6,12 → 6,12 |
/* Forward declaration, a strange C thing */ |
struct task_struct; |
struct mm_struct; |
struct vm86; |
|
#include <asm/vm86.h> |
#include <asm/math_emu.h> |
#include <asm/segment.h> |
#include <asm/types.h> |
#include <asm/sigcontext.h> |
#include <uapi/asm/sigcontext.h> |
#include <asm/current.h> |
#include <asm/cpufeature.h> |
#include <asm/page.h> |
21,6 → 21,7 |
#include <asm/desc_defs.h> |
#include <asm/nops.h> |
#include <asm/special_insns.h> |
#include <asm/fpu/types.h> |
|
#include <linux/personality.h> |
#include <linux/cpumask.h> |
52,6 → 53,11 |
return pc; |
} |
|
/* |
* These alignment constraints are for performance in the vSMP case, |
* but in the task_struct case we must also meet hardware imposed |
* alignment requirements of the FPU state: |
*/ |
#ifdef CONFIG_X86_VSMP |
# define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT) |
# define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT) |
109,6 → 115,9 |
/* in KB - valid for CPUS which support this call: */ |
int x86_cache_size; |
int x86_cache_alignment; /* In bytes */ |
/* Cache QoS architectural values: */ |
int x86_cache_max_rmid; /* max index */ |
int x86_cache_occ_scale; /* scale to bytes */ |
int x86_power; |
unsigned long loops_per_jiffy; |
/* cpuid returned max cores value: */ |
160,10 → 169,7 |
|
extern const struct seq_operations cpuinfo_op; |
|
#define cache_line_size() (x86_cache_alignment) |
|
extern void cpu_detect(struct cpuinfo_x86 *c); |
extern void fpu_detect(struct cpuinfo_x86 *c); |
|
extern void early_cpu_init(void); |
extern void identify_boot_cpu(void); |
210,8 → 216,23 |
unsigned long sp0; |
unsigned short ss0, __ss0h; |
unsigned long sp1; |
/* ss1 caches MSR_IA32_SYSENTER_CS: */ |
unsigned short ss1, __ss1h; |
|
/* |
* We don't use ring 1, so ss1 is a convenient scratch space in |
* the same cacheline as sp0. We use ss1 to cache the value in |
* MSR_IA32_SYSENTER_CS. When we context switch |
* MSR_IA32_SYSENTER_CS, we first check if the new value being |
* written matches ss1, and, if it's not, then we wrmsr the new |
* value and update ss1. |
* |
* The only reason we context switch MSR_IA32_SYSENTER_CS is |
* that we set it to zero in vm86 tasks to avoid corrupting the |
* stack if we were to go through the sysenter path from vm86 |
* mode. |
*/ |
unsigned short ss1; /* MSR_IA32_SYSENTER_CS */ |
|
unsigned short __ss1h; |
unsigned long sp2; |
unsigned short ss2, __ss2h; |
unsigned long __cr3; |
276,14 → 297,18 |
unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; |
|
/* |
* .. and then another 0x100 bytes for the emergency kernel stack: |
* Space for the temporary SYSENTER stack: |
*/ |
unsigned long stack[64]; |
unsigned long SYSENTER_stack[64]; |
|
} ____cacheline_aligned; |
|
DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss); |
DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); |
|
#ifdef CONFIG_X86_32 |
DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); |
#endif |
|
/* |
* Save the original ist values for checking stack pointers during debugging |
*/ |
291,128 → 316,6 |
unsigned long ist[7]; |
}; |
|
#define MXCSR_DEFAULT 0x1f80 |
|
struct i387_fsave_struct { |
u32 cwd; /* FPU Control Word */ |
u32 swd; /* FPU Status Word */ |
u32 twd; /* FPU Tag Word */ |
u32 fip; /* FPU IP Offset */ |
u32 fcs; /* FPU IP Selector */ |
u32 foo; /* FPU Operand Pointer Offset */ |
u32 fos; /* FPU Operand Pointer Selector */ |
|
/* 8*10 bytes for each FP-reg = 80 bytes: */ |
u32 st_space[20]; |
|
/* Software status information [not touched by FSAVE ]: */ |
u32 status; |
}; |
|
struct i387_fxsave_struct { |
u16 cwd; /* Control Word */ |
u16 swd; /* Status Word */ |
u16 twd; /* Tag Word */ |
u16 fop; /* Last Instruction Opcode */ |
union { |
struct { |
u64 rip; /* Instruction Pointer */ |
u64 rdp; /* Data Pointer */ |
}; |
struct { |
u32 fip; /* FPU IP Offset */ |
u32 fcs; /* FPU IP Selector */ |
u32 foo; /* FPU Operand Offset */ |
u32 fos; /* FPU Operand Selector */ |
}; |
}; |
u32 mxcsr; /* MXCSR Register State */ |
u32 mxcsr_mask; /* MXCSR Mask */ |
|
/* 8*16 bytes for each FP-reg = 128 bytes: */ |
