diff --git a/Documentation/devicetree/bindings/display/bridge/ti,ths8135.txt b/Documentation/devicetree/bindings/display/bridge/ti,ths813x.txt
similarity index 69%
rename from Documentation/devicetree/bindings/display/bridge/ti,ths8135.txt
rename to Documentation/devicetree/bindings/display/bridge/ti,ths813x.txt
index 6ec1a880ac18..df3d7c1ac09e 100644
--- a/Documentation/devicetree/bindings/display/bridge/ti,ths8135.txt
+++ b/Documentation/devicetree/bindings/display/bridge/ti,ths813x.txt
@@ -1,11 +1,16 @@
-THS8135 Video DAC
------------------
+THS8134 and THS8135 Video DAC
+-----------------------------
 
-This is the binding for Texas Instruments THS8135 Video DAC bridge.
+This is the binding for Texas Instruments THS8134, THS8134A, THS8134B and
+THS8135 Video DAC bridges.
 
 Required properties:
 
-- compatible: Must be "ti,ths8135"
+- compatible: Must be one of
+  "ti,ths8134"
+  "ti,ths8134a," "ti,ths8134"
+  "ti,ths8134b", "ti,ths8134"
+  "ti,ths8135"
 
 Required nodes:
 
diff --git a/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.txt b/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.txt
new file mode 100644
index 000000000000..248141c3c7e3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.txt
@@ -0,0 +1,31 @@
+ARM Versatile TFT Panels
+
+These panels are connected to the daughterboards found on the
+ARM Versatile reference designs.
+
+This device node must appear as a child to a "syscon"-compatible
+node.
+
+Required properties:
+- compatible: should be "arm,versatile-tft-panel"
+
+Required subnodes:
+- port: see display/panel/panel-common.txt, graph.txt
+
+
+Example:
+
+sysreg@0 {
+	compatible = "arm,versatile-sysreg", "syscon", "simple-mfd";
+	reg = <0x00000 0x1000>;
+
+	panel: display@0 {
+		compatible = "arm,versatile-tft-panel";
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&foo>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt b/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
index 029252253ad4..3eb1b48b47dd 100644
--- a/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
+++ b/Documentation/devicetree/bindings/display/st,stm32-ltdc.txt
@@ -98,7 +98,7 @@ Example 2: DSI panel
 			compatible = "st,stm32-dsi";
 			reg = <0x40016c00 0x800>;
 			clocks = <&rcc 1 CLK_F469_DSI>, <&clk_hse>;
-			clock-names = "ref", "pclk";
+			clock-names = "pclk", "ref";
 			resets = <&rcc STM32F4_APB2_RESET(DSI)>;
 			reset-names = "apb";
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 3bdc260e36b7..2afba909724c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4456,6 +4456,13 @@ T:	git git://anongit.freedesktop.org/drm/drm-misc
 S:	Supported
 F:	drivers/gpu/drm/pl111/
 
+DRM DRIVER FOR ARM VERSATILE TFT PANELS
+M:	Linus Walleij <linus.walleij@linaro.org>
+T:	git git://anongit.freedesktop.org/drm/drm-misc
+S:	Maintained
+F:	drivers/gpu/drm/panel/panel-arm-versatile.c
+F:	Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.txt
+
 DRM DRIVER FOR AST SERVER GRAPHICS CHIPS
 M:	Dave Airlie <airlied@redhat.com>
 S:	Odd Fixes
@@ -4610,8 +4617,8 @@ F:	include/uapi/drm/
 F:	include/linux/vga*
 
 DRM DRIVERS AND MISC GPU PATCHES
-M:	Daniel Vetter <daniel.vetter@intel.com>
 M:	Gustavo Padovan <gustavo@padovan.org>
+M:	Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
 M:	Sean Paul <seanpaul@chromium.org>
 W:	https://01.org/linuxgraphics/gfx-docs/maintainer-tools/drm-misc.html
 S:	Maintained
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 04ebe2204c12..314eb1071cce 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -374,8 +374,9 @@ EXPORT_SYMBOL(reservation_object_copy_fences);
  * @pshared: the array of shared fence ptrs returned (array is krealloc'd to
  * the required size, and must be freed by caller)
  *
- * RETURNS
- * Zero or -errno
+ * Retrieve all fences from the reservation object. If the pointer for the
+ * exclusive fence is not specified the fence is put into the array of the
+ * shared fences as well. Returns either zero or -ENOMEM.
  */
 int reservation_object_get_fences_rcu(struct reservation_object *obj,
 				      struct dma_fence **pfence_excl,
@@ -389,8 +390,8 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj,
 
 	do {
 		struct reservation_object_list *fobj;
-		unsigned seq;
-		unsigned int i;
+		unsigned int i, seq;
+		size_t sz = 0;
 
 		shared_count = i = 0;
 
@@ -402,9 +403,14 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj,
 			goto unlock;
 
 		fobj = rcu_dereference(obj->fence);
-		if (fobj) {
+		if (fobj)
+			sz += sizeof(*shared) * fobj->shared_max;
+
+		if (!pfence_excl && fence_excl)
+			sz += sizeof(*shared);
+
+		if (sz) {
 			struct dma_fence **nshared;
-			size_t sz = sizeof(*shared) * fobj->shared_max;
 
 			nshared = krealloc(shared, sz,
 					   GFP_NOWAIT | __GFP_NOWARN);
@@ -420,13 +426,19 @@ int reservation_object_get_fences_rcu(struct reservation_object *obj,
 				break;
 			}
 			shared = nshared;
-			shared_count = fobj->shared_count;
-
+			shared_count = fobj ? fobj->shared_count : 0;
 			for (i = 0; i < shared_count; ++i) {
 				shared[i] = rcu_dereference(fobj->shared[i]);
 				if (!dma_fence_get_rcu(shared[i]))
 					break;
 			}
+
+			if (!pfence_excl && fence_excl) {
+				shared[i] = fence_excl;
+				fence_excl = NULL;
+				++i;
+				++shared_count;
+			}
 		}
 
 		if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) {
@@ -448,7 +460,8 @@ unlock:
 
 	*pshared_count = shared_count;
 	*pshared = shared;
-	*pfence_excl = fence_excl;
+	if (pfence_excl)
+		*pfence_excl = fence_excl;
 
 	return ret;
 }
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 24f83f9eeaed..7779bdbd18d1 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -43,14 +43,14 @@
  * timelines.
  *
  * Fences can be created with SW_SYNC_IOC_CREATE_FENCE ioctl with struct
- * sw_sync_ioctl_create_fence as parameter.
+ * sw_sync_create_fence_data as parameter.
  *
  * To increment the timeline counter, SW_SYNC_IOC_INC ioctl should be used
  * with the increment as u32. This will update the last signaled value
  * from the timeline and signal any fence that has a seqno smaller or equal
  * to it.
  *
- * struct sw_sync_ioctl_create_fence
+ * struct sw_sync_create_fence_data
  * @value:	the seqno to initialise the fence with
  * @name:	the name of the new sync point
  * @fence:	return the fd of the new sync_file with the created fence
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d5a2eefd6c3e..31126df06c8c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1504,6 +1504,7 @@ struct amdgpu_device {
 	const struct amdgpu_asic_funcs	*asic_funcs;
 	bool				shutdown;
 	bool				need_dma32;
+	bool				need_swiotlb;
 	bool				accel_working;
 	struct work_struct		reset_work;
 	struct notifier_block		acpi_nb;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e4bb435e614b..d897c4c61a01 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1018,7 +1018,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 	}
 
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) {
+	if (adev->need_swiotlb && swiotlb_nr_tbl()) {
 		return ttm_dma_populate(&gtt->ttm, adev->dev, ctx);
 	}
 #endif
@@ -1045,7 +1045,7 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 	adev = amdgpu_ttm_adev(ttm->bdev);
 
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) {
+	if (adev->need_swiotlb && swiotlb_nr_tbl()) {
 		ttm_dma_unpopulate(&gtt->ttm, adev->dev);
 		return;
 	}
@@ -2010,7 +2010,7 @@ static int amdgpu_ttm_debugfs_init(struct amdgpu_device *adev)
 	count = ARRAY_SIZE(amdgpu_ttm_debugfs_list);
 
 #ifdef CONFIG_SWIOTLB
-	if (!swiotlb_nr_tbl())
+	if (!(adev->need_swiotlb && swiotlb_nr_tbl()))
 		--count;
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 8e28270d1ea9..5f5eb15ccf4a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -22,6 +22,7 @@
  */
 #include <linux/firmware.h>
 #include <drm/drmP.h>
+#include <drm/drm_cache.h>
 #include "amdgpu.h"
 #include "gmc_v6_0.h"
 #include "amdgpu_ucode.h"
@@ -851,6 +852,7 @@ static int gmc_v6_0_sw_init(void *handle)
 		pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(32));
 		dev_warn(adev->dev, "amdgpu: No coherent DMA available.\n");
 	}
+	adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 
 	r = gmc_v6_0_init_microcode(adev);
 	if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 86e9d682c59e..12e49bd8fd2d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -22,6 +22,7 @@
  */
 #include <linux/firmware.h>
 #include <drm/drmP.h>
+#include <drm/drm_cache.h>
 #include "amdgpu.h"
 #include "cikd.h"
 #include "cik.h"
@@ -999,6 +1000,7 @@ static int gmc_v7_0_sw_init(void *handle)
 		pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(32));
 		pr_warn("amdgpu: No coherent DMA available\n");
 	}
+	adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 
 	r = gmc_v7_0_init_microcode(adev);
 	if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 9a813d834f1a..9a170e37fbe7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -22,6 +22,7 @@
  */
 #include <linux/firmware.h>
 #include <drm/drmP.h>
+#include <drm/drm_cache.h>
 #include "amdgpu.h"
 #include "gmc_v8_0.h"
 #include "amdgpu_ucode.h"
@@ -1085,6 +1086,7 @@ static int gmc_v8_0_sw_init(void *handle)
 	 */
 	adev->need_dma32 = false;
 	dma_bits = adev->need_dma32 ? 32 : 40;
+	adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 	r = pci_set_dma_mask(adev->pdev, DMA_BIT_MASK(dma_bits));
 	if (r) {
 		adev->need_dma32 = true;
@@ -1096,6 +1098,7 @@ static int gmc_v8_0_sw_init(void *handle)
 		pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(32));
 		pr_warn("amdgpu: No coherent DMA available\n");
 	}
+	adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 
 	r = gmc_v8_0_init_microcode(adev);
 	if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 2719937e09d6..100ec69f020a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -21,6 +21,7 @@
  *
  */
 #include <linux/firmware.h>
+#include <drm/drm_cache.h>
 #include "amdgpu.h"
 #include "gmc_v9_0.h"
 #include "amdgpu_atomfirmware.h"
@@ -852,6 +853,7 @@ static int gmc_v9_0_sw_init(void *handle)
 		pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(32));
 		printk(KERN_WARNING "amdgpu: No coherent DMA available.\n");
 	}
+	adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 
 	r = gmc_v9_0_mc_init(adev);
 	if (r)
diff --git a/drivers/gpu/drm/arc/arcpgu_hdmi.c b/drivers/gpu/drm/arc/arcpgu_hdmi.c
index 0ce7f398bcff..977dfa55162f 100644
--- a/drivers/gpu/drm/arc/arcpgu_hdmi.c
+++ b/drivers/gpu/drm/arc/arcpgu_hdmi.c
@@ -15,7 +15,8 @@
  */
 
 #include <drm/drm_crtc.h>
-#include <drm/drm_encoder_slave.h>
+#include <drm/drm_encoder.h>
+#include <drm/drm_device.h>
 
 #include "arcpgu.h"
 
diff --git a/drivers/gpu/drm/arc/arcpgu_sim.c b/drivers/gpu/drm/arc/arcpgu_sim.c
index bca3a678c955..b8f6f9a5dfbe 100644
--- a/drivers/gpu/drm/arc/arcpgu_sim.c
+++ b/drivers/gpu/drm/arc/arcpgu_sim.c
@@ -15,7 +15,6 @@
  */
 
 #include <drm/drm_crtc_helper.h>
-#include <drm/drm_encoder_slave.h>
 #include <drm/drm_atomic_helper.h>
 
 #include "arcpgu.h"
@@ -29,7 +28,6 @@
 
 struct arcpgu_drm_connector {
 	struct drm_connector connector;
-	struct drm_encoder_slave *encoder_slave;
 };
 
 static int arcpgu_drm_connector_get_modes(struct drm_connector *connector)
@@ -68,7 +66,7 @@ static struct drm_encoder_funcs arcpgu_drm_encoder_funcs = {
 int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
 {
 	struct arcpgu_drm_connector *arcpgu_connector;
-	struct drm_encoder_slave *encoder;
+	struct drm_encoder *encoder;
 	struct drm_connector *connector;
 	int ret;
 
@@ -76,10 +74,10 @@ int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
 	if (encoder == NULL)
 		return -ENOMEM;
 
-	encoder->base.possible_crtcs = 1;
-	encoder->base.possible_clones = 0;
+	encoder->possible_crtcs = 1;
+	encoder->possible_clones = 0;
 
-	ret = drm_encoder_init(drm, &encoder->base, &arcpgu_drm_encoder_funcs,
+	ret = drm_encoder_init(drm, encoder, &arcpgu_drm_encoder_funcs,
 			       DRM_MODE_ENCODER_VIRTUAL, NULL);
 	if (ret)
 		return ret;
@@ -101,21 +99,19 @@ int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
 		goto error_encoder_cleanup;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, &encoder->base);
+	ret = drm_mode_connector_attach_encoder(connector, encoder);
 	if (ret < 0) {
 		dev_err(drm->dev, "could not attach connector to encoder\n");
 		drm_connector_unregister(connector);
 		goto error_connector_cleanup;
 	}
 
-	arcpgu_connector->encoder_slave = encoder;
-
 	return 0;
 
 error_connector_cleanup:
 	drm_connector_cleanup(connector);
 
 error_encoder_cleanup:
-	drm_encoder_cleanup(&encoder->base);
+	drm_encoder_cleanup(encoder);
 	return ret;
 }
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index 630721f429f7..877647ef35a9 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -249,8 +249,9 @@ static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	return drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						   DRM_PLANE_HELPER_NO_SCALING,
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 33c5ef96ced0..2885d69af456 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -148,8 +148,10 @@ static int malidp_se_check_scaling(struct malidp_plane *mp,
 	if (!crtc_state)
 		return -EINVAL;
 
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  0, INT_MAX, true, true);
 	if (ret)
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 703c2d13603f..e18800ed7cd1 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -194,20 +194,6 @@ static int atmel_hlcdc_format_to_plane_mode(u32 format, u32 *mode)
 	return 0;
 }
 
-static bool atmel_hlcdc_format_embeds_alpha(u32 format)
-{
-	int i;
-
-	for (i = 0; i < sizeof(format); i++) {
-		char tmp = (format >> (8 * i)) & 0xff;
-
-		if (tmp == 'A')
-			return true;
-	}
-
-	return false;
-}
-
 static u32 heo_downscaling_xcoef[] = {
 	0x11343311,
 	0x000000f7,
@@ -377,13 +363,13 @@ atmel_hlcdc_plane_update_general_settings(struct atmel_hlcdc_plane *plane,
 {
 	unsigned int cfg = ATMEL_HLCDC_LAYER_DMA_BLEN_INCR16 | state->ahb_id;
 	const struct atmel_hlcdc_layer_desc *desc = plane->layer.desc;
-	u32 format = state->base.fb->format->format;
+	const struct drm_format_info *format = state->base.fb->format;
 
 	/*
 	 * Rotation optimization is not working on RGB888 (rotation is still
 	 * working but without any optimization).
 	 */
-	if (format == DRM_FORMAT_RGB888)
+	if (format->format == DRM_FORMAT_RGB888)
 		cfg |= ATMEL_HLCDC_LAYER_DMA_ROTDIS;
 
 	atmel_hlcdc_layer_write_cfg(&plane->layer, ATMEL_HLCDC_LAYER_DMA_CFG,
@@ -395,7 +381,7 @@ atmel_hlcdc_plane_update_general_settings(struct atmel_hlcdc_plane *plane,
 		cfg |= ATMEL_HLCDC_LAYER_OVR | ATMEL_HLCDC_LAYER_ITER2BL |
 		       ATMEL_HLCDC_LAYER_ITER;
 
-		if (atmel_hlcdc_format_embeds_alpha(format))
+		if (format->has_alpha)
 			cfg |= ATMEL_HLCDC_LAYER_LAEN;
 		else
 			cfg |= ATMEL_HLCDC_LAYER_GAEN |
@@ -566,7 +552,7 @@ atmel_hlcdc_plane_prepare_disc_area(struct drm_crtc_state *c_state)
 		ovl_state = drm_plane_state_to_atmel_hlcdc_plane_state(ovl_s);
 
 		if (!ovl_s->fb ||
-		    atmel_hlcdc_format_embeds_alpha(ovl_s->fb->format->format) ||
+		    ovl_s->fb->format->has_alpha ||
 		    ovl_state->alpha != 255)
 			continue;
 
@@ -769,7 +755,7 @@ static int atmel_hlcdc_plane_atomic_check(struct drm_plane *p,
 
 	if ((state->crtc_h != state->src_h || state->crtc_w != state->src_w) &&
 	    (!desc->layout.memsize ||
-	     atmel_hlcdc_format_embeds_alpha(state->base.fb->format->format)))
+	     state->base.fb->format->has_alpha))
 		return -EINVAL;
 
 	if (state->crtc_x < 0 || state->crtc_y < 0)
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index ed12a7ddd64a..b49043866be6 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -1301,8 +1301,7 @@ static void unregister_i2c_dummy_clients(struct anx78xx *anx78xx)
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(anx78xx->i2c_dummy); i++)
-		if (anx78xx->i2c_dummy[i])
-			i2c_unregister_device(anx78xx->i2c_dummy[i]);
+		i2c_unregister_device(anx78xx->i2c_dummy[i]);
 }
 
 static const struct regmap_config anx78xx_regmap_config = {
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index a8905049b9da..b2756bc4225a 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -727,7 +727,6 @@ static int analogix_dp_set_link_train(struct analogix_dp_device *dp,
 
 static int analogix_dp_config_video(struct analogix_dp_device *dp)
 {
-	int retval = 0;
 	int timeout_loop = 0;
 	int done_count = 0;
 
@@ -783,10 +782,7 @@ static int analogix_dp_config_video(struct analogix_dp_device *dp)
 		usleep_range(1000, 1001);
 	}
 
-	if (retval != 0)
-		dev_err(dp->dev, "Video stream is not detected!\n");
-
-	return retval;
+	return 0;
 }
 
 static void analogix_dp_enable_scramble(struct analogix_dp_device *dp,
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index de5e7dee7ad6..498d5948d1a8 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/of_graph.h>
 #include <linux/regulator/consumer.h>
 
@@ -204,6 +205,7 @@ static int dumb_vga_probe(struct platform_device *pdev)
 
 	vga->bridge.funcs = &dumb_vga_bridge_funcs;
 	vga->bridge.of_node = pdev->dev.of_node;
+	vga->bridge.timings = of_device_get_match_data(&pdev->dev);
 
 	drm_bridge_add(&vga->bridge);
 
@@ -222,10 +224,61 @@ static int dumb_vga_remove(struct platform_device *pdev)
 	return 0;
 }
 
+/*
+ * We assume the ADV7123 DAC is the "default" for historical reasons
+ * Information taken from the ADV7123 datasheet, revision D.
+ * NOTE: the ADV7123EP seems to have other timings and need a new timings
+ * set if used.
+ */
+static const struct drm_bridge_timings default_dac_timings = {
+	/* Timing specifications, datasheet page 7 */
+	.sampling_edge = DRM_BUS_FLAG_PIXDATA_POSEDGE,
+	.setup_time_ps = 500,
+	.hold_time_ps = 1500,
+};
+
+/*
+ * Information taken from the THS8134, THS8134A, THS8134B datasheet named
+ * "SLVS205D", dated May 1990, revised March 2000.
+ */
+static const struct drm_bridge_timings ti_ths8134_dac_timings = {
+	/* From timing diagram, datasheet page 9 */
+	.sampling_edge = DRM_BUS_FLAG_PIXDATA_POSEDGE,
+	/* From datasheet, page 12 */
+	.setup_time_ps = 3000,
+	/* I guess this means latched input */
+	.hold_time_ps = 0,
+};
+
+/*
+ * Information taken from the THS8135 datasheet named "SLAS343B", dated
+ * May 2001, revised April 2013.
+ */
+static const struct drm_bridge_timings ti_ths8135_dac_timings = {
+	/* From timing diagram, datasheet page 14 */
+	.sampling_edge = DRM_BUS_FLAG_PIXDATA_POSEDGE,
+	/* From datasheet, page 16 */
+	.setup_time_ps = 2000,
+	.hold_time_ps = 500,
+};
+
 static const struct of_device_id dumb_vga_match[] = {
-	{ .compatible = "dumb-vga-dac" },
-	{ .compatible = "adi,adv7123" },
-	{ .compatible = "ti,ths8135" },
+	{
+		.compatible = "dumb-vga-dac",
+		.data = NULL,
+	},
+	{
+		.compatible = "adi,adv7123",
+		.data = &default_dac_timings,
+	},
+	{
+		.compatible = "ti,ths8135",
+		.data = &ti_ths8135_dac_timings,
+	},
+	{
+		.compatible = "ti,ths8134",
+		.data = &ti_ths8134_dac_timings,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, dumb_vga_match);
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
index d9cca4fd66ec..7bac101c285c 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-mipi-dsi.c
@@ -29,7 +29,10 @@
 #include <drm/bridge/dw_mipi_dsi.h>
 #include <video/mipi_display.h>
 
+#define HWVER_131			0x31333100	/* IP version 1.31 */
+
 #define DSI_VERSION			0x00
+#define VERSION				GENMASK(31, 8)
 
 #define DSI_PWR_UP			0x04
 #define RESET				0
@@ -136,10 +139,6 @@
 					 GEN_SW_0P_TX_LP)
 
