-- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -172,9 +172,11 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
                                    unsigned long flags)
 {
        struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
-       u32 cur_vblank, diff;
+       u32 cur_vblank, diff = 0;
        bool rc;
        struct timeval t_vblank;
+       const struct timeval *t_old;
+       u64 diff_ns;
        int count = DRM_TIMESTAMP_MAXRETRIES;
        int framedur_ns = vblank->framedur_ns;

@@ -195,13 +197,15 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
                rc = drm_get_last_vbltimestamp(dev, pipe, &t_vblank, flags);
        } while (cur_vblank != dev->driver->get_vblank_counter(dev, pipe) && --count > 0);

-       if (dev->max_vblank_count != 0) {
-               /* trust the hw counter when it's around */
-               diff = (cur_vblank - vblank->last) & dev->max_vblank_count;
-       } else if (rc && framedur_ns) {
-               const struct timeval *t_old;
-               u64 diff_ns;
-
+       /*
+        * Always use vblank timestamping based method if supported to reject
+        * redundant vblank irqs. E.g., AMD hardware needs this to not screw up
+        * due to some irq handling quirk.
+        *
+        * This also sets the diff value for use as fallback below in case the
+        * hw does not support a suitable hw vblank counter.
+        */
+       if (rc && framedur_ns) {
                t_old = &vblanktimestamp(dev, pipe, vblank->count);
                diff_ns = timeval_to_ns(&t_vblank) - timeval_to_ns(t_old);

@@ -212,11 +216,28 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe,
                 */
                diff = DIV_ROUND_CLOSEST_ULL(diff_ns, framedur_ns);

-               if (diff == 0 && flags & DRM_CALLED_FROM_VBLIRQ)
-                       DRM_DEBUG_VBL("crtc %u: Redundant vblirq ignored."
-                                     " diff_ns = %lld, framedur_ns = %d)\n",
-                                     pipe, (long long) diff_ns, framedur_ns);
-       } else {
+               if (diff == 0 && flags & DRM_CALLED_FROM_VBLIRQ) {
+                   DRM_DEBUG_VBL("crtc %u: Redundant vblirq ignored."
+                   " diff_ns = %lld, framedur_ns = %d)\n",
+                   pipe, (long long) diff_ns, framedur_ns);
+
+                   /* Treat this redundant invocation as no-op. */
+                   WARN_ON_ONCE(cur_vblank != vblank->last);
+                   return;
+               }
+       }
+
+       /*
+        * hw counters, if marked as supported via max_vblank_count != 0,
+        * *must* increment at leading edge of vblank and in sync with
+        * the firing of the hw vblank irq, otherwise we have a race here
+        * between gpu and us, where small variations in our execution
+        * timing can cause off-by-one miscounting of vblanks.
+        */
+       if (dev->max_vblank_count != 0) {
+               /* trust the hw counter when it's around */
+               diff = (cur_vblank - vblank->last) & dev->max_vblank_count;
+       } else if (!(rc && framedur_ns)) {
                /* some kind of default for drivers w/o accurate vbl timestamping */
                diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0;
        }