diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 07:57:32 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 07:57:32 -0700 |
| commit | c7208de304ac335d5d58db346bb773a471fc636b (patch) | |
| tree | 47808484fc3ff8447fe30943a33880bae00d5fee | |
| parent | Merge branch 'x86-cleanups-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip (diff) | |
| parent | x86: Fix code patching for paravirt-alternatives on 486 (diff) | |
| download | linux-dev-c7208de304ac335d5d58db346bb773a471fc636b.tar.xz linux-dev-c7208de304ac335d5d58db346bb773a471fc636b.zip | |
Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (22 commits)
x86: Fix code patching for paravirt-alternatives on 486
x86, msr: change msr-reg.o to obj-y, and export its symbols
x86: Use hard_smp_processor_id() to get apic id for AMD K8 cpus
x86, sched: Workaround broken sched domain creation for AMD Magny-Cours
x86, mcheck: Use correct cpumask for shared bank4
x86, cacheinfo: Fixup L3 cache information for AMD multi-node processors
x86: Fix CPU llc_shared_map information for AMD Magny-Cours
x86, msr: Fix msr-reg.S compilation with gas 2.16.1, on 32-bit too
x86: Move kernel_fpu_using to irq_fpu_usable in asm/i387.h
x86, msr: fix msr-reg.S compilation with gas 2.16.1
x86, msr: Export the register-setting MSR functions via /dev/*/msr
x86, msr: Create _on_cpu helpers for {rw,wr}msr_safe_regs()
x86, msr: Have the _safe MSR functions return -EIO, not -EFAULT
x86, msr: CFI annotations, cleanups for msr-reg.S
x86, asm: Make _ASM_EXTABLE() usable from assembly code
x86, asm: Add 32-bit versions of the combined CFI macros
x86, AMD: Disable wrongly set X86_FEATURE_LAHF_LM CPUID bit
x86, msr: Rewrite AMD rd/wrmsr variants
x86, msr: Add rd/wrmsr interfaces with preset registers
x86: add specific support for Intel Atom architecture
...
27 files changed, 1203 insertions, 786 deletions
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index dbea4f95fc85..1c058b552e93 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -121,6 +121,7 @@ Code Seq# Include File Comments 'c' 00-7F linux/comstats.h conflict! 'c' 00-7F linux/coda.h conflict! 'c' 80-9F arch/s390/include/asm/chsc.h +'c' A0-AF arch/x86/include/asm/msr.h 'd' 00-FF linux/char/drm/drm/h conflict! 'd' F0-FF linux/digi1.h 'e' all linux/digi1.h conflict! diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 8130334329c0..527519b8a9f9 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -262,6 +262,15 @@ config MCORE2 family in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo) +config MATOM + bool "Intel Atom" + ---help--- + + Select this for the Intel Atom platform. Intel Atom CPUs have an + in-order pipelining architecture and thus can benefit from + accordingly optimized code. Use a recent GCC with specific Atom + support in order to fully benefit from selecting this option. + config GENERIC_CPU bool "Generic-x86-64" depends on X86_64 @@ -295,7 +304,7 @@ config X86_CPU config X86_L1_CACHE_BYTES int default "128" if MPSC - default "64" if GENERIC_CPU || MK8 || MCORE2 || X86_32 + default "64" if GENERIC_CPU || MK8 || MCORE2 || MATOM || X86_32 config X86_INTERNODE_CACHE_BYTES int @@ -310,7 +319,7 @@ config X86_L1_CACHE_SHIFT default "7" if MPENTIUM4 || MPSC default "4" if X86_ELAN || M486 || M386 || MGEODEGX1 default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX - default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MVIAC7 || X86_GENERIC || GENERIC_CPU + default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU config X86_XADD def_bool y @@ -359,7 +368,7 @@ config X86_INTEL_USERCOPY config X86_USE_PPRO_CHECKSUM def_bool y - depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 + depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM config X86_USE_3DNOW def_bool y @@ -387,7 +396,7 @@ config X86_P6_NOP config X86_TSC def_bool y - depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2) && !X86_NUMAQ) || X86_64 + depends on ((MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) && !X86_NUMAQ) || X86_64 config X86_CMPXCHG64 def_bool y @@ -397,7 +406,7 @@ config X86_CMPXCHG64 # generates cmov. config X86_CMOV def_bool y - depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64) + depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM) config X86_MINIMUM_CPU_FAMILY int diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5e7db44d709e..5128b178529f 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -55,6 +55,8 @@ else cflags-$(CONFIG_MCORE2) += \ $(call cc-option,-march=core2,$(call cc-option,-mtune=generic)) + cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom) \ + $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) cflags-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=generic) KBUILD_CFLAGS += $(cflags-y) diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu index 80177ec052f0..30e9a264f69d 100644 --- a/arch/x86/Makefile_32.cpu +++ b/arch/x86/Makefile_32.cpu @@ -33,6 +33,8 @@ cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-f cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) cflags-$(CONFIG_MVIAC7) += -march=i686 cflags-$(CONFIG_MCORE2) += -march=i686 $(call tune,core2) +cflags-$(CONFIG_MATOM) += $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \ + $(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic)) # AMD Elan support cflags-$(CONFIG_X86_ELAN) += -march=i486 diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index d3ec8d588d4b..585edebe12cf 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -59,13 +59,6 @@ asmlinkage void aesni_cbc_enc(struct crypto_aes_ctx *ctx, u8 *out, 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; @@ -89,7 +82,7 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx, return -EINVAL; } - if (kernel_fpu_using()) + if (irq_fpu_usable()) err = crypto_aes_expand_key(ctx, in_key, key_len); else { kernel_fpu_begin(); @@ -110,7 +103,7 @@ 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()) + if (irq_fpu_usable()) crypto_aes_encrypt_x86(ctx, dst, src); else { kernel_fpu_begin(); @@ -123,7 +116,7 @@ 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()) + if (irq_fpu_usable()) crypto_aes_decrypt_x86(ctx, dst, src); else { kernel_fpu_begin(); @@ -349,7 +342,7 @@ 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()) { + if (irq_fpu_usable()) { struct ablkcipher_request *cryptd_req = ablkcipher_request_ctx(req); memcpy(cryptd_req, req, sizeof(*req)); @@ -370,7 +363,7 @@ 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()) { + if (irq_fpu_usable()) { struct ablkcipher_request *cryptd_req = ablkcipher_request_ctx(req); memcpy(cryptd_req, req, sizeof(*req)); diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 56be78f582f0..b3ed1e1460ff 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -3,7 +3,7 @@ #ifdef __ASSEMBLY__ # define __ASM_FORM(x) x -# define __ASM_EX_SEC .section __ex_table +# define __ASM_EX_SEC .section __ex_table, "a" #else # define __ASM_FORM(x) " " #x " " # define __ASM_EX_SEC " .section __ex_table,\"a\"\n" @@ -38,10 +38,18 @@ #define _ASM_DI __ASM_REG(di) /* Exception table entry */ +#ifdef __ASSEMBLY__ +# define _ASM_EXTABLE(from,to) \ + __ASM_EX_SEC ; \ + _ASM_ALIGN ; \ + _ASM_PTR from , to ; \ + .previous +#else # define _ASM_EXTABLE(from,to) \ __ASM_EX_SEC \ _ASM_ALIGN "\n" \ _ASM_PTR #from "," #to "\n" \ " .previous\n" +#endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 4a28d22d4793..847fee6493a2 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -95,6 +95,7 @@ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */ #define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */ /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ #define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h index 3afc5e87cfdd..ae6253ab9029 100644 --- a/arch/x86/include/asm/dwarf2.h +++ b/arch/x86/include/asm/dwarf2.h @@ -87,9 +87,25 @@ CFI_RESTORE \reg .endm #else /*!CONFIG_X86_64*/ + .macro pushl_cfi reg + pushl \reg + CFI_ADJUST_CFA_OFFSET 4 + .endm - /* 32bit defenitions are missed yet */ + .macro popl_cfi reg + popl \reg + CFI_ADJUST_CFA_OFFSET -4 + .endm + .macro movl_cfi reg offset=0 + movl %\reg, \offset(%esp) + CFI_REL_OFFSET \reg, \offset + .endm + + .macro movl_cfi_restore offset reg + movl \offset(%esp), %\reg + CFI_RESTORE \reg + .endm #endif /*!CONFIG_X86_64*/ #endif /*__ASSEMBLY__*/ diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 175adf58dd4f..fb7f0d64e14f 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -301,6 +301,14 @@ static inline void kernel_fpu_end(void) preempt_enable(); } +static inline bool irq_fpu_usable(void) +{ + struct pt_regs *regs; + + return !in_interrupt() || !