 #define DSI_GEN_HDR			0x6c
-/* TODO These 2 defines will be reworked thanks to mipi_dsi_create_packet() */
-#define GEN_HDATA(data)			(((data) & 0xffff) << 8)
-#define GEN_HTYPE(type)			(((type) & 0xff) << 0)
-
 #define DSI_GEN_PLD_DATA		0x70
 
 #define DSI_CMD_PKT_STATUS		0x74
@@ -169,11 +168,12 @@
 #define PHY_CLKHS2LP_TIME(lbcc)		(((lbcc) & 0x3ff) << 16)
 #define PHY_CLKLP2HS_TIME(lbcc)		((lbcc) & 0x3ff)
 
-/* TODO Next register is slightly different between 1.30 & 1.31 IP version */
 #define DSI_PHY_TMR_CFG			0x9c
 #define PHY_HS2LP_TIME(lbcc)		(((lbcc) & 0xff) << 24)
 #define PHY_LP2HS_TIME(lbcc)		(((lbcc) & 0xff) << 16)
 #define MAX_RD_TIME(lbcc)		((lbcc) & 0x7fff)
+#define PHY_HS2LP_TIME_V131(lbcc)	(((lbcc) & 0x3ff) << 16)
+#define PHY_LP2HS_TIME_V131(lbcc)	((lbcc) & 0x3ff)
 
 #define DSI_PHY_RSTZ			0xa0
 #define PHY_DISFORCEPLL			0
@@ -212,7 +212,9 @@
 #define DSI_INT_ST1			0xc0
 #define DSI_INT_MSK0			0xc4
 #define DSI_INT_MSK1			0xc8
+
 #define DSI_PHY_TMR_RD_CFG		0xf4
+#define MAX_RD_TIME_V131(lbcc)		((lbcc) & 0x7fff)
 
 #define PHY_STATUS_TIMEOUT_US		10000
 #define CMD_PKT_STATUS_TIMEOUT_US	20000
@@ -359,52 +361,23 @@ static int dw_mipi_dsi_gen_pkt_hdr_write(struct dw_mipi_dsi *dsi, u32 hdr_val)
 	return 0;
 }
 
-static int dw_mipi_dsi_dcs_short_write(struct dw_mipi_dsi *dsi,
-				       const struct mipi_dsi_msg *msg)
+static int dw_mipi_dsi_write(struct dw_mipi_dsi *dsi,
+			     const struct mipi_dsi_packet *packet)
 {
-	const u8 *tx_buf = msg->tx_buf;
-	u16 data = 0;
+	const u8 *tx_buf = packet->payload;
+	int len = packet->payload_length, pld_data_bytes = sizeof(u32), ret;
+	__le32 word;
 	u32 val;
 
-	if (msg->tx_len > 0)
-		data |= tx_buf[0];
-	if (msg->tx_len > 1)
-		data |= tx_buf[1] << 8;
-
-	if (msg->tx_len > 2) {
-		dev_err(dsi->dev, "too long tx buf length %zu for short write\n",
-			msg->tx_len);
-		return -EINVAL;
-	}
-
-	val = GEN_HDATA(data) | GEN_HTYPE(msg->type);
-	return dw_mipi_dsi_gen_pkt_hdr_write(dsi, val);
-}
-
-static int dw_mipi_dsi_dcs_long_write(struct dw_mipi_dsi *dsi,
-				      const struct mipi_dsi_msg *msg)
-{
-	const u8 *tx_buf = msg->tx_buf;
-	int len = msg->tx_len, pld_data_bytes = sizeof(u32), ret;
-	u32 hdr_val = GEN_HDATA(msg->tx_len) | GEN_HTYPE(msg->type);
-	u32 remainder;
-	u32 val;
-
-	if (msg->tx_len < 3) {
-		dev_err(dsi->dev, "wrong tx buf length %zu for long write\n",
-			msg->tx_len);
-		return -EINVAL;
-	}
-
-	while (DIV_ROUND_UP(len, pld_data_bytes)) {
+	while (len) {
 		if (len < pld_data_bytes) {
-			remainder = 0;
-			memcpy(&remainder, tx_buf, len);
-			dsi_write(dsi, DSI_GEN_PLD_DATA, remainder);
+			word = 0;
+			memcpy(&word, tx_buf, len);
+			dsi_write(dsi, DSI_GEN_PLD_DATA, le32_to_cpu(word));
 			len = 0;
 		} else {
-			memcpy(&remainder, tx_buf, pld_data_bytes);
-			dsi_write(dsi, DSI_GEN_PLD_DATA, remainder);
+			memcpy(&word, tx_buf, pld_data_bytes);
+			dsi_write(dsi, DSI_GEN_PLD_DATA, le32_to_cpu(word));
 			tx_buf += pld_data_bytes;
 			len -= pld_data_bytes;
 		}
@@ -419,40 +392,74 @@ static int dw_mipi_dsi_dcs_long_write(struct dw_mipi_dsi *dsi,
 		}
 	}
 
-	return dw_mipi_dsi_gen_pkt_hdr_write(dsi, hdr_val);
+	word = 0;
+	memcpy(&word, packet->header, sizeof(packet->header));
+	return dw_mipi_dsi_gen_pkt_hdr_write(dsi, le32_to_cpu(word));
+}
+
+static int dw_mipi_dsi_read(struct dw_mipi_dsi *dsi,
+			    const struct mipi_dsi_msg *msg)
+{
+	int i, j, ret, len = msg->rx_len;
+	u8 *buf = msg->rx_buf;
+	u32 val;
+
+	/* Wait end of the read operation */
+	ret = readl_poll_timeout(dsi->base + DSI_CMD_PKT_STATUS,
+				 val, !(val & GEN_RD_CMD_BUSY),
+				 1000, CMD_PKT_STATUS_TIMEOUT_US);
+	if (ret) {
+		dev_err(dsi->dev, "Timeout during read operation\n");
+		return ret;
+	}
+
+	for (i = 0; i < len; i += 4) {
+		/* Read fifo must not be empty before all bytes are read */
+		ret = readl_poll_timeout(dsi->base + DSI_CMD_PKT_STATUS,
+					 val, !(val & GEN_PLD_R_EMPTY),
+					 1000, CMD_PKT_STATUS_TIMEOUT_US);
+		if (ret) {
+			dev_err(dsi->dev, "Read payload FIFO is empty\n");
+			return ret;
+		}
+
+		val = dsi_read(dsi, DSI_GEN_PLD_DATA);
+		for (j = 0; j < 4 && j + i < len; j++)
+			buf[i + j] = val >> (8 * j);
+	}
+
+	return ret;
 }
 
 static ssize_t dw_mipi_dsi_host_transfer(struct mipi_dsi_host *host,
 					 const struct mipi_dsi_msg *msg)
 {
 	struct dw_mipi_dsi *dsi = host_to_dsi(host);
-	int ret;
+	struct mipi_dsi_packet packet;
+	int ret, nb_bytes;
 
-	/*
-	 * TODO dw drv improvements
-	 * use mipi_dsi_create_packet() instead of all following
-	 * functions and code (no switch cases, no
-	 * dw_mipi_dsi_dcs_short_write(), only the loop in long_write...)
-	 * and use packet.header...
-	 */
-	dw_mipi_message_config(dsi, msg);
-
-	switch (msg->type) {
-	case MIPI_DSI_DCS_SHORT_WRITE:
-	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
-	case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE:
-		ret = dw_mipi_dsi_dcs_short_write(dsi, msg);
-		break;
-	case MIPI_DSI_DCS_LONG_WRITE:
-		ret = dw_mipi_dsi_dcs_long_write(dsi, msg);
-		break;
-	default:
-		dev_err(dsi->dev, "unsupported message type 0x%02x\n",
-			msg->type);
-		ret = -EINVAL;
+	ret = mipi_dsi_create_packet(&packet, msg);
+	if (ret) {
+		dev_err(dsi->dev, "failed to create packet: %d\n", ret);
+		return ret;
 	}
 
-	return ret;
+	dw_mipi_message_config(dsi, msg);
+
+	ret = dw_mipi_dsi_write(dsi, &packet);
+	if (ret)
+		return ret;
+
+	if (msg->rx_buf && msg->rx_len) {
+		ret = dw_mipi_dsi_read(dsi, msg);
+		if (ret)
+			return ret;
+		nb_bytes = msg->rx_len;
+	} else {
+		nb_bytes = packet.size;
+	}
+
+	return nb_bytes;
 }
 
 static const struct mipi_dsi_host_ops dw_mipi_dsi_host_ops = {
@@ -658,6 +665,8 @@ static void dw_mipi_dsi_vertical_timing_config(struct dw_mipi_dsi *dsi,
 
 static void dw_mipi_dsi_dphy_timing_config(struct dw_mipi_dsi *dsi)
 {
+	u32 hw_version;
+
 	/*
 	 * TODO dw drv improvements
 	 * data & clock lane timers should be computed according to panel
@@ -665,8 +674,17 @@ static void dw_mipi_dsi_dphy_timing_config(struct dw_mipi_dsi *dsi)
 	 * note: DSI_PHY_TMR_CFG.MAX_RD_TIME should be in line with
 	 * DSI_CMD_MODE_CFG.MAX_RD_PKT_SIZE_LP (see CMD_MODE_ALL_LP)
 	 */
-	dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME(0x40)
-		  | PHY_LP2HS_TIME(0x40) | MAX_RD_TIME(10000));
+
+	hw_version = dsi_read(dsi, DSI_VERSION) & VERSION;
+
+	if (hw_version >= HWVER_131) {
+		dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME_V131(0x40) |
+			  PHY_LP2HS_TIME_V131(0x40));
+		dsi_write(dsi, DSI_PHY_TMR_RD_CFG, MAX_RD_TIME_V131(10000));
+	} else {
+		dsi_write(dsi, DSI_PHY_TMR_CFG, PHY_HS2LP_TIME(0x40) |
+			  PHY_LP2HS_TIME(0x40) | MAX_RD_TIME(10000));
+	}
 
 	dsi_write(dsi, DSI_PHY_TMR_LPCLK_CFG, PHY_CLKHS2LP_TIME(0x40)
 		  | PHY_CLKLP2HS_TIME(0x40));
@@ -746,9 +764,9 @@ static void dw_mipi_dsi_bridge_post_disable(struct drm_bridge *bridge)
 	pm_runtime_put(dsi->dev);
 }
 
-void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
-				 struct drm_display_mode *mode,
-				 struct drm_display_mode *adjusted_mode)
+static void dw_mipi_dsi_bridge_mode_set(struct drm_bridge *bridge,
+					struct drm_display_mode *mode,
+					struct drm_display_mode *adjusted_mode)
 {
 	struct dw_mipi_dsi *dsi = bridge_to_dsi(bridge);
 	const struct dw_mipi_dsi_phy_ops *phy_ops = dsi->plat_data->phy_ops;
@@ -922,8 +940,6 @@ __dw_mipi_dsi_probe(struct platform_device *pdev,
 	dsi->bridge.of_node = pdev->dev.of_node;
 #endif
 
-	dev_set_drvdata(dev, dsi);
-
 	return dsi;
 }
 
@@ -935,23 +951,16 @@ static void __dw_mipi_dsi_remove(struct dw_mipi_dsi *dsi)
 /*
  * Probe/remove API, used from platforms based on the DRM bridge API.
  */
-int dw_mipi_dsi_probe(struct platform_device *pdev,
-		      const struct dw_mipi_dsi_plat_data *plat_data)
+struct dw_mipi_dsi *
+dw_mipi_dsi_probe(struct platform_device *pdev,
+		  const struct dw_mipi_dsi_plat_data *plat_data)
 {
-	struct dw_mipi_dsi *dsi;
-
-	dsi = __dw_mipi_dsi_probe(pdev, plat_data);
-	if (IS_ERR(dsi))
-		return PTR_ERR(dsi);
-
-	return 0;
+	return __dw_mipi_dsi_probe(pdev, plat_data);
 }
 EXPORT_SYMBOL_GPL(dw_mipi_dsi_probe);
 
-void dw_mipi_dsi_remove(struct platform_device *pdev)
+void dw_mipi_dsi_remove(struct dw_mipi_dsi *dsi)
 {
-	struct dw_mipi_dsi *dsi = platform_get_drvdata(pdev);
-
 	mipi_dsi_host_unregister(&dsi->dsi_host);
 
 	__dw_mipi_dsi_remove(dsi);
@@ -961,31 +970,30 @@ EXPORT_SYMBOL_GPL(dw_mipi_dsi_remove);
 /*
  * Bind/unbind API, used from platforms based on the component framework.
  */
-int dw_mipi_dsi_bind(struct platform_device *pdev, struct drm_encoder *encoder,
-		     const struct dw_mipi_dsi_plat_data *plat_data)
+struct dw_mipi_dsi *
+dw_mipi_dsi_bind(struct platform_device *pdev, struct drm_encoder *encoder,
+		 const struct dw_mipi_dsi_plat_data *plat_data)
 {
 	struct dw_mipi_dsi *dsi;
 	int ret;
 
 	dsi = __dw_mipi_dsi_probe(pdev, plat_data);
 	if (IS_ERR(dsi))
-		return PTR_ERR(dsi);
+		return dsi;
 
 	ret = drm_bridge_attach(encoder, &dsi->bridge, NULL);
 	if (ret) {
-		dw_mipi_dsi_remove(pdev);
+		dw_mipi_dsi_remove(dsi);
 		DRM_ERROR("Failed to initialize bridge with drm\n");
-		return ret;
+		return ERR_PTR(ret);
 	}
 
-	return 0;
+	return dsi;
 }
 EXPORT_SYMBOL_GPL(dw_mipi_dsi_bind);
 
-void dw_mipi_dsi_unbind(struct device *dev)
+void dw_mipi_dsi_unbind(struct dw_mipi_dsi *dsi)
 {
-	struct dw_mipi_dsi *dsi = dev_get_drvdata(dev);
-
 	__dw_mipi_dsi_remove(dsi);
 }
 EXPORT_SYMBOL_GPL(dw_mipi_dsi_unbind);
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index b76d49218cf1..7d9ad20040a1 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -390,7 +390,7 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 
 	if (blob) {
 		if (blob->length != sizeof(struct drm_mode_modeinfo) ||
-		    drm_mode_convert_umode(&state->mode,
+		    drm_mode_convert_umode(state->crtc->dev, &state->mode,
 		                           (const struct drm_mode_modeinfo *)
 		                            blob->data))
 			return -EINVAL;
@@ -863,10 +863,10 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 	int ret;
 
 	/* either *both* CRTC and FB must be set, or neither */
-	if (WARN_ON(state->crtc && !state->fb)) {
+	if (state->crtc && !state->fb) {
 		DRM_DEBUG_ATOMIC("CRTC set but no FB\n");
 		return -EINVAL;
-	} else if (WARN_ON(state->fb && !state->crtc)) {
+	} else if (state->fb && !state->crtc) {
 		DRM_DEBUG_ATOMIC("FB set but no CRTC\n");
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index ab4032167094..ae3cbfe9e01c 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1878,6 +1878,8 @@ int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
 		new_crtc_state->event->base.completion = &commit->flip_done;
 		new_crtc_state->event->base.completion_release = release_crtc_commit;
 		drm_crtc_commit_get(commit);
+
+		commit->abort_completion = true;
 	}
 
 	for_each_oldnew_connector_in_state(state, conn, old_conn_state, new_conn_state, i) {
@@ -3421,8 +3423,21 @@ EXPORT_SYMBOL(drm_atomic_helper_crtc_duplicate_state);
 void __drm_atomic_helper_crtc_destroy_state(struct drm_crtc_state *state)
 {
 	if (state->commit) {
+		/*
+		 * In the event that a non-blocking commit returns
+		 * -ERESTARTSYS before the commit_tail work is queued, we will
+		 * have an extra reference to the commit object. Release it, if
+		 * the event has not been consumed by the worker.
+		 *
+		 * state->event may be freed, so we can't directly look at
+		 * state->event->base.completion.
+		 */
+		if (state->event && state->commit->abort_completion)
+			drm_crtc_commit_put(state->commit);
+
 		kfree(state->commit->event);
 		state->commit->event = NULL;
+
 		drm_crtc_commit_put(state->commit);
 	}
 
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index e6a21e69059c..d6a7eba087a0 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -205,9 +205,14 @@ int drm_connector_init(struct drm_device *dev,
 	connector->dev = dev;
 	connector->funcs = funcs;
 
-	ret = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL);
-	if (ret < 0)
+	/* connector index is used with 32bit bitmasks */
+	ret = ida_simple_get(&config->connector_ida, 0, 32, GFP_KERNEL);
+	if (ret < 0) {
+		DRM_DEBUG_KMS("Failed to allocate %s connector index: %d\n",
+			      drm_connector_enum_list[connector_type].name,
+			      ret);
 		goto out_put;
+	}
 	connector->index = ret;
 	ret = 0;
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index f0556e654116..353e24fcde9e 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -282,6 +282,10 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	WARN_ON(primary && primary->type != DRM_PLANE_TYPE_PRIMARY);
 	WARN_ON(cursor && cursor->type != DRM_PLANE_TYPE_CURSOR);
 
+	/* crtc index is used with 32bit bitmasks */
+	if (WARN_ON(config->num_crtc >= 32))
+		return -EINVAL;
+
 	crtc->dev = dev;
 	crtc->funcs = funcs;
 
@@ -610,7 +614,7 @@ retry:
 			goto out;
 		}
 
-		ret = drm_mode_convert_umode(mode, &crtc_req->mode);
+		ret = drm_mode_convert_umode(dev, mode, &crtc_req->mode);
 		if (ret) {
 			DRM_DEBUG_KMS("Invalid mode\n");
 			goto out;
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index 9dd879589a2c..9f8312137cad 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -307,10 +307,29 @@ static ssize_t crtc_crc_read(struct file *filep, char __user *user_buf,
 	return LINE_LEN(crc->values_cnt);
 }
 
+static unsigned int crtc_crc_poll(struct file *file, poll_table *wait)
+{
+	struct drm_crtc *crtc = file->f_inode->i_private;
+	struct drm_crtc_crc *crc = &crtc->crc;
+	unsigned ret;
+
+	poll_wait(file, &crc->wq, wait);
+
+	spin_lock_irq(&crc->lock);
+	if (crc->source && crtc_crc_data_count(crc))
+		ret = POLLIN | POLLRDNORM;
+	else
+		ret = 0;
+	spin_unlock_irq(&crc->lock);
+
+	return ret;
+}
+
 static const struct file_operations drm_crtc_crc_data_fops = {
 	.owner = THIS_MODULE,
 	.open = crtc_crc_open,
 	.read = crtc_crc_read,
+	.poll = crtc_crc_poll,
 	.release = crtc_crc_release,
 };
 
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index adf79be42c1e..ffe14ec3e7f2 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -146,6 +146,8 @@ u8 drm_dp_link_rate_to_bw_code(int link_rate)
 		return DP_LINK_BW_2_7;
 	case 540000:
 		return DP_LINK_BW_5_4;
+	case 810000:
+		return DP_LINK_BW_8_1;
 	}
 }
 EXPORT_SYMBOL(drm_dp_link_rate_to_bw_code);
@@ -161,6 +163,8 @@ int drm_dp_bw_code_to_link_rate(u8 link_bw)
 		return 270000;
 	case DP_LINK_BW_5_4:
 		return 540000;
+	case DP_LINK_BW_8_1:
+		return 810000;
 	}
 }
 EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate);
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 70dcfa58d3c2..36df7df5fe1a 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -2087,6 +2087,9 @@ static bool drm_dp_get_vc_payload_bw(int dp_link_bw,
 	case DP_LINK_BW_5_4:
 		*out = 10 * dp_link_count;
 		break;
+	case DP_LINK_BW_8_1:
+		*out = 15 * dp_link_count;
+		break;
 	}
 	return true;
 }
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index ddd537914575..b1cb2627548f 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2767,7 +2767,7 @@ do_detailed_mode(struct detailed_timing *timing, void *c)
 
 		drm_mode_probed_add(closure->connector, newmode);
 		closure->modes++;
-		closure->preferred = 0;
+		closure->preferred = false;
 	}
 }
 
@@ -2784,7 +2784,7 @@ add_detailed_modes(struct drm_connector *connector, struct edid *edid,
 	struct detailed_mode_closure closure = {
 		.connector = connector,
 		.edid = edid,
-		.preferred = 1,
+		.preferred = true,
 		.quirks = quirks,
 	};
 
diff --git a/drivers/gpu/drm/drm_encoder.c b/drivers/gpu/drm/drm_encoder.c
index 59e0ebe733f8..273e1c59c54a 100644
--- a/drivers/gpu/drm/drm_encoder.c
+++ b/drivers/gpu/drm/drm_encoder.c
@@ -110,6 +110,10 @@ int drm_encoder_init(struct drm_device *dev,
 {
 	int ret;
 
