i387: re-introduce FPU state preloading at context switch time

[pandora-kernel.git] / arch / x86 / kernel / process_32.c

diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 485204f..80bfe1a 100644 (file)
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -299,22 +299,11 @@ __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;
+       fpu_switch_t fpu;
 
        /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-       /*
-        * 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 (preload_fpu)
-               prefetch(next->fpu.state);
+       fpu = switch_fpu_prepare(prev_p, next_p);
 
        /*
         * Reload esp0.
@@ -354,11 +343,6 @@ __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
@@ -368,15 +352,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         */
        arch_end_context_switch(next_p);
 
-       if (preload_fpu)
-               __math_state_restore();
-
        /*
         * Restore %gs if needed (which is common)
         */
        if (prev->gs | next->gs)
                lazy_load_gs(next->gs);
 
+       switch_fpu_finish(next_p, fpu);
+
        percpu_write(current_task, next_p);
 
        return prev_p;