(regs = get_irq_regs()) || \ + user_mode(regs) || (read_cr0() & X86_CR0_TS); +} + /* * Some instructions like VIA's padlock instructions generate a spurious * DNA fault but don't modify SSE registers. And these instructions diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h index 555bc12bdcd6..3e2ce58a31a3 100644 --- a/arch/x86/include/asm/module.h +++ b/arch/x86/include/asm/module.h @@ -17,6 +17,8 @@ #define MODULE_PROC_FAMILY "586MMX " #elif defined CONFIG_MCORE2 #define MODULE_PROC_FAMILY "CORE2 " +#elif defined CONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM " #elif defined CONFIG_M686 #define MODULE_PROC_FAMILY "686 " #elif defined CONFIG_MPENTIUMII diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 48ad9d29484a..7e2b6ba962ff 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -3,10 +3,16 @@ #include <asm/msr-index.h> -#ifdef __KERNEL__ #ifndef __ASSEMBLY__ #include <linux/types.h> +#include <linux/ioctl.h> + +#define X86_IOC_RDMSR_REGS _IOWR('c', 0xA0, __u32[8]) +#define X86_IOC_WRMSR_REGS _IOWR('c', 0xA1, __u32[8]) + +#ifdef __KERNEL__ + #include <asm/asm.h> #include <asm/errno.h> #include <asm/cpumask.h> @@ -67,23 +73,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, ".previous\n\t" _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) - : "c" (msr), [fault] "i" (-EFAULT)); - return EAX_EDX_VAL(val, low, high); -} - -static inline unsigned long long native_read_msr_amd_safe(unsigned int msr, - int *err) -{ - DECLARE_ARGS(val, low, high); - - asm volatile("2: rdmsr ; xor %0,%0\n" - "1:\n\t" - ".section .fixup,\"ax\"\n\t" - "3: mov %3,%0 ; jmp 1b\n\t" - ".previous\n\t" - _ASM_EXTABLE(2b, 3b) - : "=r" (*err), EAX_EDX_RET(val, low, high) - : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT)); + : "c" (msr), [fault] "i" (-EIO)); return EAX_EDX_VAL(val, low, high); } @@ -106,13 +96,16 @@ notrace static inline int native_write_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : [err] "=a" (err) : "c" (msr), "0" (low), "d" (high), - [fault] "i" (-EFAULT) + [fault] "i" (-EIO) : "memory"); return err; } extern unsigned long long native_read_tsc(void); +extern int native_rdmsr_safe_regs(u32 regs[8]); +extern int native_wrmsr_safe_regs(u32 regs[8]); + static __always_inline unsigned long long __native_read_tsc(void) { DECLARE_ARGS(val, low, high); @@ -181,14 +174,44 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) *p = native_read_msr_safe(msr, &err); return err; } + static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { + u32 gprs[8] = { 0 }; int err; - *p = native_read_msr_amd_safe(msr, &err); + gprs[1] = msr; + gprs[7] = 0x9c5a203a; + + err = native_rdmsr_safe_regs(gprs); + + *p = gprs[0] | ((u64)gprs[2] << 32); + return err; } +static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) +{ + u32 gprs[8] = { 0 }; + + gprs[0] = (u32)val; + gprs[1] = msr; + gprs[2] = val >> 32; + gprs[7] = 0x9c5a203a; + + return native_wrmsr_safe_regs(gprs); +} + +static inline int rdmsr_safe_regs(u32 regs[8]) +{ + return native_rdmsr_safe_regs(regs); +} + +static inline int wrmsr_safe_regs(u32 regs[8]) +{ + return native_wrmsr_safe_regs(regs); +} + #define rdtscl(low) \ ((low) = (u32)__native_read_tsc()) @@ -228,6 +251,8 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); +int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); +int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); #else /* CONFIG_SMP */ static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { @@ -258,7 +283,15 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) { return wrmsr_safe(msr_no, l, h); } +static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) +{ + return rdmsr_safe_regs(regs); +} +static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) +{ + return wrmsr_safe_regs(regs); +} #endif /* CONFIG_SMP */ -#endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ +#endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_MSR_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 4fb37c8a0832..40d6586af25b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -7,689 +7,11 @@ #include <asm/pgtable_types.h> #include <asm/asm.h> -/* Bitmask of what can be clobbered: usually at least eax. */ -#define CLBR_NONE 0 -#define CLBR_EAX (1 << 0) -#define CLBR_ECX (1 << 1) -#define CLBR_EDX (1 << 2) -#define CLBR_EDI (1 << 3) - -#ifdef CONFIG_X86_32 -/* CLBR_ANY should match all regs platform has. For i386, that's just it */ -#define CLBR_ANY ((1 << 4) - 1) - -#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX) -#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX) -#define CLBR_SCRATCH (0) -#else -#define CLBR_RAX CLBR_EAX -#define CLBR_RCX CLBR_ECX -#define CLBR_RDX CLBR_EDX -#define CLBR_RDI CLBR_EDI -#define CLBR_RSI (1 << 4) -#define CLBR_R8 (1 << 5) -#define CLBR_R9 (1 << 6) -#define CLBR_R10 (1 << 7) -#define CLBR_R11 (1 << 8) - -#define CLBR_ANY ((1 << 9) - 1) - -#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \ - CLBR_RCX | CLBR_R8 | CLBR_R9) -#define CLBR_RET_REG (CLBR_RAX) -#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11) - -#include <asm/desc_defs.h> -#endif /* X86_64 */ - -#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG) +#include <asm/paravirt_types.h> #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/cpumask.h> -#include <asm/kmap_types.h> -#include <asm/desc_defs.h> - -struct page; -struct thread_struct; -struct desc_ptr; -struct tss_struct; -struct mm_struct; -struct desc_struct; -struct task_struct; - -/* - * Wrapper type for pointers to code which uses the non-standard - * calling convention. See PV_CALL_SAVE_REGS_THUNK below. - */ -struct paravirt_callee_save { - void *func; -}; - -/* general info */ -struct pv_info { - unsigned int kernel_rpl; - int shared_kernel_pmd; - int paravirt_enabled; - const char *name; -}; - -struct pv_init_ops { - /* - * Patch may replace one of the defined code sequences with - * arbitrary code, subject to the same register constraints. - * This generally means the code is not free to clobber any - * registers other than EAX. The patch function should return - * the number of bytes of code generated, as we nop pad the - * rest in generic code. - */ - unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, - unsigned long addr, unsigned len); - - /* Basic arch-specific setup */ - void (*arch_setup)(void); - char *(*memory_setup)(void); - void (*post_allocator_init)(void); - - /* Print a banner to identify the environment */ - void (*banner)(void); -}; - - -struct pv_lazy_ops { - /* Set deferred update mode, used for batching operations. */ - void (*enter)(void); - void (*leave)(void); -}; - -struct pv_time_ops { - void (*time_init)(void); - - /* Set and set time of day */ - unsigned long (*get_wallclock)(void); - int (*set_wallclock)(unsigned long); - - unsigned long long (*sched_clock)(void); - unsigned long (*get_tsc_khz)(void); -}; - -struct pv_cpu_ops { - /* hooks for various privileged instructions */ - unsigned long (*get_debugreg)(int regno); - void (*set_debugreg)(int regno, unsigned long value); - - void (*clts)(void); - - unsigned long (*read_cr0)(void); - void (*write_cr0)(unsigned long); - - unsigned long (*read_cr4_safe)(void); - unsigned long (*read_cr4)(void); - void (*write_cr4)(unsigned long); - -#ifdef CONFIG_X86_64 - unsigned long (*read_cr8)(void); - void (*write_cr8)(unsigned long); -#endif - - /* Segment descriptor handling */ - void (*load_tr_desc)(void); - void (*load_gdt)(const struct desc_ptr *); - void (*load_idt)(const struct desc_ptr *); - void (*store_gdt)(struct desc_ptr *); - void (*store_idt)(struct desc_ptr *); - void (*set_ldt)(const void *desc, unsigned entries); - unsigned long (*store_tr)(void); - void (*load_tls)(struct thread_struct *t, unsigned int cpu); -#ifdef CONFIG_X86_64 - void (*load_gs_index)(unsigned int idx); -#endif - void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum, - const void *desc); - void (*write_gdt_entry)(struct desc_struct *, - int entrynum, const void *desc, int size); - void (*write_idt_entry)(gate_desc *, - int entrynum, const gate_desc *gate); - void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries); - void (*free_ldt)(struct desc_struct *ldt, unsigned entries); - - void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t); - - void (*set_iopl_mask)(unsigned mask); - - void (*wbinvd)(void); - void (*io_delay)(void); - - /* cpuid emulation, mostly so that caps bits can be disabled */ - void (*cpuid)(unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx); - - /* MSR, PMC and TSR operations. - err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ - u64 (*read_msr_amd)(unsigned int msr, int *err); - u64 (*read_msr)(unsigned int msr, int *err); - int (*write_msr)(unsigned int msr, unsigned low, unsigned high); - - u64 (*read_tsc)(void); - u64 (*read_pmc)(int counter); - unsigned long long (*read_tscp)(unsigned int *aux); - - /* - * Atomically enable interrupts and return to userspace. This - * is only ever used to return to 32-bit processes; in a - * 64-bit kernel, it's used for 32-on-64 compat processes, but - * never native 64-bit processes. (Jump, not call.) - */ - void (*irq_enable_sysexit)(void); - - /* - * Switch to usermode gs and return to 64-bit usermode using - * sysret. Only used in 64-bit kernels to return to 64-bit - * processes. Usermode register state, including %rsp, must - * already be restored. - */ - void (*usergs_sysret64)(void); - - /* - * Switch to usermode gs and return to 32-bit usermode using - * sysret. Used to return to 32-on-64 compat processes. - * Other usermode register state, including %esp, must already - * be restored. - */ - void (*usergs_sysret32)(void); - - /* Normal iret. Jump to this with the standard iret stack - frame set up. */ - void (*iret)(void); - - void (*swapgs)(void); - - void (*start_context_switch)(struct task_struct *prev); - void (*end_context_switch)(struct task_struct *next); -}; - -struct pv_irq_ops { - void (*init_IRQ)(void); - - /* - * Get/set interrupt state. save_fl and restore_fl are only - * expected to use X86_EFLAGS_IF; all other bits - * returned from save_fl are undefined, and may be ignored by - * restore_fl. - * - * NOTE: These functions callers expect the callee to preserve - * more registers than the standard C calling convention. - */ - struct paravirt_callee_save save_fl; - struct paravirt_callee_save restore_fl; - struct paravirt_callee_save irq_disable; - struct paravirt_callee_save irq_enable; - - void (*safe_halt)(void); - void (*halt)(void); - -#ifdef CONFIG_X86_64 - void (*adjust_exception_frame)(void); -#endif -}; - -struct pv_apic_ops { -#ifdef CONFIG_X86_LOCAL_APIC - void (*setup_boot_clock)(void); - void (*setup_secondary_clock)(void); - - void (*startup_ipi_hook)(int phys_apicid, - unsigned long start_eip, - unsigned long start_esp); -#endif -}; - -struct pv_mmu_ops { - /* - * Called before/after init_mm pagetable setup. setup_start - * may reset %cr3, and may pre-install parts of the pagetable; - * pagetable setup is expected to preserve any existing - * mapping. - */ - void (*pagetable_setup_start)(pgd_t *pgd_base); - void (*pagetable_setup_done)(pgd_t *pgd_base); - - unsigned long (*read_cr2)(void); - void (*write_cr2)(unsigned long); - - unsigned long (*read_cr3)(void); - void (*write_cr3)(unsigned long); - - /* - * Hooks for intercepting the creation/use/destruction of an - * mm_struct. - */ - void (*activate_mm)(struct mm_struct *prev, - struct mm_struct *next); - void (*dup_mmap)(struct mm_struct *oldmm, - struct mm_struct *mm); - void (*exit_mmap)(struct mm_struct *mm); - - - /* TLB operations */ - void (*flush_tlb_user)(void); - void (*flush_tlb_kernel)(void); - void (*flush_tlb_single)(unsigned long addr); - void (*flush_tlb_others)(const struct cpumask *cpus, - struct mm_struct *mm, - unsigned long va); - - /* Hooks for allocating and freeing a pagetable top-level */ - int (*pgd_alloc)(struct mm_struct *mm); - void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd); - - /* - * Hooks for allocating/releasing pagetable pages when they're - * attached to a pagetable - */ - void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn); - void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn); - void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count); - void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn); - void (*release_pte)(unsigned long pfn); - void (*release_pmd)(unsigned long pfn); - void (*release_pud)(unsigned long pfn); - - /* Pagetable manipulation functions */ - void (*set_pte)(pte_t *ptep, pte_t pteval); - void (*set_pte_at)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pteval); - void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); - void (*pte_update)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep); - void (*pte_update_defer)(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); - - pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep); - void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); - - struct paravirt_callee_save pte_val; - struct paravirt_callee_save make_pte; - - struct paravirt_callee_save pgd_val; - struct paravirt_callee_save make_pgd; - -#if PAGETABLE_LEVELS >= 3 -#ifdef CONFIG_X86_PAE - void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); - void (*pte_clear)(struct mm_struct *mm, unsigned long addr, - pte_t *ptep); - void (*pmd_clear)(pmd_t *pmdp); - -#endif /* CONFIG_X86_PAE */ - - void (*set_pud)(pud_t *pudp, pud_t pudval); - - struct paravirt_callee_save pmd_val; - struct paravirt_callee_save make_pmd; - -#if PAGETABLE_LEVELS == 4 - struct paravirt_callee_save pud_val; - struct paravirt_callee_save make_pud; - - void (*set_pgd)(pgd_t *pudp, pgd_t pgdval); -#endif /* PAGETABLE_LEVELS == 4 */ -#endif /* PAGETABLE_LEVELS >= 3 */ - -#ifdef CONFIG_HIGHPTE - void *(*kmap_atomic_pte)(struct page *page, enum km_type type); -#endif - - struct pv_lazy_ops lazy_mode; - - /* dom0 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, - phys_addr_t phys, pgprot_t flags); -}; - -struct raw_spinlock; -struct pv_lock_ops { - int (*spin_is_locked)(struct raw_spinlock *lock); - int (*spin_is_contended)(struct raw_spinlock *lock); - void (*spin_lock)(struct raw_spinlock *lock); - void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags); - int (*spin_trylock)(struct raw_spinlock *lock); - void (*spin_unlock)(struct raw_spinlock *lock); -}; - -/* This contains all the paravirt structures: we get a convenient - * number for each function using the offset which we use to indicate - * what to patch. */ -struct paravirt_patch_template { - struct pv_init_ops pv_init_ops; - struct pv_time_ops pv_time_ops; - struct pv_cpu_ops pv_cpu_ops; - struct pv_irq_ops pv_irq_ops; - struct pv_apic_ops pv_apic_ops; - struct pv_mmu_ops pv_mmu_ops; - struct pv_lock_ops pv_lock_ops; -}; - -extern struct pv_info pv_info; -extern struct pv_init_ops pv_init_ops; -extern struct pv_time_ops pv_time_ops; -extern struct pv_cpu_ops pv_cpu_ops; -extern struct pv_irq_ops pv_irq_ops; -extern struct pv_apic_ops pv_apic_ops; -extern struct pv_mmu_ops pv_mmu_ops; -extern struct pv_lock_ops pv_lock_ops; - -#define PARAVIRT_PATCH(x) \ - (offsetof(struct paravirt_patch_template, x) / sizeof(void *)) - -#define paravirt_type(op) \ - [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ - [paravirt_opptr] "i" (&(op)) -#define paravirt_clobber(clobber) \ - [paravirt_clobber] "i" (clobber) - -/* - * Generate some code, and mark it as patchable by the - * apply_paravirt() alternate instruction patcher. - */ -#define _paravirt_alt(insn_string, type, clobber) \ - "771:\n\t" insn_string "\n" "772:\n" \ - ".pushsection .parainstructions,\"a\"\n" \ - _ASM_ALIGN "\n" \ - _ASM_PTR " 771b\n" \ - " .byte " type "\n" \ - " .byte 772b-771b\n" \ - " .short " clobber "\n" \ - ".popsection\n" - -/* Generate patchable code, with the default asm parameters. */ -#define paravirt_alt(insn_string) \ - _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") - -/* Simple instruction patching code. */ -#define DEF_NATIVE(ops, name, code) \ - extern const char start_##ops##_##name[], end_##ops##_##name[]; \ - asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") - -unsigned paravirt_patch_nop(void); -unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); -unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); -unsigned paravirt_patch_ignore(unsigned len); -unsigned paravirt_patch_call(void *insnbuf, - const void *target, u16 tgt_clobbers, - unsigned long addr, u16 site_clobbers, - unsigned len); -unsigned paravirt_patch_jmp(void *insnbuf, const void *target, - unsigned long addr, unsigned len); -unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, - unsigned long addr, unsigned len); - -unsigned paravirt_patch_insns(void *insnbuf, unsigned len, - const char *start, const char *end); - -unsigned native_patch(u8 type, u16 clobbers, void *ibuf, - unsigned long addr, unsigned len); - -int paravirt_disable_iospace(void); - -/* - * This generates an indirect call based on the operation type number. - * The type number, computed in PARAVIRT_PATCH, is derived from the - * offset into the paravirt_patch_template structure, and can therefore be - * freely converted back into a structure offset. - */ -#define PARAVIRT_CALL "call *%c[paravirt_opptr];" - -/* - * These macros are intended to wrap calls through one of the paravirt - * ops structs, so that they can be later identified and patched at - * runtime. - * - * Normally, a call to a pv_op function is a simple indirect call: - * (pv_op_struct.operations)(args...). - * - * Unfortunately, this is a relatively slow operation for modern CPUs, - * because it cannot necessarily determine what the destination - * address is. In this case, the address is a runtime constant, so at - * the very least we can patch the call to e a simple direct call, or - * ideally, patch an inline implementation into the callsite. (Direct - * calls are essentially free, because the call and return addresses - * are completely predictable.) - * - * For i386, these macros rely on the standard gcc "regparm(3)" calling - * convention, in which the first three arguments are placed in %eax, - * %edx, %ecx (in that order), and the remaining arguments are placed - * on the stack. All caller-save registers (eax,edx,ecx) are expected - * to be modified (either clobbered or used for return values). - * X86_64, on the other hand, already specifies a register-based calling - * conventions, returning at %rax, with parameteres going on %rdi, %rsi, - * %rdx, and %rcx. Note that for this reason, x86_64 does not need any - * special handling for dealing with 4 arguments, unlike i386. - * However, x86_64 also have to clobber all caller saved registers, which - * unfortunately, are quite a bit (r8 - r11) - * - * The call instruction itself is marked by placing its start address - * and size into the .parainstructions section, so that - * apply_paravirt() in arch/i386/kernel/alternative.c can do the - * appropriate patching under the control of the backend pv_init_ops - * implementation. - * - * Unfortunately there's no way to get gcc to generate the args setup - * for the call, and then allow the call itself to be generated by an - * inline asm. Because of this, we must do the complete arg setup and - * return value handling from within these macros. This is fairly - * cumbersome. - * - * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments. - * It could be extended to more arguments, but there would be little - * to be gained from that. For each number of arguments, there are - * the two VCALL and CALL variants for void and non-void functions. - * - * When there is a return value, the invoker of the macro must specify - * the return type. The macro then uses sizeof() on that type to - * determine whether its a 32 or 64 bit value, and places the return - * in the right register(s) (just %eax for 32-bit, and %edx:%eax for - * 64-bit). For x86_64 machines, it just returns at %rax regardless of - * the return value size. - * - * 64-bit arguments are passed as a pair of adjacent 32-bit arguments - * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments - * in low,high order - * - * Small structures are passed and returned in registers. The macro - * calling convention