blob: 41ab26ea65648b43a910f97cd7903c8bbbc2516c [file] [log] [blame]
/*
* Copyright (C) 1994 Linus Torvalds
*
* Pentium III FXSR, SSE support
* General FPU state handling cleanups
* Gareth Hughes <gareth@valinux.com>, May 2000
* x86-64 work by Andi Kleen 2002
*/
#ifndef _FPU_INTERNAL_H
#define _FPU_INTERNAL_H
#include <linux/kernel_stat.h>
#include <linux/regset.h>
#include <linux/compat.h>
#include <linux/slab.h>
#include <asm/asm.h>
#include <asm/cpufeature.h>
#include <asm/processor.h>
#include <asm/sigcontext.h>
#include <asm/user.h>
#include <asm/uaccess.h>
#include <asm/xsave.h>
#include <asm/smap.h>
#ifdef CONFIG_X86_64
# include <asm/sigcontext32.h>
# include <asm/user32.h>
int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
compat_sigset_t *set, struct pt_regs *regs);
int ia32_setup_frame(int sig, struct k_sigaction *ka,
compat_sigset_t *set, struct pt_regs *regs);
#else
# define user_i387_ia32_struct user_i387_struct
# define user32_fxsr_struct user_fxsr_struct
# define ia32_setup_frame __setup_frame
# define ia32_setup_rt_frame __setup_rt_frame
#endif
extern unsigned int mxcsr_feature_mask;
extern void fpu_init(void);
extern void eager_fpu_init(void);
DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
struct task_struct *tsk);
extern void convert_to_fxsr(struct task_struct *tsk,
const struct user_i387_ia32_struct *env);
extern user_regset_active_fn fpregs_active, xfpregs_active;
extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
xstateregs_get;
extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
xstateregs_set;
/*
* xstateregs_active == fpregs_active. Please refer to the comment
* at the definition of fpregs_active.
*/
#define xstateregs_active fpregs_active
#ifdef CONFIG_MATH_EMULATION
# define HAVE_HWFP (boot_cpu_data.hard_math)
extern void finit_soft_fpu(struct i387_soft_struct *soft);
#else
# define HAVE_HWFP 1
static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
#endif
static inline int is_ia32_compat_frame(void)
{
return config_enabled(CONFIG_IA32_EMULATION) &&
test_thread_flag(TIF_IA32);
}
static inline int is_ia32_frame(void)
{
return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
}
static inline int is_x32_frame(void)
{
return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
}
#define X87_FSW_ES (1 << 7) /* Exception Summary */
static __always_inline __pure bool use_eager_fpu(void)
{
return static_cpu_has(X86_FEATURE_EAGER_FPU);
}
static __always_inline __pure bool use_xsaveopt(void)
{
return static_cpu_has(X86_FEATURE_XSAVEOPT);
}
static __always_inline __pure bool use_xsave(void)
{
return static_cpu_has(X86_FEATURE_XSAVE);
}
static __always_inline __pure bool use_fxsr(void)
{
return static_cpu_has(X86_FEATURE_FXSR);
}
static inline void fx_finit(struct i387_fxsave_struct *fx)
{
memset(fx, 0, xstate_size);
fx->cwd = 0x37f;
fx->mxcsr = MXCSR_DEFAULT;
}
extern void __sanitize_i387_state(struct task_struct *);
static inline void sanitize_i387_state(struct task_struct *tsk)
{
if (!use_xsaveopt())
return;
__sanitize_i387_state(tsk);
}
#define user_insn(insn, output, input...) \
({ \
int err; \
asm volatile(ASM_STAC "\n" \
"1:" #insn "\n\t" \
"2: " ASM_CLAC "\n" \
".section .fixup,\"ax\"\n" \
"3: movl $-1,%[err]\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(1b, 3b) \
: [err] "=r" (err), output \
: "0"(0), input); \
err; \
})
#define check_insn(insn, output, input...) \
({ \
int err; \
asm volatile("1:" #insn "\n\t" \
"2:\n" \
".section .fixup,\"ax\"\n" \
"3: movl $-1,%[err]\n" \
" jmp 2b\n" \
".previous\n" \
_ASM_EXTABLE(1b, 3b) \
: [err] "=r" (err), output \
: "0"(0), input); \
err; \
})
static inline int fsave_user(struct i387_fsave_struct __user *fx)
{
return user_insn(fnsave %[fx]; fwait, [fx] "=m" (*fx), "m" (*fx));
}
static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
{
if (config_enabled(CONFIG_X86_32))
return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
/* See comment in fpu_fxsave() below. */
return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
}
static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
{
if (config_enabled(CONFIG_X86_32))
return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
/* See comment in fpu_fxsave() below. */
return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
"m" (*fx));
}
static inline int fxrstor_user(struct i387_fxsave_struct __user *fx)
{
if (config_enabled(CONFIG_X86_32))
return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
/* See comment in fpu_fxsave() below. */
return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
"m" (*fx));
}
static inline int frstor_checking(struct i387_fsave_struct *fx)
{
return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline int frstor_user(struct i387_fsave_struct __user *fx)
{
return user_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline void fpu_fxsave(struct fpu *fpu)
{
if (config_enabled(CONFIG_X86_32))
asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
else if (config_enabled(CONFIG_AS_FXSAVEQ))
asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
else {
/* Using "rex64; fxsave %0" is broken because, if the memory
* operand uses any extended registers for addressing, a second
* REX prefix will be generated (to the assembler, rex64
* followed by semicolon is a separate instruction), and hence
* the 64-bitness is lost.
