x86/fpu: Also check fpu_lazy_restore() when use_eager_fpu()
authorRik van Riel <riel@redhat.com>
Fri, 6 Feb 2015 20:02:05 +0000 (15:02 -0500)
committerBorislav Petkov <bp@suse.de>
Thu, 19 Feb 2015 10:15:55 +0000 (11:15 +0100)
With Oleg's patch:

  33a3ebdc077f ("x86, fpu: Don't abuse has_fpu in __kernel_fpu_begin/end()")

kernel threads no longer have an FPU state even on systems with
use_eager_fpu().

That in turn means that a task may still have its FPU state
loaded in the FPU registers, if the task only got interrupted by
kernel threads from when it went to sleep, to when it woke up
again.

In that case, there is no need to restore the FPU state for
this task, since it is still in the registers.

The kernel can simply use the same logic to determine this as
is used for !use_eager_fpu() systems.

Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Link: http://lkml.kernel.org/r/1423252925-14451-9-git-send-email-riel@redhat.com
Signed-off-by: Borislav Petkov <bp@suse.de>
arch/x86/include/asm/fpu-internal.h

index e5f8f8eaf2258b38fc6e04866fc8b2afa5a64f1d..19fb41cc4755ea785467fb5247def4ddfa89d40f 100644 (file)
@@ -458,7 +458,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
                task_disable_lazy_fpu_restore(old);
                if (fpu.preload) {
                        new->thread.fpu_counter++;
-                       if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
+                       if (fpu_lazy_restore(new, cpu))
                                fpu.preload = 0;
                        else
                                prefetch(new->thread.fpu.state);