Merge tag 'drm-intel-next-2014-06-20' of git://anongit.freedesktop.org/drm-intel into drm-next

- Accurate frontbuffer tracking and frontbuffer rendering invalidate, flush and
  flip events. This is prep work for proper PSR support and should also be
  useful for DRRS&fbc.
- Runtime suspend hardware on system suspend to support the new SOix sleep
  states, from Jesse.
- PSR updates for broadwell (Rodrigo)
- Universal plane support for cursors (Matt Roper), including core drm patches.
- Prefault gtt mappings (Chris)
- baytrail write-enable pte bit support (Akash Goel)
- mmio based flips (Sourab Gupta) instead of blitter ring flips
- interrupt handling race fixes (Oscar Mateo)

And old, not yet merged features from the previous round:
- rps/turbo support for chv (Deepak)
- some other straggling chv patches (Ville)
- proper universal plane conversion for the primary plane (Matt Roper)
- ppgtt on vlv from Jesse
- pile of cleanups, little fixes for insane corner cases and improved debug
  support all over

* tag 'drm-intel-next-2014-06-20' of git://anongit.freedesktop.org/drm-intel: (99 commits)
  drm/i915: Update DRIVER_DATE to 20140620
  drivers/i915: Fix unnoticed failure of init_ring_common()
  drm/i915: Track frontbuffer invalidation/flushing
  drm/i915: Use new frontbuffer bits to increase pll clock
  drm/i915: don't take runtime PM reference around freeze/thaw
  drm/i915: use runtime irq suspend/resume in freeze/thaw
  drm/i915: Properly track domain of the fbcon fb
  drm/i915: Print obj->frontbuffer_bits in debugfs output
  drm/i915: Introduce accurate frontbuffer tracking
  drm/i915: Drop schedule_back from psr_exit
  drm/i915: Ditch intel_edp_psr_update
  drm/i915: Drop unecessary complexity from psr_inactivate
  drm/i915: Remove ctx->last_ring
  drm/i915/chv: Ack interrupts before handling them (CHV)
  drm/i915/bdw: Ack interrupts before handling them (GEN8)
  drm/i915/vlv: Ack interrupts before handling them (VLV)
  drm/i915: Ack interrupts before handling them (GEN5 - GEN7)
  drm/i915: Don't BUG_ON in i915_gem_obj_offset
  drm/i915: Grab dev->struct_mutex in i915_gem_pageflip_info
  drm/i915: Add some L3 registers to the parser whitelist
  ...

Conflicts:
	drivers/gpu/drm/i915/i915_drv.c

drivers/gpu/drm/drm_crtc.c

@@ -41,6 +41,10 @@
 
 #include "drm_crtc_internal.h"
 
+static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
+							struct drm_mode_fb_cmd2 *r,
+							struct drm_file *file_priv);
+
 /**
  * drm_modeset_lock_all - take all modeset locks
  * @dev: drm device
@@ -723,7 +727,7 @@ DEFINE_WW_CLASS(crtc_ww_class);
  */
 int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 			      struct drm_plane *primary,
-			      void *cursor,
+			      struct drm_plane *cursor,
 			      const struct drm_crtc_funcs *funcs)
 {
 	struct drm_mode_config *config = &dev->mode_config;
@@ -748,8 +752,11 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	config->num_crtc++;
 
 	crtc->primary = primary;
+	crtc->cursor = cursor;
 	if (primary)
 		primary->possible_crtcs = 1 << drm_crtc_index(crtc);
+	if (cursor)
+		cursor->possible_crtcs = 1 << drm_crtc_index(crtc);
 
  out:
 	drm_modeset_unlock_all(dev);
@@ -2177,45 +2184,32 @@ out:
 	return ret;
 }
 
-/**
- * drm_mode_setplane - configure a plane's configuration
- * @dev: DRM device
- * @data: ioctl data*
- * @file_priv: DRM file info
+/*
+ * setplane_internal - setplane handler for internal callers
  *
- * Set plane configuration, including placement, fb, scaling, and other factors.
- * Or pass a NULL fb to disable.
+ * Note that we assume an extra reference has already been taken on fb.  If the
+ * update fails, this reference will be dropped before return; if it succeeds,
+ * the previous framebuffer (if any) will be unreferenced instead.
  *
- * Returns:
- * Zero on success, errno on failure.
+ * src_{x,y,w,h} are provided in 16.16 fixed point format
  */
-int drm_mode_setplane(struct drm_device *dev, void *data,
-		      struct drm_file *file_priv)
+static int setplane_internal(struct drm_plane *plane,
+			     struct drm_crtc *crtc,
+			     struct drm_framebuffer *fb,
+			     int32_t crtc_x, int32_t crtc_y,
+			     uint32_t crtc_w, uint32_t crtc_h,
+			     /* src_{x,y,w,h} values are 16.16 fixed point */
+			     uint32_t src_x, uint32_t src_y,
+			     uint32_t src_w, uint32_t src_h)
 {
-	struct drm_mode_set_plane *plane_req = data;
-	struct drm_plane *plane;
-	struct drm_crtc *crtc;
-	struct drm_framebuffer *fb = NULL, *old_fb = NULL;
+	struct drm_device *dev = plane->dev;
+	struct drm_framebuffer *old_fb = NULL;
 	int ret = 0;
 	unsigned int fb_width, fb_height;
 	int i;
 
-	if (!drm_core_check_feature(dev, DRIVER_MODESET))
-		return -EINVAL;
-
-	/*
-	 * First, find the plane, crtc, and fb objects.  If not available,
-	 * we don't bother to call the driver.
-	 */
-	plane = drm_plane_find(dev, plane_req->plane_id);
-	if (!plane) {
-		DRM_DEBUG_KMS("Unknown plane ID %d\n",
-			      plane_req->plane_id);
-		return -ENOENT;
-	}
-
 	/* No fb means shut it down */
-	if (!plane_req->fb_id) {
+	if (!fb) {
 		drm_modeset_lock_all(dev);
 		old_fb = plane->fb;
 		ret = plane->funcs->disable_plane(plane);
@@ -2229,14 +2223,6 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	crtc = drm_crtc_find(dev, plane_req->crtc_id);
-	if (!crtc) {
-		DRM_DEBUG_KMS("Unknown crtc ID %d\n",
-			      plane_req->crtc_id);
-		ret = -ENOENT;
-		goto out;
-	}
-
 	/* Check whether this plane is usable on this CRTC */
 	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
 		DRM_DEBUG_KMS("Invalid crtc for plane\n");
@@ -2244,14 +2230,6 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 		goto out;
 	}
 
-	fb = drm_framebuffer_lookup(dev, plane_req->fb_id);
-	if (!fb) {
-		DRM_DEBUG_KMS("Unknown framebuffer ID %d\n",
-			      plane_req->fb_id);
-		ret = -ENOENT;
-		goto out;
-	}
-
 	/* Check whether this plane supports the fb pixel format. */
 	for (i = 0; i < plane->format_count; i++)
 		if (fb->pixel_format == plane->format_types[i])
@@ -2267,43 +2245,25 @@ int drm_mode_setplane(struct drm_device *dev, void *data,
 	fb_height = fb->height << 16;
 
 	/* Make sure source coordinates are inside the fb. */
-	if (plane_req->src_w > fb_width ||
-	    plane_req->src_x > fb_width - plane_req->src_w ||
-	    plane_req->src_h > fb_height ||
-	    plane_req->src_y > fb_height - plane_req->src_h) {
+	if (src_w > fb_width ||
+	    src_x > fb_width - src_w ||
+	    src_h > fb_height ||
+	    src_y > fb_height - src_h) {
 		DRM_DEBUG_KMS("Invalid source coordinates "
 			      "%u.%06ux%u.%06u+%u.%06u+%u.%06u\n",
-			      plane_req->src_w >> 16,
-			      ((plane_req->src_w & 0xffff) * 15625) >> 10,
-			      plane_req->src_h >> 16,
-			      ((plane_req->src_h & 0xffff) * 15625) >> 10,
-			      plane_req->src_x >> 16,
-			      ((plane_req->src_x & 0xffff) * 15625) >> 10,
-			      plane_req->src_y >> 16,
-			      ((plane_req->src_y & 0xffff) * 15625) >> 10);
+			      src_w >> 16, ((src_w & 0xffff) * 15625) >> 10,
+			      src_h >> 16, ((src_h & 0xffff) * 15625) >> 10,
+			      src_x >> 16, ((src_x & 0xffff) * 15625) >> 10,
+			      src_y >> 16, ((src_y & 0xffff) * 15625) >> 10);
 		ret = -ENOSPC;
 		goto out;
 	}
 
-	/* Give drivers some help against integer overflows */
-	if (plane_req->crtc_w > INT_MAX ||
-	    plane_req->crtc_x > INT_MAX - (int32_t) plane_req->crtc_w ||
-	    plane_req->crtc_h > INT_MAX ||
-	    plane_req->crtc_y > INT_MAX - (int32_t) plane_req->crtc_h) {
-		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
-			      plane_req->crtc_w, plane_req->crtc_h,
-			      plane_req->crtc_x, plane_req->crtc_y);
-		ret = -ERANGE;
-		goto out;
-	}
-
 	drm_modeset_lock_all(dev);
 	old_fb = plane->fb;
 	ret = plane->funcs->update_plane(plane, crtc, fb,
-					 plane_req->crtc_x, plane_req->crtc_y,
-					 plane_req->crtc_w, plane_req->crtc_h,
-					 plane_req->src_x, plane_req->src_y,
-					 plane_req->src_w, plane_req->src_h);
+					 crtc_x, crtc_y, crtc_w, crtc_h,
+					 src_x, src_y, src_w, src_h);
 	if (!ret) {
 		plane->crtc = crtc;
 		plane->fb = fb;
@@ -2320,6 +2280,85 @@ out:
 		drm_framebuffer_unreference(old_fb);
 
 	return ret;
+
+}
+
+/**
+ * drm_mode_setplane - configure a plane's configuration
+ * @dev: DRM device
+ * @data: ioctl data*
+ * @file_priv: DRM file info
+ *
+ * Set plane configuration, including placement, fb, scaling, and other factors.
+ * Or pass a NULL fb to disable (planes may be disabled without providing a
+ * valid crtc).
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
+int drm_mode_setplane(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv)
+{
+	struct drm_mode_set_plane *plane_req = data;
+	struct drm_mode_object *obj;
+	struct drm_plane *plane;
+	struct drm_crtc *crtc = NULL;
+	struct drm_framebuffer *fb = NULL;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
+	/* Give drivers some help against integer overflows */
+	if (plane_req->crtc_w > INT_MAX ||
+	    plane_req->crtc_x > INT_MAX - (int32_t) plane_req->crtc_w ||
+	    plane_req->crtc_h > INT_MAX ||
+	    plane_req->crtc_y > INT_MAX - (int32_t) plane_req->crtc_h) {
+		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
+			      plane_req->crtc_w, plane_req->crtc_h,
+			      plane_req->crtc_x, plane_req->crtc_y);
+		return -ERANGE;
+	}
+
+	/*
+	 * First, find the plane, crtc, and fb objects.  If not available,
+	 * we don't bother to call the driver.
+	 */
+	obj = drm_mode_object_find(dev, plane_req->plane_id,
+				   DRM_MODE_OBJECT_PLANE);
+	if (!obj) {
+		DRM_DEBUG_KMS("Unknown plane ID %d\n",
+			      plane_req->plane_id);
+		return -ENOENT;
+	}
+	plane = obj_to_plane(obj);
+
+	if (plane_req->fb_id) {
+		fb = drm_framebuffer_lookup(dev, plane_req->fb_id);
+		if (!fb) {
+			DRM_DEBUG_KMS("Unknown framebuffer ID %d\n",
+				      plane_req->fb_id);
+			return -ENOENT;
+		}
+
+		obj = drm_mode_object_find(dev, plane_req->crtc_id,
+					   DRM_MODE_OBJECT_CRTC);
+		if (!obj) {
+			DRM_DEBUG_KMS("Unknown crtc ID %d\n",
+				      plane_req->crtc_id);
+			return -ENOENT;
+		}
+		crtc = obj_to_crtc(obj);
+	}
+
+	/*
+	 * setplane_internal will take care of deref'ing either the old or new
+	 * framebuffer depending on success.
+	 */
+	return setplane_internal(plane, crtc, fb,
+				 plane_req->crtc_x, plane_req->crtc_y,
+				 plane_req->crtc_w, plane_req->crtc_h,
+				 plane_req->src_x, plane_req->src_y,
+				 plane_req->src_w, plane_req->src_h);
 }
 
 /**
@@ -2568,6 +2607,102 @@ out:
 	return ret;
 }
 
+/**
+ * drm_mode_cursor_universal - translate legacy cursor ioctl call into a
+ *     universal plane handler call
+ * @crtc: crtc to update cursor for
+ * @req: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Legacy cursor ioctl's work directly with driver buffer handles.  To
+ * translate legacy ioctl calls into universal plane handler calls, we need to
+ * wrap the native buffer handle in a drm_framebuffer.
+ *
+ * Note that we assume any handle passed to the legacy ioctls was a 32-bit ARGB
+ * buffer with a pitch of 4*width; the universal plane interface should be used
+ * directly in cases where the hardware can support other buffer settings and
+ * userspace wants to make use of these capabilities.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
+static int drm_mode_cursor_universal(struct drm_crtc *crtc,
+				     struct drm_mode_cursor2 *req,
+				     struct drm_file *file_priv)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_framebuffer *fb = NULL;
+	struct drm_mode_fb_cmd2 fbreq = {
+		.width = req->width,
+		.height = req->height,
+		.pixel_format = DRM_FORMAT_ARGB8888,
+		.pitches = { req->width * 4 },
+		.handles = { req->handle },
+	};
+	int32_t crtc_x, crtc_y;
+	uint32_t crtc_w = 0, crtc_h = 0;
+	uint32_t src_w = 0, src_h = 0;
+	int ret = 0;
+
+	BUG_ON(!crtc->cursor);
+
+	/*
+	 * Obtain fb we'll be using (either new or existing) and take an extra
+	 * reference to it if fb != null.  setplane will take care of dropping
+	 * the reference if the plane update fails.
+	 */
+	if (req->flags & DRM_MODE_CURSOR_BO) {
+		if (req->handle) {
+			fb = add_framebuffer_internal(dev, &fbreq, file_priv);
+			if (IS_ERR(fb)) {
+				DRM_DEBUG_KMS("failed to wrap cursor buffer in drm framebuffer\n");
+				return PTR_ERR(fb);
+			}
+
+			drm_framebuffer_reference(fb);
+		} else {
+			fb = NULL;
+		}
+	} else {
+		mutex_lock(&dev->mode_config.mutex);
+		fb = crtc->cursor->fb;
+		if (fb)
+			drm_framebuffer_reference(fb);
+		mutex_unlock(&dev->mode_config.mutex);
+	}
+
+	if (req->flags & DRM_MODE_CURSOR_MOVE) {
+		crtc_x = req->x;
+		crtc_y = req->y;
+	} else {
+		crtc_x = crtc->cursor_x;
+		crtc_y = crtc->cursor_y;
+	}
+
+	if (fb) {
+		crtc_w = fb->width;
+		crtc_h = fb->height;
+		src_w = fb->width << 16;
+		src_h = fb->height << 16;
+	}
+
+	/*
+	 * setplane_internal will take care of deref'ing either the old or new
+	 * framebuffer depending on success.
+	 */
+	ret = setplane_internal(crtc->cursor, crtc, fb,
+				crtc_x, crtc_y, crtc_w, crtc_h,
+				0, 0, src_w, src_h);
+
+	/* Update successful; save new cursor position, if necessary */
+	if (ret == 0 && req->flags & DRM_MODE_CURSOR_MOVE) {
+		crtc->cursor_x = req->x;
+		crtc->cursor_y = req->y;
+	}
+
+	return ret;
+}
+
 static int drm_mode_cursor_common(struct drm_device *dev,
 				  struct drm_mode_cursor2 *req,
 				  struct drm_file *file_priv)
@@ -2587,6 +2722,13 @@ static int drm_mode_cursor_common(struct drm_device *dev,
 		return -ENOENT;
 	}
 
+	/*
+	 * If this crtc has a universal cursor plane, call that plane's update
+	 * handler rather than using legacy cursor handlers.
+	 */
+	if (crtc->cursor)
+		return drm_mode_cursor_universal(crtc, req, file_priv);
+
 	drm_modeset_lock(&crtc->mutex, NULL);
 	if (req->flags & DRM_MODE_CURSOR_BO) {
 		if (!crtc->funcs->cursor_set && !crtc->funcs->cursor_set2) {
@@ -2886,56 +3028,38 @@ static int framebuffer_check(const struct drm_mode_fb_cmd2 *r)
 	return 0;
 }
 
-/**
- * drm_mode_addfb2 - add an FB to the graphics configuration
- * @dev: drm device for the ioctl
- * @data: data pointer for the ioctl
- * @file_priv: drm file for the ioctl call
- *
- * Add a new FB to the specified CRTC, given a user request with format. This is
- * the 2nd version of the addfb ioctl, which supports multi-planar framebuffers
- * and uses fourcc codes as pixel format specifiers.
- *
- * Called by the user via ioctl.
- *
- * Returns:
- * Zero on success, errno on failure.
- */
-int drm_mode_addfb2(struct drm_device *dev,
-		    void *data, struct drm_file *file_priv)
+static struct drm_framebuffer *add_framebuffer_internal(struct drm_device *dev,
+							struct drm_mode_fb_cmd2 *r,
+							struct drm_file *file_priv)
 {
-	struct drm_mode_fb_cmd2 *r = data;
 	struct drm_mode_config *config = &dev->mode_config;
 	struct drm_framebuffer *fb;
 	int ret;
 
-	if (!drm_core_check_feature(dev, DRIVER_MODESET))
-		return -EINVAL;
-
 	if (r->flags & ~DRM_MODE_FB_INTERLACED) {
 		DRM_DEBUG_KMS("bad framebuffer flags 0x%08x\n", r->flags);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	if ((config->min_width > r->width) || (r->width > config->max_width)) {
 		DRM_DEBUG_KMS("bad framebuffer width %d, should be >= %d && <= %d\n",
 			  r->width, config->min_width, config->max_width);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 	if ((config->min_height > r->height) || (r->height > config->max_height)) {
 		DRM_DEBUG_KMS("bad framebuffer height %d, should be >= %d && <= %d\n",
 			  r->height, config->min_height, config->max_height);
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	ret = framebuffer_check(r);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	fb = dev->mode_config.funcs->fb_create(dev, file_priv, r);
 	if (IS_ERR(fb)) {
 		DRM_DEBUG_KMS("could not create framebuffer\n");
-		return PTR_ERR(fb);
+		return fb;
 	}
 
 	mutex_lock(&file_priv->fbs_lock);
@@ -2944,8 +3068,37 @@ int drm_mode_addfb2(struct drm_device *dev,
 	DRM_DEBUG_KMS("[FB:%d]\n", fb->base.id);
 	mutex_unlock(&file_priv->fbs_lock);
 
+	return fb;
+}
 
-	return ret;
+/**
+ * drm_mode_addfb2 - add an FB to the graphics configuration
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Add a new FB to the specified CRTC, given a user request with format. This is
+ * the 2nd version of the addfb ioctl, which supports multi-planar framebuffers
+ * and uses fourcc codes as pixel format specifiers.
+ *
+ * Called by the user via ioctl.
+ *
+ * Returns:
+ * Zero on success, errno on failure.
+ */
+int drm_mode_addfb2(struct drm_device *dev,
+		    void *data, struct drm_file *file_priv)
+{
+	struct drm_framebuffer *fb;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
+	fb = add_framebuffer_internal(dev, data, file_priv);
+	if (IS_ERR(fb))
+		return PTR_ERR(fb);
+
+	return 0;
 }
 
 /**

drivers/gpu/drm/i915/i915_cmd_parser.c

@@ -426,6 +426,9 @@ static const u32 gen7_render_regs[] = {
 	GEN7_SO_WRITE_OFFSET(1),
 	GEN7_SO_WRITE_OFFSET(2),
 	GEN7_SO_WRITE_OFFSET(3),
+	GEN7_L3SQCREG1,
+	GEN7_L3CNTLREG2,
+	GEN7_L3CNTLREG3,
 };
 
 static const u32 gen7_blt_regs[] = {

drivers/gpu/drm/i915/i915_debugfs.c

@@ -170,6 +170,8 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	}
 	if (obj->ring != NULL)
 		seq_printf(m, " (%s)", obj->ring->name);
+	if (obj->frontbuffer_bits)
+		seq_printf(m, " (frontbuffer: 0x%03x)", obj->frontbuffer_bits);
 }
 
 static void describe_ctx(struct seq_file *m, struct intel_context *ctx)
@@ -515,6 +517,11 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 	unsigned long flags;
 	struct intel_crtc *crtc;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	for_each_intel_crtc(dev, crtc) {
 		const char pipe = pipe_name(crtc->pipe);
@@ -556,6 +563,8 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -1029,7 +1038,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   MEMSTAT_VID_SHIFT);
 		seq_printf(m, "Current P-state: %d\n",
 			   (rgvstat & MEMSTAT_PSTATE_MASK) >> MEMSTAT_PSTATE_SHIFT);
-	} else if ((IS_GEN6(dev) || IS_GEN7(dev)) && !IS_VALLEYVIEW(dev)) {
+	} else if (IS_GEN6(dev) || (IS_GEN7(dev) && !IS_VALLEYVIEW(dev)) ||
+		   IS_BROADWELL(dev)) {
 		u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
 		u32 rp_state_limits = I915_READ(GEN6_RP_STATE_LIMITS);
 		u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
@@ -1048,7 +1058,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 
 		reqf = I915_READ(GEN6_RPNSWREQ);
 		reqf &= ~GEN6_TURBO_DISABLE;
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 			reqf >>= 24;
 		else
 			reqf >>= 25;
@@ -1065,7 +1075,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI);
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN);
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN);
-		if (IS_HASWELL(dev))
+		if (IS_HASWELL(dev) || IS_BROADWELL(dev))
 			cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
 		else
 			cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
@@ -1677,9 +1687,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 
 #ifdef CONFIG_DRM_I915_FBDEV
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	int ret = mutex_lock_interruptible(&dev->mode_config.mutex);
-	if (ret)
-		return ret;
 
 	ifbdev = dev_priv->fbdev;
 	fb = to_intel_framebuffer(ifbdev->helper.fb);
@@ -1692,7 +1699,6 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 		   atomic_read(&fb->base.refcount.refcount));
 	describe_obj(m, fb->obj);
 	seq_putc(m, '\n');
-	mutex_unlock(&dev->mode_config.mutex);
 #endif
 
 	mutex_lock(&dev->mode_config.fb_lock);
@@ -1723,7 +1729,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 	struct intel_context *ctx;
 	int ret, i;
 
-	ret = mutex_lock_interruptible(&dev->mode_config.mutex);
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
 	if (ret)
 		return ret;
 
@@ -1753,7 +1759,7 @@ static int i915_context_status(struct seq_file *m, void *unused)
 		seq_putc(m, '\n');
 	}
 
-	mutex_unlock(&dev->mode_config.mutex);
+	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
 }
@@ -1978,10 +1984,12 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 	seq_printf(m, "Sink_Support: %s\n", yesno(dev_priv->psr.sink_support));
 	seq_printf(m, "Source_OK: %s\n", yesno(dev_priv->psr.source_ok));
+	seq_printf(m, "Enabled: %s\n", yesno(dev_priv->psr.enabled));
+	seq_printf(m, "Active: %s\n", yesno(dev_priv->psr.active));
 
 	enabled = HAS_PSR(dev) &&
 		I915_READ(EDP_PSR_CTL(dev)) & EDP_PSR_ENABLE;
-	seq_printf(m, "Enabled: %s\n", yesno(enabled));
+	seq_printf(m, "HW Enabled & Active bit: %s\n", yesno(enabled));
 
 	if (HAS_PSR(dev))
 		psrperf = I915_READ(EDP_PSR_PERF_CNT(dev)) &
@@ -2223,9 +2231,12 @@ static void intel_crtc_info(struct seq_file *m, struct intel_crtc *intel_crtc)
 	struct drm_crtc *crtc = &intel_crtc->base;
 	struct intel_encoder *intel_encoder;
 
-	seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
-		   crtc->primary->fb->base.id, crtc->x, crtc->y,
-		   crtc->primary->fb->width, crtc->primary->fb->height);
+	if (crtc->primary->fb)
+		seq_printf(m, "\tfb: %d, pos: %dx%d, size: %dx%d\n",
+			   crtc->primary->fb->base.id, crtc->x, crtc->y,
+			   crtc->primary->fb->width, crtc->primary->fb->height);
+	else
+		seq_puts(m, "\tprimary plane disabled\n");
 	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
 		intel_encoder_info(m, intel_crtc, intel_encoder);
 }
@@ -2929,11 +2940,16 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe,
 	/* real source -> none transition */
 	if (source == INTEL_PIPE_CRC_SOURCE_NONE) {
 		struct intel_pipe_crc_entry *entries;
+		struct intel_crtc *crtc =
+			to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]);
 
 		DRM_DEBUG_DRIVER("stopping CRCs for pipe %c\n",
 				 pipe_name(pipe));
 
-		intel_wait_for_vblank(dev, pipe);
+		drm_modeset_lock(&crtc->base.mutex, NULL);
+		if (crtc->active)
+			intel_wait_for_vblank(dev, pipe);
+		drm_modeset_unlock(&crtc->base.mutex);
 
 		spin_lock_irq(&pipe_crc->lock);
 		entries = pipe_crc->entries;
@@ -3506,7 +3522,7 @@ i915_max_freq_get(void *data, u64 *val)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -3532,7 +3548,7 @@ i915_max_freq_set(void *data, u64 val)
 	u32 rp_state_cap, hw_max, hw_min;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -3587,7 +3603,7 @@ i915_min_freq_get(void *data, u64 *val)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
@@ -3613,7 +3629,7 @@ i915_min_freq_set(void *data, u64 val)
 	u32 rp_state_cap, hw_max, hw_min;
 	int ret;
 
-	if (!(IS_GEN6(dev) || IS_GEN7(dev)))
+	if (INTEL_INFO(dev)->gen < 6)
 		return -ENODEV;
 
 	flush_delayed_work(&dev_priv->rps.delayed_resume_work);

drivers/gpu/drm/i915/i915_dma.c

@@ -138,7 +138,7 @@ static void i915_free_hws(struct drm_device *dev)
 	I915_WRITE(HWS_PGA, 0x1ffff000);
 }
 
-void i915_kernel_lost_context(struct drm_device * dev)
+void i915_kernel_lost_context(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv;
@@ -166,7 +166,7 @@ void i915_kernel_lost_context(struct drm_device * dev)
 		master_priv->sarea_priv->perf_boxes |= I915_BOX_RING_EMPTY;
 }
 
-static int i915_dma_cleanup(struct drm_device * dev)
+static int i915_dma_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
@@ -190,7 +190,7 @@ static int i915_dma_cleanup(struct drm_device * dev)
 	return 0;
 }
 
-static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
+static int i915_initialize(struct drm_device *dev, drm_i915_init_t *init)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
@@ -235,7 +235,7 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
 	return 0;
 }
 
-static int i915_dma_resume(struct drm_device * dev)
+static int i915_dma_resume(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_engine_cs *ring = LP_RING(dev_priv);
@@ -359,7 +359,7 @@ static int validate_cmd(int cmd)
 	return 0;
 }
 
-static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords)
+static int i915_emit_cmds(struct drm_device *dev, int *buffer, int dwords)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i, ret;
@@ -369,6 +369,7 @@ static int i915_emit_cmds(struct drm_device * dev, int *buffer, int dwords)
 
 	for (i = 0; i < dwords;) {
 		int sz = validate_cmd(buffer[i]);
+
 		if (sz == 0 || i + sz > dwords)
 			return -EINVAL;
 		i += sz;
@@ -453,7 +454,7 @@ static void i915_emit_breadcrumb(struct drm_device *dev)
 	}
 }
 
-static int i915_dispatch_cmdbuffer(struct drm_device * dev,
+static int i915_dispatch_cmdbuffer(struct drm_device *dev,
 				   drm_i915_cmdbuffer_t *cmd,
 				   struct drm_clip_rect *cliprects,
 				   void *cmdbuf)
@@ -487,8 +488,8 @@ static int i915_dispatch_cmdbuffer(struct drm_device * dev,
 	return 0;
 }
 
-static int i915_dispatch_batchbuffer(struct drm_device * dev,
-				     drm_i915_batchbuffer_t * batch,
+static int i915_dispatch_batchbuffer(struct drm_device *dev,
+				     drm_i915_batchbuffer_t *batch,
 				     struct drm_clip_rect *cliprects)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -549,7 +550,7 @@ static int i915_dispatch_batchbuffer(struct drm_device * dev,
 	return 0;
 }
 
-static int i915_dispatch_flip(struct drm_device * dev)
+static int i915_dispatch_flip(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv =
@@ -755,7 +756,7 @@ fail_batch_free:
 	return ret;
 }
 
-static int i915_emit_irq(struct drm_device * dev)
+static int i915_emit_irq(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
@@ -781,7 +782,7 @@ static int i915_emit_irq(struct drm_device * dev)
 	return dev_priv->dri1.counter;
 }
 
-static int i915_wait_irq(struct drm_device * dev, int irq_nr)
+static int i915_wait_irq(struct drm_device *dev, int irq_nr)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_master_private *master_priv = dev->primary->master->driver_priv;
@@ -1266,6 +1267,7 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, enum vga_switcheroo_
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	pm_message_t pmm = { .event = PM_EVENT_SUSPEND };
+
 	if (state == VGA_SWITCHEROO_ON) {
 		pr_info("switched on\n");
 		dev->switch_power_state = DRM_SWITCH_POWER_CHANGING;
@@ -1488,10 +1490,11 @@ static void i915_dump_device_info(struct drm_i915_private *dev_priv)
 #define SEP_EMPTY
 #define PRINT_FLAG(name) info->name ? #name "," : ""
 #define SEP_COMMA ,
-	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x flags="
+	DRM_DEBUG_DRIVER("i915 device info: gen=%i, pciid=0x%04x rev=0x%02x flags="
 			 DEV_INFO_FOR_EACH_FLAG(PRINT_S, SEP_EMPTY),
 			 info->gen,
 			 dev_priv->dev->pdev->device,
+			 dev_priv->dev->pdev->revision,
 			 DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG, SEP_COMMA));
 #undef PRINT_S
 #undef SEP_EMPTY
@@ -1602,6 +1605,7 @@ 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);
 
@@ -1929,7 +1933,7 @@ int i915_driver_open(struct drm_device *dev, struct drm_file *file)
  * and DMA structures, since the kernel won't be using them, and clea
  * up any GEM state.
  */
-void i915_driver_lastclose(struct drm_device * dev)
+void i915_driver_lastclose(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -1950,7 +1954,7 @@ void i915_driver_lastclose(struct drm_device * dev)
 	i915_dma_cleanup(dev);
 }
 
-void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
+void i915_driver_preclose(struct drm_device *dev, struct drm_file *file_priv)
 {
 	mutex_lock(&dev->struct_mutex);
 	i915_gem_context_close(dev, file_priv);
@@ -2027,7 +2031,7 @@ int i915_max_ioctl = ARRAY_SIZE(i915_ioctls);
  * manage the gtt, we need to claim that all intel devices are agp.  For
  * otherwise the drm core refuses to initialize the agp support code.
  */
-int i915_driver_device_is_agp(struct drm_device * dev)
+int i915_driver_device_is_agp(struct drm_device *dev)
 {
 	return 1;
 }

drivers/gpu/drm/i915/i915_drv.c

@@ -28,6 +28,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/acpi.h>
 #include <drm/drmP.h>
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
@@ -46,8 +47,6 @@ static struct drm_driver driver;
 			  PIPE_C_OFFSET, PIPE_EDP_OFFSET }, \
 	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
 			   TRANSCODER_C_OFFSET, TRANSCODER_EDP_OFFSET }, \
-	.dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET }, \
-	.dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET }, \
 	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET }
 
