Merge tag 'drm-fixes-for-v4.12-rc5' of git://people.freedesktop.org/~airlied/linux

Pull drm fixes from Dave Airlie:
 "Intel, nouveau, rockchip, vmwgfx, imx, meson, mediatek and core fixes.

  Bit more spread out fixes this time, fixes for 7 drivers + a couple of
  core fixes.

  i915 and vmwgfx are the main ones. The vmwgfx ones fix a bunch of
  regressions in their atomic rework, and a few fixes destined for
  stable. i915 has some 4.12 regressions and older things that need to
  be fixed in stable as well.

  nouveau also has some runtime pm fixes and a timer list handling fix,
  otherwise a couple of core and small driver regression fixes"

* tag 'drm-fixes-for-v4.12-rc5' of git://people.freedesktop.org/~airlied/linux: (37 commits)
  drm/i915: fix warning for unused variable
  drm/meson: Fix driver bind when only CVBS is available
  drm/i915: Fix 90/270 rotated coordinates for FBC
  drm/i915: Restore has_fbc=1 for ILK-M
  drm/i915: Workaround VLV/CHV DSI scanline counter hardware fail
  drm/i915: Fix logical inversion for gen4 quirking
  drm/i915: Guard against i915_ggtt_disable_guc() being invoked unconditionally
  drm/i915: Always recompute watermarks when distrust_bios_wm is set, v2.
  drm/i915: Prevent the system suspend complete optimization
  drm/i915/psr: disable psr2 for resolution greater than 32X20
  drm/i915: Hold a wakeref for probing the ring registers
  drm/i915: Short-circuit i915_gem_wait_for_idle() if already idle
  drm/i915: Disable decoupled MMIO
  drm/i915/guc: Remove stale comment for q_fail
  drm/vmwgfx: Bump driver minor and date
  drm/vmwgfx: Remove unused legacy cursor functions
  drm/vmwgfx: fix spelling mistake "exeeds" -> "exceeds"
  drm/vmwgfx: Fix large topology crash
  drm/vmwgfx: Make sure to update STDU when FB is updated
  drm/vmwgfx: Make sure backup_handle is always valid
  ...

39 files changed, 334 insertions, 257 deletions

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 8be9719284b0..aa885a614e27 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -508,6 +508,8 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 		bool has_connectors =
 			!!new_crtc_state->connector_mask;
 
+		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
 		if (!drm_mode_equal(&old_crtc_state->mode, &new_crtc_state->mode)) {
 			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] mode changed\n",
 					 crtc->base.id, crtc->name);
@@ -551,6 +553,8 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 	for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) {
 		const struct drm_connector_helper_funcs *funcs = connector->helper_private;
 
+		WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+
 		/*
 		 * This only sets crtc->connectors_changed for routing changes,
 		 * drivers must set crtc->connectors_changed themselves when
@@ -650,6 +654,8 @@ drm_atomic_helper_check_planes(struct drm_device *dev,
 	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs;
 
+		WARN_ON(!drm_modeset_is_locked(&plane->mutex));
+
 		funcs = plane->helper_private;
 
 		drm_atomic_helper_plane_changed(state, old_plane_state, new_plane_state, plane);
@@ -2663,7 +2669,12 @@ int drm_atomic_helper_resume(struct drm_device *dev,
 
 	drm_modeset_acquire_init(&ctx, 0);
 	while (1) {
+		err = drm_modeset_lock_all_ctx(dev, &ctx);
+		if (err)
+			goto out;
+
 		err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
+out:
 		if (err != -EDEADLK)
 			break;
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index b5c6bb46a425..37b8ad3e30d8 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -358,7 +358,12 @@ EXPORT_SYMBOL(drm_put_dev);
 void drm_unplug_dev(struct drm_device *dev)
 {
 	/* for a USB device */
-	drm_dev_unregister(dev);
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_modeset_unregister_all(dev);
+
+	drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 
 	mutex_lock(&drm_global_mutex);
 
diff --git a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
index 5abc69c9630f..f77dcfaade6c 100644
--- a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
+++ b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
@@ -760,7 +760,7 @@ static int dsi_parse_dt(struct platform_device *pdev, struct dw_dsi *dsi)
 	 * Get the endpoint node. In our case, dsi has one output port1
 	 * to which the external HDMI bridge is connected.
 	 */
-	ret = drm_of_find_panel_or_bridge(np, 0, 0, NULL, &dsi->bridge);
+	ret = drm_of_find_panel_or_bridge(np, 1, 0, NULL, &dsi->bridge);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c994fe6e65b2..48428672fc6e 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1235,6 +1235,15 @@ int i915_driver_load(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_fini;
 
 	pci_set_drvdata(pdev, &dev_priv->drm);
+	/*
+	 * Disable the system suspend direct complete optimization, which can
+	 * leave the device suspended skipping the driver's suspend handlers
+	 * if the device was already runtime suspended. This is needed due to
+	 * the difference in our runtime and system suspend sequence and
+	 * becaue the HDA driver may require us to enable the audio power
+	 * domain during system suspend.
+	 */
+	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	ret = i915_driver_init_early(dev_priv, ent);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 963f6d4481f7..2c453a4e97d5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2991,6 +2991,16 @@ static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv)
 	return false;
 }
 
+static inline bool
+intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	if (IS_BROXTON(dev_priv) && intel_iommu_gfx_mapped)
+		return true;
+#endif
+	return false;
+}
+
 int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 				int enable_ppgtt);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b6ac3df18b58..462031cbd77f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3298,6 +3298,10 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 {
 	int ret;
 
