Merge tag 'drm-next-2019-05-09' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This has two exciting community drivers for ARM Mali accelerators.
  Since ARM has never been open source friendly on the GPU side of the
  house, the community has had to create open source drivers for the
  Mali GPUs. Lima covers the older t4xx and panfrost the newer 6xx/7xx
  series. Well done to all involved and hopefully this will help ARM
  head in the right direction.

  There is also now the ability if you don't have any of the legacy
  drivers enabled (pre-KMS) to remove all the pre-KMS support code from
  the core drm, this saves 10% or so in codesize on my machine.

  i915 also enable Icelake/Elkhart Lake Gen11 GPUs by default, vboxvideo
  moves out of staging.

  There are also some rcar-du patches which crossover with media tree
  but all should be acked by Mauro.

  Summary:

  uapi changes:
   - Colorspace connector property
   - fourcc - new YUV formts
   - timeline sync objects initially merged
   - expose FB_DAMAGE_CLIPS to atomic userspace

  new drivers:
   - vboxvideo: moved out of staging
   - aspeed: ASPEED SoC BMC chip display support
   - lima: ARM Mali4xx GPU acceleration driver support
   - panfrost: ARM Mali6xx/7xx Midgard/Bitfrost acceleration driver support

  core:
   - component helper docs
   - unplugging fixes
   - devm device init
   - MIPI/DSI rate control
   - shmem backed gem objects
   - connector, display_info, edid_quirks cleanups
   - dma_buf fence chain support
   - 64-bit dma-fence seqno comparison fixes
   - move initial fb config code to core
   - gem fence array helpers for Lima
   - ability to remove legacy support code if no drivers requires it (removes 10% of drm.ko size)
   - lease fixes

  ttm:
   - unified DRM_FILE_PAGE_OFFSET handling
   - Account for kernel allocations in kernel zone only

  panel:
   - OSD070T1718-19TS panel support
   - panel-tpo-td028ttec1 backlight support
   - Ronbo RB070D30 MIPI/DSI
   - Feiyang FY07024DI26A30-D MIPI-DSI panel
   - Rocktech jh057n00900 MIPI-DSI panel

  i915:
   - Comet Lake (Gen9) PCI IDs
   - Updated Icelake PCI IDs
   - Elkhartlake (Gen11) support
   - DP MST property addtions
   - plane and watermark fixes
   - Icelake port sync and VEBOX disable fixes
   - struct_mutex usage reduction
   - Icelake gamma fix
   - GuC reset fixes
   - make mmap more asynchronous
   - sound display power well race fixes
   - DDI/MIPI-DSI clocks for Icelake
   - Icelake RPS frequency changing support
   - Icelake workarounds

  amdgpu:
   - Use HMM for userptr
   - vega20 experimental smu11 support
   - RAS support for vega20
   - BACO support for vega12 + fixes for vega20
   - reworked IH interrupt handling
   - amdkfd RAS support
   - Freesync improvements
   - initial timeline sync object support
   - DC Z ordering fixes
   - NV12 planes support
   - colorspace properties for planes=
   - eDP opts if eDP already initialized

  nouveau:
   - misc fixes

  etnaviv:
   - misc fixes

  msm:
   - GPU zap shader support expansion
   - robustness ABI addition

  exynos:
   - Logging cleanups

  tegra:
   - Shared reset fix
   - CPU cache maintenance fix

  cirrus:
   - driver rewritten using simple helpers

  meson:
   - G12A support

  vmwgfx:
   - Resource dirtying management improvements
   - Userspace logging improvements

  virtio:
   - PRIME fixes

  rockchip:
   - rk3066 hdmi support

  sun4i:
   - DSI burst mode support

  vc4:
   - load tracker to detect underflow

  v3d:
   - v3d v4.2 support

  malidp:
   - initial Mali D71 support in komeda driver

  tfp410:
   - omap related improvement

  omapdrm:
   - drm bridge/panel support
   - drop some omap specific panels

  rcar-du:
   - Display writeback support"

* tag 'drm-next-2019-05-09' of git://anongit.freedesktop.org/drm/drm: (1507 commits)
  drm/msm/a6xx: No zap shader is not an error
  drm/cma-helper: Fix drm_gem_cma_free_object()
  drm: Fix timestamp docs for variable refresh properties.
  drm/komeda: Mark the local functions as static
  drm/komeda: Fixed warning: Function parameter or member not described
  drm/komeda: Expose bus_width to Komeda-CORE
  drm/komeda: Add sysfs attribute: core_id and config_id
  drm: add non-desktop quirk for Valve HMDs
  drm/panfrost: Show stored feature registers
  drm/panfrost: Don't scream about deferred probe
  drm/panfrost: Disable PM on probe failure
  drm/panfrost: Set DMA masks earlier
  drm/panfrost: Add sanity checks to submit IOCTL
  drm/etnaviv: initialize idle mask before querying the HW db
  drm: introduce a capability flag for syncobj timeline support
  drm: report consistent errors when checking syncobj capibility
  drm/nouveau/nouveau: forward error generated while resuming objects tree
  drm/nouveau/fb/ramgk104: fix spelling mistake "sucessfully" -> "successfully"
  drm/nouveau/i2c: Disable i2c bus access after ->fini()
  drm/nouveau: Remove duplicate ACPI_VIDEO_NOTIFY_PROBE definition
  ...