 #define GEN_CHV_PIPEOFFSETS \
@@ -55,10 +54,6 @@ static struct drm_driver driver;
 			  CHV_PIPE_C_OFFSET }, \
 	.trans_offsets = { TRANSCODER_A_OFFSET, TRANSCODER_B_OFFSET, \
 			   CHV_TRANSCODER_C_OFFSET, }, \
-	.dpll_offsets = { DPLL_A_OFFSET, DPLL_B_OFFSET, \
-			  CHV_DPLL_C_OFFSET }, \
-	.dpll_md_offsets = { DPLL_A_MD_OFFSET, DPLL_B_MD_OFFSET, \
-			     CHV_DPLL_C_MD_OFFSET }, \
 	.palette_offsets = { PALETTE_A_OFFSET, PALETTE_B_OFFSET, \
 			     CHV_PALETTE_C_OFFSET }
 
@@ -499,8 +494,7 @@ static int i915_drm_freeze(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
-
-	intel_runtime_pm_get(dev_priv);
+	pci_power_t opregion_target_state;
 
 	/* ignore lid events during suspend */
 	mutex_lock(&dev_priv->modeset_restore_lock);
@@ -526,9 +520,9 @@ static int i915_drm_freeze(struct drm_device *dev)
 			return error;
 		}
 
-		drm_irq_uninstall(dev);
+		intel_runtime_pm_disable_interrupts(dev);
 
-		intel_disable_gt_powersave(dev);
+		intel_suspend_gt_powersave(dev);
 
 		/*
 		 * Disable CRTCs directly since we want to preserve sw state
@@ -547,8 +541,14 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	i915_save_state(dev);
 
+	if (acpi_target_system_state() >= ACPI_STATE_S3)
+		opregion_target_state = PCI_D3cold;
+	else
+		opregion_target_state = PCI_D1;
+	intel_opregion_notify_adapter(dev, opregion_target_state);
+
+	intel_uncore_forcewake_reset(dev, false);
 	intel_opregion_fini(dev);
-	intel_uncore_fini(dev);
 
 	console_lock();
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED);
@@ -556,6 +556,8 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	dev_priv->suspend_count++;
 
+	intel_display_set_init_power(dev_priv, false);
+
 	return 0;
 }
 
@@ -605,7 +607,10 @@ static int i915_drm_thaw_early(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	intel_uncore_early_sanitize(dev);
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev))
+		hsw_disable_pc8(dev_priv);
+
+	intel_uncore_early_sanitize(dev, true);
 	intel_uncore_sanitize(dev);
 	intel_power_domains_init_hw(dev_priv);
 
@@ -638,8 +643,7 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 		}
 		mutex_unlock(&dev->struct_mutex);
 
-		/* We need working interrupts for modeset enabling ... */
-		drm_irq_install(dev, dev->pdev->irq);
+		intel_runtime_pm_restore_interrupts(dev);
 
 		intel_modeset_init_hw(dev);
 
@@ -676,7 +680,8 @@ static int __i915_drm_thaw(struct drm_device *dev, bool restore_gtt_mappings)
 	dev_priv->modeset_restore = MODESET_DONE;
 	mutex_unlock(&dev_priv->modeset_restore_lock);
 
-	intel_runtime_pm_put(dev_priv);
+	intel_opregion_notify_adapter(dev, PCI_D0);
+
 	return 0;
 }
 
@@ -885,6 +890,7 @@ static int i915_pm_suspend_late(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct drm_i915_private *dev_priv = drm_dev->dev_private;
 
 	/*
 	 * We have a suspedn ordering issue with the snd-hda driver also
@@ -898,6 +904,9 @@ static int i915_pm_suspend_late(struct device *dev)
 	if (drm_dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
+	if (IS_HASWELL(drm_dev) || IS_BROADWELL(drm_dev))
+		hsw_enable_pc8(dev_priv);
+
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
 

drivers/gpu/drm/i915/i915_drv.h

@@ -53,7 +53,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20080730"
+#define DRIVER_DATE		"20140620"
 
 enum pipe {
 	INVALID_PIPE = -1,
@@ -552,8 +552,6 @@ struct intel_device_info {
 	/* Register offsets for the various display pipes and transcoders */
 	int pipe_offsets[I915_MAX_TRANSCODERS];
 	int trans_offsets[I915_MAX_TRANSCODERS];
-	int dpll_offsets[I915_MAX_PIPES];
-	int dpll_md_offsets[I915_MAX_PIPES];
 	int palette_offsets[I915_MAX_PIPES];
 	int cursor_offsets[I915_MAX_PIPES];
 };
@@ -593,7 +591,6 @@ struct intel_context {
 	bool is_initialized;
 	uint8_t remap_slice;
 	struct drm_i915_file_private *file_priv;
-	struct intel_engine_cs *last_ring;
 	struct drm_i915_gem_object *obj;
 	struct i915_ctx_hang_stats hang_stats;
 	struct i915_address_space *vm;
@@ -638,6 +635,10 @@ struct i915_drrs {
 struct i915_psr {
 	bool sink_support;
 	bool source_ok;
+	bool setup_done;
+	bool enabled;
+	bool active;
+	struct delayed_work work;
 };
 
 enum intel_pch {
@@ -1331,6 +1332,17 @@ struct intel_pipe_crc {
 	wait_queue_head_t wq;
 };
 
+struct i915_frontbuffer_tracking {
+	struct mutex lock;
+
+	/*
+	 * Tracking bits for delayed frontbuffer flushing du to gpu activity or
+	 * scheduled flips.
+	 */
+	unsigned busy_bits;
+	unsigned flip_bits;
+};
+
 struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *slab;
@@ -1370,6 +1382,9 @@ 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. */
@@ -1473,6 +1488,9 @@ struct drm_i915_private {
 	bool lvds_downclock_avail;
 	/* indicates the reduced downclock for LVDS*/
 	int lvds_downclock;
+
+	struct i915_frontbuffer_tracking fb_tracking;
+
 	u16 orig_clock;
 
 	bool mchbar_need_disable;
@@ -1590,6 +1608,28 @@ struct drm_i915_gem_object_ops {
 	void (*release)(struct drm_i915_gem_object *);
 };
 
+/*
+ * Frontbuffer tracking bits. Set in obj->frontbuffer_bits while a gem bo is
+ * considered to be the frontbuffer for the given plane interface-vise. This
+ * doesn't mean that the hw necessarily already scans it out, but that any
+ * rendering (by the cpu or gpu) will land in the frontbuffer eventually.
+ *
+ * We have one bit per pipe and per scanout plane type.
+ */
+#define INTEL_FRONTBUFFER_BITS_PER_PIPE 4
+#define INTEL_FRONTBUFFER_BITS \
+	(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES)
+#define INTEL_FRONTBUFFER_PRIMARY(pipe) \
+	(1 << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
+#define INTEL_FRONTBUFFER_CURSOR(pipe) \
+	(1 << (1 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_SPRITE(pipe) \
+	(1 << (2 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_OVERLAY(pipe) \
+	(1 << (3 +(INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe))))
+#define INTEL_FRONTBUFFER_ALL_MASK(pipe) \
+	(0xf << (INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)))
+
 struct drm_i915_gem_object {
 	struct drm_gem_object base;
 
@@ -1659,6 +1699,12 @@ struct drm_i915_gem_object {
 	unsigned int pin_mappable:1;
 	unsigned int pin_display:1;
 
+	/*
+	 * Is the object to be mapped as read-only to the GPU
+	 * Only honoured if hardware has relevant pte bit
+	 */
+	unsigned long gt_ro:1;
+
 	/*
 	 * Is the GPU currently using a fence to access this buffer,
 	 */
@@ -1671,6 +1717,8 @@ struct drm_i915_gem_object {
 	unsigned int has_global_gtt_mapping:1;
 	unsigned int has_dma_mapping:1;
 
+	unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
+
 	struct sg_table *pages;
 	int pages_pin_count;
 
@@ -1717,6 +1765,10 @@ struct drm_i915_gem_object {
 };
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+		       struct drm_i915_gem_object *new,
+		       unsigned frontbuffer_bits);
+
 /**
  * Request queue structure.
  *
@@ -1938,10 +1990,8 @@ struct drm_i915_cmd_table {
 #define I915_NEED_GFX_HWS(dev)	(INTEL_INFO(dev)->need_gfx_hws)
 
 #define HAS_HW_CONTEXTS(dev)	(INTEL_INFO(dev)->gen >= 6)
-#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6 && \
-				 (!IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)))
-#define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 \
-				 && !IS_GEN8(dev))
+#define HAS_ALIASING_PPGTT(dev)	(INTEL_INFO(dev)->gen >= 6)
+#define HAS_PPGTT(dev)		(INTEL_INFO(dev)->gen >= 7 && !IS_GEN8(dev))
 #define USES_PPGTT(dev)		intel_enable_ppgtt(dev, false)
 #define USES_FULL_PPGTT(dev)	intel_enable_ppgtt(dev, true)
 
@@ -2038,6 +2088,7 @@ struct i915_params {
 	bool reset;
 	bool disable_display;
 	bool disable_vtd_wa;
+	int use_mmio_flip;
 };
 extern struct i915_params i915 __read_mostly;
 
@@ -2082,10 +2133,12 @@ extern void intel_irq_init(struct drm_device *dev);
 extern void intel_hpd_init(struct drm_device *dev);
 
 extern void intel_uncore_sanitize(struct drm_device *dev);
-extern void intel_uncore_early_sanitize(struct drm_device *dev);
+extern void intel_uncore_early_sanitize(struct drm_device *dev,
+					bool restore_forcewake);
 extern void intel_uncore_init(struct drm_device *dev);
 extern void intel_uncore_check_errors(struct drm_device *dev);
 extern void intel_uncore_fini(struct drm_device *dev);
+extern void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore);
 
 void
 i915_enable_pipestat(struct drm_i915_private *dev_priv, enum pipe pipe,
@@ -2233,6 +2286,8 @@ 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)
@@ -2443,7 +2498,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 					       u32 stolen_offset,
 					       u32 gtt_offset,
 					       u32 size);
-void i915_gem_object_release_stolen(struct drm_i915_gem_object *obj);
 
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
@@ -2603,6 +2657,8 @@ 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,

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;
@@ -1561,14 +1561,29 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ret)
 		goto unpin;
 
-	obj->fault_mappable = true;
-
+	/* Finally, remap it using the new GTT offset */
 	pfn = dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj);
 	pfn >>= PAGE_SHIFT;
-	pfn += page_offset;
 
-	/* Finally, remap it using the new GTT offset */
-	ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address, pfn);
+	if (!obj->fault_mappable) {
+		unsigned long size = min_t(unsigned long,
+					   vma->vm_end - vma->vm_start,
+					   obj->base.size);
+		int i;
+
+		for (i = 0; i < size >> PAGE_SHIFT; i++) {
+			ret = vm_insert_pfn(vma,
+					    (unsigned long)vma->vm_start + i * PAGE_SIZE,
+					    pfn + i);
+			if (ret)
+				break;
+		}
+
+		obj->fault_mappable = true;
+	} else
+		ret = vm_insert_pfn(vma,
+				    (unsigned long)vmf->virtual_address,
+				    pfn + page_offset);
 unpin:
 	i915_gem_object_ggtt_unpin(obj);
 unlock:
@@ -1616,22 +1631,6 @@ out:
 	return ret;
 }
 
-void i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
-{
-	struct i915_vma *vma;
-
-	/*
-	 * Only the global gtt is relevant for gtt memory mappings, so restrict
-	 * list traversal to objects bound into the global address space. Note
-	 * that the active list should be empty, but better safe than sorry.
-	 */
-	WARN_ON(!list_empty(&dev_priv->gtt.base.active_list));
-	list_for_each_entry(vma, &dev_priv->gtt.base.active_list, mm_list)
-		i915_gem_release_mmap(vma->obj);
-	list_for_each_entry(vma, &dev_priv->gtt.base.inactive_list, mm_list)
-		i915_gem_release_mmap(vma->obj);
-}
-
 /**
  * i915_gem_release_mmap - remove physical page mappings
  * @obj: obj in question
@@ -1657,6 +1656,15 @@ i915_gem_release_mmap(struct drm_i915_gem_object *obj)
 	obj->fault_mappable = false;
 }
 
+void
+i915_gem_release_all_mmaps(struct drm_i915_private *dev_priv)
+{
+	struct drm_i915_gem_object *obj;
+
+	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
+		i915_gem_release_mmap(obj);
+}
+
 uint32_t
 i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 {
@@ -2211,6 +2219,8 @@ i915_gem_object_move_to_inactive(struct drm_i915_gem_object *obj)
 			list_move_tail(&vma->mm_list, &vm->inactive_list);
 	}
 
+	intel_fb_obj_flush(obj, true);
+
 	list_del_init(&obj->ring_list);
 	obj->ring = NULL;
 
@@ -3540,6 +3550,8 @@ i915_gem_object_flush_gtt_write_domain(struct drm_i915_gem_object *obj)
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
+	intel_fb_obj_flush(obj, false);
+
 	trace_i915_gem_object_change_domain(obj,
 					    obj->base.read_domains,
 					    old_write_domain);
@@ -3561,6 +3573,8 @@ i915_gem_object_flush_cpu_write_domain(struct drm_i915_gem_object *obj,
 	old_write_domain = obj->base.write_domain;
 	obj->base.write_domain = 0;
 
+	intel_fb_obj_flush(obj, false);
+
 	trace_i915_gem_object_change_domain(obj,
 					    obj->base.read_domains,
 					    old_write_domain);
@@ -3614,6 +3628,9 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 		obj->dirty = 1;
 	}
 
+	if (write)
+		intel_fb_obj_invalidate(obj, NULL);
+
 	trace_i915_gem_object_change_domain(obj,
 					    old_read_domains,
 					    old_write_domain);
@@ -3950,6 +3967,9 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 		obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
+	if (write)
+		intel_fb_obj_invalidate(obj, NULL);
+
 	trace_i915_gem_object_change_domain(obj,
 					    old_read_domains,
 					    old_write_domain);
@@ -4438,13 +4458,14 @@ void i915_gem_free_object(struct drm_gem_object *gem_obj)
 	if (obj->stolen)
 		i915_gem_object_unpin_pages(obj);
 
+	WARN_ON(obj->frontbuffer_bits);
+
 	if (WARN_ON(obj->pages_pin_count))
 		obj->pages_pin_count = 0;
 	if (discard_backing_storage(obj))
 		obj->madv = I915_MADV_DONTNEED;
 	i915_gem_object_put_pages(obj);
 	i915_gem_object_free_mmap_offset(obj);
-	i915_gem_object_release_stolen(obj);
 
 	BUG_ON(obj->pages);
 
@@ -4922,6 +4943,8 @@ i915_gem_load(struct drm_device *dev)
 
 	dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
 	register_oom_notifier(&dev_priv->mm.oom_notifier);
+
+	mutex_init(&dev_priv->fb_tracking.lock);
 }
 
 void i915_gem_release(struct drm_device *dev, struct drm_file *file)
@@ -4983,6 +5006,23 @@ int i915_gem_open(struct drm_device *dev, struct drm_file *file)
 	return ret;
 }
 
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+		       struct drm_i915_gem_object *new,
+		       unsigned frontbuffer_bits)
+{
+	if (old) {
+		WARN_ON(!mutex_is_locked(&old->base.dev->struct_mutex));
+		WARN_ON(!(old->frontbuffer_bits & frontbuffer_bits));
+		old->frontbuffer_bits &= ~frontbuffer_bits;
+	}
+
+	if (new) {
+		WARN_ON(!mutex_is_locked(&new->base.dev->struct_mutex));
+		WARN_ON(new->frontbuffer_bits & frontbuffer_bits);
+		new->frontbuffer_bits |= frontbuffer_bits;
+	}
+}
+
 static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 {
 	if (!mutex_is_locked(mutex))
@@ -5065,12 +5105,13 @@ unsigned long i915_gem_obj_offset(struct drm_i915_gem_object *o,
 	    vm == &dev_priv->mm.aliasing_ppgtt->base)
 		vm = &dev_priv->gtt.base;
 
-	BUG_ON(list_empty(&o->vma_list));
 	list_for_each_entry(vma, &o->vma_list, vma_link) {
 		if (vma->vm == vm)
 			return vma->node.start;
 
 	}
+	WARN(1, "%s vma for this object not found.\n",
+	     i915_is_ggtt(vm) ? "global" : "ppgtt");
 	return -1;
 }
 

drivers/gpu/drm/i915/i915_gem_context.c

@@ -606,7 +606,7 @@ static int do_switch(struct intel_engine_cs *ring,
 		BUG_ON(!i915_gem_obj_is_pinned(from->obj));
 	}
 
-	if (from == to && from->last_ring == ring && !to->remap_slice)
+	if (from == to && !to->remap_slice)
 		return 0;
 
 	/* Trying to pin first makes error handling easier. */
@@ -703,7 +703,6 @@ static int do_switch(struct intel_engine_cs *ring,
 done:
 	i915_gem_context_reference(to);
 	ring->last_context = to;
-	to->last_ring = ring;
 
 	if (uninitialized) {
 		ret = i915_gem_render_state_init(ring);

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -975,10 +975,8 @@ i915_gem_execbuffer_move_to_active(struct list_head *vmas,
 		if (obj->base.write_domain) {
 			obj->dirty = 1;
 			obj->last_write_seqno = intel_ring_get_seqno(ring);
-			/* check for potential scanout */
-			if (i915_gem_obj_ggtt_bound(obj) &&
-			    i915_gem_obj_to_ggtt(obj)->pin_count)
-				intel_mark_fb_busy(obj, ring);
+
+			intel_fb_obj_invalidate(obj, ring);
 
 			/* update for the implicit flush after a batch */
 			obj->base.write_domain &= ~I915_GEM_GPU_DOMAINS;
@@ -1525,7 +1523,7 @@ i915_gem_execbuffer2(struct drm_device *dev, void *data,
 	ret = i915_gem_do_execbuffer(dev, data, file, args, exec2_list);
 	if (!ret) {
 		/* Copy the new buffer offsets back to the user's exec list. */
-		struct drm_i915_gem_exec_object2 *user_exec_list =
+		struct drm_i915_gem_exec_object2 __user *user_exec_list =
 				   to_user_ptr(args->buffers_ptr);
 		int i;
 

drivers/gpu/drm/i915/i915_gem_gtt.c

@@ -63,6 +63,12 @@ static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
 	}
 #endif
 
+	/* Early VLV doesn't have this */
+	if (IS_VALLEYVIEW(dev) && dev->pdev->revision < 0xb) {
+		DRM_DEBUG_DRIVER("disabling PPGTT on pre-B3 step VLV\n");
+		return 0;
+	}
+
 	return HAS_ALIASING_PPGTT(dev) ? 1 : 0;
 }
 
@@ -110,7 +116,7 @@ static inline gen8_ppgtt_pde_t gen8_pde_encode(struct drm_device *dev,
 
 static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
@@ -132,7 +138,7 @@ static gen6_gtt_pte_t snb_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
@@ -156,7 +162,7 @@ static gen6_gtt_pte_t ivb_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 flags)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= GEN6_PTE_ADDR_ENCODE(addr);
@@ -164,7 +170,8 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 	/* Mark the page as writeable.  Other platforms don't have a
 	 * setting for read-only/writable, so this matches that behavior.
 	 */
-	pte |= BYT_PTE_WRITEABLE;
+	if (!(flags & PTE_READ_ONLY))
+		pte |= BYT_PTE_WRITEABLE;
 
 	if (level != I915_CACHE_NONE)
 		pte |= BYT_PTE_SNOOPED_BY_CPU_CACHES;
@@ -174,7 +181,7 @@ static gen6_gtt_pte_t byt_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid)
+				     bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
@@ -187,7 +194,7 @@ static gen6_gtt_pte_t hsw_pte_encode(dma_addr_t addr,
 
 static gen6_gtt_pte_t iris_pte_encode(dma_addr_t addr,
 				      enum i915_cache_level level,
-				      bool valid)
+				      bool valid, u32 unused)
 {
 	gen6_gtt_pte_t pte = valid ? GEN6_PTE_VALID : 0;
 	pte |= HSW_PTE_ADDR_ENCODE(addr);
@@ -301,7 +308,7 @@ static void gen8_ppgtt_clear_range(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
 				      uint64_t start,
-				      enum i915_cache_level cache_level)
+				      enum i915_cache_level cache_level, u32 unused)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
@@ -639,7 +646,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 	uint32_t pd_entry;
 	int pte, pde;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
 
 	pd_addr = (gen6_gtt_pte_t __iomem *)dev_priv->gtt.gsm +
 		ppgtt->pd_offset / sizeof(gen6_gtt_pte_t);
@@ -941,7 +948,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned first_pte = first_entry % I915_PPGTT_PT_ENTRIES;
 	unsigned last_pte, i;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, true, 0);
 
 	while (num_entries) {
 		last_pte = first_pte + num_entries;
@@ -964,7 +971,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 				      struct sg_table *pages,
 				      uint64_t start,
-				      enum i915_cache_level cache_level)
+				      enum i915_cache_level cache_level, u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(vm, struct i915_hw_ppgtt, base);
@@ -981,7 +988,8 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 
 		pt_vaddr[act_pte] =
 			vm->pte_encode(sg_page_iter_dma_address(&sg_iter),
-				       cache_level, true);
+				       cache_level, true, flags);
+
 		if (++act_pte == I915_PPGTT_PT_ENTRIES) {
 			kunmap_atomic(pt_vaddr);
 			pt_vaddr = NULL;
@@ -1218,8 +1226,12 @@ ppgtt_bind_vma(struct i915_vma *vma,
 	       enum i915_cache_level cache_level,
 	       u32 flags)
 {
+	/* Currently applicable only to VLV */
+	if (vma->obj->gt_ro)
+		flags |= PTE_READ_ONLY;
+
 	vma->vm->insert_entries(vma->vm, vma->obj->pages, vma->node.start,
-				cache_level);
+				cache_level, flags);
 }
 
 static void ppgtt_unbind_vma(struct i915_vma *vma)
@@ -1394,7 +1406,7 @@ static inline void gen8_set_pte(void __iomem *addr, gen8_gtt_pte_t pte)
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     uint64_t start,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level, u32 unused)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
@@ -1440,7 +1452,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct sg_table *st,
 				     uint64_t start,
-				     enum i915_cache_level level)
+				     enum i915_cache_level level, u32 flags)
 {
 	struct drm_i915_private *dev_priv = vm->dev->dev_private;
 	unsigned first_entry = start >> PAGE_SHIFT;
@@ -1452,7 +1464,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 
 	for_each_sg_page(st->sgl, &sg_iter, st->nents, 0) {
 		addr = sg_page_iter_dma_address(&sg_iter);
-		iowrite32(vm->pte_encode(addr, level, true), &gtt_entries[i]);
+		iowrite32(vm->pte_encode(addr, level, true, flags), &gtt_entries[i]);
 		i++;
 	}
 
@@ -1464,7 +1476,7 @@ static void gen6_ggtt_insert_entries(struct i915_address_space *vm,
 	 */
 	if (i != 0)
 		WARN_ON(readl(&gtt_entries[i-1]) !=
-			vm->pte_encode(addr, level, true));
+			vm->pte_encode(addr, level, true, flags));
 
 	/* This next bit makes the above posting read even more important. We
 	 * want to flush the TLBs only after we're certain all the PTE updates
@@ -1518,7 +1530,7 @@ static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 		 first_entry, num_entries, max_entries))
 		num_entries = max_entries;
 
-	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch);
+	scratch_pte = vm->pte_encode(vm->scratch.addr, I915_CACHE_LLC, use_scratch, 0);
 
 	for (i = 0; i < num_entries; i++)
 		iowrite32(scratch_pte, &gtt_base[i]);
@@ -1567,6 +1579,10 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj = vma->obj;
 
+	/* Currently applicable only to VLV */
+	if (obj->gt_ro)
+		flags |= PTE_READ_ONLY;
+
 	/* If there is no aliasing PPGTT, or the caller needs a global mapping,
 	 * or we have a global mapping already but the cacheability flags have
 	 * changed, set the global PTEs.
@@ -1583,7 +1599,7 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 		    (cache_level != obj->cache_level)) {
 			vma->vm->insert_entries(vma->vm, obj->pages,
 						vma->node.start,
-						cache_level);
+						cache_level, flags);
 			obj->has_global_gtt_mapping = 1;
 		}
 	}
@@ -1595,7 +1611,7 @@ static void ggtt_bind_vma(struct i915_vma *vma,
 		appgtt->base.insert_entries(&appgtt->base,
 					    vma->obj->pages,
 					    vma->node.start,
-					    cache_level);
+					    cache_level, flags);
 		vma->obj->has_aliasing_ppgtt_mapping = 1;
 	}
 }

drivers/gpu/drm/i915/i915_gem_gtt.h

@@ -154,6 +154,7 @@ struct i915_vma {
 	void (*unbind_vma)(struct i915_vma *vma);
 	/* Map an object into an address space with the given cache flags. */
 #define GLOBAL_BIND (1<<0)
+#define PTE_READ_ONLY (1<<1)
 	void (*bind_vma)(struct i915_vma *vma,
 			 enum i915_cache_level cache_level,
 			 u32 flags);
@@ -197,7 +198,7 @@ struct i915_address_space {
 	/* FIXME: Need a more generic return type */
 	gen6_gtt_pte_t (*pte_encode)(dma_addr_t addr,
 				     enum i915_cache_level level,
-				     bool valid); /* Create a valid PTE */
+				     bool valid, u32 flags); /* Create a valid PTE */
 	void (*clear_range)(struct i915_address_space *vm,
 			    uint64_t start,
 			    uint64_t length,
@@ -205,7 +206,7 @@ struct i915_address_space {
 	void (*insert_entries)(struct i915_address_space *vm,
 			       struct sg_table *st,
 			       uint64_t start,
-			       enum i915_cache_level cache_level);
+			       enum i915_cache_level cache_level, u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
 };
 

drivers/gpu/drm/i915/i915_gem_render_state.c

@@ -28,64 +28,13 @@
 #include "i915_drv.h"
 #include "intel_renderstate.h"
 
-struct i915_render_state {
+struct render_state {
+	const struct intel_renderstate_rodata *rodata;
 	struct drm_i915_gem_object *obj;
-	unsigned long ggtt_offset;
-	void *batch;
-	u32 size;
-	u32 len;
+	u64 ggtt_offset;
+	int gen;
 };
 
-static struct i915_render_state *render_state_alloc(struct drm_device *dev)
-{
-	struct i915_render_state *so;
-	struct page *page;
-	int ret;
-
-	so = kzalloc(sizeof(*so), GFP_KERNEL);
-	if (!so)
-		return ERR_PTR(-ENOMEM);
-
-	so->obj = i915_gem_alloc_object(dev, 4096);
-	if (so->obj == NULL) {
-		ret = -ENOMEM;
-		goto free;
-	}
-	so->size = 4096;
-
-	ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0);
-	if (ret)
-		goto free_gem;
-
-	BUG_ON(so->obj->pages->nents != 1);
-	page = sg_page(so->obj->pages->sgl);
-
-	so->batch = kmap(page);
-	if (!so->batch) {
-		ret = -ENOMEM;
-		goto unpin;
-	}
-
-	so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj);
-
-	return so;
-unpin:
-	i915_gem_object_ggtt_unpin(so->obj);
-free_gem:
-	drm_gem_object_unreference(&so->obj->base);
-free:
-	kfree(so);
-	return ERR_PTR(ret);
-}
-
-static void render_state_free(struct i915_render_state *so)
-{
-	kunmap(so->batch);
-	i915_gem_object_ggtt_unpin(so->obj);
-	drm_gem_object_unreference(&so->obj->base);
-	kfree(so);
-}
-
 static const struct intel_renderstate_rodata *
 render_state_get_rodata(struct drm_device *dev, const int gen)
 {
@@ -101,98 +50,120 @@ render_state_get_rodata(struct drm_device *dev, const int gen)
 	return NULL;
 }
 
-static int render_state_setup(const int gen,
-			      const struct intel_renderstate_rodata *rodata,
-			      struct i915_render_state *so)
+static int render_state_init(struct render_state *so, struct drm_device *dev)
 {
-	const u64 goffset = i915_gem_obj_ggtt_offset(so->obj);
-	u32 reloc_index = 0;
-	u32 * const d = so->batch;
-	unsigned int i = 0;
 	int ret;
 
-	if (!rodata || rodata->batch_items * 4 > so->size)
+	so->gen = INTEL_INFO(dev)->gen;
+	so->rodata = render_state_get_rodata(dev, so->gen);
+	if (so->rodata == NULL)
+		return 0;
+
+	if (so->rodata->batch_items * 4 > 4096)
 		return -EINVAL;
 
+	so->obj = i915_gem_alloc_object(dev, 4096);
+	if (so->obj == NULL)
+		return -ENOMEM;
+
+	ret = i915_gem_obj_ggtt_pin(so->obj, 4096, 0);
+	if (ret)
+		goto free_gem;
+
+	so->ggtt_offset = i915_gem_obj_ggtt_offset(so->obj);
+	return 0;
+
+free_gem:
+	drm_gem_object_unreference(&so->obj->base);
+	return ret;
+}
+
+static int render_state_setup(struct render_state *so)
+{
+	const struct intel_renderstate_rodata *rodata = so->rodata;
+	unsigned int i = 0, reloc_index = 0;
+	struct page *page;
+	u32 *d;
+	int ret;
+
 	ret = i915_gem_object_set_to_cpu_domain(so->obj, true);
 	if (ret)
 		return ret;
 
+	page = sg_page(so->obj->pages->sgl);
+	d = kmap(page);
+
 	while (i < rodata->batch_items) {
 		u32 s = rodata->batch[i];
 
-		if (reloc_index < rodata->reloc_items &&
-		    i * 4  == rodata->reloc[reloc_index]) {
-
-			s += goffset & 0xffffffff;
-
-			/* We keep batch offsets max 32bit */
-			if (gen >= 8) {
+		if (i * 4  == rodata->reloc[reloc_index]) {
+			u64 r = s + so->ggtt_offset;
+			s = lower_32_bits(r);
+			if (so->gen >= 8) {
 				if (i + 1 >= rodata->batch_items ||
 				    rodata->batch[i + 1] != 0)
 					return -EINVAL;
 
-				d[i] = s;
-				i++;
-				s = (goffset & 0xffffffff00000000ull) >> 32;
+				d[i++] = s;
+				s = upper_32_bits(r);
 			}
 
 			reloc_index++;
 		}
 
-		d[i] = s;
-		i++;
+		d[i++] = s;
 	}
+	kunmap(page);
 
 	ret = i915_gem_object_set_to_gtt_domain(so->obj, false);
 	if (ret)
 		return ret;
 
-	if (rodata->reloc_items != reloc_index) {
-		DRM_ERROR("not all relocs resolved, %d out of %d\n",
-			  reloc_index, rodata->reloc_items);
+	if (rodata->reloc[reloc_index] != -1) {
+		DRM_ERROR("only %d relocs resolved\n", reloc_index);
 		return -EINVAL;
 	}
 
-	so->len = rodata->batch_items * 4;
-
 	return 0;
 }
 
+static void render_state_fini(struct render_state *so)
+{
+	i915_gem_object_ggtt_unpin(so->obj);
+	drm_gem_object_unreference(&so->obj->base);
+}
+
 int i915_gem_render_state_init(struct intel_engine_cs *ring)
 {
-	const int gen = INTEL_INFO(ring->dev)->gen;
-	struct i915_render_state *so;
-	const struct intel_renderstate_rodata *rodata;
+	struct render_state so;
 	int ret;
 
 	if (WARN_ON(ring->id != RCS))
 		return -ENOENT;
 
