diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 07:58:08 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-14 07:58:08 -0700 |
| commit | 625037cc405eabbfd2a39e9297e583a94886225f (patch) | |
| tree | c0a62f6cb2a565efb7cd494f558f0acbadcbabb0 /arch/x86/kernel/process_32.c | |
| parent | 8fafa0a789faaff4318cbfa9c2f827d2198505dc (diff) | |
| parent | 17950c5b243f99cbabef173415ee988c52104d7e (diff) | |
Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86-64: move clts into batch cpu state updates when preloading fpu
x86-64: move unlazy_fpu() into lazy cpu state part of context switch
x86-32: make sure clts is batched during context switch
x86: split out core __math_state_restore
Diffstat (limited to 'arch/x86/kernel/process_32.c')
| -rw-r--r-- | arch/x86/kernel/process_32.c | 27 |
1 files changed, 16 insertions, 11 deletions
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 59f4524984a..a80eddd4165 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -350,14 +350,21 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) *next = &next_p->thread; int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); + bool preload_fpu; /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - __unlazy_fpu(prev_p); + /* + * If the task has used fpu the last 5 timeslices, just do a full + * restore of the math state immediately to avoid the trap; the + * chances of needing FPU soon are obviously high now + */ + preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5; + __unlazy_fpu(prev_p); /* we're going to use this soon, after a few expensive things */ - if (next_p->fpu_counter > 5) + if (preload_fpu) prefetch(next->xstate); /* @@ -398,6 +405,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) __switch_to_xtra(prev_p, next_p, tss); + /* If we're going to preload the fpu context, make sure clts + is run while we're batching the cpu state updates. */ + if (preload_fpu) + clts(); + /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -407,15 +419,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) */ arch_end_context_switch(next_p); - /* If the task has used fpu the last 5 timeslices, just do a full - * restore of the math state immediately to avoid the trap; the - * chances of needing FPU soon are obviously high now - * - * tsk_used_math() checks prevent calling math_state_restore(), - * which can sleep in the case of !tsk_used_math() - */ - if (tsk_used_math(next_p) && next_p->fpu_counter > 5) - math_state_restore(); + if (preload_fpu) + __math_state_restore(); /* * Restore %gs if needed (which is common) |