+	/* If the device is asleep, we have no requests outstanding */
+	if (!READ_ONCE(i915->gt.awake))
+		return 0;
+
 	if (flags & I915_WAIT_LOCKED) {
 		struct i915_gem_timeline *tl;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 50b8f1139ff9..f1989b8792dd 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2191,6 +2191,101 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 		gen8_set_pte(&gtt_base[i], scratch_pte);
 }
 
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+	struct drm_i915_private *dev_priv = vm->i915;
+
+	/*
+	 * Make sure the internal GAM fifo has been cleared of all GTT
+	 * writes before exiting stop_machine(). This guarantees that
+	 * any aperture accesses waiting to start in another process
+	 * cannot back up behind the GTT writes causing a hang.
+	 * The register can be any arbitrary GAM register.
+	 */
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+	struct i915_address_space *vm;
+	dma_addr_t addr;
+	u64 offset;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+	struct insert_page *arg = _arg;
+
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+					  dma_addr_t addr,
+					  u64 offset,
+					  enum i915_cache_level level,
+					  u32 unused)
+{
+	struct insert_page arg = { vm, addr, offset, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct sg_table *st;
+	u64 start;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+
+	gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					     struct sg_table *st,
+					     u64 start,
+					     enum i915_cache_level level,
+					     u32 unused)
+{
+	struct insert_entries arg = { vm, st, start, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+	struct i915_address_space *vm;
+	u64 start;
+	u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+	struct clear_range *arg = _arg;
+
+	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+					  u64 start,
+					  u64 length)
+{
+	struct clear_range arg = { vm, start, length };
+
+	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  u64 start, u64 length)
 {
@@ -2785,6 +2880,14 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
 
+	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
+		ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->base.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->base.clear_range != nop_clear_range)
+			ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+	}
+
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
 	return ggtt_probe_common(ggtt, size);
@@ -2997,7 +3100,8 @@ void i915_ggtt_enable_guc(struct drm_i915_private *i915)
 
 void i915_ggtt_disable_guc(struct drm_i915_private *i915)
 {
-	i915->ggtt.invalidate = gen6_ggtt_invalidate;
+	if (i915->ggtt.invalidate == guc_ggtt_invalidate)
+		i915->ggtt.invalidate = gen6_ggtt_invalidate;
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index a0d6d4317a49..fb5231f98c0d 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -278,7 +278,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 			obj->mm.quirked = false;
 		}
 		if (!i915_gem_object_is_tiled(obj)) {
-			GEM_BUG_ON(!obj->mm.quirked);
+			GEM_BUG_ON(obj->mm.quirked);
 			__i915_gem_object_pin_pages(obj);
 			obj->mm.quirked = true;
 		}
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index f87b0c4e564d..1a78363c7f4a 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -208,7 +208,7 @@ static const struct intel_device_info intel_ironlake_d_info = {
 static const struct intel_device_info intel_ironlake_m_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
-	.is_mobile = 1,
+	.is_mobile = 1, .has_fbc = 1,
 };
 
 #define GEN6_FEATURES \
@@ -390,7 +390,6 @@ static const struct intel_device_info intel_skylake_gt3_info = {
 	.has_hw_contexts = 1, \
 	.has_logical_ring_contexts = 1, \
 	.has_guc = 1, \
-	.has_decoupled_mmio = 1, \
 	.has_aliasing_ppgtt = 1, \
 	.has_full_ppgtt = 1, \
 	.has_full_48bit_ppgtt = 1, \
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3cabe52a4e3b..569717a12723 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12203,6 +12203,15 @@ static void update_scanline_offset(struct intel_crtc *crtc)
 	 * type. For DP ports it behaves like most other platforms, but on HDMI
 	 * there's an extra 1 line difference. So we need to add two instead of
 	 * one to the value.
+	 *
+	 * On VLV/CHV DSI the scanline counter would appear to increment
+	 * approx. 1/3 of a scanline before start of vblank. Unfortunately
+	 * that means we can't tell whether we're in vblank or not while
+	 * we're on that particular line. We must still set scanline_offset
+	 * to 1 so that the vblank timestamps come out correct when we query
+	 * the scanline counter from within the vblank interrupt handler.
+	 * However if queried just before the start of vblank we'll get an
+	 * answer that's slightly in the future.
 	 */
 	if (IS_GEN2(dev_priv)) {
 		const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 854e8e0c836b..f94eacff196c 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1075,6 +1075,22 @@ int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
 	return 0;
 }
 
+static bool ring_is_idle(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	bool idle = true;
+
+	intel_runtime_pm_get(dev_priv);
+
+	/* No bit for gen2, so assume the CS parser is idle */
+	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+		idle = false;
+
+	intel_runtime_pm_put(dev_priv);
+
+	return idle;
+}
+
 /**
  * intel_engine_is_idle() - Report if the engine has finished process all work
  * @engine: the intel_engine_cs
@@ -1084,8 +1100,6 @@ int intel_ring_workarounds_emit(struct drm_i915_gem_request *req)
  */
 bool intel_engine_is_idle(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-
 	/* Any inflight/incomplete requests? */
 	if (!i915_seqno_passed(intel_engine_get_seqno(engine),
 			       intel_engine_last_submit(engine)))
@@ -1100,7 +1114,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return false;
 