-	rodata = render_state_get_rodata(ring->dev, gen);
-	if (rodata == NULL)
-		return 0;
+	ret = render_state_init(&so, ring->dev);
+	if (ret)
+		return ret;
 
-	so = render_state_alloc(ring->dev);
-	if (IS_ERR(so))
-		return PTR_ERR(so);
+	if (so.rodata == NULL)
+		return 0;
 
-	ret = render_state_setup(gen, rodata, so);
+	ret = render_state_setup(&so);
 	if (ret)
 		goto out;
 
 	ret = ring->dispatch_execbuffer(ring,
-					i915_gem_obj_ggtt_offset(so->obj),
-					so->len,
+					so.ggtt_offset,
+					so.rodata->batch_items * 4,
 					I915_DISPATCH_SECURE);
 	if (ret)
 		goto out;
 
-	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so->obj), ring);
+	i915_vma_move_to_active(i915_gem_obj_to_ggtt(so.obj), ring);
 
-	ret = __i915_add_request(ring, NULL, so->obj, NULL);
+	ret = __i915_add_request(ring, NULL, so.obj, NULL);
 	/* __i915_add_request moves object to inactive if it fails */
 out:
-	render_state_free(so);
+	render_state_fini(&so);
 	return ret;
 }

drivers/gpu/drm/i915/i915_gem_stolen.c

@@ -292,9 +292,20 @@ static void i915_gem_object_put_pages_stolen(struct drm_i915_gem_object *obj)
 	kfree(obj->pages);
 }
 
+
+static void
+i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
+{
+	if (obj->stolen) {
+		drm_mm_remove_node(obj->stolen);
+		kfree(obj->stolen);
+		obj->stolen = NULL;
+	}
+}
 static const struct drm_i915_gem_object_ops i915_gem_object_stolen_ops = {
 	.get_pages = i915_gem_object_get_pages_stolen,
 	.put_pages = i915_gem_object_put_pages_stolen,
+	.release = i915_gem_object_release_stolen,
 };
 
 static struct drm_i915_gem_object *
@@ -452,13 +463,3 @@ err_out:
 	drm_gem_object_unreference(&obj->base);
 	return NULL;
 }
-
-void
-i915_gem_object_release_stolen(struct drm_i915_gem_object *obj)
-{
-	if (obj->stolen) {
-		drm_mm_remove_node(obj->stolen);
-		kfree(obj->stolen);
-		obj->stolen = NULL;
-	}
-}

drivers/gpu/drm/i915/i915_irq.c

@@ -1214,6 +1214,9 @@ 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);
 }
@@ -1248,8 +1251,10 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
 		if (adj > 0)
 			adj *= 2;
-		else
-			adj = 1;
+		else {
+			/* CHV needs even encode values */
+			adj = IS_CHERRYVIEW(dev_priv->dev) ? 2 : 1;
+		}
 		new_delay = dev_priv->rps.cur_freq + adj;
 
 		/*
@@ -1267,8 +1272,10 @@ static void gen6_pm_rps_work(struct work_struct *work)
 	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
 		if (adj < 0)
 			adj *= 2;
-		else
-			adj = -1;
+		else {
+			/* CHV needs even encode values */
+			adj = IS_CHERRYVIEW(dev_priv->dev) ? -2 : -1;
+		}
 		new_delay = dev_priv->rps.cur_freq + adj;
 	} else { /* unknown event */
 		new_delay = dev_priv->rps.cur_freq;
@@ -1454,6 +1461,7 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 	if (master_ctl & (GEN8_GT_RCS_IRQ | GEN8_GT_BCS_IRQ)) {
 		tmp = I915_READ(GEN8_GT_IIR(0));
 		if (tmp) {
+			I915_WRITE(GEN8_GT_IIR(0), tmp);
 			ret = IRQ_HANDLED;
 			rcs = tmp >> GEN8_RCS_IRQ_SHIFT;
 			bcs = tmp >> GEN8_BCS_IRQ_SHIFT;
@@ -1461,7 +1469,6 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 				notify_ring(dev, &dev_priv->ring[RCS]);
 			if (bcs & GT_RENDER_USER_INTERRUPT)
 				notify_ring(dev, &dev_priv->ring[BCS]);
-			I915_WRITE(GEN8_GT_IIR(0), tmp);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT0)!\n");
 	}
@@ -1469,6 +1476,7 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 	if (master_ctl & (GEN8_GT_VCS1_IRQ | GEN8_GT_VCS2_IRQ)) {
 		tmp = I915_READ(GEN8_GT_IIR(1));
 		if (tmp) {
+			I915_WRITE(GEN8_GT_IIR(1), tmp);
 			ret = IRQ_HANDLED;
 			vcs = tmp >> GEN8_VCS1_IRQ_SHIFT;
 			if (vcs & GT_RENDER_USER_INTERRUPT)
@@ -1476,7 +1484,6 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 			vcs = tmp >> GEN8_VCS2_IRQ_SHIFT;
 			if (vcs & GT_RENDER_USER_INTERRUPT)
 				notify_ring(dev, &dev_priv->ring[VCS2]);
-			I915_WRITE(GEN8_GT_IIR(1), tmp);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT1)!\n");
 	}
@@ -1484,10 +1491,10 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 	if (master_ctl & GEN8_GT_PM_IRQ) {
 		tmp = I915_READ(GEN8_GT_IIR(2));
 		if (tmp & dev_priv->pm_rps_events) {
-			ret = IRQ_HANDLED;
-			gen8_rps_irq_handler(dev_priv, tmp);
 			I915_WRITE(GEN8_GT_IIR(2),
 				   tmp & dev_priv->pm_rps_events);
+			ret = IRQ_HANDLED;
+			gen8_rps_irq_handler(dev_priv, tmp);
 		} else
 			DRM_ERROR("The master control interrupt lied (PM)!\n");
 	}
@@ -1495,11 +1502,11 @@ static irqreturn_t gen8_gt_irq_handler(struct drm_device *dev,
 	if (master_ctl & GEN8_GT_VECS_IRQ) {
 		tmp = I915_READ(GEN8_GT_IIR(3));
 		if (tmp) {
+			I915_WRITE(GEN8_GT_IIR(3), tmp);
 			ret = IRQ_HANDLED;
 			vcs = tmp >> GEN8_VECS_IRQ_SHIFT;
 			if (vcs & GT_RENDER_USER_INTERRUPT)
 				notify_ring(dev, &dev_priv->ring[VECS]);
-			I915_WRITE(GEN8_GT_IIR(3), tmp);
 		} else
 			DRM_ERROR("The master control interrupt lied (GT3)!\n");
 	}
@@ -1805,26 +1812,28 @@ static void i9xx_hpd_irq_handler(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
 
-	if (IS_G4X(dev)) {
-		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
+	if (hotplug_status) {
+		I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+		/*
+		 * Make sure hotplug status is cleared before we clear IIR, or else we
+		 * may miss hotplug events.
+		 */
+		POSTING_READ(PORT_HOTPLUG_STAT);
 
-		intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_g4x);
-	} else {
-		u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
+		if (IS_G4X(dev)) {
+			u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_G4X;
 
-		intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915);
-	}
+			intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_g4x);
+		} else {
+			u32 hotplug_trigger = hotplug_status & HOTPLUG_INT_STATUS_I915;
 
-	if ((IS_G4X(dev) || IS_VALLEYVIEW(dev)) &&
-	    hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
-		dp_aux_irq_handler(dev);
+			intel_hpd_irq_handler(dev, hotplug_trigger, hpd_status_i915);
+		}
 
-	I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
-	/*
-	 * Make sure hotplug status is cleared before we clear IIR, or else we
-	 * may miss hotplug events.
-	 */
-	POSTING_READ(PORT_HOTPLUG_STAT);
+		if ((IS_G4X(dev) || IS_VALLEYVIEW(dev)) &&
+		    hotplug_status & DP_AUX_CHANNEL_MASK_INT_STATUS_G4X)
+			dp_aux_irq_handler(dev);
+	}
 }
 
 static irqreturn_t valleyview_irq_handler(int irq, void *arg)
@@ -1835,29 +1844,36 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 	irqreturn_t ret = IRQ_NONE;
 
 	while (true) {
-		iir = I915_READ(VLV_IIR);
+		/* Find, clear, then process each source of interrupt */
+
 		gt_iir = I915_READ(GTIIR);
+		if (gt_iir)
+			I915_WRITE(GTIIR, gt_iir);
+
 		pm_iir = I915_READ(GEN6_PMIIR);
+		if (pm_iir)
+			I915_WRITE(GEN6_PMIIR, pm_iir);
+
+		iir = I915_READ(VLV_IIR);
+		if (iir) {
+			/* Consume port before clearing IIR or we'll miss events */
+			if (iir & I915_DISPLAY_PORT_INTERRUPT)
+				i9xx_hpd_irq_handler(dev);
+			I915_WRITE(VLV_IIR, iir);
+		}
 
 		if (gt_iir == 0 && pm_iir == 0 && iir == 0)
 			goto out;
 
 		ret = IRQ_HANDLED;
 
-		snb_gt_irq_handler(dev, dev_priv, gt_iir);
-
-		valleyview_pipestat_irq_handler(dev, iir);
-
-		/* Consume port.  Then clear IIR or we'll miss events */
-		if (iir & I915_DISPLAY_PORT_INTERRUPT)
-			i9xx_hpd_irq_handler(dev);
-
+		if (gt_iir)
+			snb_gt_irq_handler(dev, dev_priv, gt_iir);
 		if (pm_iir)
 			gen6_rps_irq_handler(dev_priv, pm_iir);
-
-		I915_WRITE(GTIIR, gt_iir);
-		I915_WRITE(GEN6_PMIIR, pm_iir);
-		I915_WRITE(VLV_IIR, iir);
+		/* Call regardless, as some status bits might not be
+		 * signalled in iir */
+		valleyview_pipestat_irq_handler(dev, iir);
 	}
 
 out:
@@ -1878,21 +1894,27 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 		if (master_ctl == 0 && iir == 0)
 			break;
 
+		ret = IRQ_HANDLED;
+
 		I915_WRITE(GEN8_MASTER_IRQ, 0);
 
-		gen8_gt_irq_handler(dev, dev_priv, master_ctl);
+		/* Find, clear, then process each source of interrupt */
 
-		valleyview_pipestat_irq_handler(dev, iir);
+		if (iir) {
+			/* Consume port before clearing IIR or we'll miss events */
+			if (iir & I915_DISPLAY_PORT_INTERRUPT)
+				i9xx_hpd_irq_handler(dev);
+			I915_WRITE(VLV_IIR, iir);
+		}
 
-		/* Consume port.  Then clear IIR or we'll miss events */
-		i9xx_hpd_irq_handler(dev);
+		gen8_gt_irq_handler(dev, dev_priv, master_ctl);
 
-		I915_WRITE(VLV_IIR, iir);
+		/* Call regardless, as some status bits might not be
+		 * signalled in iir */
+		valleyview_pipestat_irq_handler(dev, iir);
 
 		I915_WRITE(GEN8_MASTER_IRQ, DE_MASTER_IRQ_CONTROL);
 		POSTING_READ(GEN8_MASTER_IRQ);
-
-		ret = IRQ_HANDLED;
 	}
 
 	return ret;
@@ -2128,6 +2150,14 @@ static void ivb_display_irq_handler(struct drm_device *dev, u32 de_iir)
 	}
 }
 
+/*
+ * To handle irqs with the minimum potential races with fresh interrupts, we:
+ * 1 - Disable Master Interrupt Control.
+ * 2 - Find the source(s) of the interrupt.
+ * 3 - Clear the Interrupt Identity bits (IIR).
+ * 4 - Process the interrupt(s) that had bits set in the IIRs.
+ * 5 - Re-enable Master Interrupt Control.
+ */
 static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
@@ -2155,32 +2185,34 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 		POSTING_READ(SDEIER);
 	}
 
+	/* Find, clear, then process each source of interrupt */
+
 	gt_iir = I915_READ(GTIIR);
 	if (gt_iir) {
+		I915_WRITE(GTIIR, gt_iir);
+		ret = IRQ_HANDLED;
 		if (INTEL_INFO(dev)->gen >= 6)
 			snb_gt_irq_handler(dev, dev_priv, gt_iir);
 		else
 			ilk_gt_irq_handler(dev, dev_priv, gt_iir);
-		I915_WRITE(GTIIR, gt_iir);
-		ret = IRQ_HANDLED;
 	}
 
 	de_iir = I915_READ(DEIIR);
 	if (de_iir) {
+		I915_WRITE(DEIIR, de_iir);
+		ret = IRQ_HANDLED;
 		if (INTEL_INFO(dev)->gen >= 7)
 			ivb_display_irq_handler(dev, de_iir);
 		else
 			ilk_display_irq_handler(dev, de_iir);
-		I915_WRITE(DEIIR, de_iir);
-		ret = IRQ_HANDLED;
 	}
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		u32 pm_iir = I915_READ(GEN6_PMIIR);
 		if (pm_iir) {
-			gen6_rps_irq_handler(dev_priv, pm_iir);
 			I915_WRITE(GEN6_PMIIR, pm_iir);
 			ret = IRQ_HANDLED;
+			gen6_rps_irq_handler(dev_priv, pm_iir);
 		}
 	}
 
@@ -2211,36 +2243,36 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 	I915_WRITE(GEN8_MASTER_IRQ, 0);
 	POSTING_READ(GEN8_MASTER_IRQ);
 
+	/* Find, clear, then process each source of interrupt */
+
 	ret = gen8_gt_irq_handler(dev, dev_priv, master_ctl);
 
 	if (master_ctl & GEN8_DE_MISC_IRQ) {
 		tmp = I915_READ(GEN8_DE_MISC_IIR);
-		if (tmp & GEN8_DE_MISC_GSE)
-			intel_opregion_asle_intr(dev);
-		else if (tmp)
-			DRM_ERROR("Unexpected DE Misc interrupt\n");
-		else
-			DRM_ERROR("The master control interrupt lied (DE MISC)!\n");
-
 		if (tmp) {
 			I915_WRITE(GEN8_DE_MISC_IIR, tmp);
 			ret = IRQ_HANDLED;
+			if (tmp & GEN8_DE_MISC_GSE)
+				intel_opregion_asle_intr(dev);
+			else
+				DRM_ERROR("Unexpected DE Misc interrupt\n");
 		}
+		else
+			DRM_ERROR("The master control interrupt lied (DE MISC)!\n");
 	}
 
 	if (master_ctl & GEN8_DE_PORT_IRQ) {
 		tmp = I915_READ(GEN8_DE_PORT_IIR);
-		if (tmp & GEN8_AUX_CHANNEL_A)
-			dp_aux_irq_handler(dev);
-		else if (tmp)
-			DRM_ERROR("Unexpected DE Port interrupt\n");
-		else
-			DRM_ERROR("The master control interrupt lied (DE PORT)!\n");
-
 		if (tmp) {
 			I915_WRITE(GEN8_DE_PORT_IIR, tmp);
 			ret = IRQ_HANDLED;
+			if (tmp & GEN8_AUX_CHANNEL_A)
+				dp_aux_irq_handler(dev);
+			else
+				DRM_ERROR("Unexpected DE Port interrupt\n");
 		}
+		else
+			DRM_ERROR("The master control interrupt lied (DE PORT)!\n");
 	}
 
 	for_each_pipe(pipe) {
@@ -2250,33 +2282,32 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 			continue;
 
 		pipe_iir = I915_READ(GEN8_DE_PIPE_IIR(pipe));
-		if (pipe_iir & GEN8_PIPE_VBLANK)
-			intel_pipe_handle_vblank(dev, pipe);
-
-		if (pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE) {
-			intel_prepare_page_flip(dev, pipe);
-			intel_finish_page_flip_plane(dev, pipe);
-		}
+		if (pipe_iir) {
+			ret = IRQ_HANDLED;
+			I915_WRITE(GEN8_DE_PIPE_IIR(pipe), pipe_iir);
+			if (pipe_iir & GEN8_PIPE_VBLANK)
+				intel_pipe_handle_vblank(dev, pipe);
 
-		if (pipe_iir & GEN8_PIPE_CDCLK_CRC_DONE)
-			hsw_pipe_crc_irq_handler(dev, pipe);
+			if (pipe_iir & GEN8_PIPE_PRIMARY_FLIP_DONE) {
+				intel_prepare_page_flip(dev, pipe);
+				intel_finish_page_flip_plane(dev, pipe);
+			}
 
-		if (pipe_iir & GEN8_PIPE_FIFO_UNDERRUN) {
-			if (intel_set_cpu_fifo_underrun_reporting(dev, pipe,
-								  false))
-				DRM_ERROR("Pipe %c FIFO underrun\n",
-					  pipe_name(pipe));
-		}
+			if (pipe_iir & GEN8_PIPE_CDCLK_CRC_DONE)
+				hsw_pipe_crc_irq_handler(dev, pipe);
 
-		if (pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS) {
-			DRM_ERROR("Fault errors on pipe %c\n: 0x%08x",
-				  pipe_name(pipe),
-				  pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS);
-		}
+			if (pipe_iir & GEN8_PIPE_FIFO_UNDERRUN) {
+				if (intel_set_cpu_fifo_underrun_reporting(dev, pipe,
+									  false))
+					DRM_ERROR("Pipe %c FIFO underrun\n",
+						  pipe_name(pipe));
+			}
 
-		if (pipe_iir) {
-			ret = IRQ_HANDLED;
-			I915_WRITE(GEN8_DE_PIPE_IIR(pipe), pipe_iir);
+			if (pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS) {
+				DRM_ERROR("Fault errors on pipe %c\n: 0x%08x",
+					  pipe_name(pipe),
+					  pipe_iir & GEN8_DE_PIPE_IRQ_FAULT_ERRORS);
+			}
 		} else
 			DRM_ERROR("The master control interrupt lied (DE PIPE)!\n");
 	}
@@ -2288,13 +2319,13 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 		 * on older pch-split platforms. But this needs testing.
 		 */
 		u32 pch_iir = I915_READ(SDEIIR);
-
-		cpt_irq_handler(dev, pch_iir);
-
 		if (pch_iir) {
 			I915_WRITE(SDEIIR, pch_iir);
 			ret = IRQ_HANDLED;
-		}
+			cpt_irq_handler(dev, pch_iir);
+		} else
+			DRM_ERROR("The master control interrupt lied (SDE)!\n");
+
 	}
 
 	I915_WRITE(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);

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)");

drivers/gpu/drm/i915/i915_reg.h

@@ -29,8 +29,8 @@
 #define _TRANSCODER(tran, a, b) ((a) + (tran)*((b)-(a)))
 
 #define _PORT(port, a, b) ((a) + (port)*((b)-(a)))
-#define _PIPE3(pipe, a, b, c) (pipe < 2 ? _PIPE(pipe, a, b) : c)
-#define _PORT3(port, a, b, c) (port < 2 ? _PORT(port, a, b) : c)
+#define _PIPE3(pipe, a, b, c) ((pipe) == PIPE_A ? (a) : \
+			       (pipe) == PIPE_B ? (b) : (c))
 
 #define _MASKED_BIT_ENABLE(a) (((a) << 16) | (a))
 #define _MASKED_BIT_DISABLE(a) ((a) << 16)
@@ -529,6 +529,16 @@ enum punit_power_well {
 #define PUNIT_FUSE_BUS2				0xf6 /* bits 47:40 */
 #define PUNIT_FUSE_BUS1				0xf5 /* bits 55:48 */
 
+#define PUNIT_GPU_STATUS_REG			0xdb
+#define PUNIT_GPU_STATUS_MAX_FREQ_SHIFT	16
+#define PUNIT_GPU_STATUS_MAX_FREQ_MASK		0xff
+#define PUNIT_GPU_STATIS_GFX_MIN_FREQ_SHIFT	8
+#define PUNIT_GPU_STATUS_GFX_MIN_FREQ_MASK	0xff
+
+#define PUNIT_GPU_DUTYCYCLE_REG		0xdf
+#define PUNIT_GPU_DUTYCYCLE_RPE_FREQ_SHIFT	8
+#define PUNIT_GPU_DUTYCYCLE_RPE_FREQ_MASK	0xff
+
 #define IOSF_NC_FB_GFX_FREQ_FUSE		0x1c
 #define   FB_GFX_MAX_FREQ_FUSE_SHIFT		3
 #define   FB_GFX_MAX_FREQ_FUSE_MASK		0x000007f8
@@ -761,6 +771,8 @@ enum punit_power_well {
 
 #define _VLV_PCS_DW8_CH0		0x8220
 #define _VLV_PCS_DW8_CH1		0x8420
+#define   CHV_PCS_USEDCLKCHANNEL_OVRRIDE	(1 << 20)
+#define   CHV_PCS_USEDCLKCHANNEL		(1 << 21)
 #define VLV_PCS_DW8(ch) _PORT(ch, _VLV_PCS_DW8_CH0, _VLV_PCS_DW8_CH1)
 
 #define _VLV_PCS01_DW8_CH0		0x0220
@@ -869,6 +881,16 @@ enum punit_power_well {
 #define   DPIO_CHV_PROP_COEFF_SHIFT	0
 #define CHV_PLL_DW6(ch) _PIPE(ch, _CHV_PLL_DW6_CH0, _CHV_PLL_DW6_CH1)
 
+#define _CHV_CMN_DW5_CH0               0x8114
+#define   CHV_BUFRIGHTENA1_DISABLE	(0 << 20)
+#define   CHV_BUFRIGHTENA1_NORMAL	(1 << 20)
+#define   CHV_BUFRIGHTENA1_FORCE	(3 << 20)
+#define   CHV_BUFRIGHTENA1_MASK		(3 << 20)
+#define   CHV_BUFLEFTENA1_DISABLE	(0 << 22)
+#define   CHV_BUFLEFTENA1_NORMAL	(1 << 22)
+#define   CHV_BUFLEFTENA1_FORCE		(3 << 22)
+#define   CHV_BUFLEFTENA1_MASK		(3 << 22)
+
 #define _CHV_CMN_DW13_CH0		0x8134
 #define _CHV_CMN_DW0_CH1		0x8080
 #define   DPIO_CHV_S1_DIV_SHIFT		21
@@ -883,8 +905,21 @@ enum punit_power_well {
 #define _CHV_CMN_DW1_CH1		0x8084
 #define   DPIO_AFC_RECAL		(1 << 14)
 #define   DPIO_DCLKP_EN			(1 << 13)
+#define   CHV_BUFLEFTENA2_DISABLE	(0 << 17) /* CL2 DW1 only */
+#define   CHV_BUFLEFTENA2_NORMAL	(1 << 17) /* CL2 DW1 only */
+#define   CHV_BUFLEFTENA2_FORCE		(3 << 17) /* CL2 DW1 only */
+#define   CHV_BUFLEFTENA2_MASK		(3 << 17) /* CL2 DW1 only */
+#define   CHV_BUFRIGHTENA2_DISABLE	(0 << 19) /* CL2 DW1 only */
+#define   CHV_BUFRIGHTENA2_NORMAL	(1 << 19) /* CL2 DW1 only */
+#define   CHV_BUFRIGHTENA2_FORCE	(3 << 19) /* CL2 DW1 only */
+#define   CHV_BUFRIGHTENA2_MASK		(3 << 19) /* CL2 DW1 only */
 #define CHV_CMN_DW14(ch) _PIPE(ch, _CHV_CMN_DW14_CH0, _CHV_CMN_DW1_CH1)
 
+#define _CHV_CMN_DW19_CH0		0x814c
+#define _CHV_CMN_DW6_CH1		0x8098
+#define   CHV_CMN_USEDCLKCHANNEL	(1 << 13)
+#define CHV_CMN_DW19(ch) _PIPE(ch, _CHV_CMN_DW19_CH0, _CHV_CMN_DW6_CH1)
+
 #define CHV_CMN_DW30			0x8178
 #define   DPIO_LRC_BYPASS		(1 << 3)
 
@@ -933,6 +968,7 @@ enum punit_power_well {
 #define   SANDYBRIDGE_FENCE_PITCH_SHIFT	32
 #define   GEN7_FENCE_MAX_PITCH_VAL	0x0800
 
+
 /* control register for cpu gtt access */
 #define TILECTL				0x101000
 #define   TILECTL_SWZCTL			(1 << 0)
@@ -1167,6 +1203,8 @@ enum punit_power_well {
 #define VLV_IMR		(VLV_DISPLAY_BASE + 0x20a8)
 #define VLV_ISR		(VLV_DISPLAY_BASE + 0x20ac)
 #define VLV_PCBR	(VLV_DISPLAY_BASE + 0x2120)
+#define VLV_PCBR_ADDR_SHIFT	12
+
 #define   DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
 #define EIR		0x020b0
 #define EMR		0x020b4
@@ -1567,11 +1605,10 @@ enum punit_power_well {
 /*
  * Clock control & power management
  */
-#define DPLL_A_OFFSET 0x6014
-#define DPLL_B_OFFSET 0x6018
-#define CHV_DPLL_C_OFFSET 0x6030
-#define DPLL(pipe) (dev_priv->info.dpll_offsets[pipe] + \
-		    dev_priv->info.display_mmio_offset)
+#define _DPLL_A (dev_priv->info.display_mmio_offset + 0x6014)
+#define _DPLL_B (dev_priv->info.display_mmio_offset + 0x6018)
+#define _CHV_DPLL_C (dev_priv->info.display_mmio_offset + 0x6030)
+#define DPLL(pipe) _PIPE3((pipe), _DPLL_A, _DPLL_B, _CHV_DPLL_C)
 
 #define VGA0	0x6000
 #define VGA1	0x6004
@@ -1659,11 +1696,10 @@ enum punit_power_well {
 #define   SDVO_MULTIPLIER_SHIFT_HIRES		4
 #define   SDVO_MULTIPLIER_SHIFT_VGA		0
 
-#define DPLL_A_MD_OFFSET 0x601c /* 965+ only */
-#define DPLL_B_MD_OFFSET 0x6020 /* 965+ only */
-#define CHV_DPLL_C_MD_OFFSET 0x603c
-#define DPLL_MD(pipe) (dev_priv->info.dpll_md_offsets[pipe] + \
-		       dev_priv->info.display_mmio_offset)
+#define _DPLL_A_MD (dev_priv->info.display_mmio_offset + 0x601c)
+#define _DPLL_B_MD (dev_priv->info.display_mmio_offset + 0x6020)
+#define _CHV_DPLL_C_MD (dev_priv->info.display_mmio_offset + 0x603c)
+#define DPLL_MD(pipe) _PIPE3((pipe), _DPLL_A_MD, _DPLL_B_MD, _CHV_DPLL_C_MD)
 
 /*
  * UDI pixel divider, controlling how many pixels are stuffed into a packet.
@@ -2373,6 +2409,7 @@ enum punit_power_well {
 #define EDP_PSR_BASE(dev)                       (IS_HASWELL(dev) ? 0x64800 : 0x6f800)
 #define EDP_PSR_CTL(dev)			(EDP_PSR_BASE(dev) + 0)
 #define   EDP_PSR_ENABLE			(1<<31)
+#define   BDW_PSR_SINGLE_FRAME			(1<<30)
 #define   EDP_PSR_LINK_DISABLE			(0<<27)
 #define   EDP_PSR_LINK_STANDBY			(1<<27)
 #define   EDP_PSR_MIN_LINK_ENTRY_TIME_MASK	(3<<25)
@@ -2530,8 +2567,14 @@ enum punit_power_well {
 #define   PORTC_HOTPLUG_LIVE_STATUS_VLV		(1 << 28)
 #define   PORTB_HOTPLUG_LIVE_STATUS_VLV		(1 << 29)
 #define   PORTD_HOTPLUG_INT_STATUS		(3 << 21)
+#define   PORTD_HOTPLUG_INT_LONG_PULSE		(2 << 21)
+#define   PORTD_HOTPLUG_INT_SHORT_PULSE		(1 << 21)
 #define   PORTC_HOTPLUG_INT_STATUS		(3 << 19)
+#define   PORTC_HOTPLUG_INT_LONG_PULSE		(2 << 19)
+#define   PORTC_HOTPLUG_INT_SHORT_PULSE		(1 << 19)
 #define   PORTB_HOTPLUG_INT_STATUS		(3 << 17)
+#define   PORTB_HOTPLUG_INT_LONG_PULSE		(2 << 17)
+#define   PORTB_HOTPLUG_INT_SHORT_PLUSE		(1 << 17)
 /* CRT/TV common between gen3+ */
 #define   CRT_HOTPLUG_INT_STATUS		(1 << 11)
 #define   TV_HOTPLUG_INT_STATUS			(1 << 10)
@@ -2585,7 +2628,7 @@ enum punit_power_well {
 
 #define PORT_DFT_I9XX				0x61150
 #define   DC_BALANCE_RESET			(1 << 25)
-#define PORT_DFT2_G4X				0x61154
+#define PORT_DFT2_G4X		(dev_priv->info.display_mmio_offset + 0x61154)
 #define   DC_BALANCE_RESET_VLV			(1 << 31)
 #define   PIPE_SCRAMBLE_RESET_MASK		(0x3 << 0)
 #define   PIPE_B_SCRAMBLE_RESET			(1 << 1)
@@ -4627,6 +4670,8 @@ enum punit_power_well {
 #define GEN7_L3CNTLREG1				0xB01C
 #define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
 #define  GEN7_L3AGDIS				(1<<19)
+#define GEN7_L3CNTLREG2				0xB020
+#define GEN7_L3CNTLREG3				0xB024
 
 #define GEN7_L3_CHICKEN_MODE_REGISTER		0xB030
 #define  GEN7_WA_L3_CHICKEN_MODE				0x20000000
@@ -4873,8 +4918,7 @@ enum punit_power_well {
 #define _PCH_TRANSA_LINK_M2	0xe0048
 #define _PCH_TRANSA_LINK_N2	0xe004c
 
-/* Per-transcoder DIP controls */
-
+/* Per-transcoder DIP controls (PCH) */
 #define _VIDEO_DIP_CTL_A         0xe0200
 #define _VIDEO_DIP_DATA_A        0xe0208
 #define _VIDEO_DIP_GCP_A         0xe0210
@@ -4887,6 +4931,7 @@ enum punit_power_well {
 #define TVIDEO_DIP_DATA(pipe) _PIPE(pipe, _VIDEO_DIP_DATA_A, _VIDEO_DIP_DATA_B)
 #define TVIDEO_DIP_GCP(pipe) _PIPE(pipe, _VIDEO_DIP_GCP_A, _VIDEO_DIP_GCP_B)
 
+/* Per-transcoder DIP controls (VLV) */
 #define VLV_VIDEO_DIP_CTL_A		(VLV_DISPLAY_BASE + 0x60200)
 #define VLV_VIDEO_DIP_DATA_A		(VLV_DISPLAY_BASE + 0x60208)
 #define VLV_VIDEO_DIP_GDCP_PAYLOAD_A	(VLV_DISPLAY_BASE + 0x60210)
@@ -4895,12 +4940,19 @@ enum punit_power_well {
 #define VLV_VIDEO_DIP_DATA_B		(VLV_DISPLAY_BASE + 0x61174)
 #define VLV_VIDEO_DIP_GDCP_PAYLOAD_B	(VLV_DISPLAY_BASE + 0x61178)
 
