From 17950c5b243f99cbabef173415ee988c52104d7e Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 24 Apr 2009 01:01:01 -0700 Subject: [PATCH] x86-64: move clts into batch cpu state updates when preloading fpu When a task is likely to be using the fpu, we preload its state during the context switch, rather than waiting for it to run an fpu instruction. Make sure the clts() happens while we're doing batched fpu state updates to optimise paravirtualized context switches. [ Impact: optimise paravirtual FPU context switch ] Signed-off-by: Jeremy Fitzhardinge Cc: Alok Kataria Cc: Rusty Russell --- arch/x86/kernel/process_64.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index c9b8904736db..a28279dbb07c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -386,9 +386,17 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); struct tss_struct *tss = &per_cpu(init_tss, cpu); unsigned fsindex, gsindex; + bool preload_fpu; + + /* + * 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; /* we're going to use this soon, after a few expensive things */ - if (next_p->fpu_counter > 5) + if (preload_fpu) prefetch(next->xstate); /* @@ -422,6 +430,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* Must be after DS reload */ unlazy_fpu(prev_p); + /* Make sure cpu is ready for new context */ + if (preload_fpu) + clts(); + /* * Leave lazy mode, flushing any hypercalls made here. * This must be done before restoring TLS segments so @@ -480,15 +492,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) __switch_to_xtra(prev_p, next_p, tss); - /* 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() + /* + * Preload the FPU context, now that we've determined that the + * task is likely to be using it. */ - if (tsk_used_math(next_p) && next_p->fpu_counter > 5) - math_state_restore(); + if (preload_fpu) + __math_state_restore(); return prev_p; }