diff options
Diffstat (limited to 'arch/x86/include/asm/processor.h')
| -rw-r--r-- | arch/x86/include/asm/processor.h | 324 |
1 files changed, 140 insertions, 184 deletions
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 45636cefa18..a4ea02351f4 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -14,21 +14,29 @@ struct mm_struct; #include <asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeature.h> -#include <asm/system.h> #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> #include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> +#include <asm/special_insns.h> #include <linux/personality.h> #include <linux/cpumask.h> #include <linux/cache.h> #include <linux/threads.h> #include <linux/math64.h> -#include <linux/init.h> #include <linux/err.h> +#include <linux/irqflags.h> + +/* + * We handle most unaligned accesses in hardware. On the other hand + * unaligned DMA can be quite expensive on some Nehalem processors. + * + * Based on this we disable the IP header alignment in network drivers. + */ +#define NET_IP_ALIGN 0 #define HBP_NUM 4 /* @@ -52,6 +60,20 @@ static inline void *current_text_addr(void) # define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif +enum tlb_infos { + ENTRIES, + NR_INFO +}; + +extern u16 __read_mostly tlb_lli_4k[NR_INFO]; +extern u16 __read_mostly tlb_lli_2m[NR_INFO]; +extern u16 __read_mostly tlb_lli_4m[NR_INFO]; +extern u16 __read_mostly tlb_lld_4k[NR_INFO]; +extern u16 __read_mostly tlb_lld_2m[NR_INFO]; +extern u16 __read_mostly tlb_lld_4m[NR_INFO]; +extern u16 __read_mostly tlb_lld_1g[NR_INFO]; +extern s8 __read_mostly tlb_flushall_shift; + /* * CPU type and hardware bug flags. Kept separately for each CPU. * Members of this structure are referenced in head.S, so think twice @@ -67,13 +89,9 @@ struct cpuinfo_x86 { char wp_works_ok; /* It doesn't on 386's */ /* Problems on some 486Dx4's and old 386's: */ - char hlt_works_ok; - char hard_math; char rfu; - char fdiv_bug; - char f00f_bug; - char coma_bug; char pad0; + char pad1; #else /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; @@ -86,7 +104,7 @@ struct cpuinfo_x86 { __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ int cpuid_level; - __u32 x86_capability[NCAPINTS]; + __u32 x86_capability[NCAPINTS + NBUGINTS]; char x86_vendor_id[16]; char x86_model_id[64]; /* in KB - valid for CPUS which support this call: */ @@ -94,16 +112,11 @@ struct cpuinfo_x86 { int x86_cache_alignment; /* In bytes */ int x86_power; unsigned long loops_per_jiffy; -#ifdef CONFIG_SMP - /* cpus sharing the last level cache: */ - cpumask_var_t llc_shared_map; -#endif /* cpuid returned max cores value: */ u16 x86_max_cores; u16 apicid; u16 initial_apicid; u16 x86_clflush_size; -#ifdef CONFIG_SMP /* number of cores as seen by the OS: */ u16 booted_cores; /* Physical processor id: */ @@ -114,7 +127,7 @@ struct cpuinfo_x86 { u8 compute_unit_id; /* Index into per_cpu list: */ u16 cpu_index; -#endif + u32 microcode; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define X86_VENDOR_INTEL 0 @@ -148,32 +161,31 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info); extern const struct seq_operations cpuinfo_op; -static inline int hlt_works(int cpu) -{ -#ifdef CONFIG_X86_32 - return cpu_data(cpu).hlt_works_ok; -#else - return 1; -#endif -} - #define cache_line_size() (boot_cpu_data.x86_cache_alignment) extern void cpu_detect(struct cpuinfo_x86 *c); - -extern struct pt_regs *idle_regs(struct pt_regs *); +extern void fpu_detect(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_boot_cpu(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); +void print_cpu_msr(struct cpuinfo_x86 *); extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c); extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); -extern unsigned short num_cache_leaves; +extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); extern void detect_extended_topology(struct cpuinfo_x86 *c); extern void detect_ht(struct cpuinfo_x86 *c); +#ifdef CONFIG_X86_32 +extern int have_cpuid_p(void); +#else +static inline int have_cpuid_p(void) +{ + return 1; +} +#endif static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { @@ -183,7 +195,8 @@ static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, "=b" (*ebx), "=c" (*ecx), "=d" (*edx) - : "0" (*eax), "2" (*ecx)); + : "0" (*eax), "2" (*ecx) + : "memory"); } static inline void load_cr3(pgd_t *pgdir) @@ -357,6 +370,20 @@ struct ymmh_struct { u32 ymmh_space[64]; }; +/* We don't support LWP yet: */ +struct lwp_struct { + u8 reserved[128]; +}; + +struct bndregs_struct { + u64 bndregs[8]; +} __packed; + +struct bndcsr_struct { + u64 cfg_reg_u; + u64 status_reg; +} __packed; + struct xsave_hdr_struct { u64 