u32 st_space[32]; |
|
/* 16*16 bytes for each XMM-reg = 256 bytes: */ |
u32 xmm_space[64]; |
|
u32 padding[12]; |
|
union { |
u32 padding1[12]; |
u32 sw_reserved[12]; |
}; |
|
} __attribute__((aligned(16))); |
|
struct i387_soft_struct { |
u32 cwd; |
u32 swd; |
u32 twd; |
u32 fip; |
u32 fcs; |
u32 foo; |
u32 fos; |
/* 8*10 bytes for each FP-reg = 80 bytes: */ |
u32 st_space[20]; |
u8 ftop; |
u8 changed; |
u8 lookahead; |
u8 no_update; |
u8 rm; |
u8 alimit; |
struct math_emu_info *info; |
u32 entry_eip; |
}; |
|
struct ymmh_struct { |
/* 16 * 16 bytes for each YMMH-reg = 256 bytes */ |
u32 ymmh_space[64]; |
}; |
|
/* We don't support LWP yet: */ |
struct lwp_struct { |
u8 reserved[128]; |
}; |
|
struct bndreg { |
u64 lower_bound; |
u64 upper_bound; |
} __packed; |
|
struct bndcsr { |
u64 bndcfgu; |
u64 bndstatus; |
} __packed; |
|
struct xsave_hdr_struct { |
u64 xstate_bv; |
u64 xcomp_bv; |
u64 reserved[6]; |
} __attribute__((packed)); |
|
struct xsave_struct { |
struct i387_fxsave_struct i387; |
struct xsave_hdr_struct xsave_hdr; |
struct ymmh_struct ymmh; |
struct lwp_struct lwp; |
struct bndreg bndreg[4]; |
struct bndcsr bndcsr; |
/* new processor state extensions will go here */ |
} __attribute__ ((packed, aligned (64))); |
|
union thread_xstate { |
struct i387_fsave_struct fsave; |
struct i387_fxsave_struct fxsave; |
struct i387_soft_struct soft; |
struct xsave_struct xsave; |
}; |
|
struct fpu { |
unsigned int last_cpu; |
unsigned int has_fpu; |
union thread_xstate *state; |
}; |
|
#ifdef CONFIG_X86_64 |
DECLARE_PER_CPU(struct orig_ist, orig_ist); |
|
461,8 → 364,6 |
#endif /* X86_64 */ |
|
extern unsigned int xstate_size; |
extern void free_thread_xstate(struct task_struct *); |
extern struct kmem_cache *task_xstate_cachep; |
|
struct perf_event; |
|
474,7 → 375,6 |
#ifdef CONFIG_X86_32 |
unsigned long sysenter_cs; |
#else |
unsigned long usersp; /* Copy from PDA */ |
unsigned short es; |
unsigned short ds; |
unsigned short fsindex; |
487,6 → 387,7 |
unsigned long fs; |
#endif |
unsigned long gs; |
|
/* Save middle states of ptrace breakpoints */ |
struct perf_event *ptrace_bps[HBP_NUM]; |
/* Debug status used for traps, single steps, etc... */ |
497,17 → 398,9 |
unsigned long cr2; |
unsigned long trap_nr; |
unsigned long error_code; |
/* floating point and extended processor state */ |
struct fpu fpu; |
#ifdef CONFIG_X86_32 |
#ifdef CONFIG_VM86 |
/* Virtual 86 mode info */ |
struct vm86_struct __user *vm86_info; |
unsigned long screen_bitmap; |
unsigned long v86flags; |
unsigned long v86mask; |
unsigned long saved_sp0; |
unsigned int saved_fs; |
unsigned int saved_gs; |
struct vm86 *vm86; |
#endif |
/* IO permissions: */ |
unsigned long *io_bitmap_ptr; |
514,15 → 407,13 |
unsigned long iopl; |
/* Max allowed port in the bitmap, in bytes: */ |
unsigned io_bitmap_max; |
|
/* Floating point and extended processor state */ |
struct fpu fpu; |
/* |
* 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 |
* WARNING: 'fpu' is dynamically-sized. It *MUST* be at |
* the end. |
*/ |
unsigned char fpu_counter; |
}; |
|
/* |
564,11 → 455,13 |
#endif |
} |
|
|
#ifdef CONFIG_PARAVIRT |
#include <asm/paravirt.h> |
#else |
#define __cpuid native_cpuid |
#define paravirt_enabled() 0 |
#define paravirt_has(x) 0 |
|
static inline void load_sp0(struct tss_struct *tss, |
struct thread_struct *thread) |
579,39 → 472,6 |
#define set_iopl_mask native_set_iopl_mask |
#endif /* CONFIG_PARAVIRT */ |
|
/* |
* Save the cr4 feature set we're using (ie |
* Pentium 4MB enable and PPro Global page |
* enable), so that any CPU's that boot up |
* after us can get the correct flags. |
*/ |
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); |
} |
|
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); |
} |
|
typedef struct { |
unsigned long seg; |
} mm_segment_t; |
686,12 → 546,12 |
} |
|
/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ |
static inline void rep_nop(void) |
static __always_inline void rep_nop(void) |
{ |
asm volatile("rep; nop" ::: "memory"); |
} |
|
static inline void cpu_relax(void) |
static __always_inline void cpu_relax(void) |
{ |
