10) == 0) { + dprintk("Found PSB header at %p\n", p); psb = (struct psb_s *) p; - dprintk ("Table version: 0x%x\n", psb->tableversion); + dprintk("Table version: 0x%x\n", psb->tableversion); if (psb->tableversion != 0x12) { - printk (KERN_INFO PFX "Sorry, only v1.2 tables supported right now\n"); + printk(KERN_INFO PFX "Sorry, only v1.2 tables" + " supported right now\n"); return -ENODEV; } - dprintk ("Flags: 0x%x\n", psb->flags); - if ((psb->flags & 1)==0) { - dprintk ("Mobile voltage regulator\n"); - } else { - dprintk ("Desktop voltage regulator\n"); - } + dprintk("Flags: 0x%x\n", psb->flags); + if ((psb->flags & 1) == 0) + dprintk("Mobile voltage regulator\n"); + else + dprintk("Desktop voltage regulator\n"); latency = psb->settlingtime; if (latency < 100) { - printk(KERN_INFO PFX "BIOS set settling time to %d microseconds. " - "Should be at least 100. Correcting.\n", latency); + printk(KERN_INFO PFX "BIOS set settling time " + "to %d microseconds. " + "Should be at least 100. " + "Correcting.\n", latency); latency = 100; } - dprintk ("Settling Time: %d microseconds.\n", psb->settlingtime); - dprintk ("Has %d PST tables. (Only dumping ones relevant to this CPU).\n", psb->numpst); + dprintk("Settling Time: %d microseconds.\n", + psb->settlingtime); + dprintk("Has %d PST tables. (Only dumping ones " + "relevant to this CPU).\n", + psb->numpst); - p += sizeof (struct psb_s); + p += sizeof(struct psb_s); pst = (struct pst_s *) p; - for (j=0; j<psb->numpst; j++) { + for (j = 0; j < psb->numpst; j++) { pst = (struct pst_s *) p; number_scales = pst->numpstates; - if ((etuple == pst->cpuid) && check_fsb(pst->fsbspeed) && - (maxfid==pst->maxfid) && (startvid==pst->startvid)) - { - dprintk ("PST:%d (@%p)\n", j, pst); - dprintk (" cpuid: 0x%x fsb: %d maxFID: 0x%x startvid: 0x%x\n", - pst->cpuid, pst->fsbspeed, pst->maxfid, pst->startvid); - - ret = get_ranges ((char *) pst + sizeof (struct pst_s)); + if ((etuple == pst->cpuid) && + check_fsb(pst->fsbspeed) && + (maxfid == pst->maxfid) && + (startvid == pst->startvid)) { + print_pst_entry(pst, j); + p = (char *)pst + sizeof(struct pst_s); + ret = get_ranges(p); return ret; } else { unsigned int k; - p = (char *) pst + sizeof (struct pst_s); - for (k=0; k<number_scales; k++) - p+=2; + p = (char *)pst + sizeof(struct pst_s); + for (k = 0; k < number_scales; k++) + p += 2; } } - printk (KERN_INFO PFX "No PST tables match this cpuid (0x%x)\n", etuple); - printk (KERN_INFO PFX "This is indicative of a broken BIOS.\n"); + printk(KERN_INFO PFX "No PST tables match this cpuid " + "(0x%x)\n", etuple); + printk(KERN_INFO PFX "This is indicative of a broken " + "BIOS.\n"); return -EINVAL; } @@ -511,13 +538,14 @@ static int powernow_decode_bios (int maxfid, int startvid) } -static int powernow_target (struct cpufreq_policy *policy, +static int powernow_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int newstate; - if (cpufreq_frequency_table_target(policy, powernow_table, target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, powernow_table, target_freq, + relation, &newstate)) return -EINVAL; change_speed(newstate); @@ -526,7 +554,7 @@ static int powernow_target (struct cpufreq_policy *policy, } -static int powernow_verify (struct cpufreq_policy *policy) +static int powernow_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, powernow_table); } @@ -566,18 +594,23 @@ static unsigned int powernow_get(unsigned int cpu) if (cpu) return 0; - rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val); + rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val); cfid = fidvidstatus.bits.CFID; - return (fsb * fid_codes[cfid] / 10); + return fsb * fid_codes[cfid] / 10; } static int __init acer_cpufreq_pst(const struct dmi_system_id *d) { - printk(KERN_WARNING "%s laptop with broken PST tables in BIOS detected.\n", d->ident); - printk(KERN_WARNING "You need to downgrade to 3A21 (09/09/2002), or try a newer BIOS than 3A71 (01/20/2003)\n"); - printk(KERN_WARNING "cpufreq scaling has been disabled as a result of this.\n"); + printk(KERN_WARNING PFX + "%s laptop with broken PST tables in BIOS detected.\n", + d->ident); + printk(KERN_WARNING PFX + "You need to downgrade to 3A21 (09/09/2002), or try a newer " + "BIOS than 3A71 (01/20/2003)\n"); + printk(KERN_WARNING PFX + "cpufreq scaling has been disabled as a result of this.\n"); return 0; } @@ -598,7 +631,7 @@ static struct dmi_system_id __initdata powernow_dmi_table[] = { { } }; -static int __init powernow_cpu_init (struct cpufreq_policy *policy) +static int __init powernow_cpu_init(struct cpufreq_policy *policy) { union msr_fidvidstatus fidvidstatus; int result; @@ -606,7 +639,7 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) if (policy->cpu != 0) return -ENODEV; - rdmsrl (MSR_K7_FID_VID_STATUS, fidvidstatus.val); + rdmsrl(MSR_K7_FID_VID_STATUS, fidvidstatus.val); recalibrate_cpu_khz(); @@ -618,19 +651,21 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) dprintk("FSB: %3dMHz\n", fsb/1000); if (dmi_check_system(powernow_dmi_table) || acpi_force) { - printk (KERN_INFO PFX "PSB/PST known to be broken. Trying ACPI instead\n"); + printk(KERN_INFO PFX "PSB/PST known to be broken. " + "Trying ACPI instead\n"); result = powernow_acpi_init(); } else { - result = powernow_decode_bios(fidvidstatus.bits.MFID, fidvidstatus.bits.SVID); + result = powernow_decode_bios(fidvidstatus.bits.MFID, + fidvidstatus.bits.SVID); if (result) { - printk (KERN_INFO PFX "Trying ACPI perflib\n"); + printk(KERN_INFO PFX "Trying ACPI perflib\n"); maximum_speed = 0; minimum_speed = -1; latency = 0; result = powernow_acpi_init(); if (result) { - printk (KERN_INFO PFX "ACPI and legacy methods failed\n"); - printk (KERN_INFO PFX "See http://www.codemonkey.org.uk/projects/cpufreq/powernow-k7.html\n"); + printk(KERN_INFO PFX + "ACPI and legacy methods failed\n"); } } else { /* SGTC use the bus clock as timer */ @@ -642,10 +677,11 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) if (result) return result; - printk (KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n", + printk(KERN_INFO PFX "Minimum speed %d MHz. Maximum speed %d MHz.\n", minimum_speed/1000, maximum_speed/1000); - policy->cpuinfo.transition_latency = cpufreq_scale(2000000UL, fsb, latency); + policy->cpuinfo.transition_latency = + cpufreq_scale(2000000UL, fsb, latency); policy->cur = powernow_get(0); @@ -654,7 +690,8 @@ static int __init powernow_cpu_init (struct cpufreq_policy *policy) return cpufreq_frequency_table_cpuinfo(policy, powernow_table); } -static int powernow_cpu_exit (struct cpufreq_policy *policy) { +static int powernow_cpu_exit(struct cpufreq_policy *policy) +{ cpufreq_frequency_table_put_attr(policy->cpu); #ifdef CONFIG_X86_POWERNOW_K7_ACPI @@ -669,7 +706,7 @@ static int powernow_cpu_exit (struct cpufreq_policy *policy) { return 0; } -static struct freq_attr* powernow_table_attr[] = { +static struct freq_attr *powernow_table_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -685,15 +722,15 @@ static struct cpufreq_driver powernow_driver = { .attr = powernow_table_attr, }; -static int __init powernow_init (void) +static int __init powernow_init(void) { - if (check_powernow()==0) + if (check_powernow() == 0) return -ENODEV; return cpufreq_register_driver(&powernow_driver); } -static void __exit powernow_exit (void) +static void __exit powernow_exit(void) { cpufreq_unregister_driver(&powernow_driver); } @@ -701,9 +738,9 @@ static void __exit powernow_exit (void) module_param(acpi_force, int, 0444); MODULE_PARM_DESC(acpi_force, "Force ACPI to be used."); -MODULE_AUTHOR ("Dave Jones <davej@redhat.com>"); -MODULE_DESCRIPTION ("Powernow driver for AMD K7 processors."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dave Jones <davej@redhat.com>"); +MODULE_DESCRIPTION("Powernow driver for AMD K7 processors."); +MODULE_LICENSE("GPL"); late_initcall(powernow_init); module_exit(powernow_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 6428aa1..4709ead 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -33,16 +33,14 @@ #include <linux/string.h> #include <linux/cpumask.h> #include <linux/sched.h> /* for current / set_cpus_allowed() */ +#include <linux/io.h> +#include <linux/delay.h> #include <asm/msr.h> -#include <asm/io.h> -#include <asm/delay.h> -#ifdef CONFIG_X86_POWERNOW_K8_ACPI #include <linux/acpi.h> #include <linux/mutex.h> #include <acpi/processor.h> -#endif #define PFX "powernow-k8: " #define VERSION "version 2.20.00" @@ -56,7 +54,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data); static int cpu_family = CPU_OPTERON; #ifndef CONFIG_SMP -DEFINE_PER_CPU(cpumask_t, cpu_core_map); +static inline const struct cpumask *cpu_core_mask(int cpu) +{ + return cpumask_of(0); +} #endif /* Return a frequency in MHz, given an input fid */ @@ -71,7 +72,8 @@ static u32 find_khz_freq_from_fid(u32 fid) return 1000 * find_freq_from_fid(fid); } -static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, u32 pstate) +static u32 find_khz_freq_from_pstate(struct cpufreq_frequency_table *data, + u32 pstate) { return data[pstate].frequency; } @@ -186,7 +188,9 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) return 1; } - lo = fid | (data->currvid << MSR_C_LO_VID_SHIFT) | MSR_C_LO_INIT_FID_VID; + lo = fid; + lo |= (data->currvid << MSR_C_LO_VID_SHIFT); + lo |= MSR_C_LO_INIT_FID_VID; dprintk("writing fid 0x%x, lo 0x%x, hi 0x%x\n", fid, lo, data->plllock * PLL_LOCK_CONVERSION); @@ -194,7 +198,9 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) do { wrmsr(MSR_FIDVID_CTL, lo, data->plllock * PLL_LOCK_CONVERSION); if (i++ > 100) { - printk(KERN_ERR PFX "Hardware error - pending bit very stuck - no further pstate changes possible\n"); + printk(KERN_ERR PFX + "Hardware error - pending bit very stuck - " + "no further pstate changes possible\n"); return 1; } } while (query_current_values_with_pending_wait(data)); @@ -202,14 +208,16 @@ static int write_new_fid(struct powernow_k8_data *data, u32 fid) count_off_irt(data); if (savevid != data->currvid) { - printk(KERN_ERR PFX "vid change on fid trans, old 0x%x, new 0x%x\n", - savevid, data->currvid); + printk(KERN_ERR PFX + "vid change on fid trans, old 0x%x, new 0x%x\n", + savevid, data->currvid); return 1; } if (fid != data->currfid) { - printk(KERN_ERR PFX "fid trans failed, fid 0x%x, curr 0x%x\n", fid, - data->currfid); + printk(KERN_ERR PFX + "fid trans failed, fid 0x%x, curr 0x%x\n", fid, + data->currfid); return 1; } @@ -228,7 +236,9 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) return 1; } - lo = data->currfid | (vid << MSR_C_LO_VID_SHIFT) | MSR_C_LO_INIT_FID_VID; + lo = data->currfid; + lo |= (vid << MSR_C_LO_VID_SHIFT); + lo |= MSR_C_LO_INIT_FID_VID; dprintk("writing vid 0x%x, lo 0x%x, hi 0x%x\n", vid, lo, STOP_GRANT_5NS); @@ -236,20 +246,24 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) do { wrmsr(MSR_FIDVID_CTL, lo, STOP_GRANT_5NS); if (i++ > 100) { - printk(KERN_ERR PFX "internal error - pending bit very stuck - no further pstate changes possible\n"); + printk(KERN_ERR PFX "internal error - pending bit " + "very stuck - no further pstate " + "changes possible\n"); return 1; } } while (query_current_values_with_pending_wait(data)); if (savefid != data->currfid) { - printk(KERN_ERR PFX "fid changed on vid trans, old 0x%x new 0x%x\n", + printk(KERN_ERR PFX "fid changed on vid trans, old " + "0x%x new 0x%x\n", savefid, data->currfid); return 1; } if (vid != data->currvid) { - printk(KERN_ERR PFX "vid trans failed, vid 0x%x, curr 0x%x\n", vid, - data->currvid); + printk(KERN_ERR PFX "vid trans failed, vid 0x%x, " + "curr 0x%x\n", + vid, data->currvid); return 1; } @@ -261,7 +275,8 @@ static int write_new_vid(struct powernow_k8_data *data, u32 vid) * Decreasing vid codes represent increasing voltages: * vid of 0 is 1.550V, vid of 0x1e is 0.800V, vid of VID_OFF is off. */ -static int decrease_vid_code_by_step(struct powernow_k8_data *data, u32 reqvid, u32 step) +static int decrease_vid_code_by_step(struct powernow_k8_data *data, + u32 reqvid, u32 step) { if ((data->currvid - reqvid) > step) reqvid = data->currvid - step; @@ -283,7 +298,8 @@ static int transition_pstate(struct powernow_k8_data *data, u32 pstate) } /* Change Opteron/Athlon64 fid and vid, by the 3 phases. */ -static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 reqvid) +static int transition_fid_vid(struct powernow_k8_data *data, + u32 reqfid, u32 reqvid) { if (core_voltage_pre_transition(data, reqvid)) return 1; @@ -298,7 +314,8 @@ static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 req return 1; if ((reqfid != data->currfid) || (reqvid != data->currvid)) { - printk(KERN_ERR PFX "failed (cpu%d): req 0x%x 0x%x, curr 0x%x 0x%x\n", + printk(KERN_ERR PFX "failed (cpu%d): req 0x%x 0x%x, " + "curr 0x%x 0x%x\n", smp_processor_id(), reqfid, reqvid, data->currfid, data->currvid); return 1; @@ -311,13 +328,15 @@ static int transition_fid_vid(struct powernow_k8_data *data, u32 reqfid, u32 req } /* Phase 1 - core voltage transition ... setup voltage */ -static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid) +static int core_voltage_pre_transition(struct powernow_k8_data *data, + u32 reqvid) { u32 rvosteps = data->rvo; u32 savefid = data->currfid; u32 maxvid, lo; - dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, reqvid 0x%x, rvo 0x%x\n", + dprintk("ph1 (cpu%d): start, currfid 0x%x, currvid 0x%x, " + "reqvid 0x%x, rvo 0x%x\n", smp_processor_id(), data->currfid, data->currvid, reqvid, data->rvo); @@ -340,7 +359,7 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid } else { dprintk("ph1: changing vid for rvo, req 0x%x\n", data->currvid - 1); - if (decrease_vid_code_by_step(data, data->currvid - 1, 1)) + if (decrease_vid_code_by_step(data, data->currvid-1, 1)) return 1; rvosteps--; } @@ -350,7 +369,8 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid return 1; if (savefid != data->currfid) { - printk(KERN_ERR PFX "ph1 err, currfid changed 0x%x\n", data->currfid); + printk(KERN_ERR PFX "ph1 err, currfid changed 0x%x\n", + data->currfid); return 1; } @@ -363,20 +383,24 @@ static int core_voltage_pre_transition(struct powernow_k8_data *data, u32 reqvid /* Phase 2 - core frequency transition */ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) { - u32 vcoreqfid, vcocurrfid, vcofiddiff, fid_interval, savevid = data->currvid; + u32 vcoreqfid, vcocurrfid, vcofiddiff; + u32 fid_interval, savevid = data->currvid; - if ((reqfid < HI_FID_TABLE_BOTTOM) && (data->currfid < HI_FID_TABLE_BOTTOM)) { - printk(KERN_ERR PFX "ph2: illegal lo-lo transition 0x%x 0x%x\n", - reqfid, data->currfid); + if ((reqfid < HI_FID_TABLE_BOTTOM) && + (data->currfid < HI_FID_TABLE_BOTTOM)) { + printk(KERN_ERR PFX "ph2: illegal lo-lo transition " + "0x%x 0x%x\n", reqfid, data->currfid); return 1; } if (data->currfid == reqfid) { - printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n", data->currfid); + printk(KERN_ERR PFX "ph2 null fid transition 0x%x\n", + data->currfid); return 0; } - dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, reqfid 0x%x\n", + dprintk("ph2 (cpu%d): starting, currfid 0x%x, currvid 0x%x, " + "reqfid 0x%x\n", smp_processor_id(), data->currfid, data->currvid, reqfid); @@ -390,14 +414,14 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) if (reqfid > data->currfid) { if (data->currfid > LO_FID_TABLE_TOP) { - if (write_new_fid(data, data->currfid + fid_interval)) { + if (write_new_fid(data, + data->currfid + fid_interval)) return 1; - } } else { if (write_new_fid - (data, 2 + convert_fid_to_vco_fid(data->currfid))) { + (data, + 2 + convert_fid_to_vco_fid(data->currfid))) return 1; - } } } else { if (write_new_fid(data, data->currfid - fid_interval)) @@ -417,7 +441,8 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) if (data->currfid != reqfid) { printk(KERN_ERR PFX - "ph2: mismatch, failed fid transition, curr 0x%x, req 0x%x\n", + "ph2: mismatch, failed fid transition, " + "curr 0x%x, req 0x%x\n", data->currfid, reqfid); return 1; } @@ -435,7 +460,8 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid) } /* Phase 3 - core voltage transition flow ... jump to the final vid. */ -static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvid) +static int core_voltage_post_transition(struct powernow_k8_data *data, + u32 reqvid) { u32 savefid = data->currfid; u32 savereqvid = reqvid; @@ -457,7 +483,8 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi if (data->currvid != reqvid) { printk(KERN_ERR PFX - "ph3: failed vid transition\n, req 0x%x, curr 0x%x", + "ph3: failed vid transition\n, " + "req 0x%x, curr 0x%x", reqvid, data->currvid); return 1; } @@ -508,7 +535,8 @@ static int check_supported_cpu(unsigned int cpu) if ((eax & CPUID_XFAM) == CPUID_XFAM_K8) { if (((eax & CPUID_USE_XFAM_XMOD) != CPUID_USE_XFAM_XMOD) || ((eax & CPUID_XMOD) > CPUID_XMOD_REV_MASK)) { - printk(KERN_INFO PFX "Processor cpuid %x not supported\n", eax); + printk(KERN_INFO PFX + "Processor cpuid %x not supported\n", eax); goto out; } @@ -520,8 +548,10 @@ static int check_supported_cpu(unsigned int cpu) } cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx); - if ((edx & P_STATE_TRANSITION_CAPABLE) != P_STATE_TRANSITION_CAPABLE) { - printk(KERN_INFO PFX "Power state transitions not supported\n"); + if ((edx & P_STATE_TRANSITION_CAPABLE) + != P_STATE_TRANSITION_CAPABLE) { + printk(KERN_INFO PFX + "Power state transitions not supported\n"); goto out; } } else { /* must be a HW Pstate capable processor */ @@ -539,7 +569,8 @@ out: return rc; } -static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) +static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, + u8 maxvid) { unsigned int j; u8 lastfid = 0xff; @@ -550,12 +581,14 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 j, pst[j].vid); return -EINVAL; } - if (pst[j].vid < data->rvo) { /* vid + rvo >= 0 */ + if (pst[j].vid < data->rvo) { + /* vid + rvo >= 0 */ printk(KERN_ERR FW_BUG PFX "0 vid exceeded with pstate" " %d\n", j); return -ENODEV; } - if (pst[j].vid < maxvid + data->rvo) { /* vid + rvo >= maxvid */ + if (pst[j].vid < maxvid + data->rvo) { + /* vid + rvo >= maxvid */ printk(KERN_ERR FW_BUG PFX "maxvid exceeded with pstate" " %d\n", j); return -ENODEV; @@ -579,23 +612,31 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8 return -EINVAL; } if (lastfid > LO_FID_TABLE_TOP) - printk(KERN_INFO FW_BUG PFX "first fid not from lo freq table\n"); + printk(KERN_INFO FW_BUG PFX + "first fid not from lo freq table\n"); return 0; } +static void invalidate_entry(struct powernow_k8_data *data, unsigned int entry) +{ + data->powernow_table[entry].frequency = CPUFREQ_ENTRY_INVALID; +} + static void print_basics(struct powernow_k8_data *data) { int j; for (j = 0; j < data->numps; j++) { - if (data->powernow_table[j].frequency != CPUFREQ_ENTRY_INVALID) { + if (data->powernow_table[j].frequency != + CPUFREQ_ENTRY_INVALID) { if (cpu_family == CPU_HW_PSTATE) { - printk(KERN_INFO PFX " %d : pstate %d (%d MHz)\n", - j, + printk(KERN_INFO PFX + " %d : pstate %d (%d MHz)\n", j, data->powernow_table[j].index, data->powernow_table[j].frequency/1000); } else { - printk(KERN_INFO PFX " %d : fid 0x%x (%d MHz), vid 0x%x\n", + printk(KERN_INFO PFX + " %d : fid 0x%x (%d MHz), vid 0x%x\n", j, data->powernow_table[j].index & 0xff, data->powernow_table[j].frequency/1000, @@ -604,20 +645,25 @@ static void print_basics(struct powernow_k8_data *data) } } if (data->batps) - printk(KERN_INFO PFX "Only %d pstates on battery\n", data->batps); + printk(KERN_INFO PFX "Only %d pstates on battery\n", + data->batps); } -static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, u8 maxvid) +static int fill_powernow_table(struct powernow_k8_data *data, + struct pst_s *pst, u8 maxvid) { struct cpufreq_frequency_table *powernow_table; unsigned int j; - if (data->batps) { /* use ACPI support to get full speed on mains power */ - printk(KERN_WARNING PFX "Only %d pstates usable (use ACPI driver for full range\n", data->batps); + if (data->batps) { + /* use ACPI support to get full speed on mains power */ + printk(KERN_WARNING PFX + "Only %d pstates usable (use ACPI driver for full " + "range\n", data->batps); data->numps = data->batps; } - for ( j=1; j<data->numps; j++ ) { + for (j = 1; j < data->numps; j++) { if (pst[j-1].fid >= pst[j].fid) { printk(KERN_ERR PFX "PST out of sequence\n"); return -EINVAL; @@ -640,9 +686,11 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, } for (j = 0; j < data->numps; j++) { + int freq; powernow_table[j].index = pst[j].fid; /* lower 8 bits */ powernow_table[j].index |= (pst[j].vid << 8); /* upper 8 bits */ - powernow_table[j].frequency = find_khz_freq_from_fid(pst[j].fid); + freq = find_khz_freq_from_fid(pst[j].fid); + powernow_table[j].frequency = freq; } powernow_table[data->numps].frequency = CPUFREQ_TABLE_END; powernow_table[data->numps].index = 0; @@ -654,11 +702,12 @@ static int fill_powernow_table(struct powernow_k8_data *data, struct pst_s *pst, dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid); data->powernow_table = powernow_table; - if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) + if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); for (j = 0; j < data->numps; j++) - if ((pst[j].fid==data->currfid) && (pst[j].vid==data->currvid)) + if ((pst[j].fid == data->currfid) && + (pst[j].vid == data->currvid)) return 0; dprintk("currfid/vid do not match PST, ignoring\n"); @@ -698,7 +747,8 @@ static int find_psb_table(struct powernow_k8_data *data) } data->vstable = psb->vstable; - dprintk("voltage stabilization time: %d(*20us)\n", data->vstable); + dprintk("voltage stabilization time: %d(*20us)\n", + data->vstable); dprintk("flags2: 0x%x\n", psb->flags2); data->rvo = psb->flags2 & 3; @@ -713,11 +763,12 @@ static int find_psb_table(struct powernow_k8_data *data) dprintk("numpst: 0x%x\n", psb->num_tables); cpst = psb->num_tables; - if ((psb->cpuid == 0x00000fc0) || (psb->cpuid == 0x00000fe0) ){ + if ((psb->cpuid == 0x00000fc0) || + (psb->cpuid == 0x00000fe0)) { thiscpuid = cpuid_eax(CPUID_PROCESSOR_SIGNATURE); - if ((thiscpuid == 0x00000fc0) || (thiscpuid == 0x00000fe0) ) { + if ((thiscpuid == 0x00000fc0) || + (thiscpuid == 0x00000fe0)) cpst = 1; - } } if (cpst != 1) { printk(KERN_ERR FW_BUG PFX "numpst must be 1\n"); @@ -732,7 +783,8 @@ static int find_psb_table(struct powernow_k8_data *data) data->numps = psb->numps; dprintk("numpstates: 0x%x\n", data->numps); - return fill_powernow_table(data, (struct pst_s *)(psb+1), maxvid); + return fill_powernow_table(data, + (struct pst_s *)(psb+1), maxvid); } /* * If you see this message, complain to BIOS manufacturer. If @@ -745,28 +797,31 @@ static int find_psb_table(struct powernow_k8_data *data) * BIOS and Kernel Developer's Guide, which is available on * www.amd.com */ - printk(KERN_ERR PFX "BIOS error - no PSB or ACPI _PSS objects\n"); + printk(KERN_ERR FW_BUG PFX "No PSB or ACPI _PSS objects\n"); return -ENODEV; } -#ifdef CONFIG_X86_POWERNOW_K8_ACPI -static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) +static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, + unsigned int index) { + acpi_integer control; + if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE)) return; - data->irt = (data->acpi_data.states[index].control >> IRT_SHIFT) & IRT_MASK; - data->rvo = (data->acpi_data.states[index].control >> RVO_SHIFT) & RVO_MASK; - data->exttype = (data->acpi_data.states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; - data->plllock = (data->acpi_data.states[index].control >> PLL_L_SHIFT) & PLL_L_MASK; - data->vidmvs = 1 << ((data->acpi_data.states[index].control >> MVS_SHIFT) & MVS_MASK); - data->vstable = (data->acpi_data.states[index].control >> VST_SHIFT) & VST_MASK; -} + control = data->acpi_data.states[index].control; data->irt = (control + >> IRT_SHIFT) & IRT_MASK; data->rvo = (control >> + RVO_SHIFT) & RVO_MASK; data->exttype = (control + >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; + data->plllock = (control >> PLL_L_SHIFT) & PLL_L_MASK; data->vidmvs = 1 + << ((control >> MVS_SHIFT) & MVS_MASK); data->vstable = + (control >> VST_SHIFT) & VST_MASK; } static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { struct cpufreq_frequency_table *powernow_table; int ret_val = -ENODEV; + acpi_integer space_id; if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) { dprintk("register performance failed: bad ACPI data\n"); @@ -779,11 +834,12 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) goto err_out; } - if ((data->acpi_data.control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || - (data->acpi_data.status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { + space_id = data->acpi_data.control_register.space_id; + if ((space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || + (space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { dprintk("Invalid control/status registers (%x - %x)\n", data->acpi_data.control_register.space_id, - data->acpi_data.status_register.space_id); + space_id); goto err_out; } @@ -802,13 +858,14 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) if (ret_val) goto err_out_mem; - powernow_table[data->acpi_data.state_count].frequency = CPUFREQ_TABLE_END; + powernow_table[data->acpi_data.state_count].frequency = + CPUFREQ_TABLE_END; powernow_table[data->acpi_data.state_count].index = 0; data->powernow_table = powernow_table; /* fill in data */ data->numps = data->acpi_data.state_count; - if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) + if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu) print_basics(data); powernow_k8_acpi_pst_values(data, 0); @@ -830,13 +887,15 @@ err_out_mem: err_out: acpi_processor_unregister_performance(&data->acpi_data, data->cpu); - /* data->acpi_data.state_count informs us at ->exit() whether ACPI was used */ + /* data->acpi_data.state_count informs us at ->exit() + * whether ACPI was used */ data->acpi_data.state_count = 0; return ret_val; } -static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table) +static int fill_powernow_table_pstate(struct powernow_k8_data *data, + struct cpufreq_frequency_table *powernow_table) { int i; u32 hi = 0, lo = 0; @@ -848,84 +907,101 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf index = data->acpi_data.states[i].control & HW_PSTATE_MASK; if (index > data->max_hw_pstate) { - printk(KERN_ERR PFX "invalid pstate %d - bad value %d.\n", i, index); - printk(KERN_ERR PFX "Please report to BIOS manufacturer\n"); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + printk(KERN_ERR PFX "invalid pstate %d - " + "bad value %d.\n", i, index); + printk(KERN_ERR PFX "Please report to BIOS " + "manufacturer\n"); + invalidate_entry(data, i); continue; } rdmsr(MSR_PSTATE_DEF_BASE + index, lo, hi); if (!(hi & HW_PSTATE_VALID_MASK)) { dprintk("invalid pstate %d, ignoring\n", index); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(data, i); continue; } powernow_table[i].index = index; - powernow_table[i].frequency = data->acpi_data.states[i].core_frequency * 1000; + powernow_table[i].frequency = + data->acpi_data.states[i].core_frequency * 1000; } return 0; } -static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table) +static int fill_powernow_table_fidvid(struct powernow_k8_data *data, + struct cpufreq_frequency_table *powernow_table) { int i; int cntlofreq = 0; + for (i = 0; i < data->acpi_data.state_count; i++) { u32 fid; u32 vid; + u32 freq, index; + acpi_integer status, control; if (data->exttype) { - fid = data->acpi_data.states[i].status & EXT_FID_MASK; - vid = (data->acpi_data.states[i].status >> VID_SHIFT) & EXT_VID_MASK; + status = data->acpi_data.states[i].status; + fid = status & EXT_FID_MASK; + vid = (status >> VID_SHIFT) & EXT_VID_MASK; } else { - fid = data->acpi_data.states[i].control & FID_MASK; - vid = (data->acpi_data.states[i].control >> VID_SHIFT) & VID_MASK; + control = data->acpi_data.states[i].control; + fid = control & FID_MASK; + vid = (control >> VID_SHIFT) & VID_MASK; } dprintk(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid); - powernow_table[i].index = fid; /* lower 8 bits */ - powernow_table[i].index |= (vid << 8); /* upper 8 bits */ - powernow_table[i].frequency = find_khz_freq_from_fid(fid); + index = fid | (vid<<8); + powernow_table[i].index = index; + + freq = find_khz_freq_from_fid(fid); + powernow_table[i].frequency = freq; /* verify frequency is OK */ - if ((powernow_table[i].frequency > (MAX_FREQ * 1000)) || - (powernow_table[i].frequency < (MIN_FREQ * 1000))) { - dprintk("invalid freq %u kHz, ignoring\n", powernow_table[i].frequency); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + if ((freq > (MAX_FREQ * 1000)) || (freq < (MIN_FREQ * 1000))) { + dprintk("invalid freq %u kHz, ignoring\n", freq); + invalidate_entry(data, i); continue; } - /* verify voltage is OK - BIOSs are using "off" to indicate invalid */ + /* verify voltage is OK - + * BIOSs are using "off" to indicate invalid */ if (vid == VID_OFF) { dprintk("invalid vid %u, ignoring\n", vid); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + invalidate_entry(data, i); continue; } /* verify only 1 entry from the lo frequency table */ if (fid < HI_FID_TABLE_BOTTOM) { if (cntlofreq) { - /* if both entries are the same, ignore this one ... */ - if ((powernow_table[i].frequency != powernow_table[cntlofreq].frequency) || - (powernow_table[i].index != powernow_table[cntlofreq].index)) { - printk(KERN_ERR PFX "Too many lo freq table entries\n"); + /* if both entries are the same, + * ignore this one ... */ + if ((freq != powernow_table[cntlofreq].frequency) || + (index != powernow_table[cntlofreq].index)) { + printk(KERN_ERR PFX + "Too many lo freq table " + "entries\n"); return 1; } - dprintk("double low frequency table entry, ignoring it.\n"); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + dprintk("double low frequency table entry, " + "ignoring it.\n"); + invalidate_entry(data, i); continue; } else cntlofreq = i; } - if (powernow_table[i].frequency != (data->acpi_data.states[i].core_frequency * 1000)) { - printk(KERN_INFO PFX "invalid freq entries %u kHz vs. %u kHz\n", - powernow_table[i].frequency, - (unsigned int) (data->acpi_data.states[i].core_frequency * 1000)); - powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; + if (freq != (data->acpi_data.states[i].core_frequency * 1000)) { + printk(KERN_INFO PFX "invalid freq entries " + "%u kHz vs. %u kHz\n", freq, + (unsigned int) + (data->acpi_data.states[i].core_frequency + * 1000)); + invalidate_entry(data, i); continue; } } @@ -935,7 +1011,8 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { if (data->acpi_data.state_count) - acpi_processor_unregister_performance(&data->acpi_data, data->cpu); + acpi_processor_unregister_performance(&data->acpi_data, + data->cpu); free_cpumask_var(data->acpi_data.shared_cpu_map); } @@ -953,15 +1030,9 @@ static int get_transition_latency(struct powernow_k8_data *data) return 1000 * max_latency; } -#else -static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; } -static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; } -static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; } -static int get_transition_latency(struct powernow_k8_data *data) { return 0; } -#endif /* CONFIG_X86_POWERNOW_K8_ACPI */ - /* Take a frequency, and issue the fid/vid transition command */ -static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned int index) +static int transition_frequency_fidvid(struct powernow_k8_data *data, + unsigned int index) { u32 fid = 0; u32 vid = 0; @@ -989,7 +1060,8 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned i return 0; } - if ((fid < HI_FID_TABLE_BOTTOM) && (data->currfid < HI_FID_TABLE_BOTTOM)) { + if ((fid < HI_FID_TABLE_BOTTOM) && + (data->currfid < HI_FID_TABLE_BOTTOM)) { printk(KERN_ERR PFX "ignoring illegal change in lo freq table-%x to 0x%x\n", data->currfid, fid); @@ -1017,7 +1089,8 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data, unsigned i } /* Take a frequency, and issue the hardware pstate transition command */ -static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned int index) +static int transition_frequency_pstate(struct powernow_k8_data *data, + unsigned int index) { u32 pstate = 0; int res, i; @@ -1029,7 +1102,8 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i pstate = index & HW_PSTATE_MASK; if (pstate > data->max_hw_pstate) return 0; - freqs.old = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); + freqs.old = find_khz_freq_from_pstate(data->powernow_table, + data->currpstate); freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate); for_each_cpu_mask_nr(i, *(data->available_cores)) { @@ -1048,7 +1122,8 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i } /* Driver entry point to switch to the target frequency */ -static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation) +static int powernowk8_target(struct cpufreq_policy *pol, + unsigned targfreq, unsigned relation) { cpumask_t oldmask; struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); @@ -1087,14 +1162,18 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi dprintk("targ: curr fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); - if ((checkvid != data->currvid) || (checkfid != data->currfid)) { + if ((checkvid != data->currvid) || + (checkfid != data->currfid)) { printk(KERN_INFO PFX - "error - out of sync, fix 0x%x 0x%x, vid 0x%x 0x%x\n", - checkfid, data->currfid, checkvid, data->currvid); + "error - out of sync, fix 0x%x 0x%x, " + "vid 0x%x 0x%x\n", + checkfid, data->currfid, + checkvid, data->currvid); } } - if (cpufreq_frequency_table_target(pol, data->powernow_table, targfreq, relation, &newstate)) + if (cpufreq_frequency_table_target(pol, data->powernow_table, + targfreq, relation, &newstate)) goto err_out; mutex_lock(&fidvid_mutex); @@ -1114,7 +1193,8 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi mutex_unlock(&fidvid_mutex); if (cpu_family == CPU_HW_PSTATE) - pol->cur = find_khz_freq_from_pstate(data->powernow_table, newstate); + pol->cur = find_khz_freq_from_pstate(data->powernow_table, + newstate); else pol->cur = find_khz_freq_from_fid(data->currfid); ret = 0; @@ -1141,6 +1221,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) struct powernow_k8_data *data; cpumask_t oldmask; int rc; + static int print_once; if (!cpu_online(pol->cpu)) return -ENODEV; @@ -1163,33 +1244,31 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) * an UP version, and is deprecated by AMD. */ if (num_online_cpus() != 1) { -#ifndef CONFIG_ACPI_PROCESSOR - printk(KERN_ERR PFX "ACPI Processor support is required " - "for SMP systems but is absent. Please load the " - "ACPI Processor module before starting this " - "driver.\n"); -#else - printk(KERN_ERR FW_BUG PFX "Your BIOS does not provide" - " ACPI _PSS objects in a way that Linux " - "understands. Please report this to the Linux " - "ACPI maintainers and complain to your BIOS " - "vendor.\n"); -#endif - kfree(data); - return -ENODEV; + /* + * Replace this one with print_once as soon as such a + * thing gets introduced + */ + if (!print_once) { + WARN_ONCE(1, KERN_ERR FW_BUG PFX "Your BIOS " + "does not provide ACPI _PSS objects " + "in a way that Linux understands. " + "Please report this to the Linux ACPI" + " maintainers and complain to your " + "BIOS vendor.\n"); + print_once++; + } + goto err_out; } if (pol->cpu != 0) { printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for " "CPU other than CPU0. Complain to your BIOS " "vendor.\n"); - kfree(data); - return -ENODEV; + goto err_out; } rc = find_psb_table(data); - if (rc) { - kfree(data); - return -ENODEV; - } + if (rc) + goto err_out; + /* Take a crude guess here. * That guess was in microseconds, so multiply with 1000 */ pol->cpuinfo.transition_latency = ( @@ -1204,16 +1283,16 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (smp_processor_id() != pol->cpu) { printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu); - goto err_out; + goto err_out_unmask; } if (pending_bit_stuck()) { printk(KERN_ERR PFX "failing init, change pending bit set\n"); - goto err_out; + goto err_out_unmask; } if (query_current_values_with_pending_wait(data)) - goto err_out; + goto err_out_unmask; if (cpu_family == CPU_OPTERON) fidvid_msr_init(); @@ -1224,11 +1303,12 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) if (cpu_family == CPU_HW_PSTATE) cpumask_copy(pol->cpus, cpumask_of(pol->cpu)); else - cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu)); + cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu)); data->available_cores = pol->cpus; if (cpu_family == CPU_HW_PSTATE) - pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate); + pol->cur = find_khz_freq_from_pstate(data->powernow_table, + data->currpstate); else pol->cur = find_khz_freq_from_fid(data->currfid); dprintk("policy current frequency %d kHz\n", pol->cur); @@ -1245,7 +1325,8 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu); if (cpu_family == CPU_HW_PSTATE) - dprintk("cpu_init done, current pstate 0x%x\n", data->currpstate); + dprintk("cpu_init done, current pstate 0x%x\n", + data->currpstate); else dprintk("cpu_init done, current fid 0x%x, vid 0x%x\n", data->currfid, data->currvid); @@ -1254,15 +1335,16 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) return 0; -err_out: +err_out_unmask: set_cpus_allowed_ptr(current, &oldmask); powernow_k8_cpu_exit_acpi(data); +err_out: kfree(data); return -ENODEV; } -static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol) +static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol) { struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu); @@ -1279,14 +1361,14 @@ static int __devexit powernowk8_cpu_exit (struct cpufreq_policy *pol) return 0; } -static unsigned int powernowk8_get (unsigned int cpu) +static unsigned int powernowk8_get(unsigned int cpu) { struct powernow_k8_data *data; cpumask_t oldmask = current->cpus_allowed; unsigned int khz = 0; unsigned int first; - first = first_cpu(per_cpu(cpu_core_map, cpu)); + first = cpumask_first(cpu_core_mask(cpu)); data = per_cpu(powernow_data, first); if (!data) @@ -1315,7 +1397,7 @@ out: return khz; } -static struct freq_attr* powernow_k8_attr[] = { +static struct freq_attr *powernow_k8_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -1360,7 +1442,8 @@ static void __exit powernowk8_exit(void) cpufreq_unregister_driver(&cpufreq_amd64_driver); } -MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and Mark Langsdorf <mark.langsdorf@amd.com>"); +MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and " + "Mark Langsdorf <mark.langsdorf@amd.com>"); MODULE_DESCRIPTION("AMD Athlon 64 and Opteron processor frequency driver."); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index 8ecc75b..6c6698f 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -45,11 +45,10 @@ struct powernow_k8_data { * frequency is in kHz */ struct cpufreq_frequency_table *powernow_table; -#ifdef CONFIG_X86_POWERNOW_K8_ACPI /* the acpi table needs to be kept. it's only available if ACPI was * used to determine valid frequency/vid/fid states */ struct acpi_processor_performance acpi_data; -#endif + /* we need to keep track of associated cores, but let cpufreq * handle hotplug events - so just point at cpufreq pol->cpus * structure */ @@ -222,10 +221,8 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid); static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index); -#ifdef CONFIG_X86_POWERNOW_K8_ACPI static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table); -#endif #ifdef CONFIG_SMP static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[]) diff --git a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c index 42da9bd..435a996 100644 --- a/arch/x86/kernel/cpu/cpufreq/sc520_freq.c +++ b/arch/x86/kernel/cpu/cpufreq/sc520_freq.c @@ -19,17 +19,19 @@ #include <linux/delay.h> #include <linux/cpufreq.h> +#include <linux/timex.h> +#include <linux/io.h> #include <asm/msr.h> -#include <asm/timex.h> -#include <asm/io.h> #define MMCR_BASE 0xfffef000 /* The default base address */ #define OFFS_CPUCTL 0x2 /* CPU Control Register */ static __u8 __iomem *cpuctl; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "sc520_freq", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "sc520_freq", msg) +#define PFX "sc520_freq: " static struct cpufreq_frequency_table sc520_freq_table[] = { {0x01, 100000}, @@ -43,7 +45,8 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu) switch (clockspeed_reg & 0x03) { default: - printk(KERN_ERR "sc520_freq: error: cpuctl register has unexpected value %02x\n", clockspeed_reg); + printk(KERN_ERR PFX "error: cpuctl register has unexpected " + "value %02x\n", clockspeed_reg); case 0x01: return 100000; case 0x02: @@ -51,7 +54,7 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu) } } -static void sc520_freq_set_cpu_state (unsigned int state) +static void sc520_freq_set_cpu_state(unsigned int state) { struct cpufreq_freqs freqs; @@ -76,18 +79,19 @@ static void sc520_freq_set_cpu_state (unsigned int state) cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE); }; -static int sc520_freq_verify (struct cpufreq_policy *policy) +static int sc520_freq_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, &sc520_freq_table[0]); } -static int sc520_freq_target (struct cpufreq_policy *policy, +static int sc520_freq_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int newstate = 0; - if (cpufreq_frequency_table_target(policy, sc520_freq_table, target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, sc520_freq_table, + target_freq, relation, &newstate)) return -EINVAL; sc520_freq_set_cpu_state(newstate); @@ -116,7 +120,7 @@ static int sc520_freq_cpu_init(struct cpufreq_policy *policy) result = cpufreq_frequency_table_cpuinfo(policy, sc520_freq_table); if (result) - return (result); + return result; cpufreq_frequency_table_get_attr(sc520_freq_table, policy->cpu); @@ -131,7 +135,7 @@ static int sc520_freq_cpu_exit(struct cpufreq_policy *policy) } -static struct freq_attr* sc520_freq_attr[] = { +static struct freq_attr *sc520_freq_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -155,13 +159,13 @@ static int __init sc520_freq_init(void) int err; /* Test if we have the right hardware */ - if(c->x86_vendor != X86_VENDOR_AMD || - c->x86 != 4 || c->x86_model != 9) { + if (c->x86_vendor != X86_VENDOR_AMD || + c->x86 != 4 || c->x86_model != 9) { dprintk("no Elan SC520 processor found!