+#define CHV_VIDEO_DIP_CTL_C		(VLV_DISPLAY_BASE + 0x611f0)
+#define CHV_VIDEO_DIP_DATA_C		(VLV_DISPLAY_BASE + 0x611f4)
+#define CHV_VIDEO_DIP_GDCP_PAYLOAD_C	(VLV_DISPLAY_BASE + 0x611f8)
+
 #define VLV_TVIDEO_DIP_CTL(pipe) \
-	 _PIPE(pipe, VLV_VIDEO_DIP_CTL_A, VLV_VIDEO_DIP_CTL_B)
+	_PIPE3((pipe), VLV_VIDEO_DIP_CTL_A, \
+	       VLV_VIDEO_DIP_CTL_B, CHV_VIDEO_DIP_CTL_C)
 #define VLV_TVIDEO_DIP_DATA(pipe) \
-	 _PIPE(pipe, VLV_VIDEO_DIP_DATA_A, VLV_VIDEO_DIP_DATA_B)
+	_PIPE3((pipe), VLV_VIDEO_DIP_DATA_A, \
+	       VLV_VIDEO_DIP_DATA_B, CHV_VIDEO_DIP_DATA_C)
 #define VLV_TVIDEO_DIP_GCP(pipe) \
-	_PIPE(pipe, VLV_VIDEO_DIP_GDCP_PAYLOAD_A, VLV_VIDEO_DIP_GDCP_PAYLOAD_B)
+	_PIPE3((pipe), VLV_VIDEO_DIP_GDCP_PAYLOAD_A, \
+		VLV_VIDEO_DIP_GDCP_PAYLOAD_B, CHV_VIDEO_DIP_GDCP_PAYLOAD_C)
 
 /* Haswell DIP controls */
 #define HSW_VIDEO_DIP_CTL_A		0x60200
@@ -5771,7 +5823,6 @@ enum punit_power_well {
 #define DDI_BUF_CTL_B				0x64100
 #define DDI_BUF_CTL(port) _PORT(port, DDI_BUF_CTL_A, DDI_BUF_CTL_B)
 #define  DDI_BUF_CTL_ENABLE			(1<<31)
-/* Haswell */
 #define  DDI_BUF_EMP_400MV_0DB_HSW		(0<<24)   /* Sel0 */
 #define  DDI_BUF_EMP_400MV_3_5DB_HSW		(1<<24)   /* Sel1 */
 #define  DDI_BUF_EMP_400MV_6DB_HSW		(2<<24)   /* Sel2 */
@@ -5781,16 +5832,6 @@ enum punit_power_well {
 #define  DDI_BUF_EMP_600MV_6DB_HSW		(6<<24)   /* Sel6 */
 #define  DDI_BUF_EMP_800MV_0DB_HSW		(7<<24)   /* Sel7 */
 #define  DDI_BUF_EMP_800MV_3_5DB_HSW		(8<<24)   /* Sel8 */
-/* Broadwell */
-#define  DDI_BUF_EMP_400MV_0DB_BDW		(0<<24)   /* Sel0 */
-#define  DDI_BUF_EMP_400MV_3_5DB_BDW		(1<<24)   /* Sel1 */
-#define  DDI_BUF_EMP_400MV_6DB_BDW		(2<<24)   /* Sel2 */
-#define  DDI_BUF_EMP_600MV_0DB_BDW		(3<<24)   /* Sel3 */
-#define  DDI_BUF_EMP_600MV_3_5DB_BDW		(4<<24)   /* Sel4 */
-#define  DDI_BUF_EMP_600MV_6DB_BDW		(5<<24)   /* Sel5 */
-#define  DDI_BUF_EMP_800MV_0DB_BDW		(6<<24)   /* Sel6 */
-#define  DDI_BUF_EMP_800MV_3_5DB_BDW		(7<<24)   /* Sel7 */
-#define  DDI_BUF_EMP_1200MV_0DB_BDW		(8<<24)   /* Sel8 */
 #define  DDI_BUF_EMP_MASK			(0xf<<24)
 #define  DDI_BUF_PORT_REVERSAL			(1<<16)
 #define  DDI_BUF_IS_IDLE			(1<<7)
@@ -6002,7 +6043,8 @@ enum punit_power_well {
 
 #define _MIPIA_PORT_CTRL			(VLV_DISPLAY_BASE + 0x61190)
 #define _MIPIB_PORT_CTRL			(VLV_DISPLAY_BASE + 0x61700)
-#define MIPI_PORT_CTRL(pipe)		_PIPE(pipe, _MIPIA_PORT_CTRL, _MIPIB_PORT_CTRL)
+#define MIPI_PORT_CTRL(tc)		_TRANSCODER(tc, _MIPIA_PORT_CTRL, \
+						_MIPIB_PORT_CTRL)
 #define  DPI_ENABLE					(1 << 31) /* A + B */
 #define  MIPIA_MIPI4DPHY_DELAY_COUNT_SHIFT		27
 #define  MIPIA_MIPI4DPHY_DELAY_COUNT_MASK		(0xf << 27)
@@ -6044,18 +6086,20 @@ enum punit_power_well {
 
 #define _MIPIA_TEARING_CTRL			(VLV_DISPLAY_BASE + 0x61194)
 #define _MIPIB_TEARING_CTRL			(VLV_DISPLAY_BASE + 0x61704)
-#define MIPI_TEARING_CTRL(pipe)		_PIPE(pipe, _MIPIA_TEARING_CTRL, _MIPIB_TEARING_CTRL)
+#define MIPI_TEARING_CTRL(tc)			_TRANSCODER(tc, \
+				_MIPIA_TEARING_CTRL, _MIPIB_TEARING_CTRL)
 #define  TEARING_EFFECT_DELAY_SHIFT			0
 #define  TEARING_EFFECT_DELAY_MASK			(0xffff << 0)
 
 /* XXX: all bits reserved */
-#define _MIPIA_AUTOPWG				(VLV_DISPLAY_BASE + 0x611a0)
+#define _MIPIA_AUTOPWG			(VLV_DISPLAY_BASE + 0x611a0)
 
 /* MIPI DSI Controller and D-PHY registers */
 
-#define _MIPIA_DEVICE_READY			(VLV_DISPLAY_BASE + 0xb000)
-#define _MIPIB_DEVICE_READY			(VLV_DISPLAY_BASE + 0xb800)
-#define MIPI_DEVICE_READY(pipe)		_PIPE(pipe, _MIPIA_DEVICE_READY, _MIPIB_DEVICE_READY)
+#define _MIPIA_DEVICE_READY		(dev_priv->mipi_mmio_base + 0xb000)
+#define _MIPIB_DEVICE_READY		(dev_priv->mipi_mmio_base + 0xb800)
+#define MIPI_DEVICE_READY(tc)		_TRANSCODER(tc, _MIPIA_DEVICE_READY, \
+						_MIPIB_DEVICE_READY)
 #define  BUS_POSSESSION					(1 << 3) /* set to give bus to receiver */
 #define  ULPS_STATE_MASK				(3 << 1)
 #define  ULPS_STATE_ENTER				(2 << 1)
@@ -6063,12 +6107,14 @@ enum punit_power_well {
 #define  ULPS_STATE_NORMAL_OPERATION			(0 << 1)
 #define  DEVICE_READY					(1 << 0)
 
-#define _MIPIA_INTR_STAT			(VLV_DISPLAY_BASE + 0xb004)
-#define _MIPIB_INTR_STAT			(VLV_DISPLAY_BASE + 0xb804)
-#define MIPI_INTR_STAT(pipe)		_PIPE(pipe, _MIPIA_INTR_STAT, _MIPIB_INTR_STAT)
-#define _MIPIA_INTR_EN				(VLV_DISPLAY_BASE + 0xb008)
-#define _MIPIB_INTR_EN				(VLV_DISPLAY_BASE + 0xb808)
-#define MIPI_INTR_EN(pipe)		_PIPE(pipe, _MIPIA_INTR_EN, _MIPIB_INTR_EN)
+#define _MIPIA_INTR_STAT		(dev_priv->mipi_mmio_base + 0xb004)
+#define _MIPIB_INTR_STAT		(dev_priv->mipi_mmio_base + 0xb804)
+#define MIPI_INTR_STAT(tc)		_TRANSCODER(tc, _MIPIA_INTR_STAT, \
+					_MIPIB_INTR_STAT)
+#define _MIPIA_INTR_EN			(dev_priv->mipi_mmio_base + 0xb008)
+#define _MIPIB_INTR_EN			(dev_priv->mipi_mmio_base + 0xb808)
+#define MIPI_INTR_EN(tc)		_TRANSCODER(tc, _MIPIA_INTR_EN, \
+					_MIPIB_INTR_EN)
 #define  TEARING_EFFECT					(1 << 31)
 #define  SPL_PKT_SENT_INTERRUPT				(1 << 30)
 #define  GEN_READ_DATA_AVAIL				(1 << 29)
@@ -6102,9 +6148,10 @@ enum punit_power_well {
 #define  RXSOT_SYNC_ERROR				(1 << 1)
 #define  RXSOT_ERROR					(1 << 0)
 
-#define _MIPIA_DSI_FUNC_PRG			(VLV_DISPLAY_BASE + 0xb00c)
-#define _MIPIB_DSI_FUNC_PRG			(VLV_DISPLAY_BASE + 0xb80c)
-#define MIPI_DSI_FUNC_PRG(pipe)		_PIPE(pipe, _MIPIA_DSI_FUNC_PRG, _MIPIB_DSI_FUNC_PRG)
+#define _MIPIA_DSI_FUNC_PRG		(dev_priv->mipi_mmio_base + 0xb00c)
+#define _MIPIB_DSI_FUNC_PRG		(dev_priv->mipi_mmio_base + 0xb80c)
+#define MIPI_DSI_FUNC_PRG(tc)		_TRANSCODER(tc, _MIPIA_DSI_FUNC_PRG, \
+						_MIPIB_DSI_FUNC_PRG)
 #define  CMD_MODE_DATA_WIDTH_MASK			(7 << 13)
 #define  CMD_MODE_NOT_SUPPORTED				(0 << 13)
 #define  CMD_MODE_DATA_WIDTH_16_BIT			(1 << 13)
@@ -6125,78 +6172,94 @@ enum punit_power_well {
 #define  DATA_LANES_PRG_REG_SHIFT			0
 #define  DATA_LANES_PRG_REG_MASK			(7 << 0)
 
-#define _MIPIA_HS_TX_TIMEOUT			(VLV_DISPLAY_BASE + 0xb010)
-#define _MIPIB_HS_TX_TIMEOUT			(VLV_DISPLAY_BASE + 0xb810)
-#define MIPI_HS_TX_TIMEOUT(pipe)	_PIPE(pipe, _MIPIA_HS_TX_TIMEOUT, _MIPIB_HS_TX_TIMEOUT)
+#define _MIPIA_HS_TX_TIMEOUT		(dev_priv->mipi_mmio_base + 0xb010)
+#define _MIPIB_HS_TX_TIMEOUT		(dev_priv->mipi_mmio_base + 0xb810)
+#define MIPI_HS_TX_TIMEOUT(tc)	_TRANSCODER(tc, _MIPIA_HS_TX_TIMEOUT, \
+					_MIPIB_HS_TX_TIMEOUT)
 #define  HIGH_SPEED_TX_TIMEOUT_COUNTER_MASK		0xffffff
 
-#define _MIPIA_LP_RX_TIMEOUT			(VLV_DISPLAY_BASE + 0xb014)
-#define _MIPIB_LP_RX_TIMEOUT			(VLV_DISPLAY_BASE + 0xb814)
-#define MIPI_LP_RX_TIMEOUT(pipe)	_PIPE(pipe, _MIPIA_LP_RX_TIMEOUT, _MIPIB_LP_RX_TIMEOUT)
+#define _MIPIA_LP_RX_TIMEOUT		(dev_priv->mipi_mmio_base + 0xb014)
+#define _MIPIB_LP_RX_TIMEOUT		(dev_priv->mipi_mmio_base + 0xb814)
+#define MIPI_LP_RX_TIMEOUT(tc)	_TRANSCODER(tc, _MIPIA_LP_RX_TIMEOUT, \
+					_MIPIB_LP_RX_TIMEOUT)
 #define  LOW_POWER_RX_TIMEOUT_COUNTER_MASK		0xffffff
 
-#define _MIPIA_TURN_AROUND_TIMEOUT		(VLV_DISPLAY_BASE + 0xb018)
-#define _MIPIB_TURN_AROUND_TIMEOUT		(VLV_DISPLAY_BASE + 0xb818)
-#define MIPI_TURN_AROUND_TIMEOUT(pipe)	_PIPE(pipe, _MIPIA_TURN_AROUND_TIMEOUT, _MIPIB_TURN_AROUND_TIMEOUT)
+#define _MIPIA_TURN_AROUND_TIMEOUT	(dev_priv->mipi_mmio_base + 0xb018)
+#define _MIPIB_TURN_AROUND_TIMEOUT	(dev_priv->mipi_mmio_base + 0xb818)
+#define MIPI_TURN_AROUND_TIMEOUT(tc)	_TRANSCODER(tc, \
+			_MIPIA_TURN_AROUND_TIMEOUT, _MIPIB_TURN_AROUND_TIMEOUT)
 #define  TURN_AROUND_TIMEOUT_MASK			0x3f
 
-#define _MIPIA_DEVICE_RESET_TIMER		(VLV_DISPLAY_BASE + 0xb01c)
-#define _MIPIB_DEVICE_RESET_TIMER		(VLV_DISPLAY_BASE + 0xb81c)
-#define MIPI_DEVICE_RESET_TIMER(pipe)	_PIPE(pipe, _MIPIA_DEVICE_RESET_TIMER, _MIPIB_DEVICE_RESET_TIMER)
+#define _MIPIA_DEVICE_RESET_TIMER	(dev_priv->mipi_mmio_base + 0xb01c)
+#define _MIPIB_DEVICE_RESET_TIMER	(dev_priv->mipi_mmio_base + 0xb81c)
+#define MIPI_DEVICE_RESET_TIMER(tc)	_TRANSCODER(tc, \
+			_MIPIA_DEVICE_RESET_TIMER, _MIPIB_DEVICE_RESET_TIMER)
 #define  DEVICE_RESET_TIMER_MASK			0xffff
 
-#define _MIPIA_DPI_RESOLUTION			(VLV_DISPLAY_BASE + 0xb020)
-#define _MIPIB_DPI_RESOLUTION			(VLV_DISPLAY_BASE + 0xb820)
-#define MIPI_DPI_RESOLUTION(pipe)	_PIPE(pipe, _MIPIA_DPI_RESOLUTION, _MIPIB_DPI_RESOLUTION)
+#define _MIPIA_DPI_RESOLUTION		(dev_priv->mipi_mmio_base + 0xb020)
+#define _MIPIB_DPI_RESOLUTION		(dev_priv->mipi_mmio_base + 0xb820)
+#define MIPI_DPI_RESOLUTION(tc)	_TRANSCODER(tc, _MIPIA_DPI_RESOLUTION, \
+					_MIPIB_DPI_RESOLUTION)
 #define  VERTICAL_ADDRESS_SHIFT				16
 #define  VERTICAL_ADDRESS_MASK				(0xffff << 16)
 #define  HORIZONTAL_ADDRESS_SHIFT			0
 #define  HORIZONTAL_ADDRESS_MASK			0xffff
 
-#define _MIPIA_DBI_FIFO_THROTTLE		(VLV_DISPLAY_BASE + 0xb024)
-#define _MIPIB_DBI_FIFO_THROTTLE		(VLV_DISPLAY_BASE + 0xb824)
-#define MIPI_DBI_FIFO_THROTTLE(pipe)	_PIPE(pipe, _MIPIA_DBI_FIFO_THROTTLE, _MIPIB_DBI_FIFO_THROTTLE)
+#define _MIPIA_DBI_FIFO_THROTTLE	(dev_priv->mipi_mmio_base + 0xb024)
+#define _MIPIB_DBI_FIFO_THROTTLE	(dev_priv->mipi_mmio_base + 0xb824)
+#define MIPI_DBI_FIFO_THROTTLE(tc)	_TRANSCODER(tc, \
+			_MIPIA_DBI_FIFO_THROTTLE, _MIPIB_DBI_FIFO_THROTTLE)
 #define  DBI_FIFO_EMPTY_HALF				(0 << 0)
 #define  DBI_FIFO_EMPTY_QUARTER				(1 << 0)
 #define  DBI_FIFO_EMPTY_7_LOCATIONS			(2 << 0)
 
 /* regs below are bits 15:0 */
-#define _MIPIA_HSYNC_PADDING_COUNT		(VLV_DISPLAY_BASE + 0xb028)
-#define _MIPIB_HSYNC_PADDING_COUNT		(VLV_DISPLAY_BASE + 0xb828)
-#define MIPI_HSYNC_PADDING_COUNT(pipe)	_PIPE(pipe, _MIPIA_HSYNC_PADDING_COUNT, _MIPIB_HSYNC_PADDING_COUNT)
-
-#define _MIPIA_HBP_COUNT			(VLV_DISPLAY_BASE + 0xb02c)
-#define _MIPIB_HBP_COUNT			(VLV_DISPLAY_BASE + 0xb82c)
-#define MIPI_HBP_COUNT(pipe)		_PIPE(pipe, _MIPIA_HBP_COUNT, _MIPIB_HBP_COUNT)
-
-#define _MIPIA_HFP_COUNT			(VLV_DISPLAY_BASE + 0xb030)
-#define _MIPIB_HFP_COUNT			(VLV_DISPLAY_BASE + 0xb830)
-#define MIPI_HFP_COUNT(pipe)		_PIPE(pipe, _MIPIA_HFP_COUNT, _MIPIB_HFP_COUNT)
-
-#define _MIPIA_HACTIVE_AREA_COUNT		(VLV_DISPLAY_BASE + 0xb034)
-#define _MIPIB_HACTIVE_AREA_COUNT		(VLV_DISPLAY_BASE + 0xb834)
-#define MIPI_HACTIVE_AREA_COUNT(pipe)	_PIPE(pipe, _MIPIA_HACTIVE_AREA_COUNT, _MIPIB_HACTIVE_AREA_COUNT)
-
-#define _MIPIA_VSYNC_PADDING_COUNT		(VLV_DISPLAY_BASE + 0xb038)
-#define _MIPIB_VSYNC_PADDING_COUNT		(VLV_DISPLAY_BASE + 0xb838)
-#define MIPI_VSYNC_PADDING_COUNT(pipe)	_PIPE(pipe, _MIPIA_VSYNC_PADDING_COUNT, _MIPIB_VSYNC_PADDING_COUNT)
-
-#define _MIPIA_VBP_COUNT			(VLV_DISPLAY_BASE + 0xb03c)
-#define _MIPIB_VBP_COUNT			(VLV_DISPLAY_BASE + 0xb83c)
-#define MIPI_VBP_COUNT(pipe)		_PIPE(pipe, _MIPIA_VBP_COUNT, _MIPIB_VBP_COUNT)
+#define _MIPIA_HSYNC_PADDING_COUNT	(dev_priv->mipi_mmio_base + 0xb028)
+#define _MIPIB_HSYNC_PADDING_COUNT	(dev_priv->mipi_mmio_base + 0xb828)
+#define MIPI_HSYNC_PADDING_COUNT(tc)	_TRANSCODER(tc, \
+			_MIPIA_HSYNC_PADDING_COUNT, _MIPIB_HSYNC_PADDING_COUNT)
+
+#define _MIPIA_HBP_COUNT		(dev_priv->mipi_mmio_base + 0xb02c)
+#define _MIPIB_HBP_COUNT		(dev_priv->mipi_mmio_base + 0xb82c)
+#define MIPI_HBP_COUNT(tc)		_TRANSCODER(tc, _MIPIA_HBP_COUNT, \
+					_MIPIB_HBP_COUNT)
+
+#define _MIPIA_HFP_COUNT		(dev_priv->mipi_mmio_base + 0xb030)
+#define _MIPIB_HFP_COUNT		(dev_priv->mipi_mmio_base + 0xb830)
+#define MIPI_HFP_COUNT(tc)		_TRANSCODER(tc, _MIPIA_HFP_COUNT, \
+					_MIPIB_HFP_COUNT)
+
+#define _MIPIA_HACTIVE_AREA_COUNT	(dev_priv->mipi_mmio_base + 0xb034)
+#define _MIPIB_HACTIVE_AREA_COUNT	(dev_priv->mipi_mmio_base + 0xb834)
+#define MIPI_HACTIVE_AREA_COUNT(tc)	_TRANSCODER(tc, \
+			_MIPIA_HACTIVE_AREA_COUNT, _MIPIB_HACTIVE_AREA_COUNT)
+
+#define _MIPIA_VSYNC_PADDING_COUNT	(dev_priv->mipi_mmio_base + 0xb038)
+#define _MIPIB_VSYNC_PADDING_COUNT	(dev_priv->mipi_mmio_base + 0xb838)
+#define MIPI_VSYNC_PADDING_COUNT(tc)	_TRANSCODER(tc, \
+			_MIPIA_VSYNC_PADDING_COUNT, _MIPIB_VSYNC_PADDING_COUNT)
+
+#define _MIPIA_VBP_COUNT		(dev_priv->mipi_mmio_base + 0xb03c)
+#define _MIPIB_VBP_COUNT		(dev_priv->mipi_mmio_base + 0xb83c)
+#define MIPI_VBP_COUNT(tc)		_TRANSCODER(tc, _MIPIA_VBP_COUNT, \
+					_MIPIB_VBP_COUNT)
+
+#define _MIPIA_VFP_COUNT		(dev_priv->mipi_mmio_base + 0xb040)
+#define _MIPIB_VFP_COUNT		(dev_priv->mipi_mmio_base + 0xb840)
+#define MIPI_VFP_COUNT(tc)		_TRANSCODER(tc, _MIPIA_VFP_COUNT, \
+					_MIPIB_VFP_COUNT)
+
+#define _MIPIA_HIGH_LOW_SWITCH_COUNT	(dev_priv->mipi_mmio_base + 0xb044)
+#define _MIPIB_HIGH_LOW_SWITCH_COUNT	(dev_priv->mipi_mmio_base + 0xb844)
+#define MIPI_HIGH_LOW_SWITCH_COUNT(tc)	_TRANSCODER(tc,	\
+		_MIPIA_HIGH_LOW_SWITCH_COUNT, _MIPIB_HIGH_LOW_SWITCH_COUNT)
 
-#define _MIPIA_VFP_COUNT			(VLV_DISPLAY_BASE + 0xb040)
-#define _MIPIB_VFP_COUNT			(VLV_DISPLAY_BASE + 0xb840)
-#define MIPI_VFP_COUNT(pipe)		_PIPE(pipe, _MIPIA_VFP_COUNT, _MIPIB_VFP_COUNT)
-
-#define _MIPIA_HIGH_LOW_SWITCH_COUNT		(VLV_DISPLAY_BASE + 0xb044)
-#define _MIPIB_HIGH_LOW_SWITCH_COUNT		(VLV_DISPLAY_BASE + 0xb844)
-#define MIPI_HIGH_LOW_SWITCH_COUNT(pipe)	_PIPE(pipe, _MIPIA_HIGH_LOW_SWITCH_COUNT, _MIPIB_HIGH_LOW_SWITCH_COUNT)
 /* regs above are bits 15:0 */
 
-#define _MIPIA_DPI_CONTROL			(VLV_DISPLAY_BASE + 0xb048)
-#define _MIPIB_DPI_CONTROL			(VLV_DISPLAY_BASE + 0xb848)
-#define MIPI_DPI_CONTROL(pipe)		_PIPE(pipe, _MIPIA_DPI_CONTROL, _MIPIB_DPI_CONTROL)
+#define _MIPIA_DPI_CONTROL		(dev_priv->mipi_mmio_base + 0xb048)
+#define _MIPIB_DPI_CONTROL		(dev_priv->mipi_mmio_base + 0xb848)
+#define MIPI_DPI_CONTROL(tc)		_TRANSCODER(tc, _MIPIA_DPI_CONTROL, \
+					_MIPIB_DPI_CONTROL)
 #define  DPI_LP_MODE					(1 << 6)
 #define  BACKLIGHT_OFF					(1 << 5)
 #define  BACKLIGHT_ON					(1 << 4)
@@ -6205,27 +6268,31 @@ enum punit_power_well {
 #define  TURN_ON					(1 << 1)
 #define  SHUTDOWN					(1 << 0)
 
-#define _MIPIA_DPI_DATA				(VLV_DISPLAY_BASE + 0xb04c)
-#define _MIPIB_DPI_DATA				(VLV_DISPLAY_BASE + 0xb84c)
-#define MIPI_DPI_DATA(pipe)		_PIPE(pipe, _MIPIA_DPI_DATA, _MIPIB_DPI_DATA)
+#define _MIPIA_DPI_DATA			(dev_priv->mipi_mmio_base + 0xb04c)
+#define _MIPIB_DPI_DATA			(dev_priv->mipi_mmio_base + 0xb84c)
+#define MIPI_DPI_DATA(tc)		_TRANSCODER(tc, _MIPIA_DPI_DATA, \
+					_MIPIB_DPI_DATA)
 #define  COMMAND_BYTE_SHIFT				0
 #define  COMMAND_BYTE_MASK				(0x3f << 0)
 
-#define _MIPIA_INIT_COUNT			(VLV_DISPLAY_BASE + 0xb050)
-#define _MIPIB_INIT_COUNT			(VLV_DISPLAY_BASE + 0xb850)
-#define MIPI_INIT_COUNT(pipe)		_PIPE(pipe, _MIPIA_INIT_COUNT, _MIPIB_INIT_COUNT)
+#define _MIPIA_INIT_COUNT		(dev_priv->mipi_mmio_base + 0xb050)
+#define _MIPIB_INIT_COUNT		(dev_priv->mipi_mmio_base + 0xb850)
+#define MIPI_INIT_COUNT(tc)		_TRANSCODER(tc, _MIPIA_INIT_COUNT, \
+					_MIPIB_INIT_COUNT)
 #define  MASTER_INIT_TIMER_SHIFT			0
 #define  MASTER_INIT_TIMER_MASK				(0xffff << 0)
 
-#define _MIPIA_MAX_RETURN_PKT_SIZE		(VLV_DISPLAY_BASE + 0xb054)
-#define _MIPIB_MAX_RETURN_PKT_SIZE		(VLV_DISPLAY_BASE + 0xb854)
-#define MIPI_MAX_RETURN_PKT_SIZE(pipe)	_PIPE(pipe, _MIPIA_MAX_RETURN_PKT_SIZE, _MIPIB_MAX_RETURN_PKT_SIZE)
+#define _MIPIA_MAX_RETURN_PKT_SIZE	(dev_priv->mipi_mmio_base + 0xb054)
+#define _MIPIB_MAX_RETURN_PKT_SIZE	(dev_priv->mipi_mmio_base + 0xb854)
+#define MIPI_MAX_RETURN_PKT_SIZE(tc)	_TRANSCODER(tc, \
+			_MIPIA_MAX_RETURN_PKT_SIZE, _MIPIB_MAX_RETURN_PKT_SIZE)
 #define  MAX_RETURN_PKT_SIZE_SHIFT			0
 #define  MAX_RETURN_PKT_SIZE_MASK			(0x3ff << 0)
 
-#define _MIPIA_VIDEO_MODE_FORMAT		(VLV_DISPLAY_BASE + 0xb058)
-#define _MIPIB_VIDEO_MODE_FORMAT		(VLV_DISPLAY_BASE + 0xb858)
-#define MIPI_VIDEO_MODE_FORMAT(pipe)	_PIPE(pipe, _MIPIA_VIDEO_MODE_FORMAT, _MIPIB_VIDEO_MODE_FORMAT)
+#define _MIPIA_VIDEO_MODE_FORMAT	(dev_priv->mipi_mmio_base + 0xb058)
+#define _MIPIB_VIDEO_MODE_FORMAT	(dev_priv->mipi_mmio_base + 0xb858)
+#define MIPI_VIDEO_MODE_FORMAT(tc)	_TRANSCODER(tc, \
+			_MIPIA_VIDEO_MODE_FORMAT, _MIPIB_VIDEO_MODE_FORMAT)
 #define  RANDOM_DPI_DISPLAY_RESOLUTION			(1 << 4)
 #define  DISABLE_VIDEO_BTA				(1 << 3)
 #define  IP_TG_CONFIG					(1 << 2)
@@ -6233,9 +6300,10 @@ enum punit_power_well {
 #define  VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS		(2 << 0)
 #define  VIDEO_MODE_BURST				(3 << 0)
 
-#define _MIPIA_EOT_DISABLE			(VLV_DISPLAY_BASE + 0xb05c)
-#define _MIPIB_EOT_DISABLE			(VLV_DISPLAY_BASE + 0xb85c)
-#define MIPI_EOT_DISABLE(pipe)		_PIPE(pipe, _MIPIA_EOT_DISABLE, _MIPIB_EOT_DISABLE)
+#define _MIPIA_EOT_DISABLE		(dev_priv->mipi_mmio_base + 0xb05c)
+#define _MIPIB_EOT_DISABLE		(dev_priv->mipi_mmio_base + 0xb85c)
+#define MIPI_EOT_DISABLE(tc)		_TRANSCODER(tc, _MIPIA_EOT_DISABLE, \
+					_MIPIB_EOT_DISABLE)
 #define  LP_RX_TIMEOUT_ERROR_RECOVERY_DISABLE		(1 << 7)
 #define  HS_RX_TIMEOUT_ERROR_RECOVERY_DISABLE		(1 << 6)
 #define  LOW_CONTENTION_RECOVERY_DISABLE		(1 << 5)
@@ -6245,28 +6313,33 @@ enum punit_power_well {
 #define  CLOCKSTOP					(1 << 1)
 #define  EOT_DISABLE					(1 << 0)
 
-#define _MIPIA_LP_BYTECLK			(VLV_DISPLAY_BASE + 0xb060)
-#define _MIPIB_LP_BYTECLK			(VLV_DISPLAY_BASE + 0xb860)
-#define MIPI_LP_BYTECLK(pipe)		_PIPE(pipe, _MIPIA_LP_BYTECLK, _MIPIB_LP_BYTECLK)
+#define _MIPIA_LP_BYTECLK		(dev_priv->mipi_mmio_base + 0xb060)
+#define _MIPIB_LP_BYTECLK		(dev_priv->mipi_mmio_base + 0xb860)
+#define MIPI_LP_BYTECLK(tc)		_TRANSCODER(tc, _MIPIA_LP_BYTECLK, \
+					_MIPIB_LP_BYTECLK)
 #define  LP_BYTECLK_SHIFT				0
 #define  LP_BYTECLK_MASK				(0xffff << 0)
 
 /* bits 31:0 */
-#define _MIPIA_LP_GEN_DATA			(VLV_DISPLAY_BASE + 0xb064)
-#define _MIPIB_LP_GEN_DATA			(VLV_DISPLAY_BASE + 0xb864)
-#define MIPI_LP_GEN_DATA(pipe)		_PIPE(pipe, _MIPIA_LP_GEN_DATA, _MIPIB_LP_GEN_DATA)
+#define _MIPIA_LP_GEN_DATA		(dev_priv->mipi_mmio_base + 0xb064)
+#define _MIPIB_LP_GEN_DATA		(dev_priv->mipi_mmio_base + 0xb864)
+#define MIPI_LP_GEN_DATA(tc)		_TRANSCODER(tc, _MIPIA_LP_GEN_DATA, \
+					_MIPIB_LP_GEN_DATA)
 
