diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 0f98957b5246fa01645f0ee700f6fea3568da2b7..10009fc6b12f628322f625d9558488731962aee6 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1575,6 +1575,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	spin_lock_init(&dev_priv->backlight_lock);
 	spin_lock_init(&dev_priv->uncore.lock);
 	spin_lock_init(&dev_priv->mm.object_stat_lock);
+	spin_lock_init(&dev_priv->mmio_flip_lock);
 	mutex_init(&dev_priv->dpio_lock);
 	mutex_init(&dev_priv->modeset_restore_lock);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c5b02159898bc706dc1742748210722d40e2b1ab..9bfc242af87fcd583a7246a23f6f1c393c91def6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1370,6 +1370,9 @@ struct drm_i915_private {
 	/* protects the irq masks */
 	spinlock_t irq_lock;
 
+	/* protects the mmio flip data */
+	spinlock_t mmio_flip_lock;
+
 	bool display_irqs_enabled;
 
 	/* To control wakeup latency, e.g. for irq-driven dp aux transfers. */
@@ -2043,6 +2046,7 @@ struct i915_params {
 	bool reset;
 	bool disable_display;
 	bool disable_vtd_wa;
+	int use_mmio_flip;
 };
 extern struct i915_params i915 __read_mostly;
 
@@ -2239,6 +2243,8 @@ bool i915_gem_retire_requests(struct drm_device *dev);
 void i915_gem_retire_requests_ring(struct intel_engine_cs *ring);
 int __must_check i915_gem_check_wedge(struct i915_gpu_error *error,
 				      bool interruptible);
+int __must_check i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno);
+
 static inline bool i915_reset_in_progress(struct i915_gpu_error *error)
 {
 	return unlikely(atomic_read(&error->reset_counter)
@@ -2608,6 +2614,8 @@ int i915_reg_read_ioctl(struct drm_device *dev, void *data,
 int i915_get_reset_stats_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file);
 
+void intel_notify_mmio_flip(struct intel_engine_cs *ring);
+
 /* overlay */
 extern struct intel_overlay_error_state *intel_overlay_capture_error_state(struct drm_device *dev);
 extern void intel_overlay_print_error_state(struct drm_i915_error_state_buf *e,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 234aa1ca2eb8c2b9a4a7496aaa3a60343ed3f353..7f643db268295048f5efd480b89ef708891f84eb 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1095,7 +1095,7 @@ i915_gem_check_wedge(struct i915_gpu_error *error,
  * Compare seqno against outstanding lazy request. Emit a request if they are
  * equal.
  */
-static int
+int
 i915_gem_check_olr(struct intel_engine_cs *ring, u32 seqno)
 {
 	int ret;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 218ef085cf7339f24197b73024901fa3e109e351..c7d4cb7600e57b85d33f12b019db4818a31b0ce7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1218,6 +1218,9 @@ static void notify_ring(struct drm_device *dev,
 
 	trace_i915_gem_request_complete(ring);
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		intel_notify_mmio_flip(ring);
+
 	wake_up_all(&ring->irq_queue);
 	i915_queue_hangcheck(dev);
 }
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index d05a2afa17dc605acc294e0e15ae88ac200b5093..81457293cd3efb06201aa7cccfea05526d8d51b4 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -48,6 +48,7 @@ struct i915_params i915 __read_mostly = {
 	.disable_display = 0,
 	.enable_cmd_parser = 1,
 	.disable_vtd_wa = 0,
+	.use_mmio_flip = 0,
 };
 
 module_param_named(modeset, i915.modeset, int, 0400);
@@ -156,3 +157,7 @@ MODULE_PARM_DESC(disable_vtd_wa, "Disable all VT-d workarounds (default: false)"
 module_param_named(enable_cmd_parser, i915.enable_cmd_parser, int, 0600);
 MODULE_PARM_DESC(enable_cmd_parser,
 		 "Enable command parsing (1=enabled [default], 0=disabled)");
+
+module_param_named(use_mmio_flip, i915.use_mmio_flip, int, 0600);
+MODULE_PARM_DESC(use_mmio_flip,
+		 "use MMIO flips (-1=never, 0=driver discretion [default], 1=always)");
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a514779a5918b0f7dcc0d1561fbcaaa75d3ed5d6..5e8e7113b453511a839c4715f82dcdd32be6523c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9248,6 +9248,147 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 	return 0;
 }
 