\n"); return -ENODEV; } cpuctl = ioremap((unsigned long)(MMCR_BASE + OFFS_CPUCTL), 1); - if(!cpuctl) { + if (!cpuctl) { printk(KERN_ERR "sc520_freq: error: failed to remap memory\n"); return -ENOMEM; } diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c index dedc1e9..016c1a4 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c @@ -39,7 +39,7 @@ static struct pci_dev *speedstep_chipset_dev; /* speedstep_processor */ -static unsigned int speedstep_processor = 0; +static unsigned int speedstep_processor; static u32 pmbase; @@ -54,7 +54,8 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { }; -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-ich", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "speedstep-ich", msg) /** @@ -62,7 +63,7 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { * * Returns: -ENODEV if no register could be found */ -static int speedstep_find_register (void) +static int speedstep_find_register(void) { if (!speedstep_chipset_dev) return -ENODEV; @@ -90,7 +91,7 @@ static int speedstep_find_register (void) * * Tries to change the SpeedStep state. */ -static void speedstep_set_state (unsigned int state) +static void speedstep_set_state(unsigned int state) { u8 pm2_blk; u8 value; @@ -133,11 +134,11 @@ static void speedstep_set_state (unsigned int state) dprintk("read at pmbase 0x%x + 0x50 returned 0x%x\n", pmbase, value); - if (state == (value & 0x1)) { - dprintk("change to %u MHz succeeded\n", (speedstep_get_processor_frequency(speedstep_processor) / 1000)); - } else { - printk (KERN_ERR "cpufreq: change failed - I/O error\n"); - } + if (state == (value & 0x1)) + dprintk("change to %u MHz succeeded\n", + speedstep_get_frequency(speedstep_processor) / 1000); + else + printk(KERN_ERR "cpufreq: change failed - I/O error\n"); return; } @@ -149,7 +150,7 @@ static void speedstep_set_state (unsigned int state) * Tries to activate the SpeedStep status and control registers. * Returns -EINVAL on an unsupported chipset, and zero on success. */ -static int speedstep_activate (void) +static int speedstep_activate(void) { u16 value = 0; @@ -175,20 +176,18 @@ static int speedstep_activate (void) * functions. Returns the SPEEDSTEP_CHIPSET_-number for the detected * chipset, or zero on failure. */ -static unsigned int speedstep_detect_chipset (void) +static unsigned int speedstep_detect_chipset(void) { speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801DB_12, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (speedstep_chipset_dev) return 4; /* 4-M */ speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_12, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (speedstep_chipset_dev) return 3; /* 3-M */ @@ -196,8 +195,7 @@ static unsigned int speedstep_detect_chipset (void) speedstep_chipset_dev = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801BA_10, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (speedstep_chipset_dev) { /* speedstep.c causes lockups on Dell Inspirons 8000 and @@ -208,8 +206,7 @@ static unsigned int speedstep_detect_chipset (void) hostbridge = pci_get_subsys(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82815_MC, - PCI_ANY_ID, - PCI_ANY_ID, + PCI_ANY_ID, PCI_ANY_ID, NULL); if (!hostbridge) @@ -236,7 +233,7 @@ static unsigned int _speedstep_get(const struct cpumask *cpus) cpus_allowed = current->cpus_allowed; set_cpus_allowed_ptr(current, cpus); - speed = speedstep_get_processor_frequency(speedstep_processor); + speed = speedstep_get_frequency(speedstep_processor); set_cpus_allowed_ptr(current, &cpus_allowed); dprintk("detected %u kHz as current frequency\n", speed); return speed; @@ -251,11 +248,12 @@ static unsigned int speedstep_get(unsigned int cpu) * speedstep_target - set a new CPUFreq policy * @policy: new policy * @target_freq: the target frequency - * @relation: how that frequency relates to achieved frequency (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) + * @relation: how that frequency relates to achieved frequency + * (CPUFREQ_RELATION_L or CPUFREQ_RELATION_H) * * Sets a new CPUFreq policy. */ -static int speedstep_target (struct cpufreq_policy *policy, +static int speedstep_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { @@ -264,7 +262,8 @@ static int speedstep_target (struct cpufreq_policy *policy, cpumask_t cpus_allowed; int i; - if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], + target_freq, relation, &newstate)) return -EINVAL; freqs.old = _speedstep_get(policy->cpus); @@ -308,7 +307,7 @@ static int speedstep_target (struct cpufreq_policy *policy, * Limit must be within speedstep_low_freq and speedstep_high_freq, with * at least one border included. */ -static int speedstep_verify (struct cpufreq_policy *policy) +static int speedstep_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]); } @@ -322,7 +321,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) /* only run on CPU to be set, or on its sibling */ #ifdef CONFIG_SMP - cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu)); + cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu)); #endif cpus_allowed = current->cpus_allowed; @@ -344,7 +343,8 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) return -EIO; dprintk("currently at %s speed setting - %i MHz\n", - (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", + (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) + ? "low" : "high", (speed / 1000)); /* cpuinfo and default policy values */ @@ -352,9 +352,9 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs); if (result) - return (result); + return result; - cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); + cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); return 0; } @@ -366,7 +366,7 @@ static int speedstep_cpu_exit(struct cpufreq_policy *policy) return 0; } -static struct freq_attr* speedstep_attr[] = { +static struct freq_attr *speedstep_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -396,13 +396,15 @@ static int __init speedstep_init(void) /* detect processor */ speedstep_processor = speedstep_detect_processor(); if (!speedstep_processor) { - dprintk("Intel(R) SpeedStep(TM) capable processor not found\n"); + dprintk("Intel(R) SpeedStep(TM) capable processor " + "not found\n"); return -ENODEV; } /* detect chipset */ if (!speedstep_detect_chipset()) { - dprintk("Intel(R) SpeedStep(TM) for this chipset not (yet) available.\n"); + dprintk("Intel(R) SpeedStep(TM) for this chipset not " + "(yet) available.\n"); return -ENODEV; } @@ -431,9 +433,11 @@ static void __exit speedstep_exit(void) } -MODULE_AUTHOR ("Dave Jones <davej@redhat.com>, Dominik Brodowski <linux@brodo.de>"); -MODULE_DESCRIPTION ("Speedstep driver for Intel mobile processors on chipsets with ICH-M southbridges."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dave Jones <davej@redhat.com>, " + "Dominik Brodowski <linux@brodo.de>"); +MODULE_DESCRIPTION("Speedstep driver for Intel mobile processors on chipsets " + "with ICH-M southbridges."); +MODULE_LICENSE("GPL"); module_init(speedstep_init); module_exit(speedstep_exit); diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c index cdac7d6..2e3c686 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c @@ -16,12 +16,16 @@ #include <linux/slab.h> #include <asm/msr.h> +#include <asm/tsc.h> #include "speedstep-lib.h" -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-lib", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "speedstep-lib", msg) + +#define PFX "speedstep-lib: " #ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK -static int relaxed_check = 0; +static int relaxed_check; #else #define relaxed_check 0 #endif @@ -30,14 +34,14 @@ static int relaxed_check = 0; * GET PROCESSOR CORE SPEED IN KHZ * *********************************************************************/ -static unsigned int pentium3_get_frequency (unsigned int processor) +static unsigned int pentium3_get_frequency(unsigned int processor) { - /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */ + /* See table 14 of p3_ds.pdf and table 22 of 29834003.pdf */ struct { unsigned int ratio; /* Frequency Multiplier (x10) */ u8 bitmap; /* power on configuration bits [27, 25:22] (in MSR 0x2a) */ - } msr_decode_mult [] = { + } msr_decode_mult[] = { { 30, 0x01 }, { 35, 0x05 }, { 40, 0x02 }, @@ -52,7 +56,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) { 85, 0x26 }, { 90, 0x20 }, { 100, 0x2b }, - { 0, 0xff } /* error or unknown value */ + { 0, 0xff } /* error or unknown value */ }; /* PIII(-M) FSB settings: see table b1-b of 24547206.pdf */ @@ -60,7 +64,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) unsigned int value; /* Front Side Bus speed in MHz */ u8 bitmap; /* power on configuration bits [18: 19] (in MSR 0x2a) */ - } msr_decode_fsb [] = { + } msr_decode_fsb[] = { { 66, 0x0 }, { 100, 0x2 }, { 133, 0x1 }, @@ -85,7 +89,7 @@ static unsigned int pentium3_get_frequency (unsigned int processor) } /* decode the multiplier */ - if (processor == SPEEDSTEP_PROCESSOR_PIII_C_EARLY) { + if (processor == SPEEDSTEP_CPU_PIII_C_EARLY) { dprintk("workaround for early PIIIs\n"); msr_lo &= 0x03c00000; } else @@ -97,9 +101,10 @@ static unsigned int pentium3_get_frequency (unsigned int processor) j++; } - dprintk("speed is %u\n", (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100)); + dprintk("speed is %u\n", + (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100)); - return (msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100); + return msr_decode_mult[j].ratio * msr_decode_fsb[i].value * 100; } @@ -112,20 +117,23 @@ static unsigned int pentiumM_get_frequency(void) /* see table B-2 of 24547212.pdf */ if (msr_lo & 0x00040000) { - printk(KERN_DEBUG "speedstep-lib: PM - invalid FSB: 0x%x 0x%x\n", msr_lo, msr_tmp); + printk(KERN_DEBUG PFX "PM - invalid FSB: 0x%x 0x%x\n", + msr_lo, msr_tmp); return 0; } msr_tmp = (msr_lo >> 22) & 0x1f; - dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * 100 * 1000)); + dprintk("bits 22-26 are 0x%x, speed is %u\n", + msr_tmp, (msr_tmp * 100 * 1000)); - return (msr_tmp * 100 * 1000); + return msr_tmp * 100 * 1000; } static unsigned int pentium_core_get_frequency(void) { u32 fsb = 0; u32 msr_lo, msr_tmp; + int ret; rdmsr(MSR_FSB_FREQ, msr_lo, msr_tmp); /* see table B-2 of 25366920.pdf */ @@ -153,12 +161,15 @@ static unsigned int pentium_core_get_frequency(void) } rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_tmp); - dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", msr_lo, msr_tmp); + dprintk("PCORE - MSR_IA32_EBL_CR_POWERON: 0x%x 0x%x\n", + msr_lo, msr_tmp); msr_tmp = (msr_lo >> 22) & 0x1f; - dprintk("bits 22-26 are 0x%x, speed is %u\n", msr_tmp, (msr_tmp * fsb)); + dprintk("bits 22-26 are 0x%x, speed is %u\n", + msr_tmp, (msr_tmp * fsb)); - return (msr_tmp * fsb); + ret = (msr_tmp * fsb); + return ret; } @@ -167,6 +178,16 @@ static unsigned int pentium4_get_frequency(void) struct cpuinfo_x86 *c = &boot_cpu_data; u32 msr_lo, msr_hi, mult; unsigned int fsb = 0; + unsigned int ret; + u8 fsb_code; + + /* Pentium 4 Model 0 and 1 do not have the Core Clock Frequency + * to System Bus Frequency Ratio Field in the Processor Frequency + * Configuration Register of the MSR. Therefore the current + * frequency cannot be calculated and has to be measured. + */ + if (c->x86_model < 2) + return cpu_khz; rdmsr(0x2c, msr_lo, msr_hi); @@ -177,62 +198,61 @@ static unsigned int pentium4_get_frequency(void) * revision #12 in Table B-1: MSRs in the Pentium 4 and * Intel Xeon Processors, on page B-4 and B-5. */ - if (c->x86_model < 2) + fsb_code = (msr_lo >> 16) & 0x7; + switch (fsb_code) { + case 0: fsb = 100 * 1000; - else { - u8 fsb_code = (msr_lo >> 16) & 0x7; - switch (fsb_code) { - case 0: - fsb = 100 * 1000; - break; - case 1: - fsb = 13333 * 10; - break; - case 2: - fsb = 200 * 1000; - break; - } + break; + case 1: + fsb = 13333 * 10; + break; + case 2: + fsb = 200 * 1000; + break; } if (!fsb) - printk(KERN_DEBUG "speedstep-lib: couldn't detect FSB speed. Please send an e-mail to <linux@brodo.de>\n"); + printk(KERN_DEBUG PFX "couldn't detect FSB speed. " + "Please send an e-mail to <linux@brodo.de>\n"); /* Multiplier. */ mult = msr_lo >> 24; - dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", fsb, mult, (fsb * mult)); + dprintk("P4 - FSB %u kHz; Multiplier %u; Speed %u kHz\n", + fsb, mult, (fsb * mult)); - return (fsb * mult); + ret = (fsb * mult); + return ret; } -unsigned int speedstep_get_processor_frequency(unsigned int processor) +unsigned int speedstep_get_frequency(unsigned int processor) { switch (processor) { - case SPEEDSTEP_PROCESSOR_PCORE: + case SPEEDSTEP_CPU_PCORE: return pentium_core_get_frequency(); - case SPEEDSTEP_PROCESSOR_PM: + case SPEEDSTEP_CPU_PM: return pentiumM_get_frequency(); - case SPEEDSTEP_PROCESSOR_P4D: - case SPEEDSTEP_PROCESSOR_P4M: + case SPEEDSTEP_CPU_P4D: + case SPEEDSTEP_CPU_P4M: return pentium4_get_frequency(); - case SPEEDSTEP_PROCESSOR_PIII_T: - case SPEEDSTEP_PROCESSOR_PIII_C: - case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: + case SPEEDSTEP_CPU_PIII_T: + case SPEEDSTEP_CPU_PIII_C: + case SPEEDSTEP_CPU_PIII_C_EARLY: return pentium3_get_frequency(processor); default: return 0; }; return 0; } -EXPORT_SYMBOL_GPL(speedstep_get_processor_frequency); +EXPORT_SYMBOL_GPL(speedstep_get_frequency); /********************************************************************* * DETECT SPEEDSTEP-CAPABLE PROCESSOR * *********************************************************************/ -unsigned int speedstep_detect_processor (void) +unsigned int speedstep_detect_processor(void) { struct cpuinfo_x86 *c = &cpu_data(0); u32 ebx, msr_lo, msr_hi; @@ -261,7 +281,7 @@ unsigned int speedstep_detect_processor (void) * sample has ebx = 0x0f, production has 0x0e. */ if ((ebx == 0x0e) || (ebx == 0x0f)) - return SPEEDSTEP_PROCESSOR_P4M; + return SPEEDSTEP_CPU_P4M; break; case 7: /* @@ -272,7 +292,7 @@ unsigned int speedstep_detect_processor (void) * samples are only of B-stepping... */ if (ebx == 0x0e) - return SPEEDSTEP_PROCESSOR_P4M; + return SPEEDSTEP_CPU_P4M; break; case 9: /* @@ -288,10 +308,13 @@ unsigned int speedstep_detect_processor (void) * M-P4-Ms may have either ebx=0xe or 0xf [see above] * M-P4/533 have either ebx=0xe or 0xf. [25317607.pdf] * also, M-P4M HTs have ebx=0x8, too - * For now, they are distinguished by the model_id string + * For now, they are distinguished by the model_id + * string */ - if ((ebx == 0x0e) || (strstr(c->x86_model_id,"Mobile Intel(R) Pentium(R) 4") != NULL)) - return SPEEDSTEP_PROCESSOR_P4M; + if ((ebx == 0x0e) || + (strstr(c->x86_model_id, + "Mobile Intel(R) Pentium(R) 4") != NULL)) + return SPEEDSTEP_CPU_P4M; break; default: break; @@ -301,7 +324,8 @@ unsigned int speedstep_detect_processor (void) switch (c->x86_model) { case 0x0B: /* Intel PIII [Tualatin] */ - /* cpuid_ebx(1) is 0x04 for desktop PIII, 0x06 for mobile PIII-M */ + /* cpuid_ebx(1) is 0x04 for desktop PIII, + * 0x06 for mobile PIII-M */ ebx = cpuid_ebx(0x00000001); dprintk("ebx is %x\n", ebx); @@ -313,14 +337,15 @@ unsigned int speedstep_detect_processor (void) /* So far all PIII-M processors support SpeedStep. See * Intel's 24540640.pdf of June 2003 */ - return SPEEDSTEP_PROCESSOR_PIII_T; + return SPEEDSTEP_CPU_PIII_T; case 0x08: /* Intel PIII [Coppermine] */ /* all mobile PIII Coppermines have FSB 100 MHz * ==> sort out a few desktop PIIIs. */ rdmsr(MSR_IA32_EBL_CR_POWERON, msr_lo, msr_hi); - dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n", msr_lo, msr_hi); + dprintk("Coppermine: MSR_IA32_EBL_CR_POWERON is 0x%x, 0x%x\n", + msr_lo, msr_hi); msr_lo &= 0x00c0000; if (msr_lo != 0x0080000) return 0; @@ -332,13 +357,15 @@ unsigned int speedstep_detect_processor (void) * bit 56 or 57 is set */ rdmsr(MSR_IA32_PLATFORM_ID, msr_lo, msr_hi); - dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", msr_lo, msr_hi); - if ((msr_hi & (1<<18)) && (relaxed_check ? 1 : (msr_hi & (3<<24)))) { + dprintk("Coppermine: MSR_IA32_PLATFORM ID is 0x%x, 0x%x\n", + msr_lo, msr_hi); + if ((msr_hi & (1<<18)) && + (relaxed_check ? 1 : (msr_hi & (3<<24)))) { if (c->x86_mask == 0x01) { dprintk("early PIII version\n"); - return SPEEDSTEP_PROCESSOR_PIII_C_EARLY; + return SPEEDSTEP_CPU_PIII_C_EARLY; } else - return SPEEDSTEP_PROCESSOR_PIII_C; + return SPEEDSTEP_CPU_PIII_C; } default: @@ -369,7 +396,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, dprintk("trying to determine both speeds\n"); /* get current speed */ - prev_speed = speedstep_get_processor_frequency(processor); + prev_speed = speedstep_get_frequency(processor); if (!prev_speed) return -EIO; @@ -379,7 +406,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, /* switch to low state */ set_state(SPEEDSTEP_LOW); - *low_speed = speedstep_get_processor_frequency(processor); + *low_speed = speedstep_get_frequency(processor); if (!*low_speed) { ret = -EIO; goto out; @@ -398,7 +425,7 @@ unsigned int speedstep_get_freqs(unsigned int processor, if (transition_latency) do_gettimeofday(&tv2); - *high_speed = speedstep_get_processor_frequency(processor); + *high_speed = speedstep_get_frequency(processor); if (!*high_speed) { ret = -EIO; goto out; @@ -426,9 +453,12 @@ unsigned int speedstep_get_freqs(unsigned int processor, /* check if the latency measurement is too high or too low * and set it to a safe value (500uSec) in that case */ - if (*transition_latency > 10000000 || *transition_latency < 50000) { - printk (KERN_WARNING "speedstep: frequency transition measured seems out of " - "range (%u nSec), falling back to a safe one of %u nSec.\n", + if (*transition_latency > 10000000 || + *transition_latency < 50000) { + printk(KERN_WARNING PFX "frequency transition " + "measured seems out of range (%u " + "nSec), falling back to a safe one of" + "%u nSec.\n", *transition_latency, 500000); *transition_latency = 500000; } @@ -436,15 +466,16 @@ unsigned int speedstep_get_freqs(unsigned int processor, out: local_irq_restore(flags); - return (ret); + return ret; } EXPORT_SYMBOL_GPL(speedstep_get_freqs); #ifdef CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK module_param(relaxed_check, int, 0444); -MODULE_PARM_DESC(relaxed_check, "Don't do all checks for speedstep capability."); +MODULE_PARM_DESC(relaxed_check, + "Don't do all checks for speedstep capability."); #endif -MODULE_AUTHOR ("Dominik Brodowski <linux@brodo.de>"); -MODULE_DESCRIPTION ("Library for Intel SpeedStep 1 or 2 cpufreq drivers."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>"); +MODULE_DESCRIPTION("Library for Intel SpeedStep 1 or 2 cpufreq drivers."); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h index b11bcc6..2b6c04e 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.h @@ -12,17 +12,17 @@ /* processors */ -#define SPEEDSTEP_PROCESSOR_PIII_C_EARLY 0x00000001 /* Coppermine core */ -#define SPEEDSTEP_PROCESSOR_PIII_C 0x00000002 /* Coppermine core */ -#define SPEEDSTEP_PROCESSOR_PIII_T 0x00000003 /* Tualatin core */ -#define SPEEDSTEP_PROCESSOR_P4M 0x00000004 /* P4-M */ +#define SPEEDSTEP_CPU_PIII_C_EARLY 0x00000001 /* Coppermine core */ +#define SPEEDSTEP_CPU_PIII_C 0x00000002 /* Coppermine core */ +#define SPEEDSTEP_CPU_PIII_T 0x00000003 /* Tualatin core */ +#define SPEEDSTEP_CPU_P4M 0x00000004 /* P4-M */ /* the following processors are not speedstep-capable and are not auto-detected * in speedstep_detect_processor(). However, their speed can be detected using - * the speedstep_get_processor_frequency() call. */ -#define SPEEDSTEP_PROCESSOR_PM 0xFFFFFF03 /* Pentium M */ -#define SPEEDSTEP_PROCESSOR_P4D 0xFFFFFF04 /* desktop P4 */ -#define SPEEDSTEP_PROCESSOR_PCORE 0xFFFFFF05 /* Core */ + * the speedstep_get_frequency() call. */ +#define SPEEDSTEP_CPU_PM 0xFFFFFF03 /* Pentium M */ +#define SPEEDSTEP_CPU_P4D 0xFFFFFF04 /* desktop P4 */ +#define SPEEDSTEP_CPU_PCORE 0xFFFFFF05 /* Core */ /* speedstep states -- only two of them */ @@ -34,7 +34,7 @@ extern unsigned int speedstep_detect_processor (void); /* detect the current speed (in khz) of the processor */ -extern unsigned int speedstep_get_processor_frequency(unsigned int processor); +extern unsigned int speedstep_get_frequency(unsigned int processor); /* detect the low and high speeds of the processor. The callback diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c index 8a85c93..befea08 100644 --- a/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c +++ b/arch/x86/kernel/cpu/cpufreq/speedstep-smi.c @@ -19,8 +19,8 @@ #include <linux/cpufreq.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/io.h> #include <asm/ist.h> -#include <asm/io.h> #include "speedstep-lib.h" @@ -30,12 +30,12 @@ * If user gives it, these are used. * */ -static int smi_port = 0; -static int smi_cmd = 0; -static unsigned int smi_sig = 0; +static int smi_port; +static int smi_cmd; +static unsigned int smi_sig; /* info about the processor */ -static unsigned int speedstep_processor = 0; +static unsigned int speedstep_processor; /* * There are only two frequency states for each processor. Values @@ -56,12 +56,13 @@ static struct cpufreq_frequency_table speedstep_freqs[] = { * of DMA activity going on? */ #define SMI_TRIES 5 -#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "speedstep-smi", msg) +#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \ + "speedstep-smi", msg) /** * speedstep_smi_ownership */ -static int speedstep_smi_ownership (void) +static int speedstep_smi_ownership(void) { u32 command, result, magic, dummy; u32 function = GET_SPEEDSTEP_OWNER; @@ -70,16 +71,18 @@ static int speedstep_smi_ownership (void) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); magic = virt_to_phys(magic_data); - dprintk("trying to obtain ownership with command %x at port %x\n", command, smi_port); + dprintk("trying to obtain ownership with command %x at port %x\n", + command, smi_port); __asm__ __volatile__( "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp\n" - : "=D" (result), "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy), - "=S" (dummy) + : "=D" (result), + "=a" (dummy), "=b" (dummy), "=c" (dummy), "=d" (dummy), + "=S" (dummy) : "a" (command), "b" (function), "c" (0), "d" (smi_port), - "D" (0), "S" (magic) + "D" (0), "S" (magic) : "memory" ); @@ -97,10 +100,10 @@ static int speedstep_smi_ownership (void) * even hangs [cf. bugme.osdl.org # 1422] on earlier systems. Empirical testing * shows that the latter occurs if !(ist_info.event & 0xFFFF). */ -static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) +static int speedstep_smi_get_freqs(unsigned int *low, unsigned int *high) { u32 command, result = 0, edi, high_mhz, low_mhz, dummy; - u32 state=0; + u32 state = 0; u32 function = GET_SPEEDSTEP_FREQS; if (!(ist_info.event & 0xFFFF)) { @@ -110,17 +113,25 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to determine frequencies with command %x at port %x\n", command, smi_port); + dprintk("trying to determine frequencies with command %x at port %x\n", + command, smi_port); __asm__ __volatile__( "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp" - : "=a" (result), "=b" (high_mhz), "=c" (low_mhz), "=d" (state), "=D" (edi), "=S" (dummy) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) + : "=a" (result), + "=b" (high_mhz), + "=c" (low_mhz), + "=d" (state), "=D" (edi), "=S" (dummy) + : "a" (command), + "b" (function), + "c" (state), + "d" (smi_port), "S" (0), "D" (0) ); - dprintk("result %x, low_freq %u, high_freq %u\n", result, low_mhz, high_mhz); + dprintk("result %x, low_freq %u, high_freq %u\n", + result, low_mhz, high_mhz); /* abort if results are obviously incorrect... */ if ((high_mhz + low_mhz) < 600) @@ -137,26 +148,30 @@ static int speedstep_smi_get_freqs (unsigned int *low, unsigned int *high) * @state: processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH) * */ -static int speedstep_get_state (void) +static int speedstep_get_state(void) { - u32 function=GET_SPEEDSTEP_STATE; + u32 function = GET_SPEEDSTEP_STATE; u32 result, state, edi, command, dummy; command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to determine current setting with command %x at port %x\n", command, smi_port); + dprintk("trying to determine current setting with command %x " + "at port %x\n", command, smi_port); __asm__ __volatile__( "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp\n" - : "=a" (result), "=b" (state), "=D" (edi), "=c" (dummy), "=d" (dummy), "=S" (dummy) - : "a" (command), "b" (function), "c" (0), "d" (smi_port), "S" (0), "D" (0) + : "=a" (result), + "=b" (state), "=D" (edi), + "=c" (dummy), "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (0), + "d" (smi_port), "S" (0), "D" (0) ); dprintk("state is %x, result is %x\n", state, result); - return (state & 1); + return state & 1; } @@ -165,11 +180,11 @@ static int speedstep_get_state (void) * @state: new processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH) * */ -static void speedstep_set_state (unsigned int state) +static void speedstep_set_state(unsigned int state) { unsigned int result = 0, command, new_state, dummy; unsigned long flags; - unsigned int function=SET_SPEEDSTEP_STATE; + unsigned int function = SET_SPEEDSTEP_STATE; unsigned int retry = 0; if (state > 0x1) @@ -180,11 +195,14 @@ static void speedstep_set_state (unsigned int state) command = (smi_sig & 0xffffff00) | (smi_cmd & 0xff); - dprintk("trying to set frequency to state %u with command %x at port %x\n", state, command, smi_port); + dprintk("trying to set frequency to state %u " + "with command %x at port %x\n", + state, command, smi_port); do { if (retry) { - dprintk("retry %u, previous result %u, waiting...\n", retry, result); + dprintk("retry %u, previous result %u, waiting...\n", + retry, result); mdelay(retry * 50); } retry++; @@ -192,20 +210,26 @@ static void speedstep_set_state (unsigned int state) "push %%ebp\n" "out %%al, (%%dx)\n" "pop %%ebp" - : "=b" (new_state), "=D" (result), "=c" (dummy), "=a" (dummy), - "=d" (dummy), "=S" (dummy) - : "a" (command), "b" (function), "c" (state), "d" (smi_port), "S" (0), "D" (0) + : "=b" (new_state), "=D" (result), + "=c" (dummy), "=a" (dummy), + "=d" (dummy), "=S" (dummy) + : "a" (command), "b" (function), "c" (state), + "d" (smi_port), "S" (0), "D" (0) ); } while ((new_state != state) && (retry <= SMI_TRIES)); /* enable IRQs */ local_irq_restore(flags); - if (new_state == state) { - dprintk("change to %u MHz succeeded after %u tries with result %u\n", (speedstep_freqs[new_state].frequency / 1000), retry, result); - } else { - printk(KERN_ERR "cpufreq: change to state %u failed with new_state %u and result %u\n", state, new_state, result); - } + if (new_state == state) + dprintk("change to %u MHz succeeded after %u tries " + "with result %u\n", + (speedstep_freqs[new_state].frequency / 1000), + retry, result); + else + printk(KERN_ERR "cpufreq: change to state %u " + "failed with new_state %u and result %u\n", + state, new_state, result); return; } @@ -219,13 +243,14 @@ static void speedstep_set_state (unsigned int state) * * Sets a new CPUFreq policy/freq. */ -static int speedstep_target (struct cpufreq_policy *policy, +static int speedstep_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { unsigned int newstate = 0; struct cpufreq_freqs freqs; - if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], target_freq, relation, &newstate)) + if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0], + target_freq, relation, &newstate)) return -EINVAL; freqs.old = speedstep_freqs[speedstep_get_state()].frequency; @@ -250,7 +275,7 @@ static int speedstep_target (struct cpufreq_policy *policy, * Limit must be within speedstep_low_freq and speedstep_high_freq, with * at least one border included. */ -static int speedstep_verify (struct cpufreq_policy *policy) +static int speedstep_verify(struct cpufreq_policy *policy) { return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]); } @@ -259,7 +284,8 @@ static int speedstep_verify (struct cpufreq_policy *policy) static int speedstep_cpu_init(struct cpufreq_policy *policy) { int result; - unsigned int speed,state; + unsigned int speed, state; + unsigned int *low, *high; /* capability check */ if (policy->cpu != 0) @@ -272,19 +298,23 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) } /* detect low and high frequency */ - result = speedstep_smi_get_freqs(&speedstep_freqs[SPEEDSTEP_LOW].frequency, - &speedstep_freqs[SPEEDSTEP_HIGH].frequency); + low = &speedstep_freqs[SPEEDSTEP_LOW].frequency; + high = &speedstep_freqs[SPEEDSTEP_HIGH].frequency; + + result = speedstep_smi_get_freqs(low, high); if (result) { - /* fall back to speedstep_lib.c dection mechanism: try both states out */ - dprintk("could not detect low and high frequencies by SMI call.\n"); + /* fall back to speedstep_lib.c dection mechanism: + * try both states out */ + dprintk("could not detect low and high frequencies " + "by SMI call.\n"); result = speedstep_get_freqs(speedstep_processor, - &speedstep_freqs[SPEEDSTEP_LOW].frequency, - &speedstep_freqs[SPEEDSTEP_HIGH].frequency, + low, high, NULL, &speedstep_set_state); if (result) { - dprintk("could not detect two different speeds -- aborting.\n"); + dprintk("could not detect two different speeds" + " -- aborting.\n"); return result; } else dprintk("workaround worked.\n"); @@ -295,7 +325,8 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) speed = speedstep_freqs[state].frequency; dprintk("currently at %s speed setting - %i MHz\n", - (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) ? "low" : "high", + (speed == speedstep_freqs[SPEEDSTEP_LOW].frequency) + ? "low" : "high", (speed / 1000)); /* cpuinfo and default policy values */ @@ -304,7 +335,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy) result = cpufreq_frequency_table_cpuinfo(policy, speedstep_freqs); if (result) - return (result); + return result; cpufreq_frequency_table_get_attr(speedstep_freqs, policy->cpu); @@ -321,7 +352,7 @@ static unsigned int speedstep_get(unsigned int cpu) { if (cpu) return -ENODEV; - return speedstep_get_processor_frequency(speedstep_processor); + return speedstep_get_frequency(speedstep_processor); } @@ -335,7 +366,7 @@ static int speedstep_resume(struct cpufreq_policy *policy) return result; } -static struct freq_attr* speedstep_attr[] = { +static struct freq_attr *speedstep_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, NULL, }; @@ -364,21 +395,23 @@ static int __init speedstep_init(void) speedstep_processor = speedstep_detect_processor(); switch (speedstep_processor) { - case SPEEDSTEP_PROCESSOR_PIII_T: - case SPEEDSTEP_PROCESSOR_PIII_C: - case SPEEDSTEP_PROCESSOR_PIII_C_EARLY: + case SPEEDSTEP_CPU_PIII_T: + case SPEEDSTEP_CPU_PIII_C: + case SPEEDSTEP_CPU_PIII_C_EARLY: break; default: speedstep_processor = 0; } if (!speedstep_processor) { - dprintk ("No supported Intel CPU detected.\n"); + dprintk("No supported Intel CPU detected.\n"); return -ENODEV; } - dprintk("signature:0x%.8lx, command:0x%.8lx, event:0x%.8lx, perf_level:0x%.8lx.\n", - ist_info.signature, ist_info.command, ist_info.event, ist_info.perf_level); + dprintk("signature:0x%.8lx, command:0x%.8lx, " + "event:0x%.8lx, perf_level:0x%.8lx.\n", + ist_info.signature, ist_info.command, + ist_info.event, ist_info.perf_level); /* Error if no IST-SMI BIOS or no PARM sig= 'ISGE' aka 'Intel Speedstep Gate E' */ @@ -416,17 +449,20 @@ static void __exit speedstep_exit(void) cpufreq_unregister_driver(&speedstep_driver); } -module_param(smi_port, int, 0444); -module_param(smi_cmd, int, 0444); -module_param(smi_sig, uint, 0444); +module_param(smi_port, int, 0444); +module_param(smi_cmd, int, 0444); +module_param(smi_sig, uint, 0444); -MODULE_PARM_DESC(smi_port, "Override the BIOS-given IST port with this value -- Intel's default setting is 0xb2"); -MODULE_PARM_DESC(smi_cmd, "Override the BIOS-given IST command with this value -- Intel's default setting is 0x82"); -MODULE_PARM_DESC(smi_sig, "Set to 1 to fake the IST signature when using the SMI interface."); +MODULE_PARM_DESC(smi_port, "Override the BIOS-given IST port with this value " + "-- Intel's default setting is 0xb2"); +MODULE_PARM_DESC(smi_cmd, "Override the BIOS-given IST command with this value " + "-- Intel's default setting is 0x82"); +MODULE_PARM_DESC(smi_sig, "Set to 1 to fake the IST signature when using the " + "SMI interface."); -MODULE_AUTHOR ("Hiroshi Miura"); -MODULE_DESCRIPTION ("Speedstep driver for IST applet SMI interface."); -MODULE_LICENSE ("GPL"); +MODULE_AUTHOR("Hiroshi Miura"); +MODULE_DESCRIPTION("Speedstep driver for IST applet SMI interface."); +MODULE_LICENSE("GPL"); module_init(speedstep_init); module_exit(speedstep_exit); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b09d4eb..7437fa1 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -4,6 +4,7 @@ #include <linux/string.h> #include <linux/bitops.h> #include <linux/smp.h> +#include <linux/sched.h> #include <linux/thread_info.h> #include <linux/module.h> @@ -61,11 +62,16 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate - * with P/T states and does not stop in deep C-states + * with P/T states and does not stop in deep C-states. + * + * It is also reliable across cores and sockets. (but not across + * cabinets - we turn it off in that case explicitly.) */ if (c->x86_power & (1 << 8)) { set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); + set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE); + sched_clock_stable = 1; } /* diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index c471eb1..483eda9 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -159,7 +159,7 @@ struct _cpuid4_info_regs { unsigned long can_disable; }; -#ifdef CONFIG_PCI +#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS) static struct pci_device_id k8_nb_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) }, @@ -324,15 +324,6 @@ __cpuinit cpuid4_cache_lookup_regs(int index, return 0; } -static int -__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) -{ - struct _cpuid4_info_regs *leaf_regs = - (struct _cpuid4_info_regs *)this_leaf; - - return cpuid4_cache_lookup_regs(index, leaf_regs); -} - static int __cpuinit find_num_cache_leaves(void) { unsigned int eax, ebx, ecx, edx; @@ -508,6 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) return l2; } +#ifdef CONFIG_SYSFS + /* pointer to _cpuid4_info array (for each cache leaf) */ static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info); #define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y])) @@ -571,6 +564,15 @@ static void __cpuinit free_cache_attributes(unsigned int cpu) per_cpu(cpuid4_info, cpu) = NULL; } +static int +__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf) +{ + struct _cpuid4_info_regs *leaf_regs = + (struct _cpuid4_info_regs *)this_leaf; + + return cpuid4_cache_lookup_regs(index, leaf_regs); +} + static void __cpuinit get_cpu_leaves(void *_retval) { int j, *retval = _retval, cpu = smp_processor_id(); @@ -612,8 +614,6 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu) return retval; } -#ifdef CONFIG_SYSFS - #include <linux/kobject.h> #include <linux/sysfs.h> diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c index ca14604..863f895 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_64.c @@ -990,7 +990,7 @@ static struct sysdev_attribute *mce_attributes[] = { NULL }; -static cpumask_t mce_device_initialized = CPU_MASK_NONE; +static cpumask_var_t mce_device_initialized; /* Per cpu sysdev init. All of the cpus still share the same ctl bank */ static __cpuinit int mce_create_device(unsigned int cpu) @@ -1021,7 +1021,7 @@ static __cpuinit int mce_create_device(unsigned int cpu) if (err) goto error2; } - cpu_set(cpu, mce_device_initialized); + cpumask_set_cpu(cpu, mce_device_initialized); return 0; error2: @@ -1043,7 +1043,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu) { int i; - if (!cpu_isset(cpu, mce_device_initialized)) + if (!cpumask_test_cpu(cpu, mce_device_initialized)) return; for (i = 0; mce_attributes[i]; i++) @@ -1053,7 +1053,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu) sysdev_remove_file(&per_cpu(device_mce, cpu), &bank_attrs[i]); sysdev_unregister(&per_cpu(device_mce,cpu)); - cpu_clear(cpu, mce_device_initialized); + cpumask_clear_cpu(cpu, mce_device_initialized); } /* Make sure there are no machine checks on offlined CPUs. */ @@ -1162,6 +1162,8 @@ static __init int mce_init_device(void) if (!mce_available(&boot_cpu_data)) return -EIO; + alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL); + err = mce_init_banks(); if (err) return err; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c index 7d01be8..56dde9c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c @@ -485,7 +485,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = cpumask_first(&per_cpu(cpu_core_map, cpu)); + i = cpumask_first(cpu_core_mask(cpu)); /* first core not up yet */ if (cpu_data(i).cpu_core_id) @@ -505,7 +505,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); + cpumask_copy(b->cpus, cpu_core_mask(cpu)); per_cpu(threshold_banks, cpu)[bank] = b; goto out; } @@ -529,7 +529,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifndef CONFIG_SMP cpumask_setall(b->cpus); #else - cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu)); + cpumask_copy(b->cpus, cpu_core_mask(cpu)); #endif per_cpu(threshold_banks, cpu)[bank] = b; diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c index 57df3d3..d6b72df 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c @@ -249,7 +249,7 @@ void cmci_rediscover(int dying) for_each_online_cpu (cpu) { if (cpu == dying) continue; - if (set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu))) + if (set_cpus_allowed_ptr(current, cpumask_of(cpu))) continue; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 37f28fc..0b776c0 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -462,9 +462,6 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, *base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT; *type = base_lo & 0xff; - printk(KERN_DEBUG " get_mtrr: cpu%d reg%02d base=%010lx size=%010lx %s\n", - cpu, reg, *base, *size, - mtrr_attrib_to_str(*type & 0xff)); out_put_cpu: put_cpu(); } diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4c42146..fb73a52 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -377,10 +377,6 @@ static const struct file_operations mtrr_fops = { .release = mtrr_close, }; - -static struct proc_dir_entry *proc_root_mtrr; - - static int mtrr_seq_show(struct seq_file *seq, void *offset) { char factor; @@ -423,11 +419,7 @@ static int __init mtrr_if_init(void) (!cpu_has(c, X86_FEATURE_CENTAUR_MCR))) return -ENODEV; - proc_root_mtrr = - proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); - - if (proc_root_mtrr) - proc_root_mtrr->owner = THIS_MODULE; + proc_create("mtrr", S_IWUSR | S_IRUGO, NULL, &mtrr_fops); return 0; } diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index d67e0e4..f93047f 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, if (c->x86_max_cores * smp_num_siblings > 1) { seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); seq_printf(m, "siblings\t: %d\n", - cpus_weight(per_cpu(cpu_core_map, cpu))); + cpumask_weight(cpu_sibling_mask(cpu))); seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); seq_printf(m, "apicid\t\t: %d\n", c->apicid); @@ -143,9 +143,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) static void *c_start(struct seq_file *m, loff_t *pos) { if (*pos == 0) /* just in case, cpu 0 is not the first */ - *pos = first_cpu(cpu_online_map); + *pos = cpumask_first(cpu_online_mask); else - *pos = next_cpu_nr(*pos - 1, cpu_online_map); + *pos = cpumask_next(*pos - 1, cpu_online_mask); if ((*pos) < nr_cpu_ids) return &cpu_data(*pos); return NULL; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 87d103d..95ea5fa 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -10,10 +10,12 @@ #include <linux/kdebug.h> #include <linux/module.h> #include <linux/ptrace.h> +#include <linux/ftrace.h> #include <linux/kexec.h> #include <linux/bug.h> #include <linux/nmi.h> #include <linux/sysfs.h> +#include <linux/ftrace.h> #include <asm/stacktrace.h> @@ -195,6 +197,11 @@ unsigned __kprobes long oops_begin(void) int cpu; unsigned long flags; + /* notify the hw-branch tracer so it may disable tracing and + add the last trace to the trace buffer - + the earlier this happens, the more useful the trace. */ + trace_hw_branch_oops(); + oops_enter(); /* racy, but better than risking deadlock. */ diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb638d9..ef2c356 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -233,7 +233,7 @@ void __init e820_print_map(char *who) */ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, - int *pnr_map) + u32 *pnr_map) { struct change_member { struct e820entry *pbios; /* pointer to original bios entry */ @@ -552,7 +552,7 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, void __init update_e820(void) { - int nr_map; + u32 nr_map; nr_map = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map)) @@ -563,7 +563,7 @@ void __init update_e820(void) } static void __init update_e820_saved(void) { - int nr_map; + u32 nr_map; nr_map = e820_saved.nr_map; if (sanitize_e820_map(e820_saved.map, ARRAY_SIZE(e820_saved.map), &nr_map)) @@ -1303,7 +1303,7 @@ early_param("memmap", parse_memmap_opt); void __init finish_e820_parsing(void) { if (userdef) { - int nr = e820.nr_map; + u32 nr = e820.nr_map; if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr) < 0) early_panic("Invalid user supplied memory map"); @@ -1386,7 +1386,7 @@ void __init e820_reserve_resources_late(void) char *__init default_machine_specific_memory_setup(void) { char *who = "BIOS-e820"; - int new_nr; + u32 new_nr; /* * Try to copy the BIOS-supplied E820-map. * diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 231bdd3..18dfa30 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -18,14 +18,28 @@ #include <linux/init.h> #include <linux/list.h> +#include <trace/syscall.h> + +#include <asm/cacheflush.h> #include <asm/ftrace.h> -#include <linux/ftrace.h> #include <asm/nops.h> #include <asm/nmi.h> #ifdef CONFIG_DYNAMIC_FTRACE +int ftrace_arch_code_modify_prepare(void) +{ + set_kernel_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_kernel_text_ro(); + return 0; +} + union ftrace_code_union { char code[MCOUNT_INSN_SIZE]; struct { @@ -66,11 +80,11 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * * 1) Put the instruction pointer into the IP buffer * and the new code into the "code" buffer. - * 2) Set a flag that says we are modifying code - * 3) Wait for any running NMIs to finish. - * 4) Write the code - * 5) clear the flag. - * 6) Wait for any running NMIs to finish. + * 2) Wait for any running NMIs to finish and set a flag that says + * we are modifying code, it is done in an atomic operation. + * 3) Write the code + * 4) clear the flag. + * 5) Wait for any running NMIs to finish. * * If an NMI is executed, the first thing it does is to call * "ftrace_nmi_enter". This will check if the flag is set to write @@ -82,9 +96,9 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) * are the same as what exists. */ -static atomic_t in_nmi = ATOMIC_INIT(0); +#define MOD_CODE_WRITE_FLAG (1 << 31) /* set when NMI should do the write */ +static atomic_t nmi_running = ATOMIC_INIT(0); static int mod_code_status; /* holds return value of text write */ -static int mod_code_write; /* set when NMI should do the write */ static void *mod_code_ip; /* holds the IP to write to */ static void *mod_code_newcode; /* holds the text to write to the IP */ @@ -101,6 +115,20 @@ int ftrace_arch_read_dyn_info(char *buf, int size) return r; } +static void clear_mod_flag(void) +{ + int old = atomic_read(&nmi_running); + + for (;;) { + int new = old & ~MOD_CODE_WRITE_FLAG; + + if (old == new) + break; + + old = atomic_cmpxchg(&nmi_running, old, new); + } +} + static void ftrace_mod_code(void) { /* @@ -111,37 +139,52 @@ static void ftrace_mod_code(void) */ mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); + + /* if we fail, then kill any new writers */ + if (mod_code_status) + clear_mod_flag(); } void ftrace_nmi_enter(void) { - atomic_inc(&in_nmi); - /* Must have in_nmi seen before reading write flag */ - smp_mb(); - if (mod_code_write) { + if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) { + smp_rmb(); ftrace_mod_code(); atomic_inc(&nmi_update_count); } + /* Must have previous changes seen before executions */ + smp_mb(); } void ftrace_nmi_exit(void) { - /* Finish all executions before clearing in_nmi */ - smp_wmb(); - atomic_dec(&in_nmi); + /* Finish all executions before clearing nmi_running */ + smp_mb(); + atomic_dec(&nmi_running); +} + +static void wait_for_nmi_and_set_mod_flag(void) +{ + if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)) + return; + + do { + cpu_relax(); + } while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG)); + + nmi_wait_count++; } static void wait_for_nmi(void) { - int waited = 0; + if (!atomic_read(&nmi_running)) + return; - while (atomic_read(&in_nmi)) { - waited = 1; + do { cpu_relax(); - } + } while (atomic_read(&nmi_running)); - if (waited) - nmi_wait_count++; + nmi_wait_count++; } static int @@ -151,14 +194,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) mod_code_newcode = new_code; /* The buffers need to be visible before we let NMIs write them */ - smp_wmb(); - - mod_code_write = 1; - - /* Make sure write bit is visible before we wait on NMIs */ smp_mb(); - wait_for_nmi(); + wait_for_nmi_and_set_mod_flag(); /* Make sure all running NMIs have finished before we write the code */ smp_mb(); @@ -166,13 +204,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code) ftrace_mod_code(); /* Make sure the write happens before clearing the bit */ - smp_wmb(); - - mod_code_write = 0; - - /* make sure NMIs see the cleared bit */ smp_mb(); + clear_mod_flag(); wait_for_nmi(); return mod_code_status; @@ -368,100 +402,8 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, old_offset, new_offset); } -#else /* CONFIG_DYNAMIC_FTRACE */ - -/* - * These functions are picked from those used on - * this page for dynamic ftrace. They have been - * simplified to ignore all traces in NMI context. - */ -static atomic_t in_nmi; - -void ftrace_nmi_enter(void) -{ - atomic_inc(&in_nmi); -} - -void ftrace_nmi_exit(void) -{ - atomic_dec(&in_nmi); -} - #endif /* !CONFIG_DYNAMIC_FTRACE */ -/* Add a function return address to the trace stack on thread info.*/ -static int push_return_trace(unsigned long ret, unsigned long long time, - unsigned long func, int *depth) -{ - int index; - - if (!current->ret_stack) - return -EBUSY; - - /* The return trace stack is full */ - if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) { - atomic_inc(¤t->trace_overrun); - return -EBUSY; - } - - index = ++current->curr_ret_stack; - barrier(); - current->ret_stack[index].ret = ret; - current->ret_stack[index].func = func; - current->ret_stack[index].calltime = time; - *depth = index; - - return 0; -} - -/* Retrieve a function return address to the trace stack on thread info.*/ -static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret) -{ - int index; - - index = current->curr_ret_stack; - - if (unlikely(index < 0)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic, otherwise we have no where to go */ - *ret = (unsigned long)panic; - return; - } - - *ret = current->ret_stack[index].ret; - trace->func = current->ret_stack[index].func; - trace->calltime = current->ret_stack[index].calltime; - trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; - barrier(); - current->curr_ret_stack--; - -} - -/* - * Send the trace to the ring-buffer. - * @return the original return address. - */ -unsigned long ftrace_return_to_handler(void) -{ - struct ftrace_graph_ret trace; - unsigned long ret; - - pop_return_trace(&trace, &ret); - trace.rettime = cpu_clock(raw_smp_processor_id()); - ftrace_graph_return(&trace); - - if (unlikely(!ret)) { - ftrace_graph_stop(); - WARN_ON(1); - /* Might as well panic. What else to do? */ - ret = (unsigned long)panic; - } - - return ret; -} - /* * Hook the return address and push it in the stack of return addrs * in current thread info. @@ -469,14 +411,13 @@ unsigned long ftrace_return_to_handler(void) void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - unsigned long long calltime; int faulted; struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; /* Nmi's are currently unsupported */ - if (unlikely(atomic_read(&in_nmi))) + if (unlikely(in_nmi())) return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) @@ -512,17 +453,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - if (unlikely(!__kernel_text_address(old))) { - ftrace_graph_stop(); - *parent = old; - WARN_ON(1); - return; - } - - calltime = cpu_clock(raw_smp_processor_id()); - - if (push_return_trace(old, calltime, - self_addr, &trace.depth) == -EBUSY) { + if (ftrace_push_return_trace(old, self_addr, &trace.depth) == -EBUSY) { *parent = old; return; } @@ -536,3 +467,66 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_FTRACE_SYSCALLS + +extern unsigned long __start_syscalls_metadata[]; +extern unsigned long __stop_syscalls_metadata[]; +extern unsigned long *sys_call_table; + +static struct syscall_metadata **syscalls_metadata; + +static struct syscall_metadata *find_syscall_meta(unsigned long *syscall) +{ + struct syscall_metadata *start; + struct syscall_metadata *stop; + char str[KSYM_SYMBOL_LEN]; + + + start = (struct syscall_metadata *)__start_syscalls_metadata; + stop = (struct syscall_metadata *)__stop_syscalls_metadata; + kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str); + + for ( ; start < stop; start++) { + if (start->name && !strcmp(start->name, str)) + return start; + } + return NULL; +} + +struct syscall_metadata *syscall_nr_to_meta(int nr) +{ + if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0) + return NULL; + + return syscalls_metadata[nr]; +} + +void arch_init_ftrace_syscalls(void) +{ + int i; + struct syscall_metadata *meta; + unsigned long **psys_syscall_table = &sys_call_table; + static atomic_t refs; + + if (atomic_inc_return(&refs) != 1) + goto end; + + syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * + FTRACE_SYSCALL_MAX, GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } + + for (i = 0; i < FTRACE_SYSCALL_MAX; i++) { + meta = find_syscall_meta(psys_syscall_table[i]); + syscalls_metadata[i] = meta; + } + return; + + /* Paranoid: avoid overflow */ +end: + atomic_dec(&refs); +} +#endif diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a00545f..648b3a2 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -80,6 +80,7 @@ static inline void hpet_clear_mapping(void) */ static int boot_hpet_disable; int hpet_force_user; +static int hpet_verbose; static int __init hpet_setup(char *str) { @@ -88,6 +89,8 @@ static int __init hpet_setup(char *str) boot_hpet_disable = 1; if (!strncmp("force", str, 5)) hpet_force_user = 1; + if (!strncmp("verbose", str, 7)) + hpet_verbose = 1; } return 1; } @@ -119,6 +122,43 @@ int is_hpet_enabled(void) } EXPORT_SYMBOL_GPL(is_hpet_enabled); +static void _hpet_print_config(const char *function, int line) +{ + u32 i, timers, l, h; + printk(KERN_INFO "hpet: %s(%d):\n", function, line); + l = hpet_readl(HPET_ID); + h = hpet_readl(HPET_PERIOD); + timers = ((l & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1; + printk(KERN_INFO "hpet: ID: 0x%x, PERIOD: 0x%x\n", l, h); + l = hpet_readl(HPET_CFG); + h = hpet_readl(HPET_STATUS); + printk(KERN_INFO "hpet: CFG: 0x%x, STATUS: 0x%x\n", l, h); + l = hpet_readl(HPET_COUNTER); + h = hpet_readl(HPET_COUNTER+4); + printk(KERN_INFO "hpet: COUNTER_l: 0x%x, COUNTER_h: 0x%x\n", l, h); + + for (i = 0; i < timers; i++) { + l = hpet_readl(HPET_Tn_CFG(i)); + h = hpet_readl(HPET_Tn_CFG(i)+4); + printk(KERN_INFO "hpet: T%d: CFG_l: 0x%x, CFG_h: 0x%x\n", + i, l, h); + l = hpet_readl(HPET_Tn_CMP(i)); + h = hpet_readl(HPET_Tn_CMP(i)+4); + printk(KERN_INFO "hpet: T%d: CMP_l: 0x%x, CMP_h: 0x%x\n", + i, l, h); + l = hpet_readl(HPET_Tn_ROUTE(i)); + h = hpet_readl(HPET_Tn_ROUTE(i)+4); + printk(KERN_INFO "hpet: T%d ROUTE_l: 0x%x, ROUTE_h: 0x%x\n", + i, l, h); + } +} + +#define hpet_print_config() \ +do { \ + if (hpet_verbose) \ + _hpet_print_config(__FUNCTION__, __LINE__); \ +} while (0) + /* * When the hpet driver (/dev/hpet) is enabled, we need to reserve * timer 0 and timer 1 in case of RTC emulation. @@ -191,27 +231,37 @@ static struct clock_event_device hpet_clockevent = { .rating = 50, }; -static void hpet_start_counter(void) +static void hpet_stop_counter(void) { unsigned long cfg = hpet_readl(HPET_CFG); - cfg &= ~HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); hpet_writel(0, HPET_COUNTER); hpet_writel(0, HPET_COUNTER + 4); +} + +static void hpet_start_counter(void) +{ + unsigned long cfg = hpet_readl(HPET_CFG); cfg |= HPET_CFG_ENABLE; hpet_writel(cfg, HPET_CFG); } +static void hpet_restart_counter(void) +{ + hpet_stop_counter(); + hpet_start_counter(); +} + static void hpet_resume_device(void) { force_hpet_resume(); } -static void hpet_restart_counter(void) +static void hpet_resume_counter(void) { hpet_resume_device(); - hpet_start_counter(); + hpet_restart_counter(); } static void hpet_enable_legacy_int(void) @@ -259,29 +309,23 @@ 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 long cfg; uint64_t delta; switch (mode) { case CLOCK_EVT_MODE_PERIODIC: + hpet_stop_counter(); delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * evt->mult; delta >>= evt->shift; - now = hpet_readl(HPET_COUNTER); - cmp = now + (unsigned long) delta; cfg = hpet_readl(HPET_Tn_CFG(timer)); /* Make sure we use edge triggered interrupts */ cfg &= ~HPET_TN_LEVEL; cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC | HPET_TN_SETVAL | HPET_TN_32BIT; hpet_writel(cfg, HPET_Tn_CFG(timer)); - /* - * The first write after writing TN_SETVAL to the - * config register sets the counter value, the second - * write sets the period. - */ - hpet_writel(cmp, HPET_Tn_CMP(timer)); - udelay(1); hpet_writel((unsigned long) delta, HPET_Tn_CMP(timer)); + hpet_start_counter(); + hpet_print_config(); break; case CLOCK_EVT_MODE_ONESHOT: @@ -308,6 +352,7 @@ static void hpet_set_mode(enum clock_event_mode mode, irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu)); enable_irq(hdev->irq); } + hpet_print_config(); break; } } @@ -526,6 +571,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer) num_timers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT); num_timers++; /* Value read out starts from 0 */ + hpet_print_config(); hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL); if (!hpet_devs) @@ -695,7 +741,7 @@ static struct clocksource clocksource_hpet = { .mask = HPET_MASK, .shift = HPET_SHIFT, .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .resume = hpet_restart_counter, + .resume = hpet_resume_counter, #ifdef CONFIG_X86_64 .vread = vread_hpet, #endif @@ -707,7 +753,7 @@ static int hpet_clocksource_register(void) cycle_t t1; /* Start the counter */ - hpet_start_counter(); + hpet_restart_counter(); /* Verify whether hpet counter works */ t1 = read_hpet(); @@ -793,6 +839,7 @@ int __init hpet_enable(void) * information and the number of channels */ id = hpet_readl(HPET_ID); + hpet_print_config(); #ifdef CONFIG_HPET_EMULATE_RTC /* @@ -845,6 +892,7 @@ static __init int hpet_late_init(void) return -ENODEV; hpet_reserve_platform_timers(hpet_readl(HPET_ID)); + hpet_print_config(); for_each_online_cpu(cpu) { hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index b8ac3b6..c3fe010 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -58,9 +58,14 @@ static int show_other_interrupts(struct seq_file *p, int prec) for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs); seq_printf(p, " Local timer interrupts\n"); + + seq_printf(p, "%*s: ", prec, "SPU"); + for_each_online_cpu(j) + seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); + seq_printf(p, " Spurious interrupts\n"); #endif if (generic_interrupt_extension) { - seq_printf(p, "PLT: "); + seq_printf(p, "%*s: ", prec, "PLT"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->generic_irqs); seq_printf(p, " Platform interrupts\n"); @@ -91,12 +96,6 @@ static int show_other_interrupts(struct seq_file *p, int prec) seq_printf(p, " Threshold APIC interrupts\n"); # endif #endif -#ifdef CONFIG_X86_LOCAL_APIC - seq_printf(p, "%*s: ", prec, "SPU"); - for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count); - seq_printf(p, " Spurious interrupts\n"); -#endif seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); @@ -133,23 +132,15 @@ int show_interrupts(struct seq_file *p, void *v) return 0; spin_lock_irqsave(&desc->lock, flags); -#ifndef CONFIG_SMP - any_count = kstat_irqs(i); -#else for_each_online_cpu(j) any_count |= kstat_irqs_cpu(i, j); -#endif action = desc->action; if (!action && !any_count) goto out; seq_printf(p, "%*d: ", prec, i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else for_each_online_cpu(j) seq_printf(p, "%10u ", kstat_irqs_cpu(i, j)); -#endif seq_printf(p, " %8s", desc->chip->name); seq_printf(p, "-%-8s", desc->name); @@ -174,6 +165,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu) #ifdef CONFIG_X86_LOCAL_APIC sum += irq_stats(cpu)->apic_timer_irqs; + sum += irq_stats(cpu)->irq_spurious_count; #endif if (generic_interrupt_extension) sum += irq_stats(cpu)->generic_irqs; @@ -188,9 +180,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += irq_stats(cpu)->irq_threshold_count; #endif #endif -#ifdef CONFIG_X86_LOCAL_APIC - sum += irq_stats(cpu)->irq_spurious_count; -#endif return sum; } diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c index bc13261..368b0a8 100644 --- a/arch/x86/kernel/irqinit_32.c +++ b/arch/x86/kernel/irqinit_32.c @@ -50,7 +50,6 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id) */ static struct irqaction fpu_irq = { .handler = math_error_irq, - .mask = CPU_MASK_NONE, .name = "fpu", }; @@ -83,7 +82,6 @@ void __init init_ISA_irqs(void) */ static struct irqaction irq2 = { .handler = no_action, - .mask = CPU_MASK_NONE, .name = "cascade", }; diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c index c7a49e0..8cd1053 100644 --- a/arch/x86/kernel/irqinit_64.c +++ b/arch/x86/kernel/irqinit_64.c @@ -45,7 +45,6 @@ static struct irqaction irq2 = { .handler = no_action, - .mask = CPU_MASK_NONE, .name = "cascade", }; DEFINE_PER_CPU(vector_irq_t, vector_irq) = { diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c index 55b9461..7b5169d 100644 --- a/arch/x86/kernel/kprobes.c +++ b/arch/x86/kernel/kprobes.c @@ -638,13 +638,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void) #else " pushf\n" /* - * Skip cs, ip, orig_ax. + * Skip cs, ip, orig_ax and gs. * trampoline_handler() will plug in these values */ - " subl $12, %esp\n" + " subl $16, %esp\n" " pushl %fs\n" - " pushl %ds\n" " pushl %es\n" + " pushl %ds\n" " pushl %eax\n" " pushl %ebp\n" " pushl %edi\n" @@ -655,10 +655,10 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " movl %esp, %eax\n" " call trampoline_handler\n" /* Move flags to cs */ - " movl 52(%esp), %edx\n" - " movl %edx, 48(%esp)\n" + " movl 56(%esp), %edx\n" + " movl %edx, 52(%esp)\n" /* Replace saved flags with true return address. */ - " movl %eax, 52(%esp)\n" + " movl %eax, 56(%esp)\n" " popl %ebx\n" " popl %ecx\n" " popl %edx\n" @@ -666,8 +666,8 @@ static void __used __kprobes kretprobe_trampoline_holder(void) " popl %edi\n" " popl %ebp\n" " popl %eax\n" - /* Skip ip, orig_ax, es, ds, fs */ - " addl $20, %esp\n" + /* Skip ds, es, fs, gs, orig_ax and ip */ + " addl $24, %esp\n" " popf\n" #endif " ret\n"); @@ -691,6 +691,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) regs->cs = __KERNEL_CS; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); + regs->gs = 0; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 8815f3c..846510b 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -348,7 +348,6 @@ static irqreturn_t mfgpt_tick(int irq, void *dev_id) static struct irqaction mfgptirq = { .handler = mfgpt_tick, .flags = IRQF_DISABLED | IRQF_NOBALANCING, - .mask = CPU_MASK_NONE, .name = "mfgpt-timer" }; diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index c25fdb3..453b579 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -12,31 +12,30 @@ * * Licensed under the terms of the GNU General Public * License version 2. See file COPYING for details. -*/ - + */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> #include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/cpumask.h> +#include <linux/pci_ids.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> #include <linux/pci.h> -#include <linux/pci_ids.h> -#include <linux/uaccess.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("AMD Microcode Update Driver"); MODULE_AUTHOR("Peter Oruba"); @@ -72,8 +71,8 @@ struct microcode_header_amd { } __attribute__((packed)); struct microcode_amd { - struct microcode_header_amd hdr; - unsigned int mpb[0]; + struct microcode_header_amd hdr; + unsigned int mpb[0]; }; #define UCODE_MAX_SIZE 2048 @@ -184,8 +183,8 @@ static int get_ucode_data(void *to, const u8 *from, size_t n) return 0; } -static void *get_next_ucode(const u8 *buf, unsigned int size, - unsigned int *mc_size) +static void * +get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size) { unsigned int total_size; u8 section_hdr[UCODE_CONTAINER_SECTION_HDR]; @@ -223,7 +222,6 @@ static void *get_next_ucode(const u8 *buf, unsigned int size, return mc; } - static int install_equiv_cpu_table(const u8 *buf) { u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE]; @@ -372,4 +370,3 @@ struct microcode_ops * __init init_amd_microcode(void) { return µcode_amd_ops; } - diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c index c9b721b..98c470c 100644 --- a/arch/x86/kernel/microcode_core.c +++ b/arch/x86/kernel/microcode_core.c @@ -70,41 +70,41 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> +#include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/smp_lock.h> +#include <linux/spinlock.h> #include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/uaccess.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); MODULE_LICENSE("GPL"); -#define MICROCODE_VERSION "2.00" +#define MICROCODE_VERSION "2.00" -static struct microcode_ops *microcode_ops; +static struct microcode_ops *microcode_ops; /* no concurrent ->write()s are allowed on /dev/cpu/microcode */ static DEFINE_MUTEX(microcode_mutex); -struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; +struct ucode_cpu_info ucode_cpu_info[NR_CPUS]; EXPORT_SYMBOL_GPL(ucode_cpu_info); #ifdef CONFIG_MICROCODE_OLD_INTERFACE @@ -198,18 +198,33 @@ static void microcode_dev_exit(void) MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); #else -#define microcode_dev_init() 0 -#define microcode_dev_exit() do { } while (0) +#define microcode_dev_init() 0 +#define microcode_dev_exit() do { } while (0) #endif /* fake device for request_firmware */ -static struct platform_device *microcode_pdev; +static struct platform_device *microcode_pdev; + +static long reload_for_cpu(void *unused) +{ + struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id(); + int err = 0; + + mutex_lock(µcode_mutex); + if (uci->valid) { + err = microcode_ops->request_microcode_fw(smp_processor_id(), + µcode_pdev->dev); + if (!err) + microcode_ops->apply_microcode(smp_processor_id()); + } + mutex_unlock(µcode_mutex); + return err; +} static ssize_t reload_store(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t sz) { - struct ucode_cpu_info *uci = ucode_cpu_info + dev->id; char *end; unsigned long val = simple_strtoul(buf, &end, 0); int err = 0; @@ -218,21 +233,9 @@ static ssize_t reload_store(struct sys_device *dev, if (end == buf) return -EINVAL; if (val == 1) { - cpumask_t old = current->cpus_allowed; - get_online_cpus(); - if (cpu_online(cpu)) { - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - mutex_lock(µcode_mutex); - if (uci->valid) { - err = microcode_ops->request_microcode_fw(cpu, - µcode_pdev->dev); - if (!err) - microcode_ops->apply_microcode(cpu); - } - mutex_unlock(µcode_mutex); - set_cpus_allowed_ptr(current, &old); - } + if (cpu_online(cpu)) + err = work_on_cpu(cpu, reload_for_cpu, NULL); put_online_cpus(); } if (err) @@ -268,8 +271,8 @@ static struct attribute *mc_default_attrs[] = { }; static struct attribute_group mc_attr_group = { - .attrs = mc_default_attrs, - .name = "microcode", + .attrs = mc_default_attrs, + .name = "microcode", }; static void __microcode_fini_cpu(int cpu) @@ -328,9 +331,9 @@ static int microcode_resume_cpu(int cpu) return 0; } -static void microcode_update_cpu(int cpu) +static long microcode_update_cpu(void *unused) { - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; + struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id(); int err = 0; /* @@ -338,30 +341,27 @@ static void microcode_update_cpu(int cpu) * otherwise just request a firmware: */ if (uci->valid) { - err = microcode_resume_cpu(cpu); - } else { - collect_cpu_info(cpu); + err = microcode_resume_cpu(smp_processor_id()); + } else { + collect_cpu_info(smp_processor_id()); if (uci->valid && system_state == SYSTEM_RUNNING) - err = microcode_ops->request_microcode_fw(cpu, + err = microcode_ops->request_microcode_fw( + smp_processor_id(), µcode_pdev->dev); } if (!err) - microcode_ops->apply_microcode(cpu); + microcode_ops->apply_microcode(smp_processor_id()); + return err; } -static void microcode_init_cpu(int cpu) +static int microcode_init_cpu(int cpu) { - cpumask_t old = current->cpus_allowed; - - set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); - /* We should bind the task to the CPU */ - BUG_ON(raw_smp_processor_id() != cpu); - + int err; mutex_lock(µcode_mutex); - microcode_update_cpu(cpu); + err = work_on_cpu(cpu, microcode_update_cpu, NULL); mutex_unlock(µcode_mutex); - set_cpus_allowed_ptr(current, &old); + return err; } static int mc_sysdev_add(struct sys_device *sys_dev) @@ -379,8 +379,9 @@ static int mc_sysdev_add(struct sys_device *sys_dev) if (err) return err; - microcode_init_cpu(cpu); - return 0; + err = microcode_init_cpu(cpu); + + return err; } static int mc_sysdev_remove(struct sys_device *sys_dev) @@ -404,14 +405,14 @@ static int mc_sysdev_resume(struct sys_device *dev) return 0; /* only CPU 0 will apply ucode here */ - microcode_update_cpu(0); + microcode_update_cpu(NULL); return 0; } static struct sysdev_driver mc_sysdev_driver = { - .add = mc_sysdev_add, - .remove = mc_sysdev_remove, - .resume = mc_sysdev_resume, + .add = mc_sysdev_add, + .remove = mc_sysdev_remove, + .resume = mc_sysdev_resume, }; static __cpuinit int @@ -424,7 +425,9 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - microcode_init_cpu(cpu); + if (microcode_init_cpu(cpu)) + printk(KERN_ERR "microcode: failed to init CPU%d\n", + cpu); case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: pr_debug("microcode: CPU%d added\n", cpu); @@ -448,7 +451,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu) } static struct notifier_block __refdata mc_cpu_notifier = { - .notifier_call = mc_cpu_callback, + .notifier_call = mc_cpu_callback, }; static int __init microcode_init(void) diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c index 5e9f4fc..149b9ec 100644 --- a/arch/x86/kernel/microcode_intel.c +++ b/arch/x86/kernel/microcode_intel.c @@ -70,28 +70,28 @@ * Fix sigmatch() macro to handle old CPUs with pf == 0. * Thanks to Stuart Swales for pointing out this bug. */ +#include <linux/platform_device.h> #include <linux/capability.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> +#include <linux/miscdevice.h> +#include <linux/firmware.h> #include <linux/smp_lock.h> +#include <linux/spinlock.h> #include <linux/cpumask.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/uaccess.h> #include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/slab.h> #include <linux/cpu.h> -#include <linux/firmware.h> -#include <linux/platform_device.h> -#include <linux/uaccess.h> +#include <linux/fs.h> +#include <linux/mm.h> -#include <asm/msr.h> -#include <asm/processor.h> #include <asm/microcode.h> +#include <asm/processor.h> +#include <asm/msr.h> MODULE_DESCRIPTION("Microcode Update Driver"); MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>"); @@ -129,12 +129,13 @@ struct extended_sigtable { struct extended_signature sigs[0]; }; -#define DEFAULT_UCODE_DATASIZE (2000) +#define DEFAULT_UCODE_DATASIZE (2000) #define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) #define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) #define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) #define DWSIZE (sizeof(u32)) + #define get_totalsize(mc) \ (((struct microcode_intel *)mc)->hdr.totalsize ? \ ((struct microcode_intel *)mc)->hdr.totalsize : \ @@ -197,30 +198,31 @@ static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf) } static inline int -update_match_revision(struct microcode_header_intel *mc_header, int rev) +update_match_revision(struct microcode_header_intel *mc_header, int rev) { return (mc_header->rev <= rev) ? 0 : 1; } static int microcode_sanity_check(void *mc) { + unsigned long total_size, data_size, ext_table_size; struct microcode_header_intel *mc_header = mc; struct extended_sigtable *ext_header = NULL; - struct extended_signature *ext_sig; - unsigned long total_size, data_size, ext_table_size; int sum, orig_sum, ext_sigcount = 0, i; + struct extended_signature *ext_sig; total_size = get_totalsize(mc_header); data_size = get_datasize(mc_header); + if (data_size + MC_HEADER_SIZE > total_size) { printk(KERN_ERR "microcode: error! " - "Bad data size in microcode data file\n"); + "Bad data size in microcode data file\n"); return -EINVAL; } if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { printk(KERN_ERR "microcode: error! " - "Unknown microcode update format\n"); + "Unknown microcode update format\n"); return -EINVAL; } ext_table_size = total_size - (MC_HEADER_SIZE + data_size); @@ -318,11 +320,15 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev) static void apply_microcode(int cpu) { + struct microcode_intel *mc_intel; + struct ucode_cpu_info *uci; unsigned long flags; unsigned int val[2]; - int cpu_num = raw_smp_processor_id(); - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct microcode_intel *mc_intel = uci->mc; + int cpu_num; + + cpu_num = raw_smp_processor_id(); + uci = ucode_cpu_info + cpu; + mc_intel = uci->mc; /* We should bind the task to the CPU */ BUG_ON(cpu_num != cpu); @@ -348,15 +354,17 @@ static void apply_microcode(int cpu) spin_unlock_irqrestore(µcode_update_lock, flags); if (val[1] != mc_intel->hdr.rev) { printk(KERN_ERR "microcode: CPU%d update from revision " - "0x%x to 0x%x failed\n", cpu_num, uci->cpu_sig.rev, val[1]); + "0x%x to 0x%x failed\n", + cpu_num, uci->cpu_sig.rev, val[1]); return; } printk(KERN_INFO "microcode: CPU%d updated from revision " - "0x%x to 0x%x, date = %04x-%02x-%02x \n", + "0x%x to 0x%x, date = %04x-%02x-%02x \n", cpu_num, uci->cpu_sig.rev, val[1], mc_intel->hdr.date & 0xffff, mc_intel->hdr.date >> 24, (mc_intel->hdr.date >> 16) & 0xff); + uci->cpu_sig.rev = val[1]; } @@ -404,18 +412,23 @@ static int generic_load_microcode(int cpu, void *data, size_t size, leftover -= mc_size; } - if (new_mc) { - if (!leftover) { - if (uci->mc) - vfree(uci->mc); - uci->mc = (struct microcode_intel *)new_mc; - pr_debug("microcode: CPU%d found a matching microcode update with" - " version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); - } else - vfree(new_mc); + if (!new_mc) + goto out; + + if (leftover) { + vfree(new_mc); + goto out; } + if (uci->mc) + vfree(uci->mc); + uci->mc = (struct microcode_intel *)new_mc; + + pr_debug("microcode: CPU%d found a matching microcode update with" + " version 0x%x (current=0x%x)\n", + cpu, new_rev, uci->cpu_sig.rev); + + out: return (int)leftover; } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index dce99dc..70fd7e4 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -679,7 +679,7 @@ void __init get_smp_config(void) __get_smp_config(0); } -static void smp_reserve_bootmem(struct mpf_intel *mpf) +static void __init smp_reserve_bootmem(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); #ifdef CONFIG_X86_32 @@ -838,7 +838,7 @@ static int __init get_MP_intsrc_index(struct mpc_intsrc *m) static struct mpc_intsrc __initdata *m_spare[SPARE_SLOT_NUM]; -static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) +static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) { int i; @@ -866,7 +866,8 @@ static void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) } } #else /* CONFIG_X86_IO_APIC */ -static inline void check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} +static +inline void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) {} #endif /* CONFIG_X86_IO_APIC */ static int check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index d28bbdc..755c21e 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -380,8 +380,9 @@ static inline struct iommu_table *find_iommu_table(struct device *dev) return tbl; } -static void calgary_unmap_sg(struct device *dev, - struct scatterlist *sglist, int nelems, int direction) +static void calgary_unmap_sg(struct device *dev, struct scatterlist *sglist, + int nelems,enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -404,7 +405,8 @@ static void calgary_unmap_sg(struct device *dev, } static int calgary_map_sg(struct device *dev, struct scatterlist *sg, - int nelems, int direction) + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); struct scatterlist *s; @@ -429,15 +431,14 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg, s->dma_address = (entry << PAGE_SHIFT) | s->offset; /* insert into HW table */ - tce_build(tbl, entry, npages, vaddr & PAGE_MASK, - direction); + tce_build(tbl, entry, npages, vaddr & PAGE_MASK, dir); s->dma_length = s->length; } return nelems; error: - calgary_unmap_sg(dev, sg, nelems, direction); + calgary_unmap_sg(dev, sg, nelems, dir, NULL); for_each_sg(sg, s, nelems, i) { sg->dma_address = bad_dma_address; sg->dma_length = 0; @@ -445,10 +446,12 @@ error: return 0; } -static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, - size_t size, int direction) +static dma_addr_t calgary_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { - void *vaddr = phys_to_virt(paddr); + void *vaddr = page_address(page) + offset; unsigned long uaddr; unsigned int npages; struct iommu_table *tbl = find_iommu_table(dev); @@ -456,17 +459,18 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr, uaddr = (unsigned long)vaddr; npages = iommu_num_pages(uaddr, size, PAGE_SIZE); - return iommu_alloc(dev, tbl, vaddr, npages, direction); + return iommu_alloc(dev, tbl, vaddr, npages, dir); } -static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle, - size_t size, int direction) +static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct iommu_table *tbl = find_iommu_table(dev); unsigned int npages; - npages = iommu_num_pages(dma_handle, size, PAGE_SIZE); - iommu_free(tbl, dma_handle, npages); + npages = iommu_num_pages(dma_addr, size, PAGE_SIZE); + iommu_free(tbl, dma_addr, npages); } static void* calgary_alloc_coherent(struct device *dev, size_t size, @@ -515,13 +519,13 @@ static void calgary_free_coherent(struct device *dev, size_t size, free_pages((unsigned long)vaddr, get_order(size)); } -static struct dma_mapping_ops calgary_dma_ops = { +static struct dma_map_ops calgary_dma_ops = { .alloc_coherent = calgary_alloc_coherent, .free_coherent = calgary_free_coherent, - .map_single = calgary_map_single, - .unmap_single = calgary_unmap_single, .map_sg = calgary_map_sg, .unmap_sg = calgary_unmap_sg, + .map_page = calgary_map_page, + .unmap_page = calgary_unmap_page, }; static inline void __iomem * busno_to_bbar(unsigned char num) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index b254285..745579b 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -1,4 +1,5 @@ #include <linux/dma-mapping.h> +#include <linux/dma-debug.h> #include <linux/dmar.h> #include <linux/bootmem.h> #include <linux/pci.h> @@ -12,7 +13,7 @@ static int forbid_dac __read_mostly; -struct dma_mapping_ops *dma_ops; +struct dma_map_ops *dma_ops; EXPORT_SYMBOL(dma_ops); static int iommu_sac_force __read_mostly; @@ -39,11 +40,14 @@ EXPORT_SYMBOL(bad_dma_address); to older i386. */ struct device x86_dma_fallback_dev = { .init_name = "fallback device", - .coherent_dma_mask = DMA_32BIT_MASK, + .coherent_dma_mask = DMA_BIT_MASK(32), .dma_mask = &x86_dma_fallback_dev.coherent_dma_mask, }; EXPORT_SYMBOL(x86_dma_fallback_dev); +/* Number of entries preallocated for DMA-API debugging */ +#define PREALLOC_DMA_DEBUG_ENTRIES 32768 + int dma_set_mask(struct device *dev, u64 mask) { if (!dev->dma_mask || !dma_supported(dev, mask)) @@ -144,7 +148,7 @@ again: if (!is_buffer_dma_capable(dma_mask, addr, size)) { __free_pages(page, get_order(size)); - if (dma_mask < DMA_32BIT_MASK && !(flag & GFP_DMA)) { + if (dma_mask < DMA_BIT_MASK(32) && !(flag & GFP_DMA)) { flag = (flag & ~GFP_DMA32) | GFP_DMA; goto again; } @@ -224,7 +228,7 @@ early_param("iommu", iommu_setup); int dma_supported(struct device *dev, u64 mask) { - struct dma_mapping_ops *ops = get_dma_ops(dev); + struct dma_map_ops *ops = get_dma_ops(dev); #ifdef CONFIG_PCI if (mask > 0xffffffff && forbid_dac > 0) { @@ -239,7 +243,7 @@ int dma_supported(struct device *dev, u64 mask) /* Copied from i386. Doesn't make much sense, because it will only work for pci_alloc_coherent. The caller just has to use GFP_DMA in this case. */ - if (mask < DMA_24BIT_MASK) + if (mask < DMA_BIT_MASK(24)) return 0; /* Tell the device to use SAC when IOMMU force is on. This @@ -254,7 +258,7 @@ int dma_supported(struct device *dev, u64 mask) SAC for these. Assume all masks <= 40 bits are of this type. Normally this doesn't make any difference, but gives more gentle handling of IOMMU overflow. */ - if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) { + if (iommu_sac_force && (mask >= DMA_BIT_MASK(40))) { dev_info(dev, "Force SAC with mask %Lx\n", mask); return 0; } @@ -265,6 +269,12 @@ EXPORT_SYMBOL(dma_supported); static int __init pci_iommu_init(void) { + dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); + +#ifdef CONFIG_PCI + dma_debug_add_bus(&pci_bus_type); +#endif + calgary_iommu_init(); intel_iommu_init(); @@ -290,8 +300,7 @@ fs_initcall(pci_iommu_init); static __devinit void via_no_dac(struct pci_dev *dev) { if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) { - printk(KERN_INFO - "PCI: VIA PCI bridge detected. Disabling DAC.