14 files changed, 369 insertions, 153 deletions

diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 4c0d51f73237..4e5922c89d7b 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -361,13 +361,6 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	paddr = drm_fb_cma_get_gem_addr(fb, state, 0);
 	DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr);
 
-	/*
-	 * backend DMA accesses DRAM directly, bypassing the system
-	 * bus. As such, the address range is different and the buffer
-	 * address needs to be corrected.
-	 */
-	paddr -= PHYS_OFFSET;
-
 	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_buffer(backend, fb, paddr);
 
@@ -720,33 +713,22 @@ static int sun4i_backend_free_sat(struct device *dev) {
  */
 static int sun4i_backend_of_get_id(struct device_node *node)
 {
-	struct device_node *port, *ep;
-	int ret = -EINVAL;
+	struct device_node *ep, *remote;
+	struct of_endpoint of_ep;
 
-	/* input is port 0 */
-	port = of_graph_get_port_by_id(node, 0);
-	if (!port)
+	/* Input port is 0, and we want the first endpoint. */
+	ep = of_graph_get_endpoint_by_regs(node, 0, -1);
+	if (!ep)
 		return -EINVAL;
 
-	/* try finding an upstream endpoint */
-	for_each_available_child_of_node(port, ep) {
-		struct device_node *remote;
-		u32 reg;
-
-		remote = of_graph_get_remote_endpoint(ep);
-		if (!remote)
-			continue;
-
-		ret = of_property_read_u32(remote, "reg", &reg);
-		if (ret)
-			continue;
-
-		ret = reg;
-	}
-
-	of_node_put(port);
+	remote = of_graph_get_remote_endpoint(ep);
+	of_node_put(ep);
+	if (!remote)
+		return -EINVAL;
 
-	return ret;
+	of_graph_parse_endpoint(remote, &of_ep);
+	of_node_put(remote);
+	return of_ep.id;
 }
 
 /* TODO: This needs to take multiple pipelines into account */
@@ -814,6 +796,27 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 	dev_set_drvdata(dev, backend);
 	spin_lock_init(&backend->frontend_lock);
 
+	if (of_find_property(dev->of_node, "interconnects", NULL)) {
+		/*
+		 * This assume we have the same DMA constraints for all our the
+		 * devices in our pipeline (all the backends, but also the
+		 * frontends). This sounds bad, but it has always been the case
+		 * for us, and DRM doesn't do per-device allocation either, so
+		 * we would need to fix DRM first...
+		 */
+		ret = of_dma_configure(drm->dev, dev->of_node, true);
+		if (ret)
+			return ret;
+	} else {
+		/*
+		 * If we don't have the interconnect property, most likely
+		 * because of an old DT, we need to set the DMA offset by hand
+		 * on our device since the RAM mapping is at 0 for the DMA bus,
+		 * unlike the CPU.
+		 */
+		drm->dev->dma_pfn_offset = PHYS_PFN_OFFSET;
+	}
+
 	backend->engine.node = dev->of_node;
 	backend->engine.ops = &sun4i_backend_engine_ops;
 	backend->engine.id = sun4i_backend_of_get_id(dev->of_node);
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi.h b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
index b685ee11623d..b08c4453d47c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi.h
@@ -269,6 +269,7 @@ struct sun4i_hdmi {
 	struct clk		*tmds_clk;
 
 	struct i2c_adapter	*i2c;
+	struct i2c_adapter	*ddc_i2c;
 
 	/* Regmap fields for I2C adapter */
 	struct regmap_field	*field_ddc_en;
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index d18862629301..8c122e637697 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -217,7 +217,7 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector)
 	struct edid *edid;
 	int ret;
 
-	edid = drm_get_edid(connector, hdmi->i2c);
+	edid = drm_get_edid(connector, hdmi->ddc_i2c ?: hdmi->i2c);
 	if (!edid)
 		return 0;
 
@@ -233,6 +233,28 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
+static struct i2c_adapter *sun4i_hdmi_get_ddc(struct device *dev)
+{
+	struct device_node *phandle, *remote;
+	struct i2c_adapter *ddc;
+
+	remote = of_graph_get_remote_node(dev->of_node, 1, -1);
+	if (!remote)
+		return ERR_PTR(-EINVAL);
+
+	phandle = of_parse_phandle(remote, "ddc-i2c-bus", 0);
+	of_node_put(remote);
+	if (!phandle)
+		return ERR_PTR(-ENODEV);
+
+	ddc = of_get_i2c_adapter_by_node(phandle);
+	of_node_put(phandle);
+	if (!ddc)
+		return ERR_PTR(-EPROBE_DEFER);
+
+	return ddc;
+}
+
 static const struct drm_connector_helper_funcs sun4i_hdmi_connector_helper_funcs = {
 	.get_modes	= sun4i_hdmi_get_modes,
 };
@@ -580,6 +602,15 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 		goto err_disable_mod_clk;
 	}
 
+	hdmi->ddc_i2c = sun4i_hdmi_get_ddc(dev);
+	if (IS_ERR(hdmi->ddc_i2c)) {
+		ret = PTR_ERR(hdmi->ddc_i2c);
+		if (ret == -ENODEV)
+			hdmi->ddc_i2c = NULL;
+		else
+			goto err_del_i2c_adapter;
+	}
+
 	drm_encoder_helper_add(&hdmi->encoder,
 			       &sun4i_hdmi_helper_funcs);
 	ret = drm_encoder_init(drm,
@@ -589,14 +620,14 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 			       NULL);
 	if (ret) {
 		dev_err(dev, "Couldn't initialise the HDMI encoder\n");
-		goto err_del_i2c_adapter;
+		goto err_put_ddc_i2c;
 	}
 
 	hdmi->encoder.possible_crtcs = drm_of_find_possible_crtcs(drm,
 								  dev->of_node);
 	if (!hdmi->encoder.possible_crtcs) {
 		ret = -EPROBE_DEFER;
-		goto err_del_i2c_adapter;
+		goto err_put_ddc_i2c;
 	}
 
 #ifdef CONFIG_DRM_SUN4I_HDMI_CEC
@@ -635,6 +666,8 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 err_cleanup_connector:
 	cec_delete_adapter(hdmi->cec_adap);
 	drm_encoder_cleanup(&hdmi->encoder);
+err_put_ddc_i2c:
+	i2c_put_adapter(hdmi->ddc_i2c);
 err_del_i2c_adapter:
 	i2c_del_adapter(hdmi->i2c);
 err_disable_mod_clk:
@@ -655,6 +688,7 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master,
 	drm_connector_cleanup(&hdmi->connector);
 	drm_encoder_cleanup(&hdmi->encoder);
 	i2c_del_adapter(hdmi->i2c);
+	i2c_put_adapter(hdmi->ddc_i2c);
 	clk_disable_unprepare(hdmi->mod_clk);
 	clk_disable_unprepare(hdmi->bus_clk);
 }
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index 147b97ed1a09..3a3ba99fed22 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -20,7 +20,7 @@ struct sun4i_lvds {
 	struct drm_connector	connector;
 	struct drm_encoder	encoder;
 