+	/* encoder index is used with 32bit bitmasks */
+	if (WARN_ON(dev->mode_config.num_encoder >= 32))
+		return -EINVAL;
+
 	ret = drm_mode_object_add(dev, &encoder->base, DRM_MODE_OBJECT_ENCODER);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 9c0152df45ad..5ca6395cd4d3 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -112,18 +112,18 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_XBGR4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_RGBX4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_BGRX4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ARGB4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ABGR4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGBA4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGRA4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
+		{ .format = DRM_FORMAT_ARGB4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_ABGR4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_RGBA4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGRA4444,	.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_XRGB1555,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_XBGR1555,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_RGBX5551,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_BGRX5551,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ARGB1555,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ABGR1555,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGBA5551,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGRA5551,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
+		{ .format = DRM_FORMAT_ARGB1555,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_ABGR1555,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_RGBA5551,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGRA5551,	.depth = 15, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_RGB565,		.depth = 16, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_BGR565,		.depth = 16, .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_RGB888,		.depth = 24, .num_planes = 1, .cpp = { 3, 0, 0 }, .hsub = 1, .vsub = 1 },
@@ -132,26 +132,26 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_XBGR8888,	.depth = 24, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_RGBX8888,	.depth = 24, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_BGRX8888,	.depth = 24, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGB565_A8,	.depth = 24, .num_planes = 2, .cpp = { 2, 1, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGR565_A8,	.depth = 24, .num_planes = 2, .cpp = { 2, 1, 0 }, .hsub = 1, .vsub = 1 },
+		{ .format = DRM_FORMAT_RGB565_A8,	.depth = 24, .num_planes = 2, .cpp = { 2, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGR565_A8,	.depth = 24, .num_planes = 2, .cpp = { 2, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_XRGB2101010,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_XBGR2101010,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_RGBX1010102,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
 		{ .format = DRM_FORMAT_BGRX1010102,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ARGB2101010,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ABGR2101010,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGBA1010102,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGRA1010102,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ARGB8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_ABGR8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGBA8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGRA8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGB888_A8,	.depth = 32, .num_planes = 2, .cpp = { 3, 1, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGR888_A8,	.depth = 32, .num_planes = 2, .cpp = { 3, 1, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_XRGB8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_XBGR8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_RGBX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_BGRX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1 },
+		{ .format = DRM_FORMAT_ARGB2101010,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_ABGR2101010,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_RGBA1010102,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGRA1010102,	.depth = 30, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_ARGB8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_ABGR8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_RGBA8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGRA8888,	.depth = 32, .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_RGB888_A8,	.depth = 32, .num_planes = 2, .cpp = { 3, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGR888_A8,	.depth = 32, .num_planes = 2, .cpp = { 3, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_XRGB8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_XBGR8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_RGBX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_BGRX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
 		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
 		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
@@ -172,7 +172,7 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
 		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
 		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1 },
+		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 	};
 
 	unsigned int i;
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 4aafe4802099..af782911c505 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -509,7 +509,7 @@ int drm_ioctl_permit(u32 flags, struct drm_file *file_priv)
 		return -EACCES;
 
 	/* MASTER is only for master or control clients */
-	if (unlikely((flags & DRM_MASTER) && 
+	if (unlikely((flags & DRM_MASTER) &&
 		     !drm_is_current_master(file_priv) &&
 		     !drm_is_control_client(file_priv)))
 		return -EACCES;
@@ -704,7 +704,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
  *
  *     ##define DRM_IOCTL_MY_DRIVER_OPERATION \
  *         DRM_IOW(DRM_COMMAND_BASE, struct my_driver_operation)
- * 
+ *
  * DRM driver private IOCTL must be in the range from DRM_COMMAND_BASE to
  * DRM_COMMAND_END. Finally you need an array of &struct drm_ioctl_desc to wire
  * up the handlers and set the access rights::
@@ -848,7 +848,7 @@ long drm_ioctl(struct file *filp,
 	if (kdata != stack_kdata)
 		kfree(kdata);
 	if (retcode)
-		DRM_DEBUG("ret = %d\n", retcode);
+		DRM_DEBUG("pid=%d, ret = %d\n", task_pid_nr(current), retcode);
 	return retcode;
 }
 EXPORT_SYMBOL(drm_ioctl);
diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index fc0ebd273ef8..7ca500b8c399 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -149,3 +149,16 @@ void drm_legacy_ioremapfree(struct drm_local_map *map, struct drm_device *dev)
 		iounmap(map->handle);
 }
 EXPORT_SYMBOL(drm_legacy_ioremapfree);
+
+u64 drm_get_max_iomem(void)
+{
+	struct resource *tmp;
+	u64 max_iomem = 0;
+
+	for (tmp = iomem_resource.child; tmp; tmp = tmp->sibling) {
+		max_iomem = max(max_iomem,  tmp->end);
+	}
+
+	return max_iomem;
+}
+EXPORT_SYMBOL(drm_get_max_iomem);
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index 4b47226b90d4..bc73b7f5b9fc 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -498,8 +498,9 @@ int mipi_dsi_shutdown_peripheral(struct mipi_dsi_device *dsi)
 		.tx_buf = (u8 [2]) { 0, 0 },
 		.tx_len = 2,
 	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
 
-	return mipi_dsi_device_transfer(dsi, &msg);
+	return (ret < 0) ? ret : 0;
 }
 EXPORT_SYMBOL(mipi_dsi_shutdown_peripheral);
 
@@ -517,8 +518,9 @@ int mipi_dsi_turn_on_peripheral(struct mipi_dsi_device *dsi)
 		.tx_buf = (u8 [2]) { 0, 0 },
 		.tx_len = 2,
 	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
 
-	return mipi_dsi_device_transfer(dsi, &msg);
+	return (ret < 0) ? ret : 0;
 }
 EXPORT_SYMBOL(mipi_dsi_turn_on_peripheral);
 
@@ -541,8 +543,9 @@ int mipi_dsi_set_maximum_return_packet_size(struct mipi_dsi_device *dsi,
 		.tx_len = sizeof(tx),
 		.tx_buf = tx,
 	};
+	int ret = mipi_dsi_device_transfer(dsi, &msg);
 
-	return mipi_dsi_device_transfer(dsi, &msg);
+	return (ret < 0) ? ret : 0;
 }
 EXPORT_SYMBOL(mipi_dsi_set_maximum_return_packet_size);
 
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 4a3f68a33844..c397b523c945 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -833,7 +833,7 @@ EXPORT_SYMBOL(drm_mode_get_hv_timing);
  */
 void drm_mode_set_crtcinfo(struct drm_display_mode *p, int adjust_flags)
 {
-	if ((p == NULL) || ((p->type & DRM_MODE_TYPE_CRTC_C) == DRM_MODE_TYPE_BUILTIN))
+	if (!p)
 		return;
 
 	p->crtc_clock = p->clock;
@@ -1023,19 +1023,18 @@ bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1,
 }
 EXPORT_SYMBOL(drm_mode_equal_no_clocks_no_stereo);
 
-/**
- * drm_mode_validate_basic - make sure the mode is somewhat sane
- * @mode: mode to check
- *
- * Check that the mode timings are at least somewhat reasonable.
- * Any hardware specific limits are left up for each driver to check.
- *
- * Returns:
- * The mode status
- */
-enum drm_mode_status
+static enum drm_mode_status
 drm_mode_validate_basic(const struct drm_display_mode *mode)
 {
+	if (mode->type & ~DRM_MODE_TYPE_ALL)
+		return MODE_BAD;
+
+	if (mode->flags & ~DRM_MODE_FLAG_ALL)
+		return MODE_BAD;
+
+	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) > DRM_MODE_FLAG_3D_MAX)
+		return MODE_BAD;
+
 	if (mode->clock == 0)
 		return MODE_CLOCK_LOW;
 
@@ -1053,7 +1052,35 @@ drm_mode_validate_basic(const struct drm_display_mode *mode)
 
 	return MODE_OK;
 }
-EXPORT_SYMBOL(drm_mode_validate_basic);
+
+/**
+ * drm_mode_validate_driver - make sure the mode is somewhat sane
+ * @dev: drm device
+ * @mode: mode to check
+ *
+ * First do basic validation on the mode, and then allow the driver
+ * to check for device/driver specific limitations via the optional
+ * &drm_mode_config_helper_funcs.mode_valid hook.
+ *
+ * Returns:
+ * The mode status
+ */
+enum drm_mode_status
+drm_mode_validate_driver(struct drm_device *dev,
+			const struct drm_display_mode *mode)
+{
+	enum drm_mode_status status;
+
+	status = drm_mode_validate_basic(mode);
+	if (status != MODE_OK)
+		return status;
+
+	if (dev->mode_config.funcs->mode_valid)
+		return dev->mode_config.funcs->mode_valid(dev, mode);
+	else
+		return MODE_OK;
+}
+EXPORT_SYMBOL(drm_mode_validate_driver);
 
 /**
  * drm_mode_validate_size - make sure modes adhere to size constraints
@@ -1555,6 +1582,7 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out,
 
 /**
  * drm_crtc_convert_umode - convert a modeinfo into a drm_display_mode
+ * @dev: drm device
  * @out: drm_display_mode to return to the user
  * @in: drm_mode_modeinfo to use
  *
@@ -1564,7 +1592,8 @@ void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out,
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_convert_umode(struct drm_display_mode *out,
+int drm_mode_convert_umode(struct drm_device *dev,
+			   struct drm_display_mode *out,
 			   const struct drm_mode_modeinfo *in)
 {
 	int ret = -EINVAL;
@@ -1574,9 +1603,6 @@ int drm_mode_convert_umode(struct drm_display_mode *out,
 		goto out;
 	}
 
-	if ((in->flags & DRM_MODE_FLAG_3D_MASK) > DRM_MODE_FLAG_3D_MAX)
-		goto out;
-
 	out->clock = in->clock;
 	out->hdisplay = in->hdisplay;
 	out->hsync_start = in->hsync_start;
@@ -1594,7 +1620,7 @@ int drm_mode_convert_umode(struct drm_display_mode *out,
 	strncpy(out->name, in->name, DRM_DISPLAY_MODE_LEN);
 	out->name[DRM_DISPLAY_MODE_LEN-1] = 0;
 
-	out->status = drm_mode_validate_basic(out);
+	out->status = drm_mode_validate_driver(dev, out);
 	if (out->status != MODE_OK)
 		goto out;
 
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 2c90519576a3..22b54663b6e7 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -173,6 +173,10 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane,
 	unsigned int format_modifier_count = 0;
 	int ret;
 
+	/* plane index is used with 32bit bitmasks */
+	if (WARN_ON(config->num_total_plane >= 32))
+		return -EINVAL;
+
 	ret = drm_mode_object_add(dev, &plane->base, DRM_MODE_OBJECT_PLANE);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 9a17725b0f7a..e82a976f0fba 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -73,6 +73,9 @@
  * Drivers should detect this situation and return back the gem object
  * from the dma-buf private.  Prime will do this automatically for drivers that
  * use the drm_gem_prime_{import,export} helpers.
+ *
+ * GEM struct &dma_buf_ops symbols are now exported. They can be resued by
+ * drivers which implement GEM interface.
  */
 
 struct drm_prime_member {
@@ -180,9 +183,20 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
 	return -ENOENT;
 }
 
-static int drm_gem_map_attach(struct dma_buf *dma_buf,
-			      struct device *target_dev,
-			      struct dma_buf_attachment *attach)
+/**
+ * drm_gem_map_attach - dma_buf attach implementation for GEM
+ * @dma_buf: buffer to attach device to
+ * @target_dev: not used
+ * @attach: buffer attachment data
+ *
+ * Allocates &drm_prime_attachment and calls &drm_driver.gem_prime_pin for
+ * device specific attachment. This can be used as the &dma_buf_ops.attach
+ * callback.
+ *
+ * Returns 0 on success, negative error code on failure.
+ */
+int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev,
+		       struct dma_buf_attachment *attach)
 {
 	struct drm_prime_attachment *prime_attach;
 	struct drm_gem_object *obj = dma_buf->priv;
@@ -200,9 +214,18 @@ static int drm_gem_map_attach(struct dma_buf *dma_buf,
 
 	return dev->driver->gem_prime_pin(obj);
 }
+EXPORT_SYMBOL(drm_gem_map_attach);
 
-static void drm_gem_map_detach(struct dma_buf *dma_buf,
-			       struct dma_buf_attachment *attach)
+/**
+ * drm_gem_map_detach - dma_buf detach implementation for GEM
+ * @dma_buf: buffer to detach from
+ * @attach: attachment to be detached
+ *
+ * Cleans up &dma_buf_attachment. This can be used as the &dma_buf_ops.detach
+ * callback.
+ */
+void drm_gem_map_detach(struct dma_buf *dma_buf,
+			struct dma_buf_attachment *attach)
 {
 	struct drm_prime_attachment *prime_attach = attach->priv;
 	struct drm_gem_object *obj = dma_buf->priv;
@@ -228,6 +251,7 @@ static void drm_gem_map_detach(struct dma_buf *dma_buf,
 	kfree(prime_attach);
 	attach->priv = NULL;
 }
+EXPORT_SYMBOL(drm_gem_map_detach);
 
 void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv,
 					struct dma_buf *dma_buf)
@@ -254,8 +278,20 @@ void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpr
 	}
 }
 
-static struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
-					    enum dma_data_direction dir)
+/**
+ * drm_gem_map_dma_buf - map_dma_buf implementation for GEM
+ * @attach: attachment whose scatterlist is to be returned
+ * @dir: direction of DMA transfer
+ *
+ * Calls &drm_driver.gem_prime_get_sg_table and then maps the scatterlist. This
+ * can be used as the &dma_buf_ops.map_dma_buf callback.
+ *
+ * Returns sg_table containing the scatterlist to be returned; returns ERR_PTR
+ * on error. May return -EINTR if it is interrupted by a signal.
+ */
+
+struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
+				     enum dma_data_direction dir)
 {
 	struct drm_prime_attachment *prime_attach = attach->priv;
 	struct drm_gem_object *obj = attach->dmabuf->priv;
@@ -291,13 +327,21 @@ static struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
 
 	return sgt;
 }
+EXPORT_SYMBOL(drm_gem_map_dma_buf);
 
-static void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
-				  struct sg_table *sgt,
-				  enum dma_data_direction dir)
+/**
+ * drm_gem_unmap_dma_buf - unmap_dma_buf implementation for GEM
+ *
+ * Not implemented. The unmap is done at drm_gem_map_detach().  This can be
+ * used as the &dma_buf_ops.unmap_dma_buf callback.
+ */
+void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
+			   struct sg_table *sgt,
+			   enum dma_data_direction dir)
 {
 	/* nothing to be done here */
 }
+EXPORT_SYMBOL(drm_gem_unmap_dma_buf);
 
 /**
  * drm_gem_dmabuf_export - dma_buf export implementation for GEM
@@ -348,47 +392,99 @@ void drm_gem_dmabuf_release(struct dma_buf *dma_buf)
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_release);
 
-static void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf)
+/**
+ * drm_gem_dmabuf_vmap - dma_buf vmap implementation for GEM
+ * @dma_buf: buffer to be mapped
+ *
+ * Sets up a kernel virtual mapping. This can be used as the &dma_buf_ops.vmap
+ * callback.
+ *
+ * Returns the kernel virtual address.
+ */
+void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
 
 	return dev->driver->gem_prime_vmap(obj);
 }
+EXPORT_SYMBOL(drm_gem_dmabuf_vmap);
 
-static void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
+/**
+ * drm_gem_dmabuf_vunmap - dma_buf vunmap implementation for GEM
+ * @dma_buf: buffer to be unmapped
+ * @vaddr: the virtual address of the buffer
+ *
+ * Releases a kernel virtual mapping. This can be used as the
+ * &dma_buf_ops.vunmap callback.
+ */
+void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
 
 	dev->driver->gem_prime_vunmap(obj, vaddr);
 }
+EXPORT_SYMBOL(drm_gem_dmabuf_vunmap);
 
-static void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-					unsigned long page_num)
-{
-	return NULL;
-}
-
-static void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-					 unsigned long page_num, void *addr)
-{
-
-}
-static void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf,
+/**
+ * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM
+ *
+ * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback.
+ */
+void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
 				 unsigned long page_num)
 {
 	return NULL;
 }
+EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic);
 
-static void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf,
+/**
+ * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM
+ *
+ * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback.
+ */
+void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
 				  unsigned long page_num, void *addr)
 {
 
 }
+EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic);
 
-static int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf,
-			       struct vm_area_struct *vma)
+/**
+ * drm_gem_dmabuf_kmap - map implementation for GEM
+ *
+ * Not implemented. This can be used as the &dma_buf_ops.map callback.
+ */
+void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
+{
+	return NULL;
+}
+EXPORT_SYMBOL(drm_gem_dmabuf_kmap);
+
+/**
+ * drm_gem_dmabuf_kunmap - unmap implementation for GEM
+ *
+ * Not implemented. This can be used as the &dma_buf_ops.unmap callback.
+ */
+void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num,
+			   void *addr)
+{
+
+}
+EXPORT_SYMBOL(drm_gem_dmabuf_kunmap);
+
+/**
+ * drm_gem_dmabuf_mmap - dma_buf mmap implementation for GEM
+ * @dma_buf: buffer to be mapped
+ * @vma: virtual address range
+ *
+ * Provides memory mapping for the buffer. This can be used as the
+ * &dma_buf_ops.mmap callback.
+ *
+ * Returns 0 on success or a negative error code on failure.
+ */
+int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct drm_device *dev = obj->dev;
@@ -398,6 +494,7 @@ static int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf,
 
 	return dev->driver->gem_prime_mmap(obj, vma);
 }
+EXPORT_SYMBOL(drm_gem_dmabuf_mmap);
 
 static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
 	.attach = drm_gem_map_attach,
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 555fbe54d6e2..2d1643bdae78 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -499,7 +499,7 @@ retry:
 
 	list_for_each_entry(mode, &connector->modes, head) {
 		if (mode->status == MODE_OK)
-			mode->status = drm_mode_validate_basic(mode);
+			mode->status = drm_mode_validate_driver(dev, mode);
 
 		if (mode->status == MODE_OK)
 			mode->status = drm_mode_validate_size(mode, maxX, maxY);
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 9f3b1c94802b..9d3f6b70812c 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -100,8 +100,9 @@ static int drm_simple_kms_plane_atomic_check(struct drm_plane *plane,
 	if (!crtc_state->enable)
 		return 0; /* nothing to check when disabling or disabled */
 
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	ret = drm_atomic_helper_check_plane_state(plane_state, crtc_state,
 						  &clip,
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index dc5d79465f9b..257299ec95c4 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -179,18 +179,6 @@ static const u8 filter_cr_horiz_tap4[] = {
 	70,	59,	48,	37,	27,	19,	11,	5,
 };
 
-static inline bool is_alpha_format(unsigned int pixel_format)
-{
-	switch (pixel_format) {
-	case DRM_FORMAT_ARGB8888:
-	case DRM_FORMAT_ARGB1555:
-	case DRM_FORMAT_ARGB4444:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static inline u32 vp_reg_read(struct mixer_context *ctx, u32 reg_id)
 {
 	return readl(ctx->vp_regs + reg_id);
@@ -625,7 +613,7 @@ static void mixer_graph_buffer(struct mixer_context *ctx,
 	mixer_reg_write(ctx, MXR_GRAPHIC_BASE(win), dma_addr);
 
 	mixer_cfg_layer(ctx, win, priority, true);
-	mixer_cfg_gfx_blend(ctx, win, is_alpha_format(fb->format->format));
+	mixer_cfg_gfx_blend(ctx, win, fb->format->has_alpha);
 
 	/* layer update mandatory for mixer 16.0.33.0 */
 	if (ctx->mxr_ver == MXR_VER_16_0_33_0 ||
diff --git a/drivers/gpu/drm/i2c/sil164_drv.c b/drivers/gpu/drm/i2c/sil164_drv.c
index ecaa58757529..c52d7a3af786 100644
--- a/drivers/gpu/drm/i2c/sil164_drv.c
+++ b/drivers/gpu/drm/i2c/sil164_drv.c
@@ -326,8 +326,7 @@ sil164_encoder_destroy(struct drm_encoder *encoder)
 {
 	struct sil164_priv *priv = to_sil164_priv(encoder);
 
-	if (priv->duallink_slave)
-		i2c_unregister_device(priv->duallink_slave);
+	i2c_unregister_device(priv->duallink_slave);
 
 	kfree(priv);
 	drm_i2c_encoder_destroy(encoder);
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index cd3f0873bbdd..9e67a7b4e3a4 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1600,8 +1600,7 @@ fail:
 	/* if encoder_init fails, the encoder slave is never registered,
 	 * so cleanup here:
 	 */
-	if (priv->cec)
-		i2c_unregister_device(priv->cec);
+	i2c_unregister_device(priv->cec);
 	return -ENXIO;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index 57ee8b786cd8..0ee32275994a 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -128,14 +128,6 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	if (!intel_state->base.crtc && !old_plane_state->base.crtc)
 		return 0;
 
-	/* Clip all planes to CRTC size, or 0x0 if CRTC is disabled */
-	intel_state->clip.x1 = 0;
-	intel_state->clip.y1 = 0;
-	intel_state->clip.x2 =
-		crtc_state->base.enable ? crtc_state->pipe_src_w : 0;
-	intel_state->clip.y2 =
-		crtc_state->base.enable ? crtc_state->pipe_src_h : 0;
-
 	if (state->fb && drm_rotation_90_or_270(state->rotation)) {
 		struct drm_format_name_buf format_name;
 
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 9f31aea51dff..1cd4a7c22bd5 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -304,9 +304,6 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	int max_dotclk = dev_priv->max_dotclk_freq;
 	int max_clock;
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
 	if (mode->clock < 25000)
 		return MODE_CLOCK_LOW;
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e9bba2ab4904..15523f0e3b44 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -6404,9 +6404,18 @@ static int intel_crtc_compute_config(struct intel_crtc *crtc,
 	 * - LVDS dual channel mode
 	 * - Double wide pipe
 	 */
-	if ((intel_crtc_has_type(pipe_config, INTEL_OUTPUT_LVDS) &&
-	     intel_is_dual_link_lvds(dev)) || pipe_config->double_wide)
-		pipe_config->pipe_src_w &= ~1;
+	if (pipe_config->pipe_src_w & 1) {
+		if (pipe_config->double_wide) {
+			DRM_DEBUG_KMS("Odd pipe source width not supported with double wide pipe\n");
+			return -EINVAL;
+		}
+
+		if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_LVDS) &&
+		    intel_is_dual_link_lvds(dev)) {
+			DRM_DEBUG_KMS("Odd pipe source width not supported with dual link LVDS\n");
+			return -EINVAL;
+		}
+	}
 