\n"); + dev_info(&dev->dev, "disabling DAC on VIA PCI bridge\n"); forbid_dac = 1; } } diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c index d5768b1..b284b58 100644 --- a/arch/x86/kernel/pci-gart_64.c +++ b/arch/x86/kernel/pci-gart_64.c @@ -255,10 +255,13 @@ static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem, } /* Map a single area into the IOMMU */ -static dma_addr_t -gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir) +static dma_addr_t gart_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long bus; + phys_addr_t paddr = page_to_phys(page) + offset; if (!dev) dev = &x86_dma_fallback_dev; @@ -275,8 +278,9 @@ gart_map_single(struct device *dev, phys_addr_t paddr, size_t size, int dir) /* * Free a DMA mapping. */ -static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, - size_t size, int direction) +static void gart_unmap_page(struct device *dev, dma_addr_t dma_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) { unsigned long iommu_page; int npages; @@ -298,8 +302,8 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr, /* * Wrapper for pci_unmap_single working with scatterlists. */ -static void -gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static void gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *s; int i; @@ -307,7 +311,7 @@ gart_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) for_each_sg(sg, s, nents, i) { if (!s->dma_length || !s->length) break; - gart_unmap_single(dev, s->dma_address, s->dma_length, dir); + gart_unmap_page(dev, s->dma_address, s->dma_length, dir, NULL); } } @@ -329,7 +333,7 @@ static int dma_map_sg_nonforce(struct device *dev, struct scatterlist *sg, addr = dma_map_area(dev, addr, s->length, dir, 0); if (addr == bad_dma_address) { if (i > 0) - gart_unmap_sg(dev, sg, i, dir); + gart_unmap_sg(dev, sg, i, dir, NULL); nents = 0; sg[0].dma_length = 0; break; @@ -400,8 +404,8 @@ dma_map_cont(struct device *dev, struct scatterlist *start, int nelems, * DMA map all entries in a scatterlist. * Merge chunks that have page aligned sizes into a continuous mapping. */ -static int -gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) +static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, + enum dma_data_direction dir, struct dma_attrs *attrs) { struct scatterlist *s, *ps, *start_sg, *sgmap; int need = 0, nextneed, i, out, start; @@ -468,7 +472,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir) error: flush_gart(); - gart_unmap_sg(dev, sg, out, dir); + gart_unmap_sg(dev, sg, out, dir, NULL); /* When it was forced or merged try again in a dumb way */ if (force_iommu || iommu_merge) { @@ -521,7 +525,7 @@ static void gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr) { - gart_unmap_single(dev, dma_addr, size, DMA_BIDIRECTIONAL); + gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); free_pages((unsigned long)vaddr, get_order(size)); } @@ -707,11 +711,11 @@ static __init int init_k8_gatt(struct agp_kern_info *info) return -1; } -static struct dma_mapping_ops gart_dma_ops = { - .map_single = gart_map_single, - .unmap_single = gart_unmap_single, +static struct dma_map_ops gart_dma_ops = { .map_sg = gart_map_sg, .unmap_sg = gart_unmap_sg, + .map_page = gart_map_page, + .unmap_page = gart_unmap_page, .alloc_coherent = gart_alloc_coherent, .free_coherent = gart_free_coherent, }; diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 8b02a39..71d412a 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -15,7 +15,7 @@ static int check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) { if (hwdev && !is_buffer_dma_capable(*hwdev->dma_mask, bus, size)) { - if (*hwdev->dma_mask >= DMA_32BIT_MASK) + if (*hwdev->dma_mask >= DMA_BIT_MASK(32)) printk(KERN_ERR "nommu_%s: overflow %Lx+%zu of device mask %Lx\n", name, (long long)bus, size, @@ -25,19 +25,19 @@ check_addr(char *name, struct device *hwdev, dma_addr_t bus, size_t size) return 1; } -static dma_addr_t -nommu_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, - int direction) +static dma_addr_t nommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) { - dma_addr_t bus = paddr; + dma_addr_t bus = page_to_phys(page) + offset; WARN_ON(size == 0); - if (!check_addr("map_single", hwdev, bus, size)) - return bad_dma_address; + if (!check_addr("map_single", dev, bus, size)) + return bad_dma_address; flush_write_buffers(); return bus; } - /* Map a set of buffers described by scatterlist in streaming * mode for DMA. This is the scatter-gather version of the * above pci_map_single interface. Here the scatter gather list @@ -54,7 +54,8 @@ nommu_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, * the same here. */ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction) + int nents, enum dma_data_direction dir, + struct dma_attrs *attrs) { struct scatterlist *s; int i; @@ -78,11 +79,11 @@ static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, free_pages((unsigned long)vaddr, get_order(size)); } -struct dma_mapping_ops nommu_dma_ops = { +struct dma_map_ops nommu_dma_ops = { .alloc_coherent = dma_generic_alloc_coherent, .free_coherent = nommu_free_coherent, - .map_single = nommu_map_single, .map_sg = nommu_map_sg, + .map_page = nommu_map_page, .is_phys = 1, }; diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb.c index d59c917..221a385 100644 --- a/arch/x86/kernel/pci-swiotlb_64.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -33,18 +33,11 @@ phys_addr_t swiotlb_bus_to_phys(dma_addr_t baddr) return baddr; } -int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size) +int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size) { return 0; } -static dma_addr_t -swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size, - int direction) -{ - return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction); -} - static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { @@ -57,20 +50,20 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -struct dma_mapping_ops swiotlb_dma_ops = { +static struct dma_map_ops swiotlb_dma_ops = { .mapping_error = swiotlb_dma_mapping_error, .alloc_coherent = x86_swiotlb_alloc_coherent, .free_coherent = swiotlb_free_coherent, - .map_single = swiotlb_map_single_phys, - .unmap_single = swiotlb_unmap_single, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu, .sync_single_range_for_device = swiotlb_sync_single_range_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, .sync_sg_for_device = swiotlb_sync_sg_for_device, - .map_sg = swiotlb_map_sg, - .unmap_sg = swiotlb_unmap_sg, + .map_sg = swiotlb_map_sg_attrs, + .unmap_sg = swiotlb_unmap_sg_attrs, + .map_page = swiotlb_map_page, + .unmap_page = swiotlb_unmap_page, .dma_supported = NULL, }; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 156f8758..ca98915 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -8,7 +8,7 @@ #include <linux/module.h> #include <linux/pm.h> #include <linux/clockchips.h> -#include <linux/ftrace.h> +#include <trace/power.h> #include <asm/system.h> #include <asm/apic.h> #include <asm/idle.h> @@ -22,6 +22,9 @@ EXPORT_SYMBOL(idle_nomwait); struct kmem_cache *task_xstate_cachep; +DEFINE_TRACE(power_start); +DEFINE_TRACE(power_end); + int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; @@ -325,7 +328,7 @@ void stop_this_cpu(void *dummy) /* * Remove this CPU: */ - cpu_clear(smp_processor_id(), cpu_online_map); + set_cpu_online(smp_processor_id(), false); disable_local_APIC(); for (;;) { @@ -475,12 +478,13 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c) return 1; } -static cpumask_t c1e_mask = CPU_MASK_NONE; +static cpumask_var_t c1e_mask; static int c1e_detected; void c1e_remove_cpu(int cpu) { - cpu_clear(cpu, c1e_mask); + if (c1e_mask != NULL) + cpumask_clear_cpu(cpu, c1e_mask); } /* @@ -509,8 +513,8 @@ static void c1e_idle(void) if (c1e_detected) { int cpu = smp_processor_id(); - if (!cpu_isset(cpu, c1e_mask)) { - cpu_set(cpu, c1e_mask); + if (!cpumask_test_cpu(cpu, c1e_mask)) { + cpumask_set_cpu(cpu, c1e_mask); /* * Force broadcast so ACPI can not interfere. Needs * to run with interrupts enabled as it uses @@ -562,6 +566,15 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) pm_idle = default_idle; } +void __init init_c1e_mask(void) +{ + /* If we're using c1e_idle, we need to allocate c1e_mask. */ + if (pm_idle == c1e_idle) { + alloc_cpumask_var(&c1e_mask, GFP_KERNEL); + cpumask_clear(c1e_mask); + } +} + static int __init idle_setup(char *str) { if (!str) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 14014d7..76f8f84 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -245,7 +245,7 @@ void prepare_to_copy(struct task_struct *tsk) unlazy_fpu(tsk); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index abb7e6a..b751a41 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -278,7 +278,7 @@ void prepare_to_copy(struct task_struct *tsk) unlazy_fpu(tsk); } -int copy_thread(int nr, unsigned long clone_flags, unsigned long sp, +int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long unused, struct task_struct *p, struct pt_regs *regs) { diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 1937871..23b7c8f 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -34,6 +34,8 @@ #include <asm/proto.h> #include <asm/ds.h> +#include <trace/syscall.h> + #include "tls.h" enum x86_regset { @@ -1415,6 +1417,9 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs) tracehook_report_syscall_entry(regs)) ret = -1L; + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_enter(regs); + if (unlikely(current->audit_context)) { if (IS_IA32) audit_syscall_entry(AUDIT_ARCH_I386, @@ -1438,6 +1443,9 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) if (unlikely(current->audit_context)) audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax); + if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE))) + ftrace_syscall_exit(regs); + if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); @@ -1455,6 +1463,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs) * system call instruction. */ if (test_thread_flag(TIF_SINGLESTEP) && - tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL)) + tracehook_consider_fatal_signal(current, SIGTRAP)) send_sigtrap(current, regs, 0, TRAP_BRKPT); } diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 6a5a2970..e95022e 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -171,7 +171,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH8_4, ich_force_enable_hpet); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICH9_7, ich_force_enable_hpet); - +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x3a16, /* ICH10 */ + ich_force_enable_hpet); static struct pci_dev *cached_dev; diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 2aef36d..1340dad 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -224,6 +224,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"), }, }, + { /* Handle problems with rebooting on Dell DXP061 */ + .callback = set_bios_reboot, + .ident = "Dell DXP061", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"), + }, + }, { } }; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a0d2623..b415843 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1049,7 +1049,6 @@ void __init x86_quirk_trap_init(void) static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER, - .mask = CPU_MASK_NONE, .name = "timer" }; diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 400331b..3a97a4c 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -153,7 +153,6 @@ static struct page * __init pcpur_get_page(unsigned int cpu, int pageno) static ssize_t __init setup_pcpu_remap(size_t static_size) { static struct vm_struct vm; - pg_data_t *last; size_t ptrs_size, dyn_size; unsigned int cpu; ssize_t ret; @@ -162,22 +161,9 @@ static ssize_t __init setup_pcpu_remap(size_t static_size) * If large page isn't supported, there's no benefit in doing * this. Also, on non-NUMA, embedding is better. */ - if (!cpu_has_pse || pcpu_need_numa()) + if (!cpu_has_pse || !pcpu_need_numa()) return -EINVAL; - last = NULL; - for_each_possible_cpu(cpu) { - int node = early_cpu_to_node(cpu); - - if (node_online(node) && NODE_DATA(node) && - last && last != NODE_DATA(node)) - goto proceed; - - last = NODE_DATA(node); - } - return -EINVAL; - -proceed: /* * Currently supports only single page. Supporting multiple * pages won't be too difficult if it ever becomes necessary. diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index dfcc74a..1442516 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -221,7 +221,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, if (!onsigstack) { /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) + if (current->sas_ss_size) sp = current->sas_ss_sp + current->sas_ss_size; } else { #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index ef7d101..58d24ef 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,11 +101,11 @@ EXPORT_SYMBOL(smp_num_siblings); DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID; /* representing HT siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_sibling_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); /* representing HT and core siblings of each logical CPU */ -DEFINE_PER_CPU(cpumask_t, cpu_core_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); /* Per CPU bogomips and other parameters */ @@ -115,11 +115,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); atomic_t init_deasserted; #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32) - -/* which logical CPUs are on which nodes */ -cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly = - { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; -EXPORT_SYMBOL(node_to_cpumask_map); /* which node each logical CPU is on */ int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 }; EXPORT_SYMBOL(cpu_to_node_map); @@ -128,7 +123,7 @@ EXPORT_SYMBOL(cpu_to_node_map); static void map_cpu_to_node(int cpu, int node) { printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node); - cpumask_set_cpu(cpu, &node_to_cpumask_map[node]); + cpumask_set_cpu(cpu, node_to_cpumask_map[node]); cpu_to_node_map[cpu] = node; } @@ -139,7 +134,7 @@ static void unmap_cpu_to_node(int cpu) printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu); for (node = 0; node < MAX_NUMNODES; node++) - cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[node]); cpu_to_node_map[cpu] = 0; } #else /* !(CONFIG_NUMA && CONFIG_X86_32) */ @@ -301,7 +296,7 @@ notrace static void __cpuinit start_secondary(void *unused) __flush_tlb_all(); #endif - /* This must be done before setting cpu_online_map */ + /* This must be done before setting cpu_online_mask */ set_cpu_sibling_map(raw_smp_processor_id()); wmb(); @@ -334,6 +329,23 @@ notrace static void __cpuinit start_secondary(void *unused) cpu_idle(); } +#ifdef CONFIG_CPUMASK_OFFSTACK +/* In this case, llc_shared_map is a pointer to a cpumask. */ +static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, + const struct cpuinfo_x86 *src) +{ + struct cpumask *llc = dst->llc_shared_map; + *dst = *src; + dst->llc_shared_map = llc; +} +#else +static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst, + const struct cpuinfo_x86 *src) +{ + *dst = *src; +} +#endif /* CONFIG_CPUMASK_OFFSTACK */ + /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU @@ -343,7 +355,7 @@ void __cpuinit smp_store_cpu_info(int id) { struct cpuinfo_x86 *c = &cpu_data(id); - *c = boot_cpu_data; + copy_cpuinfo_x86(c, &boot_cpu_data); c->cpu_index = id; if (id != 0) identify_secondary_cpu(c); @@ -367,15 +379,15 @@ void __cpuinit set_cpu_sibling_map(int cpu) cpumask_set_cpu(cpu, cpu_sibling_mask(i)); cpumask_set_cpu(i, cpu_core_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(i)); - cpumask_set_cpu(i, &c->llc_shared_map); - cpumask_set_cpu(cpu, &o->llc_shared_map); + cpumask_set_cpu(i, c->llc_shared_map); + cpumask_set_cpu(cpu, o->llc_shared_map); } } } else { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); } - cpumask_set_cpu(cpu, &c->llc_shared_map); + cpumask_set_cpu(cpu, c->llc_shared_map); if (current_cpu_data.x86_max_cores == 1) { cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu)); @@ -386,8 +398,8 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { if (per_cpu(cpu_llc_id, cpu) != BAD_APICID && per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) { - cpumask_set_cpu(i, &c->llc_shared_map); - cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map); + cpumask_set_cpu(i, c->llc_shared_map); + cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map); } if (c->phys_proc_id == cpu_data(i).phys_proc_id) { cpumask_set_cpu(i, cpu_core_mask(cpu)); @@ -425,12 +437,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu) if (sched_mc_power_savings || sched_smt_power_savings) return cpu_core_mask(cpu); else - return &c->llc_shared_map; -} - -cpumask_t cpu_coregroup_map(int cpu) -{ - return *cpu_coregroup_mask(cpu); + return c->llc_shared_map; } static void impress_friends(void) @@ -897,9 +904,8 @@ int __cpuinit native_cpu_up(unsigned int cpu) */ static __init void disable_smp(void) { - /* use the read/write pointers to the present and possible maps */ - cpumask_copy(&cpu_present_map, cpumask_of(0)); - cpumask_copy(&cpu_possible_map, cpumask_of(0)); + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); smpboot_clear_io_apic_irqs(); if (smp_found_config) @@ -1031,6 +1037,8 @@ static void __init smp_cpu_index_default(void) */ void __init native_smp_prepare_cpus(unsigned int max_cpus) { + unsigned int i; + preempt_disable(); smp_cpu_index_default(); current_cpu_data = boot_cpu_data; @@ -1044,6 +1052,14 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) boot_cpu_logical_apicid = logical_smp_processor_id(); #endif current_thread_info()->cpu = 0; /* needed? */ + for_each_possible_cpu(i) { + alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); + alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL); + alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL); + cpumask_clear(per_cpu(cpu_core_map, i)); + cpumask_clear(per_cpu(cpu_sibling_map, i)); + cpumask_clear(cpu_data(i).llc_shared_map); + } set_cpu_sibling_map(0); enable_IR_x2apic(); @@ -1132,11 +1148,11 @@ early_param("possible_cpus", _setup_possible_cpus); /* - * cpu_possible_map should be static, it cannot change as cpu's + * cpu_possible_mask should be static, it cannot change as cpu's * are onlined, or offlined. The reason is per-cpu data-structures * are allocated by some modules at init time, and dont expect to * do this dynamically on cpu arrival/departure. - * cpu_present_map on the other hand can change dynamically. + * cpu_present_mask on the other hand can change dynamically. * In case when cpu_hotplug is not compiled, then we resort to current * behaviour, which is cpu_possible == cpu_present. * - Ashok Raj diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index 3bdb648..ff5c873 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -332,3 +332,5 @@ ENTRY(sys_call_table) .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 + .long sys_preadv + .long sys_pwritev diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c index 241ec39..5ba343e 100644 --- a/arch/x86/kernel/time_64.c +++ b/arch/x86/kernel/time_64.c @@ -116,7 +116,6 @@ unsigned long __init calibrate_cpu(void) static struct irqaction irq0 = { .handler = timer_interrupt, .flags = IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER, - .mask = CPU_MASK_NONE, .name = "timer" }; @@ -125,7 +124,6 @@ void __init hpet_time_init(void) if (!hpet_enable()) setup_pit_timer(); - irq0.mask = cpumask_of_cpu(0); setup_irq(0, &irq0); } diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index 79c0732..ed0c337 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -25,6 +25,8 @@ static int uv_bau_retry_limit __read_mostly; /* position of pnode (which is nasid>>1): */ static int uv_nshift __read_mostly; +/* base pnode in this partition */ +static int uv_partition_base_pnode __read_mostly; static unsigned long uv_mmask __read_mostly; @@ -32,6 +34,34 @@ static DEFINE_PER_CPU(struct ptc_stats, ptcstats); static DEFINE_PER_CPU(struct bau_control, bau_control); /* + * Determine the first node on a blade. + */ +static int __init blade_to_first_node(int blade) +{ + int node, b; + + for_each_online_node(node) { + b = uv_node_to_blade_id(node); + if (blade == b) + return node; + } + return -1; /* shouldn't happen */ +} + +/* + * Determine the apicid of the first cpu on a blade. + */ +static int __init blade_to_first_apicid(int blade) +{ + int cpu; + + for_each_present_cpu(cpu) + if (blade == uv_cpu_to_blade_id(cpu)) + return per_cpu(x86_cpu_to_apicid, cpu); + return -1; +} + +/* * Free a software acknowledge hardware resource by clearing its Pending * bit. This will return a reply to the sender. * If the message has timed out, a reply has already been sent by the @@ -67,7 +97,7 @@ static void uv_bau_process_message(struct bau_payload_queue_entry *msg, msp = __get_cpu_var(bau_control).msg_statuses + msg_slot; cpu = uv_blade_processor_id(); msg->number_of_cpus = - uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); + uv_blade_nr_online_cpus(uv_node_to_blade_id(numa_node_id())); this_cpu_mask = 1UL << cpu; if (msp->seen_by.bits & this_cpu_mask) return; @@ -215,14 +245,14 @@ static int uv_wait_completion(struct bau_desc *bau_desc, * Returns @flush_mask if some remote flushing remains to be done. The * mask will have some bits still set. */ -const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, +const struct cpumask *uv_flush_send_and_wait(int cpu, int this_pnode, struct bau_desc *bau_desc, struct cpumask *flush_mask) { int completion_status = 0; int right_shift; int tries = 0; - int blade; + int pnode; int bit; unsigned long mmr_offset; unsigned long index; @@ -265,8 +295,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, * use the IPI method of shootdown on them. */ for_each_cpu(bit, flush_mask) { - blade = uv_cpu_to_blade_id(bit); - if (blade == this_blade) + pnode = uv_cpu_to_pnode(bit); + if (pnode == this_pnode) continue; cpumask_clear_cpu(bit, flush_mask); } @@ -275,6 +305,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade, return NULL; } +static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask); + /** * uv_flush_tlb_others - globally purge translation cache of a virtual * address or all TLB's @@ -304,20 +336,19 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm, unsigned long va, unsigned int cpu) { - static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask); + struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask); int i; int bit; - int blade; + int pnode; int uv_cpu; - int this_blade; + int this_pnode; int locals = 0; struct bau_desc *bau_desc; cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu)); uv_cpu = uv_blade_processor_id(); - this_blade = uv_numa_blade_id(); + this_pnode = uv_hub_info->pnode; bau_desc = __get_cpu_var(bau_control).descriptor_base; bau_desc += UV_ITEMS_PER_DESCRIPTOR * uv_cpu; @@ -325,13 +356,14 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, i = 0; for_each_cpu(bit, flush_mask) { - blade = uv_cpu_to_blade_id(bit); - BUG_ON(blade > (UV_DISTRIBUTION_SIZE - 1)); - if (blade == this_blade) { + pnode = uv_cpu_to_pnode(bit); + BUG_ON(pnode > (UV_DISTRIBUTION_SIZE - 1)); + if (pnode == this_pnode) { locals++; continue; } - bau_node_set(blade, &bau_desc->distribution); + bau_node_set(pnode - uv_partition_base_pnode, + &bau_desc->distribution); i++; } if (i == 0) { @@ -349,7 +381,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask, bau_desc->payload.address = va; bau_desc->payload.sending_cpu = cpu; - return uv_flush_send_and_wait(uv_cpu, this_blade, bau_desc, flush_mask); + return uv_flush_send_and_wait(uv_cpu, this_pnode, bau_desc, flush_mask); } /* @@ -417,24 +449,58 @@ void uv_bau_message_interrupt(struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * uv_enable_timeouts + * + * Each target blade (i.e. blades that have cpu's) needs to have + * shootdown message timeouts enabled. The timeout does not cause + * an interrupt, but causes an error message to be returned to + * the sender. + */ static void uv_enable_timeouts(void) { - int i; int blade; - int last_blade; + int nblades; int pnode; - int cur_cpu = 0; - unsigned long apicid; + unsigned long mmr_image; - last_blade = -1; - for_each_online_node(i) { - blade = uv_node_to_blade_id(i); - if (blade == last_blade) + nblades = uv_num_possible_blades(); + + for (blade = 0; blade < nblades; blade++) { + if (!uv_blade_nr_possible_cpus(blade)) continue; - last_blade = blade; - apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + pnode = uv_blade_to_pnode(blade); - cur_cpu += uv_blade_nr_possible_cpus(i); + mmr_image = + uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL); + /* + * Set the timeout period and then lock it in, in three + * steps; captures and locks in the period. + * + * To program the period, the SOFT_ACK_MODE must be off. + */ + mmr_image &= ~((unsigned long)1 << + UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + /* + * Set the 4-bit period. + */ + mmr_image &= ~((unsigned long)0xf << + UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD << + UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); + /* + * Subsequent reversals of the timebase bit (3) cause an + * immediate timeout of one or all INTD resources as + * indicated in bits 2:0 (7 causes all of them to timeout). + */ + mmr_image |= ((unsigned long)1 << + UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT); + uv_write_global_mmr64 + (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image); } } @@ -481,8 +547,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data) stat->requestee, stat->onetlb, stat->alltlb, stat->s_retry, stat->d_retry, stat->ptc_i); seq_printf(file, "%lx %ld %ld %ld %ld %ld %ld\n", - uv_read_global_mmr64(uv_blade_to_pnode - (uv_cpu_to_blade_id(cpu)), + uv_read_global_mmr64(uv_cpu_to_pnode(cpu), UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE), stat->sflush, stat->dflush, stat->retriesok, stat->nomsg, @@ -616,16 +681,18 @@ static struct bau_control * __init uv_table_bases_init(int blade, int node) * finish the initialization of the per-blade control structures */ static void __init -uv_table_bases_finish(int blade, int node, int cur_cpu, +uv_table_bases_finish(int blade, struct bau_control *bau_tablesp, struct bau_desc *adp) { struct bau_control *bcp; - int i; + int cpu; - for (i = cur_cpu; i < cur_cpu + uv_blade_nr_possible_cpus(blade); i++) { - bcp = (struct bau_control *)&per_cpu(bau_control, i); + for_each_present_cpu(cpu) { + if (blade != uv_cpu_to_blade_id(cpu)) + continue; + bcp = (struct bau_control *)&per_cpu(bau_control, cpu); bcp->bau_msg_head = bau_tablesp->va_queue_first; bcp->va_queue_first = bau_tablesp->va_queue_first; bcp->va_queue_last = bau_tablesp->va_queue_last; @@ -648,11 +715,10 @@ uv_activation_descriptor_init(int node, int pnode) struct bau_desc *adp; struct bau_desc *ad2; - adp = (struct bau_desc *) - kmalloc_node(16384, GFP_KERNEL, node); + adp = (struct bau_desc *)kmalloc_node(16384, GFP_KERNEL, node); BUG_ON(!adp); - pa = __pa((unsigned long)adp); + pa = uv_gpa(adp); /* need the real nasid*/ n = pa >> uv_nshift; m = pa & uv_mmask; @@ -666,8 +732,12 @@ uv_activation_descriptor_init(int node, int pnode) for (i = 0, ad2 = adp; i < UV_ACTIVATION_DESCRIPTOR_SIZE; i++, ad2++) { memset(ad2, 0, sizeof(struct bau_desc)); ad2->header.sw_ack_flag = 1; - ad2->header.base_dest_nodeid = - uv_blade_to_pnode(uv_cpu_to_blade_id(0)); + /* + * base_dest_nodeid is the first node in the partition, so + * the bit map will indicate partition-relative node numbers. + * note that base_dest_nodeid is actually a nasid. + */ + ad2->header.base_dest_nodeid = uv_partition_base_pnode << 1; ad2->header.command = UV_NET_ENDPOINT_INTD; ad2->header.int_both = 1; /* @@ -685,6 +755,8 @@ static struct bau_payload_queue_entry * __init uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) { struct bau_payload_queue_entry *pqp; + unsigned long pa; + int pn; char *cp; pqp = (struct bau_payload_queue_entry *) kmalloc_node( @@ -695,10 +767,14 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) cp = (char *)pqp + 31; pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5); bau_tablesp->va_queue_first = pqp; + /* + * need the pnode of where the memory was really allocated + */ + pa = uv_gpa(pqp); + pn = pa >> uv_nshift; uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, - ((unsigned long)pnode << - UV_PAYLOADQ_PNODE_SHIFT) | + ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | uv_physnodeaddr(pqp)); uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, uv_physnodeaddr(pqp)); @@ -714,8 +790,9 @@ uv_payload_queue_init(int node, int pnode, struct bau_control *bau_tablesp) /* * Initialization of each UV blade's structures */ -static int __init uv_init_blade(int blade, int node, int cur_cpu) +static int __init uv_init_blade(int blade) { + int node; int pnode; unsigned long pa; unsigned long apicid; @@ -723,16 +800,17 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu) struct bau_payload_queue_entry *pqp; struct bau_control *bau_tablesp; + node = blade_to_first_node(blade); bau_tablesp = uv_table_bases_init(blade, node); pnode = uv_blade_to_pnode(blade); adp = uv_activation_descriptor_init(node, pnode); pqp = uv_payload_queue_init(node, pnode, bau_tablesp); - uv_table_bases_finish(blade, node, cur_cpu, bau_tablesp, adp); + uv_table_bases_finish(blade, bau_tablesp, adp); /* * the below initialization can't be in firmware because the * messaging IRQ will be determined by the OS */ - apicid = per_cpu(x86_cpu_to_apicid, cur_cpu); + 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, @@ -747,40 +825,34 @@ static int __init uv_init_blade(int blade, int node, int cur_cpu) static int __init uv_bau_init(void) { int blade; - int node; int nblades; - int last_blade; int cur_cpu; if (!is_uv_system()) return 0; + for_each_possible_cpu(cur_cpu) + alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu), + GFP_KERNEL, cpu_to_node(cur_cpu)); + uv_bau_retry_limit = 1; uv_nshift = uv_hub_info->n_val; uv_mmask = (1UL << uv_hub_info->n_val) - 1; - nblades = 0; - last_blade = -1; - cur_cpu = 0; - for_each_online_node(node) { - blade = uv_node_to_blade_id(node); - if (blade == last_blade) - continue; - last_blade = blade; - nblades++; - } + nblades = uv_num_possible_blades(); + uv_bau_table_bases = (struct bau_control **) kmalloc(nblades * sizeof(struct bau_control *), GFP_KERNEL); BUG_ON(!uv_bau_table_bases); - last_blade = -1; - for_each_online_node(node) { - blade = uv_node_to_blade_id(node); - if (blade == last_blade) - continue; - last_blade = blade; - uv_init_blade(blade, node, cur_cpu); - cur_cpu += uv_blade_nr_possible_cpus(blade); - } + uv_partition_base_pnode = 0x7fffffff; + for (blade = 0; blade < nblades; blade++) + if (uv_blade_nr_possible_cpus(blade) && + (uv_blade_to_pnode(blade) < uv_partition_base_pnode)) + uv_partition_base_pnode = uv_blade_to_pnode(blade); + for (blade = 0; blade < nblades; blade++) + if (uv_blade_nr_possible_cpus(blade)) + uv_init_blade(blade); + alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); uv_enable_timeouts(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 462b9ba..7a567eb 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -17,20 +17,21 @@ #include <asm/delay.h> #include <asm/hypervisor.h> -unsigned int cpu_khz; /* TSC clocks / usec, not used here */ +unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); -unsigned int tsc_khz; + +unsigned int __read_mostly tsc_khz; EXPORT_SYMBOL(tsc_khz); /* * TSC can be unstable due to cpufreq or due to unsynced TSCs */ -static int tsc_unstable; +static int __read_mostly tsc_unstable; /* native_sched_clock() is called before tsc_init(), so we must start with the TSC soft disabled to prevent erroneous rdtsc usage on !cpu_has_tsc processors */ -static int tsc_disabled = -1; +static int __read_mostly tsc_disabled = -1; static int tsc_clocksource_reliable; /* @@ -543,8 +544,6 @@ unsigned long native_calibrate_tsc(void) return tsc_pit_min; } -#ifdef CONFIG_X86_32 -/* Only called from the Powernow K7 cpu freq driver */ int recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP @@ -566,7 +565,6 @@ int recalibrate_cpu_khz(void) EXPORT_SYMBOL(recalibrate_cpu_khz); -#endif /* CONFIG_X86_32 */ /* Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c index 67f9b9d..36afb98 100644 --- a/arch/x86/kernel/uv_sysfs.c +++ b/arch/x86/kernel/uv_sysfs.c @@ -21,6 +21,7 @@ #include <linux/sysdev.h> #include <asm/uv/bios.h> +#include <asm/uv/uv.h> struct kobject *sgi_uv_kobj; @@ -47,6 +48,9 @@ static int __init sgi_uv_sysfs_init(void) { unsigned long ret; + if (!is_uv_system()) + return -ENODEV; + if (!sgi_uv_kobj) sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj); if (!sgi_uv_kobj) { diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c index 33a788d..d303369 100644 --- a/arch/x86/kernel/vmiclock_32.c +++ b/arch/x86/kernel/vmiclock_32.c @@ -202,7 +202,6 @@ static struct irqaction vmi_clock_action = { .name = "vmi-timer", .handler = vmi_timer_interrupt, .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER, - .mask = CPU_MASK_ALL, }; static void __devinit vmi_time_init_clockevent(void) diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 74de562..a1d804b 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -22,7 +22,7 @@ #include <asm/paravirt.h> #include <asm/setup.h> -#ifdef CONFIG_PARAVIRT +#if defined CONFIG_PCI && defined CONFIG_PARAVIRT /* * Interrupt control on vSMPowered systems: * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' @@ -114,6 +114,7 @@ static void __init set_vsmp_pv_ops(void) } #endif +#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -139,6 +140,15 @@ int is_vsmp_box(void) } } +#else +static void __init detect_vsmp_box(void) +{ +} +int is_vsmp_box(void) +{ + return 0; +} +#endif void __init vsmp_init(void) { detect_vsmp_box(); diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index 2b54fe0..0a5b04a 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -324,7 +324,7 @@ void __ref xsave_cntxt_init(void) } /* - * for now OS knows only about FP/SSE + * Support only the state known to OS. */ pcntxt_mask = pcntxt_mask & XCNTXT_MASK; xsave_init(); diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b81125f..a58504e 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -4,6 +4,10 @@ config HAVE_KVM bool +config HAVE_KVM_IRQCHIP + bool + default y + menuconfig VIRTUALIZATION bool "Virtualization" depends on HAVE_KVM || X86 @@ -55,7 +59,8 @@ config KVM_AMD config KVM_TRACE bool "KVM trace support" - depends on KVM && MARKERS && SYSFS + depends on KVM && SYSFS + select MARKERS select RELAY select DEBUG_FS default n diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 72bd275..c13bb92 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -201,6 +201,9 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps) if (!atomic_inc_and_test(&pt->pending)) set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests); + if (!pt->reinject) + atomic_set(&pt->pending, 1); + if (vcpu0 && waitqueue_active(&vcpu0->wq)) wake_up_interruptible(&vcpu0->wq); @@ -536,6 +539,16 @@ void kvm_pit_reset(struct kvm_pit *pit) pit->pit_state.irq_ack = 1; } +static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask) +{ + struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier); + + if (!mask) { + atomic_set(&pit->pit_state.pit_timer.pending, 0); + pit->pit_state.irq_ack = 1; + } +} + struct kvm_pit *kvm_create_pit(struct kvm *kvm) { struct kvm_pit *pit; @@ -545,9 +558,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) if (!pit) return NULL; - mutex_lock(&kvm->lock); pit->irq_source_id = kvm_request_irq_source_id(kvm); - mutex_unlock(&kvm->lock); if (pit->irq_source_id < 0) { kfree(pit); return NULL; @@ -580,10 +591,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm) pit_state->irq_ack_notifier.gsi = 0; pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq; kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier); + pit_state->pit_timer.reinject = true; mutex_unlock(&pit->pit_state.lock); kvm_pit_reset(pit); + pit->mask_notifier.func = pit_mask_notifer; + kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier); + return pit; } @@ -592,6 +607,8 @@ void kvm_free_pit(struct kvm *kvm) struct hrtimer *timer; if (kvm->arch.vpit) { + kvm_unregister_irq_mask_notifier(kvm, 0, + &kvm->arch.vpit->mask_notifier); mutex_lock(&kvm->arch.vpit->pit_state.lock); timer = &kvm->arch.vpit->pit_state.pit_timer.timer; hrtimer_cancel(timer); diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h index 4178022..6acbe4b 100644 --- a/arch/x86/kvm/i8254.h +++ b/arch/x86/kvm/i8254.h @@ -9,6 +9,7 @@ struct kvm_kpit_timer { s64 period; /* unit: ns */ s64 scheduled; atomic_t pending; + bool reinject; }; struct kvm_kpit_channel_state { @@ -45,6 +46,7 @@ struct kvm_pit { struct kvm *kvm; struct kvm_kpit_state pit_state; int irq_source_id; + struct kvm_irq_mask_notifier mask_notifier; }; #define KVM_PIT_BASE_ADDRESS 0x40 diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 179dcb0..1ccb50c 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -32,11 +32,13 @@ #include <linux/kvm_host.h> static void pic_lock(struct kvm_pic *s) + __acquires(&s->lock) { spin_lock(&s->lock); } static void pic_unlock(struct kvm_pic *s) + __releases(&s->lock) { struct kvm *kvm = s->kvm; unsigned acks = s->pending_acks; @@ -49,7 +51,8 @@ static void pic_unlock(struct kvm_pic *s) spin_unlock(&s->lock); while (acks) { - kvm_notify_acked_irq(kvm, __ffs(acks)); + kvm_notify_acked_irq(kvm, SELECT_PIC(__ffs(acks)), + __ffs(acks)); acks &= acks - 1; } @@ -76,12 +79,13 @@ void kvm_pic_clear_isr_ack(struct kvm *kvm) /* * set irq level. If an edge is detected, then the IRR is set to 1 */ -static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) +static inline int pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) { - int mask; + int mask, ret = 1; mask = 1 << irq; if (s->elcr & mask) /* level triggered */ if (level) { + ret = !(s->irr & mask); s->irr |= mask; s->last_irr |= mask; } else { @@ -90,11 +94,15 @@ static inline void pic_set_irq1(struct kvm_kpic_state *s, int irq, int level) } else /* edge triggered */ if (level) { - if ((s->last_irr & mask) == 0) + if ((s->last_irr & mask) == 0) { + ret = !