diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a850b4d8d14d9a913a5de034882a9d5c8542163c..8df95849721dbfb04b0e4040f4da9f892be67d09 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -348,10 +348,10 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 		if (__save_init_fpu(old))
 			fpu_lazy_state_intact(old);
 		__thread_clear_has_fpu(old);
-		old->fpu_counter++;
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
+			new->fpu_counter++;
 			__thread_set_has_fpu(new);
 			prefetch(new->thread.fpu.state);
 		} else
@@ -359,6 +359,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 	} else {
 		old->fpu_counter = 0;
 		if (fpu.preload) {
+			new->fpu_counter++;
 			if (fpu_lazy_restore(new))
 				fpu.preload = 0;
 			else
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 80bfe1ab0031a5e9ed6ab25601d3608ba72ba1b4..bc32761bc27ab00a3f5b1cfcd8235eafa071f7a0 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -214,6 +214,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	task_user_gs(p) = get_user_gs(regs);
 
+	p->fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 	tsk = current;
 	err = -ENOMEM;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 1fd94bc4279d60472a34feea7c792e5e70b013d8..8ad880b3bc1c345dcb44e7ed4453baba4639395d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -286,6 +286,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
 	set_tsk_thread_flag(p, TIF_FORK);
 
+	p->fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 
 	savesegment(gs, p->thread.gsindex);