 	/* Cantiga+ cannot handle modes with a hsync front porch of 0.
 	 * WaPruneModeWithIncorrectHsyncOffset:ctg,elk,ilk,snb,ivb,vlv,hsw.
@@ -9343,13 +9352,18 @@ static int intel_check_cursor(struct intel_crtc_state *crtc_state,
 			      struct intel_plane_state *plane_state)
 {
 	const struct drm_framebuffer *fb = plane_state->base.fb;
+	struct drm_rect clip = {};
 	int src_x, src_y;
 	u32 offset;
 	int ret;
 
+	if (crtc_state->base.enable)
+		drm_mode_get_hv_timing(&crtc_state->base.mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
 						  &crtc_state->base,
-						  &plane_state->clip,
+						  &clip,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  true, true);
@@ -12784,6 +12798,7 @@ intel_check_primary_plane(struct intel_plane *plane,
 	int min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	int max_scale = DRM_PLANE_HELPER_NO_SCALING;
 	bool can_position = false;
+	struct drm_rect clip = {};
 	int ret;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
@@ -12795,9 +12810,13 @@ intel_check_primary_plane(struct intel_plane *plane,
 		can_position = true;
 	}
 
+	if (crtc_state->base.enable)
+		drm_mode_get_hv_timing(&crtc_state->base.mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(&state->base,
 						  &crtc_state->base,
-						  &state->clip,
+						  &clip,
 						  min_scale, max_scale,
 						  can_position, true);
 	if (ret)
@@ -14097,10 +14116,37 @@ static void intel_atomic_state_free(struct drm_atomic_state *state)
 	kfree(state);
 }
 
+static enum drm_mode_status
+intel_mode_valid(struct drm_device *dev,
+		 const struct drm_display_mode *mode)
+{
+	if (mode->vscan > 1)
+		return MODE_NO_VSCAN;
+
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
+	if (mode->flags & DRM_MODE_FLAG_HSKEW)
+		return MODE_H_ILLEGAL;
+
+	if (mode->flags & (DRM_MODE_FLAG_CSYNC |
+			   DRM_MODE_FLAG_NCSYNC |
+			   DRM_MODE_FLAG_PCSYNC))
+		return MODE_HSYNC;
+
+	if (mode->flags & (DRM_MODE_FLAG_BCAST |
+			   DRM_MODE_FLAG_PIXMUX |
+			   DRM_MODE_FLAG_CLKDIV2))
+		return MODE_BAD;
+
+	return MODE_OK;
+}
+
 static const struct drm_mode_config_funcs intel_mode_funcs = {
 	.fb_create = intel_user_framebuffer_create,
 	.get_format_info = intel_get_format_info,
 	.output_poll_changed = intel_fbdev_output_poll_changed,
+	.mode_valid = intel_mode_valid,
 	.atomic_check = intel_atomic_check,
 	.atomic_commit = intel_atomic_commit,
 	.atomic_state_alloc = intel_atomic_state_alloc,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 71355fdec94a..cdcbeb595bb1 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -406,7 +406,6 @@ struct intel_atomic_state {
 
 struct intel_plane_state {
 	struct drm_plane_state base;
-	struct drm_rect clip;
 	struct i915_vma *vma;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index f67d321376e4..51a1d6868b1e 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -1266,11 +1266,6 @@ intel_dsi_mode_valid(struct drm_connector *connector,
 
 	DRM_DEBUG_KMS("\n");
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN) {
-		DRM_DEBUG_KMS("MODE_NO_DBLESCAN\n");
-		return MODE_NO_DBLESCAN;
-	}
-
 	if (fixed_mode) {
 		if (mode->hdisplay > fixed_mode->hdisplay)
 			return MODE_PANEL;
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 754baa00bea9..59c066ca14e5 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -219,9 +219,6 @@ intel_dvo_mode_valid(struct drm_connector *connector,
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 	int target_clock = mode->clock;
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
 	/* XXX: Validate clock range */
 
 	if (fixed_mode) {
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 80682a418a70..d7d1ac79c38a 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -799,8 +799,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 		return false;
 	}
 
-	if ((cache->crtc.mode_flags & DRM_MODE_FLAG_INTERLACE) ||
-	    (cache->crtc.mode_flags & DRM_MODE_FLAG_DBLSCAN)) {
+	if (cache->crtc.mode_flags & DRM_MODE_FLAG_INTERLACE) {
 		fbc->no_fbc_reason = "incompatible mode";
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 2df18a85c3b4..23150f598dfa 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1314,9 +1314,6 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	bool force_dvi =
 		READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI;
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
 	clock = mode->clock;
 
 	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 2b8764897d68..0bf97ed5ffac 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1607,9 +1607,6 @@ intel_sdvo_mode_valid(struct drm_connector *connector,
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
 	if (intel_sdvo->pixel_clock_min > mode->clock)
 		return MODE_CLOCK_LOW;
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 32f10621fac8..3be22c0fcfb5 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -864,7 +864,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	uint32_t src_x, src_y, src_w, src_h;
 	struct drm_rect *src = &state->base.src;
 	struct drm_rect *dst = &state->base.dst;
-	const struct drm_rect *clip = &state->clip;
+	struct drm_rect clip = {};
 	int max_stride = INTEL_GEN(dev_priv) >= 9 ? 32768 : 16384;
 	int hscale, vscale;
 	int max_scale, min_scale;
@@ -923,7 +923,11 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	vscale = drm_rect_calc_vscale_relaxed(src, dst, min_scale, max_scale);
 	BUG_ON(vscale < 0);
 
-	state->base.visible = drm_rect_clip_scaled(src, dst, clip, hscale, vscale);
+	if (crtc_state->base.enable)
+		drm_mode_get_hv_timing(&crtc_state->base.mode,
+				       &clip.x2, &clip.y2);
+
+	state->base.visible = drm_rect_clip_scaled(src, dst, &clip, hscale, vscale);
 
 	crtc_x = dst->x1;
 	crtc_y = dst->y1;
diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c
index 57ed56d8623f..150628293c51 100644
--- a/drivers/gpu/drm/imx/ipuv3-plane.c
+++ b/drivers/gpu/drm/imx/ipuv3-plane.c
@@ -351,7 +351,7 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
 	struct drm_framebuffer *old_fb = old_state->fb;
 	unsigned long eba, ubo, vbo, old_ubo, old_vbo, alpha_eba;
 	bool can_position = (plane->type == DRM_PLANE_TYPE_OVERLAY);
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int hsub, vsub;
 	int ret;
 
@@ -367,10 +367,10 @@ static int ipu_plane_atomic_check(struct drm_plane *plane,
 	if (WARN_ON(!crtc_state))
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 5ef898b93d8d..b5c6eec9a584 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -108,8 +108,9 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (IS_ERR(crtc_state))
 		return PTR_ERR(crtc_state);
 
-	clip.x2 = crtc_state->mode.hdisplay;
-	clip.y2 = crtc_state->mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	return drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						   DRM_PLANE_HELPER_NO_SCALING,
diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
index d0a6ac8390f3..3801bee1f9e6 100644
--- a/drivers/gpu/drm/meson/meson_plane.c
+++ b/drivers/gpu/drm/meson/meson_plane.c
@@ -58,8 +58,9 @@ static int meson_plane_atomic_check(struct drm_plane *plane,
 	if (IS_ERR(crtc_state))
 		return PTR_ERR(crtc_state);
 
-	clip.x2 = crtc_state->mode.hdisplay;
-	clip.y2 = crtc_state->mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	return drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						   DRM_PLANE_HELPER_NO_SCALING,
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 68e5d9c94475..fb50a9ddaae8 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1620,8 +1620,8 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 			return MODE_VIRTUAL_X;
 		if (mode->vdisplay > 1024)
 			return MODE_VIRTUAL_Y;
-		if (mga_vga_calculate_mode_bandwidth(mode,
-			bpp > (31877 * 1024)))
+		if (mga_vga_calculate_mode_bandwidth(mode, bpp) >
+		    (31877 * 1024))
 			return MODE_BANDWIDTH;
 	} else if (mdev->type == G200_EV &&
 		(mga_vga_calculate_mode_bandwidth(mode, bpp)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 29678876fc09..98d4d7331767 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -286,7 +286,7 @@ static int mdp5_plane_atomic_check_with_state(struct drm_crtc_state *crtc_state,
 	uint32_t max_width, max_height;
 	bool out_of_bounds = false;
 	uint32_t caps = 0;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int min_scale, max_scale;
 	int ret;
 
@@ -320,13 +320,13 @@ static int mdp5_plane_atomic_check_with_state(struct drm_crtc_state *crtc_state,
 		return -ERANGE;
 	}
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
 	min_scale = FRAC_16_16(1, 8);
 	max_scale = FRAC_16_16(8, 1);
 
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  min_scale, max_scale,
 						  true, true);
@@ -471,7 +471,7 @@ static int mdp5_plane_atomic_async_check(struct drm_plane *plane,
 {
 	struct mdp5_plane_state *mdp5_state = to_mdp5_plane_state(state);
 	struct drm_crtc_state *crtc_state;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int min_scale, max_scale;
 	int ret;
 
@@ -499,13 +499,13 @@ static int mdp5_plane_atomic_async_check(struct drm_plane *plane,
 	    plane->state->fb != state->fb)
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
 	min_scale = FRAC_16_16(1, 8);
 	max_scale = FRAC_16_16(8, 1);
 
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  min_scale, max_scale,
 						  true, true);
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index dd8d4352ed99..1f55b3d80a56 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -232,8 +232,6 @@ struct nv50_wndw_atom {
 	struct drm_plane_state state;
 	u8 interval;
 
-	struct drm_rect clip;
-
 	struct {
 		u32  handle;
 		u16  offset:12;
@@ -848,10 +846,6 @@ nv50_wndw_atomic_check_acquire(struct nv50_wndw *wndw,
 	int ret;
 
 	NV_ATOMIC(drm, "%s acquire\n", wndw->plane.name);
-	asyw->clip.x1 = 0;
-	asyw->clip.y1 = 0;
-	asyw->clip.x2 = asyh->state.mode.hdisplay;
-	asyw->clip.y2 = asyh->state.mode.vdisplay;
 
 	asyw->image.w = fb->base.width;
 	asyw->image.h = fb->base.height;
@@ -1149,10 +1143,15 @@ static int
 nv50_curs_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
 		  struct nv50_head_atom *asyh)
 {
+	struct drm_rect clip = {};
 	int ret;
 
+	if (asyh->state.enable)
+		drm_mode_get_hv_timing(&asyh->state.mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
-						  &asyw->clip,
+						  &clip,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  true, true);
@@ -1436,13 +1435,18 @@ nv50_base_acquire(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw,
 		  struct nv50_head_atom *asyh)
 {
 	const struct drm_framebuffer *fb = asyw->state.fb;
+	struct drm_rect clip = {};
 	int ret;
 
 	if (!fb->format->depth)
 		return -EINVAL;
 
+	if (asyh->state.enable)
+		drm_mode_get_hv_timing(&asyh->state.mode,
+				       &clip.x2, &clip.y2);
+
 	ret = drm_atomic_helper_check_plane_state(&asyw->state, &asyh->state,
-						  &asyw->clip,
+						  &clip,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  DRM_PLANE_HELPER_NO_SCALING,
 						  false, true);
diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 6ba4031f3919..988048ebcc22 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -7,6 +7,16 @@ config DRM_PANEL
 menu "Display Panels"
 	depends on DRM && DRM_PANEL
 
+config DRM_PANEL_ARM_VERSATILE
+	tristate "ARM Versatile panel driver"
+	depends on OF
+	depends on MFD_SYSCON
+	select VIDEOMODE_HELPERS
+	help
+	  This driver supports the ARM Versatile panels connected to ARM
+	  reference designs. The panel is detected using special registers
+	  in the Versatile family syscon registers.
+
 config DRM_PANEL_LVDS
 	tristate "Generic LVDS panel driver"
 	depends on OF
diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile
index 6d251ebc568c..3d2a88d0e965 100644
--- a/drivers/gpu/drm/panel/Makefile
+++ b/drivers/gpu/drm/panel/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_DRM_PANEL_ARM_VERSATILE) += panel-arm-versatile.o
 obj-$(CONFIG_DRM_PANEL_LVDS) += panel-lvds.o
 obj-$(CONFIG_DRM_PANEL_SIMPLE) += panel-simple.o
 obj-$(CONFIG_DRM_PANEL_ILITEK_IL9322) += panel-ilitek-ili9322.o
diff --git a/drivers/gpu/drm/panel/panel-arm-versatile.c b/drivers/gpu/drm/panel/panel-arm-versatile.c
new file mode 100644
index 000000000000..3930b4925b15
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-arm-versatile.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Panel driver for the ARM Versatile family reference designs from
+ * ARM Limited.
+ *
+ * Author:
+ * Linus Walleij <linus.wallei@linaro.org>
+ *
+ * On the Versatile AB, these panels come mounted on daughterboards
+ * named "IB1" or "IB2" (Interface Board 1 & 2 respectively.) They
+ * are documented in ARM DUI 0225D Appendix C and D. These daughter
+ * boards support TFT display panels.
+ *
+ * - The IB1 is a passive board where the display connector defines a
+ *   few wires for encoding the display type for autodetection,
+ *   suitable display settings can then be looked up from this setting.
+ *   The magic bits can be read out from the system controller.
+ *
+ * - The IB2 is a more complex board intended for GSM phone development
+ *   with some logic and a control register, which needs to be accessed
+ *   and the board display needs to be turned on explicitly.
+ *
+ * On the Versatile PB, a special CLCD adaptor board is available
+ * supporting the same displays as the Versatile AB, plus one more
+ * Epson QCIF display.
+ *
+ */
+#include <drm/drmP.h>
+#include <drm/drm_panel.h>
+
+#include <linux/bitops.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include <video/of_videomode.h>
+#include <video/videomode.h>
+
+/*
+ * This configuration register in the Versatile and RealView
+ * family is uniformly present but appears more and more
+ * unutilized starting with the RealView series.
+ */
+#define SYS_CLCD			0x50
+
+/* The Versatile can detect the connected panel type */
+#define SYS_CLCD_CLCDID_MASK		(BIT(8)|BIT(9)|BIT(10)|BIT(11)|BIT(12))
+#define SYS_CLCD_ID_SANYO_3_8		(0x00 << 8)
+#define SYS_CLCD_ID_SHARP_8_4		(0x01 << 8)
+#define SYS_CLCD_ID_EPSON_2_2		(0x02 << 8)
+#define SYS_CLCD_ID_SANYO_2_5		(0x07 << 8)
+#define SYS_CLCD_ID_VGA			(0x1f << 8)
+
+/* IB2 control register for the Versatile daughterboard */
+#define IB2_CTRL			0x00
+#define IB2_CTRL_LCD_SD			BIT(1) /* 1 = shut down LCD */
+#define IB2_CTRL_LCD_BL_ON		BIT(0)
+#define IB2_CTRL_LCD_MASK		(BIT(0)|BIT(1))
+
+/**
+ * struct versatile_panel_type - lookup struct for the supported panels
+ */
+struct versatile_panel_type {
+	/**
+	 * @name: the name of this panel
+	 */
+	const char *name;
+	/**
+	 * @magic: the magic value from the detection register
+	 */
+	u32 magic;
+	/**
+	 * @mode: the DRM display mode for this panel
+	 */
+	struct drm_display_mode mode;
+	/**
+	 * @bus_flags: the DRM bus flags for this panel e.g. inverted clock
+	 */
+	u32 bus_flags;
+	/**
+	 * @width_mm: the panel width in mm
+	 */
+	u32 width_mm;
+	/**
+	 * @height_mm: the panel height in mm
+	 */
+	u32 height_mm;
+	/**
+	 * @ib2: the panel may be connected on an IB2 daughterboard
+	 */
+	bool ib2;
+};
+
+/**
+ * struct versatile_panel - state container for the Versatile panels
+ */
+struct versatile_panel {
+	/**
+	 * @dev: the container device
+	 */
+	struct device *dev;
+	/**
+	 * @panel: the DRM panel instance for this device
+	 */
+	struct drm_panel panel;
+	/**
+	 * @panel_type: the Versatile panel type as detected
+	 */
+	const struct versatile_panel_type *panel_type;
+	/**
+	 * @map: map to the parent syscon where the main register reside
+	 */
+	struct regmap *map;
+	/**
+	 * @ib2_map: map to the IB2 syscon, if applicable
+	 */
+	struct regmap *ib2_map;
+};
+
+static const struct versatile_panel_type versatile_panels[] = {
+	/*
+	 * Sanyo TM38QV67A02A - 3.8 inch QVGA (320x240) Color TFT
+	 * found on the Versatile AB IB1 connector or the Versatile
+	 * PB adaptor board connector.
+	 */
+	{
+		.name = "Sanyo TM38QV67A02A",
+		.magic = SYS_CLCD_ID_SANYO_3_8,
+		.width_mm = 79,
+		.height_mm = 54,
+		.mode = {
+			.clock = 10000000,
+			.hdisplay = 320,
+			.hsync_start = 320 + 6,
+			.hsync_end = 320 + 6 + 6,
+			.htotal = 320 + 6 + 6 + 6,
+			.vdisplay = 240,
+			.vsync_start = 240 + 5,
+			.vsync_end = 240 + 5 + 6,
+			.vtotal = 240 + 5 + 6 + 5,
+			.vrefresh = 116,
+			.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+		},
+	},
+	/*
+	 * Sharp LQ084V1DG21 640x480 VGA Color TFT module
+	 * found on the Versatile AB IB1 connector or the Versatile
+	 * PB adaptor board connector.
+	 */
+	{
+		.name = "Sharp LQ084V1DG21",
+		.magic = SYS_CLCD_ID_SHARP_8_4,
+		.width_mm = 171,
+		.height_mm = 130,
+		.mode = {
+			.clock = 25000000,
+			.hdisplay = 640,
+			.hsync_start = 640 + 24,
+			.hsync_end = 640 + 24 + 96,
+			.htotal = 640 + 24 + 96 + 24,
+			.vdisplay = 480,
+			.vsync_start = 480 + 11,
+			.vsync_end = 480 + 11 + 2,
+			.vtotal = 480 + 11 + 2 + 32,
+			.vrefresh = 60,
+			.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+		},
+	},
+	/*
+	 * Epson L2F50113T00 - 2.2 inch QCIF 176x220 Color TFT
+	 * found on the Versatile PB adaptor board connector.
+	 */
+	{
+		.name = "Epson L2F50113T00",
+		.magic = SYS_CLCD_ID_EPSON_2_2,
+		.width_mm = 34,
+		.height_mm = 45,
+		.mode = {
+			.clock = 625000000,
+			.hdisplay = 176,
+			.hsync_start = 176 + 2,
+			.hsync_end = 176 + 2 + 3,
+			.htotal = 176 + 2 + 3 + 3,
+			.vdisplay = 220,
+			.vsync_start = 220 + 0,
+			.vsync_end = 220 + 0 + 2,
+			.vtotal = 220 + 0 + 2 + 1,
+			.vrefresh = 390,
+			.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+		},
+		.bus_flags = DRM_BUS_FLAG_PIXDATA_NEGEDGE,
+	},
+	/*
+	 * Sanyo ALR252RGT 240x320 portrait display found on the
+	 * Versatile AB IB2 daughterboard for GSM prototyping.
+	 */
+	{
+		.name = "Sanyo ALR252RGT",
+		.magic = SYS_CLCD_ID_SANYO_2_5,
+		.width_mm = 37,
+		.height_mm = 50,
+		.mode = {
+			.clock = 5400000,
+			.hdisplay = 240,
+			.hsync_start = 240 + 10,
+			.hsync_end = 240 + 10 + 10,
+			.htotal = 240 + 10 + 10 + 20,
+			.vdisplay = 320,
+			.vsync_start = 320 + 2,
+			.vsync_end = 320 + 2 + 2,
+			.vtotal = 320 + 2 + 2 + 2,
+			.vrefresh = 116,
+			.flags = DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC,
+		},
+		.bus_flags = DRM_BUS_FLAG_PIXDATA_NEGEDGE,
+		.ib2 = true,
+	},
+};
+
+static inline struct versatile_panel *
+to_versatile_panel(struct drm_panel *panel)
+{
+	return container_of(panel, struct versatile_panel, panel);
+}
+
+static int versatile_panel_disable(struct drm_panel *panel)
+{
+	struct versatile_panel *vpanel = to_versatile_panel(panel);
+
+	/* If we're on an IB2 daughterboard, turn off display */
+	if (vpanel->ib2_map) {
+		dev_dbg(vpanel->dev, "disable IB2 display\n");
+		regmap_update_bits(vpanel->ib2_map,
+				   IB2_CTRL,
+				   IB2_CTRL_LCD_MASK,
+				   IB2_CTRL_LCD_SD);
+	}
+
+	return 0;
+}
+
+static int versatile_panel_enable(struct drm_panel *panel)
+{
+	struct versatile_panel *vpanel = to_versatile_panel(panel);
+
+	/* If we're on an IB2 daughterboard, turn on display */
+	if (vpanel->ib2_map) {
+		dev_dbg(vpanel->dev, "enable IB2 display\n");
+		regmap_update_bits(vpanel->ib2_map,
+				   IB2_CTRL,
+				   IB2_CTRL_LCD_MASK,
+				   IB2_CTRL_LCD_BL_ON);
+	}
+
+	return 0;
+}
+
+static int versatile_panel_get_modes(struct drm_panel *panel)
+{
+	struct drm_connector *connector = panel->connector;
+	struct versatile_panel *vpanel = to_versatile_panel(panel);
+	struct drm_display_mode *mode;
+
+	strncpy(connector->display_info.name, vpanel->panel_type->name,
+		DRM_DISPLAY_INFO_LEN);
+	connector->display_info.width_mm = vpanel->panel_type->width_mm;
+	connector->display_info.height_mm = vpanel->panel_type->height_mm;
+	connector->display_info.bus_flags = vpanel->panel_type->bus_flags;
+
+	mode = drm_mode_duplicate(panel->drm, &vpanel->panel_type->mode);
+	drm_mode_set_name(mode);
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+
+	mode->width_mm = vpanel->panel_type->width_mm;
+	mode->height_mm = vpanel->panel_type->height_mm;
+	drm_mode_probed_add(connector, mode);
+
+	return 1;
+}
+
+static const struct drm_panel_funcs versatile_panel_drm_funcs = {
+	.disable = versatile_panel_disable,
+	.enable = versatile_panel_enable,
+	.get_modes = versatile_panel_get_modes,
+};
+
+static int versatile_panel_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct versatile_panel *vpanel;
+	struct device *parent;
+	struct regmap *map;
+	int ret;
+	u32 val;
+	int i;
+
+	parent = dev->parent;
+	if (!parent) {
+		dev_err(dev, "no parent for versatile panel\n");
+		return -ENODEV;
+	}
+	map = syscon_node_to_regmap(parent->of_node);
+	if (IS_ERR(map)) {
+		dev_err(dev, "no regmap for versatile panel parent\n");
+		return PTR_ERR(map);
+	}
+
+	vpanel = devm_kzalloc(dev, sizeof(*vpanel), GFP_KERNEL);
+	if (!vpanel)
+		return -ENOMEM;
+
+	ret = regmap_read(map, SYS_CLCD, &val);
+	if (ret) {
+		dev_err(dev, "cannot access syscon regs\n");
+		return ret;
+	}
+
+	val &= SYS_CLCD_CLCDID_MASK;
+
+	for (i = 0; i < ARRAY_SIZE(versatile_panels); i++) {
+		const struct versatile_panel_type *pt;
+
+		pt = &versatile_panels[i];
+		if (pt->magic == val) {
+			vpanel->panel_type = pt;
+			break;
+		}
+	}
+
+	/* No panel detected or VGA, let's leave this show */
+	if (i == ARRAY_SIZE(versatile_panels)) {
+		dev_info(dev, "no panel detected\n");
+		return -ENODEV;
+	}
+
+	dev_info(dev, "detected: %s\n", vpanel->panel_type->name);
+	vpanel->dev = dev;
+	vpanel->map = map;
+
+	/* Check if the panel is mounted on an IB2 daughterboard */
+	if (vpanel->panel_type->ib2) {
+		vpanel->ib2_map = syscon_regmap_lookup_by_compatible(
+			"arm,versatile-ib2-syscon");
+		if (IS_ERR(vpanel->ib2_map))
+			vpanel->ib2_map = NULL;
+		else
+			dev_info(dev, "panel mounted on IB2 daughterboard\n");
+	}
+
+	drm_panel_init(&vpanel->panel);
+	vpanel->panel.dev = dev;
+	vpanel->panel.funcs = &versatile_panel_drm_funcs;
+
+	return drm_panel_add(&vpanel->panel);
+}
+
+static const struct of_device_id versatile_panel_match[] = {
+	{ .compatible = "arm,versatile-tft-panel", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, versatile_panel_match);
+
+static struct platform_driver versatile_panel_driver = {
+	.probe		= versatile_panel_probe,
+	.driver		= {
+		.name	= "versatile-tft-panel",
+		.of_match_table = versatile_panel_match,
+	},
+};
+module_platform_driver(versatile_panel_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("ARM Versatile panel driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
index 7f915f706fa6..74a806121f80 100644
--- a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
+++ b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
@@ -59,34 +59,28 @@ static inline struct wuxga_nt_panel *to_wuxga_nt_panel(struct drm_panel *panel)
 