 	/* Ring stopped? */
-	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+	if (!ring_is_idle(engine))
 		return false;
 
 	return true;
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index ded2add18b26..d93c58410bff 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -82,20 +82,10 @@ static unsigned int get_crtc_fence_y_offset(struct intel_crtc *crtc)
 static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
 					    int *width, int *height)
 {
-	int w, h;
-
-	if (drm_rotation_90_or_270(cache->plane.rotation)) {
-		w = cache->plane.src_h;
-		h = cache->plane.src_w;
-	} else {
-		w = cache->plane.src_w;
-		h = cache->plane.src_h;
-	}
-
 	if (width)
-		*width = w;
+		*width = cache->plane.src_w;
 	if (height)
-		*height = h;
+		*height = cache->plane.src_h;
 }
 
 static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
@@ -746,6 +736,11 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 		cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate;
 
 	cache->plane.rotation = plane_state->base.rotation;
+	/*
+	 * Src coordinates are already rotated by 270 degrees for
+	 * the 90/270 degree plane rotation cases (to match the
+	 * GTT mapping), hence no need to account for rotation here.
+	 */
 	cache->plane.src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	cache->plane.src_h = drm_rect_height(&plane_state->base.src) >> 16;
 	cache->plane.visible = plane_state->base.visible;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 570bd603f401..2ca481b5aa69 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4335,11 +4335,19 @@ skl_compute_wm(struct drm_atomic_state *state)
 	struct drm_crtc_state *cstate;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	struct skl_wm_values *results = &intel_state->wm_results;
+	struct drm_device *dev = state->dev;
 	struct skl_pipe_wm *pipe_wm;
 	bool changed = false;
 	int ret, i;
 
 	/*
+	 * When we distrust bios wm we always need to recompute to set the
+	 * expected DDB allocations for each CRTC.
+	 */
+	if (to_i915(dev)->wm.distrust_bios_wm)
+		changed = true;
+
+	/*
 	 * If this transaction isn't actually touching any CRTC's, don't
 	 * bother with watermark calculation.  Note that if we pass this
 	 * test, we're guaranteed to hold at least one CRTC state mutex,
@@ -4349,6 +4357,7 @@ skl_compute_wm(struct drm_atomic_state *state)
 	 */
 	for_each_new_crtc_in_state(state, crtc, cstate, i)
 		changed = true;
+
 	if (!changed)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index c3780d0d2baf..559f1ab42bfc 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -435,8 +435,9 @@ static bool intel_psr_match_conditions(struct intel_dp *intel_dp)
 	}
 
 	/* PSR2 is restricted to work with panel resolutions upto 3200x2000 */
-	if (intel_crtc->config->pipe_src_w > 3200 ||
-				intel_crtc->config->pipe_src_h > 2000) {
+	if (dev_priv->psr.psr2_support &&
+	    (intel_crtc->config->pipe_src_w > 3200 ||
+	     intel_crtc->config->pipe_src_h > 2000)) {
 		dev_priv->psr.psr2_support = false;
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 8c87c717c7cd..e6517edcd16b 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -83,10 +83,13 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
  */
 void intel_pipe_update_start(struct intel_crtc *crtc)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
 	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
+	bool need_vlv_dsi_wa = (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+		intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DSI);
 	DEFINE_WAIT(wait);
 
 	vblank_start = adjusted_mode->crtc_vblank_start;
@@ -139,6 +142,24 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
 
 	drm_crtc_vblank_put(&crtc->base);
 
+	/*
+	 * On VLV/CHV DSI the scanline counter would appear to
+	 * increment approx. 1/3 of a scanline before start of vblank.
+	 * The registers still get latched at start of vblank however.
+	 * This means we must not write any registers on the first
+	 * line of vblank (since not the whole line is actually in
+	 * vblank). And unfortunately we can't use the interrupt to
+	 * wait here since it will fire too soon. We could use the
+	 * frame start interrupt instead since it will fire after the
+	 * critical scanline, but that would require more changes
+	 * in the interrupt code. So for now we'll just do the nasty
+	 * thing and poll for the bad scanline to pass us by.
+	 *
+	 * FIXME figure out if BXT+ DSI suffers from this as well
+	 */
+	while (need_vlv_dsi_wa && scanline == vblank_start)
+		scanline = intel_get_crtc_scanline(crtc);
+
 	crtc->debug.scanline_start = scanline;
 	crtc->debug.start_vbl_time = ktime_get();
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h
index 4b7f73aeddac..f84115261ae7 100644
--- a/drivers/gpu/drm/i915/intel_uc.h
+++ b/drivers/gpu/drm/i915/intel_uc.h
@@ -59,8 +59,6 @@ struct drm_i915_gem_request;
  *                available in the work queue (note, the queue is shared,
  *                not per-engine). It is OK for this to be nonzero, but
  *                it should not be huge!
- *   q_fail: failed to enqueue a work item. This should never happen,
- *           because we check for space beforehand.
  *   b_fail: failed to ring the doorbell. This should never happen, unless
  *           somehow the hardware misbehaves, or maybe if the GuC firmware
  *           crashes? We probably need to reset the GPU to recover.
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 8fb801fab039..8b05ecb8fdef 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -673,7 +673,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		ret = drm_of_find_panel_or_bridge(child,
 						  imx_ldb->lvds_mux ? 4 : 2, 0,
 						  &channel->panel, &channel->bridge);
-		if (ret)
+		if (ret && ret != -ENODEV)
 			return ret;
 