can't directly deal with this, so the wrapper - * functions must do this. - * - * These PVOP_* macros are only defined within this header. This - * means that all uses must be wrapped in inline functions. This also - * makes sure the incoming and outgoing types are always correct. - */ -#ifdef CONFIG_X86_32 -#define PVOP_VCALL_ARGS \ - unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx -#define PVOP_CALL_ARGS PVOP_VCALL_ARGS - -#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) -#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x)) -#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x)) - -#define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \ - "=c" (__ecx) -#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS - -#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx) -#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS - -#define EXTRA_CLOBBERS -#define VEXTRA_CLOBBERS -#else /* CONFIG_X86_64 */ -#define PVOP_VCALL_ARGS \ - unsigned long __edi = __edi, __esi = __esi, \ - __edx = __edx, __ecx = __ecx -#define PVOP_CALL_ARGS PVOP_VCALL_ARGS, __eax - -#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) -#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x)) -#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x)) -#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x)) - -#define PVOP_VCALL_CLOBBERS "=D" (__edi), \ - "=S" (__esi), "=d" (__edx), \ - "=c" (__ecx) -#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax) - -#define PVOP_VCALLEE_CLOBBERS "=a" (__eax) -#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS - -#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11" -#define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11" -#endif /* CONFIG_X86_32 */ - -#ifdef CONFIG_PARAVIRT_DEBUG -#define PVOP_TEST_NULL(op) BUG_ON(op == NULL) -#else -#define PVOP_TEST_NULL(op) ((void)op) -#endif - -#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \ - pre, post, ...) \ - ({ \ - rettype __ret; \ - PVOP_CALL_ARGS; \ - PVOP_TEST_NULL(op); \ - /* This is 32-bit specific, but is okay in 64-bit */ \ - /* since this condition will never hold */ \ - if (sizeof(rettype) > sizeof(unsigned long)) { \ - asm volatile(pre \ - paravirt_alt(PARAVIRT_CALL) \ - post \ - : call_clbr \ - : paravirt_type(op), \ - paravirt_clobber(clbr), \ - ##__VA_ARGS__ \ - : "memory", "cc" extra_clbr); \ - __ret = (rettype)((((u64)__edx) << 32) | __eax); \ - } else { \ - asm volatile(pre \ - paravirt_alt(PARAVIRT_CALL) \ - post \ - : call_clbr \ - : paravirt_type(op), \ - paravirt_clobber(clbr), \ - ##__VA_ARGS__ \ - : "memory", "cc" extra_clbr); \ - __ret = (rettype)__eax; \ - } \ - __ret; \ - }) - -#define __PVOP_CALL(rettype, op, pre, post, ...) \ - ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \ - EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__) - -#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \ - ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ - PVOP_CALLEE_CLOBBERS, , \ - pre, post, ##__VA_ARGS__) - - -#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \ - ({ \ - PVOP_VCALL_ARGS; \ - PVOP_TEST_NULL(op); \ - asm volatile(pre \ - paravirt_alt(PARAVIRT_CALL) \ - post \ - : call_clbr \ - : paravirt_type(op), \ - paravirt_clobber(clbr), \ - ##__VA_ARGS__ \ - : "memory", "cc" extra_clbr); \ - }) - -#define __PVOP_VCALL(op, pre, post, ...) \ - ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \ - VEXTRA_CLOBBERS, \ - pre, post, ##__VA_ARGS__) - -#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...) \ - ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ - PVOP_VCALLEE_CLOBBERS, , \ - pre, post, ##__VA_ARGS__) - - - -#define PVOP_CALL0(rettype, op) \ - __PVOP_CALL(rettype, op, "", "") -#define PVOP_VCALL0(op) \ - __PVOP_VCALL(op, "", "") - -#define PVOP_CALLEE0(rettype, op) \ - __PVOP_CALLEESAVE(rettype, op, "", "") -#define PVOP_VCALLEE0(op) \ - __PVOP_VCALLEESAVE(op, "", "") - - -#define PVOP_CALL1(rettype, op, arg1) \ - __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) -#define PVOP_VCALL1(op, arg1) \ - __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1)) - -#define PVOP_CALLEE1(rettype, op, arg1) \ - __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) -#define PVOP_VCALLEE1(op, arg1) \ - __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1)) - - -#define PVOP_CALL2(rettype, op, arg1, arg2) \ - __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) -#define PVOP_VCALL2(op, arg1, arg2) \ - __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) - -#define PVOP_CALLEE2(rettype, op, arg1, arg2) \ - __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) -#define PVOP_VCALLEE2(op, arg1, arg2) \ - __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) - - -#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \ - __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) -#define PVOP_VCALL3(op, arg1, arg2, arg3) \ - __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) - -/* This is the only difference in x86_64. We can make it much simpler */ -#ifdef CONFIG_X86_32 -#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ - __PVOP_CALL(rettype, op, \ - "push %[_arg4];", "lea 4(%%esp),%%esp;", \ - PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ - PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4))) -#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ - __PVOP_VCALL(op, \ - "push %[_arg4];", "lea 4(%%esp),%%esp;", \ - "0" ((u32)(arg1)), "1" ((u32)(arg2)), \ - "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) -#else -#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ - __PVOP_CALL(rettype, op, "", "", \ - PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ - PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ - __PVOP_VCALL(op, "", "", \ - PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ - PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -#endif static inline int paravirt_enabled(void) { @@ -820,15 +142,22 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err) { return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err); } -static inline u64 paravirt_read_msr_amd(unsigned msr, int *err) + +static inline int paravirt_rdmsr_regs(u32 *regs) { - return PVOP_CALL2(u64, pv_cpu_ops.read_msr_amd, msr, err); + return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs); } + static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high); } +static inline int paravirt_wrmsr_regs(u32 *regs) +{ + return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs); +} + /* These should all do BUG_ON(_err), but our headers are too tangled. */ #define rdmsr(msr, val1, val2) \ do { \ @@ -862,6 +191,9 @@ do { \ _err; \ }) +#define rdmsr_safe_regs(regs) paravirt_rdmsr_regs(regs) +#define wrmsr_safe_regs(regs) paravirt_wrmsr_regs(regs) + static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; @@ -871,12 +203,31 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) } static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { + u32 gprs[8] = { 0 }; int err; - *p = paravirt_read_msr_amd(msr, &err); + gprs[1] = msr; + gprs[7] = 0x9c5a203a; + + err = paravirt_rdmsr_regs(gprs); + + *p = gprs[0] | ((u64)gprs[2] << 32); + return err; } +static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) +{ + u32 gprs[8] = { 0 }; + + gprs[0] = (u32)val; + gprs[1] = msr; + gprs[2] = val >> 32; + gprs[7] = 0x9c5a203a; + + return paravirt_wrmsr_regs(gprs); +} + static inline u64 paravirt_read_tsc(void) { return PVOP_CALL0(u64, pv_cpu_ops.read_tsc); @@ -1393,20 +744,6 @@ static inline void pmd_clear(pmd_t *pmdp) } #endif /* CONFIG_X86_PAE */ -/* Lazy mode for batching updates / context switch */ -enum paravirt_lazy_mode { - PARAVIRT_LAZY_NONE, - PARAVIRT_LAZY_MMU, - PARAVIRT_LAZY_CPU, -}; - -enum paravirt_lazy_mode paravirt_get_lazy_mode(void); -void paravirt_start_context_switch(struct task_struct *prev); -void paravirt_end_context_switch(struct task_struct *next); - -void paravirt_enter_lazy_mmu(void); -void paravirt_leave_lazy_mmu(void); - #define __HAVE_ARCH_START_CONTEXT_SWITCH static inline void arch_start_context_switch(struct task_struct *prev) { @@ -1437,12 +774,6 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, pv_mmu_ops.set_fixmap(idx, phys, flags); } -void _paravirt_nop(void); -u32 _paravirt_ident_32(u32); -u64 _paravirt_ident_64(u64); - -#define paravirt_nop ((void *)_paravirt_nop) - #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) static inline int __raw_spin_is_locked(struct raw_spinlock *lock) @@ -1479,17 +810,6 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock) #endif -/* These all sit in the .parainstructions section to tell us what to patch. */ -struct paravirt_patch_site { - u8 *instr; /* original instructions */ - u8 instrtype; /* type of this instruction */ - u8 len; /* length of original instruction */ - u16 clobbers; /* what registers you may clobber */ -}; - -extern struct paravirt_patch_site __parainstructions[], - __parainstructions_end[]; - #ifdef CONFIG_X86_32 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;" #define PV_RESTORE_REGS "popl %edx; popl %ecx;" diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h new file mode 100644 index 000000000000..25402d0006e7 --- /dev/null +++ b/arch/x86/include/asm/paravirt_types.h @@ -0,0 +1,721 @@ +#ifndef _ASM_X86_PARAVIRT_TYPES_H +#define _ASM_X86_PARAVIRT_TYPES_H + +/* Bitmask of what can be clobbered: usually at least eax. */ +#define CLBR_NONE 0 +#define CLBR_EAX (1 << 0) +#define CLBR_ECX (1 << 1) +#define CLBR_EDX (1 << 2) +#define CLBR_EDI (1 << 3) + +#ifdef CONFIG_X86_32 +/* CLBR_ANY should match all regs platform has. For i386, that's