drm/vblank: Use memory barriers optimized for atomic_t instead of generics.

Documentation/atomic_ops.txt tells us that there are memory
barriers optimized for atomic_inc and other atomic_t ops.

Use these instead of smp_wmb(), and also to make the required
memory barriers around vblank counter increments more explicit.
Signed-off-by: Mario Kleiner <mario.kleiner@tuebingen.mpg.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/drm_irq.c

@@ -164,8 +164,10 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 * available. In that case we can't account for this and just
 	 * hope for the best.
 	 */
-	if ((vblrc > 0) && (abs64(diff_ns) > 1000000))
+	if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
 		atomic_inc(&dev->_vblank_count[crtc]);
+		smp_mb__after_atomic_inc();
+	}
 
 	/* Invalidate all timestamps while vblank irq's are off. */
 	clear_vblank_timestamps(dev, crtc);
@@ -858,10 +860,11 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 	if (rc) {
 		tslot = atomic_read(&dev->_vblank_count[crtc]) + diff;
 		vblanktimestamp(dev, crtc, tslot) = t_vblank;
-		smp_wmb();
 	}
 
+	smp_mb__before_atomic_inc();
 	atomic_add(diff, &dev->_vblank_count[crtc]);
+	smp_mb__after_atomic_inc();
 }
 
 /**
@@ -1296,12 +1299,13 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 	if (abs64(diff_ns) > DRM_REDUNDANT_VBLIRQ_THRESH_NS) {
 		/* Store new timestamp in ringbuffer. */
 		vblanktimestamp(dev, crtc, vblcount + 1) = tvblank;
-		smp_wmb();
 
 		/* Increment cooked vblank count. This also atomically commits
 		 * the timestamp computed above.
 		 */
+		smp_mb__before_atomic_inc();
 		atomic_inc(&dev->_vblank_count[crtc]);
+		smp_mb__after_atomic_inc();
 	} else {
 		DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
 			  crtc, (int) diff_ns);