 /* bits 31:0 */
-#define _MIPIA_HS_GEN_DATA			(VLV_DISPLAY_BASE + 0xb068)
-#define _MIPIB_HS_GEN_DATA			(VLV_DISPLAY_BASE + 0xb868)
-#define MIPI_HS_GEN_DATA(pipe)		_PIPE(pipe, _MIPIA_HS_GEN_DATA, _MIPIB_HS_GEN_DATA)
-
-#define _MIPIA_LP_GEN_CTRL			(VLV_DISPLAY_BASE + 0xb06c)
-#define _MIPIB_LP_GEN_CTRL			(VLV_DISPLAY_BASE + 0xb86c)
-#define MIPI_LP_GEN_CTRL(pipe)		_PIPE(pipe, _MIPIA_LP_GEN_CTRL, _MIPIB_LP_GEN_CTRL)
-#define _MIPIA_HS_GEN_CTRL			(VLV_DISPLAY_BASE + 0xb070)
-#define _MIPIB_HS_GEN_CTRL			(VLV_DISPLAY_BASE + 0xb870)
-#define MIPI_HS_GEN_CTRL(pipe)		_PIPE(pipe, _MIPIA_HS_GEN_CTRL, _MIPIB_HS_GEN_CTRL)
+#define _MIPIA_HS_GEN_DATA		(dev_priv->mipi_mmio_base + 0xb068)
+#define _MIPIB_HS_GEN_DATA		(dev_priv->mipi_mmio_base + 0xb868)
+#define MIPI_HS_GEN_DATA(tc)		_TRANSCODER(tc, _MIPIA_HS_GEN_DATA, \
+					_MIPIB_HS_GEN_DATA)
+
+#define _MIPIA_LP_GEN_CTRL		(dev_priv->mipi_mmio_base + 0xb06c)
+#define _MIPIB_LP_GEN_CTRL		(dev_priv->mipi_mmio_base + 0xb86c)
+#define MIPI_LP_GEN_CTRL(tc)		_TRANSCODER(tc, _MIPIA_LP_GEN_CTRL, \
+					_MIPIB_LP_GEN_CTRL)
+#define _MIPIA_HS_GEN_CTRL		(dev_priv->mipi_mmio_base + 0xb070)
+#define _MIPIB_HS_GEN_CTRL		(dev_priv->mipi_mmio_base + 0xb870)
+#define MIPI_HS_GEN_CTRL(tc)		_TRANSCODER(tc, _MIPIA_HS_GEN_CTRL, \
+					_MIPIB_HS_GEN_CTRL)
 #define  LONG_PACKET_WORD_COUNT_SHIFT			8
 #define  LONG_PACKET_WORD_COUNT_MASK			(0xffff << 8)
 #define  SHORT_PACKET_PARAM_SHIFT			8
@@ -6277,9 +6350,10 @@ enum punit_power_well {
 #define  DATA_TYPE_MASK					(3f << 0)
 /* data type values, see include/video/mipi_display.h */
 
-#define _MIPIA_GEN_FIFO_STAT			(VLV_DISPLAY_BASE + 0xb074)
-#define _MIPIB_GEN_FIFO_STAT			(VLV_DISPLAY_BASE + 0xb874)
-#define MIPI_GEN_FIFO_STAT(pipe)	_PIPE(pipe, _MIPIA_GEN_FIFO_STAT, _MIPIB_GEN_FIFO_STAT)
+#define _MIPIA_GEN_FIFO_STAT		(dev_priv->mipi_mmio_base + 0xb074)
+#define _MIPIB_GEN_FIFO_STAT		(dev_priv->mipi_mmio_base + 0xb874)
+#define MIPI_GEN_FIFO_STAT(tc)	_TRANSCODER(tc, _MIPIA_GEN_FIFO_STAT, \
+					_MIPIB_GEN_FIFO_STAT)
 #define  DPI_FIFO_EMPTY					(1 << 28)
 #define  DBI_FIFO_EMPTY					(1 << 27)
 #define  LP_CTRL_FIFO_EMPTY				(1 << 26)
@@ -6295,16 +6369,18 @@ enum punit_power_well {
 #define  HS_DATA_FIFO_HALF_EMPTY			(1 << 1)
 #define  HS_DATA_FIFO_FULL				(1 << 0)
 
-#define _MIPIA_HS_LS_DBI_ENABLE			(VLV_DISPLAY_BASE + 0xb078)
-#define _MIPIB_HS_LS_DBI_ENABLE			(VLV_DISPLAY_BASE + 0xb878)
-#define MIPI_HS_LP_DBI_ENABLE(pipe)	_PIPE(pipe, _MIPIA_HS_LS_DBI_ENABLE, _MIPIB_HS_LS_DBI_ENABLE)
+#define _MIPIA_HS_LS_DBI_ENABLE		(dev_priv->mipi_mmio_base + 0xb078)
+#define _MIPIB_HS_LS_DBI_ENABLE		(dev_priv->mipi_mmio_base + 0xb878)
+#define MIPI_HS_LP_DBI_ENABLE(tc)	_TRANSCODER(tc, \
+			_MIPIA_HS_LS_DBI_ENABLE, _MIPIB_HS_LS_DBI_ENABLE)
 #define  DBI_HS_LP_MODE_MASK				(1 << 0)
 #define  DBI_LP_MODE					(1 << 0)
 #define  DBI_HS_MODE					(0 << 0)
 
-#define _MIPIA_DPHY_PARAM			(VLV_DISPLAY_BASE + 0xb080)
-#define _MIPIB_DPHY_PARAM			(VLV_DISPLAY_BASE + 0xb880)
-#define MIPI_DPHY_PARAM(pipe)		_PIPE(pipe, _MIPIA_DPHY_PARAM, _MIPIB_DPHY_PARAM)
+#define _MIPIA_DPHY_PARAM		(dev_priv->mipi_mmio_base + 0xb080)
+#define _MIPIB_DPHY_PARAM		(dev_priv->mipi_mmio_base + 0xb880)
+#define MIPI_DPHY_PARAM(tc)		_TRANSCODER(tc, _MIPIA_DPHY_PARAM, \
+					_MIPIB_DPHY_PARAM)
 #define  EXIT_ZERO_COUNT_SHIFT				24
 #define  EXIT_ZERO_COUNT_MASK				(0x3f << 24)
 #define  TRAIL_COUNT_SHIFT				16
@@ -6315,34 +6391,41 @@ enum punit_power_well {
 #define  PREPARE_COUNT_MASK				(0x3f << 0)
 
 /* bits 31:0 */
-#define _MIPIA_DBI_BW_CTRL			(VLV_DISPLAY_BASE + 0xb084)
-#define _MIPIB_DBI_BW_CTRL			(VLV_DISPLAY_BASE + 0xb884)
-#define MIPI_DBI_BW_CTRL(pipe)		_PIPE(pipe, _MIPIA_DBI_BW_CTRL, _MIPIB_DBI_BW_CTRL)
-
-#define _MIPIA_CLK_LANE_SWITCH_TIME_CNT		(VLV_DISPLAY_BASE + 0xb088)
-#define _MIPIB_CLK_LANE_SWITCH_TIME_CNT		(VLV_DISPLAY_BASE + 0xb888)
-#define MIPI_CLK_LANE_SWITCH_TIME_CNT(pipe)	_PIPE(pipe, _MIPIA_CLK_LANE_SWITCH_TIME_CNT, _MIPIB_CLK_LANE_SWITCH_TIME_CNT)
+#define _MIPIA_DBI_BW_CTRL		(dev_priv->mipi_mmio_base + 0xb084)
+#define _MIPIB_DBI_BW_CTRL		(dev_priv->mipi_mmio_base + 0xb884)
+#define MIPI_DBI_BW_CTRL(tc)		_TRANSCODER(tc, _MIPIA_DBI_BW_CTRL, \
+					_MIPIB_DBI_BW_CTRL)
+
+#define _MIPIA_CLK_LANE_SWITCH_TIME_CNT		(dev_priv->mipi_mmio_base \
+							+ 0xb088)
+#define _MIPIB_CLK_LANE_SWITCH_TIME_CNT		(dev_priv->mipi_mmio_base \
+							+ 0xb888)
+#define MIPI_CLK_LANE_SWITCH_TIME_CNT(tc)	_TRANSCODER(tc, \
+	_MIPIA_CLK_LANE_SWITCH_TIME_CNT, _MIPIB_CLK_LANE_SWITCH_TIME_CNT)
 #define  LP_HS_SSW_CNT_SHIFT				16
 #define  LP_HS_SSW_CNT_MASK				(0xffff << 16)
 #define  HS_LP_PWR_SW_CNT_SHIFT				0
 #define  HS_LP_PWR_SW_CNT_MASK				(0xffff << 0)
 
-#define _MIPIA_STOP_STATE_STALL			(VLV_DISPLAY_BASE + 0xb08c)
-#define _MIPIB_STOP_STATE_STALL			(VLV_DISPLAY_BASE + 0xb88c)
-#define MIPI_STOP_STATE_STALL(pipe)	_PIPE(pipe, _MIPIA_STOP_STATE_STALL, _MIPIB_STOP_STATE_STALL)
+#define _MIPIA_STOP_STATE_STALL		(dev_priv->mipi_mmio_base + 0xb08c)
+#define _MIPIB_STOP_STATE_STALL		(dev_priv->mipi_mmio_base + 0xb88c)
+#define MIPI_STOP_STATE_STALL(tc)	_TRANSCODER(tc, \
+			_MIPIA_STOP_STATE_STALL, _MIPIB_STOP_STATE_STALL)
 #define  STOP_STATE_STALL_COUNTER_SHIFT			0
 #define  STOP_STATE_STALL_COUNTER_MASK			(0xff << 0)
 
-#define _MIPIA_INTR_STAT_REG_1			(VLV_DISPLAY_BASE + 0xb090)
-#define _MIPIB_INTR_STAT_REG_1			(VLV_DISPLAY_BASE + 0xb890)
-#define MIPI_INTR_STAT_REG_1(pipe)	_PIPE(pipe, _MIPIA_INTR_STAT_REG_1, _MIPIB_INTR_STAT_REG_1)
-#define _MIPIA_INTR_EN_REG_1			(VLV_DISPLAY_BASE + 0xb094)
-#define _MIPIB_INTR_EN_REG_1			(VLV_DISPLAY_BASE + 0xb894)
-#define MIPI_INTR_EN_REG_1(pipe)	_PIPE(pipe, _MIPIA_INTR_EN_REG_1, _MIPIB_INTR_EN_REG_1)
+#define _MIPIA_INTR_STAT_REG_1		(dev_priv->mipi_mmio_base + 0xb090)
+#define _MIPIB_INTR_STAT_REG_1		(dev_priv->mipi_mmio_base + 0xb890)
+#define MIPI_INTR_STAT_REG_1(tc)	_TRANSCODER(tc, \
+				_MIPIA_INTR_STAT_REG_1, _MIPIB_INTR_STAT_REG_1)
+#define _MIPIA_INTR_EN_REG_1		(dev_priv->mipi_mmio_base + 0xb094)
+#define _MIPIB_INTR_EN_REG_1		(dev_priv->mipi_mmio_base + 0xb894)
+#define MIPI_INTR_EN_REG_1(tc)	_TRANSCODER(tc, _MIPIA_INTR_EN_REG_1, \
+					_MIPIB_INTR_EN_REG_1)
 #define  RX_CONTENTION_DETECTED				(1 << 0)
 
 /* XXX: only pipe A ?!? */
-#define MIPIA_DBI_TYPEC_CTRL			(VLV_DISPLAY_BASE + 0xb100)
+#define MIPIA_DBI_TYPEC_CTRL		(dev_priv->mipi_mmio_base + 0xb100)
 #define  DBI_TYPEC_ENABLE				(1 << 31)
 #define  DBI_TYPEC_WIP					(1 << 30)
 #define  DBI_TYPEC_OPTION_SHIFT				28
@@ -6356,9 +6439,10 @@ enum punit_power_well {
 
 /* MIPI adapter registers */
 
-#define _MIPIA_CTRL				(VLV_DISPLAY_BASE + 0xb104)
-#define _MIPIB_CTRL				(VLV_DISPLAY_BASE + 0xb904)
-#define MIPI_CTRL(pipe)			_PIPE(pipe, _MIPIA_CTRL, _MIPIB_CTRL)
+#define _MIPIA_CTRL			(dev_priv->mipi_mmio_base + 0xb104)
+#define _MIPIB_CTRL			(dev_priv->mipi_mmio_base + 0xb904)
+#define MIPI_CTRL(tc)			_TRANSCODER(tc, _MIPIA_CTRL, \
+					_MIPIB_CTRL)
 #define  ESCAPE_CLOCK_DIVIDER_SHIFT			5 /* A only */
 #define  ESCAPE_CLOCK_DIVIDER_MASK			(3 << 5)
 #define  ESCAPE_CLOCK_DIVIDER_1				(0 << 5)
@@ -6370,50 +6454,52 @@ enum punit_power_well {
 #define  READ_REQUEST_PRIORITY_HIGH			(3 << 3)
 #define  RGB_FLIP_TO_BGR				(1 << 2)
 
-#define _MIPIA_DATA_ADDRESS			(VLV_DISPLAY_BASE + 0xb108)
-#define _MIPIB_DATA_ADDRESS			(VLV_DISPLAY_BASE + 0xb908)
-#define MIPI_DATA_ADDRESS(pipe)		_PIPE(pipe, _MIPIA_DATA_ADDRESS, _MIPIB_DATA_ADDRESS)
+#define _MIPIA_DATA_ADDRESS		(dev_priv->mipi_mmio_base + 0xb108)
+#define _MIPIB_DATA_ADDRESS		(dev_priv->mipi_mmio_base + 0xb908)
+#define MIPI_DATA_ADDRESS(tc)		_TRANSCODER(tc, _MIPIA_DATA_ADDRESS, \
+					_MIPIB_DATA_ADDRESS)
 #define  DATA_MEM_ADDRESS_SHIFT				5
 #define  DATA_MEM_ADDRESS_MASK				(0x7ffffff << 5)
 #define  DATA_VALID					(1 << 0)
 
-#define _MIPIA_DATA_LENGTH			(VLV_DISPLAY_BASE + 0xb10c)
-#define _MIPIB_DATA_LENGTH			(VLV_DISPLAY_BASE + 0xb90c)
-#define MIPI_DATA_LENGTH(pipe)		_PIPE(pipe, _MIPIA_DATA_LENGTH, _MIPIB_DATA_LENGTH)
+#define _MIPIA_DATA_LENGTH		(dev_priv->mipi_mmio_base + 0xb10c)
+#define _MIPIB_DATA_LENGTH		(dev_priv->mipi_mmio_base + 0xb90c)
+#define MIPI_DATA_LENGTH(tc)		_TRANSCODER(tc, _MIPIA_DATA_LENGTH, \
+					_MIPIB_DATA_LENGTH)
 #define  DATA_LENGTH_SHIFT				0
 #define  DATA_LENGTH_MASK				(0xfffff << 0)
 
-#define _MIPIA_COMMAND_ADDRESS			(VLV_DISPLAY_BASE + 0xb110)
-#define _MIPIB_COMMAND_ADDRESS			(VLV_DISPLAY_BASE + 0xb910)
-#define MIPI_COMMAND_ADDRESS(pipe)	_PIPE(pipe, _MIPIA_COMMAND_ADDRESS, _MIPIB_COMMAND_ADDRESS)
+#define _MIPIA_COMMAND_ADDRESS		(dev_priv->mipi_mmio_base + 0xb110)
+#define _MIPIB_COMMAND_ADDRESS		(dev_priv->mipi_mmio_base + 0xb910)
+#define MIPI_COMMAND_ADDRESS(tc)	_TRANSCODER(tc, \
+				_MIPIA_COMMAND_ADDRESS, _MIPIB_COMMAND_ADDRESS)
 #define  COMMAND_MEM_ADDRESS_SHIFT			5
 #define  COMMAND_MEM_ADDRESS_MASK			(0x7ffffff << 5)
 #define  AUTO_PWG_ENABLE				(1 << 2)
 #define  MEMORY_WRITE_DATA_FROM_PIPE_RENDERING		(1 << 1)
 #define  COMMAND_VALID					(1 << 0)
 
-#define _MIPIA_COMMAND_LENGTH			(VLV_DISPLAY_BASE + 0xb114)
-#define _MIPIB_COMMAND_LENGTH			(VLV_DISPLAY_BASE + 0xb914)
-#define MIPI_COMMAND_LENGTH(pipe)	_PIPE(pipe, _MIPIA_COMMAND_LENGTH, _MIPIB_COMMAND_LENGTH)
+#define _MIPIA_COMMAND_LENGTH		(dev_priv->mipi_mmio_base + 0xb114)
+#define _MIPIB_COMMAND_LENGTH		(dev_priv->mipi_mmio_base + 0xb914)
+#define MIPI_COMMAND_LENGTH(tc)	_TRANSCODER(tc, _MIPIA_COMMAND_LENGTH, \
+					_MIPIB_COMMAND_LENGTH)
 #define  COMMAND_LENGTH_SHIFT(n)			(8 * (n)) /* n: 0...3 */
 #define  COMMAND_LENGTH_MASK(n)				(0xff << (8 * (n)))
 
-#define _MIPIA_READ_DATA_RETURN0		(VLV_DISPLAY_BASE + 0xb118)
-#define _MIPIB_READ_DATA_RETURN0		(VLV_DISPLAY_BASE + 0xb918)
-#define MIPI_READ_DATA_RETURN(pipe, n) \
-	(_PIPE(pipe, _MIPIA_READ_DATA_RETURN0, _MIPIB_READ_DATA_RETURN0) + 4 * (n)) /* n: 0...7 */
+#define _MIPIA_READ_DATA_RETURN0	(dev_priv->mipi_mmio_base + 0xb118)
+#define _MIPIB_READ_DATA_RETURN0	(dev_priv->mipi_mmio_base + 0xb918)
+#define MIPI_READ_DATA_RETURN(tc, n) \
+	(_TRANSCODER(tc, _MIPIA_READ_DATA_RETURN0, _MIPIB_READ_DATA_RETURN0) \
+					+ 4 * (n)) /* n: 0...7 */
 
-#define _MIPIA_READ_DATA_VALID			(VLV_DISPLAY_BASE + 0xb138)
-#define _MIPIB_READ_DATA_VALID			(VLV_DISPLAY_BASE + 0xb938)
-#define MIPI_READ_DATA_VALID(pipe)	_PIPE(pipe, _MIPIA_READ_DATA_VALID, _MIPIB_READ_DATA_VALID)
+#define _MIPIA_READ_DATA_VALID		(dev_priv->mipi_mmio_base + 0xb138)
+#define _MIPIB_READ_DATA_VALID		(dev_priv->mipi_mmio_base + 0xb938)
+#define MIPI_READ_DATA_VALID(tc)	_TRANSCODER(tc, \
+				_MIPIA_READ_DATA_VALID, _MIPIB_READ_DATA_VALID)
 #define  READ_DATA_VALID(n)				(1 << (n))
 
 /* For UMS only (deprecated): */
 #define _PALETTE_A (dev_priv->info.display_mmio_offset + 0xa000)
 #define _PALETTE_B (dev_priv->info.display_mmio_offset + 0xa800)
-#define _DPLL_A (dev_priv->info.display_mmio_offset + 0x6014)
-#define _DPLL_B (dev_priv->info.display_mmio_offset + 0x6018)
-#define _DPLL_A_MD (dev_priv->info.display_mmio_offset + 0x601c)
-#define _DPLL_B_MD (dev_priv->info.display_mmio_offset + 0x6020)
 
 #endif /* _I915_REG_H_ */

drivers/gpu/drm/i915/intel_ddi.c

@@ -76,12 +76,12 @@ static const u32 bdw_ddi_translations_edp[] = {
 	0x00FFFFFF, 0x00000012,		/* eDP parameters */
 	0x00EBAFFF, 0x00020011,
 	0x00C71FFF, 0x0006000F,
+	0x00AAAFFF, 0x000E000A,
 	0x00FFFFFF, 0x00020011,
 	0x00DB6FFF, 0x0005000F,
 	0x00BEEFFF, 0x000A000C,
 	0x00FFFFFF, 0x0005000F,
 	0x00DB6FFF, 0x000A000C,
-	0x00FFFFFF, 0x000A000C,
 	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
 };
 
@@ -89,12 +89,12 @@ static const u32 bdw_ddi_translations_dp[] = {
 	0x00FFFFFF, 0x0007000E,		/* DP parameters */
 	0x00D75FFF, 0x000E000A,
 	0x00BEFFFF, 0x00140006,
+	0x80B2CFFF, 0x001B0002,
 	0x00FFFFFF, 0x000E000A,
 	0x00D75FFF, 0x00180004,
 	0x80CB2FFF, 0x001B0002,
 	0x00F7DFFF, 0x00180004,
 	0x80D75FFF, 0x001B0002,
-	0x80FFFFFF, 0x001B0002,
 	0x00FFFFFF, 0x00140006		/* HDMI parameters 800mV 0dB*/
 };
 

drivers/gpu/drm/i915/intel_display.c

@@ -39,12 +39,45 @@
 #include "i915_trace.h"
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_rect.h>
 #include <linux/dma_remapping.h>
 
+/* Primary plane formats supported by all gen */
+#define COMMON_PRIMARY_FORMATS \
+	DRM_FORMAT_C8, \
+	DRM_FORMAT_RGB565, \
+	DRM_FORMAT_XRGB8888, \
+	DRM_FORMAT_ARGB8888
+
+/* Primary plane formats for gen <= 3 */
+static const uint32_t intel_primary_formats_gen2[] = {
+	COMMON_PRIMARY_FORMATS,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ARGB1555,
+};
+
+/* Primary plane formats for gen >= 4 */
+static const uint32_t intel_primary_formats_gen4[] = {
+	COMMON_PRIMARY_FORMATS, \
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_ARGB2101010,
+	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_ABGR2101010,
+};
+
+/* Cursor formats */
+static const uint32_t intel_cursor_formats[] = {
+	DRM_FORMAT_ARGB8888,
+};
+
 #define DIV_ROUND_CLOSEST_ULL(ll, d)	\
-	({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
+({ unsigned long long _tmp = (ll)+(d)/2; do_div(_tmp, d); _tmp; })
 
-static void intel_increase_pllclock(struct drm_crtc *crtc);
+static void intel_increase_pllclock(struct drm_device *dev,
+				    enum pipe pipe);
 static void intel_crtc_update_cursor(struct drm_crtc *crtc, bool on);
 
 static void i9xx_crtc_clock_get(struct intel_crtc *crtc,
@@ -1712,6 +1745,17 @@ static void chv_disable_pll(struct drm_i915_private *dev_priv, enum pipe pipe)
 	val &= ~DPIO_DCLKP_EN;
 	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW14(port), val);
 
+	/* disable left/right clock distribution */
+	if (pipe != PIPE_B) {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+	} else {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+	}
+
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
@@ -1749,6 +1793,9 @@ static void intel_prepare_shared_dpll(struct intel_crtc *crtc)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_shared_dpll *pll = intel_crtc_to_shared_dpll(crtc);
 
+	if (WARN_ON(pll == NULL))
+		return;
+
 	WARN_ON(!pll->refcount);
 	if (pll->active == 0) {
 		DRM_DEBUG_DRIVER("setting up %s\n", pll->name);
@@ -2314,6 +2361,7 @@ static bool intel_alloc_plane_obj(struct intel_crtc *crtc,
 		goto out_unref_obj;
 	}
 
+	obj->frontbuffer_bits = INTEL_FRONTBUFFER_PRIMARY(crtc->pipe);
 	mutex_unlock(&dev->struct_mutex);
 
 	DRM_DEBUG_KMS("plane fb obj %p\n", obj);
@@ -2359,6 +2407,7 @@ static void intel_find_plane_obj(struct intel_crtc *intel_crtc,
 		if (i915_gem_obj_ggtt_offset(fb->obj) == plane_config->base) {
 			drm_framebuffer_reference(c->primary->fb);
 			intel_crtc->base.primary->fb = c->primary->fb;
+			fb->obj->frontbuffer_bits |= INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
 			break;
 		}
 	}
@@ -2546,7 +2595,7 @@ intel_pipe_set_base_atomic(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 
 	if (dev_priv->display.disable_fbc)
 		dev_priv->display.disable_fbc(dev);
-	intel_increase_pllclock(crtc);
+	intel_increase_pllclock(dev, to_intel_crtc(crtc)->pipe);
 
 	dev_priv->display.update_primary_plane(crtc, fb, x, y);
 
@@ -2647,7 +2696,9 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	enum pipe pipe = intel_crtc->pipe;
 	struct drm_framebuffer *old_fb;
+	struct drm_i915_gem_object *obj = to_intel_framebuffer(fb)->obj;
 	int ret;
 
 	if (intel_crtc_has_pending_flip(crtc)) {
@@ -2668,10 +2719,13 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		return -EINVAL;
 	}
 
+	old_fb = crtc->primary->fb;
+
 	mutex_lock(&dev->struct_mutex);
-	ret = intel_pin_and_fence_fb_obj(dev,
-					 to_intel_framebuffer(fb)->obj,
-					 NULL);
+	ret = intel_pin_and_fence_fb_obj(dev, obj, NULL);
+	if (ret == 0)
+		i915_gem_track_fb(to_intel_framebuffer(old_fb)->obj, obj,
+				  INTEL_FRONTBUFFER_PRIMARY(pipe));
 	mutex_unlock(&dev->struct_mutex);
 	if (ret != 0) {
 		DRM_ERROR("pin & fence failed\n");
@@ -2711,7 +2765,9 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 
 	dev_priv->display.update_primary_plane(crtc, fb, x, y);
 
-	old_fb = crtc->primary->fb;
+	if (intel_crtc->active)
+		intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_PRIMARY(pipe));
+
 	crtc->primary->fb = fb;
 	crtc->x = x;
 	crtc->y = y;
@@ -2726,7 +2782,6 @@ intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
-	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 
 	return 0;
@@ -3892,6 +3947,8 @@ static void intel_crtc_enable_planes(struct drm_crtc *crtc)
 	int pipe = intel_crtc->pipe;
 	int plane = intel_crtc->plane;
 
+	drm_vblank_on(dev, pipe);
+
 	intel_enable_primary_hw_plane(dev_priv, plane, pipe);
 	intel_enable_planes(crtc);
 	/* The fixup needs to happen before cursor is enabled */
@@ -3904,8 +3961,14 @@ static void intel_crtc_enable_planes(struct drm_crtc *crtc)
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
-	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
+
+	/*
+	 * FIXME: Once we grow proper nuclear flip support out of this we need
+	 * to compute the mask of flip planes precisely. For the time being
+	 * consider this a flip from a NULL plane.
+	 */
+	intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_ALL_MASK(pipe));
 }
 
 static void intel_crtc_disable_planes(struct drm_crtc *crtc)
@@ -3917,7 +3980,6 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc)
 	int plane = intel_crtc->plane;
 
 	intel_crtc_wait_for_pending_flips(crtc);
-	drm_crtc_vblank_off(crtc);
 
 	if (dev_priv->fbc.plane == plane)
 		intel_disable_fbc(dev);
@@ -3928,6 +3990,15 @@ static void intel_crtc_disable_planes(struct drm_crtc *crtc)
 	intel_crtc_update_cursor(crtc, false);
 	intel_disable_planes(crtc);
 	intel_disable_primary_hw_plane(dev_priv, plane, pipe);
+
+	/*
+	 * FIXME: Once we grow proper nuclear flip support out of this we need
+	 * to compute the mask of flip planes precisely. For the time being
+	 * consider this a flip to a NULL plane.
+	 */
+	intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_ALL_MASK(pipe));
+
+	drm_vblank_off(dev, pipe);
 }
 
 static void ironlake_crtc_enable(struct drm_crtc *crtc)
@@ -4006,8 +4077,6 @@ static void ironlake_crtc_enable(struct drm_crtc *crtc)
 		cpt_verify_modeset(dev, intel_crtc->pipe);
 
 	intel_crtc_enable_planes(crtc);
-
-	drm_crtc_vblank_on(crtc);
 }
 
 /* IPS only exists on ULT machines and is tied to pipe A. */
@@ -4121,8 +4190,6 @@ static void haswell_crtc_enable(struct drm_crtc *crtc)
 	 * to change the workaround. */
 	haswell_mode_set_planes_workaround(intel_crtc);
 	intel_crtc_enable_planes(crtc);
-
-	drm_crtc_vblank_on(crtc);
 }
 
 static void ironlake_pfit_disable(struct intel_crtc *crtc)
@@ -4200,7 +4267,6 @@ static void ironlake_crtc_disable(struct drm_crtc *crtc)
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
-	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 }
 
@@ -4248,7 +4314,6 @@ static void haswell_crtc_disable(struct drm_crtc *crtc)
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
-	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 }
 
@@ -4633,8 +4698,6 @@ static void valleyview_crtc_enable(struct drm_crtc *crtc)
 
 	intel_crtc_enable_planes(crtc);
 
-	drm_crtc_vblank_on(crtc);
-
 	/* Underruns don't raise interrupts, so check manually. */
 	i9xx_check_fifo_underruns(dev);
 }
@@ -4727,8 +4790,6 @@ static void i9xx_crtc_enable(struct drm_crtc *crtc)
 	if (IS_GEN2(dev))
 		intel_set_cpu_fifo_underrun_reporting(dev, pipe, true);
 
-	drm_crtc_vblank_on(crtc);
-
 	/* Underruns don't raise interrupts, so check manually. */
 	i9xx_check_fifo_underruns(dev);
 }
@@ -4805,7 +4866,6 @@ static void i9xx_crtc_disable(struct drm_crtc *crtc)
 
 	mutex_lock(&dev->struct_mutex);
 	intel_update_fbc(dev);
-	intel_edp_psr_update(dev);
 	mutex_unlock(&dev->struct_mutex);
 }
 
@@ -4850,16 +4910,43 @@ void intel_crtc_update_dpms(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_encoder *intel_encoder;
+	enum intel_display_power_domain domain;
+	unsigned long domains;
 	bool enable = false;
 
 	for_each_encoder_on_crtc(dev, crtc, intel_encoder)
 		enable |= intel_encoder->connectors_active;
 
-	if (enable)
-		dev_priv->display.crtc_enable(crtc);
-	else
-		dev_priv->display.crtc_disable(crtc);
+	if (enable) {
+		if (!intel_crtc->active) {
+			/*
+			 * FIXME: DDI plls and relevant code isn't converted
+			 * yet, so do runtime PM for DPMS only for all other
+			 * platforms for now.
+			 */
+			if (!HAS_DDI(dev)) {
+				domains = get_crtc_power_domains(crtc);
+				for_each_power_domain(domain, domains)
+					intel_display_power_get(dev_priv, domain);
+				intel_crtc->enabled_power_domains = domains;
+			}
+
+			dev_priv->display.crtc_enable(crtc);
+		}
+	} else {
+		if (intel_crtc->active) {
+			dev_priv->display.crtc_disable(crtc);
+
+			if (!HAS_DDI(dev)) {
+				domains = intel_crtc->enabled_power_domains;
+				for_each_power_domain(domain, domains)
+					intel_display_power_put(dev_priv, domain);
+				intel_crtc->enabled_power_domains = 0;
+			}
+		}
+	}
 
 	intel_crtc_update_sarea(crtc, enable);
 }
@@ -4869,6 +4956,8 @@ static void intel_crtc_disable(struct drm_crtc *crtc)
 	struct drm_device *dev = crtc->dev;
 	struct drm_connector *connector;
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *old_obj;
+	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 
 	/* crtc should still be enabled when we disable it. */
 	WARN_ON(!crtc->enabled);
@@ -4878,12 +4967,15 @@ static void intel_crtc_disable(struct drm_crtc *crtc)
 	dev_priv->display.off(crtc);
 
 	assert_plane_disabled(dev->dev_private, to_intel_crtc(crtc)->plane);
-	assert_cursor_disabled(dev_priv, to_intel_crtc(crtc)->pipe);
-	assert_pipe_disabled(dev->dev_private, to_intel_crtc(crtc)->pipe);
+	assert_cursor_disabled(dev_priv, pipe);
+	assert_pipe_disabled(dev->dev_private, pipe);
 
 	if (crtc->primary->fb) {
+		old_obj = to_intel_framebuffer(crtc->primary->fb)->obj;
 		mutex_lock(&dev->struct_mutex);
-		intel_unpin_fb_obj(to_intel_framebuffer(crtc->primary->fb)->obj);
+		intel_unpin_fb_obj(old_obj);
+		i915_gem_track_fb(old_obj, NULL,
+				  INTEL_FRONTBUFFER_PRIMARY(pipe));
 		mutex_unlock(&dev->struct_mutex);
 		crtc->primary->fb = NULL;
 	}
@@ -7991,8 +8083,8 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	int pipe = intel_crtc->pipe;
-	int x = intel_crtc->cursor_x;
-	int y = intel_crtc->cursor_y;
+	int x = crtc->cursor_x;
+	int y = crtc->cursor_y;
 	u32 base = 0, pos = 0;
 
 	if (on)
@@ -8036,21 +8128,27 @@ static void intel_crtc_update_cursor(struct drm_crtc *crtc,
 	intel_crtc->cursor_base = base;
 }
 