-	struct sun4i_tcon	*tcon;
+	struct drm_panel	*panel;
 };
 
 static inline struct sun4i_lvds *
@@ -41,9 +41,8 @@ static int sun4i_lvds_get_modes(struct drm_connector *connector)
 {
 	struct sun4i_lvds *lvds =
 		drm_connector_to_sun4i_lvds(connector);
-	struct sun4i_tcon *tcon = lvds->tcon;
 
-	return drm_panel_get_modes(tcon->panel);
+	return drm_panel_get_modes(lvds->panel);
 }
 
 static struct drm_connector_helper_funcs sun4i_lvds_con_helper_funcs = {
@@ -54,9 +53,8 @@ static void
 sun4i_lvds_connector_destroy(struct drm_connector *connector)
 {
 	struct sun4i_lvds *lvds = drm_connector_to_sun4i_lvds(connector);
-	struct sun4i_tcon *tcon = lvds->tcon;
 
-	drm_panel_detach(tcon->panel);
+	drm_panel_detach(lvds->panel);
 	drm_connector_cleanup(connector);
 }
 
@@ -71,26 +69,24 @@ static const struct drm_connector_funcs sun4i_lvds_con_funcs = {
 static void sun4i_lvds_encoder_enable(struct drm_encoder *encoder)
 {
 	struct sun4i_lvds *lvds = drm_encoder_to_sun4i_lvds(encoder);
-	struct sun4i_tcon *tcon = lvds->tcon;
 
 	DRM_DEBUG_DRIVER("Enabling LVDS output\n");
 
-	if (tcon->panel) {
-		drm_panel_prepare(tcon->panel);
-		drm_panel_enable(tcon->panel);
+	if (lvds->panel) {
+		drm_panel_prepare(lvds->panel);
+		drm_panel_enable(lvds->panel);
 	}
 }
 
 static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder)
 {
 	struct sun4i_lvds *lvds = drm_encoder_to_sun4i_lvds(encoder);
-	struct sun4i_tcon *tcon = lvds->tcon;
 
 	DRM_DEBUG_DRIVER("Disabling LVDS output\n");
 
-	if (tcon->panel) {
-		drm_panel_disable(tcon->panel);
-		drm_panel_unprepare(tcon->panel);
+	if (lvds->panel) {
+		drm_panel_disable(lvds->panel);
+		drm_panel_unprepare(lvds->panel);
 	}
 }
 
@@ -113,11 +109,10 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	lvds = devm_kzalloc(drm->dev, sizeof(*lvds), GFP_KERNEL);
 	if (!lvds)
 		return -ENOMEM;
-	lvds->tcon = tcon;
 	encoder = &lvds->encoder;
 
 	ret = drm_of_find_panel_or_bridge(tcon->dev->of_node, 1, 0,
-					  &tcon->panel, &bridge);
+					  &lvds->panel, &bridge);
 	if (ret) {
 		dev_info(drm->dev, "No panel or bridge found... LVDS output disabled\n");
 		return 0;
@@ -138,7 +133,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	/* The LVDS encoder can only work with the TCON channel 0 */
 	lvds->encoder.possible_crtcs = drm_crtc_mask(&tcon->crtc->crtc);
 
-	if (tcon->panel) {
+	if (lvds->panel) {
 		drm_connector_helper_add(&lvds->connector,
 					 &sun4i_lvds_con_helper_funcs);
 		ret = drm_connector_init(drm, &lvds->connector,
@@ -152,7 +147,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 		drm_connector_attach_encoder(&lvds->connector,
 						  &lvds->encoder);
 
-		ret = drm_panel_attach(tcon->panel, &lvds->connector);
+		ret = drm_panel_attach(lvds->panel, &lvds->connector);
 		if (ret) {
 			dev_err(drm->dev, "Couldn't attach our panel\n");
 			goto err_cleanup_connector;
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index cae19e7bbeaa..d9e2502b49fa 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -27,6 +27,8 @@ struct sun4i_rgb {
 	struct drm_encoder	encoder;
 
 	struct sun4i_tcon	*tcon;
+	struct drm_panel	*panel;
+	struct drm_bridge	*bridge;
 };
 
 static inline struct sun4i_rgb *
@@ -47,11 +49,18 @@ static int sun4i_rgb_get_modes(struct drm_connector *connector)
 {
 	struct sun4i_rgb *rgb =
 		drm_connector_to_sun4i_rgb(connector);
-	struct sun4i_tcon *tcon = rgb->tcon;
 
-	return drm_panel_get_modes(tcon->panel);
+	return drm_panel_get_modes(rgb->panel);
 }
 
+/*
+ * VESA DMT defines a tolerance of 0.5% on the pixel clock, while the
+ * CVT spec reuses that tolerance in its examples, so it looks to be a
+ * good default tolerance for the EDID-based modes. Define it to 5 per
+ * mille to avoid floating point operations.
+ */
+#define SUN4I_RGB_DOTCLOCK_TOLERANCE_PER_MILLE	5
+
 static enum drm_mode_status sun4i_rgb_mode_valid(struct drm_encoder *crtc,
 						 const struct drm_display_mode *mode)
 {
@@ -59,8 +68,9 @@ static enum drm_mode_status sun4i_rgb_mode_valid(struct drm_encoder *crtc,
 	struct sun4i_tcon *tcon = rgb->tcon;
 	u32 hsync = mode->hsync_end - mode->hsync_start;
 	u32 vsync = mode->vsync_end - mode->vsync_start;
-	unsigned long rate = mode->clock * 1000;
-	long rounded_rate;
+	unsigned long long rate = mode->clock * 1000;
+	unsigned long long lowest, highest;
+	unsigned long long rounded_rate;
 
 	DRM_DEBUG_DRIVER("Validating modes...\n");
 
@@ -92,15 +102,39 @@ static enum drm_mode_status sun4i_rgb_mode_valid(struct drm_encoder *crtc,
 
 	DRM_DEBUG_DRIVER("Vertical parameters OK\n");
 
+	/*
+	 * TODO: We should use the struct display_timing if available
+	 * and / or trying to stretch the timings within that
+	 * tolerancy to take care of panels that we wouldn't be able
+	 * to have a exact match for.
+	 */
+	if (rgb->panel) {
+		DRM_DEBUG_DRIVER("RGB panel used, skipping clock rate checks");
+		goto out;
+	}
+
+	/*
+	 * That shouldn't ever happen unless something is really wrong, but it
+	 * doesn't harm to check.
+	 */
+	if (!rgb->bridge)
+		goto out;
+
 	tcon->dclk_min_div = 6;
 	tcon->dclk_max_div = 127;
 	rounded_rate = clk_round_rate(tcon->dclk, rate);
-	if (rounded_rate < rate)
+
+	lowest = rate * (1000 - SUN4I_RGB_DOTCLOCK_TOLERANCE_PER_MILLE);
+	do_div(lowest, 1000);
+	if (rounded_rate < lowest)
 		return MODE_CLOCK_LOW;
 
-	if (rounded_rate > rate)
+	highest = rate * (1000 + SUN4I_RGB_DOTCLOCK_TOLERANCE_PER_MILLE);
+	do_div(highest, 1000);
+	if (rounded_rate > highest)
 		return MODE_CLOCK_HIGH;
 
+out:
 	DRM_DEBUG_DRIVER("Clock rate OK\n");
 
 	return MODE_OK;
@@ -114,9 +148,8 @@ static void
 sun4i_rgb_connector_destroy(struct drm_connector *connector)
 {
 	struct sun4i_rgb *rgb = drm_connector_to_sun4i_rgb(connector);
-	struct sun4i_tcon *tcon = rgb->tcon;
 
-	drm_panel_detach(tcon->panel);
+	drm_panel_detach(rgb->panel);
 	drm_connector_cleanup(connector);
 }
 
@@ -131,26 +164,24 @@ static const struct drm_connector_funcs sun4i_rgb_con_funcs = {
 static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder)
 {
 	struct sun4i_rgb *rgb = drm_encoder_to_sun4i_rgb(encoder);
-	struct sun4i_tcon *tcon = rgb->tcon;
 
 	DRM_DEBUG_DRIVER("Enabling RGB output\n");
 
-	if (tcon->panel) {
-		drm_panel_prepare(tcon->panel);
-		drm_panel_enable(tcon->panel);
+	if (rgb->panel) {
+		drm_panel_prepare(rgb->panel);
+		drm_panel_enable(rgb->panel);
 	}
 }
 
 static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder)
 {
 	struct sun4i_rgb *rgb = drm_encoder_to_sun4i_rgb(encoder);
-	struct sun4i_tcon *tcon = rgb->tcon;
 
 	DRM_DEBUG_DRIVER("Disabling RGB output\n");
 
-	if (tcon->panel) {
-		drm_panel_disable(tcon->panel);
-		drm_panel_unprepare(tcon->panel);
+	if (rgb->panel) {
+		drm_panel_disable(rgb->panel);
+		drm_panel_unprepare(rgb->panel);
 	}
 }
 
@@ -172,7 +203,6 @@ static struct drm_encoder_funcs sun4i_rgb_enc_funcs = {
 int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 {
 	struct drm_encoder *encoder;
-	struct drm_bridge *bridge;
 	struct sun4i_rgb *rgb;
 	int ret;
 
@@ -183,7 +213,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	encoder = &rgb->encoder;
 
 	ret = drm_of_find_panel_or_bridge(tcon->dev->of_node, 1, 0,
-					  &tcon->panel, &bridge);
+					  &rgb->panel, &rgb->bridge);
 	if (ret) {
 		dev_info(drm->dev, "No panel or bridge found... RGB output disabled\n");
 		return 0;
@@ -204,7 +234,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	/* The RGB encoder can only work with the TCON channel 0 */
 	rgb->encoder.possible_crtcs = drm_crtc_mask(&tcon->crtc->crtc);
 
-	if (tcon->panel) {
+	if (rgb->panel) {
 		drm_connector_helper_add(&rgb->connector,
 					 &sun4i_rgb_con_helper_funcs);
 		ret = drm_connector_init(drm, &rgb->connector,
@@ -218,15 +248,15 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 		drm_connector_attach_encoder(&rgb->connector,
 						  &rgb->encoder);
 
-		ret = drm_panel_attach(tcon->panel, &rgb->connector);
+		ret = drm_panel_attach(rgb->panel, &rgb->connector);
 		if (ret) {
 			dev_err(drm->dev, "Couldn't attach our panel\n");
 			goto err_cleanup_connector;
 		}
 	}
 
-	if (bridge) {
-		ret = drm_bridge_attach(encoder, bridge, NULL);
+	if (rgb->bridge) {
+		ret = drm_bridge_attach(encoder, rgb->bridge, NULL);
 		if (ret) {
 			dev_err(drm->dev, "Couldn't attach our bridge\n");
 			goto err_cleanup_connector;
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 7136fc91c603..9d8d8124b1f6 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -236,8 +236,8 @@ static struct sun4i_tcon *sun4i_get_tcon0(struct drm_device *drm)
 	return NULL;
 }
 
-void sun4i_tcon_set_mux(struct sun4i_tcon *tcon, int channel,
-			const struct drm_encoder *encoder)
+static void sun4i_tcon_set_mux(struct sun4i_tcon *tcon, int channel,
+			       const struct drm_encoder *encoder)
 {
 	int ret = -ENOTSUPP;
 
@@ -341,8 +341,8 @@ static void sun4i_tcon0_mode_set_cpu(struct sun4i_tcon *tcon,
 	u32 block_space, start_delay;
 	u32 tcon_div;
 
