i387: fix up some fpu_counter confusion

This makes sure we clear the FPU usage counter for newly created tasks,
just so that we start off in a known state (for example, don't try to
preload the FPU state on the first task switch etc).

It also fixes a thinko in when we increment the fpu_counter at task
switch time, introduced by commit 34ddc81a ("i387: re-introduce FPU
state preloading at context switch time").  We should increment the
*new* task fpu_counter, not the old task, and only if we decide to use
that state (whether lazily or preloaded).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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

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;

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);