-static int intel_crtc_cursor_set(struct drm_crtc *crtc,
-				 struct drm_file *file,
-				 uint32_t handle,
-				 uint32_t width, uint32_t height)
+/*
+ * intel_crtc_cursor_set_obj - Set cursor to specified GEM object
+ *
+ * Note that the object's reference will be consumed if the update fails.  If
+ * the update succeeds, the reference of the old object (if any) will be
+ * consumed.
+ */
+static int intel_crtc_cursor_set_obj(struct drm_crtc *crtc,
+				     struct drm_i915_gem_object *obj,
+				     uint32_t width, uint32_t height)
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	struct drm_i915_gem_object *obj;
+	enum pipe pipe = intel_crtc->pipe;
 	unsigned old_width;
 	uint32_t addr;
 	int ret;
 
 	/* if we want to turn off the cursor ignore width and height */
-	if (!handle) {
+	if (!obj) {
 		DRM_DEBUG_KMS("cursor off\n");
 		addr = 0;
 		obj = NULL;
@@ -8066,12 +8164,8 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 		return -EINVAL;
 	}
 
-	obj = to_intel_bo(drm_gem_object_lookup(dev, file, handle));
-	if (&obj->base == NULL)
-		return -ENOENT;
-
 	if (obj->base.size < width * height * 4) {
-		DRM_DEBUG_KMS("buffer is to small\n");
+		DRM_DEBUG_KMS("buffer is too small\n");
 		ret = -ENOMEM;
 		goto fail;
 	}
@@ -8126,9 +8220,10 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 	if (intel_crtc->cursor_bo) {
 		if (!INTEL_INFO(dev)->cursor_needs_physical)
 			i915_gem_object_unpin_from_display_plane(intel_crtc->cursor_bo);
-		drm_gem_object_unreference(&intel_crtc->cursor_bo->base);
 	}
 
+	i915_gem_track_fb(intel_crtc->cursor_bo, obj,
+			  INTEL_FRONTBUFFER_CURSOR(pipe));
 	mutex_unlock(&dev->struct_mutex);
 
 	old_width = intel_crtc->cursor_width;
@@ -8144,6 +8239,8 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 		intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
 	}
 
+	intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_CURSOR(pipe));
+
 	return 0;
 fail_unpin:
 	i915_gem_object_unpin_from_display_plane(obj);
@@ -8154,19 +8251,6 @@ fail:
 	return ret;
 }
 
-static int intel_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
-{
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-
-	intel_crtc->cursor_x = clamp_t(int, x, SHRT_MIN, SHRT_MAX);
-	intel_crtc->cursor_y = clamp_t(int, y, SHRT_MIN, SHRT_MAX);
-
-	if (intel_crtc->active)
-		intel_crtc_update_cursor(crtc, intel_crtc->cursor_bo != NULL);
-
-	return 0;
-}
-
 static void intel_crtc_gamma_set(struct drm_crtc *crtc, u16 *red, u16 *green,
 				 u16 *blue, uint32_t start, uint32_t size)
 {
@@ -8667,12 +8751,10 @@ struct drm_display_mode *intel_crtc_mode_get(struct drm_device *dev,
 	return mode;
 }
 
-static void intel_increase_pllclock(struct drm_crtc *crtc)
+static void intel_increase_pllclock(struct drm_device *dev,
+				    enum pipe pipe)
 {
-	struct drm_device *dev = crtc->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
 	int dpll_reg = DPLL(pipe);
 	int dpll;
 
@@ -8773,28 +8855,179 @@ out:
 	intel_runtime_pm_put(dev_priv);
 }
 
-void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
-			struct intel_engine_cs *ring)
+
+/**
+ * intel_mark_fb_busy - mark given planes as busy
+ * @dev: DRM device
+ * @frontbuffer_bits: bits for the affected planes
+ * @ring: optional ring for asynchronous commands
+ *
+ * This function gets called every time the screen contents change. It can be
+ * used to keep e.g. the update rate at the nominal refresh rate with DRRS.
+ */
+static void intel_mark_fb_busy(struct drm_device *dev,
+			       unsigned frontbuffer_bits,
+			       struct intel_engine_cs *ring)
 {
-	struct drm_device *dev = obj->base.dev;
-	struct drm_crtc *crtc;
+	enum pipe pipe;
 
 	if (!i915.powersave)
 		return;
 
-	for_each_crtc(dev, crtc) {
-		if (!crtc->primary->fb)
-			continue;
-
-		if (to_intel_framebuffer(crtc->primary->fb)->obj != obj)
+	for_each_pipe(pipe) {
+		if (!(frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(pipe)))
 			continue;
 
-		intel_increase_pllclock(crtc);
+		intel_increase_pllclock(dev, pipe);
 		if (ring && intel_fbc_enabled(dev))
 			ring->fbc_dirty = true;
 	}
 }
 
+/**
+ * intel_fb_obj_invalidate - invalidate frontbuffer object
+ * @obj: GEM object to invalidate
+ * @ring: set for asynchronous rendering
+ *
+ * This function gets called every time rendering on the given object starts and
+ * frontbuffer caching (fbc, low refresh rate for DRRS, panel self refresh) must
+ * be invalidated. If @ring is non-NULL any subsequent invalidation will be delayed
+ * until the rendering completes or a flip on this frontbuffer plane is
+ * scheduled.
+ */
+void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
+			     struct intel_engine_cs *ring)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	if (!obj->frontbuffer_bits)
+		return;
+
+	if (ring) {
+		mutex_lock(&dev_priv->fb_tracking.lock);
+		dev_priv->fb_tracking.busy_bits
+			|= obj->frontbuffer_bits;
+		dev_priv->fb_tracking.flip_bits
+			&= ~obj->frontbuffer_bits;
+		mutex_unlock(&dev_priv->fb_tracking.lock);
+	}
+
+	intel_mark_fb_busy(dev, obj->frontbuffer_bits, ring);
+
+	intel_edp_psr_exit(dev);
+}
+
+/**
+ * intel_frontbuffer_flush - flush frontbuffer
+ * @dev: DRM device
+ * @frontbuffer_bits: frontbuffer plane tracking bits
+ *
+ * This function gets called every time rendering on the given planes has
+ * completed and frontbuffer caching can be started again. Flushes will get
+ * delayed if they're blocked by some oustanding asynchronous rendering.
+ *
+ * Can be called without any locks held.
+ */
+void intel_frontbuffer_flush(struct drm_device *dev,
+			     unsigned frontbuffer_bits)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Delay flushing when rings are still busy.*/
+	mutex_lock(&dev_priv->fb_tracking.lock);
+	frontbuffer_bits &= ~dev_priv->fb_tracking.busy_bits;
+	mutex_unlock(&dev_priv->fb_tracking.lock);
+
+	intel_mark_fb_busy(dev, frontbuffer_bits, NULL);
+
+	intel_edp_psr_exit(dev);
+}
+
+/**
+ * intel_fb_obj_flush - flush frontbuffer object
+ * @obj: GEM object to flush
+ * @retire: set when retiring asynchronous rendering
+ *
+ * This function gets called every time rendering on the given object has
+ * completed and frontbuffer caching can be started again. If @retire is true
+ * then any delayed flushes will be unblocked.
+ */
+void intel_fb_obj_flush(struct drm_i915_gem_object *obj,
+			bool retire)
+{
+	struct drm_device *dev = obj->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned frontbuffer_bits;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	if (!obj->frontbuffer_bits)
+		return;
+
+	frontbuffer_bits = obj->frontbuffer_bits;
+
+	if (retire) {
+		mutex_lock(&dev_priv->fb_tracking.lock);
+		/* Filter out new bits since rendering started. */
+		frontbuffer_bits &= dev_priv->fb_tracking.busy_bits;
+
+		dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
+		mutex_unlock(&dev_priv->fb_tracking.lock);
+	}
+
+	intel_frontbuffer_flush(dev, frontbuffer_bits);
+}
+
+/**
+ * intel_frontbuffer_flip_prepare - prepare asnychronous frontbuffer flip
+ * @dev: DRM device
+ * @frontbuffer_bits: frontbuffer plane tracking bits
+ *
+ * This function gets called after scheduling a flip on @obj. The actual
+ * frontbuffer flushing will be delayed until completion is signalled with
+ * intel_frontbuffer_flip_complete. If an invalidate happens in between this
+ * flush will be cancelled.
+ *
+ * Can be called without any locks held.
+ */
+void intel_frontbuffer_flip_prepare(struct drm_device *dev,
+				    unsigned frontbuffer_bits)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	mutex_lock(&dev_priv->fb_tracking.lock);
+	dev_priv->fb_tracking.flip_bits
+		|= frontbuffer_bits;
+	mutex_unlock(&dev_priv->fb_tracking.lock);
+}
+
+/**
+ * intel_frontbuffer_flip_complete - complete asynchronous frontbuffer flush
+ * @dev: DRM device
+ * @frontbuffer_bits: frontbuffer plane tracking bits
+ *
+ * This function gets called after the flip has been latched and will complete
+ * on the next vblank. It will execute the fush if it hasn't been cancalled yet.
+ *
+ * Can be called without any locks held.
+ */
+void intel_frontbuffer_flip_complete(struct drm_device *dev,
+				     unsigned frontbuffer_bits)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	mutex_lock(&dev_priv->fb_tracking.lock);
+	/* Mask any cancelled flips. */
+	frontbuffer_bits &= dev_priv->fb_tracking.flip_bits;
+	dev_priv->fb_tracking.flip_bits &= ~frontbuffer_bits;
+	mutex_unlock(&dev_priv->fb_tracking.lock);
+
+	intel_frontbuffer_flush(dev, frontbuffer_bits);
+}
+
 static void intel_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -8812,8 +9045,6 @@ static void intel_crtc_destroy(struct drm_crtc *crtc)
 		kfree(work);
 	}
 
-	intel_crtc_cursor_set(crtc, NULL, 0, 0, 0);
-
 	drm_crtc_cleanup(crtc);
 
 	kfree(intel_crtc);
@@ -8824,6 +9055,7 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 	struct intel_unpin_work *work =
 		container_of(__work, struct intel_unpin_work, work);
 	struct drm_device *dev = work->crtc->dev;
+	enum pipe pipe = to_intel_crtc(work->crtc)->pipe;
 
 	mutex_lock(&dev->struct_mutex);
 	intel_unpin_fb_obj(work->old_fb_obj);
@@ -8833,6 +9065,8 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 	intel_update_fbc(dev);
 	mutex_unlock(&dev->struct_mutex);
 
+	intel_frontbuffer_flip_complete(dev, INTEL_FRONTBUFFER_PRIMARY(pipe));
+
 	BUG_ON(atomic_read(&to_intel_crtc(work->crtc)->unpin_work_count) == 0);
 	atomic_dec(&to_intel_crtc(work->crtc)->unpin_work_count);
 
@@ -9202,6 +9436,147 @@ 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,
@@ -9222,6 +9597,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	struct drm_framebuffer *old_fb = crtc->primary->fb;
 	struct drm_i915_gem_object *obj = to_intel_framebuffer(fb)->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	enum pipe pipe = intel_crtc->pipe;
 	struct intel_unpin_work *work;
 	struct intel_engine_cs *ring;
 	unsigned long flags;
@@ -9290,7 +9666,7 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 	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;
+		work->flip_count = I915_READ(PIPE_FLIPCOUNT_GM45(pipe)) + 1;
 
 	if (IS_VALLEYVIEW(dev)) {
 		ring = &dev_priv->ring[BCS];
@@ -9309,12 +9685,20 @@ 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;
 
+	i915_gem_track_fb(work->old_fb_obj, obj,
+			  INTEL_FRONTBUFFER_PRIMARY(pipe));
+
 	intel_disable_fbc(dev);
-	intel_mark_fb_busy(obj, NULL);
+	intel_frontbuffer_flip_prepare(dev, INTEL_FRONTBUFFER_PRIMARY(pipe));
 	mutex_unlock(&dev->struct_mutex);
 
 	trace_i915_flip_request(intel_crtc->plane, obj);
@@ -9344,7 +9728,7 @@ out_hang:
 		intel_crtc_wait_for_pending_flips(crtc);
 		ret = intel_pipe_set_base(crtc, crtc->x, crtc->y, fb);
 		if (ret == 0 && event)
-			drm_send_vblank_event(dev, intel_crtc->pipe, event);
+			drm_send_vblank_event(dev, pipe, event);
 	}
 	return ret;
 }
@@ -10379,10 +10763,13 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 	 */
 	for_each_intel_crtc_masked(dev, modeset_pipes, intel_crtc) {
 		struct drm_framebuffer *old_fb;
+		struct drm_i915_gem_object *old_obj = NULL;
+		struct drm_i915_gem_object *obj =
+			to_intel_framebuffer(fb)->obj;
 
 		mutex_lock(&dev->struct_mutex);
 		ret = intel_pin_and_fence_fb_obj(dev,
-						 to_intel_framebuffer(fb)->obj,
+						 obj,
 						 NULL);
 		if (ret != 0) {
 			DRM_ERROR("pin & fence failed\n");
@@ -10390,8 +10777,12 @@ static int __intel_set_mode(struct drm_crtc *crtc,
 			goto done;
 		}
 		old_fb = crtc->primary->fb;
-		if (old_fb)
-			intel_unpin_fb_obj(to_intel_framebuffer(old_fb)->obj);
+		if (old_fb) {
+			old_obj = to_intel_framebuffer(old_fb)->obj;
+			intel_unpin_fb_obj(old_obj);
+		}
+		i915_gem_track_fb(old_obj, obj,
+				  INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe));
 		mutex_unlock(&dev->struct_mutex);
 
 		crtc->primary->fb = fb;
@@ -10563,12 +10954,17 @@ intel_set_config_compute_mode_changes(struct drm_mode_set *set,
 	if (is_crtc_connector_off(set)) {
 		config->mode_changed = true;
 	} else if (set->crtc->primary->fb != set->fb) {
-		/* If we have no fb then treat it as a full mode set */
+		/*
+		 * If we have no fb, we can only flip as long as the crtc is
+		 * active, otherwise we need a full mode set.  The crtc may
+		 * be active if we've only disabled the primary plane, or
+		 * in fastboot situations.
+		 */
 		if (set->crtc->primary->fb == NULL) {
 			struct intel_crtc *intel_crtc =
 				to_intel_crtc(set->crtc);
 
-			if (intel_crtc->active && i915.fastboot) {
+			if (intel_crtc->active) {
 				DRM_DEBUG_KMS("crtc has no fb, will flip\n");
 				config->fb_changed = true;
 			} else {
@@ -10806,10 +11202,24 @@ static int intel_crtc_set_config(struct drm_mode_set *set)
 		ret = intel_set_mode(set->crtc, set->mode,
 				     set->x, set->y, set->fb);
 	} else if (config->fb_changed) {
+		struct drm_i915_private *dev_priv = dev->dev_private;
+		struct intel_crtc *intel_crtc = to_intel_crtc(set->crtc);
+
 		intel_crtc_wait_for_pending_flips(set->crtc);
 
 		ret = intel_pipe_set_base(set->crtc,
 					  set->x, set->y, set->fb);
+
+		/*
+		 * We need to make sure the primary plane is re-enabled if it
+		 * has previously been turned off.
+		 */
+		if (!intel_crtc->primary_enabled && ret == 0) {
+			WARN_ON(!intel_crtc->active);
+			intel_enable_primary_hw_plane(dev_priv, intel_crtc->plane,
+						      intel_crtc->pipe);
+		}
+
 		/*
 		 * In the fastboot case this may be our only check of the
 		 * state after boot.  It would be better to only do it on
@@ -10850,8 +11260,6 @@ out_config:
 }
 
 static const struct drm_crtc_funcs intel_crtc_funcs = {
-	.cursor_set = intel_crtc_cursor_set,
-	.cursor_move = intel_crtc_cursor_move,
 	.gamma_set = intel_crtc_gamma_set,
 	.set_config = intel_crtc_set_config,
 	.destroy = intel_crtc_destroy,
@@ -10959,17 +11367,318 @@ static void intel_shared_dpll_init(struct drm_device *dev)
 	BUG_ON(dev_priv->num_shared_dpll > I915_NUM_PLLS);
 }
 
+static int
+intel_primary_plane_disable(struct drm_plane *plane)
+{
+	struct drm_device *dev = plane->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct intel_crtc *intel_crtc;
+
+	if (!plane->fb)
+		return 0;
+
+	BUG_ON(!plane->crtc);
+
+	intel_crtc = to_intel_crtc(plane->crtc);
+
+	/*
+	 * Even though we checked plane->fb above, it's still possible that
+	 * the primary plane has been implicitly disabled because the crtc
+	 * coordinates given weren't visible, or because we detected
+	 * that it was 100% covered by a sprite plane.  Or, the CRTC may be
+	 * off and we've set a fb, but haven't actually turned on the CRTC yet.
+	 * In either case, we need to unpin the FB and let the fb pointer get
+	 * updated, but otherwise we don't need to touch the hardware.
+	 */
+	if (!intel_crtc->primary_enabled)
+		goto disable_unpin;
+
+	intel_crtc_wait_for_pending_flips(plane->crtc);
+	intel_disable_primary_hw_plane(dev_priv, intel_plane->plane,
+				       intel_plane->pipe);
+disable_unpin:
+	i915_gem_track_fb(to_intel_framebuffer(plane->fb)->obj, NULL,
+			  INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe));
+	intel_unpin_fb_obj(to_intel_framebuffer(plane->fb)->obj);
+	plane->fb = NULL;
+
+	return 0;
+}
+
+static int
+intel_primary_plane_setplane(struct drm_plane *plane, struct drm_crtc *crtc,
+			     struct drm_framebuffer *fb, int crtc_x, int crtc_y,
+			     unsigned int crtc_w, unsigned int crtc_h,
+			     uint32_t src_x, uint32_t src_y,
+			     uint32_t src_w, uint32_t src_h)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_plane *intel_plane = to_intel_plane(plane);
+	struct drm_i915_gem_object *obj, *old_obj = NULL;
+	struct drm_rect dest = {
+		/* integer pixels */
+		.x1 = crtc_x,
+		.y1 = crtc_y,
+		.x2 = crtc_x + crtc_w,
+		.y2 = crtc_y + crtc_h,
+	};
+	struct drm_rect src = {
+		/* 16.16 fixed point */
+		.x1 = src_x,
+		.y1 = src_y,
+		.x2 = src_x + src_w,
+		.y2 = src_y + src_h,
+	};
+	const struct drm_rect clip = {
+		/* integer pixels */
+		.x2 = intel_crtc->active ? intel_crtc->config.pipe_src_w : 0,
+		.y2 = intel_crtc->active ? intel_crtc->config.pipe_src_h : 0,
+	};
+	bool visible;
+	int ret;
+
+	ret = drm_plane_helper_check_update(plane, crtc, fb,
+					    &src, &dest, &clip,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    false, true, &visible);
+
+	if (ret)
+		return ret;
+
+	if (plane->fb)
+		old_obj = to_intel_framebuffer(plane->fb)->obj;
+	obj = to_intel_framebuffer(fb)->obj;
+
+	/*
+	 * If the CRTC isn't enabled, we're just pinning the framebuffer,
+	 * updating the fb pointer, and returning without touching the
+	 * hardware.  This allows us to later do a drmModeSetCrtc with fb=-1 to
+	 * turn on the display with all planes setup as desired.
+	 */
+	if (!crtc->enabled) {
+		/*
+		 * If we already called setplane while the crtc was disabled,
+		 * we may have an fb pinned; unpin it.
+		 */
+		if (plane->fb)
+			intel_unpin_fb_obj(old_obj);
+
+		i915_gem_track_fb(old_obj, obj,
+				  INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe));
+
+		/* Pin and return without programming hardware */
+		return intel_pin_and_fence_fb_obj(dev, obj, NULL);
+	}
+
+	intel_crtc_wait_for_pending_flips(crtc);
+
+	/*
+	 * If clipping results in a non-visible primary plane, we'll disable
+	 * the primary plane.  Note that this is a bit different than what
+	 * happens if userspace explicitly disables the plane by passing fb=0
+	 * because plane->fb still gets set and pinned.
+	 */
+	if (!visible) {
+		/*
+		 * Try to pin the new fb first so that we can bail out if we
+		 * fail.
+		 */
+		if (plane->fb != fb) {
+			ret = intel_pin_and_fence_fb_obj(dev, obj, NULL);
+			if (ret)
+				return ret;
+		}
+
+		i915_gem_track_fb(old_obj, obj,
+				  INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe));
+
+		if (intel_crtc->primary_enabled)
+			intel_disable_primary_hw_plane(dev_priv,
+						       intel_plane->plane,
+						       intel_plane->pipe);
+
+
+		if (plane->fb != fb)
+			if (plane->fb)
+				intel_unpin_fb_obj(old_obj);
+
+		return 0;
+	}
+
+	ret = intel_pipe_set_base(crtc, src.x1, src.y1, fb);
+	if (ret)
+		return ret;
+
+	if (!intel_crtc->primary_enabled)
+		intel_enable_primary_hw_plane(dev_priv, intel_crtc->plane,
+					      intel_crtc->pipe);
+
+	return 0;
+}
+
+/* Common destruction function for both primary and cursor planes */
+static void intel_plane_destroy(struct drm_plane *plane)
+{
+	struct intel_plane *intel_plane = to_intel_plane(plane);
+	drm_plane_cleanup(plane);
+	kfree(intel_plane);
+}
+
+static const struct drm_plane_funcs intel_primary_plane_funcs = {
+	.update_plane = intel_primary_plane_setplane,
+	.disable_plane = intel_primary_plane_disable,
+	.destroy = intel_plane_destroy,
+};
+
+static struct drm_plane *intel_primary_plane_create(struct drm_device *dev,
+						    int pipe)
+{
+	struct intel_plane *primary;
+	const uint32_t *intel_primary_formats;
+	int num_formats;
+
+	primary = kzalloc(sizeof(*primary), GFP_KERNEL);
+	if (primary == NULL)
+		return NULL;
+
+	primary->can_scale = false;
+	primary->max_downscale = 1;
+	primary->pipe = pipe;
+	primary->plane = pipe;
+	if (HAS_FBC(dev) && INTEL_INFO(dev)->gen < 4)
+		primary->plane = !pipe;
+
+	if (INTEL_INFO(dev)->gen <= 3) {
+		intel_primary_formats = intel_primary_formats_gen2;
+		num_formats = ARRAY_SIZE(intel_primary_formats_gen2);
+	} else {
+		intel_primary_formats = intel_primary_formats_gen4;
+		num_formats = ARRAY_SIZE(intel_primary_formats_gen4);
+	}
+
+	drm_universal_plane_init(dev, &primary->base, 0,
+				 &intel_primary_plane_funcs,
+				 intel_primary_formats, num_formats,
+				 DRM_PLANE_TYPE_PRIMARY);
+	return &primary->base;
+}
+
+static int
+intel_cursor_plane_disable(struct drm_plane *plane)
+{
+	if (!plane->fb)
+		return 0;
+
+	BUG_ON(!plane->crtc);
+
+	return intel_crtc_cursor_set_obj(plane->crtc, NULL, 0, 0);
+}
+
+static int
+intel_cursor_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+			  struct drm_framebuffer *fb, int crtc_x, int crtc_y,
+			  unsigned int crtc_w, unsigned int crtc_h,
+			  uint32_t src_x, uint32_t src_y,
+			  uint32_t src_w, uint32_t src_h)
+{
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	struct drm_i915_gem_object *obj = intel_fb->obj;
+	struct drm_rect dest = {
+		/* integer pixels */
+		.x1 = crtc_x,
+		.y1 = crtc_y,
+		.x2 = crtc_x + crtc_w,
+		.y2 = crtc_y + crtc_h,
+	};
+	struct drm_rect src = {
+		/* 16.16 fixed point */
+		.x1 = src_x,
+		.y1 = src_y,
+		.x2 = src_x + src_w,
+		.y2 = src_y + src_h,
+	};
+	const struct drm_rect clip = {
+		/* integer pixels */
+		.x2 = intel_crtc->config.pipe_src_w,
+		.y2 = intel_crtc->config.pipe_src_h,
+	};
+	bool visible;
+	int ret;
+
+	ret = drm_plane_helper_check_update(plane, crtc, fb,
+					    &src, &dest, &clip,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    DRM_PLANE_HELPER_NO_SCALING,
+					    true, true, &visible);
+	if (ret)
+		return ret;
+
+	crtc->cursor_x = crtc_x;
+	crtc->cursor_y = crtc_y;
+	if (fb != crtc->cursor->fb) {
+		return intel_crtc_cursor_set_obj(crtc, obj, crtc_w, crtc_h);
+	} else {
+		intel_crtc_update_cursor(crtc, visible);
+		return 0;
+	}
+}
+static const struct drm_plane_funcs intel_cursor_plane_funcs = {
+	.update_plane = intel_cursor_plane_update,
+	.disable_plane = intel_cursor_plane_disable,
+	.destroy = intel_plane_destroy,
+};
+
+static struct drm_plane *intel_cursor_plane_create(struct drm_device *dev,
+						   int pipe)
+{
+	struct intel_plane *cursor;
+
+	cursor = kzalloc(sizeof(*cursor), GFP_KERNEL);
+	if (cursor == NULL)
+		return NULL;
+
+	cursor->can_scale = false;
+	cursor->max_downscale = 1;
+	cursor->pipe = pipe;
+	cursor->plane = pipe;
+
+	drm_universal_plane_init(dev, &cursor->base, 0,
+				 &intel_cursor_plane_funcs,
+				 intel_cursor_formats,
+				 ARRAY_SIZE(intel_cursor_formats),
+				 DRM_PLANE_TYPE_CURSOR);
+	return &cursor->base;
+}
+
 static void intel_crtc_init(struct drm_device *dev, int pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_crtc *intel_crtc;
-	int i;
+	struct drm_plane *primary = NULL;
+	struct drm_plane *cursor = NULL;
+	int i, ret;
 
 	intel_crtc = kzalloc(sizeof(*intel_crtc), GFP_KERNEL);
 	if (intel_crtc == NULL)
 		return;
 
-	drm_crtc_init(dev, &intel_crtc->base, &intel_crtc_funcs);
+	primary = intel_primary_plane_create(dev, pipe);
+	if (!primary)
+		goto fail;
+
+	cursor = intel_cursor_plane_create(dev, pipe);
+	if (!cursor)
+		goto fail;
+
+	ret = drm_crtc_init_with_planes(dev, &intel_crtc->base, primary,
+					cursor, &intel_crtc_funcs);
+	if (ret)
+		goto fail;
 
 	drm_mode_crtc_set_gamma_size(&intel_crtc->base, 256);
 	for (i = 0; i < 256; i++) {
@@ -10980,7 +11689,7 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 
 	/*
 	 * On gen2/3 only plane A can do fbc, but the panel fitter and lvds port
-	 * is hooked to plane B. Hence we want plane A feeding pipe B.
+	 * is hooked to pipe B. Hence we want plane A feeding pipe B.
 	 */
 	intel_crtc->pipe = pipe;
 	intel_crtc->plane = pipe;
@@ -11002,6 +11711,14 @@ static void intel_crtc_init(struct drm_device *dev, int pipe)
 	drm_crtc_helper_add(&intel_crtc->base, &intel_helper_funcs);
 
 	WARN_ON(drm_crtc_index(&intel_crtc->base) != intel_crtc->pipe);
+	return;
+
+fail:
+	if (primary)
+		drm_plane_cleanup(primary);
+	if (cursor)
+		drm_plane_cleanup(cursor);
+	kfree(intel_crtc);
 }
 
 enum pipe intel_get_pipe_from_connector(struct intel_connector *connector)
@@ -11236,6 +11953,8 @@ static void intel_setup_outputs(struct drm_device *dev)
 	if (SUPPORTS_TV(dev))
 		intel_tv_init(dev);
 
+	intel_edp_psr_init(dev);
+
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, base.head) {
 		encoder->base.possible_crtcs = encoder->crtc_mask;
 		encoder->base.possible_clones =
@@ -11249,11 +11968,14 @@ static void intel_setup_outputs(struct drm_device *dev)
 
 static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
+	struct drm_device *dev = fb->dev;
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 
 	drm_framebuffer_cleanup(fb);
+	mutex_lock(&dev->struct_mutex);
 	WARN_ON(!intel_fb->obj->framebuffer_references--);
-	drm_gem_object_unreference_unlocked(&intel_fb->obj->base);
+	drm_gem_object_unreference(&intel_fb->obj->base);
+	mutex_unlock(&dev->struct_mutex);
 	kfree(intel_fb);
 }
 
@@ -12266,7 +12988,6 @@ void intel_connector_unregister(struct intel_connector *intel_connector)
 void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_crtc *crtc;
 	struct drm_connector *connector;
 
 	/*
@@ -12286,14 +13007,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	intel_unregister_dsm_handler();
 
-	for_each_crtc(dev, crtc) {
-		/* Skip inactive CRTCs */
-		if (!crtc->primary->fb)
-			continue;
-
-		intel_increase_pllclock(crtc);
-	}
-
 	intel_disable_fbc(dev);
 
 	intel_disable_gt_powersave(dev);

drivers/gpu/drm/i915/intel_dp.c

@@ -1613,11 +1613,9 @@ static void intel_dp_get_config(struct intel_encoder *encoder,
 	}
 }
 
-static bool is_edp_psr(struct drm_device *dev)
+static bool is_edp_psr(struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
-	return dev_priv->psr.sink_support;
+	return intel_dp->psr_dpcd[0] & DP_PSR_IS_SUPPORTED;
 }
 
 static bool intel_edp_is_psr_enabled(struct drm_device *dev)
@@ -1665,7 +1663,7 @@ static void intel_edp_psr_setup(struct intel_dp *intel_dp)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct edp_vsc_psr psr_vsc;
 
-	if (intel_dp->psr_setup_done)
+	if (dev_priv->psr.setup_done)
 		return;
 
 	/* Prepare VSC packet as per EDP 1.3 spec, Table 3.10 */
@@ -1680,21 +1678,26 @@ static void intel_edp_psr_setup(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR_DEBUG_CTL(dev), EDP_PSR_DEBUG_MASK_MEMUP |
 		   EDP_PSR_DEBUG_MASK_HPD | EDP_PSR_DEBUG_MASK_LPSP);
 
-	intel_dp->psr_setup_done = true;
+	dev_priv->psr.setup_done = true;
 }
 
 static void intel_edp_psr_enable_sink(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t aux_clock_divider;
 	int precharge = 0x3;
 	int msg_size = 5;       /* Header(4) + Message(1) */
+	bool only_standby = false;
 
 	aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, 0);
 