xstate_bv; u64 reserved1[2]; @@ -367,6 +394,9 @@ struct xsave_struct { struct i387_fxsave_struct i387; struct xsave_hdr_struct xsave_hdr; struct ymmh_struct ymmh; + struct lwp_struct lwp; + struct bndregs_struct bndregs; + struct bndcsr_struct bndcsr; /* new processor state extensions will go here */ } __attribute__ ((packed, aligned (64))); @@ -378,6 +408,8 @@ union thread_xstate { }; struct fpu { + unsigned int last_cpu; + unsigned int has_fpu; union thread_xstate *state; }; @@ -397,12 +429,11 @@ union irq_stack_union { }; }; -DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union); +DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible; DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); DECLARE_PER_CPU(unsigned int, irq_count); -extern unsigned long kernel_eflags; extern asmlinkage void ignore_sysret(void); #else /* X86_64 */ #ifdef CONFIG_CC_STACKPROTECTOR @@ -418,6 +449,15 @@ struct stack_canary { }; DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary); #endif +/* + * per-CPU IRQ handling stacks + */ +struct irq_stack { + u32 stack[THREAD_SIZE/sizeof(u32)]; +} __aligned(THREAD_SIZE); + +DECLARE_PER_CPU(struct irq_stack *, hardirq_stack); +DECLARE_PER_CPU(struct irq_stack *, softirq_stack); #endif /* X86_64 */ extern unsigned int xstate_size; @@ -455,7 +495,7 @@ struct thread_struct { unsigned long ptrace_dr7; /* Fault info: */ unsigned long cr2; - unsigned long trap_no; + unsigned long trap_nr; unsigned long error_code; /* floating point and extended processor state */ struct fpu fpu; @@ -474,63 +514,17 @@ struct thread_struct { unsigned long iopl; /* Max allowed port in the bitmap, in bytes: */ unsigned io_bitmap_max; + /* + * fpu_counter contains the number of consecutive context switches + * that the FPU is used. If this is over a threshold, the lazy fpu + * saving becomes unlazy to save the trap. This is an unsigned char + * so that after 256 times the counter wraps and the behavior turns + * lazy again; this to deal with bursty apps that only use FPU for + * a short time + */ + unsigned char fpu_counter; }; -static inline unsigned long native_get_debugreg(int regno) -{ - unsigned long val = 0; /* Damn you, gcc! */ - - switch (regno) { - case 0: - asm("mov %%db0, %0" :"=r" (val)); - break; - case 1: - asm("mov %%db1, %0" :"=r" (val)); - break; - case 2: - asm("mov %%db2, %0" :"=r" (val)); - break; - case 3: - asm("mov %%db3, %0" :"=r" (val)); - break; - case 6: - asm("mov %%db6, %0" :"=r" (val)); - break; - case 7: - asm("mov %%db7, %0" :"=r" (val)); - break; - default: - BUG(); - } - return val; -} - -static inline void native_set_debugreg(int regno, unsigned long value) -{ - switch (regno) { - case 0: - asm("mov %0, %%db0" ::"r" (value)); - break; - case 1: - asm("mov %0, %%db1" ::"r" (value)); - break; - case 2: - asm("mov %0, %%db2" ::"r" (value)); - break; - case 3: - asm("mov %0, %%db3" ::"r" (value)); - break; - case 6: - asm("mov %0, %%db6" ::"r" (value)); - break; - case 7: - asm("mov %0, %%db7" ::"r" (value)); - break; - default: - BUG(); - } -} - /* * Set IOPL bits in EFLAGS from given mask */ @@ -576,14 +570,6 @@ static inline void native_swapgs(void) #define __cpuid native_cpuid #define paravirt_enabled() 0 -/* - * These special macros can be used to get or set a debugging register - */ -#define get_debugreg(var, register) \ - (var) = native_get_debugreg(register) -#define set_debugreg(value, register) \ - native_set_debugreg(register, value) - static inline void load_sp0(struct tss_struct *tss, struct thread_struct *thread) { @@ -599,13 +585,16 @@ static inline void load_sp0(struct tss_struct *tss, * enable), so that any CPU's that boot up * after us can get the correct flags. */ -extern unsigned long mmu_cr4_features; +extern unsigned long mmu_cr4_features; +extern u32 *trampoline_cr4_features; static inline void set_in_cr4(unsigned long mask) { unsigned long cr4; mmu_cr4_features |= mask; + if (trampoline_cr4_features) + *trampoline_cr4_features = mmu_cr4_features; cr4 = read_cr4(); cr4 |= mask; write_cr4(cr4); @@ -616,6 +605,8 @@ static inline void clear_in_cr4(unsigned long mask) unsigned long cr4; mmu_cr4_features &= ~mask; + if (trampoline_cr4_features) + *trampoline_cr4_features = mmu_cr4_features; cr4 = read_cr4(); cr4 &= ~mask; write_cr4(cr4); @@ -626,17 +617,9 @@ typedef struct { } mm_segment_t; -/* - * create a kernel thread without removing it from tasklists - */ -extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); - /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -/* Prepare to copy thread state - unlazy all lazy state */ -extern void prepare_to_copy(struct task_struct *tsk); - unsigned long get_wchan(struct task_struct *p); /* @@ -718,58 +701,45 @@ static inline void sync_core(void) { int tmp; -#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 +#ifdef CONFIG_M486 + /* + * Do a CPUID if available, otherwise do a jump. The jump + * can conveniently enough be the jump around CPUID. + */ + asm volatile("cmpl %2,%1\n\t" + "jl 1f\n\t" + "cpuid\n" + "1:" + : "=a" (tmp) + : "rm" (boot_cpu_data.cpuid_level), "ri" (0), "0" (1) + : "ebx", "ecx", "edx", "memory"); +#else + /* + * 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"); #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, - unsigned long edx) -{ - /* "monitor %eax, %ecx, %edx;" */ - asm volatile(".byte 0x0f, 0x01, 0xc8;" - :: "a" (eax), "c" (ecx), "d"(edx)); -} - -static inline void __mwait(unsigned long eax, unsigned long ecx) -{ - /* "mwait %eax, %ecx;" */ - asm volatile(".byte 0x0f, 0x01, 0xc9;" - :: "a" (eax), "c" (ecx)); } -static inline void __sti_mwait(unsigned long eax, unsigned long ecx) -{ - trace_hardirqs_on(); - /* "mwait %eax, %ecx;" */ - asm volatile("sti; .byte 0x0f, 0x01, 0xc9;" - :: "a" (eax), "c" (ecx)); -} - -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 void init_amd_e400_c1e_mask(void); extern unsigned long boot_option_idle_override; -extern bool c1e_detected; +extern bool amd_e400_c1e_detected; enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, - IDLE_POLL, IDLE_FORCE_MWAIT}; + IDLE_POLL}; extern void enable_sep_cpu(void); extern int sysenter_setup(void); extern void early_trap_init(void); +void early_trap_pf_init(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; @@ -801,6 +771,8 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr) wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); } +extern void set_task_blockstep(struct task_struct *task, bool on); + /* * from system description table in BIOS. Mostly for MCA use, but * others may find it useful: @@ -930,9 +902,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ 0xc0000000 : 0xFFFFe000) -#define TASK_SIZE (test_thread_flag(TIF_IA32) ? \ +#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) -#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \ +#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ IA32_PAGE_OFFSET : TASK_SIZE_MAX) #define STACK_TOP TASK_SIZE @@ -954,6 +926,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); + +/* + * User space RSP while inside the SYSCALL fast path + */ +DECLARE_PER_CPU(unsigned long, old_rsp); + #endif /* CONFIG_X86_64 */ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, @@ -974,55 +952,33 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip, extern int get_tsc_mode(unsigned long adr); extern int set_tsc_mode(unsigned int val); -extern int amd_get_nb_id(int cpu); +extern u16 amd_get_nb_id(int cpu); -struct aperfmperf { - u64 aperf, mperf; -}; - -static inline void get_aperfmperf(struct aperfmperf *am) +static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { - WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF)); - - rdmsrl(MSR_IA32_APERF, am->aperf); - rdmsrl(MSR_IA32_MPERF, am->mperf); -} - -#define APERFMPERF_SHIFT 10 + uint32_t base, eax, signature[3]; -static inline -unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, - struct aperfmperf *new) -{ - u64 aperf = new->aperf - old->aperf; - u64 mperf = new->mperf - old->mperf; - unsigned long ratio = aperf; + for (base = 0x40000000; base < 0x40010000; base += 0x100) { + cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); - mperf >>= APERFMPERF_SHIFT; - if (mperf) - ratio = div64_u64(aperf, mperf); + if (!memcmp(sig, signature, 12) && + (leaves == 0 || ((eax - base) >= leaves))) + return base; + } - return ratio; + return 0; } -/* - * AMD errata checking - */ -#ifdef CONFIG_CPU_SUP_AMD -extern const int amd_erratum_383[]; -extern const int amd_erratum_400[]; -extern bool cpu_has_amd_erratum(const int *); - -#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } -#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } -#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ - ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) -#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) -#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) -#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) +extern unsigned long arch_align_stack(unsigned long sp); +extern void free_init_pages(char *what, unsigned long begin, unsigned long end); +void default_idle(void); +#ifdef CONFIG_XEN +bool xen_set_default_idle(void); #else -#define cpu_has_amd_erratum(x) (false) -#endif /* CONFIG_CPU_SUP_AMD */ +#define xen_set_default_idle 0 +#endif +void stop_this_cpu(void *dummy); +void df_debug(struct pt_regs *regs, long error_code); #endif /* _ASM_X86_PROCESSOR_H */ |