diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 6fbd19564e4e..9e9a70e50c72 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -552,6 +552,10 @@ __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);
 
+	/* we're going to use this soon, after a few expensive things */
+	if (next_p->fpu_counter>5)
+		prefetch(&next->i387.fxsave);
+
 	/*
 	 * Reload esp0, LDT and the page table pointer:
 	 */
@@ -629,6 +633,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	    || test_tsk_thread_flag(prev_p, TIF_IO_BITMAP))
 		__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
+	 */
+	if (next_p->fpu_counter>5)
+		math_state_restore();
 	return prev_p;
 }
 
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 28e53342f294..ffc40cff1e07 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -1136,6 +1136,7 @@ asmlinkage void math_state_restore(void)
 		init_fpu(me);
 	restore_fpu_checking(&me->thread.i387.fxsave);
 	task_thread_info(me)->status |= TS_USEDFPU;
+	me->fpu_counter++;
 }
 
 void __init trap_init(void)
diff --git a/include/asm-x86_64/i387.h b/include/asm-x86_64/i387.h
index cba8a3b0cded..60c0f4853fdb 100644
--- a/include/asm-x86_64/i387.h
+++ b/include/asm-x86_64/i387.h
@@ -24,6 +24,7 @@ extern unsigned int mxcsr_feature_mask;
 extern void mxcsr_feature_mask_init(void);
 extern void init_fpu(struct task_struct *child);
 extern int save_i387(struct _fpstate __user *buf);
+extern asmlinkage void math_state_restore(void);
 
 /*
  * FPU lazy state save handling...
@@ -31,7 +32,9 @@ extern int save_i387(struct _fpstate __user *buf);
 
 #define unlazy_fpu(tsk) do { \
 	if (task_thread_info(tsk)->status & TS_USEDFPU) \
-		save_init_fpu(tsk); \
+		save_init_fpu(tsk); 			\
+	else						\
+		tsk->fpu_counter = 0;			\
 } while (0)
 
 /* Ignore delayed exceptions from user space */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 34ed0d99b1bd..807556c5bcd2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -865,6 +865,15 @@ struct task_struct {
 	struct key *thread_keyring;	/* keyring private to this thread */
 	unsigned char jit_keyring;	/* default keyring to attach requested keys to */
 #endif
+	/*
+	 * fpu_counter contains the number of consecutive context switches
+	 * that the FPU is used. If this is over a threshold, the lazy fpu
+	 * saving becomes unlazy to save the trap. This is an unsigned char
+	 * so that after 256 times the counter wraps and the behavior turns
+	 * lazy again; this to deal with bursty apps that only use FPU for
+	 * a short time
+	 */
+	unsigned char fpu_counter;
 	int oomkilladj; /* OOM kill score adjustment (bit shift). */
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock