summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/i387.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-02-19 13:27:00 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2012-02-20 10:58:54 -0800
commit7e16838d94b566a17b65231073d179bc04d590c8 (patch)
tree356ae3999d89d2419fd4b85b062a24820f4a4d82 /arch/x86/include/asm/i387.h
parent80ab6f1e8c981b1b6604b2f22e36c917526235cd (diff)
i387: support lazy restore of FPU state
This makes us recognize when we try to restore FPU state that matches what we already have in the FPU on this CPU, and avoids the restore entirely if so. To do this, we add two new data fields: - a percpu 'fpu_owner_task' variable that gets written any time we update the "has_fpu" field, and thus acts as a kind of back-pointer to the task that owns the CPU. The exception is when we save the FPU state as part of a context switch - if the save can keep the FPU state around, we leave the 'fpu_owner_task' variable pointing at the task whose FP state still remains on the CPU. - a per-thread 'last_cpu' field, that indicates which CPU that thread used its FPU on last. We update this on every context switch (writing an invalid CPU number if the last context switch didn't leave the FPU in a lazily usable state), so we know that *that* thread has done nothing else with the FPU since. These two fields together can be used when next switching back to the task to see if the CPU still matches: if 'fpu_owner_task' matches the task we are switching to, we know that no other task (or kernel FPU usage) touched the FPU on this CPU in the meantime, and if the current CPU number matches the 'last_cpu' field, we know that this thread did no other FP work on any other CPU, so the FPU state on the CPU must match what was saved on last context switch. In that case, we can avoid the 'f[x]rstor' entirely, and just clear the CR0.TS bit. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'arch/x86/include/asm/i387.h')
-rw-r--r--arch/x86/include/asm/i387.h35
1 files changed, 23 insertions, 12 deletions
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 74c607b37e87..247904945d3f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -32,6 +32,8 @@ extern int init_fpu(struct task_struct *child);
extern void math_state_restore(void);
extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
extern user_regset_active_fn fpregs_active, xfpregs_active;
extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
xstateregs_get;
@@ -276,7 +278,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
"emms\n\t" /* clear stack tags */
"fildl %P[addr]", /* set F?P to defined value */
X86_FEATURE_FXSAVE_LEAK,
- [addr] "m" (tsk->thread.has_fpu));
+ [addr] "m" (tsk->thread.fpu.has_fpu));
return fpu_restore_checking(&tsk->thread.fpu);
}
@@ -288,19 +290,21 @@ static inline int restore_fpu_checking(struct task_struct *tsk)
*/
static inline int __thread_has_fpu(struct task_struct *tsk)
{
- return tsk->thread.has_fpu;
+ 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.has_fpu = 0;
+ tsk->thread.fpu.has_fpu = 0;
+ percpu_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.has_fpu = 1;
+ tsk->thread.fpu.has_fpu = 1;
+ percpu_write(fpu_owner_task, tsk);
}
/*
@@ -345,18 +349,22 @@ typedef struct { int preload; } fpu_switch_t;
* We don't do that yet, so "fpu_lazy_restore()" always returns
* false, but some day..
*/
-#define fpu_lazy_restore(tsk) (0)
-#define fpu_lazy_state_intact(tsk) do { } while (0)
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+ return new == percpu_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)
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
{
fpu_switch_t fpu;
fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
if (__thread_has_fpu(old)) {
- if (__save_init_fpu(old))
- fpu_lazy_state_intact(old);
- __thread_clear_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) {
@@ -367,9 +375,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
stts();
} else {
old->fpu_counter = 0;
+ old->thread.fpu.last_cpu = ~0;
if (fpu.preload) {
new->fpu_counter++;
- if (fpu_lazy_restore(new))
+ if (fpu_lazy_restore(new, cpu))
fpu.preload = 0;
else
prefetch(new->thread.fpu.state);
@@ -463,8 +472,10 @@ static inline void kernel_fpu_begin(void)
__save_init_fpu(me);
__thread_clear_has_fpu(me);
/* We do 'stts()' in kernel_fpu_end() */
- } else
+ } else {
+ percpu_write(fpu_owner_task, NULL);
clts();
+ }
}
static inline void kernel_fpu_end(void)