 		/* panel ddc only if there is no bridge */
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 808b995a990f..b5cc6e12334c 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -19,6 +19,7 @@
 #include <drm/drm_of.h>
 #include <linux/clk.h>
 #include <linux/component.h>
+#include <linux/iopoll.h>
 #include <linux/irq.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -900,16 +901,12 @@ static int mtk_dsi_host_detach(struct mipi_dsi_host *host,
 
 static void mtk_dsi_wait_for_idle(struct mtk_dsi *dsi)
 {
-	u32 timeout_ms = 500000; /* total 1s ~ 2s timeout */
-
-	while (timeout_ms--) {
-		if (!(readl(dsi->regs + DSI_INTSTA) & DSI_BUSY))
-			break;
-
-		usleep_range(2, 4);
-	}
+	int ret;
+	u32 val;
 
-	if (timeout_ms == 0) {
+	ret = readl_poll_timeout(dsi->regs + DSI_INTSTA, val, !(val & DSI_BUSY),
+				 4, 2000000);
+	if (ret) {
 		DRM_WARN("polling dsi wait not busy timeout!\n");
 
 		mtk_dsi_enable(dsi);
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 41a1c03b0347..0a4ffd724146 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1062,7 +1062,7 @@ static int mtk_hdmi_setup_vendor_specific_infoframe(struct mtk_hdmi *hdmi,
 	}
 
 	err = hdmi_vendor_infoframe_pack(&frame, buffer, sizeof(buffer));
-	if (err) {
+	if (err < 0) {
 		dev_err(hdmi->dev, "Failed to pack vendor infoframe: %zd\n",
 			err);
 		return err;
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 75382f5f0fce..10b227d83e9a 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -152,7 +152,7 @@ static struct regmap_config meson_regmap_config = {
 	.max_register   = 0x1000,
 };
 
-static int meson_drv_bind(struct device *dev)
+static int meson_drv_bind_master(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct meson_drm *priv;
@@ -233,10 +233,12 @@ static int meson_drv_bind(struct device *dev)
 	if (ret)
 		goto free_drm;
 
-	ret = component_bind_all(drm->dev, drm);
-	if (ret) {
-		dev_err(drm->dev, "Couldn't bind all components\n");
-		goto free_drm;
+	if (has_components) {
+		ret = component_bind_all(drm->dev, drm);
+		if (ret) {
+			dev_err(drm->dev, "Couldn't bind all components\n");
+			goto free_drm;
+		}
 	}
 
 	ret = meson_plane_create(priv);
@@ -276,6 +278,11 @@ free_drm:
 	return ret;
 }
 
+static int meson_drv_bind(struct device *dev)
+{
+	return meson_drv_bind_master(dev, true);
+}
+
 static void meson_drv_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
@@ -357,6 +364,9 @@ static int meson_drv_probe(struct platform_device *pdev)
 		count += meson_probe_remote(pdev, &match, np, remote);
 	}
 
+	if (count && !match)
+		return meson_drv_bind_master(&pdev->dev, false);
+
 	/* If some endpoints were found, initialize the nodes */
 	if (count) {
 		dev_info(&pdev->dev, "Queued %d outputs on vpu\n", count);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
index 6a567fe347b3..820a4805916f 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
@@ -4,6 +4,7 @@
 
 struct nvkm_alarm {
 	struct list_head head;
+	struct list_head exec;
 	u64 timestamp;
 	void (*func)(struct nvkm_alarm *);
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 36268e1802b5..15a13d09d431 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -80,7 +80,7 @@ int nouveau_modeset = -1;
 module_param_named(modeset, nouveau_modeset, int, 0400);
 
 MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
-int nouveau_runtime_pm = -1;
+static int nouveau_runtime_pm = -1;
 module_param_named(runpm, nouveau_runtime_pm, int, 0400);
 
 static struct drm_driver driver_stub;
@@ -495,7 +495,7 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags)
 	nouveau_fbcon_init(dev);
 	nouveau_led_init(dev);
 
-	if (nouveau_runtime_pm != 0) {
+	if (nouveau_pmops_runtime()) {
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
 		pm_runtime_set_active(dev->dev);
@@ -527,7 +527,7 @@ nouveau_drm_unload(struct drm_device *dev)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
-	if (nouveau_runtime_pm != 0) {
+	if (nouveau_pmops_runtime()) {
 		pm_runtime_get_sync(dev->dev);
 		pm_runtime_forbid(dev->dev);
 	}
@@ -726,6 +726,14 @@ nouveau_pmops_thaw(struct device *dev)
 	return nouveau_do_resume(drm_dev, false);
 }
 
+bool
+nouveau_pmops_runtime()
+{
+	if (nouveau_runtime_pm == -1)
+		return nouveau_is_optimus() || nouveau_is_v1_dsm();
+	return nouveau_runtime_pm == 1;
+}
+
 static int
 nouveau_pmops_runtime_suspend(struct device *dev)
 {
@@ -733,14 +741,7 @@ nouveau_pmops_runtime_suspend(struct device *dev)
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (nouveau_runtime_pm == 0) {
-		pm_runtime_forbid(dev);
-		return -EBUSY;
-	}
-
-	/* are we optimus enabled? */
-	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
-		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+	if (!nouveau_pmops_runtime()) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
@@ -765,8 +766,10 @@ nouveau_pmops_runtime_resume(struct device *dev)
 	struct nvif_device *device = &nouveau_drm(drm_dev)->client.device;
 	int ret;
 
-	if (nouveau_runtime_pm == 0)
-		return -EINVAL;
+	if (!nouveau_pmops_runtime()) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
@@ -796,14 +799,7 @@ nouveau_pmops_runtime_idle(struct device *dev)
 	struct nouveau_drm *drm = nouveau_drm(drm_dev);
 	struct drm_crtc *crtc;
 