*
* Using "fxsaveq %0" would be the ideal choice, but is only
* supported starting with gas 2.16.
*
* Using, as a workaround, the properly prefixed form below
* isn't accepted by any binutils version so far released,
* complaining that the same type of prefix is used twice if
* an extended register is needed for addressing (fix submitted
* to mainline 2005-11-21).
*
* asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
*
* This, however, we can work around by forcing the compiler to
* select an addressing mode that doesn't require extended
* registers.
*/
asm volatile( "rex64/fxsave (%[fx])"
: "=m" (fpu->state->fxsave)
: [fx] "R" (&fpu->state->fxsave));
}
}
/*
* These must be called with preempt disabled. Returns
* 'true' if the FPU state is still intact.
*/
static inline int fpu_save_init(struct fpu *fpu)
{
if (use_xsave()) {
fpu_xsave(fpu);
/*
* xsave header may indicate the init state of the FP.
*/
if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
return 1;
} else if (use_fxsr()) {
fpu_fxsave(fpu);
} else {
asm volatile("fnsave %[fx]; fwait"
: [fx] "=m" (fpu->state->fsave));
return 0;
}
/*
* If exceptions are pending, we need to clear them so
* that we don't randomly get exceptions later.
*
* FIXME! Is this perhaps only true for the old-style
* irq13 case? Maybe we could leave the x87 state
* intact otherwise?
*/
if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
asm volatile("fnclex");
return 0;
}
return 1;
}
static inline int __save_init_fpu(struct task_struct *tsk)
{
return fpu_save_init(&tsk->thread.fpu);
}
static inline int fpu_restore_checking(struct fpu *fpu)
{
if (use_xsave())
return fpu_xrstor_checking(&fpu->state->xsave);
else if (use_fxsr())
return fxrstor_checking(&fpu->state->fxsave);
else
return frstor_checking(&fpu->state->fsave);
}
static inline int restore_fpu_checking(struct task_struct *tsk)
{
/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
is pending. Clear the x87 state here by setting it to fixed
values. "m" is a random variable that should be in L1 */
alternative_input(
ASM_NOP8 ASM_NOP2,
"emms\n\t" /* clear stack tags */
"fildl %P[addr]", /* set F?P to defined value */
X86_FEATURE_FXSAVE_LEAK,
[addr] "m" (tsk->thread.fpu.has_fpu));
return fpu_restore_checking(&tsk->thread.fpu);
}
/*
* Software FPU state helpers. Careful: these need to
* be preemption protection *and* they need to be
* properly paired with the CR0.TS changes!
*/
static inline int __thread_has_fpu(struct task_struct *tsk)
{
return tsk->thread.fpu.has_fpu;
}
/* Must be paired with an 'stts' after! */
static inline void __thread_clear_has_fpu(struct task_struct *tsk)
{
tsk->thread.fpu.has_fpu = 0;
this_cpu_write(fpu_owner_task, NULL);
}
/* Must be paired with a 'clts' before! */
static inline void __thread_set_has_fpu(struct task_struct *tsk)
{
tsk->thread.fpu.has_fpu = 1;
this_cpu_write(fpu_owner_task, tsk);
}
/*
* Encapsulate the CR0.TS handling together with the
* software flag.
*
* These generally need preemption protection to work,
* do try to avoid using these on their own.
*/
static inline void __thread_fpu_end(struct task_struct *tsk)
{
__thread_clear_has_fpu(tsk);
if (!use_eager_fpu())
stts();
}
static inline void __thread_fpu_begin(struct task_struct *tsk)
{
if (!use_eager_fpu())
clts();
__thread_set_has_fpu(tsk);
}
static inline void __drop_fpu(struct task_struct *tsk)
{
if (__thread_has_fpu(tsk)) {
/* Ignore delayed exceptions from user space */
asm volatile("1: fwait\n"
"2:\n"
_ASM_EXTABLE(1b, 2b));
__thread_fpu_end(tsk);
}
}
static inline void drop_fpu(struct task_struct *tsk)
{
/*
* Forget coprocessor state..
*/
preempt_disable();
tsk->fpu_counter = 0;
__drop_fpu(tsk);
clear_used_math();
preempt_enable();
}
static inline void drop_init_fpu(struct task_struct *tsk)
{
if (!use_eager_fpu())
drop_fpu(tsk);
else {
if (use_xsave())
xrstor_state(init_xstate_buf, -1);
else
fxrstor_checking(&init_xstate_buf->i387);
}
}
/*
* FPU state switching for scheduling.
*
* This is a two-stage process:
*
* - switch_fpu_prepare() saves the old state and
* sets the new state of the CR0.TS bit. This is
* done within the context of the old process.