(s->irr & mask); s->irr |= mask; + } s->last_irr |= mask; } else s->last_irr &= ~mask; + + return (s->imr & mask) ? -1 : ret; } /* @@ -171,16 +179,19 @@ void kvm_pic_update_irq(struct kvm_pic *s) pic_unlock(s); } -void kvm_pic_set_irq(void *opaque, int irq, int level) +int kvm_pic_set_irq(void *opaque, int irq, int level) { struct kvm_pic *s = opaque; + int ret = -1; pic_lock(s); if (irq >= 0 && irq < PIC_NUM_PINS) { - pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); + ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level); pic_update_irq(s); } pic_unlock(s); + + return ret; } /* @@ -232,7 +243,7 @@ int kvm_pic_read_irq(struct kvm *kvm) } pic_update_irq(s); pic_unlock(s); - kvm_notify_acked_irq(kvm, irq); + kvm_notify_acked_irq(kvm, SELECT_PIC(irq), irq); return intno; } diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 82579ee..9f59318 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -32,6 +32,8 @@ #include "lapic.h" #define PIC_NUM_PINS 16 +#define SELECT_PIC(irq) \ + ((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE) struct kvm; struct kvm_vcpu; diff --git a/arch/x86/kvm/kvm_svm.h b/arch/x86/kvm/kvm_svm.h index 8e5ee99..ed66e4c 100644 --- a/arch/x86/kvm/kvm_svm.h +++ b/arch/x86/kvm/kvm_svm.h @@ -18,7 +18,6 @@ static const u32 host_save_user_msrs[] = { }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) -#define NUM_DB_REGS 4 struct kvm_vcpu; @@ -29,18 +28,23 @@ struct vcpu_svm { struct svm_cpu_data *svm_data; uint64_t asid_generation; - unsigned long db_regs[NUM_DB_REGS]; - u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; u64 host_gs_base; unsigned long host_cr2; - unsigned long host_db_regs[NUM_DB_REGS]; - unsigned long host_dr6; - unsigned long host_dr7; u32 *msrpm; + struct vmcb *hsave; + u64 hsave_msr; + + u64 nested_vmcb; + + /* These are the merged vectors */ + u32 *nested_msrpm; + + /* gpa pointers to the real vectors */ + u64 nested_vmcb_msrpm; }; #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 2d4477c..2a36f7f 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -145,11 +145,20 @@ struct kvm_rmap_desc { struct kvm_rmap_desc *more; }; -struct kvm_shadow_walk { - int (*entry)(struct kvm_shadow_walk *walk, struct kvm_vcpu *vcpu, - u64 addr, u64 *spte, int level); +struct kvm_shadow_walk_iterator { + u64 addr; + hpa_t shadow_addr; + int level; + u64 *sptep; + unsigned index; }; +#define for_each_shadow_entry(_vcpu, _addr, _walker) \ + for (shadow_walk_init(&(_walker), _vcpu, _addr); \ + shadow_walk_okay(&(_walker)); \ + shadow_walk_next(&(_walker))) + + struct kvm_unsync_walk { int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk); }; @@ -343,7 +352,6 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc, BUG_ON(!mc->nobjs); p = mc->objects[--mc->nobjs]; - memset(p, 0, size); return p; } @@ -794,10 +802,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&sp->oos_link); - ASSERT(is_empty_shadow_page(sp->spt)); bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); sp->multimapped = 0; - sp->global = 1; sp->parent_pte = parent_pte; --vcpu->kvm->arch.n_free_mmu_pages; return sp; @@ -983,8 +989,8 @@ struct kvm_mmu_pages { idx < 512; \ idx = find_next_bit(bitmap, 512, idx+1)) -int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, - int idx) +static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, + int idx) { int i; @@ -1059,7 +1065,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry(sp, node, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical + if (sp->gfn == gfn && !sp->role.direct && !sp->role.invalid) { pgprintk("%s: found role %x\n", __func__, sp->role.word); @@ -1115,8 +1121,9 @@ struct mmu_page_path { i < pvec.nr && ({ sp = pvec.page[i].sp; 1;}); \ i = mmu_pages_next(&pvec, &parents, i)) -int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents, - int i) +static int mmu_pages_next(struct kvm_mmu_pages *pvec, + struct mmu_page_path *parents, + int i) { int n; @@ -1135,7 +1142,7 @@ int mmu_pages_next(struct kvm_mmu_pages *pvec, struct mmu_page_path *parents, return n; } -void mmu_pages_clear_parents(struct mmu_page_path *parents) +static void mmu_pages_clear_parents(struct mmu_page_path *parents) { struct kvm_mmu_page *sp; unsigned int level = 0; @@ -1193,7 +1200,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, unsigned level, - int metaphysical, + int direct, unsigned access, u64 *parent_pte) { @@ -1204,10 +1211,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp; struct hlist_node *node, *tmp; - role.word = 0; - role.glevels = vcpu->arch.mmu.root_level; + role = vcpu->arch.mmu.base_role; role.level = level; - role.metaphysical = metaphysical; + role.direct = direct; role.access = access; if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) { quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level)); @@ -1242,8 +1248,9 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, pgprintk("%s: adding gfn %lx role %x\n", __func__, gfn, role.word); sp->gfn = gfn; sp->role = role; + sp->global = role.cr4_pge; hlist_add_head(&sp->hash_link, bucket); - if (!metaphysical) { + if (!direct) { if (rmap_write_protect(vcpu->kvm, gfn)) kvm_flush_remote_tlbs(vcpu->kvm); account_shadowed(vcpu->kvm, gfn); @@ -1255,35 +1262,35 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, return sp; } -static int walk_shadow(struct kvm_shadow_walk *walker, - struct kvm_vcpu *vcpu, u64 addr) +static void shadow_walk_init(struct kvm_shadow_walk_iterator *iterator, + struct kvm_vcpu *vcpu, u64 addr) { - hpa_t shadow_addr; - int level; - int r; - u64 *sptep; - unsigned index; - - shadow_addr = vcpu->arch.mmu.root_hpa; - level = vcpu->arch.mmu.shadow_root_level; - if (level == PT32E_ROOT_LEVEL) { - shadow_addr = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; - shadow_addr &= PT64_BASE_ADDR_MASK; - if (!shadow_addr) - return 1; - --level; + iterator->addr = addr; + iterator->shadow_addr = vcpu->arch.mmu.root_hpa; + iterator->level = vcpu->arch.mmu.shadow_root_level; + if (iterator->level == PT32E_ROOT_LEVEL) { + iterator->shadow_addr + = vcpu->arch.mmu.pae_root[(addr >> 30) & 3]; + iterator->shadow_addr &= PT64_BASE_ADDR_MASK; + --iterator->level; + if (!iterator->shadow_addr) + iterator->level = 0; } +} - while (level >= PT_PAGE_TABLE_LEVEL) { - index = SHADOW_PT_INDEX(addr, level); - sptep = ((u64 *)__va(shadow_addr)) + index; - r = walker->entry(walker, vcpu, addr, sptep, level); - if (r) - return r; - shadow_addr = *sptep & PT64_BASE_ADDR_MASK; - --level; - } - return 0; +static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator) +{ + if (iterator->level < PT_PAGE_TABLE_LEVEL) + return false; + iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level); + iterator->sptep = ((u64 *)__va(iterator->shadow_addr)) + iterator->index; + return true; +} + +static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) +{ + iterator->shadow_addr = *iterator->sptep & PT64_BASE_ADDR_MASK; + --iterator->level; } static void kvm_mmu_page_unlink_children(struct kvm *kvm, @@ -1388,7 +1395,7 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_page_unlink_children(kvm, sp); kvm_mmu_unlink_parents(kvm, sp); kvm_flush_remote_tlbs(kvm); - if (!sp->role.invalid && !sp->role.metaphysical) + if (!sp->role.invalid && !sp->role.direct) unaccount_shadowed(kvm, sp->gfn); if (sp->unsync) kvm_unlink_unsync_page(kvm, sp); @@ -1451,7 +1458,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) index = kvm_page_table_hashfn(gfn); bucket = &kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) - if (sp->gfn == gfn && !sp->role.metaphysical) { + if (sp->gfn == gfn && !sp->role.direct) { pgprintk("%s: gfn %lx role %x\n", __func__, gfn, sp->role.word); r = 1; @@ -1463,11 +1470,20 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) { + unsigned index; + struct hlist_head *bucket; struct kvm_mmu_page *sp; + struct hlist_node *node, *nn; - while ((sp = kvm_mmu_lookup_page(kvm, gfn)) != NULL) { - pgprintk("%s: zap %lx %x\n", __func__, gfn, sp->role.word); - kvm_mmu_zap_page(kvm, sp); + index = kvm_page_table_hashfn(gfn); + bucket = &kvm->arch.mmu_page_hash[index]; + hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) { + if (sp->gfn == gfn && !sp->role.direct + && !sp->role.invalid) { + pgprintk("%s: zap %lx %x\n", + __func__, gfn, sp->role.word); + kvm_mmu_zap_page(kvm, sp); + } } } @@ -1622,7 +1638,7 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) bucket = &vcpu->kvm->arch.mmu_page_hash[index]; /* don't unsync if pagetable is shadowed with multiple roles */ hlist_for_each_entry_safe(s, node, n, bucket, hash_link) { - if (s->gfn != sp->gfn || s->role.metaphysical) + if (s->gfn != sp->gfn || s->role.direct) continue; if (s->role.word != sp->role.word) return 1; @@ -1669,8 +1685,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, u64 mt_mask = shadow_mt_mask; struct kvm_mmu_page *sp = page_header(__pa(shadow_pte)); - if (!(vcpu->arch.cr4 & X86_CR4_PGE)) - global = 0; if (!global && sp->global) { sp->global = 0; if (sp->unsync) { @@ -1777,12 +1791,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, pgprintk("hfn old %lx new %lx\n", spte_to_pfn(*shadow_pte), pfn); rmap_remove(vcpu->kvm, shadow_pte); - } else { - if (largepage) - was_rmapped = is_large_pte(*shadow_pte); - else - was_rmapped = 1; - } + } else + was_rmapped = 1; } if (set_spte(vcpu, shadow_pte, pte_access, user_fault, write_fault, dirty, largepage, global, gfn, pfn, speculative, true)) { @@ -1820,67 +1830,42 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) { } -struct direct_shadow_walk { - struct kvm_shadow_walk walker; - pfn_t pfn; - int write; - int largepage; - int pt_write; -}; - -static int direct_map_entry(struct kvm_shadow_walk *_walk, - struct kvm_vcpu *vcpu, - u64 addr, u64 *sptep, int level) +static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, + int largepage, gfn_t gfn, pfn_t pfn) { - struct direct_shadow_walk *walk = - container_of(_walk, struct direct_shadow_walk, walker); + struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; + int pt_write = 0; gfn_t pseudo_gfn; - gfn_t gfn = addr >> PAGE_SHIFT; - - if (level == PT_PAGE_TABLE_LEVEL - || (walk->largepage && level == PT_DIRECTORY_LEVEL)) { - mmu_set_spte(vcpu, sptep, ACC_ALL, ACC_ALL, - 0, walk->write, 1, &walk->pt_write, - walk->largepage, 0, gfn, walk->pfn, false); - ++vcpu->stat.pf_fixed; - return 1; - } - if (*sptep == shadow_trap_nonpresent_pte) { - pseudo_gfn = (addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; - sp = kvm_mmu_get_page(vcpu, pseudo_gfn, (gva_t)addr, level - 1, - 1, ACC_ALL, sptep); - if (!sp) { - pgprintk("nonpaging_map: ENOMEM\n"); - kvm_release_pfn_clean(walk->pfn); - return -ENOMEM; + for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { + if (iterator.level == PT_PAGE_TABLE_LEVEL + || (largepage && iterator.level == PT_DIRECTORY_LEVEL)) { + mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, ACC_ALL, + 0, write, 1, &pt_write, + largepage, 0, gfn, pfn, false); + ++vcpu->stat.pf_fixed; + break; } - set_shadow_pte(sptep, - __pa(sp->spt) - | PT_PRESENT_MASK | PT_WRITABLE_MASK - | shadow_user_mask | shadow_x_mask); - } - return 0; -} + if (*iterator.sptep == shadow_trap_nonpresent_pte) { + pseudo_gfn = (iterator.addr & PT64_DIR_BASE_ADDR_MASK) >> PAGE_SHIFT; + sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, + iterator.level - 1, + 1, ACC_ALL, iterator.sptep); + if (!sp) { + pgprintk("nonpaging_map: ENOMEM\n"); + kvm_release_pfn_clean(pfn); + return -ENOMEM; + } -static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int largepage, gfn_t gfn, pfn_t pfn) -{ - int r; - struct direct_shadow_walk walker = { - .walker = { .entry = direct_map_entry, }, - .pfn = pfn, - .largepage = largepage, - .write = write, - .pt_write = 0, - }; - - r = walk_shadow(&walker.walker, vcpu, gfn << PAGE_SHIFT); - if (r < 0) - return r; - return walker.pt_write; + set_shadow_pte(iterator.sptep, + __pa(sp->spt) + | PT_PRESENT_MASK | PT_WRITABLE_MASK + | shadow_user_mask | shadow_x_mask); + } + } + return pt_write; } static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn) @@ -1962,7 +1947,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) int i; gfn_t root_gfn; struct kvm_mmu_page *sp; - int metaphysical = 0; + int direct = 0; root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT; @@ -1971,18 +1956,18 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) ASSERT(!VALID_PAGE(root)); if (tdp_enabled) - metaphysical = 1; + direct = 1; sp = kvm_mmu_get_page(vcpu, root_gfn, 0, - PT64_ROOT_LEVEL, metaphysical, + PT64_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; vcpu->arch.mmu.root_hpa = root; return; } - metaphysical = !is_paging(vcpu); + direct = !is_paging(vcpu); if (tdp_enabled) - metaphysical = 1; + direct = 1; for (i = 0; i < 4; ++i) { hpa_t root = vcpu->arch.mmu.pae_root[i]; @@ -1996,7 +1981,7 @@ static void mmu_alloc_roots(struct kvm_vcpu *vcpu) } else if (vcpu->arch.mmu.root_level == 0) root_gfn = 0; sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, metaphysical, + PT32_ROOT_LEVEL, direct, ACC_ALL, NULL); root = __pa(sp->spt); ++sp->root_count; @@ -2251,17 +2236,23 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) static int init_kvm_softmmu(struct kvm_vcpu *vcpu) { + int r; + ASSERT(vcpu); ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); if (!is_paging(vcpu)) - return nonpaging_init_context(vcpu); + r = nonpaging_init_context(vcpu); else if (is_long_mode(vcpu)) - return paging64_init_context(vcpu); + r = paging64_init_context(vcpu); else if (is_pae(vcpu)) - return paging32E_init_context(vcpu); + r = paging32E_init_context(vcpu); else - return paging32_init_context(vcpu); + r = paging32_init_context(vcpu); + + vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level; + + return r; } static int init_kvm_mmu(struct kvm_vcpu *vcpu) @@ -2492,7 +2483,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, index = kvm_page_table_hashfn(gfn); bucket = &vcpu->kvm->arch.mmu_page_hash[index]; hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) { - if (sp->gfn != gfn || sp->role.metaphysical || sp->role.invalid) + if (sp->gfn != gfn || sp->role.direct || sp->role.invalid) continue; pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8; misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); @@ -3130,7 +3121,7 @@ static void audit_write_protection(struct kvm_vcpu *vcpu) gfn_t gfn; list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) { - if (sp->role.metaphysical) + if (sp->role.direct) continue; gfn = unalias_gfn(vcpu->kvm, sp->gfn); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 258e5d5..eaab214 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -54,7 +54,7 @@ static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) static inline int is_long_mode(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 - return vcpu->arch.shadow_efer & EFER_LME; + return vcpu->arch.shadow_efer & EFER_LMA; #else return 0; #endif diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 9fd78b6..6bd7020 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -25,7 +25,6 @@ #if PTTYPE == 64 #define pt_element_t u64 #define guest_walker guest_walker64 - #define shadow_walker shadow_walker64 #define FNAME(name) paging##64_##name #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK #define PT_DIR_BASE_ADDR_MASK PT64_DIR_BASE_ADDR_MASK @@ -42,7 +41,6 @@ #elif PTTYPE == 32 #define pt_element_t u32 #define guest_walker guest_walker32 - #define shadow_walker shadow_walker32 #define FNAME(name) paging##32_##name #define PT_BASE_ADDR_MASK PT32_BASE_ADDR_MASK #define PT_DIR_BASE_ADDR_MASK PT32_DIR_BASE_ADDR_MASK @@ -73,18 +71,6 @@ struct guest_walker { u32 error_code; }; -struct shadow_walker { - struct kvm_shadow_walk walker; - struct guest_walker *guest_walker; - int user_fault; - int write_fault; - int largepage; - int *ptwrite; - pfn_t pfn; - u64 *sptep; - gpa_t pte_gpa; -}; - static gfn_t gpte_to_gfn(pt_element_t gpte) { return (gpte & PT_BASE_ADDR_MASK) >> PAGE_SHIFT; @@ -283,91 +269,79 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page, /* * Fetch a shadow pte for a specific level in the paging hierarchy. */ -static int FNAME(shadow_walk_entry)(struct kvm_shadow_walk *_sw, - struct kvm_vcpu *vcpu, u64 addr, - u64 *sptep, int level) +static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, + struct guest_walker *gw, + int user_fault, int write_fault, int largepage, + int *ptwrite, pfn_t pfn) { - struct shadow_walker *sw = - container_of(_sw, struct shadow_walker, walker); - struct guest_walker *gw = sw->guest_walker; unsigned access = gw->pt_access; struct kvm_mmu_page *shadow_page; - u64 spte; - int metaphysical; + u64 spte, *sptep; + int direct; gfn_t table_gfn; int r; + int level; pt_element_t curr_pte; + struct kvm_shadow_walk_iterator iterator; - if (level == PT_PAGE_TABLE_LEVEL - || (sw->largepage && level == PT_DIRECTORY_LEVEL)) { - mmu_set_spte(vcpu, sptep, access, gw->pte_access & access, - sw->user_fault, sw->write_fault, - gw->ptes[gw->level-1] & PT_DIRTY_MASK, - sw->ptwrite, sw->largepage, - gw->ptes[gw->level-1] & PT_GLOBAL_MASK, - gw->gfn, sw->pfn, false); - sw->sptep = sptep; - return 1; - } + if (!is_present_pte(gw->ptes[gw->level - 1])) + return NULL; - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) - return 0; + for_each_shadow_entry(vcpu, addr, iterator) { + level = iterator.level; + sptep = iterator.sptep; + if (level == PT_PAGE_TABLE_LEVEL + || (largepage && level == PT_DIRECTORY_LEVEL)) { + mmu_set_spte(vcpu, sptep, access, + gw->pte_access & access, + user_fault, write_fault, + gw->ptes[gw->level-1] & PT_DIRTY_MASK, + ptwrite, largepage, + gw->ptes[gw->level-1] & PT_GLOBAL_MASK, + gw->gfn, pfn, false); + break; + } - if (is_large_pte(*sptep)) { - set_shadow_pte(sptep, shadow_trap_nonpresent_pte); - kvm_flush_remote_tlbs(vcpu->kvm); - rmap_remove(vcpu->kvm, sptep); - } + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) + continue; - if (level == PT_DIRECTORY_LEVEL && gw->level == PT_DIRECTORY_LEVEL) { - metaphysical = 1; - if (!is_dirty_pte(gw->ptes[level - 1])) - access &= ~ACC_WRITE_MASK; - table_gfn = gpte_to_gfn(gw->ptes[level - 1]); - } else { - metaphysical = 0; - table_gfn = gw->table_gfn[level - 2]; - } - shadow_page = kvm_mmu_get_page(vcpu, table_gfn, (gva_t)addr, level-1, - metaphysical, access, sptep); - if (!metaphysical) { - r = kvm_read_guest_atomic(vcpu->kvm, gw->pte_gpa[level - 2], - &curr_pte, sizeof(curr_pte)); - if (r || curr_pte != gw->ptes[level - 2]) { - kvm_mmu_put_page(shadow_page, sptep); - kvm_release_pfn_clean(sw->pfn); - sw->sptep = NULL; - return 1; + if (is_large_pte(*sptep)) { + rmap_remove(vcpu->kvm, sptep); + set_shadow_pte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); } - } - spte = __pa(shadow_page->spt) | PT_PRESENT_MASK | PT_ACCESSED_MASK - | PT_WRITABLE_MASK | PT_USER_MASK; - *sptep = spte; - return 0; -} - -static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, - struct guest_walker *guest_walker, - int user_fault, int write_fault, int largepage, - int *ptwrite, pfn_t pfn) -{ - struct shadow_walker walker = { - .walker = { .entry = FNAME(shadow_walk_entry), }, - .guest_walker = guest_walker, - .user_fault = user_fault, - .write_fault = write_fault, - .largepage = largepage, - .ptwrite = ptwrite, - .pfn = pfn, - }; - - if (!is_present_pte(guest_walker->ptes[guest_walker->level - 1])) - return NULL; + if (level == PT_DIRECTORY_LEVEL + && gw->level == PT_DIRECTORY_LEVEL) { + direct = 1; + if (!is_dirty_pte(gw->ptes[level - 1])) + access &= ~ACC_WRITE_MASK; + table_gfn = gpte_to_gfn(gw->ptes[level - 1]); + } else { + direct = 0; + table_gfn = gw->table_gfn[level - 2]; + } + shadow_page = kvm_mmu_get_page(vcpu, table_gfn, addr, level-1, + direct, access, sptep); + if (!direct) { + r = kvm_read_guest_atomic(vcpu->kvm, + gw->pte_gpa[level - 2], + &curr_pte, sizeof(curr_pte)); + if (r || curr_pte != gw->ptes[level - 2]) { + kvm_mmu_put_page(shadow_page, sptep); + kvm_release_pfn_clean(pfn); + sptep = NULL; + break; + } + } - walk_shadow(&walker.walker, vcpu, addr); + spte = __pa(shadow_page->spt) + | PT_PRESENT_MASK | PT_ACCESSED_MASK + | PT_WRITABLE_MASK | PT_USER_MASK; + *sptep = spte; + } - return walker.sptep; + return sptep; } /* @@ -465,54 +439,56 @@ out_unlock: return 0; } -static int FNAME(shadow_invlpg_entry)(struct kvm_shadow_walk *_sw, - struct kvm_vcpu *vcpu, u64 addr, - u64 *sptep, int level) +static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { - struct shadow_walker *sw = - container_of(_sw, struct shadow_walker, walker); - - /* FIXME: properly handle invlpg on large guest pages */ - if (level == PT_PAGE_TABLE_LEVEL || - ((level == PT_DIRECTORY_LEVEL) && is_large_pte(*sptep))) { - struct kvm_mmu_page *sp = page_header(__pa(sptep)); + struct kvm_shadow_walk_iterator iterator; + pt_element_t gpte; + gpa_t pte_gpa = -1; + int level; + u64 *sptep; + int need_flush = 0; - sw->pte_gpa = (sp->gfn << PAGE_SHIFT); - sw->pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); + spin_lock(&vcpu->kvm->mmu_lock); - if (is_shadow_present_pte(*sptep)) { - rmap_remove(vcpu->kvm, sptep); - if (is_large_pte(*sptep)) - --vcpu->kvm->stat.lpages; + for_each_shadow_entry(vcpu, gva, iterator) { + 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))) { + struct kvm_mmu_page *sp = page_header(__pa(sptep)); + + pte_gpa = (sp->gfn << PAGE_SHIFT); + pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); + + if (is_shadow_present_pte(*sptep)) { + rmap_remove(vcpu->kvm, sptep); + if (is_large_pte(*sptep)) + --vcpu->kvm->stat.lpages; + need_flush = 1; + } + set_shadow_pte(sptep, shadow_trap_nonpresent_pte); + break; } - set_shadow_pte(sptep, shadow_trap_nonpresent_pte); - return 1; - } - if (!is_shadow_present_pte(*sptep)) - return 1; - return 0; -} -static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) -{ - pt_element_t gpte; - struct shadow_walker walker = { - .walker = { .entry = FNAME(shadow_invlpg_entry), }, - .pte_gpa = -1, - }; + if (!is_shadow_present_pte(*sptep)) + break; + } - spin_lock(&vcpu->kvm->mmu_lock); - walk_shadow(&walker.walker, vcpu, gva); + if (need_flush) + kvm_flush_remote_tlbs(vcpu->kvm); spin_unlock(&vcpu->kvm->mmu_lock); - if (walker.pte_gpa == -1) + + if (pte_gpa == -1) return; - if (kvm_read_guest_atomic(vcpu->kvm, walker.pte_gpa, &gpte, + if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, sizeof(pt_element_t))) return; if (is_present_pte(gpte) && (gpte & PT_ACCESSED_MASK)) { if (mmu_topup_memory_caches(vcpu)) return; - kvm_mmu_pte_write(vcpu, walker.pte_gpa, (const u8 *)&gpte, + kvm_mmu_pte_write(vcpu, pte_gpa, (const u8 *)&gpte, sizeof(pt_element_t), 0); } } @@ -540,7 +516,7 @@ static void FNAME(prefetch_page)(struct kvm_vcpu *vcpu, pt_element_t pt[256 / sizeof(pt_element_t)]; gpa_t pte_gpa; - if (sp->role.metaphysical + if (sp->role.direct || (PTTYPE == 32 && sp->role.level > PT_PAGE_TABLE_LEVEL)) { nonpaging_prefetch_page(vcpu, sp); return; @@ -619,7 +595,6 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) #undef pt_element_t #undef guest_walker -#undef shadow_walker #undef FNAME #undef PT_BASE_ADDR_MASK #undef PT_INDEX diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a9e769e..1821c20 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -38,9 +38,6 @@ MODULE_LICENSE("GPL"); #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 -#define DR7_GD_MASK (1 << 13) -#define DR6_BD_MASK (1 << 13) - #define SEG_TYPE_LDT 2 #define SEG_TYPE_BUSY_TSS16 3 @@ -50,6 +47,15 @@ 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 + /* enable NPT for AMD64 and X86 with PAE */ #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) static bool npt_enabled = true; @@ -60,14 +66,29 @@ static int npt = 1; module_param(npt, int, S_IRUGO); +static int nested = 0; +module_param(nested, int, S_IRUGO); + static void kvm_reput_irq(struct vcpu_svm *svm); static void svm_flush_tlb(struct kvm_vcpu *vcpu); +static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override); +static int nested_svm_vmexit(struct vcpu_svm *svm); +static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb, + void *arg2, void *opaque); +static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code); + static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_svm, vcpu); } +static inline bool is_nested(struct vcpu_svm *svm) +{ + return svm->nested_vmcb; +} + static unsigned long iopm_base; struct kvm_ldttss_desc { @@ -157,32 +178,6 @@ static inline void kvm_write_cr2(unsigned long val) asm volatile ("mov %0, %%cr2" :: "r" (val)); } -static inline unsigned long read_dr6(void) -{ - unsigned long dr6; - - asm volatile ("mov %%dr6, %0" : "=r" (dr6)); - return dr6; -} - -static inline void write_dr6(unsigned long val) -{ - asm volatile ("mov %0, %%dr6" :: "r" (val)); -} - -static inline unsigned long read_dr7(void) -{ - unsigned long dr7; - - asm volatile ("mov %%dr7, %0" : "=r" (dr7)); - return dr7; -} - -static inline void write_dr7(unsigned long val) -{ - asm volatile ("mov %0, %%dr7" :: "r" (val)); -} - static inline void force_new_asid(struct kvm_vcpu *vcpu) { to_svm(vcpu)->asid_generation--; @@ -198,7 +193,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) if (!npt_enabled && !(efer & EFER_LMA)) efer &= ~EFER_LME; - to_svm(vcpu)->vmcb->save.efer = efer | MSR_EFER_SVME_MASK; + to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; vcpu->arch.shadow_efer = efer; } @@ -207,6 +202,11 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, { struct vcpu_svm *svm = to_svm(vcpu); + /* If we are within a nested VM we'd better #VMEXIT and let the + guest handle the exception */ + if (nested_svm_check_exception(svm, nr, has_error_code, error_code)) + return; + svm->vmcb->control.event_inj = nr | SVM_EVTINJ_VALID | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0) @@ -242,7 +242,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, svm->next_rip); svm->vmcb->control.int_state &= ~SVM_INTERRUPT_SHADOW_MASK; - vcpu->arch.interrupt_window_open = 1; + vcpu->arch.interrupt_window_open = (svm->vcpu.arch.hflags & HF_GIF_MASK); } static int has_svm(void) @@ -250,7 +250,7 @@ static int has_svm(void) const char *msg; if (!cpu_has_svm(&msg)) { - printk(KERN_INFO "has_svn: %s\n", msg); + printk(KERN_INFO "has_svm: %s\n", msg); return 0; } @@ -292,7 +292,7 @@ static void svm_hardware_enable(void *garbage) svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer | MSR_EFER_SVME_MASK); + wrmsrl(MSR_EFER, efer | EFER_SVME); wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(svm_data->save_area) << PAGE_SHIFT); @@ -417,6 +417,14 @@ static __init int svm_hardware_setup(void) if (boot_cpu_has(X86_FEATURE_NX)) kvm_enable_efer_bits(EFER_NX); + if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) + kvm_enable_efer_bits(EFER_FFXSR); + + if (nested) { + printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); + kvm_enable_efer_bits(EFER_SVME); + } + for_each_online_cpu(cpu) { r = svm_cpu_init(cpu); if (r) @@ -559,7 +567,7 @@ static void init_vmcb(struct vcpu_svm *svm) init_sys_seg(&save->ldtr, SEG_TYPE_LDT); init_sys_seg(&save->tr, SEG_TYPE_BUSY_TSS16); - save->efer = MSR_EFER_SVME_MASK; + save->efer = EFER_SVME; save->dr6 = 0xffff0ff0; save->dr7 = 0x400; save->rflags = 2; @@ -591,6 +599,9 @@ static void init_vmcb(struct vcpu_svm *svm) save->cr4 = 0; } force_new_asid(&svm->vcpu); + + svm->nested_vmcb = 0; + svm->vcpu.arch.hflags = HF_GIF_MASK; } static int svm_vcpu_reset(struct kvm_vcpu *vcpu) @@ -615,6 +626,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) struct vcpu_svm *svm; struct page *page; struct page *msrpm_pages; + struct page *hsave_page; + struct page *nested_msrpm_pages; int err; svm = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL); @@ -637,14 +650,25 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); if (!msrpm_pages) goto uninit; + + nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER); + if (!nested_msrpm_pages) + goto uninit; + svm->msrpm = page_address(msrpm_pages); svm_vcpu_init_msrpm(svm->msrpm); + hsave_page = alloc_page(GFP_KERNEL); + if (!hsave_page) + goto uninit; + svm->hsave = page_address(hsave_page); + + svm->nested_msrpm = page_address(nested_msrpm_pages); + svm->vmcb = page_address(page); clear_page(svm->vmcb); svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; - memset(svm->db_regs, 0, sizeof(svm->db_regs)); init_vmcb(svm); fx_init(&svm->vcpu); @@ -669,6 +693,8 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu) __free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); + __free_page(virt_to_page(svm->hsave)); + __free_pages(virt_to_page(svm->nested_msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); } @@ -718,6 +744,16 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } +static void svm_set_vintr(struct vcpu_svm *svm) +{ + svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR; +} + +static void svm_clear_vintr(struct vcpu_svm *svm) +{ + svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); +} + static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) { struct vmcb_save_area *save = &to_svm(vcpu)->vmcb->save; @@ -760,20 +796,37 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1; var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1; - /* - * SVM always stores 0 for the 'G' bit in the CS selector in - * the VMCB on a VMEXIT. This hurts cross-vendor migration: - * Intel's VMENTRY has a check on the 'G' bit. - */ - if (seg == VCPU_SREG_CS) + switch (seg) { + case VCPU_SREG_CS: + /* + * SVM always stores 0 for the 'G' bit in the CS selector in + * the VMCB on a VMEXIT. This hurts cross-vendor migration: + * Intel's VMENTRY has a check on the 'G' bit. + */ var->g = s->limit > 0xfffff; - - /* - * Work around a bug where the busy flag in the tr selector - * isn't exposed - */ - if (seg == VCPU_SREG_TR) + break; + case VCPU_SREG_TR: + /* + * Work around a bug where the busy flag in the tr selector + * isn't exposed + */ var->type |= 0x2; + break; + case VCPU_SREG_DS: + case VCPU_SREG_ES: + case VCPU_SREG_FS: + case VCPU_SREG_GS: + /* + * The accessed bit must always be set in the segment + * descriptor cache, although it can be cleared in the + * descriptor, the cached bit always remains at 1. Since + * Intel has a check on this, set it here to support + * cross-vendor migration. + */ + if (!var->unusable) + var->type |= 0x1; + break; + } var->unusable = !var->present; } @@ -905,9 +958,37 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, } -static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - return -EOPNOTSUPP; + int old_debug = vcpu->guest_debug; + struct vcpu_svm *svm = to_svm(vcpu); + + vcpu->guest_debug = dbg->control; + + svm->vmcb->control.intercept_exceptions &= + ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + svm->vmcb->control.intercept_exceptions |= + 1 << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + svm->vmcb->control.intercept_exceptions |= + 1 << BP_VECTOR; + } else + vcpu->guest_debug = 0; + + 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; } static int svm_get_irq(struct kvm_vcpu *vcpu) @@ -949,7 +1030,29 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data) static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr) { - unsigned long val = to_svm(vcpu)->db_regs[dr]; + struct vcpu_svm *svm = to_svm(vcpu); + unsigned long val; + + switch (dr) { + case 0 ... 3: + val = vcpu->arch.db[dr]; + break; + case 6: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + val = vcpu->arch.dr6; + else + val = svm->vmcb->save.dr6; + break; + case 7: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) + val = vcpu->arch.dr7; + else + val = svm->vmcb->save.dr7; + break; + default: + val = 0; + } + KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); return val; } @@ -959,33 +1062,40 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value, { struct vcpu_svm *svm = to_svm(vcpu); - *exception = 0; + KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)value, handler); - if (svm->vmcb->save.dr7 & DR7_GD_MASK) { - svm->vmcb->save.dr7 &= ~DR7_GD_MASK; - svm->vmcb->save.dr6 |= DR6_BD_MASK; - *exception = DB_VECTOR; - return; - } + *exception = 0; switch (dr) { case 0 ... 3: - svm->db_regs[dr] = value; + vcpu->arch.db[dr] = value; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = value; return; case 4 ... 5: - if (vcpu->arch.cr4 & X86_CR4_DE) { + if (vcpu->arch.cr4 & X86_CR4_DE) *exception = UD_VECTOR; + return; + case 6: + if (value & 0xffffffff00000000ULL) { + *exception = GP_VECTOR; return; } - case 7: { - if (value & ~((1ULL << 32) - 1)) { + vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1; + return; + case 7: + if (value & 0xffffffff00000000ULL) { *exception = GP_VECTOR; return; } - svm->vmcb->save.dr7 = value; + vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + svm->vmcb->save.dr7 = vcpu->arch.dr7; + vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK); + } return; - } default: + /* FIXME: Possible case? */ printk(KERN_DEBUG "%s: unexpected dr %u\n", __func__, dr); *exception = UD_VECTOR; @@ -1031,6 +1141,27 @@ 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) +{ + if (!(svm->vcpu.guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + kvm_queue_exception(&svm->vcpu, DB_VECTOR); + return 1; + } + 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 = DB_VECTOR; + return 0; +} + +static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_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) { int er; @@ -1080,7 +1211,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */ - int size, down, in, string, rep; + int size, in, string; unsigned port; ++svm->vcpu.stat.io_exits; @@ -1099,8 +1230,6 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) in = (io_info & SVM_IOIO_TYPE_MASK) != 0; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; - rep = (io_info & SVM_IOIO_REP_MASK) != 0; - down = (svm->vmcb->save.rflags & X86_EFLAGS_DF) != 0; skip_emulated_instruction(&svm->vcpu); return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port); @@ -1139,6 +1268,567 @@ static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) return 1; } +static int nested_svm_check_permissions(struct vcpu_svm *svm) +{ + if (!(svm->vcpu.arch.shadow_efer & EFER_SVME) + || !is_paging(&svm->vcpu)) { + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; + } + + if (svm->vmcb->save.cpl) { + kvm_inject_gp(&svm->vcpu, 0); + return 1; + } + + return 0; +} + +static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, + bool has_error_code, u32 error_code) +{ + if (is_nested(svm)) { + svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = error_code; + svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2; + if (nested_svm_exit_handled(svm, false)) { + nsvm_printk("VMexit -> EXCP 0x%x\n", nr); + + nested_svm_vmexit(svm); + return 1; + } + } + + return 0; +} + +static inline int nested_svm_intr(struct vcpu_svm *svm) +{ + if (is_nested(svm)) { + if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) + return 0; + + if (!(svm->vcpu.arch.hflags & HF_HIF_MASK)) + return 0; + + svm->vmcb->control.exit_code = SVM_EXIT_INTR; + + if (nested_svm_exit_handled(svm, false)) { + nsvm_printk("VMexit -> INTR\n"); + nested_svm_vmexit(svm); + return 1; + } + } + + return 0; +} + +static struct page *nested_svm_get_page(struct vcpu_svm *svm, u64 gpa) +{ + 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)) { + printk(KERN_INFO "%s: could not find page at 0x%llx\n", + __func__, gpa); + kvm_release_page_clean(page); + kvm_inject_gp(&svm->vcpu, 0); + return NULL; + } + return page; +} + +static int nested_svm_do(struct vcpu_svm *svm, + u64 arg1_gpa, u64 arg2_gpa, void *opaque, + int (*handler)(struct vcpu_svm *svm, + void *arg1, + void *arg2, + void *opaque)) +{ + struct page *arg1_page; + struct page *arg2_page = NULL; + void *arg1; + void *arg2 = NULL; + int retval; + + arg1_page = nested_svm_get_page(svm, arg1_gpa); + if(arg1_page == NULL) + return 1; + + if (arg2_gpa) { + arg2_page = nested_svm_get_page(svm, arg2_gpa); + if(arg2_page == NULL) { + kvm_release_page_clean(arg1_page); + return 1; + } + } + + arg1 = kmap_atomic(arg1_page, KM_USER0); + if (arg2_gpa) + arg2 = kmap_atomic(arg2_page, KM_USER1); + + retval = handler(svm, arg1, arg2, opaque); + + kunmap_atomic(arg1, KM_USER0); + if (arg2_gpa) + kunmap_atomic(arg2, KM_USER1); + + kvm_release_page_dirty(arg1_page); + if (arg2_gpa) + kvm_release_page_dirty(arg2_page); + + return retval; +} + +static int nested_svm_exit_handled_real(struct vcpu_svm *svm, + void *arg1, + void *arg2, + void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + bool kvm_overrides = *(bool *)opaque; + u32 exit_code = svm->vmcb->control.exit_code; + + if (kvm_overrides) { + switch (exit_code) { + case SVM_EXIT_INTR: + case SVM_EXIT_NMI: + return 0; + /* For now we are always handling NPFs when using them */ + case SVM_EXIT_NPF: + if (npt_enabled) + return 0; + break; + /* When we're shadowing, trap PFs */ + case SVM_EXIT_EXCP_BASE + PF_VECTOR: + if (!npt_enabled) + return 0; + break; + default: + break; + } + } + + switch (exit_code) { + case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { + u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); + if (nested_vmcb->control.intercept_cr_read & cr_bits) + return 1; + break; + } + case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: { + u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0); + if (nested_vmcb->control.intercept_cr_write & cr_bits) + return 1; + break; + } + case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: { + u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0); + if (nested_vmcb->control.intercept_dr_read & dr_bits) + return 1; + break; + } + case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: { + u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0); + if (nested_vmcb->control.intercept_dr_write & dr_bits) + return 1; + break; + } + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: { + u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); + if (nested_vmcb->control.intercept_exceptions & excp_bits) + return 1; + break; + } + default: { + u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR); + nsvm_printk("exit code: 0x%x\n", exit_code); + if (nested_vmcb->control.intercept & exit_bits) + return 1; + } + } + + return 0; +} + +static int nested_svm_exit_handled_msr(struct vcpu_svm *svm, + void *arg1, void *arg2, + void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + u8 *msrpm = (u8 *)arg2; + u32 t0, t1; + u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX]; + u32 param = svm->vmcb->control.exit_info_1 & 1; + + if (!(nested_vmcb->control.intercept & (1ULL << INTERCEPT_MSR_PROT))) + return 0; + + switch(msr) { + case 0 ... 0x1fff: + t0 = (msr * 2) % 8; + t1 = msr / 8; + break; + case 0xc0000000 ... 0xc0001fff: + t0 = (8192 + msr - 0xc0000000) * 2; + t1 = (t0 / 8); + t0 %= 8; + break; + case 0xc0010000 ... 