-	tcon->dclk_min_div = 4;
-	tcon->dclk_max_div = 127;
+	tcon->dclk_min_div = SUN6I_DSI_TCON_DIV;
+	tcon->dclk_max_div = SUN6I_DSI_TCON_DIV;
 
 	sun4i_tcon0_mode_set_common(tcon, mode);
 
@@ -561,10 +561,10 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon,
 	 * Following code is a way to avoid quirks all around TCON
 	 * and DOTCLOCK drivers.
 	 */
-	if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_POSEDGE)
+	if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE)
 		clk_set_phase(tcon->dclk, 240);
 
-	if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
+	if (display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_DRIVE_NEGEDGE)
 		clk_set_phase(tcon->dclk, 0);
 
 	regmap_update_bits(tcon->regs, SUN4I_TCON0_IO_POL_REG,
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.h b/drivers/gpu/drm/sun4i/sun4i_tcon.h
index b5214d71610f..84cfb1952ff7 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.h
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.h
@@ -257,8 +257,6 @@ struct sun4i_tcon {
 	struct reset_control		*lcd_rst;
 	struct reset_control		*lvds_rst;
 
-	struct drm_panel		*panel;
-
 	/* Platform adjustments */
 	const struct sun4i_tcon_quirks	*quirks;
 
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 318994cd1b85..6ff585055a07 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -24,7 +24,9 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_probe_helper.h>
 
+#include "sun4i_crtc.h"
 #include "sun4i_drv.h"
+#include "sun4i_tcon.h"
 #include "sun6i_mipi_dsi.h"
 
 #include <video/mipi_display.h>
@@ -33,6 +35,8 @@
 #define SUN6I_DSI_CTL_EN			BIT(0)
 
 #define SUN6I_DSI_BASIC_CTL_REG		0x00c
+#define SUN6I_DSI_BASIC_CTL_TRAIL_INV(n)		(((n) & 0xf) << 4)
+#define SUN6I_DSI_BASIC_CTL_TRAIL_FILL		BIT(3)
 #define SUN6I_DSI_BASIC_CTL_HBP_DIS		BIT(2)
 #define SUN6I_DSI_BASIC_CTL_HSA_HSE_DIS		BIT(1)
 #define SUN6I_DSI_BASIC_CTL_VIDEO_BURST		BIT(0)
@@ -153,6 +157,8 @@
 
 #define SUN6I_DSI_CMD_TX_REG(n)		(0x300 + (n) * 0x04)
 
+#define SUN6I_DSI_SYNC_POINT		40
+
 enum sun6i_dsi_start_inst {
 	DSI_START_LPRX,
 	DSI_START_LPTX,
@@ -358,7 +364,54 @@ static void sun6i_dsi_inst_init(struct sun6i_dsi *dsi,
 static u16 sun6i_dsi_get_video_start_delay(struct sun6i_dsi *dsi,
 					   struct drm_display_mode *mode)
 {
-	return mode->vtotal - (mode->vsync_end - mode->vdisplay) + 1;
+	u16 start = clamp(mode->vtotal - mode->vdisplay - 10, 8, 100);
+	u16 delay = mode->vtotal - (mode->vsync_end - mode->vdisplay) + start;
+
+	if (delay > mode->vtotal)
+		delay = delay % mode->vtotal;
+
+	return max_t(u16, delay, 1);
+}
+
+static u16 sun6i_dsi_get_line_num(struct sun6i_dsi *dsi,
+				  struct drm_display_mode *mode)
+{
+	struct mipi_dsi_device *device = dsi->device;
+	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+
+	return mode->htotal * Bpp / device->lanes;
+}
+
+static u16 sun6i_dsi_get_drq_edge0(struct sun6i_dsi *dsi,
+				   struct drm_display_mode *mode,
+				   u16 line_num, u16 edge1)
+{
+	u16 edge0 = edge1;
+
+	edge0 += (mode->hdisplay + 40) * SUN6I_DSI_TCON_DIV / 8;
+
+	if (edge0 > line_num)
+		return edge0 - line_num;
+
+	return 1;
+}
+
+static u16 sun6i_dsi_get_drq_edge1(struct sun6i_dsi *dsi,
+				   struct drm_display_mode *mode,
+				   u16 line_num)
+{
+	struct mipi_dsi_device *device = dsi->device;
+	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
+	unsigned int hbp = mode->htotal - mode->hsync_end;
+	u16 edge1;
+
+	edge1 = SUN6I_DSI_SYNC_POINT;
+	edge1 += (mode->hdisplay + hbp + 20) * Bpp / device->lanes;
+
+	if (edge1 > line_num)
+		return line_num;
+
+	return edge1;
 }
 
 static void sun6i_dsi_setup_burst(struct sun6i_dsi *dsi,
@@ -367,7 +420,23 @@ static void sun6i_dsi_setup_burst(struct sun6i_dsi *dsi,
 	struct mipi_dsi_device *device = dsi->device;
 	u32 val = 0;
 
-	if ((mode->hsync_end - mode->hdisplay) > 20) {
+	if (device->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
+		u16 line_num = sun6i_dsi_get_line_num(dsi, mode);
+		u16 edge0, edge1;
+
+		edge1 = sun6i_dsi_get_drq_edge1(dsi, mode, line_num);
+		edge0 = sun6i_dsi_get_drq_edge0(dsi, mode, line_num, edge1);
+
+		regmap_write(dsi->regs, SUN6I_DSI_BURST_DRQ_REG,
+			     SUN6I_DSI_BURST_DRQ_EDGE0(edge0) |
+			     SUN6I_DSI_BURST_DRQ_EDGE1(edge1));
+
+		regmap_write(dsi->regs, SUN6I_DSI_BURST_LINE_REG,
+			     SUN6I_DSI_BURST_LINE_NUM(line_num) |
+			     SUN6I_DSI_BURST_LINE_SYNC_POINT(SUN6I_DSI_SYNC_POINT));
+
+		val = SUN6I_DSI_TCON_DRQ_ENABLE_MODE;
+	} else if ((mode->hsync_end - mode->hdisplay) > 20) {
 		/* Maaaaaagic */
 		u16 drq = (mode->hsync_end - mode->hdisplay) - 20;
 