-	if (nouveau_runtime_pm == 0) {
-		pm_runtime_forbid(dev);
-		return -EBUSY;
-	}
-
-	/* are we optimus enabled? */
-	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
-		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+	if (!nouveau_pmops_runtime()) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index eadec2f49ad3..a11b6aaed325 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -108,8 +108,6 @@ nouveau_cli(struct drm_file *fpriv)
 #include <nvif/object.h>
 #include <nvif/device.h>
 
-extern int nouveau_runtime_pm;
-
 struct nouveau_drm {
 	struct nouveau_cli client;
 	struct drm_device *dev;
@@ -195,6 +193,7 @@ nouveau_drm(struct drm_device *dev)
 
 int nouveau_pmops_suspend(struct device *);
 int nouveau_pmops_resume(struct device *);
+bool nouveau_pmops_runtime(void);
 
 #include <nvkm/core/tegra.h>
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index a4aacbc0cec8..02fe0efb9e16 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -87,7 +87,7 @@ void
 nouveau_vga_init(struct nouveau_drm *drm)
 {
 	struct drm_device *dev = drm->dev;
-	bool runtime = false;
+	bool runtime = nouveau_pmops_runtime();
 
 	/* only relevant for PCI devices */
 	if (!dev->pdev)
@@ -99,10 +99,6 @@ nouveau_vga_init(struct nouveau_drm *drm)
 	if (pci_is_thunderbolt_attached(dev->pdev))
 		return;
 
-	if (nouveau_runtime_pm == 1)
-		runtime = true;
-	if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
-		runtime = true;
 	vga_switcheroo_register_client(dev->pdev, &nouveau_switcheroo_ops, runtime);
 
 	if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
@@ -113,18 +109,13 @@ void
 nouveau_vga_fini(struct nouveau_drm *drm)
 {
 	struct drm_device *dev = drm->dev;
-	bool runtime = false;
+	bool runtime = nouveau_pmops_runtime();
 
 	vga_client_register(dev->pdev, NULL, NULL, NULL);
 
 	if (pci_is_thunderbolt_attached(dev->pdev))
 		return;
 
-	if (nouveau_runtime_pm == 1)
-		runtime = true;
-	if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
-		runtime = true;
-
 	vga_switcheroo_unregister_client(dev->pdev);
 	if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
 		vga_switcheroo_fini_domain_pm_ops(drm->dev->dev);
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index a7663249b3ba..06e564a9ccb2 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -2107,7 +2107,8 @@ nv50_head_atomic_check(struct drm_crtc *crtc, struct drm_crtc_state *state)
 					asyc->set.dither = true;
 			}
 		} else {
-			asyc->set.mask = ~0;
+			if (asyc)
+				asyc->set.mask = ~0;
 			asyh->set.mask = ~0;
 		}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
index f2a86eae0a0d..2437f7d41ca2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
@@ -50,7 +50,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 		/* Move to completed list.  We'll drop the lock before
 		 * executing the callback so it can reschedule itself.
 		 */
-		list_move_tail(&alarm->head, &exec);
+		list_del_init(&alarm->head);
+		list_add(&alarm->exec, &exec);
 	}
 
 	/* Shut down interrupt if no more pending alarms. */
@@ -59,8 +60,8 @@ nvkm_timer_alarm_trigger(struct nvkm_timer *tmr)
 	spin_unlock_irqrestore(&tmr->lock, flags);
 
 	/* Execute completed callbacks. */
-	list_for_each_entry_safe(alarm, atemp, &exec, head) {
-		list_del_init(&alarm->head);
+	list_for_each_entry_safe(alarm, atemp, &exec, exec) {
+		list_del(&alarm->exec);
 		alarm->func(alarm);
 	}
 }
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index d8fa7a9c9240..ce5f2d1f9994 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -245,8 +245,6 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder,
 				      struct drm_connector_state *conn_state)
 {
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
-	struct rockchip_dp_device *dp = to_dp(encoder);
-	int ret;
 
 	/*
 	 * The hardware IC designed that VOP must output the RGB10 video
@@ -258,16 +256,6 @@ rockchip_dp_drm_encoder_atomic_check(struct drm_encoder *encoder,
 
 	s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
 	s->output_type = DRM_MODE_CONNECTOR_eDP;
-	if (dp->data->chip_type == RK3399_EDP) {
-		/*
-		 * For RK3399, VOP Lit must code the out mode to RGB888,
-		 * VOP Big must code the out mode to RGB10.
-		 */
-		ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node,
-							encoder);
-		if (ret > 0)
-			s->output_mode = ROCKCHIP_OUT_MODE_P888;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index a2169dd3d26b..14fa1f8351e8 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -615,7 +615,6 @@ static void cdn_dp_encoder_enable(struct drm_encoder *encoder)
 {
 	struct cdn_dp_device *dp = encoder_to_dp(encoder);
 	int ret, val;
-	struct rockchip_crtc_state *state;
 
 	ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, encoder);
 	if (ret < 0) {
@@ -625,14 +624,10 @@ static void cdn_dp_encoder_enable(struct drm_encoder *encoder)
 