rep_nop(); |
} |
775,14 → 635,6 |
|
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: |
*/ |
extern unsigned int machine_id; |
extern unsigned int machine_submodel_id; |
extern unsigned int BIOS_revision; |
|
/* Boot loader type from the setup header: */ |
extern int bootloader_type; |
extern int bootloader_version; |
794,10 → 646,10 |
#define ARCH_HAS_SPINLOCK_PREFETCH |
|
#ifdef CONFIG_X86_32 |
# define BASE_PREFETCH ASM_NOP4 |
# define BASE_PREFETCH "" |
# define ARCH_HAS_PREFETCH |
#else |
# define BASE_PREFETCH "prefetcht0 (%1)" |
# define BASE_PREFETCH "prefetcht0 %P1" |
#endif |
|
/* |
832,6 → 684,9 |
prefetchw(x); |
} |
|
#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ |
TOP_OF_KERNEL_STACK_PADDING) |
|
#ifdef CONFIG_X86_32 |
/* |
* User space process size: 3GB (default). |
842,39 → 697,15 |
#define STACK_TOP_MAX STACK_TOP |
|
#define INIT_THREAD { \ |
.sp0 = sizeof(init_stack) + (long)&init_stack, \ |
.vm86_info = NULL, \ |
.sp0 = TOP_OF_INIT_STACK, \ |
.sysenter_cs = __KERNEL_CS, \ |
.io_bitmap_ptr = NULL, \ |
} |
|
/* |
* Note that the .io_bitmap member must be extra-big. This is because |
* the CPU will access an additional byte beyond the end of the IO |
* permission bitmap. The extra byte must be all 1 bits, and must |
* be within the limit. |
*/ |
#define INIT_TSS { \ |
.x86_tss = { \ |
.sp0 = sizeof(init_stack) + (long)&init_stack, \ |
.ss0 = __KERNEL_DS, \ |
.ss1 = __KERNEL_CS, \ |
.io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \ |
}, \ |
.io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, \ |
} |
|
extern unsigned long thread_saved_pc(struct task_struct *tsk); |
|
#define THREAD_SIZE_LONGS (THREAD_SIZE/sizeof(unsigned long)) |
#define KSTK_TOP(info) \ |
({ \ |
unsigned long *__ptr = (unsigned long *)(info); \ |
(unsigned long)(&__ptr[THREAD_SIZE_LONGS]); \ |
}) |
|
/* |
* The below -8 is to reserve 8 bytes on top of the ring0 stack. |
* TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack. |
* This is necessary to guarantee that the entire "struct pt_regs" |
* is accessible even if the CPU haven't stored the SS/ESP registers |
* on the stack (interrupt gate does not save these registers |
885,9 → 716,9 |
*/ |
#define task_pt_regs(task) \ |
({ \ |
struct pt_regs *__regs__; \ |
__regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \ |
__regs__ - 1; \ |
unsigned long __ptr = (unsigned long)task_stack_page(task); \ |
__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ |
((struct pt_regs *)__ptr) - 1; \ |
}) |
|
#define KSTK_ESP(task) (task_pt_regs(task)->sp) |
919,13 → 750,9 |
#define STACK_TOP_MAX TASK_SIZE_MAX |
|
#define INIT_THREAD { \ |
.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \ |
.sp0 = TOP_OF_INIT_STACK \ |
} |
|
#define INIT_TSS { \ |
.x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \ |
} |
|
/* |
* Return saved PC of a blocked thread. |
* What is this good for? it will be always the scheduler or ret_from_fork. |
935,11 → 762,6 |
#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, |
961,18 → 783,18 |
extern int set_tsc_mode(unsigned int val); |
|
/* Register/unregister a process' MPX related resource */ |
#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk)) |
#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk)) |
#define MPX_ENABLE_MANAGEMENT() mpx_enable_management() |
#define MPX_DISABLE_MANAGEMENT() mpx_disable_management() |
|
#ifdef CONFIG_X86_INTEL_MPX |
extern int mpx_enable_management(struct task_struct *tsk); |
extern int mpx_disable_management(struct task_struct *tsk); |
extern int mpx_enable_management(void); |
extern int mpx_disable_management(void); |
#else |
static inline int mpx_enable_management(struct task_struct *tsk) |
static inline int mpx_enable_management(void) |
{ |
return -EINVAL; |
} |
static inline int mpx_disable_management(struct task_struct *tsk) |
static inline int mpx_disable_management(void) |
{ |
return -EINVAL; |
} |
979,6 → 801,7 |
#endif /* CONFIG_X86_INTEL_MPX */ |
|
extern u16 amd_get_nb_id(int cpu); |
extern u32 amd_get_nodes_per_socket(void); |
|
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) |
{ |