diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 445e84e2be743af32f7534774f6604105dad7535..bab5d17f67d114e97af6c231115e1b6c96152d4a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3867,6 +3867,7 @@ enum punit_power_well {
 #define _PIPEA_FRMCOUNT_GM45	0x70040
 #define _PIPEA_FLIPCOUNT_GM45	0x70044
 #define PIPE_FRMCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FRMCOUNT_GM45)
+#define PIPE_FLIPCOUNT_GM45(pipe) _PIPE2(pipe, _PIPEA_FLIPCOUNT_GM45)
 
 /* Cursor A & B regs */
 #define _CURACNTR		0x70080
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index bcb0c2eafde0090aed89e15216dbd49bc6356f73..930746527e9d8c0e46a4ed0ce0e48aa0b7d8dbe2 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -8846,6 +8846,48 @@ void intel_finish_page_flip_plane(struct drm_device *dev, int plane)
 	do_intel_finish_page_flip(dev, crtc);
 }
 
+/* Is 'a' after or equal to 'b'? */
+static bool g4x_flip_count_after_eq(u32 a, u32 b)
+{
+	return !((a - b) & 0x80000000);
+}
+
+static bool page_flip_finished(struct intel_crtc *crtc)
+{
+	struct drm_device *dev = crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/*
+	 * The relevant registers doen't exist on pre-ctg.
+	 * As the flip done interrupt doesn't trigger for mmio
+	 * flips on gmch platforms, a flip count check isn't
+	 * really needed there. But since ctg has the registers,
+	 * include it in the check anyway.
+	 */
+	if (INTEL_INFO(dev)->gen < 5 && !IS_G4X(dev))
+		return true;
+
+	/*
+	 * A DSPSURFLIVE check isn't enough in case the mmio and CS flips
+	 * used the same base address. In that case the mmio flip might
+	 * have completed, but the CS hasn't even executed the flip yet.
+	 *
+	 * A flip count check isn't enough as the CS might have updated
+	 * the base address just after start of vblank, but before we
+	 * managed to process the interrupt. This means we'd complete the
+	 * CS flip too soon.
+	 *
+	 * Combining both checks should get us a good enough result. It may
+	 * still happen that the CS flip has been executed, but has not
+	 * yet actually completed. But in case the base address is the same
+	 * anyway, we don't really care.
+	 */
+	return (I915_READ(DSPSURFLIVE(crtc->plane)) & ~0xfff) ==
+		crtc->unpin_work->gtt_offset &&
+		g4x_flip_count_after_eq(I915_READ(PIPE_FLIPCOUNT_GM45(crtc->pipe)),
+				    crtc->unpin_work->flip_count);
+}
+
 void intel_prepare_page_flip(struct drm_device *dev, int plane)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -8858,7 +8900,7 @@ void intel_prepare_page_flip(struct drm_device *dev, int plane)
 	 * is also accompanied by a spurious intel_prepare_page_flip().
 	 */
 	spin_lock_irqsave(&dev->event_lock, flags);
-	if (intel_crtc->unpin_work)
+	if (intel_crtc->unpin_work && page_flip_finished(intel_crtc))
 		atomic_inc_not_zero(&intel_crtc->unpin_work->pending);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
@@ -8888,6 +8930,9 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	if (ret)
 		goto err;
 
+	intel_crtc->unpin_work->gtt_offset =
+		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+
 	ret = intel_ring_begin(ring, 6);
 	if (ret)
 		goto err_unpin;
@@ -8904,7 +8949,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -8933,6 +8978,9 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	if (ret)
 		goto err;
 
+	intel_crtc->unpin_work->gtt_offset =
+		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+
 	ret = intel_ring_begin(ring, 6);
 	if (ret)
 		goto err_unpin;
@@ -8946,7 +8994,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -8975,6 +9023,9 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	if (ret)
 		goto err;
 
+	intel_crtc->unpin_work->gtt_offset =
+		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		goto err_unpin;
@@ -8986,8 +9037,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring,
-			(i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) |
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -9024,6 +9074,9 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	if (ret)
 		goto err;
 
+	intel_crtc->unpin_work->gtt_offset =
+		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+
 	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		goto err_unpin;
@@ -9031,7 +9084,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -9073,6 +9126,9 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 	if (ret)
 		goto err;
 
+	intel_crtc->unpin_work->gtt_offset =
+		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
+
 	switch (intel_crtc->plane) {
 	case PLANE_A:
 		plane_bit = MI_DISPLAY_FLIP_IVB_PLANE_A;
@@ -9150,7 +9206,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, intel_crtc->unpin_work->gtt_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -9248,6 +9304,9 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	atomic_inc(&intel_crtc->unpin_work_count);
 	intel_crtc->reset_counter = atomic_read(&dev_priv->gpu_error.reset_counter);
 
+	if (INTEL_INFO(dev)->gen >= 5 || IS_G4X(dev))
+		work->flip_count = I915_READ(PIPE_FLIPCOUNT_GM45(intel_crtc->pipe)) + 1;
+
 	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, page_flip_flags);
 	if (ret)
 		goto cleanup_pending;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0ef2777514fefc24b58b2d075097d396d4525084..df7808cbb1112da54f3a97affa15a58ef71b402d 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -615,6 +615,8 @@ struct intel_unpin_work {
 #define INTEL_FLIP_INACTIVE	0
 #define INTEL_FLIP_PENDING	1
 #define INTEL_FLIP_COMPLETE	2
+	u32 flip_count;
+	u32 gtt_offset;
 	bool enable_stall_check;
 };