0xc0011fff: + t0 = (16384 + msr - 0xc0010000) * 2; + t1 = (t0 / 8); + t0 %= 8; + break; + default: + return 1; + break; + } + if (msrpm[t1] & ((1 << param) << t0)) + return 1; + + return 0; +} + +static int nested_svm_exit_handled(struct vcpu_svm *svm, bool kvm_override) +{ + bool k = kvm_override; + + switch (svm->vmcb->control.exit_code) { + case SVM_EXIT_MSR: + return nested_svm_do(svm, svm->nested_vmcb, + svm->nested_vmcb_msrpm, NULL, + nested_svm_exit_handled_msr); + default: break; + } + + return nested_svm_do(svm, svm->nested_vmcb, 0, &k, + nested_svm_exit_handled_real); +} + +static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + struct vmcb *hsave = svm->hsave; + u64 nested_save[] = { nested_vmcb->save.cr0, + nested_vmcb->save.cr3, + nested_vmcb->save.cr4, + nested_vmcb->save.efer, + nested_vmcb->control.intercept_cr_read, + nested_vmcb->control.intercept_cr_write, + nested_vmcb->control.intercept_dr_read, + nested_vmcb->control.intercept_dr_write, + nested_vmcb->control.intercept_exceptions, + nested_vmcb->control.intercept, + nested_vmcb->control.msrpm_base_pa, + nested_vmcb->control.iopm_base_pa, + nested_vmcb->control.tsc_offset }; + + /* Give the current vmcb to the guest */ + memcpy(nested_vmcb, svm->vmcb, sizeof(struct vmcb)); + nested_vmcb->save.cr0 = nested_save[0]; + if (!npt_enabled) + nested_vmcb->save.cr3 = nested_save[1]; + nested_vmcb->save.cr4 = nested_save[2]; + nested_vmcb->save.efer = nested_save[3]; + nested_vmcb->control.intercept_cr_read = nested_save[4]; + nested_vmcb->control.intercept_cr_write = nested_save[5]; + nested_vmcb->control.intercept_dr_read = nested_save[6]; + nested_vmcb->control.intercept_dr_write = nested_save[7]; + nested_vmcb->control.intercept_exceptions = nested_save[8]; + nested_vmcb->control.intercept = nested_save[9]; + nested_vmcb->control.msrpm_base_pa = nested_save[10]; + nested_vmcb->control.iopm_base_pa = nested_save[11]; + nested_vmcb->control.tsc_offset = nested_save[12]; + + /* We always set V_INTR_MASKING and remember the old value in hflags */ + if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) + nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK; + + if ((nested_vmcb->control.int_ctl & V_IRQ_MASK) && + (nested_vmcb->control.int_vector)) { + nsvm_printk("WARNING: IRQ 0x%x still enabled on #VMEXIT\n", + nested_vmcb->control.int_vector); + } + + /* Restore the original control entries */ + svm->vmcb->control = hsave->control; + + /* Kill any pending exceptions */ + if (svm->vcpu.arch.exception.pending == true) + nsvm_printk("WARNING: Pending Exception\n"); + svm->vcpu.arch.exception.pending = false; + + /* Restore selected save entries */ + svm->vmcb->save.es = hsave->save.es; + svm->vmcb->save.cs = hsave->save.cs; + svm->vmcb->save.ss = hsave->save.ss; + svm->vmcb->save.ds = hsave->save.ds; + svm->vmcb->save.gdtr = hsave->save.gdtr; + svm->vmcb->save.idtr = hsave->save.idtr; + svm->vmcb->save.rflags = hsave->save.rflags; + svm_set_efer(&svm->vcpu, hsave->save.efer); + svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); + svm_set_cr4(&svm->vcpu, hsave->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = hsave->save.cr3; + svm->vcpu.arch.cr3 = hsave->save.cr3; + } else { + kvm_set_cr3(&svm->vcpu, hsave->save.cr3); + } + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, hsave->save.rax); + kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, hsave->save.rsp); + kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, hsave->save.rip); + svm->vmcb->save.dr7 = 0; + svm->vmcb->save.cpl = 0; + svm->vmcb->control.exit_int_info = 0; + + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + /* Exit nested SVM mode */ + svm->nested_vmcb = 0; + + return 0; +} + +static int nested_svm_vmexit(struct vcpu_svm *svm) +{ + nsvm_printk("VMexit\n"); + if (nested_svm_do(svm, svm->nested_vmcb, 0, + NULL, nested_svm_vmexit_real)) + return 1; + + kvm_mmu_reset_context(&svm->vcpu); + kvm_mmu_load(&svm->vcpu); + + return 0; +} + +static int nested_svm_vmrun_msrpm(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + int i; + u32 *nested_msrpm = (u32*)arg1; + for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++) + svm->nested_msrpm[i] = svm->msrpm[i] | nested_msrpm[i]; + svm->vmcb->control.msrpm_base_pa = __pa(svm->nested_msrpm); + + return 0; +} + +static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1, + void *arg2, void *opaque) +{ + struct vmcb *nested_vmcb = (struct vmcb *)arg1; + struct vmcb *hsave = svm->hsave; + + /* nested_vmcb is our indicator if nested SVM is activated */ + svm->nested_vmcb = svm->vmcb->save.rax; + + /* Clear internal status */ + svm->vcpu.arch.exception.pending = false; + + /* Save the old vmcb, so we don't need to pick what we save, but + can restore everything when a VMEXIT occurs */ + memcpy(hsave, svm->vmcb, sizeof(struct vmcb)); + /* We need to remember the original CR3 in the SPT case */ + if (!npt_enabled) + hsave->save.cr3 = svm->vcpu.arch.cr3; + hsave->save.cr4 = svm->vcpu.arch.cr4; + hsave->save.rip = svm->next_rip; + + if (svm->vmcb->save.rflags & X86_EFLAGS_IF) + svm->vcpu.arch.hflags |= HF_HIF_MASK; + else + svm->vcpu.arch.hflags &= ~HF_HIF_MASK; + + /* Load the nested guest state */ + svm->vmcb->save.es = nested_vmcb->save.es; + svm->vmcb->save.cs = nested_vmcb->save.cs; + svm->vmcb->save.ss = nested_vmcb->save.ss; + svm->vmcb->save.ds = nested_vmcb->save.ds; + svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; + svm->vmcb->save.idtr = nested_vmcb->save.idtr; + svm->vmcb->save.rflags = nested_vmcb->save.rflags; + svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); + svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); + svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); + if (npt_enabled) { + svm->vmcb->save.cr3 = nested_vmcb->save.cr3; + svm->vcpu.arch.cr3 = nested_vmcb->save.cr3; + } else { + kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3); + kvm_mmu_reset_context(&svm->vcpu); + } + svm->vmcb->save.cr2 = nested_vmcb->save.cr2; + kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax); + kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp); + kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip); + /* In case we don't even reach vcpu_run, the fields are not updated */ + svm->vmcb->save.rax = nested_vmcb->save.rax; + svm->vmcb->save.rsp = nested_vmcb->save.rsp; + svm->vmcb->save.rip = nested_vmcb->save.rip; + svm->vmcb->save.dr7 = nested_vmcb->save.dr7; + svm->vmcb->save.dr6 = nested_vmcb->save.dr6; + svm->vmcb->save.cpl = nested_vmcb->save.cpl; + + /* We don't want a nested guest to be more powerful than the guest, + so all intercepts are ORed */ + svm->vmcb->control.intercept_cr_read |= + nested_vmcb->control.intercept_cr_read; + svm->vmcb->control.intercept_cr_write |= + nested_vmcb->control.intercept_cr_write; + svm->vmcb->control.intercept_dr_read |= + nested_vmcb->control.intercept_dr_read; + svm->vmcb->control.intercept_dr_write |= + nested_vmcb->control.intercept_dr_write; + svm->vmcb->control.intercept_exceptions |= + nested_vmcb->control.intercept_exceptions; + + svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + + svm->nested_vmcb_msrpm = nested_vmcb->control.msrpm_base_pa; + + 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; + + svm->vcpu.arch.hflags |= HF_GIF_MASK; + + return 0; +} + +static int nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb) +{ + to_vmcb->save.fs = from_vmcb->save.fs; + to_vmcb->save.gs = from_vmcb->save.gs; + to_vmcb->save.tr = from_vmcb->save.tr; + to_vmcb->save.ldtr = from_vmcb->save.ldtr; + to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base; + to_vmcb->save.star = from_vmcb->save.star; + to_vmcb->save.lstar = from_vmcb->save.lstar; + to_vmcb->save.cstar = from_vmcb->save.cstar; + to_vmcb->save.sfmask = from_vmcb->save.sfmask; + to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs; + to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp; + to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip; + + return 1; +} + +static int nested_svm_vmload(struct vcpu_svm *svm, void *nested_vmcb, + void *arg2, void *opaque) +{ + return nested_svm_vmloadsave((struct vmcb *)nested_vmcb, svm->vmcb); +} + +static int nested_svm_vmsave(struct vcpu_svm *svm, void *nested_vmcb, + void *arg2, void *opaque) +{ + return nested_svm_vmloadsave(svm->vmcb, (struct vmcb *)nested_vmcb); +} + +static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmload); + + return 1; +} + +static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + nested_svm_do(svm, svm->vmcb->save.rax, 0, NULL, nested_svm_vmsave); + + return 1; +} + +static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + nsvm_printk("VMrun\n"); + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + if (nested_svm_do(svm, svm->vmcb->save.rax, 0, + NULL, nested_svm_vmrun)) + return 1; + + if (nested_svm_do(svm, svm->nested_vmcb_msrpm, 0, + NULL, nested_svm_vmrun_msrpm)) + return 1; + + return 1; +} + +static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + svm->vcpu.arch.hflags |= HF_GIF_MASK; + + return 1; +} + +static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) +{ + if (nested_svm_check_permissions(svm)) + return 1; + + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + + svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + + /* After a CLGI no interrupts should come */ + svm_clear_vintr(svm); + svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + + return 1; +} + static int invalid_op_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run) { @@ -1250,6 +1940,15 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) case MSR_IA32_LASTINTTOIP: *data = svm->vmcb->save.last_excp_to; break; + case MSR_VM_HSAVE_PA: + *data = svm->hsave_msr; + break; + case MSR_VM_CR: + *data = 0; + break; + case MSR_IA32_UCODE_REV: + *data = 0x01000065; + break; default: return kvm_get_msr_common(vcpu, ecx, data); } @@ -1344,6 +2043,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", ecx, data); break; + case MSR_VM_HSAVE_PA: + svm->hsave_msr = data; + break; default: return kvm_set_msr_common(vcpu, ecx, data); } @@ -1380,7 +2082,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm, { KVMTRACE_0D(PEND_INTR, &svm->vcpu, handler); - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); + svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; /* * If the user space waits to inject interrupts, exit as soon as @@ -1417,6 +2119,8 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_WRITE_DR3] = emulate_on_interception, [SVM_EXIT_WRITE_DR5] = emulate_on_interception, [SVM_EXIT_WRITE_DR7] = emulate_on_interception, + [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, + [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception, [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception, @@ -1436,12 +2140,12 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm, [SVM_EXIT_MSR] = msr_interception, [SVM_EXIT_TASK_SWITCH] = task_switch_interception, [SVM_EXIT_SHUTDOWN] = shutdown_interception, - [SVM_EXIT_VMRUN] = invalid_op_interception, + [SVM_EXIT_VMRUN] = vmrun_interception, [SVM_EXIT_VMMCALL] = vmmcall_interception, - [SVM_EXIT_VMLOAD] = invalid_op_interception, - [SVM_EXIT_VMSAVE] = invalid_op_interception, - [SVM_EXIT_STGI] = invalid_op_interception, - [SVM_EXIT_CLGI] = invalid_op_interception, + [SVM_EXIT_VMLOAD] = vmload_interception, + [SVM_EXIT_VMSAVE] = vmsave_interception, + [SVM_EXIT_STGI] = stgi_interception, + [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = invalid_op_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, [SVM_EXIT_MONITOR] = invalid_op_interception, @@ -1457,6 +2161,17 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) KVMTRACE_3D(VMEXIT, vcpu, exit_code, (u32)svm->vmcb->save.rip, (u32)((u64)svm->vmcb->save.rip >> 32), entryexit); + if (is_nested(svm)) { + 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); + if (nested_svm_exit_handled(svm, true)) { + nested_svm_vmexit(svm); + nsvm_printk("-> #VMEXIT\n"); + return 1; + } + } + if (npt_enabled) { int mmu_reload = 0; if ((vcpu->arch.cr0 ^ svm->vmcb->save.cr0) & X86_CR0_PG) { @@ -1544,6 +2259,8 @@ static void svm_set_irq(struct kvm_vcpu *vcpu, int irq) { struct vcpu_svm *svm = to_svm(vcpu); + nested_svm_intr(svm); + svm_inject_irq(svm, irq); } @@ -1589,11 +2306,17 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu) if (!kvm_cpu_has_interrupt(vcpu)) goto out; + if (nested_svm_intr(svm)) + goto out; + + if (!(svm->vcpu.arch.hflags & HF_GIF_MASK)) + goto out; + if (!(vmcb->save.rflags & X86_EFLAGS_IF) || (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || (vmcb->control.event_inj & SVM_EVTINJ_VALID)) { /* unable to deliver irq, set pending irq */ - vmcb->control.intercept |= (1ULL << INTERCEPT_VINTR); + svm_set_vintr(svm); svm_inject_irq(svm, 0x0); goto out; } @@ -1615,7 +2338,8 @@ static void kvm_reput_irq(struct vcpu_svm *svm) } svm->vcpu.arch.interrupt_window_open = - !(control->int_state & SVM_INTERRUPT_SHADOW_MASK); + !(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && + (svm->vcpu.arch.hflags & HF_GIF_MASK); } static void svm_do_inject_vector(struct vcpu_svm *svm) @@ -1637,9 +2361,13 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, struct vcpu_svm *svm = to_svm(vcpu); struct vmcb_control_area *control = &svm->vmcb->control; + if (nested_svm_intr(svm)) + return; + svm->vcpu.arch.interrupt_window_open = (!(control->int_state & SVM_INTERRUPT_SHADOW_MASK) && - (svm->vmcb->save.rflags & X86_EFLAGS_IF)); + (svm->vmcb->save.rflags & X86_EFLAGS_IF) && + (svm->vcpu.arch.hflags & HF_GIF_MASK)); if (svm->vcpu.arch.interrupt_window_open && svm->vcpu.arch.irq_summary) /* @@ -1652,9 +2380,9 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, */ if (!svm->vcpu.arch.interrupt_window_open && (svm->vcpu.arch.irq_summary || kvm_run->request_interrupt_window)) - control->intercept |= 1ULL << INTERCEPT_VINTR; - else - control->intercept &= ~(1ULL << INTERCEPT_VINTR); + svm_set_vintr(svm); + else + svm_clear_vintr(svm); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -1662,22 +2390,6 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void save_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %%dr0, %0" : "=r"(db_regs[0])); - asm volatile ("mov %%dr1, %0" : "=r"(db_regs[1])); - asm volatile ("mov %%dr2, %0" : "=r"(db_regs[2])); - asm volatile ("mov %%dr3, %0" : "=r"(db_regs[3])); -} - -static void load_db_regs(unsigned long *db_regs) -{ - asm volatile ("mov %0, %%dr0" : : "r"(db_regs[0])); - asm volatile ("mov %0, %%dr1" : : "r"(db_regs[1])); - asm volatile ("mov %0, %%dr2" : : "r"(db_regs[2])); - asm volatile ("mov %0, %%dr3" : : "r"(db_regs[3])); -} - static void svm_flush_tlb(struct kvm_vcpu *vcpu) { force_new_asid(vcpu); @@ -1736,19 +2448,12 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) gs_selector = kvm_read_gs(); ldt_selector = kvm_read_ldt(); svm->host_cr2 = kvm_read_cr2(); - svm->host_dr6 = read_dr6(); - svm->host_dr7 = read_dr7(); - svm->vmcb->save.cr2 = vcpu->arch.cr2; + if (!is_nested(svm)) + svm->vmcb->save.cr2 = vcpu->arch.cr2; /* required for live migration with NPT */ if (npt_enabled) svm->vmcb->save.cr3 = vcpu->arch.cr3; - if (svm->vmcb->save.dr7 & 0xff) { - write_dr7(0); - save_db_regs(svm->host_db_regs); - load_db_regs(svm->db_regs); - } - clgi(); local_irq_enable(); @@ -1824,16 +2529,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) #endif ); - if ((svm->vmcb->save.dr7 & 0xff)) - load_db_regs(svm->host_db_regs); - vcpu->arch.cr2 = svm->vmcb->save.cr2; vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - write_dr6(svm->host_dr6); - write_dr7(svm->host_dr7); kvm_write_cr2(svm->host_cr2); kvm_load_fs(fs_selector); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 7611af5..bb48133 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -91,6 +91,7 @@ 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; @@ -189,21 +190,21 @@ static inline int is_page_fault(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_no_device(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_invalid_opcode(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | INTR_INFO_VALID_MASK)) == - (INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); + (INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK); } static inline int is_external_interrupt(u32 intr_info) @@ -480,8 +481,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) eb = (1u << PF_VECTOR) | (1u << UD_VECTOR); if (!vcpu->fpu_active) eb |= 1u << NM_VECTOR; - if (vcpu->guest_debug.enabled) - eb |= 1u << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + eb |= 1u << DB_VECTOR; + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + eb |= 1u << BP_VECTOR; + } if (vcpu->arch.rmode.active) eb = ~0; if (vm_need_ept()) @@ -747,29 +753,33 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error_code, u32 error_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u32 intr_info = nr | INTR_INFO_VALID_MASK; - if (has_error_code) + if (has_error_code) { vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + intr_info |= INTR_INFO_DELIVER_CODE_MASK; + } if (vcpu->arch.rmode.active) { vmx->rmode.irq.pending = true; vmx->rmode.irq.vector = nr; vmx->rmode.irq.rip = kvm_rip_read(vcpu); - if (nr == BP_VECTOR) + if (nr == BP_VECTOR || nr == OF_VECTOR) vmx->rmode.irq.rip++; - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - nr | INTR_TYPE_SOFT_INTR - | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) - | INTR_INFO_VALID_MASK); + intr_info |= INTR_TYPE_SOFT_INTR; + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1); return; } - vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, - nr | INTR_TYPE_EXCEPTION - | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0) - | INTR_INFO_VALID_MASK); + if (nr == BP_VECTOR || nr == OF_VECTOR) { + vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1); + intr_info |= INTR_TYPE_SOFT_EXCEPTION; + } else + intr_info |= INTR_TYPE_HARD_EXCEPTION; + + vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info); } static bool vmx_exception_injected(struct kvm_vcpu *vcpu) @@ -856,11 +866,8 @@ static u64 guest_read_tsc(void) * writes 'guest_tsc' into guest's timestamp counter "register" * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc */ -static void guest_write_tsc(u64 guest_tsc) +static void guest_write_tsc(u64 guest_tsc, u64 host_tsc) { - u64 host_tsc; - - rdtscll(host_tsc); vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc); } @@ -925,14 +932,15 @@ 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; + u64 host_tsc; int ret = 0; switch (msr_index) { -#ifdef CONFIG_X86_64 case MSR_EFER: vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); break; +#ifdef CONFIG_X86_64 case MSR_FS_BASE: vmcs_writel(GUEST_FS_BASE, data); break; @@ -950,7 +958,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_TIME_STAMP_COUNTER: - guest_write_tsc(data); + rdtscll(host_tsc); + guest_write_tsc(data, host_tsc); break; case MSR_P6_PERFCTR0: case MSR_P6_PERFCTR1: @@ -999,40 +1008,28 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg) +static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { - unsigned long dr7 = 0x400; - int old_singlestep; - - old_singlestep = vcpu->guest_debug.singlestep; - - vcpu->guest_debug.enabled = dbg->enabled; - if (vcpu->guest_debug.enabled) { - int i; + int old_debug = vcpu->guest_debug; + unsigned long flags; - dr7 |= 0x200; /* exact */ - for (i = 0; i < 4; ++i) { - if (!dbg->breakpoints[i].enabled) - continue; - vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address; - dr7 |= 2 << (i*2); /* global enable */ - dr7 |= 0 << (i*4+16); /* execution breakpoint */ - } + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; - vcpu->guest_debug.singlestep = dbg->singlestep; - } else - vcpu->guest_debug.singlestep = 0; - - if (old_singlestep && !vcpu->guest_debug.singlestep) { - unsigned long flags; + 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); + 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); - } + vmcs_writel(GUEST_RFLAGS, flags); update_exception_bitmap(vcpu); - vmcs_writel(GUEST_DR7, dr7); return 0; } @@ -1433,6 +1430,29 @@ continue_rmode: init_rmode(vcpu->kvm); } +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); + + vcpu->arch.shadow_efer = efer; + if (!msr) + return; + if (efer & EFER_LMA) { + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) | + VM_ENTRY_IA32E_MODE); + msr->data = efer; + } else { + vmcs_write32(VM_ENTRY_CONTROLS, + vmcs_read32(VM_ENTRY_CONTROLS) & + ~VM_ENTRY_IA32E_MODE); + + msr->data = efer & ~EFER_LME; + } + setup_msrs(vmx); +} + #ifdef CONFIG_X86_64 static void enter_lmode(struct kvm_vcpu *vcpu) @@ -1447,13 +1467,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu) (guest_tr_ar & ~AR_TYPE_MASK) | AR_TYPE_BUSY_64_TSS); } - vcpu->arch.shadow_efer |= EFER_LMA; - - find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME; - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) - | VM_ENTRY_IA32E_MODE); + vmx_set_efer(vcpu, vcpu->arch.shadow_efer); } static void exit_lmode(struct kvm_vcpu *vcpu) @@ -1612,30 +1627,6 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) vmcs_writel(GUEST_CR4, hw_cr4); } -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); - - vcpu->arch.shadow_efer = efer; - if (!msr) - return; - if (efer & EFER_LMA) { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) | - VM_ENTRY_IA32E_MODE); - msr->data = efer; - - } else { - vmcs_write32(VM_ENTRY_CONTROLS, - vmcs_read32(VM_ENTRY_CONTROLS) & - ~VM_ENTRY_IA32E_MODE); - - msr->data = efer & ~EFER_LME; - } - setup_msrs(vmx); -} - static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg) { struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; @@ -1653,7 +1644,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, var->limit = vmcs_read32(sf->limit); var->selector = vmcs_read16(sf->selector); ar = vmcs_read32(sf->ar_bytes); - if (ar & AR_UNUSABLE_MASK) + if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state) ar = 0; var->type = ar & 15; var->s = (ar >> 4) & 1; @@ -1788,14 +1779,16 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &cs, VCPU_SREG_CS); cs_rpl = cs.selector & SELECTOR_RPL_MASK; + if (cs.unusable) + return false; if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK)) return false; if (!cs.s) return false; - if (!(~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK))) { + if (cs.type & AR_TYPE_WRITEABLE_MASK) { if (cs.dpl > cs_rpl) return false; - } else if (cs.type & AR_TYPE_CODE_MASK) { + } else { if (cs.dpl != cs_rpl) return false; } @@ -1814,7 +1807,9 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &ss, VCPU_SREG_SS); ss_rpl = ss.selector & SELECTOR_RPL_MASK; - if ((ss.type != 3) || (ss.type != 7)) + if (ss.unusable) + return true; + if (ss.type != 3 && ss.type != 7) return false; if (!ss.s) return false; @@ -1834,6 +1829,8 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg) vmx_get_segment(vcpu, &var, seg); rpl = var.selector & SELECTOR_RPL_MASK; + if (var.unusable) + return true; if (!var.s) return false; if (!var.present) @@ -1855,9 +1852,11 @@ static bool tr_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &tr, VCPU_SREG_TR); + if (tr.unusable) + return false; if (tr.selector & SELECTOR_TI_MASK) /* TI = 1 */ return false; - if ((tr.type != 3) || (tr.type != 11)) /* TODO: Check if guest is in IA32e mode */ + if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */ return false; if (!tr.present) return false; @@ -1871,6 +1870,8 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu) vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR); + if (ldtr.unusable) + return true; if (ldtr.selector & SELECTOR_TI_MASK) /* TI = 1 */ return false; if (ldtr.type != 2) @@ -2112,7 +2113,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) { u32 host_sysenter_cs, msr_low, msr_high; u32 junk; - u64 host_pat; + u64 host_pat, tsc_this, tsc_base; unsigned long a; struct descriptor_table dt; int i; @@ -2240,6 +2241,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL); vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK); + tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc; + rdtscll(tsc_this); + if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc) + tsc_base = tsc_this; + + guest_write_tsc(0, tsc_base); return 0; } @@ -2319,7 +2326,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) kvm_rip_write(vcpu, 0); kvm_register_write(vcpu, VCPU_REGS_RSP, 0); - /* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */ vmcs_writel(GUEST_DR7, 0x400); vmcs_writel(GUEST_GDTR_BASE, 0); @@ -2332,8 +2338,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); - guest_write_tsc(0); - /* Special registers */ vmcs_write64(GUEST_IA32_DEBUGCTL, 0); @@ -2486,6 +2490,11 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu, { vmx_update_window_states(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_STI | + GUEST_INTR_STATE_MOV_SS); + if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) { if (vcpu->arch.interrupt.pending) { enable_nmi_window(vcpu); @@ -2536,24 +2545,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr) return 0; } -static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu) -{ - struct kvm_guest_debug *dbg = &vcpu->guest_debug; - - set_debugreg(dbg->bp[0], 0); - set_debugreg(dbg->bp[1], 1); - set_debugreg(dbg->bp[2], 2); - set_debugreg(dbg->bp[3], 3); - - if (dbg->singlestep) { - unsigned long flags; - - flags = vmcs_readl(GUEST_RFLAGS); - flags |= X86_EFLAGS_TF | X86_EFLAGS_RF; - vmcs_writel(GUEST_RFLAGS, flags); - } -} - static int handle_rmode_exception(struct kvm_vcpu *vcpu, int vec, u32 err_code) { @@ -2570,9 +2561,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * the required debugging infrastructure rework. */ switch (vec) { - case DE_VECTOR: case DB_VECTOR: + if (vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return 0; + kvm_queue_exception(vcpu, vec); + return 1; case BP_VECTOR: + if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) + return 0; + /* fall through */ + case DE_VECTOR: case OF_VECTOR: case BR_VECTOR: case UD_VECTOR: @@ -2589,8 +2588,8 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); - u32 intr_info, error_code; - unsigned long cr2, rip; + u32 intr_info, ex_no, error_code; + unsigned long cr2, rip, dr6; u32 vect_info; enum emulation_result er; @@ -2649,14 +2648,30 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) return 1; } - if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) == - (INTR_TYPE_EXCEPTION | 1)) { + ex_no = intr_info & INTR_INFO_VECTOR_MASK; + switch (ex_no) { + case DB_VECTOR: + dr6 = vmcs_readl(EXIT_QUALIFICATION); + if (!(vcpu->guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { + vcpu->arch.dr6 = dr6 | DR6_FIXED_1; + kvm_queue_exception(vcpu, DB_VECTOR); + return 1; + } + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); + /* fall through */ + case BP_VECTOR: kvm_run->exit_reason = KVM_EXIT_DEBUG; - return 0; + kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip; + kvm_run->debug.arch.exception = ex_no; + break; + default: + kvm_run->exit_reason = KVM_EXIT_EXCEPTION; + kvm_run->ex.exception = ex_no; + kvm_run->ex.error_code = error_code; + break; } - kvm_run->exit_reason = KVM_EXIT_EXCEPTION; - kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK; - kvm_run->ex.error_code = error_code; return 0; } @@ -2677,7 +2692,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { unsigned long exit_qualification; - int size, down, in, string, rep; + int size, in, string; unsigned port; ++vcpu->stat.io_exits; @@ -2693,8 +2708,6 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) size = (exit_qualification & 7) + 1; in = (exit_qualification & 8) != 0; - down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0; - rep = (exit_qualification & 32) != 0; port = exit_qualification >> 16; skip_emulated_instruction(vcpu); @@ -2795,21 +2808,44 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) unsigned long val; int dr, reg; - /* - * FIXME: this code assumes the host is debugging the guest. - * need to deal with guest debugging itself too. - */ + dr = vmcs_readl(GUEST_DR7); + if (dr & DR7_GD) { + /* + * As the vm-exit takes precedence over the debug trap, we + * need to emulate the latter, either for the host or the + * 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 = + vmcs_readl(GUEST_CS_BASE) + + vmcs_readl(GUEST_RIP); + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + return 0; + } else { + vcpu->arch.dr7 &= ~DR7_GD; + vcpu->arch.dr6 |= DR6_BD; + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); + kvm_queue_exception(vcpu, DB_VECTOR); + return 1; + } + } + exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - dr = exit_qualification & 7; - reg = (exit_qualification >> 8) & 15; - if (exit_qualification & 16) { - /* mov from dr */ + dr = exit_qualification & DEBUG_REG_ACCESS_NUM; + reg = DEBUG_REG_ACCESS_REG(exit_qualification); + if (exit_qualification & TYPE_MOV_FROM_DR) { switch (dr) { + case 0 ... 3: + val = vcpu->arch.db[dr]; + break; case 6: - val = 0xffff0ff0; + val = vcpu->arch.dr6; break; case 7: - val = 0x400; + val = vcpu->arch.dr7; break; default: val = 0; @@ -2817,7 +2853,38 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_register_write(vcpu, reg, val); KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler); } else { - /* mov to dr */ + val = vcpu->arch.regs[reg]; + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4 ... 5: + if (vcpu->arch.cr4 & X86_CR4_DE) + kvm_queue_exception(vcpu, UD_VECTOR); + break; + case 6: + if (val & 0xffffffff00000000ULL) { + kvm_queue_exception(vcpu, GP_VECTOR); + break; + } + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + break; + case 7: + if (val & 0xffffffff00000000ULL) { + kvm_queue_exception(vcpu, GP_VECTOR); + break; + } + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + vmcs_writel(GUEST_DR7, vcpu->arch.dr7); + vcpu->arch.switch_db_regs = + (val & DR7_BP_EN_MASK); + } + break; + } + KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler); } skip_emulated_instruction(vcpu); return 1; @@ -2968,17 +3035,25 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } tss_selector = exit_qualification; - return kvm_task_switch(vcpu, tss_selector, reason); + if (!kvm_task_switch(vcpu, tss_selector, reason)) + return 0; + + /* clear all local breakpoint enable flags */ + vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); + + /* + * TODO: What about debug traps on tss switch? + * Are we supposed to inject them and update dr6? + */ + + return 1; } static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { u64 exit_qualification; - enum emulation_result er; gpa_t gpa; - unsigned long hva; int gla_validity; - int r; exit_qualification = vmcs_read64(EXIT_QUALIFICATION); @@ -3001,32 +3076,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); - hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT); - if (!kvm_is_error_hva(hva)) { - r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); - if (r < 0) { - printk(KERN_ERR "EPT: Not enough memory!\n"); - return -ENOMEM; - } - return 1; - } else { - /* must be MMIO */ - er = emulate_instruction(vcpu, kvm_run, 0, 0, 0); - - if (er == EMULATE_FAIL) { - printk(KERN_ERR - "EPT: Fail to handle EPT violation vmexit!er is %d\n", - er); - printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n", - (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS), - (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS)); - printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n", - (long unsigned int)exit_qualification); - return -ENOTSUPP; - } else if (er == EMULATE_DO_MMIO) - return 0; - } - return 1; + return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0); } static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) @@ -3046,7 +3096,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { struct vcpu_vmx *vmx = to_vmx(vcpu); - int err; + enum emulation_result err = EMULATE_DONE; preempt_enable(); local_irq_enable(); @@ -3071,10 +3121,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu, local_irq_disable(); preempt_disable(); - /* Guest state should be valid now except if we need to - * emulate an MMIO */ - if (guest_state_valid(vcpu)) - vmx->emulation_required = 0; + vmx->invalid_state_emulation_result = err; } /* @@ -3123,8 +3170,11 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *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) - 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; + } /* Access CR3 don't cause VMExit in paging mode, so we need * to sync with guest real CR3. */ @@ -3238,7 +3288,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx) vmx->vcpu.arch.nmi_injected = false; } kvm_clear_exception_queue(&vmx->vcpu); - if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) { + if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION || + type == INTR_TYPE_SOFT_EXCEPTION)) { if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) { error = vmcs_read32(IDT_VECTORING_ERROR_CODE); kvm_queue_exception_e(&vmx->vcpu, vector, error); @@ -3259,6 +3310,11 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu) vmx_update_window_states(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO, + GUEST_INTR_STATE_STI | + GUEST_INTR_STATE_MOV_SS); + if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) { if (vcpu->arch.interrupt.pending) { enable_nmi_window(vcpu); @@ -3347,6 +3403,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) */ vmcs_writel(HOST_CR0, read_cr0()); + set_debugreg(vcpu->arch.dr6, 6); + asm( /* Store host registers */ "push %%"R"dx; push %%"R"bp;" @@ -3441,6 +3499,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)); vcpu->arch.regs_dirty = 0; + get_debugreg(vcpu->arch.dr6, 6); + vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD); if (vmx->rmode.irq.pending) fixup_rmode_irq(vmx); @@ -3595,7 +3655,6 @@ static struct kvm_x86_ops vmx_x86_ops = { .vcpu_put = vmx_vcpu_put, .set_guest_debug = set_guest_debug, - .guest_debug_pre = kvm_guest_debug_pre, .get_msr = vmx_get_msr, .set_msr = vmx_set_msr, .get_segment_base = vmx_get_segment_base, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 758b7a1..8ca100a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -36,6 +36,7 @@ #include <linux/highmem.h> #include <linux/iommu.h> #include <linux/intel-iommu.h> +#include <linux/cpufreq.h> #include <asm/uaccess.h> #include <asm/msr.h> @@ -69,6 +70,8 @@ static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL; static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); @@ -173,6 +176,7 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { ++vcpu->stat.pf_guest; + if (vcpu->arch.exception.pending) { if (vcpu->arch.exception.nr == PF_VECTOR) { printk(KERN_DEBUG "kvm: inject_page_fault:" @@ -361,6 +365,7 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) } kvm_x86_ops->set_cr4(vcpu, cr4); vcpu->arch.cr4 = cr4; + vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled; kvm_mmu_sync_global(vcpu); kvm_mmu_reset_context(vcpu); } @@ -442,6 +447,11 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +static inline u32 bit(int bitno) +{ + return 1 << (bitno & 31); +} + /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. @@ -456,7 +466,7 @@ static u32 msrs_to_save[] = { MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT + MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; static unsigned num_msrs_to_save; @@ -481,6 +491,28 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) return; } + if (efer & EFER_FFXSR) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) { + printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } + + if (efer & EFER_SVME) { + struct kvm_cpuid_entry2 *feat; + + feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) { + printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n"); + kvm_inject_gp(vcpu, 0); + return; + } + } + kvm_x86_ops->set_efer(vcpu, efer); efer &= ~EFER_LMA; @@ -586,6 +618,8 @@ static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info * hv_clock->tsc_to_system_mul); } +static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz); + static void kvm_write_guest_time(struct kvm_vcpu *v) { struct timespec ts; @@ -596,9 +630,9 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) if ((!vcpu->time_page)) return; - if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) { - kvm_set_time_scale(tsc_khz, &vcpu->hv_clock); - vcpu->hv_clock_tsc_khz = tsc_khz; + if (unlikely(vcpu->hv_clock_tsc_khz != __get_cpu_var(cpu_tsc_khz))) { + kvm_set_time_scale(__get_cpu_var(cpu_tsc_khz), &vcpu->hv_clock); + vcpu->hv_clock_tsc_khz = __get_cpu_var(cpu_tsc_khz); } /* Keep irq disabled to prevent changes to the clock */ @@ -629,6 +663,16 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT); } +static int kvm_request_guest_time_update(struct kvm_vcpu *v) +{ + struct kvm_vcpu_arch *vcpu = &v->arch; + + if (!vcpu->time_page) + return 0; + set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests); + return 1; +} + static bool msr_mtrr_valid(unsigned msr) { switch (msr) { @@ -722,6 +766,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) break; case MSR_IA32_UCODE_REV: case MSR_IA32_UCODE_WRITE: + case MSR_VM_HSAVE_PA: break; case 0x200 ... 0x2ff: return set_msr_mtrr(vcpu, msr, data); @@ -758,7 +803,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) vcpu->arch.time_page = NULL; } - kvm_write_guest_time(vcpu); + kvm_request_guest_time_update(vcpu); break; } default: @@ -843,6 +888,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: case MSR_IA32_LASTINTTOIP: + case MSR_VM_HSAVE_PA: data = 0; break; case MSR_MTRRcap: @@ -967,10 +1013,13 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_MMU_SHADOW_CACHE_CONTROL: case KVM_CAP_SET_TSS_ADDR: case KVM_CAP_EXT_CPUID: + case KVM_CAP_CLOCKSOURCE: case KVM_CAP_PIT: case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: case KVM_CAP_SYNC_MMU: + case KVM_CAP_REINJECT_CONTROL: + case KVM_CAP_IRQ_INJECT_STATUS: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -991,9 +1040,6 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IOMMU: r = iommu_found(); break; - case KVM_CAP_CLOCKSOURCE: - r = boot_cpu_has(X86_FEATURE_CONSTANT_TSC); - break; default: r = 0; break; @@ -1044,7 +1090,7 @@ long kvm_arch_dev_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_dev_ioctl_get_supported_cpuid(&cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; @@ -1064,7 +1110,7 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); - kvm_write_guest_time(vcpu); + kvm_request_guest_time_update(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -1142,8 +1188,8 @@ out: } static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) { int r; @@ -1162,8 +1208,8 @@ out: } static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) { int r; @@ -1172,7 +1218,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, goto out; r = -EFAULT; if (copy_to_user(entries, &vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) + vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) goto out; return 0; @@ -1181,18 +1227,13 @@ out: return r; } -static inline u32 bit(int bitno) -{ - return 1 << (bitno & 31); -} - static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) + u32 index) { entry->function = function; entry->index = index; cpuid_count(entry->function, entry->index, - &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); + &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); entry->flags = 0; } @@ -1222,15 +1263,17 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, #ifdef CONFIG_X86_64 bit(X86_FEATURE_LM) | #endif + bit(X86_FEATURE_FXSR_OPT) | bit(X86_FEATURE_MMXEXT) | bit(X86_FEATURE_3DNOWEXT) | bit(X86_FEATURE_3DNOW); const u32 kvm_supported_word3_x86_features = bit(X86_FEATURE_XMM3) | bit(X86_FEATURE_CX16); const u32 kvm_supported_word6_x86_features = - bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY); + bit(X86_FEATURE_LAHF_LM) | bit(X86_FEATURE_CMP_LEGACY) | + bit(X86_FEATURE_SVM); - /* all func 2 cpuid_count() should be called on the same cpu */ + /* all calls to cpuid_count() should be made on the same cpu */ get_cpu(); do_cpuid_1_ent(entry, function, index); ++*nent; @@ -1304,7 +1347,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) + struct kvm_cpuid_entry2 __user *entries) { struct kvm_cpuid_entry2 *cpuid_entries; int limit, nent = 0, r = -E2BIG; @@ -1321,7 +1364,7 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[0].eax; for (func = 1; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); + &nent, cpuid->nent); r = -E2BIG; if (nent >= cpuid->nent) goto out_free; @@ -1330,10 +1373,10 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, limit = cpuid_entries[nent - 1].eax; for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); + &nent, cpuid->nent); r = -EFAULT; if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) + nent * sizeof(struct kvm_cpuid_entry2))) goto out_free; cpuid->nent = nent; r = 0; @@ -1477,7 +1520,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_set_cpuid2(vcpu, &cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; break; @@ -1490,7 +1533,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid)) goto out; r = kvm_vcpu_ioctl_get_cpuid2(vcpu, &cpuid, - cpuid_arg->entries); + cpuid_arg->entries); if (r) goto out; r = -EFAULT; @@ -1710,6 +1753,15 @@ static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps) return r; } +static int kvm_vm_ioctl_reinject(struct kvm *kvm, + struct kvm_reinject_control *control) +{ + if (!kvm->arch.vpit) + return -ENXIO; + kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject; + return 0; +} + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -1807,13 +1859,26 @@ long kvm_arch_vm_ioctl(struct file *filp, } } else goto out; + r = kvm_setup_default_irq_routing(kvm); + if (r) { + kfree(kvm->arch.vpic); + kfree(kvm->arch.vioapic); + goto out; + } break; case KVM_CREATE_PIT: + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpit) + goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm); if (kvm->arch.vpit) r = 0; + create_pit_unlock: + mutex_unlock(&kvm->lock); break; + case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; @@ -1821,10 +1886,17 @@ long kvm_arch_vm_ioctl(struct file *filp, if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; if (irqchip_in_kernel(kvm)) { + __s32 status; mutex_lock(&kvm->lock); - kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, - irq_event.irq, irq_event.level); + status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, + irq_event.irq, irq_event.level); mutex_unlock(&kvm->lock); + if (ioctl == KVM_IRQ_LINE_STATUS) { + irq_event.status = status; + if (copy_to_user(argp, &irq_event, + sizeof irq_event)) + goto out; + } r = 0; } break; @@ -1907,6 +1979,17 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_REINJECT_CONTROL: { + struct kvm_reinject_control control; + r = -EFAULT; + if (copy_from_user(&control, argp, sizeof(control))) + goto out; + r = kvm_vm_ioctl_reinject(kvm, &control); + if (r) + goto out; + r = 0; + break; + } default: ; } @@ -1960,10 +2043,38 @@ static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu, return dev; } -int emulator_read_std(unsigned long addr, - void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) +static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu) +{ + void *data = val; + int r = X86EMUL_CONTINUE; + + while (bytes) { + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + unsigned offset = addr & (PAGE_SIZE-1); + unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); + int ret; + + if (gpa == UNMAPPED_GVA) { + r = X86EMUL_PROPAGATE_FAULT; + goto out; + } + ret = kvm_read_guest(vcpu->kvm, gpa, data, toread); + if (ret < 0) { + r = X86EMUL_UNHANDLEABLE; + goto out; + } + + bytes -= toread; + data += toread; + addr += toread; + } +out: + return r; +} + +static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu) { void *data = val; int r = X86EMUL_CONTINUE; @@ -1971,27 +2082,27 @@ int emulator_read_std(unsigned long addr, while (bytes) { gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); unsigned offset = addr & (PAGE_SIZE-1); - unsigned tocopy = min(bytes, (unsigned)PAGE_SIZE - offset); + unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; if (gpa == UNMAPPED_GVA) { r = X86EMUL_PROPAGATE_FAULT; goto out; } - ret = kvm_read_guest(vcpu->kvm, gpa, data, tocopy); + ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite); if (ret < 0) { r = X86EMUL_UNHANDLEABLE; goto out; } - bytes -= tocopy; - data += tocopy; - addr += tocopy; + bytes -= towrite; + data += towrite; + addr += towrite; } out: return r; } -EXPORT_SYMBOL_GPL(emulator_read_std); + static int emulator_read_emulated(unsigned long addr, void *val, @@ -2013,8 +2124,8 @@ static int emulator_read_emulated(unsigned long addr, if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto mmio; - if (emulator_read_std(addr, val, bytes, vcpu) - == X86EMUL_CONTINUE) + if (kvm_read_guest_virt(addr, val, bytes, vcpu) + == X86EMUL_CONTINUE) return X86EMUL_CONTINUE; if (gpa == UNMAPPED_GVA) return X86EMUL_PROPAGATE_FAULT; @@ -2217,7 +2328,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - emulator_read_std(rip_linear, (void *)opcodes, 4, vcpu); + kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu); printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); @@ -2225,7 +2336,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); static struct x86_emulate_ops emulate_ops = { - .read_std = emulator_read_std, + .read_std = kvm_read_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, @@ -2327,40 +2438,19 @@ int emulate_instruction(struct kvm_vcpu *vcpu, } EXPORT_SYMBOL_GPL(emulate_instruction); -static void free_pio_guest_pages(struct kvm_vcpu *vcpu) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(vcpu->arch.pio.guest_pages); ++i) - if (vcpu->arch.pio.guest_pages[i]) { - kvm_release_page_dirty(vcpu->arch.pio.guest_pages[i]); - vcpu->arch.pio.guest_pages[i] = NULL; - } -} - static int pio_copy_data(struct kvm_vcpu *vcpu) { void *p = vcpu->arch.pio_data; - void *q; + gva_t q = vcpu->arch.pio.guest_gva; unsigned bytes; - int nr_pages = vcpu->arch.pio.guest_pages[1] ? 