1 files changed, 21 insertions, 15 deletions

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ebefb5407b9d..ad535b683170 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -55,9 +55,6 @@
 
 asmlinkage extern void ret_from_fork(void);
 
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-
 DEFINE_PER_CPU(unsigned long, old_rsp);
 static DEFINE_PER_CPU(unsigned char, is_idle);
 
@@ -386,9 +383,17 @@ __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);
 
         /*
@@ -419,6 +424,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
         load_TLS(next, cpu);
 
+        /* 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
@@ -459,9 +471,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                 wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
         prev->gsindex = gsindex;
 
-        /* Must be after DS reload */
-        unlazy_fpu(prev_p);
-
         /*
          * Switch the PDA and FPU contexts.
          */
@@ -480,15 +489,12 @@ __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;
 }