just it */ +#define CLBR_ANY ((1 << 4) - 1) + +#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX) +#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX) +#define CLBR_SCRATCH (0) +#else +#define CLBR_RAX CLBR_EAX +#define CLBR_RCX CLBR_ECX +#define CLBR_RDX CLBR_EDX +#define CLBR_RDI CLBR_EDI +#define CLBR_RSI (1 << 4) +#define CLBR_R8 (1 << 5) +#define CLBR_R9 (1 << 6) +#define CLBR_R10 (1 << 7) +#define CLBR_R11 (1 << 8) + +#define CLBR_ANY ((1 << 9) - 1) + +#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \ + CLBR_RCX | CLBR_R8 | CLBR_R9) +#define CLBR_RET_REG (CLBR_RAX) +#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11) + +#endif /* X86_64 */ + +#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG) + +#ifndef __ASSEMBLY__ + +#include <asm/desc_defs.h> +#include <asm/kmap_types.h> + +struct page; +struct thread_struct; +struct desc_ptr; +struct tss_struct; +struct mm_struct; +struct desc_struct; +struct task_struct; +struct cpumask; + +/* + * Wrapper type for pointers to code which uses the non-standard + * calling convention. See PV_CALL_SAVE_REGS_THUNK below. + */ +struct paravirt_callee_save { + void *func; +}; + +/* general info */ +struct pv_info { + unsigned int kernel_rpl; + int shared_kernel_pmd; + int paravirt_enabled; + const char *name; +}; + +struct pv_init_ops { + /* + * Patch may replace one of the defined code sequences with + * arbitrary code, subject to the same register constraints. + * This generally means the code is not free to clobber any + * registers other than EAX. The patch function should return + * the number of bytes of code generated, as we nop pad the + * rest in generic code. + */ + unsigned (*patch)(u8 type, u16 clobber, void *insnbuf, + unsigned long addr, unsigned len); + + /* Basic arch-specific setup */ + void (*arch_setup)(void); + char *(*memory_setup)(void); + void (*post_allocator_init)(void); + + /* Print a banner to identify the environment */ + void (*banner)(void); +}; + + +struct pv_lazy_ops { + /* Set deferred update mode, used for batching operations. */ + void (*enter)(void); + void (*leave)(void); +}; + +struct pv_time_ops { + void (*time_init)(void); + + /* Set and set time of day */ + unsigned long (*get_wallclock)(void); + int (*set_wallclock)(unsigned long); + + unsigned long long (*sched_clock)(void); + unsigned long (*get_tsc_khz)(void); +}; + +struct pv_cpu_ops { + /* hooks for various privileged instructions */ + unsigned long (*get_debugreg)(int regno); + void (*set_debugreg)(int regno, unsigned long value); + + void (*clts)(void); + + unsigned long (*read_cr0)(void); + void (*write_cr0)(unsigned long); + + unsigned long (*read_cr4_safe)(void); + unsigned long (*read_cr4)(void); + void (*write_cr4)(unsigned long); + +#ifdef CONFIG_X86_64 + unsigned long (*read_cr8)(void); + void (*write_cr8)(unsigned long); +#endif + + /* Segment descriptor handling */ + void (*load_tr_desc)(void); + void (*load_gdt)(const struct desc_ptr *); + void (*load_idt)(const struct desc_ptr *); + void (*store_gdt)(struct desc_ptr *); + void (*store_idt)(struct desc_ptr *); + void (*set_ldt)(const void *desc, unsigned entries); + unsigned long (*store_tr)(void); + void (*load_tls)(struct thread_struct *t, unsigned int cpu); +#ifdef CONFIG_X86_64 + void (*load_gs_index)(unsigned int idx); +#endif + void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum, + const void *desc); + void (*write_gdt_entry)(struct desc_struct *, + int entrynum, const void *desc, int size); + void (*write_idt_entry)(gate_desc *, + int entrynum, const gate_desc *gate); + void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries); + void (*free_ldt)(struct desc_struct *ldt, unsigned entries); + + void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t); + + void (*set_iopl_mask)(unsigned mask); + + void (*wbinvd)(void); + void (*io_delay)(void); + + /* cpuid emulation, mostly so that caps bits can be disabled */ + void (*cpuid)(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx); + + /* MSR, PMC and TSR operations. + err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */ + u64 (*read_msr)(unsigned int msr, int *err); + int (*rdmsr_regs)(u32 *regs); + int (*write_msr)(unsigned int msr, unsigned low, unsigned high); + int (*wrmsr_regs)(u32 *regs); + + u64 (*read_tsc)(void); + u64 (*read_pmc)(int counter); + unsigned long long (*read_tscp)(unsigned int *aux); + + /* + * Atomically enable interrupts and return to userspace. This + * is only ever used to return to 32-bit processes; in a + * 64-bit kernel, it's used for 32-on-64 compat processes, but + * never native 64-bit processes. (Jump, not call.) + */ + void (*irq_enable_sysexit)(void); + + /* + * Switch to usermode gs and return to 64-bit usermode using + * sysret. Only used in 64-bit kernels to return to 64-bit + * processes. Usermode register state, including %rsp, must + * already be restored. + */ + void (*usergs_sysret64)(void); + + /* + * Switch to usermode gs and return to 32-bit usermode using + * sysret. Used to return to 32-on-64 compat processes. + * Other usermode register state, including %esp, must already + * be restored. + */ + void (*usergs_sysret32)(void); + + /* Normal iret. Jump to this with the standard iret stack + frame set up. */ + void (*iret)(void); + + void (*swapgs)(void); + + void (*start_context_switch)(struct task_struct *prev); + void (*end_context_switch)(struct task_struct *next); +}; + +struct pv_irq_ops { + void (*init_IRQ)(void); + + /* + * Get/set interrupt state. save_fl and restore_fl are only + * expected to use X86_EFLAGS_IF; all other bits + * returned from save_fl are undefined, and may be ignored by + * restore_fl. + * + * NOTE: These functions callers expect the callee to preserve + * more registers than the standard C calling convention. + */ + struct paravirt_callee_save save_fl; + struct paravirt_callee_save restore_fl; + struct paravirt_callee_save irq_disable; + struct paravirt_callee_save irq_enable; + + void (*safe_halt)(void); + void (*halt)(void); + +#ifdef CONFIG_X86_64 + void (*adjust_exception_frame)(void); +#endif +}; + +struct pv_apic_ops { +#ifdef CONFIG_X86_LOCAL_APIC + void (*setup_boot_clock)(void); + void (*setup_secondary_clock)(void); + + void (*startup_ipi_hook)(int phys_apicid, + unsigned long start_eip, + unsigned long start_esp); +#endif +}; + +struct pv_mmu_ops { + /* + * Called before/after init_mm pagetable setup. setup_start + * may reset %cr3, and may pre-install parts of the pagetable; + * pagetable setup is expected to preserve any existing + * mapping. + */ + void (*pagetable_setup_start)(pgd_t *pgd_base); + void (*pagetable_setup_done)(pgd_t *pgd_base); + + unsigned long (*read_cr2)(void); + void (*write_cr2)(unsigned long); + + unsigned long (*read_cr3)(void); + void (*write_cr3)(unsigned long); + + /* + * Hooks for intercepting the creation/use/destruction of an + * mm_struct. + */ + void (*activate_mm)(struct mm_struct *prev, + struct mm_struct *next); + void (*dup_mmap)(struct mm_struct *oldmm, + struct mm_struct *mm); + void (*exit_mmap)(struct mm_struct *mm); + + + /* TLB operations */ + void (*flush_tlb_user)(void); + void (*flush_tlb_kernel)(void); + void (*flush_tlb_single)(unsigned long addr); + void (*flush_tlb_others)(const struct cpumask *cpus, + struct mm_struct *mm, + unsigned long va); + + /* Hooks for allocating and freeing a pagetable top-level */ + int (*pgd_alloc)(struct mm_struct *mm); + void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd); + + /* + * Hooks for allocating/releasing pagetable pages when they're + * attached to a pagetable + */ + void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count); + void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn); + void (*release_pte)(unsigned long pfn); + void (*release_pmd)(unsigned long pfn); + void (*release_pud)(unsigned long pfn); + + /* Pagetable manipulation functions */ + void (*set_pte)(pte_t *ptep, pte_t pteval); + void (*set_pte_at)(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval); + void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); + void (*pte_update)(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); + void (*pte_update_defer)(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); + + pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); + void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); + + struct paravirt_callee_save pte_val; + struct paravirt_callee_save make_pte; + + struct paravirt_callee_save pgd_val; + struct paravirt_callee_save make_pgd; + +#if PAGETABLE_LEVELS >= 3 +#ifdef CONFIG_X86_PAE + void (*set_pte_atomic)(pte_t *ptep, pte_t pteval); + void (*pte_clear)(struct mm_struct *mm, unsigned long addr, + pte_t *ptep); + void (*pmd_clear)(pmd_t *pmdp); + +#endif /* CONFIG_X86_PAE */ + + void (*set_pud)(pud_t *pudp, pud_t pudval); + + struct paravirt_callee_save pmd_val; + struct paravirt_callee_save make_pmd; + +#if PAGETABLE_LEVELS == 4 + struct paravirt_callee_save pud_val; + struct paravirt_callee_save make_pud; + + void (*set_pgd)(pgd_t *pudp, pgd_t pgdval); +#endif /* PAGETABLE_LEVELS == 4 */ +#endif /* PAGETABLE_LEVELS >= 3 */ + +#ifdef CONFIG_HIGHPTE + void *(*kmap_atomic_pte)(struct page *page, enum km_type type); +#endif + + struct pv_lazy_ops lazy_mode; + + /* dom0 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, + phys_addr_t phys, pgprot_t flags); +}; + +struct raw_spinlock; +struct pv_lock_ops { + int (*spin_is_locked)(struct raw_spinlock *lock); + int (*spin_is_contended)(struct raw_spinlock *lock); + void (*spin_lock)(struct raw_spinlock *lock); + void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags); + int (*spin_trylock)(struct raw_spinlock *lock); + void (*spin_unlock)(struct raw_spinlock *lock); +}; + +/* This contains all the paravirt structures: we get a convenient + * number for each function using the offset which we use to indicate + * what to patch. */ +struct paravirt_patch_template { + struct pv_init_ops pv_init_ops; + struct pv_time_ops pv_time_ops; + struct pv_cpu_ops pv_cpu_ops; + struct pv_irq_ops pv_irq_ops; + struct pv_apic_ops pv_apic_ops; + struct pv_mmu_ops pv_mmu_ops; + struct pv_lock_ops pv_lock_ops; +}; + +extern struct pv_info pv_info; +extern struct pv_init_ops pv_init_ops; +extern struct pv_time_ops pv_time_ops; +extern struct pv_cpu_ops pv_cpu_ops; +extern struct pv_irq_ops pv_irq_ops; +extern struct pv_apic_ops pv_apic_ops; +extern struct pv_mmu_ops pv_mmu_ops; +extern struct pv_lock_ops pv_lock_ops; + +#define PARAVIRT_PATCH(x) \ + (offsetof(struct paravirt_patch_template, x) / sizeof(void *)) + +#define paravirt_type(op) \ + [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ + [paravirt_opptr] "i" (&(op)) +#define paravirt_clobber(clobber) \ + [paravirt_clobber] "i" (clobber) + +/* + * Generate some code, and mark it as patchable by the + * apply_paravirt() alternate instruction patcher. + */ +#define _paravirt_alt(insn_string, type, clobber) \ + "771:\n\t" insn_string "\n" "772:\n" \ + ".pushsection .parainstructions,\"a\"\n" \ + _ASM_ALIGN "\n" \ + _ASM_PTR " 771b\n" \ + " .byte " type "\n" \ + " .byte 772b-771b\n" \ + " .short " clobber "\n" \ + ".popsection\n" + +/* Generate patchable code, with the default asm parameters. */ +#define paravirt_alt(insn_string) \ + _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") + +/* Simple instruction patching code. */ +#define DEF_NATIVE(ops, name, code) \ + extern const char start_##ops##_##name[], end_##ops##_##name[]; \ + asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") + +unsigned paravirt_patch_nop(void); +unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); +unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); +unsigned paravirt_patch_ignore(unsigned len); +unsigned paravirt_patch_call(void *insnbuf, + const void *target, u16 tgt_clobbers, + unsigned long addr, u16 site_clobbers, + unsigned len); +unsigned paravirt_patch_jmp(void *insnbuf, const void *target, + unsigned long addr, unsigned len); +unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, + unsigned long addr, unsigned len); + +unsigned paravirt_patch_insns(void *insnbuf, unsigned len, + const char *start, const char *end); + +unsigned native_patch(u8 type, u16 clobbers, void *ibuf, + unsigned long addr, unsigned len); + +int paravirt_disable_iospace(void); + +/* + * This generates an indirect call based on the operation type number. + * The type number, computed in PARAVIRT_PATCH, is derived from the + * offset into the paravirt_patch_template structure, and can therefore be + * freely converted back into a structure offset. + */ +#define PARAVIRT_CALL "call *%c[paravirt_opptr];" + +/* + * These macros are intended to wrap calls through one of the paravirt + * ops structs, so that they can be later identified and patched at + * runtime. + * + * Normally, a call to a pv_op function is a simple indirect call: + * (pv_op_struct.operations)(args...). + * + * Unfortunately, this is a relatively slow operation for modern CPUs, + * because it cannot necessarily determine what the destination + * address is. In this case, the address is a runtime constant, so at + * the very least we can patch the call to e a simple direct call, or + * ideally, patch an inline implementation into the callsite. (Direct + * calls are essentially free, because the call and return addresses + * are completely predictable.) + * + * For i386, these macros rely on the standard gcc "regparm(3)" calling + * convention, in which the first three arguments are placed in %eax, + * %edx, %ecx (in that order), and the remaining arguments are placed + * on the stack. All caller-save registers (eax,edx,ecx) are expected + * to be modified (either clobbered or used for return values). + * X86_64, on the other hand, already specifies a register-based calling + * conventions, returning at %rax, with parameteres going on %rdi, %rsi, + * %rdx, and %rcx. Note that for this reason, x86_64 does not need any + * special handling for dealing with 4 arguments, unlike i386. + * However, x86_64 also have to clobber all caller saved registers, which + * unfortunately, are quite a bit (r8 - r11) + * + * The call instruction itself is marked by placing its start address + * and size into the .parainstructions section, so that + * apply_paravirt() in arch/i386/kernel/alternative.c can do the + * appropriate patching under the control of the backend pv_init_ops + * implementation. + * + * Unfortunately there's no way to get gcc to generate the args setup + * for the call, and then allow the call itself to be generated by an + * inline asm. Because of this, we must do the complete arg setup and + * return value handling from within these macros. This is fairly + * cumbersome. + * + * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments. + * It could be extended to more arguments, but there would be little + * to be gained from that. For each number of arguments, there are + * the two VCALL and CALL variants for void and non-void functions. + * + * When there is a return value, the invoker of the macro must specify + * the return type. The macro then uses sizeof() on that type to + * determine whether its a 32 or 64 bit value, and places the return + * in the right register(s) (just %eax for 32-bit, and %edx:%eax for + * 64-bit). For x86_64 machines, it just returns at %rax regardless of + * the return value size. + * + * 64-bit arguments are passed as a pair of adjacent 32-bit arguments + * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments + * in low,high order + * + * Small structures are passed and returned in registers. The macro + * calling convention can't directly deal with this, so the wrapper + * functions must do this. + * + * These PVOP_* macros are only defined within this header. This + * means that all uses must be wrapped in inline functions. This also + * makes sure the incoming and outgoing types are always correct. + */ +#ifdef CONFIG_X86_32 +#define PVOP_VCALL_ARGS \ + unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx +#define PVOP_CALL_ARGS PVOP_VCALL_ARGS + +#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) +#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x)) +#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x)) + +#define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \ + "=c" (__ecx) +#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS + +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx) +#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS + +#define EXTRA_CLOBBERS +#define VEXTRA_CLOBBERS +#else /* CONFIG_X86_64 */ +#define PVOP_VCALL_ARGS \ + unsigned long __edi = __edi, __esi = __esi, \ + __edx = __edx, __ecx = __ecx +#define PVOP_CALL_ARGS PVOP_VCALL_ARGS, __eax + +#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) +#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x)) +#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x)) +#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x)) + +#define PVOP_VCALL_CLOBBERS "=D" (__edi), \ + "=S" (__esi), "=d" (__edx), \ + "=c" (__ecx) +#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax) + +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax) +#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS + +#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11" +#define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11" +#endif /* CONFIG_X86_32 */ + +#ifdef CONFIG_PARAVIRT_DEBUG +#define PVOP_TEST_NULL(op) BUG_ON(op == NULL) +#else +#define PVOP_TEST_NULL(op) ((void)op) +#endif + +#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \ + pre, post, ...) \ + ({ \ + rettype __ret; \ + PVOP_CALL_ARGS; \ + PVOP_TEST_NULL(op); \ + /* This is 32-bit specific, but is okay in 64-bit */ \ + /* since this condition will never hold */ \ + if (sizeof(rettype) > sizeof(unsigned long)) { \ + asm volatile(pre \ + paravirt_alt(PARAVIRT_CALL) \ + post \ + : call_clbr \ + : paravirt_type(op), \ + paravirt_clobber(clbr), \ + ##__VA_ARGS__ \ + : "memory", "cc" extra_clbr); \ + __ret = (rettype)((((u64)__edx) << 32) | __eax); \ + } else { \ + asm volatile(pre \ + paravirt_alt(PARAVIRT_CALL) \ + post \ + : call_clbr \ + : paravirt_type(op), \ + paravirt_clobber(clbr), \ + ##__VA_ARGS__ \ + : "memory", "cc" extra_clbr); \ + __ret = (rettype)__eax; \ + } \ + __ret; \ + }) + +#define __PVOP_CALL(rettype, op, pre, post, ...) \ + ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \ + EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__) + +#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \ + ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ + PVOP_CALLEE_CLOBBERS, , \ + pre, post, ##__VA_ARGS__) + + +#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \ + ({ \ + PVOP_VCALL_ARGS; \ + PVOP_TEST_NULL(op); \ + asm volatile(pre \ + paravirt_alt(PARAVIRT_CALL) \ + post \ + : call_clbr \ + : paravirt_type(op), \ + paravirt_clobber(clbr), \ + ##__VA_ARGS__ \ + : "memory", "cc" extra_clbr); \ + }) + +#define __PVOP_VCALL(op, pre, post, ...) \ + ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \ + VEXTRA_CLOBBERS, \ + pre, post, ##__VA_ARGS__) + +#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...) \ + ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ + PVOP_VCALLEE_CLOBBERS, , \ + pre, post, ##__VA_ARGS__) + + + +#define PVOP_CALL0(rettype, op) \ + __PVOP_CALL(rettype, op, "", "") +#define PVOP_VCALL0(op) \ + __PVOP_VCALL(op, "", "") + +#define PVOP_CALLEE0(rettype, op) \ + __PVOP_CALLEESAVE(rettype, op, "", "") +#define PVOP_VCALLEE0(op) \ + __PVOP_VCALLEESAVE(op, "", "") + + +#define PVOP_CALL1(rettype, op, arg1) \ + __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) +#define PVOP_VCALL1(op, arg1) \ + __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1)) + +#define PVOP_CALLEE1(rettype, op, arg1) \ + __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) +#define PVOP_VCALLEE1(op, arg1) \ + __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1)) + + +#define PVOP_CALL2(rettype, op, arg1, arg2) \ + __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) +#define PVOP_VCALL2(op, arg1, arg2) \ + __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) + +#define PVOP_CALLEE2(rettype, op, arg1, arg2) \ + __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) +#define PVOP_VCALLEE2(op, arg1, arg2) \ + __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2)) + + +#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \ + __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) +#define PVOP_VCALL3(op, arg1, arg2, arg3) \ + __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) + +/* This is the only difference in x86_64. We can make it much simpler */ +#ifdef CONFIG_X86_32 +#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ + __PVOP_CALL(rettype, op, \ + "push %[_arg4];", "lea 4(%%esp),%%esp;", \ + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4))) +#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ + __PVOP_VCALL(op, \ + "push %[_arg4];", "lea 4(%%esp),%%esp;", \ + "0" ((u32)(arg1)), "1" ((u32)(arg2)), \ + "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) +#else +#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ + __PVOP_CALL(rettype, op, "", "", \ + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) +#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ + __PVOP_VCALL(op, "", "", \ + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) +#endif + +/* Lazy mode for batching updates / context switch */ +enum paravirt_lazy_mode { + PARAVIRT_LAZY_NONE, + PARAVIRT_LAZY_MMU, + PARAVIRT_LAZY_CPU, +}; + +enum paravirt_lazy_mode paravirt_get_lazy_mode(void); +void paravirt_start_context_switch(struct task_struct *prev); +void paravirt_end_context_switch(struct task_struct *next); + +void paravirt_enter_lazy_mmu(void); +void paravirt_leave_lazy_mmu(void); + +void _paravirt_nop(void); +u32 _paravirt_ident_32(u32); +u64 _paravirt_ident_64(u64); + +#define paravirt_nop ((void *)_paravirt_nop) + +/* These all sit in the .parainstructions section to tell us what to patch. */ +struct paravirt_patch_site { + u8 *instr; /* original instructions */ + u8 instrtype; /* type of this instruction */ + u8 len; /* length of original instruction */ + u16 clobbers; /* what registers you may clobber */ +}; + +extern struct paravirt_patch_site __parainstructions[], + __parainstructions_end[]; + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_PARAVIRT_TYPES_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ac7e79654f3a..e08ea043e085 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -713,13 +713,23 @@ static inline void cpu_relax(void) rep_nop(); } -/* Stop speculative execution: */ +/* Stop speculative execution and prefetching of modified code. */ static inline void sync_core(void) { int tmp; - asm volatile("cpuid" : "=a" (tmp) : "0" (1) - : "ebx", "ecx", "edx", "memory"); +#if defined(CONFIG_M386) || defined(CONFIG_M486) + if (boot_cpu_data.x86 < 5) + /* There is no speculative execution. + * jmp is a barrier to prefetching. */ + asm volatile("jmp 1f\n1:\n" ::: "memory"); + else +#endif + /* cpuid is a barrier to speculative execution. + * Prefetched instructions are automatically + * invalidated when modified. */ + asm volatile("cpuid" : "=a" (tmp) : "0" (1) + : "ebx", "ecx", "edx", "memory"); } static inline void __monitor(const void *eax, unsigned long ecx, diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 486935143e02..de7353c0ce9c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -498,8 +498,8 @@ static void *__init_or_module text_poke_early(void *addr, const void *opcode, unsigned long flags; local_irq_save(flags); memcpy(addr, opcode, len); - local_irq_restore(flags); sync_core(); + local_irq_restore(flags); /* Could also do a CLFLUSH here to speed up CPU recovery; but that causes hangs on some VIA CPUs. */ return addr; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 83b217c7225f..22a47c82f3c0 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -253,6 +253,64 @@ static int __cpuinit nearby_node(int apicid) #endif /* + * Fixup core topology information for AMD multi-node processors. + * Assumption 1: Number of cores in each internal node is the same. + * Assumption 2: Mixed systems with both single-node and dual-node + * processors are not supported. + */ +#ifdef CONFIG_X86_HT +static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_PCI + u32 t, cpn; + u8 n, n_id; + int cpu = smp_processor_id(); + + /* fixup topology information only once for a core */ + if (cpu_has(c, X86_FEATURE_AMD_DCM)) + return; + + /* check for multi-node processor on boot cpu */ + t = read_pci_config(0, 24, 3, 0xe8); + if (!(t & (1 << 29))) + return; + + set_cpu_cap(c, X86_FEATURE_AMD_DCM); + + /* cores per node: each internal node has half the number of cores */ + cpn = c->x86_max_cores >> 1; + + /* even-numbered NB_id of this dual-node processor */ + n = c->phys_proc_id << 1; + + /* + * determine internal node id and assign cores fifty-fifty to + * each node of the dual-node processor + */ + t = read_pci_config(0, 24 + n, 3, 0xe8); + n = (t>>30) & 0x3; + if (n == 0) { + if (c->cpu_core_id < cpn) + n_id = 0; + else + n_id = 1; + } else { + if (c->cpu_core_id < cpn) + n_id = 1; + else + n_id = 0; + } + + /* compute entire NodeID, use llc_shared_map to store sibling info */ + per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id; + + /* fixup core id to be in range from 0 to cpn */ + c->cpu_core_id = c->cpu_core_id % cpn; +#endif +} +#endif + +/* * On a AMD dual core setup the lower bits of the APIC id distingush the cores. * Assumes number of cores is a power of two. */ @@ -269,6 +327,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c) c->phys_proc_id = c->initial_apicid >> bits; /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; + /* fixup topology information on multi-node processors */ + if ((c->x86 == 0x10) && (c->x86_model == 9)) + amd_fixup_dcm(c); #endif } @@ -277,9 +338,10 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c) #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64) int cpu = smp_processor_id(); int node; - unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid; + unsigned apicid = c->apicid; + + node = per_cpu(cpu_llc_id, cpu); - node = c->phys_proc_id; if (apicid_to_node[apicid] != NUMA_NO_NODE) node = apicid_to_node[apicid]; if (!node_online(node)) { @@ -406,12 +468,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) /* * Some BIOSes incorrectly force this feature, but only K8 * revision D (model = 0x14) and later actually support it. + * (AMD Erratum #110, docId: 25759). */ - if (c->x86_model < 0x14) + if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) { + u64 val; + clear_cpu_cap(c, X86_FEATURE_LAHF_LM); + if (!rdmsrl_amd_safe(0xc001100d, &val)) { + val &= ~(1ULL << 32); + wrmsrl_amd_safe(0xc001100d, val); + } + } + } if (c->x86 == 0x10 || c->x86 == 0x11) set_cpu_cap(c, X86_FEATURE_REP_GOOD); + + /* get apicid instead of initial apic id from cpuid */ + c->apicid = hard_smp_processor_id(); #else /* diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index 306bf0dca061..804c40e2bc3e 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -241,7 +241,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, case 0: if (!l1->val) return; - assoc = l1->assoc; + assoc = assocs[l1->assoc]; line_size = l1->line_size; lines_per_tag = l1->lines_per_tag; size_in_kb = l1->size_in_kb; @@ -249,7 +249,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, case 2: if (!l2.val) return; - assoc = l2.assoc; + assoc = assocs[l2.assoc]; line_size = l2.line_size; lines_per_tag = l2.lines_per_tag; /* cpu_data has errata corrections for K7 applied */ @@ -258,10 +258,14 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, case 3: if (!l3.val) return; - assoc = l3.assoc; + assoc = assocs[l3.assoc]; line_size = l3.line_size; lines_per_tag = l3.lines_per_tag; size_in_kb = l3.size_encoded * 512; + if (boot_cpu_has(X86_FEATURE_AMD_DCM)) { + size_in_kb = size_in_kb >> 1; + assoc = assoc >> 1; + } break; default: return; @@ -270,18 +274,14 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, eax->split.is_self_initializing = 1; eax->split.type = types[leaf]; eax->split.level = levels[leaf]; - if (leaf == 3) - eax->split.num_threads_sharing = - current_cpu_data.x86_max_cores - 1; - else - eax->split.num_threads_sharing = 0; + eax->split.num_threads_sharing = 0; eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1; - if (assoc == 0xf) + if (assoc == 0xffff) eax->split.is_fully_associative = 1; ebx->split.coherency_line_size = line_size - 1; - ebx->split.ways_of_associativity = assocs[assoc] - 1; + ebx->split.ways_of_associativity = assoc - 1; ebx->split.physical_line_partition = lines_per_tag - 1; ecx->split.number_of_sets = (size_in_kb * 1024) / line_size / (ebx->split.ways_of_associativity + 1) - 1; @@ -523,6 +523,18 