2 : 1; + int ret; - q = vmap(vcpu->arch.pio.guest_pages, nr_pages, VM_READ|VM_WRITE, - PAGE_KERNEL); - if (!q) { - free_pio_guest_pages(vcpu); - return -ENOMEM; - } - q += vcpu->arch.pio.guest_page_offset; bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; if (vcpu->arch.pio.in) - memcpy(q, p, bytes); + ret = kvm_write_guest_virt(q, p, bytes, vcpu); else - memcpy(p, q, bytes); - q -= vcpu->arch.pio.guest_page_offset; - vunmap(q); - free_pio_guest_pages(vcpu); - return 0; + ret = kvm_read_guest_virt(q, p, bytes, vcpu); + return ret; } int complete_pio(struct kvm_vcpu *vcpu) @@ -2471,7 +2561,6 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.in = in; vcpu->arch.pio.string = 0; vcpu->arch.pio.down = 0; - vcpu->arch.pio.guest_page_offset = 0; vcpu->arch.pio.rep = 0; if (vcpu->run->io.direction == KVM_EXIT_IO_IN) @@ -2499,9 +2588,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, gva_t address, int rep, unsigned port) { unsigned now, in_page; - int i, ret = 0; - int nr_pages = 1; - struct page *page; + int ret = 0; struct kvm_io_device *pio_dev; vcpu->run->exit_reason = KVM_EXIT_IO; @@ -2513,7 +2600,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.in = in; vcpu->arch.pio.string = 1; vcpu->arch.pio.down = down; - vcpu->arch.pio.guest_page_offset = offset_in_page(address); vcpu->arch.pio.rep = rep; if (vcpu->run->io.direction == KVM_EXIT_IO_IN) @@ -2533,15 +2619,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, else in_page = offset_in_page(address) + size; now = min(count, (unsigned long)in_page / size); - if (!now) { - /* - * String I/O straddles page boundary. Pin two guest pages - * so that we satisfy atomicity constraints. Do just one - * transaction to avoid complexity. - */ - nr_pages = 2; + if (!now) now = 1; - } if (down) { /* * String I/O in reverse. Yuck. Kill the guest, fix later. @@ -2556,15 +2635,7 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) kvm_x86_ops->skip_emulated_instruction(vcpu); - for (i = 0; i < nr_pages; ++i) { - page = gva_to_page(vcpu, address + i * PAGE_SIZE); - vcpu->arch.pio.guest_pages[i] = page; - if (!page) { - kvm_inject_gp(vcpu, 0); - free_pio_guest_pages(vcpu); - return 1; - } - } + vcpu->arch.pio.guest_gva = address; pio_dev = vcpu_find_pio_dev(vcpu, port, vcpu->arch.pio.cur_count, @@ -2572,7 +2643,11 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, if (!vcpu->arch.pio.in) { /* string PIO write */ ret = pio_copy_data(vcpu); - if (ret >= 0 && pio_dev) { + if (ret == X86EMUL_PROPAGATE_FAULT) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if (ret == 0 && pio_dev) { pio_string_write(pio_dev, vcpu); complete_pio(vcpu); if (vcpu->arch.pio.count == 0) @@ -2587,9 +2662,72 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, } EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); +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) +{ + struct cpufreq_freqs *freq = data; + struct kvm *kvm; + 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); + + spin_lock(&kvm_lock); + list_for_each_entry(kvm, &vm_list, vm_list) { + for (i = 0; i < KVM_MAX_VCPUS; ++i) { + vcpu = kvm->vcpus[i]; + if (!vcpu) + continue; + if (vcpu->cpu != freq->cpu) + continue; + if (!kvm_request_guest_time_update(vcpu)) + continue; + if (vcpu->cpu != smp_processor_id()) + send_ipi++; + } + } + spin_unlock(&kvm_lock); + + if (freq->old < freq->new && send_ipi) { + /* + * We upscale the frequency. Must make the guest + * doesn't see old kvmclock values while running with + * the new frequency, otherwise we risk the guest sees + * time go backwards. + * + * In case we update the frequency for another cpu + * (which might be in guest context) send an interrupt + * to kick the cpu out of guest context. Next time + * guest context is entered kvmclock will be updated, + * so the guest will not see stale values. + */ + smp_call_function_single(freq->cpu, bounce_off, NULL, 1); + } + return 0; +} + +static struct notifier_block kvmclock_cpufreq_notifier_block = { + .notifier_call = kvmclock_cpufreq_notifier +}; + int kvm_arch_init(void *opaque) { - int r; + int r, cpu; struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; if (kvm_x86_ops) { @@ -2620,6 +2758,15 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_base_ptes(PT_PRESENT_MASK); kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0, 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); + } + return 0; out: @@ -2827,25 +2974,20 @@ static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) return 0; if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) + !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) return 0; return 1; } -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index) { int i; - u32 function, index; - struct kvm_cpuid_entry2 *e, *best; + struct kvm_cpuid_entry2 *best = NULL; - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); - best = NULL; for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + struct kvm_cpuid_entry2 *e; + e = &vcpu->arch.cpuid_entries[i]; if (is_matching_cpuid_entry(e, function, index)) { if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) @@ -2860,6 +3002,21 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) if (!best || e->function > best->function) best = e; } + return best; +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 function, index; + struct kvm_cpuid_entry2 *best; + + function = kvm_register_read(vcpu, VCPU_REGS_RAX); + index = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_register_write(vcpu, VCPU_REGS_RAX, 0); + kvm_register_write(vcpu, VCPU_REGS_RBX, 0); + kvm_register_write(vcpu, VCPU_REGS_RCX, 0); + kvm_register_write(vcpu, VCPU_REGS_RDX, 0); + best = kvm_find_cpuid_entry(vcpu, function, index); if (best) { kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); @@ -2945,6 +3102,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (vcpu->requests) { if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests)) __kvm_migrate_timers(vcpu); + if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests)) + kvm_write_guest_time(vcpu); if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests)) kvm_mmu_sync_roots(vcpu); if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests)) @@ -2979,9 +3138,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - if (vcpu->guest_debug.enabled) - kvm_x86_ops->guest_debug_pre(vcpu); - vcpu->guest_mode = 1; /* * Make sure that guest_mode assignment won't happen after @@ -3002,10 +3158,34 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_guest_enter(); + get_debugreg(vcpu->arch.host_dr6, 6); + get_debugreg(vcpu->arch.host_dr7, 7); + if (unlikely(vcpu->arch.switch_db_regs)) { + get_debugreg(vcpu->arch.host_db[0], 0); + get_debugreg(vcpu->arch.host_db[1], 1); + get_debugreg(vcpu->arch.host_db[2], 2); + get_debugreg(vcpu->arch.host_db[3], 3); + + set_debugreg(0, 7); + set_debugreg(vcpu->arch.eff_db[0], 0); + set_debugreg(vcpu->arch.eff_db[1], 1); + set_debugreg(vcpu->arch.eff_db[2], 2); + set_debugreg(vcpu->arch.eff_db[3], 3); + } KVMTRACE_0D(VMENTRY, vcpu, entryexit); kvm_x86_ops->run(vcpu, kvm_run); + if (unlikely(vcpu->arch.switch_db_regs)) { + set_debugreg(0, 7); + set_debugreg(vcpu->arch.host_db[0], 0); + set_debugreg(vcpu->arch.host_db[1], 1); + set_debugreg(vcpu->arch.host_db[2], 2); + set_debugreg(vcpu->arch.host_db[3], 3); + } + set_debugreg(vcpu->arch.host_dr6, 6); + set_debugreg(vcpu->arch.host_dr7, 7); + vcpu->guest_mode = 0; local_irq_enable(); @@ -3192,7 +3372,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) /* * Don't leak debug flags in case they were set for guest debugging */ - if (vcpu->guest_debug.enabled && vcpu->guest_debug.singlestep) + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); vcpu_put(vcpu); @@ -3811,15 +3991,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, return 0; } -int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu, - struct kvm_debug_guest *dbg) +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) { - int r; + 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)) { + for (i = 0; i < KVM_NR_DB_REGS; ++i) + vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; + vcpu->arch.switch_db_regs = + (dbg->arch.debugreg[7] & DR7_BP_EN_MASK); + } else { + for (i = 0; i < KVM_NR_DB_REGS; i++) + vcpu->arch.eff_db[i] = vcpu->arch.db[i]; + vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); + } + r = 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); + vcpu_put(vcpu); return r; @@ -4007,6 +4204,11 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.nmi_pending = false; vcpu->arch.nmi_injected = false; + vcpu->arch.switch_db_regs = 0; + memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = DR6_FIXED_1; + vcpu->arch.dr7 = DR7_FIXED_1; + return kvm_x86_ops->vcpu_reset(vcpu); } @@ -4100,6 +4302,8 @@ struct kvm *kvm_arch_create_vm(void) /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap); + rdtscll(kvm->arch.vm_init_tsc); + return kvm; } diff --git a/arch/x86/kvm/x86_emulate.c b/arch/x86/kvm/x86_emulate.c index d174db7..ca91749 100644 --- a/arch/x86/kvm/x86_emulate.c +++ b/arch/x86/kvm/x86_emulate.c @@ -178,7 +178,7 @@ static u32 opcode_table[256] = { 0, ImplicitOps | Stack, 0, 0, ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov, /* 0xC8 - 0xCF */ - 0, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, ImplicitOps | Stack, 0, 0, 0, 0, /* 0xD0 - 0xD7 */ ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM, @@ -1136,18 +1136,19 @@ static inline void emulate_push(struct x86_emulate_ctxt *ctxt) } static int emulate_pop(struct x86_emulate_ctxt *ctxt, - struct x86_emulate_ops *ops) + struct x86_emulate_ops *ops, + void *dest, int len) { struct decode_cache *c = &ctxt->decode; int rc; rc = ops->read_emulated(register_address(c, ss_base(ctxt), c->regs[VCPU_REGS_RSP]), - &c->src.val, c->src.bytes, ctxt->vcpu); + dest, len, ctxt->vcpu); if (rc != 0) return rc; - register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->src.bytes); + register_address_increment(c, &c->regs[VCPU_REGS_RSP], len); return rc; } @@ -1157,11 +1158,9 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt, struct decode_cache *c = &ctxt->decode; int rc; - c->src.bytes = c->dst.bytes; - rc = emulate_pop(ctxt, ops); + rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes); if (rc != 0) return rc; - c->dst.val = c->src.val; return 0; } @@ -1279,6 +1278,25 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt, return 0; } +static int emulate_ret_far(struct x86_emulate_ctxt *ctxt, + struct x86_emulate_ops *ops) +{ + struct decode_cache *c = &ctxt->decode; + int rc; + unsigned long cs; + + rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes); + if (rc) + return rc; + if (c->op_bytes == 4) + c->eip = (u32)c->eip; + rc = emulate_pop(ctxt, ops, &cs, c->op_bytes); + if (rc) + return rc; + rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, 1, VCPU_SREG_CS); + return rc; +} + static inline int writeback(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops) { @@ -1467,11 +1485,9 @@ special_insn: break; case 0x58 ... 0x5f: /* pop reg */ pop_instruction: - c->src.bytes = c->op_bytes; - rc = emulate_pop(ctxt, ops); + rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes); if (rc != 0) goto done; - c->dst.val = c->src.val; break; case 0x63: /* movsxd */ if (ctxt->mode != X86EMUL_MODE_PROT64) @@ -1738,6 +1754,11 @@ special_insn: mov: c->dst.val = c->src.val; break; + case 0xcb: /* ret far */ + rc = emulate_ret_far(ctxt, ops); + if (rc) + goto done; + break; case 0xd0 ... 0xd1: /* Grp2 */ c->src.val = 1; emulate_grp2(ctxt); @@ -1908,11 +1929,16 @@ twobyte_insn: c->dst.type = OP_NONE; break; case 3: /* lidt/vmmcall */ - if (c->modrm_mod == 3 && c->modrm_rm == 1) { - rc = kvm_fix_hypercall(ctxt->vcpu); - if (rc) - goto done; - kvm_emulate_hypercall(ctxt->vcpu); + if (c->modrm_mod == 3) { + switch (c->modrm_rm) { + case 1: + rc = kvm_fix_hypercall(ctxt->vcpu); + if (rc) + goto done; + break; + default: + goto cannot_emulate; + } } else { rc = read_descriptor(ctxt, ops, c->src.ptr, &size, &address, diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index 90e44a1..a208536 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -107,7 +107,7 @@ static void async_hcall(unsigned long call, unsigned long arg1, local_irq_save(flags); if (lguest_data.hcall_status[next_call] != 0xFF) { /* Table full, so do normal hcall which will flush table. */ - hcall(call, arg1, arg2, arg3); + kvm_hypercall3(call, arg1, arg2, arg3); } else { lguest_data.hcalls[next_call].arg0 = call; lguest_data.hcalls[next_call].arg1 = arg1; @@ -134,13 +134,32 @@ static void async_hcall(unsigned long call, unsigned long arg1, * * So, when we're in lazy mode, we call async_hcall() to store the call for * future processing: */ -static void lazy_hcall(unsigned long call, +static void lazy_hcall1(unsigned long call, + unsigned long arg1) +{ + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) + kvm_hypercall1(call, arg1); + else + async_hcall(call, arg1, 0, 0); +} + +static void lazy_hcall2(unsigned long call, + unsigned long arg1, + unsigned long arg2) +{ + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) + kvm_hypercall2(call, arg1, arg2); + else + async_hcall(call, arg1, arg2, 0); +} + +static void lazy_hcall3(unsigned long call, unsigned long arg1, unsigned long arg2, unsigned long arg3) { if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) - hcall(call, arg1, arg2, arg3); + kvm_hypercall3(call, arg1, arg2, arg3); else async_hcall(call, arg1, arg2, arg3); } @@ -150,7 +169,7 @@ static void lazy_hcall(unsigned long call, static void lguest_leave_lazy_mode(void) { paravirt_leave_lazy(paravirt_get_lazy_mode()); - hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0); + kvm_hypercall0(LHCALL_FLUSH_ASYNC); } /*G:033 @@ -229,7 +248,7 @@ static void lguest_write_idt_entry(gate_desc *dt, /* Keep the local copy up to date. */ native_write_idt_entry(dt, entrynum, g); /* Tell Host about this new entry. */ - hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); + kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]); } /* Changing to a different IDT is very rare: we keep the IDT up-to-date every @@ -241,7 +260,7 @@ static void lguest_load_idt(const struct desc_ptr *desc) struct desc_struct *idt = (void *)desc->address; for (i = 0; i < (desc->size+1)/8; i++) - hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); + kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b); } /* @@ -254,15 +273,15 @@ static void lguest_load_idt(const struct desc_ptr *desc) * controls the entire thing and the Guest asks it to make changes using the * LOAD_GDT hypercall. * - * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY - * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? Wouldn't - * it be even better if you were the one to send the patch to fix it? + * This is the exactly like the IDT code. */ static void lguest_load_gdt(const struct desc_ptr *desc) { - BUG_ON((desc->size+1)/8 != GDT_ENTRIES); - hcall(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES, 0); + unsigned int i; + struct desc_struct *gdt = (void *)desc->address; + + for (i = 0; i < (desc->size+1)/8; i++) + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b); } /* For a single GDT entry which changes, we do the lazy thing: alter our GDT, @@ -272,7 +291,9 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) { native_write_gdt_entry(dt, entrynum, desc, type); - hcall(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES, 0); + /* Tell Host about this new entry. */ + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum, + dt[entrynum].a, dt[entrynum].b); } /* OK, I lied. There are three "thread local storage" GDT entries which change @@ -284,7 +305,7 @@ static void lguest_load_tls(struct thread_struct *t, unsigned int cpu) * can't handle us removing entries we're currently using. So we clear * the GS register here: if it's needed it'll be reloaded anyway. */ lazy_load_gs(0); - lazy_hcall(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu, 0); + lazy_hcall2(LHCALL_LOAD_TLS, __pa(&t->tls_array), cpu); } /*G:038 That's enough excitement for now, back to ploughing through each of @@ -382,7 +403,7 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx, static unsigned long current_cr0; static void lguest_write_cr0(unsigned long val) { - lazy_hcall(LHCALL_TS, val & X86_CR0_TS, 0, 0); + lazy_hcall1(LHCALL_TS, val & X86_CR0_TS); current_cr0 = val; } @@ -396,7 +417,7 @@ static unsigned long lguest_read_cr0(void) * the vowels have been optimized out. */ static void lguest_clts(void) { - lazy_hcall(LHCALL_TS, 0, 0, 0); + lazy_hcall1(LHCALL_TS, 0); current_cr0 &= ~X86_CR0_TS; } @@ -418,7 +439,7 @@ static bool cr3_changed = false; static void lguest_write_cr3(unsigned long cr3) { lguest_data.pgdir = cr3; - lazy_hcall(LHCALL_NEW_PGTABLE, cr3, 0, 0); + lazy_hcall1(LHCALL_NEW_PGTABLE, cr3); cr3_changed = true; } @@ -490,11 +511,17 @@ static void lguest_write_cr4(unsigned long val) * into a process' address space. We set the entry then tell the Host the * toplevel and address this corresponds to. The Guest uses one pagetable per * process, so we need to tell the Host which one we're changing (mm->pgd). */ +static void lguest_pte_update(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + lazy_hcall3(LHCALL_SET_PTE, __pa(mm->pgd), addr, ptep->pte_low); +} + static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pteval) { *ptep = pteval; - lazy_hcall(LHCALL_SET_PTE, __pa(mm->pgd), addr, pteval.pte_low); + lguest_pte_update(mm, addr, ptep); } /* The Guest calls this to set a top-level entry. Again, we set the entry then @@ -503,8 +530,8 @@ static void lguest_set_pte_at(struct mm_struct *mm, unsigned long addr, static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval) { *pmdp = pmdval; - lazy_hcall(LHCALL_SET_PMD, __pa(pmdp)&PAGE_MASK, - (__pa(pmdp)&(PAGE_SIZE-1))/4, 0); + lazy_hcall2(LHCALL_SET_PMD, __pa(pmdp) & PAGE_MASK, + (__pa(pmdp) & (PAGE_SIZE - 1)) / 4); } /* There are a couple of legacy places where the kernel sets a PTE, but we @@ -520,7 +547,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval) { *ptep = pteval; if (cr3_changed) - lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 1); } /* Unfortunately for Lguest, the pv_mmu_ops for page tables were based on @@ -536,7 +563,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval) static void lguest_flush_tlb_single(unsigned long addr) { /* Simply set it to zero: if it was not, it will fault back in. */ - lazy_hcall(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); + lazy_hcall3(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0); } /* This is what happens after the Guest has removed a large number of entries. @@ -544,7 +571,7 @@ static void lguest_flush_tlb_single(unsigned long addr) * have changed, ie. virtual addresses below PAGE_OFFSET. */ static void lguest_flush_tlb_user(void) { - lazy_hcall(LHCALL_FLUSH_TLB, 0, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 0); } /* This is called when the kernel page tables have changed. That's not very @@ -552,7 +579,7 @@ static void lguest_flush_tlb_user(void) * slow), so it's worth separating this from the user flushing above. */ static void lguest_flush_tlb_kernel(void) { - lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0); + lazy_hcall1(LHCALL_FLUSH_TLB, 1); } /* @@ -689,7 +716,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta, } /* Please wake us this far in the future. */ - hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0); + kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta); return 0; } @@ -700,7 +727,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode, case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* A 0 argument shuts the clock down. */ - hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0); + kvm_hypercall0(LHCALL_SET_CLOCKEVENT); break; case CLOCK_EVT_MODE_ONESHOT: /* This is what we expect. */ @@ -775,8 +802,8 @@ static void lguest_time_init(void) static void lguest_load_sp0(struct tss_struct *tss, struct thread_struct *thread) { - lazy_hcall(LHCALL_SET_STACK, __KERNEL_DS|0x1, thread->sp0, - THREAD_SIZE/PAGE_SIZE); + lazy_hcall3(LHCALL_SET_STACK, __KERNEL_DS | 0x1, thread->sp0, + THREAD_SIZE / PAGE_SIZE); } /* Let's just say, I wouldn't do debugging under a Guest. */ @@ -849,7 +876,7 @@ static void set_lguest_basic_apic_ops(void) /* STOP! Until an interrupt comes in. */ static void lguest_safe_halt(void) { - hcall(LHCALL_HALT, 0, 0, 0); + kvm_hypercall0(LHCALL_HALT); } /* The SHUTDOWN hypercall takes a string to describe what's happening, and @@ -859,7 +886,8 @@ static void lguest_safe_halt(void) * rather than virtual addresses, so we use __pa() here. */ static void lguest_power_off(void) { - hcall(LHCALL_SHUTDOWN, __pa("Power down"), LGUEST_SHUTDOWN_POWEROFF, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"), + LGUEST_SHUTDOWN_POWEROFF); } /* @@ -869,7 +897,7 @@ static void lguest_power_off(void) */ static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p) { - hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF); /* The hcall won't return, but to keep gcc happy, we're "done". */ return NOTIFY_DONE; } @@ -910,7 +938,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) len = sizeof(scratch) - 1; scratch[len] = '\0'; memcpy(scratch, buf, len); - hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0); + kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch)); /* This routine returns the number of bytes actually written. */ return len; @@ -920,7 +948,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count) * Launcher to reboot us. */ static void lguest_restart(char *reason) { - hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0); + kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART); } /*G:050 @@ -1040,6 +1068,8 @@ __init void lguest_init(void) pv_mmu_ops.read_cr3 = lguest_read_cr3; pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu; pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode; + pv_mmu_ops.pte_update = lguest_pte_update; + pv_mmu_ops.pte_update_defer = lguest_pte_update; #ifdef CONFIG_X86_LOCAL_APIC /* apic read/write intercepts */ diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S index 10b9bd3..f795419 100644 --- a/arch/x86/lguest/i386_head.S +++ b/arch/x86/lguest/i386_head.S @@ -27,8 +27,8 @@ ENTRY(lguest_entry) /* We make the "initialization" hypercall now to tell the Host about * us, and also find out where it put our page tables. */ movl $LHCALL_LGUEST_INIT, %eax - movl $lguest_data - __PAGE_OFFSET, %edx - int $LGUEST_TRAP_ENTRY + movl $lguest_data - __PAGE_OFFSET, %ebx + .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */ /* Set up the initial stack so we can run C code. */ movl $(init_thread_union+THREAD_SIZE),%esp diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 0853774..fdd30d0 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE) += mmiotrace.o mmiotrace-y := kmmio.o pf_in.o mmio-mod.o obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o -obj-$(CONFIG_NUMA) += numa_$(BITS).o +obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_K8_NUMA) += k8topology_64.o obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index be54176..6340cef 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -219,6 +219,22 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end, return 1; } +/** + * get_user_pages_fast() - pin user pages in memory + * @start: starting user address + * @nr_pages: number of pages from start to pin + * @write: whether pages will be written to + * @pages: array that receives pointers to the pages pinned. + * Should be at least nr_pages long. + * + * Attempt to pin user pages in memory without taking mm->mmap_sem. + * If not successful, it will fall back to taking the lock and + * calling get_user_pages(). + * + * Returns number of pages pinned. This may be fewer than the number + * requested. If nr_pages is 0 or negative, returns 0. If no pages + * were pinned, returns -errno. + */ int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 522db5e..8126e8d 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -19,49 +19,6 @@ void kunmap(struct page *page) kunmap_high(page); } -static void debug_kmap_atomic_prot(enum km_type type) -{ -#ifdef CONFIG_DEBUG_HIGHMEM - static unsigned warn_count = 10; - - if (unlikely(warn_count == 0)) - return; - - if (unlikely(in_interrupt())) { - if (in_irq()) { - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ && - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } else if (!irqs_disabled()) { /* softirq */ - if (type != KM_IRQ0 && type != KM_IRQ1 && - type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 && - type != KM_SKB_SUNRPC_DATA && - type != KM_SKB_DATA_SOFTIRQ && - type != KM_BOUNCE_READ) { - WARN_ON(1); - warn_count--; - } - } - } - - if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ || - type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) { - if (!irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) { - if (irq_count() == 0 && !irqs_disabled()) { - WARN_ON(1); - warn_count--; - } - } -#endif -} - /* * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because * no global lock is needed and because the kmap code must perform a global TLB @@ -81,7 +38,7 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot) if (!PageHighMem(page)) return page_address(page); - debug_kmap_atomic_prot(type); + debug_kmap_atomic(type); idx = type + KM_TYPE_NR*smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index db81e9a..749559e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -1054,17 +1054,47 @@ 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; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, start+size); + + set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT); +} + +void set_kernel_text_ro(void) +{ + unsigned long start = PFN_ALIGN(_text); + unsigned long size = PFN_ALIGN(_etext) - start; + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, start+size); + + set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); +} + void mark_rodata_ro(void) { unsigned long start = PFN_ALIGN(_text); unsigned long size = PFN_ALIGN(_etext) - start; -#ifndef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); printk(KERN_INFO "Write protecting the kernel text: %luk\n", size >> 10); + kernel_set_to_readonly = 1; + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n", start, start+size); @@ -1073,7 +1103,6 @@ void mark_rodata_ro(void) printk(KERN_INFO "Testing CPA: write protecting again\n"); set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT); #endif -#endif /* CONFIG_DYNAMIC_FTRACE */ start += size; size = (unsigned long)__end_rodata - start; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 54efa57d..1753e80 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -734,21 +734,48 @@ void __init mem_init(void) const int rodata_test_data = 0xC3; EXPORT_SYMBOL_GPL(rodata_test_data); +static int kernel_set_to_readonly; + +void set_kernel_text_rw(void) +{ + unsigned long start = PFN_ALIGN(_stext); + unsigned long end = PFN_ALIGN(__start_rodata); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read write\n", + start, end); + + 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); + + if (!kernel_set_to_readonly) + return; + + pr_debug("Set kernel text: %lx - %lx for read only\n", + start, end); + + 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 rodata_start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK; -#ifdef CONFIG_DYNAMIC_FTRACE - /* Dynamic tracing modifies the kernel text section */ - start = rodata_start; -#endif - printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n", (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + kernel_set_to_readonly = 1; + /* * The rodata section (but not the kernel text!) should also be * not-executable. diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 699c9b2..8056545 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -19,10 +19,11 @@ #include <asm/iomap.h> #include <asm/pat.h> #include <linux/module.h> +#include <linux/highmem.h> int is_io_mapping_possible(resource_size_t base, unsigned long size) { -#ifndef CONFIG_X86_PAE +#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT) /* There is no way to map greater than 1 << 32 address without PAE */ if (base + size > 0x100000000ULL) return 0; @@ -38,6 +39,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) pagefault_disable(); + debug_kmap_atomic(type); idx = type + KM_TYPE_NR * smp_processor_id(); vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0dfa09d..8a45093 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -280,15 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return NULL; area->phys_addr = phys_addr; vaddr = (unsigned long) area->addr; - if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { + + if (kernel_map_sync_memtype(phys_addr, size, prot_val)) { free_memtype(phys_addr, phys_addr + size); free_vm_area(area); return NULL; } - if (ioremap_change_attr(vaddr, size, prot_val) < 0) { + if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) { free_memtype(phys_addr, phys_addr + size); - vunmap(area->addr); + free_vm_area(area); return NULL; } @@ -374,7 +375,8 @@ static void __iomem *ioremap_default(resource_size_t phys_addr, * - 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, -1, &flags); + err = reserve_memtype(phys_addr, phys_addr + size, + _PAGE_CACHE_WB, &flags); if (err < 0) return NULL; @@ -547,7 +549,7 @@ void __init early_ioremap_reset(void) } static void __init __early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t flags) + phys_addr_t phys, pgprot_t flags) { unsigned long addr = __fix_to_virt(idx); pte_t *pte; @@ -566,7 +568,7 @@ static void __init __early_set_fixmap(enum fixed_addresses idx, } static inline void __init early_set_fixmap(enum fixed_addresses idx, - unsigned long phys, pgprot_t prot) + phys_addr_t phys, pgprot_t prot) { if (after_paging_init) __set_fixmap(idx, phys, prot); @@ -607,9 +609,10 @@ static int __init check_early_ioremap_leak(void) late_initcall(check_early_ioremap_leak); static void __init __iomem * -__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) +__early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) { - unsigned long offset, last_addr; + unsigned long offset; + resource_size_t last_addr; unsigned int nrpages; enum fixed_addresses idx0, idx; int i, slot; @@ -625,15 +628,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } if (slot < 0) { - printk(KERN_INFO "early_iomap(%08lx, %08lx) not found slot\n", - phys_addr, size); + printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n", + (u64)phys_addr, size); WARN_ON(1); return NULL; } if (early_ioremap_debug) { - printk(KERN_INFO "early_ioremap(%08lx, %08lx) [%d] => ", - phys_addr, size, slot); + printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ", + (u64)phys_addr, size, slot); dump_stack(); } @@ -680,13 +683,15 @@ __early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot) } /* Remap an IO device */ -void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_ioremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO); } /* Remap memory */ -void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size) +void __init __iomem * +early_memremap(resource_size_t phys_addr, unsigned long size) { return __early_ioremap(phys_addr, size, PAGE_KERNEL); } diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index 2c4baa8..c9342ed 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -378,27 +378,34 @@ static void clear_trace_list(void) } #ifdef CONFIG_HOTPLUG_CPU -static cpumask_t downed_cpus; +static cpumask_var_t downed_cpus; static void enter_uniprocessor(void) { int cpu; int err; + if (downed_cpus == NULL && + !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) { + pr_notice(NAME "Failed to allocate mask\n"); + goto out; + } + get_online_cpus(); - downed_cpus = cpu_online_map; - cpu_clear(first_cpu(cpu_online_map), downed_cpus); + cpumask_copy(downed_cpus, cpu_online_mask); + cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus); if (num_online_cpus() > 1) pr_notice(NAME "Disabling non-boot CPUs...\n"); put_online_cpus(); - for_each_cpu_mask(cpu, downed_cpus) { + for_each_cpu(cpu, downed_cpus) { err = cpu_down(cpu); if (!err) pr_info(NAME "CPU%d is down.\n", cpu); else pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err); } +out: if (num_online_cpus() > 1) pr_warning(NAME "multiple CPUs still online, " "may miss events.\n"); @@ -411,10 +418,10 @@ static void __ref leave_uniprocessor(void) int cpu; int err; - if (cpus_weight(downed_cpus) == 0) + if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0) return; pr_notice(NAME "Re-enabling CPUs...\n"); - for_each_cpu_mask(cpu, downed_cpus) { + for_each_cpu(cpu, downed_cpus) { err = cpu_up(cpu); if (!err) pr_info(NAME "enabled CPU%d.\n", cpu); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c new file mode 100644 index 0000000..550df48 --- /dev/null +++ b/arch/x86/mm/numa.c @@ -0,0 +1,67 @@ +/* Common code for 32 and 64-bit NUMA */ +#include <linux/topology.h> +#include <linux/module.h> +#include <linux/bootmem.h> + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +# define DBG(x...) printk(KERN_DEBUG x) +#else +# define DBG(x...) +#endif + +/* + * Which logical CPUs are on which nodes + */ +cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; +EXPORT_SYMBOL(node_to_cpumask_map); + +/* + * Allocate node_to_cpumask_map based on number of available nodes + * Requires node_possible_map to be valid. + * + * Note: node_to_cpumask() is not valid until after this is done. + * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) + */ +void __init setup_node_to_cpumask_map(void) +{ + unsigned int node, num = 0; + + /* setup nr_node_ids if not done yet */ + if (nr_node_ids == MAX_NUMNODES) { + for_each_node_mask(node, node_possible_map) + num = node; + nr_node_ids = num + 1; + } + + /* allocate the map */ + for (node = 0; node < nr_node_ids; node++) + alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]); + + /* cpumask_of_node() will now work */ + pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); +} + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +/* + * Returns a pointer to the bitmask of CPUs on Node 'node'. + */ +const struct cpumask *cpumask_of_node(int node) +{ + if (node >= nr_node_ids) { + printk(KERN_WARNING + "cpumask_of_node(%d): node > nr_node_ids(%d)\n", + node, nr_node_ids); + dump_stack(); + return cpu_none_mask; + } + if (node_to_cpumask_map[node] == NULL) { + printk(KERN_WARNING + "cpumask_of_node(%d): no node_to_cpumask_map!\n", + node); + dump_stack(); + return cpu_online_mask; + } + return node_to_cpumask_map[node]; +} +EXPORT_SYMBOL(cpumask_of_node); +#endif diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 64c9cf0..d73aaa8 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -20,12 +20,6 @@ #include <asm/acpi.h> #include <asm/k8.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(x...) printk(KERN_DEBUG x) -#else -# define DBG(x...) -#endif - struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -49,12 +43,6 @@ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE); EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map); /* - * Which logical CPUs are on which nodes - */ -cpumask_t *node_to_cpumask_map; -EXPORT_SYMBOL(node_to_cpumask_map); - -/* * Given a shift value, try to populate memnodemap[] * Returns : * 1 if OK @@ -661,36 +649,6 @@ void __init init_cpu_to_node(void) #endif -/* - * Allocate node_to_cpumask_map based on number of available nodes - * Requires node_possible_map to be valid. - * - * Note: node_to_cpumask() is not valid until after this is done. - * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.) - */ -void __init setup_node_to_cpumask_map(void) -{ - unsigned int node, num = 0; - cpumask_t *map; - - /* setup nr_node_ids if not done yet */ - if (nr_node_ids == MAX_NUMNODES) { - for_each_node_mask(node, node_possible_map) - num = node; - nr_node_ids = num + 1; - } - - /* allocate the map */ - map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t)); - DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids); - - pr_debug("Node to cpumask map at %p for %d nodes\n", - map, nr_node_ids); - - /* node_to_cpumask() will now work */ - node_to_cpumask_map = map; -} - void __cpuinit numa_set_node(int cpu, int node) { int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map); @@ -723,12 +681,12 @@ void __cpuinit numa_clear_node(int cpu) void __cpuinit numa_add_cpu(int cpu) { - cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); + cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } void __cpuinit numa_remove_cpu(int cpu) { - cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); + cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]); } #else /* CONFIG_DEBUG_PER_CPU_MAPS */ @@ -739,20 +697,20 @@ void __cpuinit numa_remove_cpu(int cpu) static void __cpuinit numa_set_cpumask(int cpu, int enable) { int node = early_cpu_to_node(cpu); - cpumask_t *mask; + struct cpumask *mask; char buf[64]; - if (node_to_cpumask_map == NULL) { - printk(KERN_ERR "node_to_cpumask_map NULL\n"); + mask = node_to_cpumask_map[node]; + if (mask == NULL) { + printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node); dump_stack(); return; } - mask = &node_to_cpumask_map[node]; if (enable) - cpu_set(cpu, *mask); + cpumask_set_cpu(cpu, mask); else - cpu_clear(cpu, *mask); + cpumask_clear_cpu(cpu, mask); cpulist_scnprintf(buf, sizeof(buf), mask); printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n", @@ -799,59 +757,6 @@ int early_cpu_to_node(int cpu) return per_cpu(x86_cpu_to_node_map, cpu); } - -/* empty cpumask */ -static const cpumask_t cpu_mask_none; - -/* - * Returns a pointer to the bitmask of CPUs on Node 'node'. - */ -const cpumask_t *cpumask_of_node(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "cpumask_of_node(%d): no node_to_cpumask_map!\n", - node); - dump_stack(); - return (const cpumask_t *)&cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "cpumask_of_node(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return &cpu_mask_none; - } - return &node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(cpumask_of_node); - -/* - * Returns a bitmask of CPUs on Node 'node'. - * - * Side note: this function creates the returned cpumask on the stack - * so with a high NR_CPUS count, excessive stack space is used. The - * node_to_cpumask_ptr function should be used whenever possible. - */ -cpumask_t node_to_cpumask(int node) -{ - if (node_to_cpumask_map == NULL) { - printk(KERN_WARNING - "node_to_cpumask(%d): no node_to_cpumask_map!