 static int wuxga_nt_panel_on(struct wuxga_nt_panel *wuxga_nt)
 {
-	struct mipi_dsi_device *dsi = wuxga_nt->dsi;
-	int ret;
-
-	ret = mipi_dsi_turn_on_peripheral(dsi);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+	return mipi_dsi_turn_on_peripheral(wuxga_nt->dsi);
 }
 
 static int wuxga_nt_panel_disable(struct drm_panel *panel)
 {
 	struct wuxga_nt_panel *wuxga_nt = to_wuxga_nt_panel(panel);
+	int mipi_ret, bl_ret = 0;
 
 	if (!wuxga_nt->enabled)
 		return 0;
 
-	mipi_dsi_shutdown_peripheral(wuxga_nt->dsi);
+	mipi_ret = mipi_dsi_shutdown_peripheral(wuxga_nt->dsi);
 
 	if (wuxga_nt->backlight) {
 		wuxga_nt->backlight->props.power = FB_BLANK_POWERDOWN;
 		wuxga_nt->backlight->props.state |= BL_CORE_FBBLANK;
-		backlight_update_status(wuxga_nt->backlight);
+		bl_ret = backlight_update_status(wuxga_nt->backlight);
 	}
 
 	wuxga_nt->enabled = false;
 
-	return 0;
+	return mipi_ret ? mipi_ret : bl_ret;
 }
 
 static int wuxga_nt_panel_unprepare(struct drm_panel *panel)
diff --git a/drivers/gpu/drm/pl111/Kconfig b/drivers/gpu/drm/pl111/Kconfig
index e5e2abd66491..82cb3e60ddc8 100644
--- a/drivers/gpu/drm/pl111/Kconfig
+++ b/drivers/gpu/drm/pl111/Kconfig
@@ -8,6 +8,7 @@ config DRM_PL111
 	select DRM_GEM_CMA_HELPER
 	select DRM_BRIDGE
 	select DRM_PANEL_BRIDGE
+	select DRM_DUMB_VGA_DAC
 	select VT_HW_CONSOLE_BINDING if FRAMEBUFFER_CONSOLE
 	help
 	  Choose this option for DRM support for the PL111 CLCD controller.
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 06c4bf756b69..d75923896609 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -94,6 +94,7 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 	const struct drm_display_mode *mode = &cstate->mode;
 	struct drm_framebuffer *fb = plane->state->fb;
 	struct drm_connector *connector = priv->connector;
+	struct drm_bridge *bridge = priv->bridge;
 	u32 cntl;
 	u32 ppl, hsw, hfp, hbp;
 	u32 lpp, vsw, vfp, vbp;
@@ -137,17 +138,46 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 	tim2 = readl(priv->regs + CLCD_TIM2);
 	tim2 &= (TIM2_BCD | TIM2_PCD_LO_MASK | TIM2_PCD_HI_MASK);
 
+	if (priv->variant->broken_clockdivider)
+		tim2 |= TIM2_BCD;
+
 	if (mode->flags & DRM_MODE_FLAG_NHSYNC)
 		tim2 |= TIM2_IHS;
 
 	if (mode->flags & DRM_MODE_FLAG_NVSYNC)
 		tim2 |= TIM2_IVS;
 
-	if (connector->display_info.bus_flags & DRM_BUS_FLAG_DE_LOW)
-		tim2 |= TIM2_IOE;
+	if (connector) {
+		if (connector->display_info.bus_flags & DRM_BUS_FLAG_DE_LOW)
+			tim2 |= TIM2_IOE;
 
-	if (connector->display_info.bus_flags & DRM_BUS_FLAG_PIXDATA_NEGEDGE)
-		tim2 |= TIM2_IPC;
+		if (connector->display_info.bus_flags &
+		    DRM_BUS_FLAG_PIXDATA_NEGEDGE)
+			tim2 |= TIM2_IPC;
+	}
+
+	if (bridge) {
+		const struct drm_bridge_timings *btimings = bridge->timings;
+
+		/*
+		 * Here is when things get really fun. Sometimes the bridge
+		 * timings are such that the signal out from PL11x is not
+		 * stable before the receiving bridge (such as a dumb VGA DAC
+		 * or similar) samples it. If that happens, we compensate by
+		 * the only method we have: output the data on the opposite
+		 * edge of the clock so it is for sure stable when it gets
+		 * sampled.
+		 *
+		 * The PL111 manual does not contain proper timining diagrams
+		 * or data for these details, but we know from experiments
+		 * that the setup time is more than 3000 picoseconds (3 ns).
+		 * If we have a bridge that requires the signal to be stable
+		 * earlier than 3000 ps before the clock pulse, we have to
+		 * output the data on the opposite edge to avoid flicker.
+		 */
+		if (btimings && btimings->setup_time_ps >= 3000)
+			tim2 ^= TIM2_IPC;
+	}
 
 	tim2 |= cpl << 16;
 	writel(tim2, priv->regs + CLCD_TIM2);
@@ -172,10 +202,17 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 		cntl |= CNTL_LCDBPP24 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_BGR565:
-		cntl |= CNTL_LCDBPP16_565;
+		if (priv->variant->is_pl110)
+			cntl |= CNTL_LCDBPP16;
+		else
+			cntl |= CNTL_LCDBPP16_565;
 		break;
 	case DRM_FORMAT_RGB565:
-		cntl |= CNTL_LCDBPP16_565 | CNTL_BGR;
+		if (priv->variant->is_pl110)
+			cntl |= CNTL_LCDBPP16;
+		else
+			cntl |= CNTL_LCDBPP16_565;
+		cntl |= CNTL_BGR;
 		break;
 	case DRM_FORMAT_ABGR1555:
 	case DRM_FORMAT_XBGR1555:
@@ -199,6 +236,10 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 		break;
 	}
 
+	/* The PL110 in Integrator/Versatile does the BGR routing externally */
+	if (priv->variant->external_bgr)
+		cntl &= ~CNTL_BGR;
+
 	/* Power sequence: first enable and chill */
 	writel(cntl, priv->regs + priv->ctrl);
 
@@ -215,7 +256,8 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 	cntl |= CNTL_LCDPWR;
 	writel(cntl, priv->regs + priv->ctrl);
 
-	drm_crtc_vblank_on(crtc);
+	if (!priv->variant->broken_vblank)
+		drm_crtc_vblank_on(crtc);
 }
 
 void pl111_display_disable(struct drm_simple_display_pipe *pipe)
@@ -225,7 +267,8 @@ void pl111_display_disable(struct drm_simple_display_pipe *pipe)
 	struct pl111_drm_dev_private *priv = drm->dev_private;
 	u32 cntl;
 
-	drm_crtc_vblank_off(crtc);
+	if (!priv->variant->broken_vblank)
+		drm_crtc_vblank_off(crtc);
 
 	/* Power Down */
 	cntl = readl(priv->regs + priv->ctrl);
@@ -417,6 +460,11 @@ pl111_init_clock_divider(struct drm_device *drm)
 		dev_err(drm->dev, "CLCD: unable to get clcdclk.\n");
 		return PTR_ERR(parent);
 	}
+	/* If the clock divider is broken, use the parent directly */
+	if (priv->variant->broken_clockdivider) {
+		priv->clk = parent;
+		return 0;
+	}
 	parent_name = __clk_get_name(parent);
 
 	spin_lock_init(&priv->tim2_lock);
diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h
index 07fa2cdb364a..6d0e450e51b1 100644
--- a/drivers/gpu/drm/pl111/pl111_drm.h
+++ b/drivers/gpu/drm/pl111/pl111_drm.h
@@ -36,12 +36,20 @@ struct drm_minor;
  * struct pl111_variant_data - encodes IP differences
  * @name: the name of this variant
  * @is_pl110: this is the early PL110 variant
+ * @external_bgr: this is the Versatile Pl110 variant with external
+ *	BGR/RGB routing
+ * @broken_clockdivider: the clock divider is broken and we need to
+ *	use the supplied clock directly
+ * @broken_vblank: the vblank IRQ is broken on this variant
  * @formats: array of supported pixel formats on this variant
  * @nformats: the length of the array of supported pixel formats
  */
 struct pl111_variant_data {
 	const char *name;
 	bool is_pl110;
+	bool external_bgr;
+	bool broken_clockdivider;
+	bool broken_vblank;
 	const u32 *formats;
 	unsigned int nformats;
 };
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index acb738c69873..1231905150d0 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -58,6 +58,8 @@
 #include <linux/dma-buf.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_graph.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic_helper.h>
@@ -85,9 +87,13 @@ static int pl111_modeset_init(struct drm_device *dev)
 {
 	struct drm_mode_config *mode_config;
 	struct pl111_drm_dev_private *priv = dev->dev_private;
-	struct drm_panel *panel;
-	struct drm_bridge *bridge;
+	struct device_node *np = dev->dev->of_node;
+	struct device_node *remote;
+	struct drm_panel *panel = NULL;
+	struct drm_bridge *bridge = NULL;
+	bool defer = false;
 	int ret = 0;
+	int i;
 
 	drm_mode_config_init(dev);
 	mode_config = &dev->mode_config;
@@ -97,10 +103,54 @@ static int pl111_modeset_init(struct drm_device *dev)
 	mode_config->min_height = 1;
 	mode_config->max_height = 768;
 
-	ret = drm_of_find_panel_or_bridge(dev->dev->of_node,
-					  0, 0, &panel, &bridge);
-	if (ret && ret != -ENODEV)
-		return ret;
+	i = 0;
+	for_each_endpoint_of_node(np, remote) {
+		struct drm_panel *tmp_panel;
+		struct drm_bridge *tmp_bridge;
+
+		dev_dbg(dev->dev, "checking endpoint %d\n", i);
+
+		ret = drm_of_find_panel_or_bridge(dev->dev->of_node,
+						  0, i,
+						  &tmp_panel,
+						  &tmp_bridge);
+		if (ret) {
+			if (ret == -EPROBE_DEFER) {
+				/*
+				 * Something deferred, but that is often just
+				 * another way of saying -ENODEV, but let's
+				 * cast a vote for later deferral.
+				 */
+				defer = true;
+			} else if (ret != -ENODEV) {
+				/* Continue, maybe something else is working */
+				dev_err(dev->dev,
+					"endpoint %d returns %d\n", i, ret);
+			}
+		}
+
+		if (tmp_panel) {
+			dev_info(dev->dev,
+				 "found panel on endpoint %d\n", i);
+			panel = tmp_panel;
+		}
+		if (tmp_bridge) {
+			dev_info(dev->dev,
+				 "found bridge on endpoint %d\n", i);
+			bridge = tmp_bridge;
+		}
+
+		i++;
+	}
+
+	/*
+	 * If we can't find neither panel nor bridge on any of the
+	 * endpoints, and any of them retured -EPROBE_DEFER, then
+	 * let's defer this driver too.
+	 */
+	if ((!panel && !bridge) && defer)
+		return -EPROBE_DEFER;
+
 	if (panel) {
 		bridge = drm_panel_bridge_add(panel,
 					      DRM_MODE_CONNECTOR_Unknown);
@@ -108,11 +158,17 @@ static int pl111_modeset_init(struct drm_device *dev)
 			ret = PTR_ERR(bridge);
 			goto out_config;
 		}
-		/*
-		 * TODO: when we are using a different bridge than a panel
-		 * (such as a dumb VGA connector) we need to devise a different
-		 * method to get the connector out of the bridge.
-		 */
+	} else if (bridge) {
+		dev_info(dev->dev, "Using non-panel bridge\n");
+	} else {
+		dev_err(dev->dev, "No bridge, exiting\n");
+		return -ENODEV;
+	}
+
+	priv->bridge = bridge;
+	if (panel) {
+		priv->panel = panel;
+		priv->connector = panel->connector;
 	}
 
 	ret = pl111_display_init(dev);
@@ -126,14 +182,12 @@ static int pl111_modeset_init(struct drm_device *dev)
 	if (ret)
 		return ret;
 
-	priv->bridge = bridge;
-	priv->panel = panel;
-	priv->connector = panel->connector;
-
-	ret = drm_vblank_init(dev, 1);
-	if (ret != 0) {
-		dev_err(dev->dev, "Failed to init vblank\n");
-		goto out_bridge;
+	if (!priv->variant->broken_vblank) {
+		ret = drm_vblank_init(dev, 1);
+		if (ret != 0) {
+			dev_err(dev->dev, "Failed to init vblank\n");
+			goto out_bridge;
+		}
 	}
 
 	drm_mode_config_reset(dev);
@@ -170,10 +224,6 @@ static struct drm_driver pl111_drm_driver = {
 	.dumb_create = drm_gem_cma_dumb_create,
 	.gem_free_object_unlocked = drm_gem_cma_free_object,
 	.gem_vm_ops = &drm_gem_cma_vm_ops,
-
-	.enable_vblank = pl111_enable_vblank,
-	.disable_vblank = pl111_disable_vblank,
-
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_import = drm_gem_prime_import,
@@ -191,7 +241,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 {
 	struct device *dev = &amba_dev->dev;
 	struct pl111_drm_dev_private *priv;
-	struct pl111_variant_data *variant = id->data;
+	const struct pl111_variant_data *variant = id->data;
 	struct drm_device *drm;
 	int ret;
 
@@ -199,6 +249,11 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	if (!priv)
 		return -ENOMEM;
 
+	if (!variant->broken_vblank) {
+		pl111_drm_driver.enable_vblank = pl111_enable_vblank;
+		pl111_drm_driver.disable_vblank = pl111_disable_vblank;
+	}
+
 	drm = drm_dev_alloc(&pl111_drm_driver, dev);
 	if (IS_ERR(drm))
 		return PTR_ERR(drm);
@@ -207,27 +262,10 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	drm->dev_private = priv;
 	priv->variant = variant;
 
-	/*
-	 * The PL110 and PL111 variants have two registers
-	 * swapped: interrupt enable and control. For this reason
-	 * we use offsets that we can change per variant.
-	 */
+	/* The two variants swap this register */
 	if (variant->is_pl110) {
-		/*
-		 * The ARM Versatile boards are even more special:
-		 * their PrimeCell ID say they are PL110 but the
-		 * control and interrupt enable registers are anyway
-		 * swapped to the PL111 order so they are not following
-		 * the PL110 datasheet.
-		 */
-		if (of_machine_is_compatible("arm,versatile-ab") ||
-		    of_machine_is_compatible("arm,versatile-pb")) {
-			priv->ienb = CLCD_PL111_IENB;
-			priv->ctrl = CLCD_PL111_CNTL;
-		} else {
-			priv->ienb = CLCD_PL110_IENB;
-			priv->ctrl = CLCD_PL110_CNTL;
-		}
+		priv->ienb = CLCD_PL110_IENB;
+		priv->ctrl = CLCD_PL110_CNTL;
 	} else {
 		priv->ienb = CLCD_PL111_IENB;
 		priv->ctrl = CLCD_PL111_CNTL;
@@ -239,6 +277,11 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 		return PTR_ERR(priv->regs);
 	}
 
+	/* This may override some variant settings */
+	ret = pl111_versatile_init(dev, priv);
+	if (ret)
+		goto dev_unref;
+
 	/* turn off interrupts before requesting the irq */
 	writel(0, priv->regs + priv->ienb);
 
@@ -249,10 +292,6 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 		return ret;
 	}
 
-	ret = pl111_versatile_init(dev, priv);
-	if (ret)
-		goto dev_unref;
-
 	ret = pl111_modeset_init(drm);
 	if (ret != 0)
 		goto dev_unref;
@@ -284,8 +323,7 @@ static int pl111_amba_remove(struct amba_device *amba_dev)
 }
 
 /*
- * This variant exist in early versions like the ARM Integrator
- * and this version lacks the 565 and 444 pixel formats.
+ * This early variant lacks the 565 and 444 pixel formats.
  */
 static const u32 pl110_pixel_formats[] = {
 	DRM_FORMAT_ABGR8888,
diff --git a/drivers/gpu/drm/pl111/pl111_versatile.c b/drivers/gpu/drm/pl111/pl111_versatile.c
index 97d4af6925a3..05a4b89e0934 100644
--- a/drivers/gpu/drm/pl111/pl111_versatile.c
+++ b/drivers/gpu/drm/pl111/pl111_versatile.c
@@ -1,3 +1,4 @@
+#include <linux/amba/clcd-regs.h>
 #include <linux/device.h>
 #include <linux/of.h>
 #include <linux/regmap.h>
@@ -64,10 +65,8 @@ static const struct of_device_id versatile_clcd_of_match[] = {
 #define INTEGRATOR_CLCD_LCDBIASEN	BIT(8)
 #define INTEGRATOR_CLCD_LCDBIASUP	BIT(9)
 #define INTEGRATOR_CLCD_LCDBIASDN	BIT(10)
-/* Bits 11,12,13 controls the LCD type */
-#define INTEGRATOR_CLCD_LCDMUX_MASK	(BIT(11)|BIT(12)|BIT(13))
+/* Bits 11,12,13 controls the LCD or VGA bridge type */
 #define INTEGRATOR_CLCD_LCDMUX_LCD24	BIT(11)
-#define INTEGRATOR_CLCD_LCDMUX_VGA565	BIT(12)
 #define INTEGRATOR_CLCD_LCDMUX_SHARP	(BIT(11)|BIT(12))
 #define INTEGRATOR_CLCD_LCDMUX_VGA555	BIT(13)
 #define INTEGRATOR_CLCD_LCDMUX_VGA24	(BIT(11)|BIT(12)|BIT(13))
@@ -82,16 +81,7 @@ static const struct of_device_id versatile_clcd_of_match[] = {
 /* 0 = 24bit VGA, 1 = 18bit VGA */
 #define INTEGRATOR_CLCD_LCD_N24BITEN	BIT(19)
 
-#define INTEGRATOR_CLCD_MASK		(INTEGRATOR_CLCD_LCDBIASEN | \
-					 INTEGRATOR_CLCD_LCDBIASUP | \
-					 INTEGRATOR_CLCD_LCDBIASDN | \
-					 INTEGRATOR_CLCD_LCDMUX_MASK | \
-					 INTEGRATOR_CLCD_LCD0_EN | \
-					 INTEGRATOR_CLCD_LCD1_EN | \
-					 INTEGRATOR_CLCD_LCD_STATIC1 | \
-					 INTEGRATOR_CLCD_LCD_STATIC2 | \
-					 INTEGRATOR_CLCD_LCD_STATIC | \
-					 INTEGRATOR_CLCD_LCD_N24BITEN)
+#define INTEGRATOR_CLCD_MASK		GENMASK(19, 8)
 
 static void pl111_integrator_enable(struct drm_device *drm, u32 format)
 {
@@ -106,11 +96,8 @@ static void pl111_integrator_enable(struct drm_device *drm, u32 format)
 	switch (format) {
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_XRGB8888:
-		break;
-	case DRM_FORMAT_BGR565:
-	case DRM_FORMAT_RGB565:
-		/* truecolor RGB565 */
-		val |= INTEGRATOR_CLCD_LCDMUX_VGA565;
+		/* 24bit formats */
+		val |= INTEGRATOR_CLCD_LCDMUX_VGA24;
 		break;
 	case DRM_FORMAT_XBGR1555:
 	case DRM_FORMAT_XRGB1555:
@@ -217,6 +204,57 @@ static void pl111_realview_clcd_enable(struct drm_device *drm, u32 format)
 			   SYS_CLCD_NLCDIOON | SYS_CLCD_PWR3V5SWITCH);
 }
 