 	DRM_DEV_DEBUG_KMS(dp->dev, "vop %s output to cdn-dp\n",
 			  (ret) ? "LIT" : "BIG");
-	state = to_rockchip_crtc_state(encoder->crtc->state);
-	if (ret) {
+	if (ret)
 		val = DP_SEL_VOP_LIT | (DP_SEL_VOP_LIT << 16);
-		state->output_mode = ROCKCHIP_OUT_MODE_P888;
-	} else {
+	else
 		val = DP_SEL_VOP_LIT << 16;
-		state->output_mode = ROCKCHIP_OUT_MODE_AAAA;
-	}
 
 	ret = cdn_dp_grf_write(dp, GRF_SOC_CON9, val);
 	if (ret)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 3f7a82d1e095..45589d6ce65e 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -875,6 +875,7 @@ static bool vop_crtc_mode_fixup(struct drm_crtc *crtc,
 static void vop_crtc_enable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
+	const struct vop_data *vop_data = vop->data;
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc->state);
 	struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
 	u16 hsync_len = adjusted_mode->hsync_end - adjusted_mode->hsync_start;
@@ -967,6 +968,13 @@ static void vop_crtc_enable(struct drm_crtc *crtc)
 		DRM_DEV_ERROR(vop->dev, "unsupported connector_type [%d]\n",
 			      s->output_type);
 	}
+
+	/*
+	 * if vop is not support RGB10 output, need force RGB10 to RGB888.
+	 */
+	if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
+	    !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10))
+		s->output_mode = ROCKCHIP_OUT_MODE_P888;
 	VOP_CTRL_SET(vop, out_mode, s->output_mode);
 
 	VOP_CTRL_SET(vop, htotal_pw, (htotal << 16) | hsync_len);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 5a4faa85dbd2..9979fd0c2282 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -142,6 +142,9 @@ struct vop_data {
 	const struct vop_intr *intr;
 	const struct vop_win_data *win;
 	unsigned int win_size;
+
+#define VOP_FEATURE_OUTPUT_RGB10	BIT(0)
+	u64 feature;
 };
 
 /* interrupt define */
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
index 0da44442aab0..bafd698a28b1 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
@@ -275,6 +275,7 @@ static const struct vop_intr rk3288_vop_intr = {
 static const struct vop_data rk3288_vop = {
 	.init_table = rk3288_init_reg_table,
 	.table_size = ARRAY_SIZE(rk3288_init_reg_table),
+	.feature = VOP_FEATURE_OUTPUT_RGB10,
 	.intr = &rk3288_vop_intr,
 	.ctrl = &rk3288_ctrl_data,
 	.win = rk3288_vop_win_data,
@@ -343,6 +344,7 @@ static const struct vop_reg_data rk3399_init_reg_table[] = {
 static const struct vop_data rk3399_vop_big = {
 	.init_table = rk3399_init_reg_table,
 	.table_size = ARRAY_SIZE(rk3399_init_reg_table),
+	.feature = VOP_FEATURE_OUTPUT_RGB10,
 	.intr = &rk3399_vop_intr,
 	.ctrl = &rk3399_ctrl_data,
 	/*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 130d51c5ec6a..4b948fba9eec 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -41,9 +41,9 @@
 #include <drm/ttm/ttm_module.h>
 #include "vmwgfx_fence.h"
 
-#define VMWGFX_DRIVER_DATE "20170221"
+#define VMWGFX_DRIVER_DATE "20170607"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 12
+#define VMWGFX_DRIVER_MINOR 13
 #define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index b6a0806b06bf..a1c68e6a689e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -368,6 +368,8 @@ static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv,
 				return fifo_state->static_buffer;
 			else {
 				fifo_state->dynamic_buffer = vmalloc(bytes);
+				if (!fifo_state->dynamic_buffer)
+					goto out_err;
 				return fifo_state->dynamic_buffer;
 			}
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index ef9f3a2a4030..1d2db5d912b0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -274,108 +274,6 @@ void vmw_kms_cursor_post_execbuf(struct vmw_private *dev_priv)
 }
 
 
-
-/**
- * vmw_du_cursor_plane_update() - Update cursor image and location
- *
- * @plane: plane object to update
- * @crtc: owning CRTC of @plane
- * @fb: framebuffer to flip onto plane
- * @crtc_x: x offset of plane on crtc
- * @crtc_y: y offset of plane on crtc
- * @crtc_w: width of plane rectangle on crtc
- * @crtc_h: height of plane rectangle on crtc
- * @src_x: Not used
- * @src_y: Not used
- * @src_w: Not used
- * @src_h: Not used
- *
- *
- * RETURNS:
- * Zero on success, error code on failure
- */
-int vmw_du_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 vmw_private *dev_priv = vmw_priv(crtc->dev);
-	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
-	struct vmw_surface *surface = NULL;
-	struct vmw_dma_buffer *dmabuf = NULL;
-	s32 hotspot_x, hotspot_y;
-	int ret;
-
-	hotspot_x = du->hotspot_x + fb->hot_x;
-	hotspot_y = du->hotspot_y + fb->hot_y;
-
-	/* A lot of the code assumes this */
-	if (crtc_w != 64 || crtc_h != 64) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (vmw_framebuffer_to_vfb(fb)->dmabuf)
-		dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer;
-	else
-		surface = vmw_framebuffer_to_vfbs(fb)->surface;
-
-	if (surface && !surface->snooper.image) {
-		DRM_ERROR("surface not suitable for cursor\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* setup new image */
-	ret = 0;
-	if (surface) {
-		/* vmw_user_surface_lookup takes one reference */
-		du->cursor_surface = surface;
-
-		du->cursor_age = du->cursor_surface->snooper.age;
-
-		ret = vmw_cursor_update_image(dev_priv, surface->snooper.image,
-					      64, 64, hotspot_x, hotspot_y);
-	} else if (dmabuf) {
-		/* vmw_user_surface_lookup takes one reference */
-		du->cursor_dmabuf = dmabuf;
-
-		ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, crtc_w, crtc_h,
-					       hotspot_x, hotspot_y);
-	} else {
-		vmw_cursor_update_position(dev_priv, false, 0, 0);
-		goto out;
-	}
-
-	if (!ret) {
-		du->cursor_x = crtc_x + du->set_gui_x;
-		du->cursor_y = crtc_y + du->set_gui_y;
-
-		vmw_cursor_update_position(dev_priv, true,
-					   du->cursor_x + hotspot_x,
-					   du->cursor_y + hotspot_y);
-	}
-
-out:
-	return ret;
-}
-
-
-int vmw_du_cursor_plane_disable(struct drm_plane *plane)
-{
-	if (plane->fb) {
-		drm_framebuffer_unreference(plane->fb);
-		plane->fb = NULL;
-	}
-
-	return -EINVAL;
-}
-
-
 void vmw_du_cursor_plane_destroy(struct drm_plane *plane)
 {
 	vmw_cursor_update_position(plane->dev->dev_private, false, 0, 0);
@@ -473,18 +371,6 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 
 