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index) int index_msb, i; struct cpuinfo_x86 *c = &cpu_data(cpu); + if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) { + struct cpuinfo_x86 *d; + for_each_online_cpu(i) { + if (!per_cpu(cpuid4_info, i)) + continue; + d = &cpu_data(i); + this_leaf = CPUID4_INFO_IDX(i, index); + cpumask_copy(to_cpumask(this_leaf->shared_cpu_map), + d->llc_shared_map); + } + return; + } this_leaf = CPUID4_INFO_IDX(cpu, index); num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index ddae21620bda..1fecba404fd8 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -489,12 +489,14 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) int i, err = 0; struct threshold_bank *b = NULL; char name[32]; + struct cpuinfo_x86 *c = &cpu_data(cpu); + sprintf(name, "threshold_bank%i", bank); #ifdef CONFIG_SMP if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */ - i = cpumask_first(cpu_core_mask(cpu)); + i = cpumask_first(c->llc_shared_map); /* first core not up yet */ if (cpu_data(i).cpu_core_id) @@ -514,7 +516,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) if (err) goto out; - cpumask_copy(b->cpus, cpu_core_mask(cpu)); + cpumask_copy(b->cpus, c->llc_shared_map); per_cpu(threshold_banks, cpu)[bank] = b; goto out; @@ -539,7 +541,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) #ifndef CONFIG_SMP cpumask_setall(b->cpus); #else - cpumask_copy(b->cpus, cpu_core_mask(cpu)); + cpumask_copy(b->cpus, c->llc_shared_map); #endif per_cpu(threshold_banks, cpu)[bank] = b; diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 1e904346bbf4..62ac8cb6ba27 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -116,11 +116,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize); #endif seq_printf(m, "clflush size\t: %u\n", c->x86_clflush_size); -#ifdef CONFIG_X86_64 seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment); seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", c->x86_phys_bits, c->x86_virt_bits); -#endif seq_printf(m, "power management:"); for (i = 0; i < 32; i++) { diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 98fd6cd4e3a4..7dd950094178 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -1,6 +1,7 @@ /* ----------------------------------------------------------------------- * * * Copyright 2000-2008 H. Peter Anvin - All Rights Reserved + * Copyright 2009 Intel Corporation; author: H. Peter Anvin * * 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 @@ -80,11 +81,8 @@ static ssize_t msr_read(struct file *file, char __user *buf, for (; count; count -= 8) { err = rdmsr_safe_on_cpu(cpu, reg, &data[0], &data[1]); - if (err) { - if (err == -EFAULT) /* Fix idiotic error code */ - err = -EIO; + if (err) break; - } if (copy_to_user(tmp, &data, 8)) { err = -EFAULT; break; @@ -115,11 +113,8 @@ static ssize_t msr_write(struct file *file, const char __user *buf, break; } err = wrmsr_safe_on_cpu(cpu, reg, data[0], data[1]); - if (err) { - if (err == -EFAULT) /* Fix idiotic error code */ - err = -EIO; + if (err) break; - } tmp += 2; bytes += 8; } @@ -127,6 +122,54 @@ static ssize_t msr_write(struct file *file, const char __user *buf, return bytes ? bytes : err; } +static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) +{ + u32 __user *uregs = (u32 __user *)arg; + u32 regs[8]; + int cpu = iminor(file->f_path.dentry->d_inode); + int err; + + switch (ioc) { + case X86_IOC_RDMSR_REGS: + if (!(file->f_mode & FMODE_READ)) { + err = -EBADF; + break; + } + if (copy_from_user(®s, uregs, sizeof regs)) { + err = -EFAULT; + break; + } + err = rdmsr_safe_regs_on_cpu(cpu, regs); + if (err) + break; + if (copy_to_user(uregs, ®s, sizeof regs)) + err = -EFAULT; + break; + + case X86_IOC_WRMSR_REGS: + if (!(file->f_mode & FMODE_WRITE)) { + err = -EBADF; + break; + } + if (copy_from_user(®s, uregs, sizeof regs)) { + err = -EFAULT; + break; + } + err = wrmsr_safe_regs_on_cpu(cpu, regs); + if (err) + break; + if (copy_to_user(uregs, ®s, sizeof regs)) + err = -EFAULT; + break; + + default: + err = -ENOTTY; + break; + } + + return err; +} + static int msr_open(struct inode *inode, struct file *file) { unsigned int cpu = iminor(file->f_path.dentry->d_inode); @@ -157,6 +200,8 @@ static const struct file_operations msr_fops = { .read = msr_read, .write = msr_write, .open = msr_open, + .unlocked_ioctl = msr_ioctl, + .compat_ioctl = msr_ioctl, }; static int __cpuinit msr_device_create(int cpu) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 70ec9b951d76..f5b0b4a01fb2 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -362,8 +362,9 @@ struct pv_cpu_ops pv_cpu_ops = { #endif .wbinvd = native_wbinvd, .read_msr = native_read_msr_safe, - .read_msr_amd = native_read_msr_amd_safe, + .rdmsr_regs = native_rdmsr_safe_regs, .write_msr = native_write_msr_safe, + .wrmsr_regs = native_wrmsr_safe_regs, .read_tsc = native_read_tsc, .read_pmc = native_read_pmc, .read_tscp = native_read_tscp, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2fecda69ee64..c36cc1452cdc 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -434,7 +434,8 @@ const struct cpumask *cpu_coregroup_mask(int cpu) * For perf, we return last level cache shared map. * And for power savings, we return cpu_core_map */ - if (sched_mc_power_savings || sched_smt_power_savings) + if ((sched_mc_power_savings || sched_smt_power_savings) && + !(cpu_has(c, X86_FEATURE_AMD_DCM))) return cpu_core_mask(cpu); else return c->llc_shared_map; diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 07c31899c9c2..9e609206fac9 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -9,6 +9,8 @@ lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o getuser.o putuser.o lib-y += memcpy_$(BITS).o +obj-y += msr-reg.o msr-reg-export.o + ifeq ($(CONFIG_X86_32),y) obj-y += atomic64_32.o lib-y += checksum_32.o diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c new file mode 100644 index 000000000000..a311cc59b65d --- /dev/null +++ b/arch/x86/lib/msr-reg-export.c @@ -0,0 +1,5 @@ +#include <linux/module.h> +#include <asm/msr.h> + +EXPORT_SYMBOL(native_rdmsr_safe_regs); +EXPORT_SYMBOL(native_wrmsr_safe_regs); diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S new file mode 100644 index 000000000000..69fa10623f21 --- /dev/null +++ b/arch/x86/lib/msr-reg.S @@ -0,0 +1,102 @@ +#include <linux/linkage.h> +#include <linux/errno.h> +#include <asm/dwarf2.h> +#include <asm/asm.h> +#include <asm/msr.h> + +#ifdef CONFIG_X86_64 +/* + * int native_{rdmsr,wrmsr}_safe_regs(u32 gprs[8]); + * + * reg layout: u32 gprs[eax, ecx, edx, ebx, esp, ebp, esi, edi] + * + */ +.macro op_safe_regs op +ENTRY(native_\op\()_safe_regs) + CFI_STARTPROC + pushq_cfi %rbx + pushq_cfi %rbp + movq %rdi, %r10 /* Save pointer */ + xorl %r11d, %r11d /* Return value */ + movl (%rdi), %eax + movl 4(%rdi), %ecx + movl 8(%rdi), %edx + movl 12(%rdi), %ebx + movl 20(%rdi), %ebp + movl 24(%rdi), %esi + movl 28(%rdi), %edi + CFI_REMEMBER_STATE +1: \op +2: movl %eax, (%r10) + movl %r11d, %eax /* Return value */ + movl %ecx, 4(%r10) + movl %edx, 8(%r10) + movl %ebx, 12(%r10) + movl %ebp, 20(%r10) + movl %esi, 24(%r10) + movl %edi, 28(%r10) + popq_cfi %rbp + popq_cfi %rbx + ret +3: + CFI_RESTORE_STATE + movl $-EIO, %r11d + jmp 2b + + _ASM_EXTABLE(1b, 3b) + CFI_ENDPROC +ENDPROC(native_\op\()_safe_regs) +.endm + +#else /* X86_32 */ + +.macro op_safe_regs op +ENTRY(native_\op\()_safe_regs) + CFI_STARTPROC + pushl_cfi %ebx + pushl_cfi %ebp + pushl_cfi %esi + pushl_cfi %edi + pushl_cfi $0 /* Return value */ + pushl_cfi %eax + movl 4(%eax), %ecx + movl 8(%eax), %edx + movl 12(%eax), %ebx + movl 20(%eax), %ebp + movl 24(%eax), %esi + movl 28(%eax), %edi + movl (%eax), %eax + CFI_REMEMBER_STATE +1: \op +2: pushl_cfi %eax + movl 4(%esp), %eax + popl_cfi (%eax) + addl $4, %esp + CFI_ADJUST_CFA_OFFSET -4 + movl %ecx, 4(%eax) + movl %edx, 8(%eax) + movl %ebx, 12(%eax) + movl %ebp, 20(%eax) + movl %esi, 24(%eax) + movl %edi, 28(%eax) + popl_cfi %eax + popl_cfi %edi + popl_cfi %esi + popl_cfi %ebp + popl_cfi %ebx + ret +3: + CFI_RESTORE_STATE + movl $-EIO, 4(%esp) + jmp 2b + + _ASM_EXTABLE(1b, 3b) + CFI_ENDPROC +ENDPROC(native_\op\()_safe_regs) +.endm + +#endif + +op_safe_regs rdmsr +op_safe_regs wrmsr + diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index caa24aca8115..33a1e3ca22d8 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -175,3 +175,52 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h) return err ? err : rv.err; } EXPORT_SYMBOL(wrmsr_safe_on_cpu); + +/* + * These variants are significantly slower, but allows control over + * the entire 32-bit GPR set. + */ +struct msr_regs_info { + u32 *regs; + int err; +}; + +static void __rdmsr_safe_regs_on_cpu(void *info) +{ + struct msr_regs_info *rv = info; + + rv->err = rdmsr_safe_regs(rv->regs); +} + +static void __wrmsr_safe_regs_on_cpu(void *info) +{ + struct msr_regs_info *rv = info; + + rv->err = wrmsr_safe_regs(rv->regs); +} + +int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +{ + int err; + struct msr_regs_info rv; + + rv.regs = regs; + rv.err = -EIO; + err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu); + +int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +{ + int err; + struct msr_regs_info rv; + + rv.regs = regs; + rv.err = -EIO; + err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1); + + return err ? err : rv.err; +} +EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index eb33aaa8415d..b62ccb840cfb 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -714,7 +714,7 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) set: base = ((u64)high << 32) | low; if (HYPERVISOR_set_segment_base(which, base) != 0) - ret = -EFAULT; + ret = -EIO; break; #endif |