@@ -384,8 +453,19 @@ static void sun6i_dsi_setup_burst(struct sun6i_dsi *dsi,
 static void sun6i_dsi_setup_inst_loop(struct sun6i_dsi *dsi,
 				      struct drm_display_mode *mode)
 {
+	struct mipi_dsi_device *device = dsi->device;
 	u16 delay = 50 - 1;
 
+	if (device->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
+		delay = (mode->htotal - mode->hdisplay) * 150;
+		delay /= (mode->clock / 1000) * 8;
+		delay -= 50;
+	}
+
+	regmap_write(dsi->regs, SUN6I_DSI_INST_LOOP_SEL_REG,
+		     2 << (4 * DSI_INST_ID_LP11) |
+		     3 << (4 * DSI_INST_ID_DLY));
+
 	regmap_write(dsi->regs, SUN6I_DSI_INST_LOOP_NUM_REG(0),
 		     SUN6I_DSI_INST_LOOP_NUM_N0(50 - 1) |
 		     SUN6I_DSI_INST_LOOP_NUM_N1(delay));
@@ -451,49 +531,68 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 {
 	struct mipi_dsi_device *device = dsi->device;
 	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
-	u16 hbp, hfp, hsa, hblk, vblk;
+	u16 hbp = 0, hfp = 0, hsa = 0, hblk = 0, vblk = 0;
+	u32 basic_ctl = 0;
 	size_t bytes;
 	u8 *buffer;
 
 	/* Do all timing calculations up front to allocate buffer space */
 
-	/*
-	 * A sync period is composed of a blanking packet (4 bytes +
-	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
-	 * minimal size is therefore 10 bytes
-	 */
-#define HSA_PACKET_OVERHEAD	10
-	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
-		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+	if (device->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) {
+		hblk = mode->hdisplay * Bpp;
+		basic_ctl = SUN6I_DSI_BASIC_CTL_VIDEO_BURST |
+			    SUN6I_DSI_BASIC_CTL_HSA_HSE_DIS |
+			    SUN6I_DSI_BASIC_CTL_HBP_DIS;
 
-	/*
-	 * The backporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
+		if (device->lanes == 4)
+			basic_ctl |= SUN6I_DSI_BASIC_CTL_TRAIL_FILL |
+				     SUN6I_DSI_BASIC_CTL_TRAIL_INV(0xc);
+	} else {
+		/*
+		 * A sync period is composed of a blanking packet (4
+		 * bytes + payload + 2 bytes) and a sync event packet
+		 * (4 bytes). Its minimal size is therefore 10 bytes
+		 */
+#define HSA_PACKET_OVERHEAD	10
+		hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+			  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+
+		/*
+		 * The backporch is set using a blanking packet (4
+		 * bytes + payload + 2 bytes). Its minimal size is
+		 * therefore 6 bytes
+		 */
 #define HBP_PACKET_OVERHEAD	6
-	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
-		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
-
-	/*
-	 * The frontporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
+		hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+			  (mode->htotal - mode->hsync_end) * Bpp - HBP_PACKET_OVERHEAD);
+
+		/*
+		 * The frontporch is set using a blanking packet (4
+		 * bytes + payload + 2 bytes). Its minimal size is
+		 * therefore 6 bytes
+		 */
 #define HFP_PACKET_OVERHEAD	6
-	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
-		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
-
-	/*
-	 * hblk seems to be the line + porches length.
-	 */
-	hblk = mode->htotal * Bpp - hsa;
-
-	/*
-	 * And I'm not entirely sure what vblk is about. The driver in
-	 * Allwinner BSP is using a rather convoluted calculation
-	 * there only for 4 lanes. However, using 0 (the !4 lanes
-	 * case) even with a 4 lanes screen seems to work...
-	 */
-	vblk = 0;
+		hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+			  (mode->hsync_start - mode->hdisplay) * Bpp - HFP_PACKET_OVERHEAD);
+
+		/*
+		 * The blanking is set using a sync event (4 bytes)
+		 * and a blanking packet (4 bytes + payload + 2
+		 * bytes). Its minimal size is therefore 10 bytes.
+		 */
+#define HBLK_PACKET_OVERHEAD	10
+		hblk = max((unsigned int)HBLK_PACKET_OVERHEAD,
+			   (mode->htotal - (mode->hsync_end - mode->hsync_start)) * Bpp -
+			   HBLK_PACKET_OVERHEAD);
+
+		/*
+		 * And I'm not entirely sure what vblk is about. The driver in
+		 * Allwinner BSP is using a rather convoluted calculation
+		 * there only for 4 lanes. However, using 0 (the !4 lanes
+		 * case) even with a 4 lanes screen seems to work...
+		 */
+		vblk = 0;
+	}
 
 	/* How many bytes do we need to send all payloads? */
 	bytes = max_t(size_t, max(max(hfp, hblk), max(hsa, hbp)), vblk);
@@ -501,7 +600,7 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 	if (WARN_ON(!buffer))
 		return;
 
-	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, 0);
+	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, basic_ctl);
 
 	regmap_write(dsi->regs, SUN6I_DSI_SYNC_HSS_REG,
 		     sun6i_dsi_build_sync_pkt(MIPI_DSI_H_SYNC_START,
@@ -526,8 +625,8 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 	regmap_write(dsi->regs, SUN6I_DSI_BASIC_SIZE0_REG,
 		     SUN6I_DSI_BASIC_SIZE0_VSA(mode->vsync_end -
 					       mode->vsync_start) |
-		     SUN6I_DSI_BASIC_SIZE0_VBP(mode->vsync_start -
-					       mode->vdisplay));
+		     SUN6I_DSI_BASIC_SIZE0_VBP(mode->vtotal -
+					       mode->vsync_end));
 
 	regmap_write(dsi->regs, SUN6I_DSI_BASIC_SIZE1_REG,
 		     SUN6I_DSI_BASIC_SIZE1_VACT(mode->vdisplay) |
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h
index a07090579f84..5c3ad5be0690 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.h
@@ -13,6 +13,8 @@
 #include <drm/drm_encoder.h>
 #include <drm/drm_mipi_dsi.h>
 