\n", node); - dump_stack(); - return cpu_online_map; - } - if (node >= nr_node_ids) { - printk(KERN_WARNING - "node_to_cpumask(%d): node > nr_node_ids(%d)\n", - node, nr_node_ids); - dump_stack(); - return cpu_mask_none; - } - return node_to_cpumask_map[node]; -} -EXPORT_SYMBOL(node_to_cpumask); - /* * --------- end of debug versions of the numa functions --------- */ diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index d71e1b6..797f9f1 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -945,71 +945,94 @@ int _set_memory_uc(unsigned long addr, int numpages) int set_memory_uc(unsigned long addr, int numpages) { + int ret; + /* * for now UC MINUS. see comments in ioremap_nocache() */ - if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_UC_MINUS, NULL)) - return -EINVAL; + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_err; + + ret = _set_memory_uc(addr, numpages); + if (ret) + goto out_free; - return _set_memory_uc(addr, numpages); + return 0; + +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_uc); int set_memory_array_uc(unsigned long *addr, int addrinarray) { - unsigned long start; - unsigned long end; - int i; + int i, j; + int ret; + /* * for now UC MINUS. see comments in ioremap_nocache() */ for (i = 0; i < addrinarray; i++) { - start = __pa(addr[i]); - for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL)) - goto out; + ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE, + _PAGE_CACHE_UC_MINUS, NULL); + if (ret) + goto out_free; } - return change_page_attr_set(addr, addrinarray, + ret = change_page_attr_set(addr, addrinarray, __pgprot(_PAGE_CACHE_UC_MINUS), 1); -out: - for (i = 0; i < addrinarray; i++) { - unsigned long tmp = __pa(addr[i]); - - if (tmp == start) - break; - for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - free_memtype(tmp, end); - } - return -EINVAL; + if (ret) + goto out_free; + + return 0; + +out_free: + for (j = 0; j < i; j++) + free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE); + + return ret; } EXPORT_SYMBOL(set_memory_array_uc); int _set_memory_wc(unsigned long addr, int numpages) { - return change_page_attr_set(&addr, numpages, + int ret; + ret = change_page_attr_set(&addr, numpages, + __pgprot(_PAGE_CACHE_UC_MINUS), 0); + + if (!ret) { + ret = change_page_attr_set(&addr, numpages, __pgprot(_PAGE_CACHE_WC), 0); + } + return ret; } int set_memory_wc(unsigned long addr, int numpages) { + int ret; + if (!pat_enabled) return set_memory_uc(addr, numpages); - if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, - _PAGE_CACHE_WC, NULL)) - return -EINVAL; + ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, + _PAGE_CACHE_WC, NULL); + if (ret) + goto out_err; + + ret = _set_memory_wc(addr, numpages); + if (ret) + goto out_free; + + return 0; - return _set_memory_wc(addr, numpages); +out_free: + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); +out_err: + return ret; } EXPORT_SYMBOL(set_memory_wc); @@ -1021,29 +1044,31 @@ int _set_memory_wb(unsigned long addr, int numpages) int set_memory_wb(unsigned long addr, int numpages) { - free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + int ret; + + ret = _set_memory_wb(addr, numpages); + if (ret) + return ret; - return _set_memory_wb(addr, numpages); + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); + return 0; } EXPORT_SYMBOL(set_memory_wb); int set_memory_array_wb(unsigned long *addr, int addrinarray) { int i; + int ret; - for (i = 0; i < addrinarray; i++) { - unsigned long start = __pa(addr[i]); - unsigned long end; - - for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) { - if (end != __pa(addr[i + 1])) - break; - i++; - } - free_memtype(start, end); - } - return change_page_attr_clear(addr, addrinarray, + ret = change_page_attr_clear(addr, addrinarray, __pgprot(_PAGE_CACHE_MASK), 1); + if (ret) + return ret; + + for (i = 0; i < addrinarray; i++) + free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE); + + return 0; } EXPORT_SYMBOL(set_memory_array_wb); @@ -1136,6 +1161,8 @@ int set_pages_array_wb(struct page **pages, int addrinarray) retval = cpa_clear_pages_array(pages, addrinarray, __pgprot(_PAGE_CACHE_MASK)); + if (retval) + return retval; for (i = 0; i < addrinarray; i++) { start = (unsigned long)page_address(pages[i]); @@ -1143,7 +1170,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray) free_memtype(start, end); } - return retval; + return 0; } EXPORT_SYMBOL(set_pages_array_wb); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 640339e..e6718bb 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -31,7 +31,7 @@ #ifdef CONFIG_X86_PAT int __read_mostly pat_enabled = 1; -void __cpuinit pat_disable(const char *reason) +static inline void pat_disable(const char *reason) { pat_enabled = 0; printk(KERN_INFO "%s\n", reason); @@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type) u8 mtrr_type; mtrr_type = mtrr_type_lookup(start, end); - if (mtrr_type == MTRR_TYPE_UNCACHABLE) - return _PAGE_CACHE_UC; - if (mtrr_type == MTRR_TYPE_WRCOMB) - return _PAGE_CACHE_WC; + if (mtrr_type != MTRR_TYPE_WRBACK) + return _PAGE_CACHE_UC_MINUS; + + return _PAGE_CACHE_WB; } return req_type; @@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return 0; } - if (req_type == -1) { - /* - * Call mtrr_lookup to get the type hint. This is an - * optimization for /dev/mem mmap'ers into WB memory (BIOS - * tools and ACPI tools). Use WB request for WB memory and use - * UC_MINUS otherwise. - */ - u8 mtrr_type = mtrr_type_lookup(start, end); - - if (mtrr_type == MTRR_TYPE_WRBACK) - actual_type = _PAGE_CACHE_WB; - else - actual_type = _PAGE_CACHE_UC_MINUS; - } else { - actual_type = pat_x_mtrr_type(start, end, - req_type & _PAGE_CACHE_MASK); - } + /* + * Call mtrr_lookup to get the type hint. This is an + * optimization for /dev/mem mmap'ers into WB memory (BIOS + * tools and ACPI tools). Use WB request for WB memory and use + * UC_MINUS otherwise. + */ + actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK); if (new_type) *new_type = actual_type; @@ -546,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { - u64 offset = ((u64) pfn) << PAGE_SHIFT; - unsigned long flags = -1; - int retval; + unsigned long flags = _PAGE_CACHE_WB; if (!range_is_allowed(pfn, size)) return 0; @@ -576,64 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, } #endif - /* - * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot. - * - * Without O_SYNC, we want to get - * - 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 - */ - if (flags != -1) { - retval = reserve_memtype(offset, offset + size, flags, NULL); - } else { - retval = reserve_memtype(offset, offset + size, -1, &flags); - } - - if (retval < 0) - return 0; - - if (((pfn < max_low_pfn_mapped) || - (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { - free_memtype(offset, offset + size); - printk(KERN_INFO - "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", - current->comm, current->pid, - cattr_name(flags), - offset, (unsigned long long)(offset + size)); - return 0; - } - *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) | flags); return 1; } -void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK); - u64 addr = (u64)pfn << PAGE_SHIFT; - unsigned long flags; - - reserve_memtype(addr, addr + size, want_flags, &flags); - if (flags != want_flags) { - printk(KERN_INFO - "%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n", - current->comm, current->pid, - cattr_name(want_flags), - addr, (unsigned long long)(addr + size), - cattr_name(flags)); - } -} - -void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot) -{ - u64 addr = (u64)pfn << PAGE_SHIFT; - - free_memtype(addr, addr + size); -} - /* * Change the memory type for the physial address range in kernel identity * mapping space if that range is a part of identity map. @@ -671,8 +606,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, { int is_ram = 0; int ret; - unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); + unsigned long flags = want_flags; is_ram = pat_pagerange_is_ram(paddr, paddr + size); @@ -734,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size) * * If the vma has a linear pfn mapping for the entire range, we get the prot * from pte and reserve the entire vma range with single reserve_pfn_range call. - * Otherwise, we reserve the entire vma range, my ging through the PTEs page - * by page to get physical address and protection. */ int track_pfn_vma_copy(struct vm_area_struct *vma) { - int retval = 0; - unsigned long i, j; resource_size_t paddr; unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* * reserve the whole chunk covered by vma. We need the * starting address and protection from pte. */ - if (follow_phys(vma, vma_start, 0, &prot, &paddr)) { + if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { WARN_ON_ONCE(1); return -EINVAL; } @@ -764,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma) return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } - /* reserve entire vma page by page, using pfn and prot from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - pgprot = __pgprot(prot); - retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - if (follow_phys(vma, vma_start + j, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -795,50 +708,28 @@ cleanup_ret: * prot is passed in as a parameter for the new mapping. If the vma has a * linear pfn mapping for the entire range reserve the entire vma range with * single reserve_pfn_range call. - * Otherwise, we look t the pfn and size and reserve only the specified range - * page by page. - * - * Note that this function can be called with caller trying to map only a - * subrange/page inside the vma. */ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot, unsigned long pfn, unsigned long size) { - int retval = 0; - unsigned long i, j; - resource_size_t base_paddr; resource_size_t paddr; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return 0; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* reserve the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; return reserve_pfn_range(paddr, vma_size, prot, 0); } - /* reserve page by page using pfn and size */ - base_paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = base_paddr + i; - retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0); - if (retval) - goto cleanup_ret; - } return 0; - -cleanup_ret: - /* Reserve error: Cleanup partial reservation and return error */ - for (j = 0; j < i; j += PAGE_SIZE) { - paddr = base_paddr + j; - free_pfn_range(paddr, PAGE_SIZE); - } - - return retval; } /* @@ -849,39 +740,23 @@ cleanup_ret: void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn, unsigned long size) { - unsigned long i; resource_size_t paddr; - unsigned long prot; - unsigned long vma_start = vma->vm_start; - unsigned long vma_end = vma->vm_end; - unsigned long vma_size = vma_end - vma_start; + unsigned long vma_size = vma->vm_end - vma->vm_start; if (!pat_enabled) return; + /* + * For now, only handle remap_pfn_range() vmas where + * is_linear_pfn_mapping() == TRUE. Handling of + * vm_insert_pfn() is TBD. + */ if (is_linear_pfn_mapping(vma)) { /* free the whole chunk starting from vm_pgoff */ paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; free_pfn_range(paddr, vma_size); return; } - - if (size != 0 && size != vma_size) { - /* free page by page, using pfn and size */ - paddr = (resource_size_t)pfn << PAGE_SHIFT; - for (i = 0; i < size; i += PAGE_SIZE) { - paddr = paddr + i; - free_pfn_range(paddr, PAGE_SIZE); - } - } else { - /* free entire vma, page by page, using the pfn from pte */ - for (i = 0; i < vma_size; i += PAGE_SIZE) { - if (follow_phys(vma, vma_start + i, 0, &prot, &paddr)) - continue; - - free_pfn_range(paddr, PAGE_SIZE); - } - } } pgprot_t pgprot_writecombine(pgprot_t prot) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 5b7c7c84..7aa03a5 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -345,7 +345,8 @@ void __native_set_fixmap(enum fixed_addresses idx, pte_t pte) fixmaps_set++; } -void native_set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t flags) +void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, + pgprot_t flags) { __native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags)); } diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 574c8bc..c7d272b 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -116,6 +116,36 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) reserve_early(phys, phys + length, "ACPI SLIT"); } +/* Callback for Proximity Domain -> x2APIC mapping */ +void __init +acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa) +{ + int pxm, node; + int apic_id; + + if (srat_disabled()) + return; + if (pa->header.length < sizeof(struct acpi_srat_x2apic_cpu_affinity)) { + bad_srat(); + return; + } + if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0) + return; + pxm = pa->proximity_domain; + node = setup_node(pxm); + if (node < 0) { + printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm); + bad_srat(); + return; + } + + apic_id = pa->apic_id; + apicid_to_node[apic_id] = node; + acpi_numa = 1; + printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", + pxm, apic_id, node); +} + /* Callback for Proximity Domain -> LAPIC mapping */ void __init acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c index 4c4a51c..819b131 100644 --- a/arch/x86/oprofile/op_model_p4.c +++ b/arch/x86/oprofile/op_model_p4.c @@ -380,7 +380,7 @@ static unsigned int get_stagger(void) { #ifdef CONFIG_SMP int cpu = smp_processor_id(); - return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu))); + return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map)); #endif return 0; } diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c index f6adf2c..aaf26ae 100644 --- a/arch/x86/pci/early.c +++ b/arch/x86/pci/early.c @@ -69,11 +69,12 @@ void early_dump_pci_device(u8 bus, u8 slot, u8 func) int j; u32 val; - printk(KERN_INFO "PCI: %02x:%02x:%02x", bus, slot, func); + printk(KERN_INFO "pci 0000:%02x:%02x.%d config space:", + bus, slot, func); for (i = 0; i < 256; i += 4) { if (!(i & 0x0f)) - printk("\n%04x:",i); + printk("\n %02x:",i); val = read_pci_config(bus, slot, func, i); for (j = 0; j < 4; j++) { @@ -96,20 +97,22 @@ void early_dump_pci_devices(void) for (func = 0; func < 8; func++) { u32 class; u8 type; + class = read_pci_config(bus, slot, func, PCI_CLASS_REVISION); if (class == 0xffffffff) - break; + continue; early_dump_pci_device(bus, slot, func); - /* No multi-function device? */ - type = read_pci_config_byte(bus, slot, func, + if (func == 0) { + type = read_pci_config_byte(bus, slot, + func, PCI_HEADER_TYPE); - if (!(type & 0x80)) - break; + if (!(type & 0x80)) + break; + } } } } } - diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 9c49919..6dd8955 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -495,26 +495,6 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SIEMENS, 0x0015, pci_siemens_interrupt_controller); /* - * Regular PCI devices have 256 bytes, but AMD Family 10h/11h CPUs have - * 4096 bytes configuration space for each function of their processor - * configuration space. - */ -static void amd_cpu_pci_cfg_space_size(struct pci_dev *dev) -{ - dev->cfg_size = pci_cfg_space_size_ext(dev); -} -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1200, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1201, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1202, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1203, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1204, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1300, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1301, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1302, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1303, amd_cpu_pci_cfg_space_size); -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, 0x1304, amd_cpu_pci_cfg_space_size); - -/* * SB600: Disable BAR1 on device 14.0 to avoid HPET resources from * confusing the PCI engine: */ diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index f234a37..f1817f7 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -258,24 +258,7 @@ void pcibios_set_master(struct pci_dev *dev) pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); } -static void pci_unmap_page_range(struct vm_area_struct *vma) -{ - u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; - free_memtype(addr, addr + vma->vm_end - vma->vm_start); -} - -static void pci_track_mmap_page_range(struct vm_area_struct *vma) -{ - u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT; - unsigned long flags = pgprot_val(vma->vm_page_prot) - & _PAGE_CACHE_MASK; - - reserve_memtype(addr, addr + vma->vm_end - vma->vm_start, flags, NULL); -} - static struct vm_operations_struct pci_mmap_ops = { - .open = pci_track_mmap_page_range, - .close = pci_unmap_page_range, .access = generic_access_phys, }; @@ -283,11 +266,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine) { unsigned long prot; - u64 addr = vma->vm_pgoff << PAGE_SHIFT; - unsigned long len = vma->vm_end - vma->vm_start; - unsigned long flags; - unsigned long new_flags; - int retval; /* I/O space cannot be accessed via normal processor loads and * stores on this platform. @@ -308,30 +286,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, vma->vm_page_prot = __pgprot(prot); - flags = pgprot_val(vma->vm_page_prot) & _PAGE_CACHE_MASK; - retval = reserve_memtype(addr, addr + len, flags, &new_flags); - if (retval) - return retval; - - if (flags != new_flags) { - if (!is_new_memtype_allowed(flags, new_flags)) { - free_memtype(addr, addr+len); - return -EINVAL; - } - flags = new_flags; - vma->vm_page_prot = __pgprot( - (pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK) | - flags); - } - - if (((vma->vm_pgoff < max_low_pfn_mapped) || - (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) && - vma->vm_pgoff < max_pfn_mapped)) && - ioremap_change_attr((unsigned long)__va(addr), len, flags)) { - free_memtype(addr, addr + len); - return -EINVAL; - } - if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, vma->vm_end - vma->vm_start, vma->vm_page_prot)) diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index f1065b1..4061bb0 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -50,8 +50,6 @@ static int __init pci_legacy_init(void) if (pci_root_bus) pci_bus_add_devices(pci_root_bus); - pcibios_fixup_peer_bridges(); - return 0; } @@ -67,6 +65,7 @@ int __init pci_subsys_init(void) pci_visws_init(); #endif pci_legacy_init(); + pcibios_fixup_peer_bridges(); pcibios_irq_init(); pcibios_init(); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 89bf924..905bb52 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/acpi.h> #include <linux/bitmap.h> +#include <linux/sort.h> #include <asm/e820.h> #include <asm/pci_x86.h> @@ -24,24 +25,49 @@ /* Indicate if the mmcfg resources have been placed into the resource table. */ static int __initdata pci_mmcfg_resources_inserted; +static __init int extend_mmcfg(int num) +{ + struct acpi_mcfg_allocation *new; + int new_num = pci_mmcfg_config_num + num; + + new = kzalloc(sizeof(pci_mmcfg_config[0]) * new_num, GFP_KERNEL); + if (!new) + return -1; + + if (pci_mmcfg_config) { + memcpy(new, pci_mmcfg_config, + sizeof(pci_mmcfg_config[0]) * new_num); + kfree(pci_mmcfg_config); + } + pci_mmcfg_config = new; + + return 0; +} + +static __init void fill_one_mmcfg(u64 addr, int segment, int start, int end) +{ + int i = pci_mmcfg_config_num; + + pci_mmcfg_config_num++; + pci_mmcfg_config[i].address = addr; + pci_mmcfg_config[i].pci_segment = segment; + pci_mmcfg_config[i].start_bus_number = start; + pci_mmcfg_config[i].end_bus_number = end; +} + static const char __init *pci_mmcfg_e7520(void) { u32 win; raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win); win = win & 0xf000; - if(win == 0x0000 || win == 0xf000) - pci_mmcfg_config_num = 0; - else { - pci_mmcfg_config_num = 1; - pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL); - if (!pci_mmcfg_config) - return NULL; - pci_mmcfg_config[0].address = win << 16; - pci_mmcfg_config[0].pci_segment = 0; - pci_mmcfg_config[0].start_bus_number = 0; - pci_mmcfg_config[0].end_bus_number = 255; - } + if (win == 0x0000 || win == 0xf000) + return NULL; + + if (extend_mmcfg(1) == -1) + return NULL; + + fill_one_mmcfg(win << 16, 0, 0, 255); return "Intel Corporation E7520 Memory Controller Hub"; } @@ -50,13 +76,11 @@ static const char __init *pci_mmcfg_intel_945(void) { u32 pciexbar, mask = 0, len = 0; - pci_mmcfg_config_num = 1; - raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0x48, 4, &pciexbar); /* Enable bit */ if (!(pciexbar & 1)) - pci_mmcfg_config_num = 0; + return NULL; /* Size bits */ switch ((pciexbar >> 1) & 3) { @@ -73,28 +97,23 @@ static const char __init *pci_mmcfg_intel_945(void) len = 0x04000000U; break; default: - pci_mmcfg_config_num = 0; + return NULL; } /* Errata #2, things break when not aligned on a 256Mb boundary */ /* Can only happen in 64M/128M mode */ if ((pciexbar & mask) & 0x0fffffffU) - pci_mmcfg_config_num = 0; + return NULL; /* Don't hit the APIC registers and their friends */ if ((pciexbar & mask) >= 0xf0000000U) - pci_mmcfg_config_num = 0; - - if (pci_mmcfg_config_num) { - pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]), GFP_KERNEL); - if (!pci_mmcfg_config) - return NULL; - pci_mmcfg_config[0].address = pciexbar & mask; - pci_mmcfg_config[0].pci_segment = 0; - pci_mmcfg_config[0].start_bus_number = 0; - pci_mmcfg_config[0].end_bus_number = (len >> 20) - 1; - } + return NULL; + + if (extend_mmcfg(1) == -1) + return NULL; + + fill_one_mmcfg(pciexbar & mask, 0, 0, (len >> 20) - 1); return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub"; } @@ -138,22 +157,77 @@ static const char __init *pci_mmcfg_amd_fam10h(void) busnbits = 8; } - pci_mmcfg_config_num = (1 << segnbits); - pci_mmcfg_config = kzalloc(sizeof(pci_mmcfg_config[0]) * - pci_mmcfg_config_num, GFP_KERNEL); - if (!pci_mmcfg_config) + if (extend_mmcfg(1 << segnbits) == -1) return NULL; - for (i = 0; i < (1 << segnbits); i++) { - pci_mmcfg_config[i].address = base + (1<<28) * i; - pci_mmcfg_config[i].pci_segment = i; - pci_mmcfg_config[i].start_bus_number = 0; - pci_mmcfg_config[i].end_bus_number = (1 << busnbits) - 1; - } + for (i = 0; i < (1 << segnbits); i++) + fill_one_mmcfg(base + (1<<28) * i, i, 0, (1 << busnbits) - 1); return "AMD Family 10h NB"; } +static bool __initdata mcp55_checked; +static const char __init *pci_mmcfg_nvidia_mcp55(void) +{ + int bus; + int mcp55_mmconf_found = 0; + + static const u32 extcfg_regnum = 0x90; + static const u32 extcfg_regsize = 4; + static const u32 extcfg_enable_mask = 1<<31; + static const u32 extcfg_start_mask = 0xff<<16; + static const int extcfg_start_shift = 16; + static const u32 extcfg_size_mask = 0x3<<28; + static const int extcfg_size_shift = 28; + static const int extcfg_sizebus[] = {0x100, 0x80, 0x40, 0x20}; + static const u32 extcfg_base_mask[] = {0x7ff8, 0x7ffc, 0x7ffe, 0x7fff}; + static const int extcfg_base_lshift = 25; + + /* + * do check if amd fam10h already took over + */ + if (!acpi_disabled || pci_mmcfg_config_num || mcp55_checked) + return NULL; + + mcp55_checked = true; + for (bus = 0; bus < 256; bus++) { + u64 base; + u32 l, extcfg; + u16 vendor, device; + int start, size_index, end; + + raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), 0, 4, &l); + vendor = l & 0xffff; + device = (l >> 16) & 0xffff; + + if (PCI_VENDOR_ID_NVIDIA != vendor || 0x0369 != device) + continue; + + raw_pci_ops->read(0, bus, PCI_DEVFN(0, 0), extcfg_regnum, + extcfg_regsize, &extcfg); + + if (!(extcfg & extcfg_enable_mask)) + continue; + + if (extend_mmcfg(1) == -1) + continue; + + size_index = (extcfg & extcfg_size_mask) >> extcfg_size_shift; + base = extcfg & extcfg_base_mask[size_index]; + /* base could > 4G */ + base <<= extcfg_base_lshift; + start = (extcfg & extcfg_start_mask) >> extcfg_start_shift; + end = start + extcfg_sizebus[size_index] - 1; + fill_one_mmcfg(base, 0, start, end); + mcp55_mmconf_found++; + } + + if (!mcp55_mmconf_found) + return NULL; + + return "nVidia MCP55"; +} + struct pci_mmcfg_hostbridge_probe { u32 bus; u32 devfn; @@ -171,8 +245,52 @@ static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = { 0x1200, pci_mmcfg_amd_fam10h }, { 0xff, PCI_DEVFN(0, 0), PCI_VENDOR_ID_AMD, 0x1200, pci_mmcfg_amd_fam10h }, + { 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_NVIDIA, + 0x0369, pci_mmcfg_nvidia_mcp55 }, }; +static int __init cmp_mmcfg(const void *x1, const void *x2) +{ + const typeof(pci_mmcfg_config[0]) *m1 = x1; + const typeof(pci_mmcfg_config[0]) *m2 = x2; + int start1, start2; + + start1 = m1->start_bus_number; + start2 = m2->start_bus_number; + + return start1 - start2; +} + +static void __init pci_mmcfg_check_end_bus_number(void) +{ + int i; + typeof(pci_mmcfg_config[0]) *cfg, *cfgx; + + /* sort them at first */ + sort(pci_mmcfg_config, pci_mmcfg_config_num, + sizeof(pci_mmcfg_config[0]), cmp_mmcfg, NULL); + + /* last one*/ + if (pci_mmcfg_config_num > 0) { + i = pci_mmcfg_config_num - 1; + cfg = &pci_mmcfg_config[i]; + if (cfg->end_bus_number < cfg->start_bus_number) + cfg->end_bus_number = 255; + } + + /* don't overlap please */ + for (i = 0; i < pci_mmcfg_config_num - 1; i++) { + cfg = &pci_mmcfg_config[i]; + cfgx = &pci_mmcfg_config[i+1]; + + if (cfg->end_bus_number < cfg->start_bus_number) + cfg->end_bus_number = 255; + + if (cfg->end_bus_number >= cfgx->start_bus_number) + cfg->end_bus_number = cfgx->start_bus_number - 1; + } +} + static int __init pci_mmcfg_check_hostbridge(void) { u32 l; @@ -186,31 +304,33 @@ static int __init pci_mmcfg_check_hostbridge(void) pci_mmcfg_config_num = 0; pci_mmcfg_config = NULL; - name = NULL; - for (i = 0; !name && i < ARRAY_SIZE(pci_mmcfg_probes); i++) { + for (i = 0; i < ARRAY_SIZE(pci_mmcfg_probes); i++) { bus = pci_mmcfg_probes[i].bus; devfn = pci_mmcfg_probes[i].devfn; raw_pci_ops->read(0, bus, devfn, 0, 4, &l); vendor = l & 0xffff; device = (l >> 16) & 0xffff; + name = NULL; if (pci_mmcfg_probes[i].vendor == vendor && pci_mmcfg_probes[i].device == device) name = pci_mmcfg_probes[i].probe(); - } - if (name) { - printk(KERN_INFO "PCI: Found %s %s MMCONFIG support.\n", - name, pci_mmcfg_config_num ? "with" : "without"); + if (name) + printk(KERN_INFO "PCI: Found %s with MMCONFIG support.\n", + name); } - return name != NULL; + /* some end_bus_number is crazy, fix it */ + pci_mmcfg_check_end_bus_number(); + + return pci_mmcfg_config_num != 0; } static void __init pci_mmcfg_insert_resources(void) { -#define PCI_MMCFG_RESOURCE_NAME_LEN 19 +#define PCI_MMCFG_RESOURCE_NAME_LEN 24 int i; struct resource *res; char *names; @@ -228,9 +348,10 @@ static void __init pci_mmcfg_insert_resources(void) struct acpi_mcfg_allocation *cfg = &pci_mmcfg_config[i]; num_buses = cfg->end_bus_number - cfg->start_bus_number + 1; res->name = names; - snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, "PCI MMCONFIG %u", - cfg->pci_segment); - res->start = cfg->address; + snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, + "PCI MMCONFIG %u [%02x-%02x]", cfg->pci_segment, + cfg->start_bus_number, cfg->end_bus_number); + res->start = cfg->address + (cfg->start_bus_number << 20); res->end = res->start + (num_buses << 20) - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; insert_resource(&iomem_resource, res); @@ -354,8 +475,6 @@ static void __init pci_mmcfg_reject_broken(int early) (pci_mmcfg_config[0].address == 0)) return; - cfg = &pci_mmcfg_config[0]; - for (i = 0; i < pci_mmcfg_config_num; i++) { int valid = 0; u64 addr, size; @@ -423,10 +542,10 @@ static void __init __pci_mmcfg_init(int early) known_bridge = 1; } - if (!known_bridge) { + if (!known_bridge) acpi_table_parse(ACPI_SIG_MCFG, acpi_parse_mcfg); - pci_mmcfg_reject_broken(early); - } + + pci_mmcfg_reject_broken(early); if ((pci_mmcfg_config_num == 0) || (pci_mmcfg_config == NULL) || diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 30007ff..94349f8 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -112,13 +112,18 @@ static struct pci_raw_ops pci_mmcfg = { static void __iomem * __init mcfg_ioremap(struct acpi_mcfg_allocation *cfg) { void __iomem *addr; - u32 size; - - size = (cfg->end_bus_number + 1) << 20; - addr = ioremap_nocache(cfg->address, size); + u64 start, size; + + start = cfg->start_bus_number; + start <<= 20; + start += cfg->address; + size = cfg->end_bus_number + 1 - cfg->start_bus_number; + size <<= 20; + addr = ioremap_nocache(start, size); if (addr) { printk(KERN_INFO "PCI: Using MMCONFIG at %Lx - %Lx\n", - cfg->address, cfg->address + size - 1); + start, start + size - 1); + addr -= cfg->start_bus_number << 20; } return addr; } @@ -157,7 +162,7 @@ void __init pci_mmcfg_arch_free(void) for (i = 0; i < pci_mmcfg_config_num; ++i) { if (pci_mmcfg_virt[i].virt) { - iounmap(pci_mmcfg_virt[i].virt); + iounmap(pci_mmcfg_virt[i].virt + (pci_mmcfg_virt[i].cfg->start_bus_number << 20)); pci_mmcfg_virt[i].virt = NULL; pci_mmcfg_virt[i].cfg = NULL; } diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 9ff4d5b..58b32db 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -1,2 +1,7 @@ +# __restore_processor_state() restores %gs after S3 resume and so should not +# itself be stack-protected +nostackp := $(call cc-option, -fno-stack-protector) +CFLAGS_cpu_$(BITS).o := $(nostackp) + obj-$(CONFIG_PM_SLEEP) += cpu_$(BITS).o obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c index 274d060..ce702c5 100644 --- a/arch/x86/power/cpu_32.c +++ b/arch/x86/power/cpu_32.c @@ -12,6 +12,7 @@ #include <asm/mtrr.h> #include <asm/mce.h> #include <asm/xcr.h> +#include <asm/suspend.h> static struct saved_context saved_context; diff --git a/arch/x86/power/cpu_64.c b/arch/x86/power/cpu_64.c index e3b6cf7..5343540 100644 --- a/arch/x86/power/cpu_64.c +++ b/arch/x86/power/cpu_64.c @@ -15,6 +15,7 @@ #include <asm/pgtable.h> #include <asm/mtrr.h> #include <asm/xcr.h> +#include <asm/suspend.h> static void fix_processor_context(void); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 6dd000d..65fdc86 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -14,6 +14,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/mtrr.h> +#include <asm/suspend.h> /* References to section boundaries */ extern const void __nosave_begin, __nosave_end; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 82cd39a..f09e8c3 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -42,6 +42,7 @@ #include <asm/xen/hypervisor.h> #include <asm/fixmap.h> #include <asm/processor.h> +#include <asm/proto.h> #include <asm/msr-index.h> #include <asm/setup.h> #include <asm/desc.h> @@ -168,21 +169,23 @@ static void __init xen_banner(void) xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); } +static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0; +static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0; + static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { + unsigned maskecx = ~0; unsigned maskedx = ~0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. */ - if (*ax == 1) - maskedx = ~((1 << X86_FEATURE_APIC) | /* disable APIC */ - (1 << X86_FEATURE_ACPI) | /* disable ACPI */ - (1 << X86_FEATURE_MCE) | /* disable MCE */ - (1 << X86_FEATURE_MCA) | /* disable MCA */ - (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + if (*ax == 1) { + maskecx = cpuid_leaf1_ecx_mask; + maskedx = cpuid_leaf1_edx_mask; + } asm(XEN_EMULATE_PREFIX "cpuid" : "=a" (*ax), @@ -190,9 +193,43 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, "=c" (*cx), "=d" (*dx) : "0" (*ax), "2" (*cx)); + + *cx &= maskecx; *dx &= maskedx; } +static __init void xen_init_cpuid_mask(void) +{ + unsigned int ax, bx, cx, dx; + + cpuid_leaf1_edx_mask = + ~((1 << X86_FEATURE_MCE) | /* disable MCE */ + (1 << X86_FEATURE_MCA) | /* disable MCA */ + (1 << X86_FEATURE_ACC)); /* thermal monitoring */ + + if (!xen_initial_domain()) + cpuid_leaf1_edx_mask &= + ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ + (1 << X86_FEATURE_ACPI)); /* disable ACPI */ + + ax = 1; + xen_cpuid(&ax, &bx, &cx, &dx); + + /* cpuid claims we support xsave; try enabling it to see what happens */ + if (cx & (1 << (X86_FEATURE_XSAVE % 32))) { + unsigned long cr4; + + set_in_cr4(X86_CR4_OSXSAVE); + + cr4 = read_cr4(); + + if ((cr4 & X86_CR4_OSXSAVE) == 0) + cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32)); + + clear_in_cr4(X86_CR4_OSXSAVE); + } +} + static void xen_set_debugreg(int reg, unsigned long val) { HYPERVISOR_set_debugreg(reg, val); @@ -284,12 +321,11 @@ static void xen_set_ldt(const void *addr, unsigned entries) static void xen_load_gdt(const struct desc_ptr *dtr) { - unsigned long *frames; unsigned long va = dtr->address; unsigned int size = dtr->size + 1; unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE; + unsigned long frames[pages]; int f; - struct multicall_space mcs; /* A GDT can be up to 64k in size, which corresponds to 8192 8-byte entries, or 16 4k pages.. */ @@ -297,19 +333,26 @@ static void xen_load_gdt(const struct desc_ptr *dtr) BUG_ON(size > 65536); BUG_ON(va & ~PAGE_MASK); - mcs = xen_mc_entry(sizeof(*frames) * pages); - frames = mcs.args; - for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) { - frames[f] = arbitrary_virt_to_mfn((void *)va); + int level; + pte_t *ptep = lookup_address(va, &level); + unsigned long pfn, mfn; + void *virt; + + BUG_ON(ptep == NULL); + + pfn = pte_pfn(*ptep); + mfn = pfn_to_mfn(pfn); + virt = __va(PFN_PHYS(pfn)); + + frames[f] = mfn; make_lowmem_page_readonly((void *)va); - make_lowmem_page_readonly(mfn_to_virt(frames[f])); + make_lowmem_page_readonly(virt); } - MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct)); - - xen_mc_issue(PARAVIRT_LAZY_CPU); + if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct))) + BUG(); } static void load_TLS_descriptor(struct thread_struct *t, @@ -385,7 +428,7 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) { - if (val->type != 0xf && val->type != 0xe) + if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT) return 0; info->vector = vector; @@ -393,8 +436,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, info->cs = gate_segment(*val); info->flags = val->dpl; /* interrupt gates clear IF */ - if (val->type == 0xe) - info->flags |= 4; + if (val->type == GATE_INTERRUPT) + info->flags |= 1 << 2; return 1; } @@ -872,7 +915,6 @@ static const struct machine_ops __initdata xen_machine_ops = { .emergency_restart = xen_emergency_restart, }; - /* First C function to be called on Xen boot */ asmlinkage void __init xen_start_kernel(void) { @@ -897,6 +939,8 @@ asmlinkage void __init xen_start_kernel(void) xen_init_irq_ops(); + xen_init_cpuid_mask(); + #ifdef CONFIG_X86_LOCAL_APIC /* * set up the basic apic ops. @@ -938,6 +982,11 @@ asmlinkage void __init xen_start_kernel(void) if (!xen_initial_domain()) __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD); +#ifdef CONFIG_X86_64 + /* Work out if we support NX */ + check_efer(); +#endif + /* Don't do the full vcpu_info placement stuff until we have a possible map and a non-dummy shared_info. */ per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0]; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index db3802f..9842b12 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -184,7 +184,7 @@ static inline unsigned p2m_index(unsigned long pfn) } /* Build the parallel p2m_top_mfn structures */ -void xen_setup_mfn_list_list(void) +static void __init xen_build_mfn_list_list(void) { unsigned pfn, idx; @@ -198,7 +198,10 @@ void xen_setup_mfn_list_list(void) unsigned topidx = idx * P2M_ENTRIES_PER_PAGE; p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]); } +} +void xen_setup_mfn_list_list(void) +{ BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = @@ -218,6 +221,8 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_top[topidx] = &mfn_list[pfn]; } + + xen_build_mfn_list_list(); } unsigned long get_phys_to_machine(unsigned long pfn) @@ -233,47 +238,74 @@ unsigned long get_phys_to_machine(unsigned long pfn) } EXPORT_SYMBOL_GPL(get_phys_to_machine); -static void alloc_p2m(unsigned long **pp, unsigned long *mfnp) +/* install a new p2m_top page */ +bool install_p2mtop_page(unsigned long pfn, unsigned long *p) { - unsigned long *p; + unsigned topidx = p2m_top_index(pfn); + unsigned long **pfnp, *mfnp; unsigned i; - p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); - BUG_ON(p == NULL); + pfnp = &p2m_top[topidx]; + mfnp = &p2m_top_mfn[topidx]; for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++) p[i] = INVALID_P2M_ENTRY; - if (cmpxchg(pp, p2m_missing, p) != p2m_missing) - free_page((unsigned long)p); - else + if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) { *mfnp = virt_to_mfn(p); + return true; + } + + return false; } -void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +static void alloc_p2m(unsigned long pfn) { - unsigned topidx, idx; + unsigned long *p; - if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { - BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); - return; - } + p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL); + BUG_ON(p == NULL); + + if (!install_p2mtop_page(pfn, p)) + free_page((unsigned long)p); +} + +/* Try to install p2m mapping; fail if intermediate bits missing */ +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + unsigned topidx, idx; if (unlikely(pfn >= MAX_DOMAIN_PAGES)) { BUG_ON(mfn != INVALID_P2M_ENTRY); - return; + return true; } topidx = p2m_top_index(pfn); if (p2m_top[topidx] == p2m_missing) { - /* no need to allocate a page to store an invalid entry */ if (mfn == INVALID_P2M_ENTRY) - return; - alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]); + return true; + return false; } idx = p2m_index(pfn); p2m_top[topidx][idx] = mfn; + + return true; +} + +void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) { + BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY); + return; + } + + if (unlikely(!__set_phys_to_machine(pfn, mfn))) { + alloc_p2m(pfn); + + if (!__set_phys_to_machine(pfn, mfn)) + BUG(); + } } unsigned long arbitrary_virt_to_mfn(void *vaddr) @@ -987,7 +1019,7 @@ static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page, return 0; } -void __init xen_mark_init_mm_pinned(void) +static void __init xen_mark_init_mm_pinned(void) { xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1270,8 +1302,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, } *args; struct multicall_space mcs; - BUG_ON(cpumask_empty(cpus)); - BUG_ON(!mm); + if (cpumask_empty(cpus)) + return; /* nothing to do */ mcs = xen_mc_entry(sizeof(*args)); args = mcs.args; @@ -1438,6 +1470,15 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) } #endif +static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +{ + struct mmuext_op op; + op.cmd = cmd; + op.arg1.mfn = pfn_to_mfn(pfn); + if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) + BUG(); +} + /* Early in boot, while setting up the initial pagetable, assume everything is pinned. */ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) @@ -1446,22 +1487,29 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn) BUG_ON(mem_map); /* should only be used early */ #endif make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); + pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); +} + +/* Used for pmd and pud */ +static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn) +{ +#ifdef CONFIG_FLATMEM + BUG_ON(mem_map); /* should only be used early */ +#endif + make_lowmem_page_readonly(__va(PFN_PHYS(pfn))); } /* Early release_pte assumes that all pts are pinned, since there's only init_mm and anything attached to that is pinned. */ -static void xen_release_pte_init(unsigned long pfn) +static __init void xen_release_pte_init(unsigned long pfn) { + pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } -static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) +static __init void xen_release_pmd_init(unsigned long pfn) { - struct mmuext_op op; - op.cmd = cmd; - op.arg1.mfn = pfn_to_mfn(pfn); - if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF)) - BUG(); + make_lowmem_page_readwrite(__va(PFN_PHYS(pfn))); } /* This needs to make sure the new pte page is pinned iff its being @@ -1750,7 +1798,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, } #endif /* CONFIG_X86_64 */ -static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) +static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) { pte_t pte; @@ -1773,6 +1821,9 @@ static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot) #ifdef CONFIG_X86_LOCAL_APIC case FIX_APIC_BASE: /* maps dummy local APIC */ #endif + case FIX_TEXT_POKE0: + case FIX_TEXT_POKE1: + /* All local page mappings */ pte = pfn_pte(phys, prot); break; @@ -1819,7 +1870,6 @@ __init void xen_post_allocator_init(void) xen_mark_init_mm_pinned(); } - const struct pv_mmu_ops xen_mmu_ops __initdata = { .pagetable_setup_start = xen_pagetable_setup_start, .pagetable_setup_done = xen_pagetable_setup_done, @@ -1843,9 +1893,9 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .alloc_pte = xen_alloc_pte_init, .release_pte = xen_release_pte_init, - .alloc_pmd = xen_alloc_pte_init, + .alloc_pmd = xen_alloc_pmd_init, .alloc_pmd_clone = paravirt_nop, - .release_pmd = xen_release_pte_init, + .release_pmd = xen_release_pmd_init, #ifdef CONFIG_HIGHPTE .kmap_atomic_pte = xen_kmap_atomic_pte, @@ -1883,8 +1933,8 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = { .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_pgd = xen_set_pgd_hyper, - .alloc_pud = xen_alloc_pte_init, - .release_pud = xen_release_pte_init, + .alloc_pud = xen_alloc_pmd_init, + .release_pud = xen_release_pmd_init, #endif /* PAGETABLE_LEVELS == 4 */ .activate_mm = xen_activate_mm, diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h index 24d1b44..da73026 100644 --- a/arch/x86/xen/mmu.h +++ b/arch/x86/xen/mmu.h @@ -11,6 +11,9 @@ enum pt_level { }; +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool install_p2mtop_page(unsigned long pfn, unsigned long *p); + void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 8d47056..429834e 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -158,7 +158,7 @@ static void __init xen_fill_possible_map(void) rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); if (rc >= 0) { num_processors++; - cpu_set(i, cpu_possible_map); + set_cpu_possible(i, true); } } } @@ -197,7 +197,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) { for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--) continue; - cpu_clear(cpu, cpu_possible_map); + set_cpu_possible(cpu, false); } for_each_possible_cpu (cpu) { @@ -210,7 +210,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus) if (IS_ERR(idle)) panic("failed fork for CPU %d", cpu); - cpu_set(cpu, cpu_present_map); + set_cpu_present(cpu, true); } } @@ -317,7 +317,7 @@ static int __cpuinit xen_cpu_up(unsigned int cpu) BUG_ON(rc); while(per_cpu(cpu_state, cpu) != CPU_ONLINE) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); barrier(); } @@ -422,7 +422,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask) /* Make sure other vcpus get a chance to run if they need to. */ for_each_cpu(cpu, mask) { if (xen_vcpu_stolen(cpu)) { - HYPERVISOR_sched_op(SCHEDOP_yield, 0); + HYPERVISOR_sched_op(SCHEDOP_yield, NULL); break; } } diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 2f5ef26..2013946 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -57,8 +57,6 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id); bool xen_vcpu_stolen(int vcpu); -void xen_mark_init_mm_pinned(void); - void xen_setup_vcpu_info_placement(void); #ifdef CONFIG_SMP |