+static bool use_mmio_flip(struct intel_engine_cs *ring,
+			  struct drm_i915_gem_object *obj)
+{
+	/*
+	 * This is not being used for older platforms, because
+	 * non-availability of flip done interrupt forces us to use
+	 * CS flips. Older platforms derive flip done using some clever
+	 * tricks involving the flip_pending status bits and vblank irqs.
+	 * So using MMIO flips there would disrupt this mechanism.
+	 */
+
+	if (INTEL_INFO(ring->dev)->gen < 5)
+		return false;
+
+	if (i915.use_mmio_flip < 0)
+		return false;
+	else if (i915.use_mmio_flip > 0)
+		return true;
+	else
+		return ring != obj->ring;
+}
+
+static void intel_do_mmio_flip(struct intel_crtc *intel_crtc)
+{
+	struct drm_device *dev = intel_crtc->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_framebuffer *intel_fb =
+		to_intel_framebuffer(intel_crtc->base.primary->fb);
+	struct drm_i915_gem_object *obj = intel_fb->obj;
+	u32 dspcntr;
+	u32 reg;
+
+	intel_mark_page_flip_active(intel_crtc);
+
+	reg = DSPCNTR(intel_crtc->plane);
+	dspcntr = I915_READ(reg);
+
+	if (INTEL_INFO(dev)->gen >= 4) {
+		if (obj->tiling_mode != I915_TILING_NONE)
+			dspcntr |= DISPPLANE_TILED;
+		else
+			dspcntr &= ~DISPPLANE_TILED;
+	}
+	I915_WRITE(reg, dspcntr);
+
+	I915_WRITE(DSPSURF(intel_crtc->plane),
+		   intel_crtc->unpin_work->gtt_offset);
+	POSTING_READ(DSPSURF(intel_crtc->plane));
+}
+
+static int intel_postpone_flip(struct drm_i915_gem_object *obj)
+{
+	struct intel_engine_cs *ring;
+	int ret;
+
+	lockdep_assert_held(&obj->base.dev->struct_mutex);
+
+	if (!obj->last_write_seqno)
+		return 0;
+
+	ring = obj->ring;
+
+	if (i915_seqno_passed(ring->get_seqno(ring, true),
+			      obj->last_write_seqno))
+		return 0;
+
+	ret = i915_gem_check_olr(ring, obj->last_write_seqno);
+	if (ret)
+		return ret;
+
+	if (WARN_ON(!ring->irq_get(ring)))
+		return 0;
+
+	return 1;
+}
+
+void intel_notify_mmio_flip(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+	struct intel_crtc *intel_crtc;
+	unsigned long irq_flags;
+	u32 seqno;
+
+	seqno = ring->get_seqno(ring, false);
+
+	spin_lock_irqsave(&dev_priv->mmio_flip_lock, irq_flags);
+	for_each_intel_crtc(ring->dev, intel_crtc) {
+		struct intel_mmio_flip *mmio_flip;
+
+		mmio_flip = &intel_crtc->mmio_flip;
+		if (mmio_flip->seqno == 0)
+			continue;
+
+		if (ring->id != mmio_flip->ring_id)
+			continue;
+
+		if (i915_seqno_passed(seqno, mmio_flip->seqno)) {
+			intel_do_mmio_flip(intel_crtc);
+			mmio_flip->seqno = 0;
+			ring->irq_put(ring);
+		}
+	}
+	spin_unlock_irqrestore(&dev_priv->mmio_flip_lock, irq_flags);
+}
+
+static int intel_queue_mmio_flip(struct drm_device *dev,
+				 struct drm_crtc *crtc,
+				 struct drm_framebuffer *fb,
+				 struct drm_i915_gem_object *obj,
+				 struct intel_engine_cs *ring,
+				 uint32_t flags)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	unsigned long irq_flags;
+	int ret;
+
+	if (WARN_ON(intel_crtc->mmio_flip.seqno))
+		return -EBUSY;
+
+	ret = intel_postpone_flip(obj);
+	if (ret < 0)
+		return ret;
+	if (ret == 0) {
+		intel_do_mmio_flip(intel_crtc);
+		return 0;
+	}
+
+	spin_lock_irqsave(&dev_priv->mmio_flip_lock, irq_flags);
+	intel_crtc->mmio_flip.seqno = obj->last_write_seqno;
+	intel_crtc->mmio_flip.ring_id = obj->ring->id;
+	spin_unlock_irqrestore(&dev_priv->mmio_flip_lock, irq_flags);
+
+	/*
+	 * Double check to catch cases where irq fired before
+	 * mmio flip data was ready
+	 */
+	intel_notify_mmio_flip(obj->ring);
+	return 0;
+}
+
 static int intel_default_queue_flip(struct drm_device *dev,
 				    struct drm_crtc *crtc,
 				    struct drm_framebuffer *fb,
@@ -9358,7 +9499,12 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	work->gtt_offset =
 		i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset;
 
-	ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring, page_flip_flags);
+	if (use_mmio_flip(ring, obj))
+		ret = intel_queue_mmio_flip(dev, crtc, fb, obj, ring,
+					    page_flip_flags);
+	else
+		ret = dev_priv->display.queue_flip(dev, crtc, fb, obj, ring,
+				page_flip_flags);
 	if (ret)
 		goto cleanup_unpin;
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9aa95f01b1604390be3225dedcf6e656401c6aec..cac7539320327d584e1396de67b7c7a8e1732cfc 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -358,6 +358,11 @@ struct intel_pipe_wm {
 	bool sprites_scaled;
 };
 
+struct intel_mmio_flip {
+	u32 seqno;
+	u32 ring_id;
+};
+
 struct intel_crtc {
 	struct drm_crtc base;
 	enum pipe pipe;
@@ -411,6 +416,7 @@ struct intel_crtc {
 	wait_queue_head_t vbl_wait;
 
 	int scanline_offset;
+	struct intel_mmio_flip mmio_flip;
 };
 
 struct intel_plane_wm_parameters {