*
* - switch_fpu_finish() restores the new state as
* necessary.
*/
typedef struct { int preload; } fpu_switch_t;
/*
* Must be run with preemption disabled: this clears the fpu_owner_task,
* on this CPU.
*
* This will disable any lazy FPU state restore of the current FPU state,
* but if the current thread owns the FPU, it will still be saved by.
*/
static inline void __cpu_disable_lazy_restore(unsigned int cpu)
{
per_cpu(fpu_owner_task, cpu) = NULL;
}
static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
{
return new == this_cpu_read_stable(fpu_owner_task) &&
cpu == new->thread.fpu.last_cpu;
}
static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
{
fpu_switch_t fpu;
/*
* If the task has used the math, pre-load the FPU on xsave processors
* or if the past 5 consecutive context-switches used math.
*/
fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
new->fpu_counter > 5);
if (__thread_has_fpu(old)) {
if (!__save_init_fpu(old))
cpu = ~0;
old->thread.fpu.last_cpu = cpu;
old->thread.fpu.has_fpu = 0; /* But leave fpu_owner_task! */
/* Don't change CR0.TS if we just switch! */
if (fpu.preload) {
new->fpu_counter++;
__thread_set_has_fpu(new);
prefetch(new->thread.fpu.state);
} else if (!use_eager_fpu())
stts();
} else {
old->fpu_counter = 0;
old->thread.fpu.last_cpu = ~0;
if (fpu.preload) {
new->fpu_counter++;
if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
fpu.preload = 0;
else
prefetch(new->thread.fpu.state);
__thread_fpu_begin(new);
}
}
return fpu;
}
/*
* By the time this gets called, we've already cleared CR0.TS and
* given the process the FPU if we are going to preload the FPU
* state - all we need to do is to conditionally restore the register
* state itself.
*/
static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
{
if (fpu.preload) {
if (unlikely(restore_fpu_checking(new)))
drop_init_fpu(new);
}
}
/*
* Signal frame handlers...
*/
extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
static inline int xstate_sigframe_size(void)
{
return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
}
static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
{
void __user *buf_fx = buf;
int size = xstate_sigframe_size();
if (ia32_frame && use_fxsr()) {
buf_fx = buf + sizeof(struct i387_fsave_struct);
size += sizeof(struct i387_fsave_struct);
}
return __restore_xstate_sig(buf, buf_fx, size);
}
/*
* Need to be preemption-safe.
*
* NOTE! user_fpu_begin() must be used only immediately before restoring
* it. This function does not do any save/restore on their own.
*/
static inline void user_fpu_begin(void)
{
preempt_disable();
if (!user_has_fpu())
__thread_fpu_begin(current);
preempt_enable();
}
static inline void __save_fpu(struct task_struct *tsk)
{
if (use_xsave())
xsave_state(&tsk->thread.fpu.state->xsave, -1);
else
fpu_fxsave(&tsk->thread.fpu);
}
/*
* These disable preemption on their own and are safe
*/
static inline void save_init_fpu(struct task_struct *tsk)
{
WARN_ON_ONCE(!__thread_has_fpu(tsk));
if (use_eager_fpu()) {
__save_fpu(tsk);
return;
}
preempt_disable();
__save_init_fpu(tsk);
__thread_fpu_end(tsk);
preempt_enable();
}
/*
* i387 state interaction
*/
static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
{
if (cpu_has_fxsr) {
return tsk->thread.fpu.state->fxsave.cwd;
} else {
return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
}
}
static inline unsigned short get_fpu_swd(struct task_struct *tsk)
{
if (cpu_has_fxsr) {
return tsk->thread.fpu.state->fxsave.swd;
} else {
return (unsigned short)tsk->thread.fpu.state->fsave.swd;
}
}
static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
{
if (cpu_has_xmm) {
return tsk->thread.fpu.state->fxsave.mxcsr;
} else {
return MXCSR_DEFAULT;
}
}
static bool fpu_allocated(struct fpu *fpu)
{
return fpu->state != NULL;
}
static inline int fpu_alloc(struct fpu *fpu)
{
if (fpu_allocated(fpu))
return 0;
fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
if (!fpu->state)
return -ENOMEM;
WARN_ON((unsigned long)fpu->state & 15);
return 0;
}
static inline void fpu_free(struct fpu *fpu)
{
if (fpu->state) {
kmem_cache_free(task_xstate_cachep, fpu->state);
fpu->state = NULL;
}
}
static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
{
if (use_eager_fpu()) {
memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
__save_fpu(dst);
} else {
struct fpu *dfpu = &dst->thread.fpu;
struct fpu *sfpu = &src->thread.fpu;
unlazy_fpu(src);
memcpy(dfpu->state, sfpu->state, xstate_size);
}
}
static inline unsigned long
alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
unsigned long *size)
{
unsigned long frame_size = xstate_sigframe_size();
*buf_fx = sp = round_down(sp - frame_size, 64);
if (ia32_frame && use_fxsr()) {
frame_size += sizeof(struct i387_fsave_struct);
sp -= sizeof(struct i387_fsave_struct);
}
*size = frame_size;
return sp;
}
#endif