+#define SUN6I_DSI_TCON_DIV	4
+
 struct sun6i_dsi {
 	struct drm_connector	connector;
 	struct drm_encoder	encoder;
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 30a2eff55687..fd20a928cf4d 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -325,38 +325,22 @@ static struct regmap_config sun8i_mixer_regmap_config = {
 
 static int sun8i_mixer_of_get_id(struct device_node *node)
 {
-	struct device_node *port, *ep;
-	int ret = -EINVAL;
+	struct device_node *ep, *remote;
+	struct of_endpoint of_ep;
 
-	/* output is port 1 */
-	port = of_graph_get_port_by_id(node, 1);
-	if (!port)
+	/* Output port is 1, and we want the first endpoint. */
+	ep = of_graph_get_endpoint_by_regs(node, 1, -1);
+	if (!ep)
 		return -EINVAL;
 
-	/* try to find downstream endpoint */
-	for_each_available_child_of_node(port, ep) {
-		struct device_node *remote;
-		u32 reg;
-
-		remote = of_graph_get_remote_endpoint(ep);
-		if (!remote)
-			continue;
-
-		ret = of_property_read_u32(remote, "reg", &reg);
-		if (!ret) {
-			of_node_put(remote);
-			of_node_put(ep);
-			of_node_put(port);
-
-			return reg;
-		}
-
-		of_node_put(remote);
-	}
-
-	of_node_put(port);
+	remote = of_graph_get_remote_endpoint(ep);
+	of_node_put(ep);
+	if (!remote)
+		return -EINVAL;
 
-	return ret;
+	of_graph_parse_endpoint(remote, &of_ep);
+	of_node_put(remote);
+	return of_ep.id;
 }
 
 static int sun8i_mixer_bind(struct device *dev, struct device *master,
@@ -554,6 +538,7 @@ static int sun8i_mixer_remove(struct platform_device *pdev)
 static const struct sun8i_mixer_cfg sun8i_a83t_mixer0_cfg = {
 	.ccsc		= 0,
 	.scaler_mask	= 0xf,
+	.scanline_yuv	= 2048,
 	.ui_num		= 3,
 	.vi_num		= 1,
 };
@@ -561,6 +546,7 @@ static const struct sun8i_mixer_cfg sun8i_a83t_mixer0_cfg = {
 static const struct sun8i_mixer_cfg sun8i_a83t_mixer1_cfg = {
 	.ccsc		= 1,
 	.scaler_mask	= 0x3,
+	.scanline_yuv	= 2048,
 	.ui_num		= 1,
 	.vi_num		= 1,
 };
@@ -569,6 +555,7 @@ static const struct sun8i_mixer_cfg sun8i_h3_mixer0_cfg = {
 	.ccsc		= 0,
 	.mod_rate	= 432000000,
 	.scaler_mask	= 0xf,
+	.scanline_yuv	= 2048,
 	.ui_num		= 3,
 	.vi_num		= 1,
 };
@@ -577,6 +564,7 @@ static const struct sun8i_mixer_cfg sun8i_r40_mixer0_cfg = {
 	.ccsc		= 0,
 	.mod_rate	= 297000000,
 	.scaler_mask	= 0xf,
+	.scanline_yuv	= 2048,
 	.ui_num		= 3,
 	.vi_num		= 1,
 };
@@ -585,6 +573,7 @@ static const struct sun8i_mixer_cfg sun8i_r40_mixer1_cfg = {
 	.ccsc		= 1,
 	.mod_rate	= 297000000,
 	.scaler_mask	= 0x3,
+	.scanline_yuv	= 2048,
 	.ui_num		= 1,
 	.vi_num		= 1,
 };
@@ -593,6 +582,7 @@ static const struct sun8i_mixer_cfg sun8i_v3s_mixer_cfg = {
 	.vi_num = 2,
 	.ui_num = 1,
 	.scaler_mask = 0x3,
+	.scanline_yuv = 2048,
 	.ccsc = 0,
 	.mod_rate = 150000000,
 };
@@ -601,6 +591,7 @@ static const struct sun8i_mixer_cfg sun50i_a64_mixer0_cfg = {
 	.ccsc		= 0,
 	.mod_rate	= 297000000,
 	.scaler_mask	= 0xf,
+	.scanline_yuv	= 4096,
 	.ui_num		= 3,
 	.vi_num		= 1,
 };
@@ -609,6 +600,7 @@ static const struct sun8i_mixer_cfg sun50i_a64_mixer1_cfg = {
 	.ccsc		= 1,
 	.mod_rate	= 297000000,
 	.scaler_mask	= 0x3,
+	.scanline_yuv	= 2048,
 	.ui_num		= 1,
 	.vi_num		= 1,
 };
@@ -618,6 +610,7 @@ static const struct sun8i_mixer_cfg sun50i_h6_mixer0_cfg = {
 	.is_de3		= true,
 	.mod_rate	= 600000000,
 	.scaler_mask	= 0xf,
+	.scanline_yuv	= 4096,
 	.ui_num		= 3,
 	.vi_num		= 1,
 };
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index 913d14ce68b0..80e084caa084 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -159,6 +159,7 @@ struct de2_fmt_info {
  * @mod_rate: module clock rate that needs to be set in order to have
  *	a functional block.
  * @is_de3: true, if this is next gen display engine 3.0, false otherwise.
+ * @scaline_yuv: size of a scanline for VI scaler for YUV formats.
  */
 struct sun8i_mixer_cfg {
 	int		vi_num;
@@ -167,6 +168,7 @@ struct sun8i_mixer_cfg {
 	int		ccsc;
 	unsigned long	mod_rate;
 	unsigned int	is_de3 : 1;
+	unsigned int	scanline_yuv;
 };
 
 struct sun8i_mixer {
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index b1e7c76e9c17..3267d0f9b9b2 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -269,12 +269,12 @@ static int sun8i_tcon_top_remove(struct platform_device *pdev)
 	return 0;
 }
 