+	if (IS_BROADWELL(dev) && dig_port->port != PORT_A)
+		only_standby = true;
+
 	/* Enable PSR in sink */
-	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT)
+	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT || only_standby)
 		drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
 				   DP_PSR_ENABLE & ~DP_PSR_MAIN_LINK_ACTIVE);
 	else
@@ -1713,18 +1716,24 @@ static void intel_edp_psr_enable_sink(struct intel_dp *intel_dp)
 
 static void intel_edp_psr_enable_source(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t max_sleep_time = 0x1f;
 	uint32_t idle_frames = 1;
 	uint32_t val = 0x0;
 	const uint32_t link_entry_time = EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES;
+	bool only_standby = false;
+
+	if (IS_BROADWELL(dev) && dig_port->port != PORT_A)
+		only_standby = true;
 
-	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT) {
+	if (intel_dp->psr_dpcd[1] & DP_PSR_NO_TRAIN_ON_EXIT || only_standby) {
 		val |= EDP_PSR_LINK_STANDBY;
 		val |= EDP_PSR_TP2_TP3_TIME_0us;
 		val |= EDP_PSR_TP1_TIME_0us;
 		val |= EDP_PSR_SKIP_AUX_EXIT;
+		val |= IS_BROADWELL(dev) ? BDW_PSR_SINGLE_FRAME : 0;
 	} else
 		val |= EDP_PSR_LINK_DISABLE;
 
@@ -1752,8 +1761,8 @@ static bool intel_edp_psr_match_conditions(struct intel_dp *intel_dp)
 		return false;
 	}
 
-	if ((intel_encoder->type != INTEL_OUTPUT_EDP) ||
-	    (dig_port->port != PORT_A)) {
+	if (IS_HASWELL(dev) && (intel_encoder->type != INTEL_OUTPUT_EDP ||
+				dig_port->port != PORT_A)) {
 		DRM_DEBUG_KMS("HSW ties PSR to DDI A (eDP)\n");
 		return false;
 	}
@@ -1782,6 +1791,10 @@ static bool intel_edp_psr_match_conditions(struct intel_dp *intel_dp)
 		return false;
 	}
 
+	/* Below limitations aren't valid for Broadwell */
+	if (IS_BROADWELL(dev))
+		goto out;
+
 	if (I915_READ(SPRCTL(intel_crtc->pipe)) & SPRITE_ENABLE) {
 		DRM_DEBUG_KMS("PSR condition failed: Sprite is Enabled\n");
 		return false;
@@ -1798,34 +1811,48 @@ static bool intel_edp_psr_match_conditions(struct intel_dp *intel_dp)
 		return false;
 	}
 
+ out:
 	dev_priv->psr.source_ok = true;
 	return true;
 }
 
 static void intel_edp_psr_do_enable(struct intel_dp *intel_dp)
 {
-	struct drm_device *dev = intel_dp_to_dev(intel_dp);
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (!intel_edp_psr_match_conditions(intel_dp) ||
-	    intel_edp_is_psr_enabled(dev))
+	if (intel_edp_is_psr_enabled(dev))
 		return;
 
-	/* Setup PSR once */
-	intel_edp_psr_setup(intel_dp);
-
 	/* Enable PSR on the panel */
 	intel_edp_psr_enable_sink(intel_dp);
 
 	/* Enable PSR on the host */
 	intel_edp_psr_enable_source(intel_dp);
+
+	dev_priv->psr.enabled = true;
+	dev_priv->psr.active = true;
 }
 
 void intel_edp_psr_enable(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 
-	if (intel_edp_psr_match_conditions(intel_dp) &&
-	    !intel_edp_is_psr_enabled(dev))
+	if (!HAS_PSR(dev)) {
+		DRM_DEBUG_KMS("PSR not supported on this platform\n");
+		return;
+	}
+
+	if (!is_edp_psr(intel_dp)) {
+		DRM_DEBUG_KMS("PSR not supported by this panel\n");
+		return;
+	}
+
+	/* Setup PSR once */
+	intel_edp_psr_setup(intel_dp);
+
+	if (intel_edp_psr_match_conditions(intel_dp))
 		intel_edp_psr_do_enable(intel_dp);
 }
 
@@ -1834,7 +1861,7 @@ void intel_edp_psr_disable(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	if (!intel_edp_is_psr_enabled(dev))
+	if (!dev_priv->psr.enabled)
 		return;
 
 	I915_WRITE(EDP_PSR_CTL(dev),
@@ -1844,10 +1871,15 @@ void intel_edp_psr_disable(struct intel_dp *intel_dp)
 	if (_wait_for((I915_READ(EDP_PSR_STATUS_CTL(dev)) &
 		       EDP_PSR_STATUS_STATE_MASK) == 0, 2000, 10))
 		DRM_ERROR("Timed out waiting for PSR Idle State\n");
+
+	dev_priv->psr.enabled = false;
 }
 
-void intel_edp_psr_update(struct drm_device *dev)
+static void intel_edp_psr_work(struct work_struct *work)
 {
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), psr.work.work);
+	struct drm_device *dev = dev_priv->dev;
 	struct intel_encoder *encoder;
 	struct intel_dp *intel_dp = NULL;
 
@@ -1855,17 +1887,52 @@ void intel_edp_psr_update(struct drm_device *dev)
 		if (encoder->type == INTEL_OUTPUT_EDP) {
 			intel_dp = enc_to_intel_dp(&encoder->base);
 
-			if (!is_edp_psr(dev))
-				return;
-
 			if (!intel_edp_psr_match_conditions(intel_dp))
 				intel_edp_psr_disable(intel_dp);
 			else
-				if (!intel_edp_is_psr_enabled(dev))
-					intel_edp_psr_do_enable(intel_dp);
+				intel_edp_psr_do_enable(intel_dp);
 		}
 }
 
+static void intel_edp_psr_inactivate(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	dev_priv->psr.active = false;
+
+	I915_WRITE(EDP_PSR_CTL(dev), I915_READ(EDP_PSR_CTL(dev))
+		   & ~EDP_PSR_ENABLE);
+}
+
+void intel_edp_psr_exit(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!HAS_PSR(dev))
+		return;
+
+	if (!dev_priv->psr.setup_done)
+		return;
+
+	cancel_delayed_work_sync(&dev_priv->psr.work);
+
+	if (dev_priv->psr.active)
+		intel_edp_psr_inactivate(dev);
+
+	schedule_delayed_work(&dev_priv->psr.work,
+			      msecs_to_jiffies(100));
+}
+
+void intel_edp_psr_init(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	if (!HAS_PSR(dev))
+		return;
+
+	INIT_DELAYED_WORK(&dev_priv->psr.work, intel_edp_psr_work);
+}
+
 static void intel_disable_dp(struct intel_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
@@ -2119,6 +2186,70 @@ static void chv_pre_enable_dp(struct intel_encoder *encoder)
 	vlv_wait_port_ready(dev_priv, dport);
 }
 
+static void chv_dp_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 val;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* program left/right clock distribution */
+	if (pipe != PIPE_B) {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA1_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA1_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+	} else {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA2_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA2_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+	}
+
+	/* program clock channel usage */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
+
+	/*
+	 * This a a bit weird since generally CL
+	 * matches the pipe, but here we need to
+	 * pick the CL based on the port.
+	 */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW19(ch));
+	if (pipe != PIPE_B)
+		val &= ~CHV_CMN_USEDCLKCHANNEL;
+	else
+		val |= CHV_CMN_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW19(ch), val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
 /*
  * Native read with retry for link status and receiver capability reads for
  * cases where the sink may still be asleep.
@@ -2156,18 +2287,14 @@ intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_
 				       DP_LINK_STATUS_SIZE) == DP_LINK_STATUS_SIZE;
 }
 
-/*
- * These are source-specific values; current Intel hardware supports
- * a maximum voltage of 800mV and a maximum pre-emphasis of 6dB
- */
-
+/* These are source-specific values. */
 static uint8_t
 intel_dp_voltage_max(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 
-	if (IS_VALLEYVIEW(dev) || IS_BROADWELL(dev))
+	if (IS_VALLEYVIEW(dev))
 		return DP_TRAIN_VOLTAGE_SWING_1200;
 	else if (IS_GEN7(dev) && port == PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_800;
@@ -2183,18 +2310,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 	struct drm_device *dev = intel_dp_to_dev(intel_dp);
 	enum port port = dp_to_dig_port(intel_dp)->port;
 
-	if (IS_BROADWELL(dev)) {
-		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_400:
-		case DP_TRAIN_VOLTAGE_SWING_600:
-			return DP_TRAIN_PRE_EMPHASIS_6;
-		case DP_TRAIN_VOLTAGE_SWING_800:
-			return DP_TRAIN_PRE_EMPHASIS_3_5;
-		case DP_TRAIN_VOLTAGE_SWING_1200:
-		default:
-			return DP_TRAIN_PRE_EMPHASIS_0;
-		}
-	} else if (IS_HASWELL(dev)) {
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
 		case DP_TRAIN_VOLTAGE_SWING_400:
 			return DP_TRAIN_PRE_EMPHASIS_9_5;
@@ -2666,41 +2782,6 @@ intel_hsw_signal_levels(uint8_t train_set)
 	}
 }
 
-static uint32_t
-intel_bdw_signal_levels(uint8_t train_set)
-{
-	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
-					 DP_TRAIN_PRE_EMPHASIS_MASK);
-	switch (signal_levels) {
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_400MV_0DB_BDW;	/* Sel0 */
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_3_5:
-		return DDI_BUF_EMP_400MV_3_5DB_BDW;	/* Sel1 */
-	case DP_TRAIN_VOLTAGE_SWING_400 | DP_TRAIN_PRE_EMPHASIS_6:
-		return DDI_BUF_EMP_400MV_6DB_BDW;	/* Sel2 */
-
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_600MV_0DB_BDW;	/* Sel3 */
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_3_5:
-		return DDI_BUF_EMP_600MV_3_5DB_BDW;	/* Sel4 */
-	case DP_TRAIN_VOLTAGE_SWING_600 | DP_TRAIN_PRE_EMPHASIS_6:
-		return DDI_BUF_EMP_600MV_6DB_BDW;	/* Sel5 */
-
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_800MV_0DB_BDW;	/* Sel6 */
-	case DP_TRAIN_VOLTAGE_SWING_800 | DP_TRAIN_PRE_EMPHASIS_3_5:
-		return DDI_BUF_EMP_800MV_3_5DB_BDW;	/* Sel7 */
-
-	case DP_TRAIN_VOLTAGE_SWING_1200 | DP_TRAIN_PRE_EMPHASIS_0:
-		return DDI_BUF_EMP_1200MV_0DB_BDW;	/* Sel8 */
-
-	default:
-		DRM_DEBUG_KMS("Unsupported voltage swing/pre-emphasis level:"
-			      "0x%x\n", signal_levels);
-		return DDI_BUF_EMP_400MV_0DB_BDW;	/* Sel0 */
-	}
-}
-
 /* Properly updates "DP" with the correct signal levels. */
 static void
 intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP)
@@ -2711,10 +2792,7 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp, uint32_t *DP)
 	uint32_t signal_levels, mask;
 	uint8_t train_set = intel_dp->train_set[0];
 
-	if (IS_BROADWELL(dev)) {
-		signal_levels = intel_bdw_signal_levels(train_set);
-		mask = DDI_BUF_EMP_MASK;
-	} else if (IS_HASWELL(dev)) {
+	if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		signal_levels = intel_hsw_signal_levels(train_set);
 		mask = DDI_BUF_EMP_MASK;
 	} else if (IS_CHERRYVIEW(dev)) {
@@ -4279,8 +4357,6 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 
 	intel_dp_aux_init(intel_dp, intel_connector);
 
-	intel_dp->psr_setup_done = false;
-
 	if (!intel_edp_init_connector(intel_dp, intel_connector, &power_seq)) {
 		drm_dp_aux_unregister(&intel_dp->aux);
 		if (is_edp(intel_dp)) {
@@ -4337,6 +4413,7 @@ intel_dp_init(struct drm_device *dev, int output_reg, enum port port)
 	intel_encoder->get_hw_state = intel_dp_get_hw_state;
 	intel_encoder->get_config = intel_dp_get_config;
 	if (IS_CHERRYVIEW(dev)) {
+		intel_encoder->pre_pll_enable = chv_dp_pre_pll_enable;
 		intel_encoder->pre_enable = chv_pre_enable_dp;
 		intel_encoder->enable = vlv_enable_dp;
 		intel_encoder->post_disable = chv_post_disable_dp;

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;
@@ -384,7 +389,6 @@ struct intel_crtc {
 
 	struct drm_i915_gem_object *cursor_bo;
 	uint32_t cursor_addr;
-	int16_t cursor_x, cursor_y;
 	int16_t cursor_width, cursor_height;
 	uint32_t cursor_cntl;
 	uint32_t cursor_base;
@@ -412,6 +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 {
@@ -428,7 +433,6 @@ struct intel_plane {
 	struct drm_i915_gem_object *obj;
 	bool can_scale;
 	int max_downscale;
-	u32 lut_r[1024], lut_g[1024], lut_b[1024];
 	int crtc_x, crtc_y;
 	unsigned int crtc_w, crtc_h;
 	uint32_t src_x, src_y;
@@ -537,7 +541,6 @@ struct intel_dp {
 	unsigned long last_power_cycle;
 	unsigned long last_power_on;
 	unsigned long last_backlight_off;
-	bool psr_setup_done;
 	bool use_tps3;
 	struct intel_connector *attached_connector;
 
@@ -721,8 +724,33 @@ bool intel_has_pending_fb_unpin(struct drm_device *dev);
 int intel_pch_rawclk(struct drm_device *dev);
 int valleyview_cur_cdclk(struct drm_i915_private *dev_priv);
 void intel_mark_busy(struct drm_device *dev);
-void intel_mark_fb_busy(struct drm_i915_gem_object *obj,
-			struct intel_engine_cs *ring);
+void intel_fb_obj_invalidate(struct drm_i915_gem_object *obj,
+			     struct intel_engine_cs *ring);
+void intel_frontbuffer_flip_prepare(struct drm_device *dev,
+				    unsigned frontbuffer_bits);
+void intel_frontbuffer_flip_complete(struct drm_device *dev,
+				     unsigned frontbuffer_bits);
+void intel_frontbuffer_flush(struct drm_device *dev,
+			     unsigned frontbuffer_bits);
+/**
+ * intel_frontbuffer_flip - prepare frontbuffer flip
+ * @dev: DRM device
+ * @frontbuffer_bits: frontbuffer plane tracking bits
+ *
+ * This function gets called after scheduling a flip on @obj. This is for
+ * synchronous plane updates which will happen on the next vblank and which will
+ * not get delayed by pending gpu rendering.
+ *
+ * Can be called without any locks held.
+ */
+static inline
+void intel_frontbuffer_flip(struct drm_device *dev,
+			    unsigned frontbuffer_bits)
+{
+	intel_frontbuffer_flush(dev, frontbuffer_bits);
+}
+
+void intel_fb_obj_flush(struct drm_i915_gem_object *obj, bool retire);
 void intel_mark_idle(struct drm_device *dev);
 void intel_crtc_restore_mode(struct drm_crtc *crtc);
 void intel_crtc_update_dpms(struct drm_crtc *crtc);
@@ -831,11 +859,13 @@ void intel_edp_panel_on(struct intel_dp *intel_dp);
 void intel_edp_panel_off(struct intel_dp *intel_dp);
 void intel_edp_psr_enable(struct intel_dp *intel_dp);
 void intel_edp_psr_disable(struct intel_dp *intel_dp);
-void intel_edp_psr_update(struct drm_device *dev);
 void intel_dp_set_drrs_state(struct drm_device *dev, int refresh_rate);
+void intel_edp_psr_exit(struct drm_device *dev);
+void intel_edp_psr_init(struct drm_device *dev);
+
 
 /* intel_dsi.c */
-bool intel_dsi_init(struct drm_device *dev);
+void intel_dsi_init(struct drm_device *dev);
 
 
 /* intel_dvo.c */
@@ -961,6 +991,7 @@ void intel_init_gt_powersave(struct drm_device *dev);
 void intel_cleanup_gt_powersave(struct drm_device *dev);
 void intel_enable_gt_powersave(struct drm_device *dev);
 void intel_disable_gt_powersave(struct drm_device *dev);
+void intel_suspend_gt_powersave(struct drm_device *dev);
 void intel_reset_gt_powersave(struct drm_device *dev);
 void ironlake_teardown_rc6(struct drm_device *dev);
 void gen6_update_ring_freq(struct drm_device *dev);

drivers/gpu/drm/i915/intel_dsi.c

@@ -657,7 +657,7 @@ static const struct drm_connector_funcs intel_dsi_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 };
 
-bool intel_dsi_init(struct drm_device *dev)
+void intel_dsi_init(struct drm_device *dev)
 {
 	struct intel_dsi *intel_dsi;
 	struct intel_encoder *intel_encoder;
@@ -673,29 +673,29 @@ bool intel_dsi_init(struct drm_device *dev)
 
 	/* There is no detection method for MIPI so rely on VBT */
 	if (!dev_priv->vbt.has_mipi)
-		return false;
+		return;
+
+	if (IS_VALLEYVIEW(dev)) {
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
+	} else {
+		DRM_ERROR("Unsupported Mipi device to reg base");
+		return;
+	}
 
 	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
 	if (!intel_dsi)
-		return false;
+		return;
 
 	intel_connector = kzalloc(sizeof(*intel_connector), GFP_KERNEL);
 	if (!intel_connector) {
 		kfree(intel_dsi);
-		return false;
+		return;
 	}
 
 	intel_encoder = &intel_dsi->base;
 	encoder = &intel_encoder->base;
 	intel_dsi->attached_connector = intel_connector;
 
-	if (IS_VALLEYVIEW(dev)) {
-		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
-	} else {
-		DRM_ERROR("Unsupported Mipi device to reg base");
-		return false;
-	}
-
 	connector = &intel_connector->base;
 
 	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI);
@@ -753,12 +753,10 @@ bool intel_dsi_init(struct drm_device *dev)
 	fixed_mode->type |= DRM_MODE_TYPE_PREFERRED;
 	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
 
-	return true;
+	return;
 
 err:
 	drm_encoder_cleanup(&intel_encoder->base);
 	kfree(intel_dsi);
 	kfree(intel_connector);
-
-	return false;
 }

drivers/gpu/drm/i915/intel_dsi_panel_vbt.c

@@ -143,7 +143,7 @@ static u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi, u8 *data)
 	case MIPI_DSI_DCS_LONG_WRITE:
 		dsi_vc_dcs_write(intel_dsi, vc, data, len);
 		break;
-	};
+	}
 
 	data += len;
 
@@ -294,7 +294,8 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	intel_dsi->rst_timer_val = mipi_config->device_reset_timer;
 	intel_dsi->init_count = mipi_config->master_init_timer;
 	intel_dsi->bw_timer = mipi_config->dbi_bw_timer;
-	intel_dsi->video_frmt_cfg_bits = mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
+	intel_dsi->video_frmt_cfg_bits =
+		mipi_config->bta_enabled ? DISABLE_VIDEO_BTA : 0;
 
 	switch (intel_dsi->escape_clk_div) {
 	case 0:
@@ -351,7 +352,8 @@ static bool generic_init(struct intel_dsi_device *dsi)
 	 *
 	 * prepare count
 	 */
-	ths_prepare_ns = max(mipi_config->ths_prepare, mipi_config->tclk_prepare);
+	ths_prepare_ns = max(mipi_config->ths_prepare,
+			     mipi_config->tclk_prepare);
 	prepare_cnt = DIV_ROUND_UP(ths_prepare_ns * ui_den, ui_num * 2);
 
 	/* exit zero count */

drivers/gpu/drm/i915/intel_dvo.c

@@ -112,7 +112,15 @@ static struct intel_dvo *intel_attached_dvo(struct drm_connector *connector)
 
 static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 {
+	struct drm_device *dev = connector->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dvo *intel_dvo = intel_attached_dvo(&connector->base);
+	u32 tmp;
+
+	tmp = I915_READ(intel_dvo->dev.dvo_reg);
+
+	if (!(tmp & DVO_ENABLE))
+		return false;
 
 	return intel_dvo->dev.dev_ops->get_hw_state(&intel_dvo->dev);
 }

drivers/gpu/drm/i915/intel_fbdev.c

@@ -43,10 +43,36 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
+static int intel_fbdev_set_par(struct fb_info *info)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+	struct intel_fbdev *ifbdev =
+		container_of(fb_helper, struct intel_fbdev, helper);
+	int ret;
+
+	ret = drm_fb_helper_set_par(info);
+
+	if (ret == 0) {
+		/*
+		 * FIXME: fbdev presumes that all callbacks also work from
+		 * atomic contexts and relies on that for emergency oops
+		 * printing. KMS totally doesn't do that and the locking here is
+		 * by far not the only place this goes wrong.  Ignore this for
+		 * now until we solve this for real.
+		 */
+		mutex_lock(&fb_helper->dev->struct_mutex);
+		ret = i915_gem_object_set_to_gtt_domain(ifbdev->fb->obj,
+							true);
+		mutex_unlock(&fb_helper->dev->struct_mutex);
+	}
+
+	return ret;
+}
+
 static struct fb_ops intelfb_ops = {
 	.owner = THIS_MODULE,
 	.fb_check_var = drm_fb_helper_check_var,
-	.fb_set_par = drm_fb_helper_set_par,
+	.fb_set_par = intel_fbdev_set_par,
 	.fb_fillrect = cfb_fillrect,
 	.fb_copyarea = cfb_copyarea,
 	.fb_imageblit = cfb_imageblit,
@@ -417,7 +443,7 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		}
 		crtcs[i] = new_crtc;
 
-		DRM_DEBUG_KMS("connector %s on pipe %d [CRTC:%d]: %dx%d%s\n",
+		DRM_DEBUG_KMS("connector %s on pipe %c [CRTC:%d]: %dx%d%s\n",
 			      connector->name,
 			      pipe_name(to_intel_crtc(encoder->crtc)->pipe),
 			      encoder->crtc->base.id,

drivers/gpu/drm/i915/intel_hdmi.c

@@ -1229,6 +1229,70 @@ static void vlv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->dpio_lock);
 }
 
+static void chv_hdmi_pre_pll_enable(struct intel_encoder *encoder)
+{
+	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_crtc *intel_crtc =
+		to_intel_crtc(encoder->base.crtc);
+	enum dpio_channel ch = vlv_dport_to_channel(dport);
+	enum pipe pipe = intel_crtc->pipe;
+	u32 val;
+
+	mutex_lock(&dev_priv->dpio_lock);
+
+	/* program left/right clock distribution */
+	if (pipe != PIPE_B) {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW5_CH0);
+		val &= ~(CHV_BUFLEFTENA1_MASK | CHV_BUFRIGHTENA1_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA1_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA1_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW5_CH0, val);
+	} else {
+		val = vlv_dpio_read(dev_priv, pipe, _CHV_CMN_DW1_CH1);
+		val &= ~(CHV_BUFLEFTENA2_MASK | CHV_BUFRIGHTENA2_MASK);
+		if (ch == DPIO_CH0)
+			val |= CHV_BUFLEFTENA2_FORCE;
+		if (ch == DPIO_CH1)
+			val |= CHV_BUFRIGHTENA2_FORCE;
+		vlv_dpio_write(dev_priv, pipe, _CHV_CMN_DW1_CH1, val);
+	}
+
+	/* program clock channel usage */
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS01_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS01_DW8(ch), val);
+
+	val = vlv_dpio_read(dev_priv, pipe, VLV_PCS23_DW8(ch));
+	val |= CHV_PCS_USEDCLKCHANNEL_OVRRIDE;
+	if (pipe != PIPE_B)
+		val &= ~CHV_PCS_USEDCLKCHANNEL;
+	else
+		val |= CHV_PCS_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, VLV_PCS23_DW8(ch), val);
+
+	/*
+	 * This a a bit weird since generally CL
+	 * matches the pipe, but here we need to
+	 * pick the CL based on the port.
+	 */
+	val = vlv_dpio_read(dev_priv, pipe, CHV_CMN_DW19(ch));
+	if (pipe != PIPE_B)
+		val &= ~CHV_CMN_USEDCLKCHANNEL;
+	else
+		val |= CHV_CMN_USEDCLKCHANNEL;
+	vlv_dpio_write(dev_priv, pipe, CHV_CMN_DW19(ch), val);
+
+	mutex_unlock(&dev_priv->dpio_lock);
+}
+
 static void vlv_hdmi_post_disable(struct intel_encoder *encoder)
 {
 	struct intel_digital_port *dport = enc_to_dig_port(&encoder->base);
@@ -1528,6 +1592,7 @@ void intel_hdmi_init(struct drm_device *dev, int hdmi_reg, enum port port)
 	intel_encoder->get_hw_state = intel_hdmi_get_hw_state;
 	intel_encoder->get_config = intel_hdmi_get_config;
 	if (IS_CHERRYVIEW(dev)) {
+		intel_encoder->pre_pll_enable = chv_hdmi_pre_pll_enable;
 		intel_encoder->pre_enable = chv_hdmi_pre_enable;
 		intel_encoder->enable = vlv_enable_hdmi;
 		intel_encoder->post_disable = chv_hdmi_post_disable;

drivers/gpu/drm/i915/intel_overlay.c

@@ -415,6 +415,10 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay)
 	}
 
 	intel_overlay_release_old_vid_tail(overlay);
+
+
+	i915_gem_track_fb(overlay->old_vid_bo, NULL,
+			  INTEL_FRONTBUFFER_OVERLAY(overlay->crtc->pipe));
 	return 0;
 }
 
@@ -686,6 +690,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	bool scale_changed = false;
 	struct drm_device *dev = overlay->dev;
 	u32 swidth, swidthsw, sheight, ostride;
+	enum pipe pipe = overlay->crtc->pipe;
 
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 	BUG_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
@@ -713,7 +718,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 		oconfig = OCONF_CC_OUT_8BIT;
 		if (IS_GEN4(overlay->dev))
 			oconfig |= OCONF_CSC_MODE_BT709;
-		oconfig |= overlay->crtc->pipe == 0 ?
+		oconfig |= pipe == 0 ?
 			OCONF_PIPE_A : OCONF_PIPE_B;
 		iowrite32(oconfig, &regs->OCONFIG);
 		intel_overlay_unmap_regs(overlay, regs);
@@ -776,9 +781,15 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	if (ret)
 		goto out_unpin;
 
+	i915_gem_track_fb(overlay->vid_bo, new_bo,
+			  INTEL_FRONTBUFFER_OVERLAY(pipe));
+
 	overlay->old_vid_bo = overlay->vid_bo;
 	overlay->vid_bo = new_bo;
 
+	intel_frontbuffer_flip(dev,
+			       INTEL_FRONTBUFFER_OVERLAY(pipe));
+
 	return 0;
 
 out_unpin:

drivers/gpu/drm/i915/intel_pm.c

@@ -529,7 +529,10 @@ void intel_update_fbc(struct drm_device *dev)
 		goto out_disable;
 	}
 
-	if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) {
+	if (INTEL_INFO(dev)->gen >= 8 || IS_HASWELL(dev)) {
+		max_width = 4096;
+		max_height = 4096;
+	} else if (IS_G4X(dev) || INTEL_INFO(dev)->gen >= 5) {
 		max_width = 4096;
 		max_height = 2048;
 	} else {
@@ -864,95 +867,95 @@ static int i845_get_fifo_size(struct drm_device *dev, int plane)
 
 /* Pineview has different values for various configs */
 static const struct intel_watermark_params pineview_display_wm = {
-	PINEVIEW_DISPLAY_FIFO,
-	PINEVIEW_MAX_WM,
-	PINEVIEW_DFT_WM,
-	PINEVIEW_GUARD_WM,
-	PINEVIEW_FIFO_LINE_SIZE
+	.fifo_size = PINEVIEW_DISPLAY_FIFO,
+	.max_wm = PINEVIEW_MAX_WM,
+	.default_wm = PINEVIEW_DFT_WM,
+	.guard_size = PINEVIEW_GUARD_WM,
+	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params pineview_display_hplloff_wm = {
-	PINEVIEW_DISPLAY_FIFO,
-	PINEVIEW_MAX_WM,
-	PINEVIEW_DFT_HPLLOFF_WM,
-	PINEVIEW_GUARD_WM,
-	PINEVIEW_FIFO_LINE_SIZE
+	.fifo_size = PINEVIEW_DISPLAY_FIFO,
+	.max_wm = PINEVIEW_MAX_WM,
+	.default_wm = PINEVIEW_DFT_HPLLOFF_WM,
+	.guard_size = PINEVIEW_GUARD_WM,
+	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params pineview_cursor_wm = {
-	PINEVIEW_CURSOR_FIFO,
-	PINEVIEW_CURSOR_MAX_WM,
-	PINEVIEW_CURSOR_DFT_WM,
-	PINEVIEW_CURSOR_GUARD_WM,
-	PINEVIEW_FIFO_LINE_SIZE,
+	.fifo_size = PINEVIEW_CURSOR_FIFO,
+	.max_wm = PINEVIEW_CURSOR_MAX_WM,
+	.default_wm = PINEVIEW_CURSOR_DFT_WM,
+	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
+	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params pineview_cursor_hplloff_wm = {
-	PINEVIEW_CURSOR_FIFO,
-	PINEVIEW_CURSOR_MAX_WM,
-	PINEVIEW_CURSOR_DFT_WM,
-	PINEVIEW_CURSOR_GUARD_WM,
-	PINEVIEW_FIFO_LINE_SIZE
+	.fifo_size = PINEVIEW_CURSOR_FIFO,
+	.max_wm = PINEVIEW_CURSOR_MAX_WM,
+	.default_wm = PINEVIEW_CURSOR_DFT_WM,
+	.guard_size = PINEVIEW_CURSOR_GUARD_WM,
+	.cacheline_size = PINEVIEW_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params g4x_wm_info = {
-	G4X_FIFO_SIZE,
-	G4X_MAX_WM,
-	G4X_MAX_WM,
-	2,
-	G4X_FIFO_LINE_SIZE,
+	.fifo_size = G4X_FIFO_SIZE,
+	.max_wm = G4X_MAX_WM,
+	.default_wm = G4X_MAX_WM,
+	.guard_size = 2,
+	.cacheline_size = G4X_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params g4x_cursor_wm_info = {
-	I965_CURSOR_FIFO,
-	I965_CURSOR_MAX_WM,
-	I965_CURSOR_DFT_WM,
-	2,
-	G4X_FIFO_LINE_SIZE,
+	.fifo_size = I965_CURSOR_FIFO,
+	.max_wm = I965_CURSOR_MAX_WM,
+	.default_wm = I965_CURSOR_DFT_WM,
+	.guard_size = 2,
+	.cacheline_size = G4X_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params valleyview_wm_info = {
-	VALLEYVIEW_FIFO_SIZE,
-	VALLEYVIEW_MAX_WM,
-	VALLEYVIEW_MAX_WM,
-	2,
-	G4X_FIFO_LINE_SIZE,
+	.fifo_size = VALLEYVIEW_FIFO_SIZE,
+	.max_wm = VALLEYVIEW_MAX_WM,
+	.default_wm = VALLEYVIEW_MAX_WM,
+	.guard_size = 2,
+	.cacheline_size = G4X_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params valleyview_cursor_wm_info = {
-	I965_CURSOR_FIFO,
-	VALLEYVIEW_CURSOR_MAX_WM,
-	I965_CURSOR_DFT_WM,
-	2,
-	G4X_FIFO_LINE_SIZE,
+	.fifo_size = I965_CURSOR_FIFO,
+	.max_wm = VALLEYVIEW_CURSOR_MAX_WM,
+	.default_wm = I965_CURSOR_DFT_WM,
+	.guard_size = 2,
+	.cacheline_size = G4X_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params i965_cursor_wm_info = {
-	I965_CURSOR_FIFO,
-	I965_CURSOR_MAX_WM,
-	I965_CURSOR_DFT_WM,
-	2,
-	I915_FIFO_LINE_SIZE,
+	.fifo_size = I965_CURSOR_FIFO,
+	.max_wm = I965_CURSOR_MAX_WM,
+	.default_wm = I965_CURSOR_DFT_WM,
+	.guard_size = 2,
+	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params i945_wm_info = {
-	I945_FIFO_SIZE,
-	I915_MAX_WM,
-	1,
-	2,
-	I915_FIFO_LINE_SIZE
+	.fifo_size = I945_FIFO_SIZE,
+	.max_wm = I915_MAX_WM,
+	.default_wm = 1,
+	.guard_size = 2,
+	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params i915_wm_info = {
-	I915_FIFO_SIZE,
-	I915_MAX_WM,
-	1,
-	2,
-	I915_FIFO_LINE_SIZE
+	.fifo_size = I915_FIFO_SIZE,
+	.max_wm = I915_MAX_WM,
+	.default_wm = 1,
+	.guard_size = 2,
+	.cacheline_size = I915_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params i830_wm_info = {
-	I855GM_FIFO_SIZE,
-	I915_MAX_WM,
-	1,
-	2,
-	I830_FIFO_LINE_SIZE
+	.fifo_size = I855GM_FIFO_SIZE,
+	.max_wm = I915_MAX_WM,
+	.default_wm = 1,
+	.guard_size = 2,
+	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
 static const struct intel_watermark_params i845_wm_info = {
-	I830_FIFO_SIZE,
-	I915_MAX_WM,
-	1,
-	2,
-	I830_FIFO_LINE_SIZE
+	.fifo_size = I830_FIFO_SIZE,
+	.max_wm = I915_MAX_WM,
+	.default_wm = 1,
+	.guard_size = 2,
+	.cacheline_size = I830_FIFO_LINE_SIZE,
 };
 