 void
-vmw_du_cursor_plane_atomic_disable(struct drm_plane *plane,
-				   struct drm_plane_state *old_state)
-{
-	struct drm_crtc *crtc = plane->state->crtc ?: old_state->crtc;
-	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
-
-	drm_atomic_set_fb_for_plane(plane->state, NULL);
-	vmw_cursor_update_position(dev_priv, false, 0, 0);
-}
-
-
-void
 vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 				  struct drm_plane_state *old_state)
 {
@@ -1498,6 +1384,7 @@ vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
 	 */
 	if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)  &&
 	    dmabuf && only_2d &&
+	    mode_cmd->width > 64 &&  /* Don't create a proxy for cursor */
 	    dev_priv->active_display_unit == vmw_du_screen_target) {
 		ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd,
 					      dmabuf, &surface);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 13f2f1d2818a..5f8d678ae675 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -256,10 +256,6 @@ int vmw_du_crtc_gamma_set(struct drm_crtc *crtc,
 			   u16 *r, u16 *g, u16 *b,
 			   uint32_t size,
 			   struct drm_modeset_acquire_ctx *ctx);
-int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv,
-			    uint32_t handle, uint32_t width, uint32_t height,
-			    int32_t hot_x, int32_t hot_y);
-int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
 int vmw_du_connector_set_property(struct drm_connector *connector,
 				  struct drm_property *property,
 				  uint64_t val);
@@ -339,15 +335,6 @@ void vmw_kms_create_implicit_placement_property(struct vmw_private *dev_priv,
 /* Universal Plane Helpers */
 void vmw_du_primary_plane_destroy(struct drm_plane *plane);
 void vmw_du_cursor_plane_destroy(struct drm_plane *plane);
-int vmw_du_cursor_plane_disable(struct drm_plane *plane);
-int vmw_du_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);
 
 /* Atomic Helpers */
 int vmw_du_primary_plane_atomic_check(struct drm_plane *plane,
@@ -356,8 +343,6 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
 				     struct drm_plane_state *state);
 void vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 				       struct drm_plane_state *old_state);
-void vmw_du_cursor_plane_atomic_disable(struct drm_plane *plane,
-					struct drm_plane_state *old_state);
 int vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 				   struct drm_plane_state *new_state);
 void vmw_du_plane_cleanup_fb(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index bad31bdf09b6..50be1f034f9e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -56,6 +56,8 @@ enum stdu_content_type {
  * @right: Right side of bounding box.
  * @top: Top side of bounding box.
  * @bottom: Bottom side of bounding box.
+ * @fb_left: Left side of the framebuffer/content bounding box
+ * @fb_top: Top of the framebuffer/content bounding box
  * @buf: DMA buffer when DMA-ing between buffer and screen targets.
  * @sid: Surface ID when copying between surface and screen targets.
  */
@@ -63,6 +65,7 @@ struct vmw_stdu_dirty {
 	struct vmw_kms_dirty base;
 	SVGA3dTransferType  transfer;
 	s32 left, right, top, bottom;
+	s32 fb_left, fb_top;
 	u32 pitch;
 	union {
 		struct vmw_dma_buffer *buf;
@@ -647,7 +650,7 @@ static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
  *
  * @dirty: The closure structure.
  *
- * This function calculates the bounding box for all the incoming clips
+ * This function calculates the bounding box for all the incoming clips.
  */
 static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
 {
@@ -656,11 +659,19 @@ static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
 
 	dirty->num_hits = 1;
 
-	/* Calculate bounding box */
+	/* Calculate destination bounding box */
 	ddirty->left = min_t(s32, ddirty->left, dirty->unit_x1);
 	ddirty->top = min_t(s32, ddirty->top, dirty->unit_y1);
 	ddirty->right = max_t(s32, ddirty->right, dirty->unit_x2);
 	ddirty->bottom = max_t(s32, ddirty->bottom, dirty->unit_y2);
+
+	/*
+	 * Calculate content bounding box.  We only need the top-left
+	 * coordinate because width and height will be the same as the
+	 * destination bounding box above
+	 */
+	ddirty->fb_left = min_t(s32, ddirty->fb_left, dirty->fb_x);
+	ddirty->fb_top  = min_t(s32, ddirty->fb_top, dirty->fb_y);
 }
 