+/* PL110 pixel formats for Integrator, vanilla PL110 */
+static const u32 pl110_integrator_pixel_formats[] = {
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XRGB1555,
+};
+
+/* Extended PL110 pixel formats for Integrator and Versatile */
+static const u32 pl110_versatile_pixel_formats[] = {
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_BGR565, /* Uses external PLD */
+	DRM_FORMAT_RGB565, /* Uses external PLD */
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XRGB1555,
+};
+
+/*
+ * The Integrator variant is a PL110 with a bunch of broken, or not
+ * yet implemented features
+ */
+static const struct pl111_variant_data pl110_integrator = {
+	.name = "PL110 Integrator",
+	.is_pl110 = true,
+	.broken_clockdivider = true,
+	.broken_vblank = true,
+	.formats = pl110_integrator_pixel_formats,
+	.nformats = ARRAY_SIZE(pl110_integrator_pixel_formats),
+};
+
+/*
+ * This is the in-between PL110 variant found in the ARM Versatile,
+ * supporting RGB565/BGR565
+ */
+static const struct pl111_variant_data pl110_versatile = {
+	.name = "PL110 Versatile",
+	.is_pl110 = true,
+	.external_bgr = true,
+	.formats = pl110_versatile_pixel_formats,
+	.nformats = ARRAY_SIZE(pl110_versatile_pixel_formats),
+};
+
 int pl111_versatile_init(struct device *dev, struct pl111_drm_dev_private *priv)
 {
 	const struct of_device_id *clcd_id;
@@ -241,14 +279,24 @@ int pl111_versatile_init(struct device *dev, struct pl111_drm_dev_private *priv)
 	switch (versatile_clcd_type) {
 	case INTEGRATOR_CLCD_CM:
 		versatile_syscon_map = map;
+		priv->variant = &pl110_integrator;
 		priv->variant_display_enable = pl111_integrator_enable;
 		dev_info(dev, "set up callbacks for Integrator PL110\n");
 		break;
 	case VERSATILE_CLCD:
 		versatile_syscon_map = map;
+		/* This can do RGB565 with external PLD */
+		priv->variant = &pl110_versatile;
 		priv->variant_display_enable = pl111_versatile_enable;
 		priv->variant_display_disable = pl111_versatile_disable;
-		dev_info(dev, "set up callbacks for Versatile PL110+\n");
+		/*
+		 * The Versatile has a variant halfway between PL110
+		 * and PL111 where these two registers have already been
+		 * swapped.
+		 */
+		priv->ienb = CLCD_PL111_IENB;
+		priv->ctrl = CLCD_PL111_CNTL;
+		dev_info(dev, "set up callbacks for Versatile PL110\n");
 		break;
 	case REALVIEW_CLCD_EB:
 	case REALVIEW_CLCD_PB1176:
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index d34887873dea..4a2eb409aacc 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -2387,6 +2387,7 @@ struct radeon_device {
 	struct radeon_dummy_page	dummy_page;
 	bool				shutdown;
 	bool				need_dma32;
+	bool				need_swiotlb;
 	bool				accel_working;
 	bool				fastfb_working; /* IGP feature*/
 	bool				needs_reset, in_reset;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 8d3e3d2e0090..7f40c6f7c4dd 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_cache.h>
 #include <drm/radeon_drm.h>
 #include <linux/pm_runtime.h>
 #include <linux/vgaarb.h>
@@ -1378,6 +1379,7 @@ int radeon_device_init(struct radeon_device *rdev,
 		pci_set_consistent_dma_mask(rdev->pdev, DMA_BIT_MASK(32));
 		pr_warn("radeon: No coherent DMA available\n");
 	}
+	rdev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
 
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index a0a839bc39bf..c1e3862a48a4 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -756,7 +756,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm,
 #endif
 
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) {
+	if (rdev->need_swiotlb && swiotlb_nr_tbl()) {
 		return ttm_dma_populate(&gtt->ttm, rdev->dev, ctx);
 	}
 #endif
@@ -788,7 +788,7 @@ static void radeon_ttm_tt_unpopulate(struct ttm_tt *ttm)
 #endif
 
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) {
+	if (rdev->need_swiotlb && swiotlb_nr_tbl()) {
 		ttm_dma_unpopulate(&gtt->ttm, rdev->dev);
 		return;
 	}
@@ -1155,7 +1155,7 @@ static int radeon_ttm_debugfs_init(struct radeon_device *rdev)
 	count = ARRAY_SIZE(radeon_ttm_debugfs_list);
 
 #ifdef CONFIG_SWIOTLB
-	if (!swiotlb_nr_tbl())
+	if (!(rdev->need_swiotlb && swiotlb_nr_tbl()))
 		--count;
 #endif
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
index 4a3d16cf3ed6..5687a94d4cb1 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c
@@ -572,7 +572,7 @@ int __rcar_du_plane_atomic_check(struct drm_plane *plane,
 {
 	struct drm_device *dev = plane->dev;
 	struct drm_crtc_state *crtc_state;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int ret;
 
 	if (!state->crtc) {
@@ -589,10 +589,9 @@ int __rcar_du_plane_atomic_check(struct drm_plane *plane,
 	if (IS_ERR(crtc_state))
 		return PTR_ERR(crtc_state);
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->mode.hdisplay;
-	clip.y2 = crtc_state->mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  DRM_PLANE_HELPER_NO_SCALING,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index ba7505292b78..7715853ef90a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -253,17 +253,6 @@ static bool is_yuv_support(uint32_t format)
 	}
 }
 
-static bool is_alpha_support(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_ARGB8888:
-	case DRM_FORMAT_ABGR8888:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static uint16_t scl_vop_cal_scale(enum scale_mode mode, uint32_t src,
 				  uint32_t dst, bool is_horizontal,
 				  int vsu_mode, int *vskiplines)
@@ -641,7 +630,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 	struct vop_win *vop_win = to_vop_win(plane);
 	const struct vop_win_data *win = vop_win->data;
 	int ret;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int min_scale = win->phy->scl ? FRAC_16_16(1, 8) :
 					DRM_PLANE_HELPER_NO_SCALING;
 	int max_scale = win->phy->scl ? FRAC_16_16(8, 1) :
@@ -654,10 +643,9 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 	if (WARN_ON(!crtc_state))
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  min_scale, max_scale,
@@ -790,7 +778,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	rb_swap = has_rb_swapped(fb->format->format);
 	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
-	if (is_alpha_support(fb->format->format)) {
+	if (fb->format->has_alpha) {
 		VOP_WIN_SET(vop, win, dst_alpha_ctl,
 			    DST_FACTOR_M0(ALPHA_SRC_INVERSE));
 		val = SRC_ALPHA_EN(1) | SRC_COLOR_M0(ALPHA_SRC_PRE_MUL) |
diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c
index 8fe954c27fba..8bc7e8418b8d 100644
--- a/drivers/gpu/drm/stm/drv.c
+++ b/drivers/gpu/drm/stm/drv.c
@@ -31,6 +31,24 @@ static const struct drm_mode_config_funcs drv_mode_config_funcs = {
 	.atomic_commit = drm_atomic_helper_commit,
 };
 
+static int stm_gem_cma_dumb_create(struct drm_file *file,
+				   struct drm_device *dev,
+				   struct drm_mode_create_dumb *args)
+{
+#ifdef CONFIG_MMU
+	unsigned int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
+
+	/*
+	 * in order to optimize data transfer, pitch is aligned on
+	 * 128 bytes, height is aligned on 4 bytes
+	 */
+	args->pitch = roundup(min_pitch, 128);
+	args->height = roundup(args->height, 4);
+#endif
+
+	return drm_gem_cma_dumb_create_internal(file, dev, args);
+}
+
 DEFINE_DRM_GEM_CMA_FOPS(drv_driver_fops);
 
 static struct drm_driver drv_driver = {
@@ -44,7 +62,7 @@ static struct drm_driver drv_driver = {
 	.minor = 0,
 	.patchlevel = 0,
 	.fops = &drv_driver_fops,
-	.dumb_create = drm_gem_cma_dumb_create,
+	.dumb_create = stm_gem_cma_dumb_create,
 	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_free_object_unlocked = drm_gem_cma_free_object,
diff --git a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
index fd02506274da..a514b593f37c 100644
--- a/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
+++ b/drivers/gpu/drm/stm/dw_mipi_dsi-stm.c
@@ -14,7 +14,14 @@
 #include <drm/bridge/dw_mipi_dsi.h>
 #include <video/mipi_display.h>
 
-/* DSI wrapper register & bit definitions */
+#define HWVER_130			0x31333000	/* IP version 1.30 */
+#define HWVER_131			0x31333100	/* IP version 1.31 */
+
+/* DSI digital registers & bit definitions */
+#define DSI_VERSION			0x00
+#define VERSION				GENMASK(31, 8)
+
+/* DSI wrapper registers & bit definitions */
 /* Note: registers are named as in the Reference Manual */
 #define DSI_WCFGR	0x0400		/* Wrapper ConFiGuration Reg */
 #define WCFGR_DSIM	BIT(0)		/* DSI Mode */
@@ -65,6 +72,10 @@ enum dsi_color {
 struct dw_mipi_dsi_stm {
 	void __iomem *base;
 	struct clk *pllref_clk;
+	struct dw_mipi_dsi *dsi;
+	u32 hw_version;
+	int lane_min_kbps;
+	int lane_max_kbps;
 };
 
 static inline void dsi_write(struct dw_mipi_dsi_stm *dsi, u32 reg, u32 val)
@@ -121,7 +132,8 @@ static int dsi_pll_get_clkout_khz(int clkin_khz, int idf, int ndiv, int odf)
 	return DIV_ROUND_CLOSEST(clkin_khz * ndiv, divisor);
 }
 
-static int dsi_pll_get_params(int clkin_khz, int clkout_khz,
+static int dsi_pll_get_params(struct dw_mipi_dsi_stm *dsi,
+			      int clkin_khz, int clkout_khz,
 			      int *idf, int *ndiv, int *odf)
 {
 	int i, o, n, n_min, n_max;
@@ -131,8 +143,8 @@ static int dsi_pll_get_params(int clkin_khz, int clkout_khz,
 	if (clkin_khz <= 0 || clkout_khz <= 0)
 		return -EINVAL;
 
-	fvco_min = LANE_MIN_KBPS * 2 * ODF_MAX;
-	fvco_max = LANE_MAX_KBPS * 2 * ODF_MIN;
+	fvco_min = dsi->lane_min_kbps * 2 * ODF_MAX;
+	fvco_max = dsi->lane_max_kbps * 2 * ODF_MIN;
 
 	best_delta = 1000000; /* big started value (1000000khz) */
 
@@ -212,6 +224,15 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, struct drm_display_mode *mode,
 	int ret, bpp;
 	u32 val;
 
+	/* Update lane capabilities according to hw version */
+	dsi->hw_version = dsi_read(dsi, DSI_VERSION) & VERSION;
+	dsi->lane_min_kbps = LANE_MIN_KBPS;
+	dsi->lane_max_kbps = LANE_MAX_KBPS;
+	if (dsi->hw_version == HWVER_131) {
+		dsi->lane_min_kbps *= 2;
+		dsi->lane_max_kbps *= 2;
+	}
+
 	pll_in_khz = (unsigned int)(clk_get_rate(dsi->pllref_clk) / 1000);
 
 	/* Compute requested pll out */
@@ -219,12 +240,12 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, struct drm_display_mode *mode,
 	pll_out_khz = mode->clock * bpp / lanes;
 	/* Add 20% to pll out to be higher than pixel bw (burst mode only) */
 	pll_out_khz = (pll_out_khz * 12) / 10;
-	if (pll_out_khz > LANE_MAX_KBPS) {
-		pll_out_khz = LANE_MAX_KBPS;
+	if (pll_out_khz > dsi->lane_max_kbps) {
+		pll_out_khz = dsi->lane_max_kbps;
 		DRM_WARN("Warning max phy mbps is used\n");
 	}
-	if (pll_out_khz < LANE_MIN_KBPS) {
-		pll_out_khz = LANE_MIN_KBPS;
+	if (pll_out_khz < dsi->lane_min_kbps) {
+		pll_out_khz = dsi->lane_min_kbps;
 		DRM_WARN("Warning min phy mbps is used\n");
 	}
 
@@ -232,7 +253,8 @@ dw_mipi_dsi_get_lane_mbps(void *priv_data, struct drm_display_mode *mode,
 	idf = 0;
 	ndiv = 0;
 	odf = 0;
-	ret = dsi_pll_get_params(pll_in_khz, pll_out_khz, &idf, &ndiv, &odf);
+	ret = dsi_pll_get_params(dsi, pll_in_khz, pll_out_khz,
+				 &idf, &ndiv, &odf);
 	if (ret)
 		DRM_WARN("Warning dsi_pll_get_params(): bad params\n");
 
@@ -312,21 +334,24 @@ static int dw_mipi_dsi_stm_probe(struct platform_device *pdev)
 	dw_mipi_dsi_stm_plat_data.base = dsi->base;
 	dw_mipi_dsi_stm_plat_data.priv_data = dsi;
 
-	ret = dw_mipi_dsi_probe(pdev, &dw_mipi_dsi_stm_plat_data);
-	if (ret) {
+	platform_set_drvdata(pdev, dsi);
+
+	dsi->dsi = dw_mipi_dsi_probe(pdev, &dw_mipi_dsi_stm_plat_data);
+	if (IS_ERR(dsi->dsi)) {
 		DRM_ERROR("Failed to initialize mipi dsi host\n");
 		clk_disable_unprepare(dsi->pllref_clk);
+		return PTR_ERR(dsi->dsi);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int dw_mipi_dsi_stm_remove(struct platform_device *pdev)
 {
-	struct dw_mipi_dsi_stm *dsi = dw_mipi_dsi_stm_plat_data.priv_data;
+	struct dw_mipi_dsi_stm *dsi = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(dsi->pllref_clk);
-	dw_mipi_dsi_remove(pdev);
+	dw_mipi_dsi_remove(dsi->dsi);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index 6dc5d4ec4e17..1a3277e483d5 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -175,6 +175,8 @@
 
 #define LXCFBLNR_CFBLN	GENMASK(10, 0)	/* Color Frame Buffer Line Number */
 
+#define CLUT_SIZE	256
+
 #define CONSTA_MAX	0xFF		/* CONSTant Alpha MAX= 1.0 */
 #define BF1_PAXCA	0x600		/* Pixel Alpha x Constant Alpha */
 #define BF1_CA		0x400		/* Constant Alpha */
@@ -326,6 +328,26 @@ static inline u32 to_drm_pixelformat(enum ltdc_pix_fmt pf)
 	}
 }
 
+static inline u32 get_pixelformat_without_alpha(u32 drm)
+{
+	switch (drm) {
+	case DRM_FORMAT_ARGB4444:
+		return DRM_FORMAT_XRGB4444;
+	case DRM_FORMAT_RGBA4444:
+		return DRM_FORMAT_RGBX4444;
+	case DRM_FORMAT_ARGB1555:
+		return DRM_FORMAT_XRGB1555;
+	case DRM_FORMAT_RGBA5551:
+		return DRM_FORMAT_RGBX5551;
+	case DRM_FORMAT_ARGB8888:
+		return DRM_FORMAT_XRGB8888;
+	case DRM_FORMAT_RGBA8888:
+		return DRM_FORMAT_RGBX8888;
+	default:
+		return 0;
+	}
+}
+
 static irqreturn_t ltdc_irq_thread(int irq, void *arg)
 {
 	struct drm_device *ddev = arg;
@@ -363,6 +385,28 @@ static irqreturn_t ltdc_irq(int irq, void *arg)
  * DRM_CRTC
  */
 
+static void ltdc_crtc_update_clut(struct drm_crtc *crtc)
+{
+	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
+	struct drm_color_lut *lut;
+	u32 val;
+	int i;
+
+	if (!crtc || !crtc->state)
+		return;
+
+	if (!crtc->state->color_mgmt_changed || !crtc->state->gamma_lut)
+		return;
+
+	lut = (struct drm_color_lut *)crtc->state->gamma_lut->data;
+
+	for (i = 0; i < CLUT_SIZE; i++, lut++) {
+		val = ((lut->red << 8) & 0xff0000) | (lut->green & 0xff00) |
+			(lut->blue >> 8) | (i << 24);
+		reg_write(ldev->regs, LTDC_L1CLUTWR, val);
+	}
+}
+
 static void ltdc_crtc_atomic_enable(struct drm_crtc *crtc,
 				    struct drm_crtc_state *old_state)
 {
@@ -404,12 +448,35 @@ static void ltdc_crtc_atomic_disable(struct drm_crtc *crtc,
 	reg_set(ldev->regs, LTDC_SRCR, SRCR_IMR);
 }
 
+static bool ltdc_crtc_mode_fixup(struct drm_crtc *crtc,
+				 const struct drm_display_mode *mode,
+				 struct drm_display_mode *adjusted_mode)
+{
+	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
+	int rate = mode->clock * 1000;
+
+	/*
+	 * TODO clk_round_rate() does not work yet. When ready, it can
+	 * be used instead of clk_set_rate() then clk_get_rate().
+	 */
+
+	clk_disable(ldev->pixel_clk);
+	if (clk_set_rate(ldev->pixel_clk, rate) < 0) {
+		DRM_ERROR("Cannot set rate (%dHz) for pixel clk\n", rate);
+		return false;
+	}
+	clk_enable(ldev->pixel_clk);
+
+	adjusted_mode->clock = clk_get_rate(ldev->pixel_clk) / 1000;
+
+	return true;
+}
+
 static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
 	struct ltdc_device *ldev = crtc_to_ltdc(crtc);
 	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 	struct videomode vm;
-	int rate = mode->clock * 1000;
 	u32 hsync, vsync, accum_hbp, accum_vbp, accum_act_w, accum_act_h;
 	u32 total_width, total_height;
 	u32 val;
@@ -432,15 +499,6 @@ static void ltdc_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	total_width = accum_act_w + vm.hfront_porch;
 	total_height = accum_act_h + vm.vfront_porch;
 
-	clk_disable(ldev->pixel_clk);
-
-	if (clk_set_rate(ldev->pixel_clk, rate) < 0) {
-		DRM_ERROR("Cannot set rate (%dHz) for pixel clk\n", rate);
-		return;
-	}
-
-	clk_enable(ldev->pixel_clk);
-
 	/* Configures the HS, VS, DE and PC polarities. Default Active Low */
 	val = 0;
 
@@ -486,6 +544,8 @@ static void ltdc_crtc_atomic_flush(struct drm_crtc *crtc,
 
 	DRM_DEBUG_ATOMIC("\n");
 
+	ltdc_crtc_update_clut(crtc);
+
 	/* Commit shadow registers = update planes at next vblank */
 	reg_set(ldev->regs, LTDC_SRCR, SRCR_VBR);
 
@@ -502,6 +562,7 @@ static void ltdc_crtc_atomic_flush(struct drm_crtc *crtc,
 }
 
 static const struct drm_crtc_helper_funcs ltdc_crtc_helper_funcs = {
+	.mode_fixup = ltdc_crtc_mode_fixup,
 	.mode_set_nofb = ltdc_crtc_mode_set_nofb,
 	.atomic_flush = ltdc_crtc_atomic_flush,
 	.atomic_enable = ltdc_crtc_atomic_enable,
@@ -533,6 +594,7 @@ static const struct drm_crtc_funcs ltdc_crtc_funcs = {
 	.reset = drm_atomic_helper_crtc_reset,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
+	.gamma_set = drm_atomic_helper_legacy_gamma_set,
 };
 
 /*
@@ -638,6 +700,14 @@ static void ltdc_plane_atomic_update(struct drm_plane *plane,
 
 	/* Specifies the blending factors */
 	val = BF1_PAXCA | BF2_1PAXCA;
+	if (!fb->format->has_alpha)
+		val = BF1_CA | BF2_1CA;
+
+	/* Manage hw-specific capabilities */
+	if (ldev->caps.non_alpha_only_l1 &&
+	    plane->type != DRM_PLANE_TYPE_PRIMARY)
+		val = BF1_PAXCA | BF2_1PAXCA;
+
 	reg_update_bits(ldev->regs, LTDC_L1BFCR + lofs,
 			LXBFCR_BF2 | LXBFCR_BF1, val);
 
@@ -705,8 +775,8 @@ static struct drm_plane *ltdc_plane_create(struct drm_device *ddev,
 	struct device *dev = ddev->dev;
 	struct drm_plane *plane;
 	unsigned int i, nb_fmt = 0;
-	u32 formats[NB_PF];
-	u32 drm_fmt;
+	u32 formats[NB_PF * 2];
+	u32 drm_fmt, drm_fmt_no_alpha;
 	int ret;
 
 	/* Get supported pixel formats */
@@ -715,6 +785,18 @@ static struct drm_plane *ltdc_plane_create(struct drm_device *ddev,
 		if (!drm_fmt)
 			continue;
 		formats[nb_fmt++] = drm_fmt;
+
+		/* Add the no-alpha related format if any & supported */
+		drm_fmt_no_alpha = get_pixelformat_without_alpha(drm_fmt);
+		if (!drm_fmt_no_alpha)
+			continue;
+
+		/* Manage hw-specific capabilities */
+		if (ldev->caps.non_alpha_only_l1 &&
+		    type != DRM_PLANE_TYPE_PRIMARY)
+			continue;
+
+		formats[nb_fmt++] = drm_fmt_no_alpha;
 	}
 
 	plane = devm_kzalloc(dev, sizeof(*plane), GFP_KERNEL);
@@ -765,6 +847,9 @@ static int ltdc_crtc_init(struct drm_device *ddev, struct drm_crtc *crtc)
 
 	drm_crtc_helper_add(crtc, &ltdc_crtc_helper_funcs);
 