-const struct sun8i_tcon_top_quirks sun8i_r40_tcon_top_quirks = {
+static const struct sun8i_tcon_top_quirks sun8i_r40_tcon_top_quirks = {
 	.has_tcon_tv1	= true,
 	.has_dsi	= true,
 };
 
-const struct sun8i_tcon_top_quirks sun50i_h6_tcon_top_quirks = {
+static const struct sun8i_tcon_top_quirks sun50i_h6_tcon_top_quirks = {
 	/* Nothing special */
 };
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 8a0616238467..bb8e026d6405 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -80,6 +80,8 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 	u32 bld_base, ch_base;
 	u32 outsize, insize;
 	u32 hphase, vphase;
+	u32 hn = 0, hm = 0;
+	u32 vn = 0, vm = 0;
 	bool subsampled;
 
 	DRM_DEBUG_DRIVER("Updating VI channel %d overlay %d\n",
@@ -137,12 +139,41 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 	subsampled = format->hsub > 1 || format->vsub > 1;
 
 	if (insize != outsize || subsampled || hphase || vphase) {
-		u32 hscale, vscale;
+		unsigned int scanline, required;
+		struct drm_display_mode *mode;
+		u32 hscale, vscale, fps;
+		u64 ability;
 
 		DRM_DEBUG_DRIVER("HW scaling is enabled\n");
 
-		hscale = state->src_w / state->crtc_w;
-		vscale = state->src_h / state->crtc_h;
+		mode = &plane->state->crtc->state->mode;
+		fps = (mode->clock * 1000) / (mode->vtotal * mode->htotal);
+		ability = clk_get_rate(mixer->mod_clk);
+		/* BSP algorithm assumes 80% efficiency of VI scaler unit */
+		ability *= 80;
+		do_div(ability, mode->vdisplay * fps * max(src_w, dst_w));
+
+		required = src_h * 100 / dst_h;
+
+		if (ability < required) {
+			DRM_DEBUG_DRIVER("Using vertical coarse scaling\n");
+			vm = src_h;
+			vn = (u32)ability * dst_h / 100;
+			src_h = vn;
+		}
+
+		/* it seems that every RGB scaler has buffer for 2048 pixels */
+		scanline = subsampled ? mixer->cfg->scanline_yuv : 2048;
+
+		if (src_w > scanline) {
+			DRM_DEBUG_DRIVER("Using horizontal coarse scaling\n");
+			hm = src_w;
+			hn = scanline;
+			src_w = hn;
+		}
+
+		hscale = (src_w << 16) / dst_w;
+		vscale = (src_h << 16) / dst_h;
 
 		sun8i_vi_scaler_setup(mixer, channel, src_w, src_h, dst_w,
 				      dst_h, hscale, vscale, hphase, vphase,
@@ -153,6 +184,23 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 		sun8i_vi_scaler_enable(mixer, channel, false);
 	}
 
+	regmap_write(mixer->engine.regs,
+		     SUN8I_MIXER_CHAN_VI_HDS_Y(ch_base),
+		     SUN8I_MIXER_CHAN_VI_DS_N(hn) |
+		     SUN8I_MIXER_CHAN_VI_DS_M(hm));
+	regmap_write(mixer->engine.regs,
+		     SUN8I_MIXER_CHAN_VI_HDS_UV(ch_base),
+		     SUN8I_MIXER_CHAN_VI_DS_N(hn) |
+		     SUN8I_MIXER_CHAN_VI_DS_M(hm));
+	regmap_write(mixer->engine.regs,
+		     SUN8I_MIXER_CHAN_VI_VDS_Y(ch_base),
+		     SUN8I_MIXER_CHAN_VI_DS_N(vn) |
+		     SUN8I_MIXER_CHAN_VI_DS_M(vm));
+	regmap_write(mixer->engine.regs,
+		     SUN8I_MIXER_CHAN_VI_VDS_UV(ch_base),
+		     SUN8I_MIXER_CHAN_VI_DS_N(vn) |
+		     SUN8I_MIXER_CHAN_VI_DS_M(vm));
+
 	/* Set base coordinates */
 	DRM_DEBUG_DRIVER("Layer destination coordinates X: %d Y: %d\n",
 			 state->dst.x1, state->dst.y1);
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.h b/drivers/gpu/drm/sun4i/sun8i_vi_layer.h
index 8a5e6d01c85d..a223a4839f45 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.h
@@ -24,6 +24,14 @@
 		((base) + 0x30 * (layer) + 0x18 + 4 * (plane))
 #define SUN8I_MIXER_CHAN_VI_OVL_SIZE(base) \
 		((base) + 0xe8)
+#define SUN8I_MIXER_CHAN_VI_HDS_Y(base) \
+		((base) + 0xf0)
+#define SUN8I_MIXER_CHAN_VI_HDS_UV(base) \
+		((base) + 0xf4)
+#define SUN8I_MIXER_CHAN_VI_VDS_Y(base) \
+		((base) + 0xf8)
+#define SUN8I_MIXER_CHAN_VI_VDS_UV(base) \
+		((base) + 0xfc)
 
 #define SUN8I_MIXER_CHAN_VI_LAYER_ATTR_EN		BIT(0)
 /* RGB mode should be set for RGB formats and cleared for YCbCr */
@@ -33,6 +41,9 @@
 #define SUN50I_MIXER_CHAN_VI_LAYER_ATTR_ALPHA_MASK	GENMASK(31, 24)
 #define SUN50I_MIXER_CHAN_VI_LAYER_ATTR_ALPHA(x)	((x) << 24)
 
+#define SUN8I_MIXER_CHAN_VI_DS_N(x)			((x) << 16)
+#define SUN8I_MIXER_CHAN_VI_DS_M(x)			((x) << 0)
+
 struct sun8i_mixer;
 
 struct sun8i_vi_layer {