 
@@ -697,11 +708,11 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
 	/* Assume we are blitting from Host (display_srf) to Guest (dmabuf) */
 	src_pitch = stdu->display_srf->base_size.width * stdu->cpp;
 	src = ttm_kmap_obj_virtual(&stdu->host_map, &not_used);
-	src += dirty->unit_y1 * src_pitch + dirty->unit_x1 * stdu->cpp;
+	src += ddirty->top * src_pitch + ddirty->left * stdu->cpp;
 
 	dst_pitch = ddirty->pitch;
 	dst = ttm_kmap_obj_virtual(&stdu->guest_map, &not_used);
-	dst += dirty->fb_y * dst_pitch + dirty->fb_x * stdu->cpp;
+	dst += ddirty->fb_top * dst_pitch + ddirty->fb_left * stdu->cpp;
 
 
 	/* Figure out the real direction */
@@ -760,7 +771,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
 	}
 
 out_cleanup:
-	ddirty->left = ddirty->top = S32_MAX;
+	ddirty->left = ddirty->top = ddirty->fb_left = ddirty->fb_top = S32_MAX;
 	ddirty->right = ddirty->bottom = S32_MIN;
 }
 
@@ -812,6 +823,7 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 		SVGA3D_READ_HOST_VRAM;
 	ddirty.left = ddirty.top = S32_MAX;
 	ddirty.right = ddirty.bottom = S32_MIN;
+	ddirty.fb_left = ddirty.fb_top = S32_MAX;
 	ddirty.pitch = vfb->base.pitches[0];
 	ddirty.buf = buf;
 	ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit;
@@ -1355,6 +1367,11 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 		DRM_ERROR("Failed to bind surface to STDU.\n");
 	else
 		crtc->primary->fb = plane->state->fb;
+
+	ret = vmw_stdu_update_st(dev_priv, stdu);
+
+	if (ret)
+		DRM_ERROR("Failed to update STDU.\n");
 }
 
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 7681341fe32b..6b70bd259953 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1274,11 +1274,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	int ret;
 	uint32_t size;
-	uint32_t backup_handle;
+	uint32_t backup_handle = 0;
 
 	if (req->multisample_count != 0)
 		return -EINVAL;
 
+	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
 	if (unlikely(vmw_user_surface_size == 0))
 		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
 			128;
@@ -1314,12 +1317,16 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
 					     &res->backup,
 					     &user_srf->backup_base);
-		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
-		    res->backup_size) {
-			DRM_ERROR("Surface backup buffer is too small.\n");
-			vmw_dmabuf_unreference(&res->backup);
-			ret = -EINVAL;
-			goto out_unlock;
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer is too small.\n");
+				vmw_dmabuf_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->buffer_handle;
+			}
 		}
 	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
 		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
@@ -1491,7 +1498,7 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 				 dev_priv->stdu_max_height);
 
 		if (size.width > max_width || size.height > max_height) {
-			DRM_ERROR("%ux%u\n, exeeds max surface size %ux%u",
+			DRM_ERROR("%ux%u\n, exceeds max surface size %ux%u",
 				  size.width, size.height,
 				  max_width, max_height);
 			return -EINVAL;
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 16d556816b5f..2fb5f432a54c 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -725,15 +725,16 @@ void ipu_set_ic_src_mux(struct ipu_soc *ipu, int csi_id, bool vdi)
 	spin_lock_irqsave(&ipu->lock, flags);
 
 	val = ipu_cm_read(ipu, IPU_CONF);
-	if (vdi) {
+	if (vdi)
 		val |= IPU_CONF_IC_INPUT;
-	} else {
+	else
 		val &= ~IPU_CONF_IC_INPUT;
-		if (csi_id == 1)
-			val |= IPU_CONF_CSI_SEL;
-		else
-			val &= ~IPU_CONF_CSI_SEL;
-	}
+
+	if (csi_id == 1)
+		val |= IPU_CONF_CSI_SEL;
+	else
+		val &= ~IPU_CONF_CSI_SEL;
+
 	ipu_cm_write(ipu, val, IPU_CONF);
 
 	spin_unlock_irqrestore(&ipu->lock, flags);
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index c55563379e2e..c35f74c83065 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -131,8 +131,6 @@ int ipu_pre_get(struct ipu_pre *pre)
 	if (pre->in_use)
 		return -EBUSY;
 
-	clk_prepare_enable(pre->clk_axi);
-
 	/* first get the engine out of reset and remove clock gating */
 	writel(0, pre->regs + IPU_PRE_CTRL);
 
@@ -149,12 +147,7 @@ int ipu_pre_get(struct ipu_pre *pre)
 
 void ipu_pre_put(struct ipu_pre *pre)
 {
-	u32 val;
-
-	val = IPU_PRE_CTRL_SFTRST | IPU_PRE_CTRL_CLKGATE;
-	writel(val, pre->regs + IPU_PRE_CTRL);
-
-	clk_disable_unprepare(pre->clk_axi);
+	writel(IPU_PRE_CTRL_SFTRST, pre->regs + IPU_PRE_CTRL);
 
 	pre->in_use = false;
 }
@@ -249,6 +242,8 @@ static int ipu_pre_probe(struct platform_device *pdev)
 	if (!pre->buffer_virt)
 		return -ENOMEM;
 
+	clk_prepare_enable(pre->clk_axi);
+
 	pre->dev = dev;
 	platform_set_drvdata(pdev, pre);
 	mutex_lock(&ipu_pre_list_mutex);
@@ -268,6 +263,8 @@ static int ipu_pre_remove(struct platform_device *pdev)
 	available_pres--;
 	mutex_unlock(&ipu_pre_list_mutex);
 
+	clk_disable_unprepare(pre->clk_axi);
+
 	if (pre->buffer_virt)
 		gen_pool_free(pre->iram, (unsigned long)pre->buffer_virt,
 			      IPU_PRE_MAX_WIDTH * IPU_PRE_NUM_SCANLINES * 4);