+	drm_mode_crtc_set_gamma_size(crtc, CLUT_SIZE);
+	drm_crtc_enable_color_mgmt(crtc, 0, false, CLUT_SIZE);
+
 	DRM_DEBUG_DRIVER("CRTC:%d created\n", crtc->base.id);
 
 	/* Add planes. Note : the first layer is used by primary plane */
@@ -839,10 +924,19 @@ static int ltdc_get_caps(struct drm_device *ddev)
 	case HWVER_10300:
 		ldev->caps.reg_ofs = REG_OFS_NONE;
 		ldev->caps.pix_fmt_hw = ltdc_pix_fmt_a0;
+		/*
+		 * Hw older versions support non-alpha color formats derived
+		 * from native alpha color formats only on the primary layer.
+		 * For instance, RG16 native format without alpha works fine
+		 * on 2nd layer but XR24 (derived color format from AR24)
+		 * does not work on 2nd layer.
+		 */
+		ldev->caps.non_alpha_only_l1 = true;
 		break;
 	case HWVER_20101:
 		ldev->caps.reg_ofs = REG_OFS_4;
 		ldev->caps.pix_fmt_hw = ltdc_pix_fmt_a1;
+		ldev->caps.non_alpha_only_l1 = false;
 		break;
 	default:
 		return -ENODEV;
diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h
index edd1c0a446d1..edb268129c54 100644
--- a/drivers/gpu/drm/stm/ltdc.h
+++ b/drivers/gpu/drm/stm/ltdc.h
@@ -17,6 +17,7 @@ struct ltdc_caps {
 	u32 reg_ofs;		/* register offset for applicable regs */
 	u32 bus_width;		/* bus width (32 or 64 bits) */
 	const u32 *pix_fmt_hw;	/* supported pixel formats */
+	bool non_alpha_only_l1; /* non-native no-alpha formats on layer 1 */
 };
 
 struct ltdc_device {
diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 2b37a6abbb1d..582607c0c488 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 sun4i-backend-y			+= sun4i_backend.o sun4i_layer.o
+sun4i-frontend-y		+= sun4i_frontend.o
 
 sun4i-drm-y			+= sun4i_drv.o
 sun4i-drm-y			+= sun4i_framebuffer.o
@@ -24,6 +25,6 @@ obj-$(CONFIG_DRM_SUN4I)		+= sun4i-tcon.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun4i_tv.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun6i_drc.o
 
-obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o
+obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o sun4i-frontend.o
 obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index 847eecbe4d14..245b189fc4d8 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -11,6 +11,7 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
@@ -26,6 +27,7 @@
 
 #include "sun4i_backend.h"
 #include "sun4i_drv.h"
+#include "sun4i_frontend.h"
 #include "sun4i_layer.h"
 #include "sunxi_engine.h"
 
@@ -93,7 +95,7 @@ void sun4i_backend_layer_enable(struct sun4i_backend *backend,
 static int sun4i_backend_drm_format_to_layer(struct drm_plane *plane,
 					     u32 format, u32 *mode)
 {
-	if ((plane->type == DRM_PLANE_TYPE_PRIMARY) &&
+	if (plane && (plane->type == DRM_PLANE_TYPE_PRIMARY) &&
 	    (format == DRM_FORMAT_ARGB8888))
 		format = DRM_FORMAT_XRGB8888;
 
@@ -141,7 +143,6 @@ int sun4i_backend_update_layer_coord(struct sun4i_backend *backend,
 				     int layer, struct drm_plane *plane)
 {
 	struct drm_plane_state *state = plane->state;
-	struct drm_framebuffer *fb = state->fb;
 
 	DRM_DEBUG_DRIVER("Updating layer %d\n", layer);
 
@@ -153,12 +154,6 @@ int sun4i_backend_update_layer_coord(struct sun4i_backend *backend,
 						   state->crtc_h));
 	}
 
-	/* Set the line width */
-	DRM_DEBUG_DRIVER("Layer line width: %d bits\n", fb->pitches[0] * 8);
-	regmap_write(backend->engine.regs,
-		     SUN4I_BACKEND_LAYLINEWIDTH_REG(layer),
-		     fb->pitches[0] * 8);
-
 	/* Set height and width */
 	DRM_DEBUG_DRIVER("Layer size W: %u H: %u\n",
 			 state->crtc_w, state->crtc_h);
@@ -210,6 +205,30 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend,
 	return 0;
 }
 
+int sun4i_backend_update_layer_frontend(struct sun4i_backend *backend,
+					int layer, uint32_t fmt)
+{
+	u32 val;
+	int ret;
+
+	ret = sun4i_backend_drm_format_to_layer(NULL, fmt, &val);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Invalid format\n");
+		return ret;
+	}
+
+	regmap_update_bits(backend->engine.regs,
+			   SUN4I_BACKEND_ATTCTL_REG0(layer),
+			   SUN4I_BACKEND_ATTCTL_REG0_LAY_VDOEN,
+			   SUN4I_BACKEND_ATTCTL_REG0_LAY_VDOEN);
+
+	regmap_update_bits(backend->engine.regs,
+			   SUN4I_BACKEND_ATTCTL_REG1(layer),
+			   SUN4I_BACKEND_ATTCTL_REG1_LAY_FBFMT, val);
+
+	return 0;
+}
+
 int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 				      int layer, struct drm_plane *plane)
 {
@@ -218,6 +237,12 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	u32 lo_paddr, hi_paddr;
 	dma_addr_t paddr;
 
+	/* Set the line width */
+	DRM_DEBUG_DRIVER("Layer line width: %d bits\n", fb->pitches[0] * 8);
+	regmap_write(backend->engine.regs,
+		     SUN4I_BACKEND_LAYLINEWIDTH_REG(layer),
+		     fb->pitches[0] * 8);
+
 	/* Get the start of the displayed memory */
 	paddr = drm_fb_cma_get_gem_addr(fb, state, 0);
 	DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr);
@@ -246,6 +271,176 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	return 0;
 }
 
+int sun4i_backend_update_layer_zpos(struct sun4i_backend *backend, int layer,
+				    struct drm_plane *plane)
+{
+	struct drm_plane_state *state = plane->state;
+	unsigned int priority = state->normalized_zpos;
+
+	DRM_DEBUG_DRIVER("Setting layer %d's priority to %d\n", layer, priority);
+
+	regmap_update_bits(backend->engine.regs, SUN4I_BACKEND_ATTCTL_REG0(layer),
+			   SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL_MASK,
+			   SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL(priority));
+
+	return 0;
+}
+
+static bool sun4i_backend_plane_uses_scaler(struct drm_plane_state *state)
+{
+	u16 src_h = state->src_h >> 16;
+	u16 src_w = state->src_w >> 16;
+
+	DRM_DEBUG_DRIVER("Input size %dx%d, output size %dx%d\n",
+			 src_w, src_h, state->crtc_w, state->crtc_h);
+
+	if ((state->crtc_h != src_h) || (state->crtc_w != src_w))
+		return true;
+
+	return false;
+}
+
+static bool sun4i_backend_plane_uses_frontend(struct drm_plane_state *state)
+{
+	struct sun4i_layer *layer = plane_to_sun4i_layer(state->plane);
+	struct sun4i_backend *backend = layer->backend;
+
+	if (IS_ERR(backend->frontend))
+		return false;
+
+	return sun4i_backend_plane_uses_scaler(state);
+}
+
+static void sun4i_backend_atomic_begin(struct sunxi_engine *engine,
+				       struct drm_crtc_state *old_state)
+{
+	u32 val;
+
+	WARN_ON(regmap_read_poll_timeout(engine->regs,
+					 SUN4I_BACKEND_REGBUFFCTL_REG,
+					 val, !(val & SUN4I_BACKEND_REGBUFFCTL_LOADCTL),
+					 100, 50000));
+}
+
+static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
+				      struct drm_crtc_state *crtc_state)
+{
+	struct drm_atomic_state *state = crtc_state->state;
+	struct drm_device *drm = state->dev;
+	struct drm_plane *plane;
+	unsigned int num_planes = 0;
+	unsigned int num_alpha_planes = 0;
+	unsigned int num_frontend_planes = 0;
+
+	DRM_DEBUG_DRIVER("Starting checking our planes\n");
+
+	if (!crtc_state->planes_changed)
+		return 0;
+
+	drm_for_each_plane_mask(plane, drm, crtc_state->plane_mask) {
+		struct drm_plane_state *plane_state =
+			drm_atomic_get_plane_state(state, plane);
+		struct sun4i_layer_state *layer_state =
+			state_to_sun4i_layer_state(plane_state);
+		struct drm_framebuffer *fb = plane_state->fb;
+		struct drm_format_name_buf format_name;
+
+		if (sun4i_backend_plane_uses_frontend(plane_state)) {
+			DRM_DEBUG_DRIVER("Using the frontend for plane %d\n",
+					 plane->index);
+
+			layer_state->uses_frontend = true;
+			num_frontend_planes++;
+		} else {
+			layer_state->uses_frontend = false;
+		}
+
+		DRM_DEBUG_DRIVER("Plane FB format is %s\n",
+				 drm_get_format_name(fb->format->format,
+						     &format_name));
+		if (fb->format->has_alpha)
+			num_alpha_planes++;
+
+		num_planes++;
+	}
+
+	/*
+	 * The hardware is a bit unusual here.
+	 *
+	 * Even though it supports 4 layers, it does the composition
+	 * in two separate steps.
+	 *
+	 * The first one is assigning a layer to one of its two
+	 * pipes. If more that 1 layer is assigned to the same pipe,
+	 * and if pixels overlaps, the pipe will take the pixel from
+	 * the layer with the highest priority.
+	 *
+	 * The second step is the actual alpha blending, that takes
+	 * the two pipes as input, and uses the eventual alpha
+	 * component to do the transparency between the two.
+	 *
+	 * This two steps scenario makes us unable to guarantee a
+	 * robust alpha blending between the 4 layers in all
+	 * situations, since this means that we need to have one layer
+	 * with alpha at the lowest position of our two pipes.
+	 *
+	 * However, we cannot even do that, since the hardware has a
+	 * bug where the lowest plane of the lowest pipe (pipe 0,
+	 * priority 0), if it has any alpha, will discard the pixel
+	 * entirely and just display the pixels in the background
+	 * color (black by default).
+	 *
+	 * This means that we effectively have only three valid
+	 * configurations with alpha, all of them with the alpha being
+	 * on pipe1 with the lowest position, which can be 1, 2 or 3
+	 * depending on the number of planes and their zpos.
+	 */
+	if (num_alpha_planes > SUN4I_BACKEND_NUM_ALPHA_LAYERS) {
+		DRM_DEBUG_DRIVER("Too many planes with alpha, rejecting...\n");
+		return -EINVAL;
+	}
+
+	if (num_frontend_planes > SUN4I_BACKEND_NUM_FRONTEND_LAYERS) {
+		DRM_DEBUG_DRIVER("Too many planes going through the frontend, rejecting\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG_DRIVER("State valid with %u planes, %u alpha, %u video\n",
+			 num_planes, num_alpha_planes, num_frontend_planes);
+
+	return 0;
+}
+
+static void sun4i_backend_vblank_quirk(struct sunxi_engine *engine)
+{
+	struct sun4i_backend *backend = engine_to_sun4i_backend(engine);
+	struct sun4i_frontend *frontend = backend->frontend;
+
+	if (!frontend)
+		return;
+
+	/*
+	 * In a teardown scenario with the frontend involved, we have
+	 * to keep the frontend enabled until the next vblank, and
+	 * only then disable it.
+	 *
+	 * This is due to the fact that the backend will not take into
+	 * account the new configuration (with the plane that used to
+	 * be fed by the frontend now disabled) until we write to the
+	 * commit bit and the hardware fetches the new configuration
+	 * during the next vblank.
+	 *
+	 * So we keep the frontend around in order to prevent any
+	 * visual artifacts.
+	 */
+	spin_lock(&backend->frontend_lock);
+	if (backend->frontend_teardown) {
+		sun4i_frontend_exit(frontend);
+		backend->frontend_teardown = false;
+	}
+	spin_unlock(&backend->frontend_lock);
+};
+
 static int sun4i_backend_init_sat(struct device *dev) {
 	struct sun4i_backend *backend = dev_get_drvdata(dev);
 	int ret;
@@ -330,11 +525,43 @@ static int sun4i_backend_of_get_id(struct device_node *node)
 	return ret;
 }
 
+/* TODO: This needs to take multiple pipelines into account */
+static struct sun4i_frontend *sun4i_backend_find_frontend(struct sun4i_drv *drv,
+							  struct device_node *node)
+{
+	struct device_node *port, *ep, *remote;
+	struct sun4i_frontend *frontend;
+
+	port = of_graph_get_port_by_id(node, 0);
+	if (!port)
+		return ERR_PTR(-EINVAL);
+
+	for_each_available_child_of_node(port, ep) {
+		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote)
+			continue;
+
+		/* does this node match any registered engines? */
+		list_for_each_entry(frontend, &drv->frontend_list, list) {
+			if (remote == frontend->node) {
+				of_node_put(remote);
+				of_node_put(port);
+				return frontend;
+			}
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
 static const struct sunxi_engine_ops sun4i_backend_engine_ops = {
+	.atomic_begin			= sun4i_backend_atomic_begin,
+	.atomic_check			= sun4i_backend_atomic_check,
 	.commit				= sun4i_backend_commit,
 	.layers_init			= sun4i_layers_init,
 	.apply_color_correction		= sun4i_backend_apply_color_correction,
 	.disable_color_correction	= sun4i_backend_disable_color_correction,
+	.vblank_quirk			= sun4i_backend_vblank_quirk,
 };
 
 static struct regmap_config sun4i_backend_regmap_config = {
@@ -360,6 +587,7 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 	if (!backend)
 		return -ENOMEM;
 	dev_set_drvdata(dev, backend);
+	spin_lock_init(&backend->frontend_lock);
 
 	backend->engine.node = dev->of_node;
 	backend->engine.ops = &sun4i_backend_engine_ops;
@@ -367,6 +595,10 @@ static int sun4i_backend_bind(struct device *dev, struct device *master,
 	if (backend->engine.id < 0)
 		return backend->engine.id;
 
+	backend->frontend = sun4i_backend_find_frontend(drv, dev->of_node);
+	if (IS_ERR(backend->frontend))
+		dev_warn(dev, "Couldn't find matching frontend, frontend features disabled\n");
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(regs))
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.h b/drivers/gpu/drm/sun4i/sun4i_backend.h
index ac3cc029f5cd..52e77591186a 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.h
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.h
@@ -72,6 +72,7 @@
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PIPESEL(x)		((x) << 15)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL_MASK	GENMASK(11, 10)
 #define SUN4I_BACKEND_ATTCTL_REG0_LAY_PRISEL(x)			((x) << 10)
+#define SUN4I_BACKEND_ATTCTL_REG0_LAY_VDOEN		BIT(1)
 
 #define SUN4I_BACKEND_ATTCTL_REG1(l)		(0x8a0 + (0x4 * (l)))
 #define SUN4I_BACKEND_ATTCTL_REG1_LAY_HSCAFCT		GENMASK(15, 14)
@@ -111,7 +112,9 @@
 #define SUN4I_BACKEND_SPRALPHACTL_REG		0x90c
 #define SUN4I_BACKEND_IYUVCTL_REG		0x920
 #define SUN4I_BACKEND_IYUVADD_REG(c)		(0x930 + (0x4 * (c)))
-#define SUN4I_BACKEND_IYUVLINEWITDTH_REG(c)	(0x940 + (0x4 * (c)))
+
+#define SUN4I_BACKEND_IYUVLINEWIDTH_REG(c)	(0x940 + (0x4 * (c)))
+
 #define SUN4I_BACKEND_YGCOEF_REG(c)		(0x950 + (0x4 * (c)))
 #define SUN4I_BACKEND_YGCONS_REG		0x95c
 #define SUN4I_BACKEND_URCOEF_REG(c)		(0x960 + (0x4 * (c)))
@@ -143,8 +146,13 @@
 #define SUN4I_BACKEND_HWCCOLORTAB_OFF		0x4c00
 #define SUN4I_BACKEND_PIPE_OFF(p)		(0x5000 + (0x400 * (p)))
 
+#define SUN4I_BACKEND_NUM_LAYERS		4
+#define SUN4I_BACKEND_NUM_ALPHA_LAYERS		1
+#define SUN4I_BACKEND_NUM_FRONTEND_LAYERS	1
+
 struct sun4i_backend {
 	struct sunxi_engine	engine;
+	struct sun4i_frontend	*frontend;
 
 	struct reset_control	*reset;
 
@@ -154,6 +162,10 @@ struct sun4i_backend {
 
 	struct clk		*sat_clk;
 	struct reset_control	*sat_reset;
+
+	/* Protects against races in the frontend teardown */
+	spinlock_t		frontend_lock;
+	bool			frontend_teardown;
 };
 
 static inline struct sun4i_backend *
@@ -170,5 +182,9 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend,
 				       int layer, struct drm_plane *plane);
 int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 				      int layer, struct drm_plane *plane);
+int sun4i_backend_update_layer_frontend(struct sun4i_backend *backend,
+					int layer, uint32_t in_fmt);
+int sun4i_backend_update_layer_zpos(struct sun4i_backend *backend,
+				    int layer, struct drm_plane *plane);
 
 #endif /* _SUN4I_BACKEND_H_ */
diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c
index 5decae0069d0..3b2d11b675e8 100644
--- a/drivers/gpu/drm/sun4i/sun4i_crtc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c
@@ -25,6 +25,7 @@
 
 #include <video/videomode.h>
 
+#include "sun4i_backend.h"
 #include "sun4i_crtc.h"
 #include "sun4i_drv.h"
 #include "sunxi_engine.h"
@@ -46,11 +47,25 @@ static struct drm_encoder *sun4i_crtc_get_encoder(struct drm_crtc *crtc)
 	return NULL;
 }
 
+static int sun4i_crtc_atomic_check(struct drm_crtc *crtc,
+				    struct drm_crtc_state *state)
+{
+	struct sun4i_crtc *scrtc = drm_crtc_to_sun4i_crtc(crtc);
+	struct sunxi_engine *engine = scrtc->engine;
+	int ret = 0;
+
+	if (engine && engine->ops && engine->ops->atomic_check)
+		ret = engine->ops->atomic_check(engine, state);
+
+	return ret;
+}
+
 static void sun4i_crtc_atomic_begin(struct drm_crtc *crtc,
 				    struct drm_crtc_state *old_state)
 {
 	struct sun4i_crtc *scrtc = drm_crtc_to_sun4i_crtc(crtc);
 	struct drm_device *dev = crtc->dev;
+	struct sunxi_engine *engine = scrtc->engine;
 	unsigned long flags;
 
 	if (crtc->state->event) {
@@ -60,7 +75,10 @@ static void sun4i_crtc_atomic_begin(struct drm_crtc *crtc,
 		scrtc->event = crtc->state->event;
 		spin_unlock_irqrestore(&dev->event_lock, flags);
 		crtc->state->event = NULL;
-	 }
+	}
+
+	if (engine->ops->atomic_begin)
+		engine->ops->atomic_begin(engine, old_state);
 }
 
 static void sun4i_crtc_atomic_flush(struct drm_crtc *crtc,
@@ -125,6 +143,7 @@ static void sun4i_crtc_mode_set_nofb(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_helper_funcs sun4i_crtc_helper_funcs = {
+	.atomic_check	= sun4i_crtc_atomic_check,
 	.atomic_begin	= sun4i_crtc_atomic_begin,
 	.atomic_flush	= sun4i_crtc_atomic_flush,
 	.atomic_enable	= sun4i_crtc_atomic_enable,
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 4570da0227b4..3957c2ff6870 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -23,6 +23,7 @@
 #include <drm/drm_of.h>
 
 #include "sun4i_drv.h"
+#include "sun4i_frontend.h"
 #include "sun4i_framebuffer.h"
 #include "sun4i_tcon.h"
 
@@ -91,6 +92,7 @@ static int sun4i_drv_bind(struct device *dev)
 		goto free_drm;
 	}
 	drm->dev_private = drv;
+	INIT_LIST_HEAD(&drv->frontend_list);
 	INIT_LIST_HEAD(&drv->engine_list);
 	INIT_LIST_HEAD(&drv->tcon_list);
 
@@ -177,6 +179,14 @@ static bool sun4i_drv_node_is_frontend(struct device_node *node)
 		of_device_is_compatible(node, "allwinner,sun8i-a33-display-frontend");
 }
 
+static bool sun4i_drv_node_is_supported_frontend(struct device_node *node)
+{
+	if (IS_ENABLED(CONFIG_DRM_SUN4I_BACKEND))
+		return !!of_match_node(sun4i_frontend_of_table, node);
+
+	return false;
+}
+
 static bool sun4i_drv_node_is_tcon(struct device_node *node)
 {
 	return !!of_match_node(sun4i_tcon_of_table, node);
@@ -225,9 +235,11 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 	int count = 0;
 
 	/*
-	 * We don't support the frontend for now, so we will never
-	 * have a device bound. Just skip over it, but we still want
-	 * the rest our pipeline to be added.
+	 * The frontend has been disabled in some of our old device
+	 * trees. If we find a node that is the frontend and is
+	 * disabled, we should just follow through and parse its
+	 * child, but without adding it to the component list.
+	 * Otherwise, we obviously want to add it to the list.
 	 */
 	if (!sun4i_drv_node_is_frontend(node) &&
 	    !of_device_is_available(node))
@@ -240,7 +252,14 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 	if (sun4i_drv_node_is_connector(node))
 		return 0;
 