 /**
@@ -3348,6 +3351,13 @@ static void gen6_disable_rps(struct drm_device *dev)
 		gen6_disable_rps_interrupts(dev);
 }
 
+static void cherryview_disable_rps(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	I915_WRITE(GEN6_RC_CONTROL, 0);
+}
+
 static void valleyview_disable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3727,6 +3737,35 @@ void gen6_update_ring_freq(struct drm_device *dev)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
+int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
+{
+	u32 val, rp0;
+
+	val = vlv_punit_read(dev_priv, PUNIT_GPU_STATUS_REG);
+	rp0 = (val >> PUNIT_GPU_STATUS_MAX_FREQ_SHIFT) & PUNIT_GPU_STATUS_MAX_FREQ_MASK;
+
+	return rp0;
+}
+
+static int cherryview_rps_rpe_freq(struct drm_i915_private *dev_priv)
+{
+	u32 val, rpe;
+
+	val = vlv_punit_read(dev_priv, PUNIT_GPU_DUTYCYCLE_REG);
+	rpe = (val >> PUNIT_GPU_DUTYCYCLE_RPE_FREQ_SHIFT) & PUNIT_GPU_DUTYCYCLE_RPE_FREQ_MASK;
+
+	return rpe;
+}
+
+int cherryview_rps_min_freq(struct drm_i915_private *dev_priv)
+{
+	u32 val, rpn;
+
+	val = vlv_punit_read(dev_priv, PUNIT_GPU_STATUS_REG);
+	rpn = (val >> PUNIT_GPU_STATIS_GFX_MIN_FREQ_SHIFT) & PUNIT_GPU_STATUS_GFX_MIN_FREQ_MASK;
+	return rpn;
+}
+
 int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
 {
 	u32 val, rp0;
@@ -3766,6 +3805,35 @@ static void valleyview_check_pctx(struct drm_i915_private *dev_priv)
 			     dev_priv->vlv_pctx->stolen->start);
 }
 
+
+/* Check that the pcbr address is not empty. */
+static void cherryview_check_pctx(struct drm_i915_private *dev_priv)
+{
+	unsigned long pctx_addr = I915_READ(VLV_PCBR) & ~4095;
+
+	WARN_ON((pctx_addr >> VLV_PCBR_ADDR_SHIFT) == 0);
+}
+
+static void cherryview_setup_pctx(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	unsigned long pctx_paddr, paddr;
+	struct i915_gtt *gtt = &dev_priv->gtt;
+	u32 pcbr;
+	int pctx_size = 32*1024;
+
+	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	pcbr = I915_READ(VLV_PCBR);
+	if ((pcbr >> VLV_PCBR_ADDR_SHIFT) == 0) {
+		paddr = (dev_priv->mm.stolen_base +
+			 (gtt->stolen_size - pctx_size));
+
+		pctx_paddr = (paddr & (~4095));
+		I915_WRITE(VLV_PCBR, pctx_paddr);
+	}
+}
+
 static void valleyview_setup_pctx(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -3855,11 +3923,135 @@ static void valleyview_init_gt_powersave(struct drm_device *dev)
 	mutex_unlock(&dev_priv->rps.hw_lock);
 }
 
+static void cherryview_init_gt_powersave(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	cherryview_setup_pctx(dev);
+
+	mutex_lock(&dev_priv->rps.hw_lock);
+
+	dev_priv->rps.max_freq = cherryview_rps_max_freq(dev_priv);
+	dev_priv->rps.rp0_freq = dev_priv->rps.max_freq;
+	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.max_freq),
+			 dev_priv->rps.max_freq);
+
+	dev_priv->rps.efficient_freq = cherryview_rps_rpe_freq(dev_priv);
+	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
+
+	dev_priv->rps.min_freq = cherryview_rps_min_freq(dev_priv);
+	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.min_freq),
+			 dev_priv->rps.min_freq);
+
+	/* Preserve min/max settings in case of re-init */
+	if (dev_priv->rps.max_freq_softlimit == 0)
+		dev_priv->rps.max_freq_softlimit = dev_priv->rps.max_freq;
+
+	if (dev_priv->rps.min_freq_softlimit == 0)
+		dev_priv->rps.min_freq_softlimit = dev_priv->rps.min_freq;
+
+	mutex_unlock(&dev_priv->rps.hw_lock);
+}
+
 static void valleyview_cleanup_gt_powersave(struct drm_device *dev)
 {
 	valleyview_cleanup_pctx(dev);
 }
 
+static void cherryview_enable_rps(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_engine_cs *ring;
+	u32 gtfifodbg, val, rc6_mode = 0, pcbr;
+	int i;
+
+	WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
+
+	gtfifodbg = I915_READ(GTFIFODBG);
+	if (gtfifodbg) {
+		DRM_DEBUG_DRIVER("GT fifo had a previous error %x\n",
+				 gtfifodbg);
+		I915_WRITE(GTFIFODBG, gtfifodbg);
+	}
+
+	cherryview_check_pctx(dev_priv);
+
+	/* 1a & 1b: Get forcewake during program sequence. Although the driver
+	 * hasn't enabled a state yet where we need forcewake, BIOS may have.*/
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
+	/* 2a: Program RC6 thresholds.*/
+	I915_WRITE(GEN6_RC6_WAKE_RATE_LIMIT, 40 << 16);
+	I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000); /* 12500 * 1280ns */
+	I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25); /* 25 * 1280ns */
+
+	for_each_ring(ring, dev_priv, i)
+		I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
+	I915_WRITE(GEN6_RC_SLEEP, 0);
+
+	I915_WRITE(GEN6_RC6_THRESHOLD, 50000); /* 50/125ms per EI */
+
+	/* allows RC6 residency counter to work */
+	I915_WRITE(VLV_COUNTER_CONTROL,
+		   _MASKED_BIT_ENABLE(VLV_COUNT_RANGE_HIGH |
+				      VLV_MEDIA_RC6_COUNT_EN |
+				      VLV_RENDER_RC6_COUNT_EN));
+
+	/* For now we assume BIOS is allocating and populating the PCBR  */
+	pcbr = I915_READ(VLV_PCBR);
+
+	DRM_DEBUG_DRIVER("PCBR offset : 0x%x\n", pcbr);
+
+	/* 3: Enable RC6 */
+	if ((intel_enable_rc6(dev) & INTEL_RC6_ENABLE) &&
+						(pcbr >> VLV_PCBR_ADDR_SHIFT))
+		rc6_mode = GEN6_RC_CTL_EI_MODE(1);
+
+	I915_WRITE(GEN6_RC_CONTROL, rc6_mode);
+
+	/* 4 Program defaults and thresholds for RPS*/
+	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
+	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
+	I915_WRITE(GEN6_RP_UP_EI, 66000);
+	I915_WRITE(GEN6_RP_DOWN_EI, 350000);
+
+	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	/* WaDisablePwrmtrEvent:chv (pre-production hw) */
+	I915_WRITE(0xA80C, I915_READ(0xA80C) & 0x00ffffff);
+	I915_WRITE(0xA810, I915_READ(0xA810) & 0xffffff00);
+
+	/* 5: Enable RPS */
+	I915_WRITE(GEN6_RP_CONTROL,
+		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+		   GEN6_RP_MEDIA_IS_GFX | /* WaSetMaskForGfxBusyness:chv (pre-production hw ?) */
+		   GEN6_RP_ENABLE |
+		   GEN6_RP_UP_BUSY_AVG |
+		   GEN6_RP_DOWN_IDLE_AVG);
+
+	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
+
+	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", val & 0x10 ? "yes" : "no");
+	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+
+	dev_priv->rps.cur_freq = (val >> 8) & 0xff;
+	DRM_DEBUG_DRIVER("current GPU freq: %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.cur_freq),
+			 dev_priv->rps.cur_freq);
+
+	DRM_DEBUG_DRIVER("setting GPU freq to %d MHz (%u)\n",
+			 vlv_gpu_freq(dev_priv, dev_priv->rps.efficient_freq),
+			 dev_priv->rps.efficient_freq);
+
+	valleyview_set_rps(dev_priv->dev, dev_priv->rps.efficient_freq);
+
+	gen6_gt_force_wake_put(dev_priv, FORCEWAKE_ALL);
+}
+
 static void valleyview_enable_rps(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -4668,33 +4860,57 @@ void intel_init_gt_powersave(struct drm_device *dev)
 {
 	i915.enable_rc6 = sanitize_rc6_option(dev, i915.enable_rc6);
 
-	if (IS_VALLEYVIEW(dev))
+	if (IS_CHERRYVIEW(dev))
+		cherryview_init_gt_powersave(dev);
+	else if (IS_VALLEYVIEW(dev))
 		valleyview_init_gt_powersave(dev);
 }
 
 void intel_cleanup_gt_powersave(struct drm_device *dev)
 {
-	if (IS_VALLEYVIEW(dev))
+	if (IS_CHERRYVIEW(dev))
+		return;
+	else if (IS_VALLEYVIEW(dev))
 		valleyview_cleanup_gt_powersave(dev);
 }
 
+/**
+ * intel_suspend_gt_powersave - suspend PM work and helper threads
+ * @dev: drm device
+ *
+ * We don't want to disable RC6 or other features here, we just want
+ * to make sure any work we've queued has finished and won't bother
+ * us while we're suspended.
+ */
+void intel_suspend_gt_powersave(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/* Interrupts should be disabled already to avoid re-arming. */
+	WARN_ON(dev->irq_enabled && !dev_priv->pm.irqs_disabled);
+
+	flush_delayed_work(&dev_priv->rps.delayed_resume_work);
+
+	cancel_work_sync(&dev_priv->rps.work);
+}
+
 void intel_disable_gt_powersave(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	/* Interrupts should be disabled already to avoid re-arming. */
-	WARN_ON(dev->irq_enabled);
+	WARN_ON(dev->irq_enabled && !dev_priv->pm.irqs_disabled);
 
 	if (IS_IRONLAKE_M(dev)) {
 		ironlake_disable_drps(dev);
 		ironlake_disable_rc6(dev);
-	} else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) {
-		if (cancel_delayed_work_sync(&dev_priv->rps.delayed_resume_work))
-			intel_runtime_pm_put(dev_priv);
+	} else if (INTEL_INFO(dev)->gen >= 6) {
+		intel_suspend_gt_powersave(dev);
 
-		cancel_work_sync(&dev_priv->rps.work);
 		mutex_lock(&dev_priv->rps.hw_lock);
-		if (IS_VALLEYVIEW(dev))
+		if (IS_CHERRYVIEW(dev))
+			cherryview_disable_rps(dev);
+		else if (IS_VALLEYVIEW(dev))
 			valleyview_disable_rps(dev);
 		else
 			gen6_disable_rps(dev);
@@ -4712,7 +4928,9 @@ static void intel_gen6_powersave_work(struct work_struct *work)
 
 	mutex_lock(&dev_priv->rps.hw_lock);
 
-	if (IS_VALLEYVIEW(dev)) {
+	if (IS_CHERRYVIEW(dev)) {
+		cherryview_enable_rps(dev);
+	} else if (IS_VALLEYVIEW(dev)) {
 		valleyview_enable_rps(dev);
 	} else if (IS_BROADWELL(dev)) {
 		gen8_enable_rps(dev);
@@ -4737,7 +4955,7 @@ void intel_enable_gt_powersave(struct drm_device *dev)
 		ironlake_enable_rc6(dev);
 		intel_init_emon(dev);
 		mutex_unlock(&dev->struct_mutex);
-	} else if (IS_GEN6(dev) || IS_GEN7(dev) || IS_BROADWELL(dev)) {
+	} else if (INTEL_INFO(dev)->gen >= 6) {
 		/*
 		 * PCU communication is slow and this doesn't need to be
 		 * done at any specific time, so do this out of our fast path

drivers/gpu/drm/i915/intel_renderstate.h

@@ -28,7 +28,6 @@
 
 struct intel_renderstate_rodata {
 	const u32 *reloc;
-	const u32 reloc_items;
 	const u32 *batch;
 	const u32 batch_items;
 };
@@ -40,7 +39,6 @@ extern const struct intel_renderstate_rodata gen8_null_state;
 #define RO_RENDERSTATE(_g)						\
 	const struct intel_renderstate_rodata gen ## _g ## _null_state = { \
 		.reloc = gen ## _g ## _null_state_relocs,		\
-		.reloc_items = sizeof(gen ## _g ## _null_state_relocs)/4, \
 		.batch = gen ## _g ## _null_state_batch,		\
 		.batch_items = sizeof(gen ## _g ## _null_state_batch)/4, \
 	}

drivers/gpu/drm/i915/intel_renderstate_gen6.c

@@ -6,6 +6,7 @@ static const u32 gen6_null_state_relocs[] = {
 	0x0000002c,
 	0x000001e0,
 	0x000001e4,
+	-1,
 };
 
 static const u32 gen6_null_state_batch[] = {

drivers/gpu/drm/i915/intel_renderstate_gen7.c

@@ -5,6 +5,7 @@ static const u32 gen7_null_state_relocs[] = {
 	0x00000010,
 	0x00000018,
 	0x000001ec,
+	-1,
 };
 
 static const u32 gen7_null_state_batch[] = {

drivers/gpu/drm/i915/intel_renderstate_gen8.c

@@ -5,6 +5,7 @@ static const u32 gen8_null_state_relocs[] = {
 	0x00000050,
 	0x00000060,
 	0x000003ec,
+	-1,
 };
 
 static const u32 gen8_null_state_batch[] = {

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -604,6 +604,8 @@ static int init_render_ring(struct intel_engine_cs *ring)
 	struct drm_device *dev = ring->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int ret = init_ring_common(ring);
+	if (ret)
+		return ret;
 
 	/* WaTimedSingleVertexDispatch:cl,bw,ctg,elk,ilk,snb */
 	if (INTEL_INFO(dev)->gen >= 4 && INTEL_INFO(dev)->gen < 7)
@@ -1397,6 +1399,9 @@ static int allocate_ring_buffer(struct intel_engine_cs *ring)
 	if (obj == NULL)
 		return -ENOMEM;
 
+	/* mark ring buffers as read-only from GPU side by default */
+	obj->gt_ro = 1;
+
 	ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
 	if (ret)
 		goto err_unref;
@@ -1746,14 +1751,15 @@ int intel_ring_cacheline_align(struct intel_engine_cs *ring)
 
 void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno)
 {
-	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	BUG_ON(ring->outstanding_lazy_seqno);
 
-	if (INTEL_INFO(ring->dev)->gen >= 6) {
+	if (INTEL_INFO(dev)->gen == 6 || INTEL_INFO(dev)->gen == 7) {
 		I915_WRITE(RING_SYNC_0(ring->mmio_base), 0);
 		I915_WRITE(RING_SYNC_1(ring->mmio_base), 0);
-		if (HAS_VEBOX(ring->dev))
+		if (HAS_VEBOX(dev))
 			I915_WRITE(RING_SYNC_2(ring->mmio_base), 0);
 	}
 

drivers/gpu/drm/i915/intel_sprite.c

@@ -819,6 +819,7 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_device *dev = plane->dev;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_plane *intel_plane = to_intel_plane(plane);
+	enum pipe pipe = intel_crtc->pipe;
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct drm_i915_gem_object *old_obj = intel_plane->obj;
@@ -1006,6 +1007,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 	 */
 	ret = intel_pin_and_fence_fb_obj(dev, obj, NULL);
 
+	i915_gem_track_fb(old_obj, obj,
+			  INTEL_FRONTBUFFER_SPRITE(pipe));
 	mutex_unlock(&dev->struct_mutex);
 
 	if (ret)
@@ -1039,6 +1042,8 @@ intel_update_plane(struct drm_plane *plane, struct drm_crtc *crtc,
 		else
 			intel_plane->disable_plane(plane, crtc);
 
+		intel_frontbuffer_flip(dev, INTEL_FRONTBUFFER_SPRITE(pipe));
+
 		if (!primary_was_enabled && primary_enabled)
 			intel_post_enable_primary(crtc);
 	}
@@ -1068,6 +1073,7 @@ intel_disable_plane(struct drm_plane *plane)
 	struct drm_device *dev = plane->dev;
 	struct intel_plane *intel_plane = to_intel_plane(plane);
 	struct intel_crtc *intel_crtc;
+	enum pipe pipe;
 
 	if (!plane->fb)
 		return 0;
@@ -1076,6 +1082,7 @@ intel_disable_plane(struct drm_plane *plane)
 		return -EINVAL;
 
 	intel_crtc = to_intel_crtc(plane->crtc);
+	pipe = intel_crtc->pipe;
 
 	if (intel_crtc->active) {
 		bool primary_was_enabled = intel_crtc->primary_enabled;
@@ -1094,6 +1101,8 @@ intel_disable_plane(struct drm_plane *plane)
 
 		mutex_lock(&dev->struct_mutex);
 		intel_unpin_fb_obj(intel_plane->obj);
+		i915_gem_track_fb(intel_plane->obj, NULL,
+				  INTEL_FRONTBUFFER_SPRITE(pipe));
 		mutex_unlock(&dev->struct_mutex);
 
 		intel_plane->obj = NULL;

drivers/gpu/drm/i915/intel_uncore.c

@@ -231,8 +231,8 @@ static void __vlv_force_wake_get(struct drm_i915_private *dev_priv,
 	}
 
 	/* WaRsForcewakeWaitTC0:vlv */
-	__gen6_gt_wait_for_thread_c0(dev_priv);
-
+	if (!IS_CHERRYVIEW(dev_priv->dev))
+		__gen6_gt_wait_for_thread_c0(dev_priv);
 }
 
 static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
@@ -250,9 +250,10 @@ static void __vlv_force_wake_put(struct drm_i915_private *dev_priv,
 		__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
 				_MASKED_BIT_DISABLE(FORCEWAKE_KERNEL));
 
-	/* The below doubles as a POSTING_READ */
-	gen6_gt_check_fifodbg(dev_priv);
-
+	/* something from same cacheline, but !FORCEWAKE_VLV */
+	__raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV);
+	if (!IS_CHERRYVIEW(dev_priv->dev))
+		gen6_gt_check_fifodbg(dev_priv);
 }
 
 static void vlv_force_wake_get(struct drm_i915_private *dev_priv, int fw_engine)
@@ -315,7 +316,7 @@ static void gen6_force_wake_timer(unsigned long arg)
 	intel_runtime_pm_put(dev_priv);
 }
 
-static void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
+void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	unsigned long irqflags;
@@ -357,16 +358,12 @@ static void intel_uncore_forcewake_reset(struct drm_device *dev, bool restore)
 			dev_priv->uncore.fifo_count =
 				__raw_i915_read32(dev_priv, GTFIFOCTL) &
 				GT_FIFO_FREE_ENTRIES_MASK;
-	} else {
-		dev_priv->uncore.forcewake_count = 0;
-		dev_priv->uncore.fw_rendercount = 0;
-		dev_priv->uncore.fw_mediacount = 0;
 	}
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
-void intel_uncore_early_sanitize(struct drm_device *dev)
+void intel_uncore_early_sanitize(struct drm_device *dev, bool restore_forcewake)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
@@ -389,7 +386,7 @@ void intel_uncore_early_sanitize(struct drm_device *dev)
 		__raw_i915_write32(dev_priv, GTFIFODBG,
 				   __raw_i915_read32(dev_priv, GTFIFODBG));
 
-	intel_uncore_forcewake_reset(dev, false);
+	intel_uncore_forcewake_reset(dev, restore_forcewake);
 }
 
 void intel_uncore_sanitize(struct drm_device *dev)
@@ -469,16 +466,43 @@ void assert_force_wake_inactive(struct drm_i915_private *dev_priv)
 #define NEEDS_FORCE_WAKE(dev_priv, reg) \
 	 ((reg) < 0x40000 && (reg) != FORCEWAKE)
 
-#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
-	(((reg) >= 0x2000 && (reg) < 0x4000) ||\
-	((reg) >= 0x5000 && (reg) < 0x8000) ||\
-	((reg) >= 0xB000 && (reg) < 0x12000) ||\
-	((reg) >= 0x2E000 && (reg) < 0x30000))
+#define REG_RANGE(reg, start, end) ((reg) >= (start) && (reg) < (end))
 
-#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg)\
-	(((reg) >= 0x12000 && (reg) < 0x14000) ||\
-	((reg) >= 0x22000 && (reg) < 0x24000) ||\
-	((reg) >= 0x30000 && (reg) < 0x40000))
+#define FORCEWAKE_VLV_RENDER_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x2000, 0x4000) || \
+	 REG_RANGE((reg), 0x5000, 0x8000) || \
+	 REG_RANGE((reg), 0xB000, 0x12000) || \
+	 REG_RANGE((reg), 0x2E000, 0x30000))
+
+#define FORCEWAKE_VLV_MEDIA_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x12000, 0x14000) || \
+	 REG_RANGE((reg), 0x22000, 0x24000) || \
+	 REG_RANGE((reg), 0x30000, 0x40000))
+
+#define FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x2000, 0x4000) || \
+	 REG_RANGE((reg), 0x5000, 0x8000) || \
+	 REG_RANGE((reg), 0x8300, 0x8500) || \
+	 REG_RANGE((reg), 0xB000, 0xC000) || \
+	 REG_RANGE((reg), 0xE000, 0xE800))
+
+#define FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x8800, 0x8900) || \
+	 REG_RANGE((reg), 0xD000, 0xD800) || \
+	 REG_RANGE((reg), 0x12000, 0x14000) || \
+	 REG_RANGE((reg), 0x1A000, 0x1C000) || \
+	 REG_RANGE((reg), 0x1E800, 0x1EA00) || \
+	 REG_RANGE((reg), 0x30000, 0x40000))
+
+#define FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg) \
+	(REG_RANGE((reg), 0x4000, 0x5000) || \
+	 REG_RANGE((reg), 0x8000, 0x8300) || \
+	 REG_RANGE((reg), 0x8500, 0x8600) || \
+	 REG_RANGE((reg), 0x9000, 0xB000) || \
+	 REG_RANGE((reg), 0xC000, 0xC800) || \
+	 REG_RANGE((reg), 0xF000, 0x10000) || \
+	 REG_RANGE((reg), 0x14000, 0x14400) || \
+	 REG_RANGE((reg), 0x22000, 0x24000))
 
 static void
 ilk_dummy_write(struct drm_i915_private *dev_priv)
@@ -573,7 +597,35 @@ vlv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
 	REG_READ_FOOTER; \
 }
 
+#define __chv_read(x) \
+static u##x \
+chv_read##x(struct drm_i915_private *dev_priv, off_t reg, bool trace) { \
+	unsigned fwengine = 0; \
+	REG_READ_HEADER(x); \
+	if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) { \
+		if (dev_priv->uncore.fw_rendercount == 0) \
+			fwengine = FORCEWAKE_RENDER; \
+	} else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) { \
+		if (dev_priv->uncore.fw_mediacount == 0) \
+			fwengine = FORCEWAKE_MEDIA; \
+	} else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) { \
+		if (dev_priv->uncore.fw_rendercount == 0) \
+			fwengine |= FORCEWAKE_RENDER; \
+		if (dev_priv->uncore.fw_mediacount == 0) \
+			fwengine |= FORCEWAKE_MEDIA; \
+	} \
+	if (fwengine) \
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, fwengine); \
+	val = __raw_i915_read##x(dev_priv, reg); \
+	if (fwengine) \
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, fwengine); \
+	REG_READ_FOOTER; \
+}
 
+__chv_read(8)
+__chv_read(16)
+__chv_read(32)
+__chv_read(64)
 __vlv_read(8)
 __vlv_read(16)
 __vlv_read(32)
@@ -591,6 +643,7 @@ __gen4_read(16)
 __gen4_read(32)
 __gen4_read(64)
 
+#undef __chv_read
 #undef __vlv_read
 #undef __gen6_read
 #undef __gen5_read
@@ -695,6 +748,38 @@ gen8_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace
 	REG_WRITE_FOOTER; \
 }
 
+#define __chv_write(x) \
+static void \
+chv_write##x(struct drm_i915_private *dev_priv, off_t reg, u##x val, bool trace) { \
+	unsigned fwengine = 0; \
+	bool shadowed = is_gen8_shadowed(dev_priv, reg); \
+	REG_WRITE_HEADER; \
+	if (!shadowed) { \
+		if (FORCEWAKE_CHV_RENDER_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_rendercount == 0) \
+				fwengine = FORCEWAKE_RENDER; \
+		} else if (FORCEWAKE_CHV_MEDIA_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_mediacount == 0) \
+				fwengine = FORCEWAKE_MEDIA; \
+		} else if (FORCEWAKE_CHV_COMMON_RANGE_OFFSET(reg)) { \
+			if (dev_priv->uncore.fw_rendercount == 0) \
+				fwengine |= FORCEWAKE_RENDER; \
+			if (dev_priv->uncore.fw_mediacount == 0) \
+				fwengine |= FORCEWAKE_MEDIA; \
+		} \
+	} \
+	if (fwengine) \
+		dev_priv->uncore.funcs.force_wake_get(dev_priv, fwengine); \
+	__raw_i915_write##x(dev_priv, reg, val); \
+	if (fwengine) \
+		dev_priv->uncore.funcs.force_wake_put(dev_priv, fwengine); \
+	REG_WRITE_FOOTER; \
+}
+
+__chv_write(8)
+__chv_write(16)
+__chv_write(32)
+__chv_write(64)
 __gen8_write(8)
 __gen8_write(16)
 __gen8_write(32)
@@ -716,6 +801,7 @@ __gen4_write(16)
 __gen4_write(32)
 __gen4_write(64)
 
+#undef __chv_write
 #undef __gen8_write
 #undef __hsw_write
 #undef __gen6_write
@@ -731,7 +817,7 @@ void intel_uncore_init(struct drm_device *dev)
 	setup_timer(&dev_priv->uncore.force_wake_timer,
 		    gen6_force_wake_timer, (unsigned long)dev_priv);
 
-	intel_uncore_early_sanitize(dev);
+	intel_uncore_early_sanitize(dev, false);
 
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->uncore.funcs.force_wake_get = __vlv_force_wake_get;
@@ -779,14 +865,26 @@ void intel_uncore_init(struct drm_device *dev)
 
 	switch (INTEL_INFO(dev)->gen) {
 	default:
-		dev_priv->uncore.funcs.mmio_writeb  = gen8_write8;
-		dev_priv->uncore.funcs.mmio_writew  = gen8_write16;
-		dev_priv->uncore.funcs.mmio_writel  = gen8_write32;
-		dev_priv->uncore.funcs.mmio_writeq  = gen8_write64;
-		dev_priv->uncore.funcs.mmio_readb  = gen6_read8;
-		dev_priv->uncore.funcs.mmio_readw  = gen6_read16;
-		dev_priv->uncore.funcs.mmio_readl  = gen6_read32;
-		dev_priv->uncore.funcs.mmio_readq  = gen6_read64;
+		if (IS_CHERRYVIEW(dev)) {
+			dev_priv->uncore.funcs.mmio_writeb  = chv_write8;
+			dev_priv->uncore.funcs.mmio_writew  = chv_write16;
+			dev_priv->uncore.funcs.mmio_writel  = chv_write32;
+			dev_priv->uncore.funcs.mmio_writeq  = chv_write64;
+			dev_priv->uncore.funcs.mmio_readb  = chv_read8;
+			dev_priv->uncore.funcs.mmio_readw  = chv_read16;
+			dev_priv->uncore.funcs.mmio_readl  = chv_read32;
+			dev_priv->uncore.funcs.mmio_readq  = chv_read64;
+
+		} else {
+			dev_priv->uncore.funcs.mmio_writeb  = gen8_write8;
+			dev_priv->uncore.funcs.mmio_writew  = gen8_write16;
+			dev_priv->uncore.funcs.mmio_writel  = gen8_write32;
+			dev_priv->uncore.funcs.mmio_writeq  = gen8_write64;
+			dev_priv->uncore.funcs.mmio_readb  = gen6_read8;
+			dev_priv->uncore.funcs.mmio_readw  = gen6_read16;
+			dev_priv->uncore.funcs.mmio_readl  = gen6_read32;
+			dev_priv->uncore.funcs.mmio_readq  = gen6_read64;
+		}
 		break;
 	case 7:
 	case 6:
@@ -1053,18 +1151,16 @@ static int gen6_do_reset(struct drm_device *dev)
 
 int intel_gpu_reset(struct drm_device *dev)
 {
-	switch (INTEL_INFO(dev)->gen) {
-	case 8:
-	case 7:
-	case 6: return gen6_do_reset(dev);
-	case 5: return ironlake_do_reset(dev);
-	case 4:
-		if (IS_G4X(dev))
-			return g4x_do_reset(dev);
-		else
-			return i965_do_reset(dev);
-	default: return -ENODEV;
-	}
+	if (INTEL_INFO(dev)->gen >= 6)
+		return gen6_do_reset(dev);
+	else if (IS_GEN5(dev))
+		return ironlake_do_reset(dev);
+	else if (IS_G4X(dev))
+		return g4x_do_reset(dev);
+	else if (IS_GEN4(dev))
+		return i965_do_reset(dev);
+	else
+		return -ENODEV;
 }
 
 void intel_uncore_check_errors(struct drm_device *dev)

include/drm/drm_crtc.h

@@ -331,6 +331,10 @@ struct drm_crtc {
 	struct drm_plane *primary;
 	struct drm_plane *cursor;
 
+	/* position of cursor plane on crtc */
+	int cursor_x;
+	int cursor_y;
+
 	/* Temporary tracking of the old fb while a modeset is ongoing. Used
 	 * by drm_mode_set_config_internal to implement correct refcounting. */
 	struct drm_framebuffer *old_fb;
@@ -858,7 +862,7 @@ struct drm_prop_enum_list {
 extern int drm_crtc_init_with_planes(struct drm_device *dev,
 				     struct drm_crtc *crtc,
 				     struct drm_plane *primary,
-				     void *cursor,
+				     struct drm_plane *cursor,
 				     const struct drm_crtc_funcs *funcs);
 extern int drm_crtc_init(struct drm_device *dev,
 			 struct drm_crtc *crtc,