-	if (!sun4i_drv_node_is_frontend(node)) {
+	/*
+	 * If the device is either just a regular device, or an
+	 * enabled frontend supported by the driver, we add it to our
+	 * component list.
+	 */
+	if (!sun4i_drv_node_is_frontend(node) ||
+	    (sun4i_drv_node_is_supported_frontend(node) &&
+	     of_device_is_available(node))) {
 		/* Add current component */
 		DRM_DEBUG_DRIVER("Adding component %pOF\n", node);
 		drm_of_component_match_add(dev, match, compare_of, node);
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.h b/drivers/gpu/drm/sun4i/sun4i_drv.h
index 2825f140da54..5750b8ce8b31 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.h
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.h
@@ -19,6 +19,7 @@
 
 struct sun4i_drv {
 	struct list_head	engine_list;
+	struct list_head	frontend_list;
 	struct list_head	tcon_list;
 };
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_framebuffer.c b/drivers/gpu/drm/sun4i/sun4i_framebuffer.c
index 38a36c0dfa2f..5f29850ef8ac 100644
--- a/drivers/gpu/drm/sun4i/sun4i_framebuffer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_framebuffer.c
@@ -10,6 +10,7 @@
  * the License, or (at your option) any later version.
  */
 
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_fb_cma_helper.h>
@@ -19,13 +20,33 @@
 #include "sun4i_drv.h"
 #include "sun4i_framebuffer.h"
 
+static int sun4i_de_atomic_check(struct drm_device *dev,
+				 struct drm_atomic_state *state)
+{
+	int ret;
+
+	ret = drm_atomic_helper_check_modeset(dev, state);
+	if (ret)
+		return ret;
+
+	ret = drm_atomic_normalize_zpos(dev, state);
+	if (ret)
+		return ret;
+
+	return drm_atomic_helper_check_planes(dev, state);
+}
+
 static const struct drm_mode_config_funcs sun4i_de_mode_config_funcs = {
 	.output_poll_changed	= drm_fb_helper_output_poll_changed,
-	.atomic_check		= drm_atomic_helper_check,
+	.atomic_check		= sun4i_de_atomic_check,
 	.atomic_commit		= drm_atomic_helper_commit,
 	.fb_create		= drm_gem_fb_create,
 };
 
+static struct drm_mode_config_helper_funcs sun4i_de_mode_config_helpers = {
+	.atomic_commit_tail	= drm_atomic_helper_commit_tail_rpm,
+};
+
 int sun4i_framebuffer_init(struct drm_device *drm)
 {
 	drm_mode_config_reset(drm);
@@ -34,6 +55,7 @@ int sun4i_framebuffer_init(struct drm_device *drm)
 	drm->mode_config.max_height = 8192;
 
 	drm->mode_config.funcs = &sun4i_de_mode_config_funcs;
+	drm->mode_config.helper_private = &sun4i_de_mode_config_helpers;
 
 	return drm_fb_cma_fbdev_init(drm, 32, 0);
 }
diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c
new file mode 100644
index 000000000000..ddf6cfa6dd23
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c
@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+#include <drm/drmP.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+
+#include "sun4i_drv.h"
+#include "sun4i_frontend.h"
+
+static const u32 sun4i_frontend_vert_coef[32] = {
+	0x00004000, 0x000140ff, 0x00033ffe, 0x00043ffd,
+	0x00063efc, 0xff083dfc, 0x000a3bfb, 0xff0d39fb,
+	0xff0f37fb, 0xff1136fa, 0xfe1433fb, 0xfe1631fb,
+	0xfd192ffb, 0xfd1c2cfb, 0xfd1f29fb, 0xfc2127fc,
+	0xfc2424fc, 0xfc2721fc, 0xfb291ffd, 0xfb2c1cfd,
+	0xfb2f19fd, 0xfb3116fe, 0xfb3314fe, 0xfa3611ff,
+	0xfb370fff, 0xfb390dff, 0xfb3b0a00, 0xfc3d08ff,
+	0xfc3e0600, 0xfd3f0400, 0xfe3f0300, 0xff400100,
+};
+
+static const u32 sun4i_frontend_horz_coef[64] = {
+	0x40000000, 0x00000000, 0x40fe0000, 0x0000ff03,
+	0x3ffd0000, 0x0000ff05, 0x3ffc0000, 0x0000ff06,
+	0x3efb0000, 0x0000ff08, 0x3dfb0000, 0x0000ff09,
+	0x3bfa0000, 0x0000fe0d, 0x39fa0000, 0x0000fe0f,
+	0x38fa0000, 0x0000fe10, 0x36fa0000, 0x0000fe12,
+	0x33fa0000, 0x0000fd16, 0x31fa0000, 0x0000fd18,
+	0x2ffa0000, 0x0000fd1a, 0x2cfa0000, 0x0000fc1e,
+	0x29fa0000, 0x0000fc21, 0x27fb0000, 0x0000fb23,
+	0x24fb0000, 0x0000fb26, 0x21fb0000, 0x0000fb29,
+	0x1ffc0000, 0x0000fa2b, 0x1cfc0000, 0x0000fa2e,
+	0x19fd0000, 0x0000fa30, 0x16fd0000, 0x0000fa33,
+	0x14fd0000, 0x0000fa35, 0x11fe0000, 0x0000fa37,
+	0x0ffe0000, 0x0000fa39, 0x0dfe0000, 0x0000fa3b,
+	0x0afe0000, 0x0000fa3e, 0x08ff0000, 0x0000fb3e,
+	0x06ff0000, 0x0000fb40, 0x05ff0000, 0x0000fc40,
+	0x03ff0000, 0x0000fd41, 0x01ff0000, 0x0000fe42,
+};
+
+static void sun4i_frontend_scaler_init(struct sun4i_frontend *frontend)
+{
+	int i;
+
+	for (i = 0; i < 32; i++) {
+		regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZCOEF0_REG(i),
+			     sun4i_frontend_horz_coef[2 * i]);
+		regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZCOEF0_REG(i),
+			     sun4i_frontend_horz_coef[2 * i]);
+		regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZCOEF1_REG(i),
+			     sun4i_frontend_horz_coef[2 * i + 1]);
+		regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZCOEF1_REG(i),
+			     sun4i_frontend_horz_coef[2 * i + 1]);
+		regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTCOEF_REG(i),
+			     sun4i_frontend_vert_coef[i]);
+		regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTCOEF_REG(i),
+			     sun4i_frontend_vert_coef[i]);
+	}
+
+	regmap_update_bits(frontend->regs, SUN4I_FRONTEND_FRM_CTRL_REG,
+			   SUN4I_FRONTEND_FRM_CTRL_COEF_ACCESS_CTRL,
+			   SUN4I_FRONTEND_FRM_CTRL_COEF_ACCESS_CTRL);
+}
+
+int sun4i_frontend_init(struct sun4i_frontend *frontend)
+{
+	return pm_runtime_get_sync(frontend->dev);
+}
+EXPORT_SYMBOL(sun4i_frontend_init);
+
+void sun4i_frontend_exit(struct sun4i_frontend *frontend)
+{
+	pm_runtime_put(frontend->dev);
+}
+EXPORT_SYMBOL(sun4i_frontend_exit);
+
+void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend,
+				  struct drm_plane *plane)
+{
+	struct drm_plane_state *state = plane->state;
+	struct drm_framebuffer *fb = state->fb;
+	dma_addr_t paddr;
+
+	/* Set the line width */
+	DRM_DEBUG_DRIVER("Frontend stride: %d bytes\n", fb->pitches[0]);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_LINESTRD0_REG,
+		     fb->pitches[0]);
+
+	/* Set the physical address of the buffer in memory */
+	paddr = drm_fb_cma_get_gem_addr(fb, state, 0);
+	paddr -= PHYS_OFFSET;
+	DRM_DEBUG_DRIVER("Setting buffer address to %pad\n", &paddr);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_BUF_ADDR0_REG, paddr);
+}
+EXPORT_SYMBOL(sun4i_frontend_update_buffer);
+
+static int sun4i_frontend_drm_format_to_input_fmt(uint32_t fmt, u32 *val)
+{
+	switch (fmt) {
+	case DRM_FORMAT_ARGB8888:
+		*val = 5;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int sun4i_frontend_drm_format_to_output_fmt(uint32_t fmt, u32 *val)
+{
+	switch (fmt) {
+	case DRM_FORMAT_XRGB8888:
+	case DRM_FORMAT_ARGB8888:
+		*val = 2;
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+int sun4i_frontend_update_formats(struct sun4i_frontend *frontend,
+				  struct drm_plane *plane, uint32_t out_fmt)
+{
+	struct drm_plane_state *state = plane->state;
+	struct drm_framebuffer *fb = state->fb;
+	u32 out_fmt_val;
+	u32 in_fmt_val;
+	int ret;
+
+	ret = sun4i_frontend_drm_format_to_input_fmt(fb->format->format,
+						     &in_fmt_val);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Invalid input format\n");
+		return ret;
+	}
+
+	ret = sun4i_frontend_drm_format_to_output_fmt(out_fmt, &out_fmt_val);
+	if (ret) {
+		DRM_DEBUG_DRIVER("Invalid output format\n");
+		return ret;
+	}
+
+	/*
+	 * I have no idea what this does exactly, but it seems to be
+	 * related to the scaler FIR filter phase parameters.
+	 */
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZPHASE_REG, 0x400);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZPHASE_REG, 0x400);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE0_REG, 0x400);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE0_REG, 0x400);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE1_REG, 0x400);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE1_REG, 0x400);
+
+	regmap_write(frontend->regs, SUN4I_FRONTEND_INPUT_FMT_REG,
+		     SUN4I_FRONTEND_INPUT_FMT_DATA_MOD(1) |
+		     SUN4I_FRONTEND_INPUT_FMT_DATA_FMT(in_fmt_val) |
+		     SUN4I_FRONTEND_INPUT_FMT_PS(1));
+
+	/*
+	 * TODO: It look like the A31 and A80 at least will need the
+	 * bit 7 (ALPHA_EN) enabled when using a format with alpha (so
+	 * ARGB8888).
+	 */
+	regmap_write(frontend->regs, SUN4I_FRONTEND_OUTPUT_FMT_REG,
+		     SUN4I_FRONTEND_OUTPUT_FMT_DATA_FMT(out_fmt_val));
+
+	return 0;
+}
+EXPORT_SYMBOL(sun4i_frontend_update_formats);
+
+void sun4i_frontend_update_coord(struct sun4i_frontend *frontend,
+				 struct drm_plane *plane)
+{
+	struct drm_plane_state *state = plane->state;
+
+	/* Set height and width */
+	DRM_DEBUG_DRIVER("Frontend size W: %u H: %u\n",
+			 state->crtc_w, state->crtc_h);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_INSIZE_REG,
+		     SUN4I_FRONTEND_INSIZE(state->src_h >> 16,
+					   state->src_w >> 16));
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_INSIZE_REG,
+		     SUN4I_FRONTEND_INSIZE(state->src_h >> 16,
+					   state->src_w >> 16));
+
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_OUTSIZE_REG,
+		     SUN4I_FRONTEND_OUTSIZE(state->crtc_h, state->crtc_w));
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_OUTSIZE_REG,
+		     SUN4I_FRONTEND_OUTSIZE(state->crtc_h, state->crtc_w));
+
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZFACT_REG,
+		     state->src_w / state->crtc_w);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZFACT_REG,
+		     state->src_w / state->crtc_w);
+
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTFACT_REG,
+		     state->src_h / state->crtc_h);
+	regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTFACT_REG,
+		     state->src_h / state->crtc_h);
+
+	regmap_write_bits(frontend->regs, SUN4I_FRONTEND_FRM_CTRL_REG,
+			  SUN4I_FRONTEND_FRM_CTRL_REG_RDY,
+			  SUN4I_FRONTEND_FRM_CTRL_REG_RDY);
+}
+EXPORT_SYMBOL(sun4i_frontend_update_coord);
+
+int sun4i_frontend_enable(struct sun4i_frontend *frontend)
+{
+	regmap_write_bits(frontend->regs, SUN4I_FRONTEND_FRM_CTRL_REG,
+			  SUN4I_FRONTEND_FRM_CTRL_FRM_START,
+			  SUN4I_FRONTEND_FRM_CTRL_FRM_START);
+
+	return 0;
+}
+EXPORT_SYMBOL(sun4i_frontend_enable);
+
+static struct regmap_config sun4i_frontend_regmap_config = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= 0x0a14,
+};
+
+static int sun4i_frontend_bind(struct device *dev, struct device *master,
+			 void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct sun4i_frontend *frontend;
+	struct drm_device *drm = data;
+	struct sun4i_drv *drv = drm->dev_private;
+	struct resource *res;
+	void __iomem *regs;
+
+	frontend = devm_kzalloc(dev, sizeof(*frontend), GFP_KERNEL);
+	if (!frontend)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, frontend);
+	frontend->dev = dev;
+	frontend->node = dev->of_node;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	frontend->regs = devm_regmap_init_mmio(dev, regs,
+					       &sun4i_frontend_regmap_config);
+	if (IS_ERR(frontend->regs)) {
+		dev_err(dev, "Couldn't create the frontend regmap\n");
+		return PTR_ERR(frontend->regs);
+	}
+
+	frontend->reset = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(frontend->reset)) {
+		dev_err(dev, "Couldn't get our reset line\n");
+		return PTR_ERR(frontend->reset);
+	}
+
+	frontend->bus_clk = devm_clk_get(dev, "ahb");
+	if (IS_ERR(frontend->bus_clk)) {
+		dev_err(dev, "Couldn't get our bus clock\n");
+		return PTR_ERR(frontend->bus_clk);
+	}
+
+	frontend->mod_clk = devm_clk_get(dev, "mod");
+	if (IS_ERR(frontend->mod_clk)) {
+		dev_err(dev, "Couldn't get our mod clock\n");
+		return PTR_ERR(frontend->mod_clk);
+	}
+
+	frontend->ram_clk = devm_clk_get(dev, "ram");
+	if (IS_ERR(frontend->ram_clk)) {
+		dev_err(dev, "Couldn't get our ram clock\n");
+		return PTR_ERR(frontend->ram_clk);
+	}
+
+	list_add_tail(&frontend->list, &drv->frontend_list);
+	pm_runtime_enable(dev);
+
+	return 0;
+}
+
+static void sun4i_frontend_unbind(struct device *dev, struct device *master,
+			    void *data)
+{
+	struct sun4i_frontend *frontend = dev_get_drvdata(dev);
+
+	list_del(&frontend->list);
+	pm_runtime_force_suspend(dev);
+}
+
+static const struct component_ops sun4i_frontend_ops = {
+	.bind	= sun4i_frontend_bind,
+	.unbind	= sun4i_frontend_unbind,
+};
+
+static int sun4i_frontend_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &sun4i_frontend_ops);
+}
+
+static int sun4i_frontend_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &sun4i_frontend_ops);
+
+	return 0;
+}
+
+static int sun4i_frontend_runtime_resume(struct device *dev)
+{
+	struct sun4i_frontend *frontend = dev_get_drvdata(dev);
+	int ret;
+
+	clk_set_rate(frontend->mod_clk, 300000000);
+
+	clk_prepare_enable(frontend->bus_clk);
+	clk_prepare_enable(frontend->mod_clk);
+	clk_prepare_enable(frontend->ram_clk);
+
+	ret = reset_control_reset(frontend->reset);
+	if (ret) {
+		dev_err(dev, "Couldn't reset our device\n");
+		return ret;
+	}
+
+	regmap_update_bits(frontend->regs, SUN4I_FRONTEND_EN_REG,
+			   SUN4I_FRONTEND_EN_EN,
+			   SUN4I_FRONTEND_EN_EN);
+
+	regmap_update_bits(frontend->regs, SUN4I_FRONTEND_BYPASS_REG,
+			   SUN4I_FRONTEND_BYPASS_CSC_EN,
+			   SUN4I_FRONTEND_BYPASS_CSC_EN);
+
+	sun4i_frontend_scaler_init(frontend);
+
+	return 0;
+}
+
+static int sun4i_frontend_runtime_suspend(struct device *dev)
+{
+	struct sun4i_frontend *frontend = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(frontend->ram_clk);
+	clk_disable_unprepare(frontend->mod_clk);
+	clk_disable_unprepare(frontend->bus_clk);
+
+	reset_control_assert(frontend->reset);
+
+	return 0;
+}
+
+static const struct dev_pm_ops sun4i_frontend_pm_ops = {
+	.runtime_resume		= sun4i_frontend_runtime_resume,
+	.runtime_suspend	= sun4i_frontend_runtime_suspend,
+};
+
+const struct of_device_id sun4i_frontend_of_table[] = {
+	{ .compatible = "allwinner,sun8i-a33-display-frontend" },
+	{ }
+};
+EXPORT_SYMBOL(sun4i_frontend_of_table);
+MODULE_DEVICE_TABLE(of, sun4i_frontend_of_table);
+
+static struct platform_driver sun4i_frontend_driver = {
+	.probe		= sun4i_frontend_probe,
+	.remove		= sun4i_frontend_remove,
+	.driver		= {
+		.name		= "sun4i-frontend",
+		.of_match_table	= sun4i_frontend_of_table,
+		.pm		= &sun4i_frontend_pm_ops,
+	},
+};
+module_platform_driver(sun4i_frontend_driver);
+
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
+MODULE_DESCRIPTION("Allwinner A10 Display Engine Frontend Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.h b/drivers/gpu/drm/sun4i/sun4i_frontend.h
new file mode 100644
index 000000000000..02661ce81f3e
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun4i_frontend.h
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2017 Free Electrons
+ * Maxime Ripard <maxime.ripard@free-electrons.com>
+ */
+
+#ifndef _SUN4I_FRONTEND_H_
+#define _SUN4I_FRONTEND_H_
+
+#include <linux/list.h>
+
+#define SUN4I_FRONTEND_EN_REG			0x000
+#define SUN4I_FRONTEND_EN_EN				BIT(0)
+
+#define SUN4I_FRONTEND_FRM_CTRL_REG		0x004
+#define SUN4I_FRONTEND_FRM_CTRL_COEF_ACCESS_CTRL	BIT(23)
+#define SUN4I_FRONTEND_FRM_CTRL_FRM_START		BIT(16)
+#define SUN4I_FRONTEND_FRM_CTRL_COEF_RDY		BIT(1)
+#define SUN4I_FRONTEND_FRM_CTRL_REG_RDY			BIT(0)
+
+#define SUN4I_FRONTEND_BYPASS_REG		0x008
+#define SUN4I_FRONTEND_BYPASS_CSC_EN			BIT(1)
+
+#define SUN4I_FRONTEND_BUF_ADDR0_REG		0x020
+
+#define SUN4I_FRONTEND_LINESTRD0_REG		0x040
+
+#define SUN4I_FRONTEND_INPUT_FMT_REG		0x04c
+#define SUN4I_FRONTEND_INPUT_FMT_DATA_MOD(mod)		((mod) << 8)
+#define SUN4I_FRONTEND_INPUT_FMT_DATA_FMT(fmt)		((fmt) << 4)
+#define SUN4I_FRONTEND_INPUT_FMT_PS(ps)			(ps)
+
+#define SUN4I_FRONTEND_OUTPUT_FMT_REG		0x05c
+#define SUN4I_FRONTEND_OUTPUT_FMT_DATA_FMT(fmt)		(fmt)
+
+#define SUN4I_FRONTEND_CH0_INSIZE_REG		0x100
+#define SUN4I_FRONTEND_INSIZE(h, w)			((((h) - 1) << 16) | (((w) - 1)))
+
+#define SUN4I_FRONTEND_CH0_OUTSIZE_REG		0x104
+#define SUN4I_FRONTEND_OUTSIZE(h, w)			((((h) - 1) << 16) | (((w) - 1)))
+
+#define SUN4I_FRONTEND_CH0_HORZFACT_REG		0x108
+#define SUN4I_FRONTEND_HORZFACT(i, f)			(((i) << 16) | (f))
+
+#define SUN4I_FRONTEND_CH0_VERTFACT_REG		0x10c
+#define SUN4I_FRONTEND_VERTFACT(i, f)			(((i) << 16) | (f))
+
+#define SUN4I_FRONTEND_CH0_HORZPHASE_REG	0x110
+#define SUN4I_FRONTEND_CH0_VERTPHASE0_REG	0x114
+#define SUN4I_FRONTEND_CH0_VERTPHASE1_REG	0x118
+
+#define SUN4I_FRONTEND_CH1_INSIZE_REG		0x200
+#define SUN4I_FRONTEND_CH1_OUTSIZE_REG		0x204
+#define SUN4I_FRONTEND_CH1_HORZFACT_REG		0x208
+#define SUN4I_FRONTEND_CH1_VERTFACT_REG		0x20c
+
+#define SUN4I_FRONTEND_CH1_HORZPHASE_REG	0x210
+#define SUN4I_FRONTEND_CH1_VERTPHASE0_REG	0x214
+#define SUN4I_FRONTEND_CH1_VERTPHASE1_REG	0x218
+
+#define SUN4I_FRONTEND_CH0_HORZCOEF0_REG(i)	(0x400 + i * 4)
+#define SUN4I_FRONTEND_CH0_HORZCOEF1_REG(i)	(0x480 + i * 4)
+#define SUN4I_FRONTEND_CH0_VERTCOEF_REG(i)	(0x500 + i * 4)
+#define SUN4I_FRONTEND_CH1_HORZCOEF0_REG(i)	(0x600 + i * 4)
+#define SUN4I_FRONTEND_CH1_HORZCOEF1_REG(i)	(0x680 + i * 4)
+#define SUN4I_FRONTEND_CH1_VERTCOEF_REG(i)	(0x700 + i * 4)
+
+struct clk;
+struct device_node;
+struct drm_plane;
+struct regmap;
+struct reset_control;
+
+struct sun4i_frontend {
+	struct list_head	list;
+	struct device		*dev;
+	struct device_node	*node;
+
+	struct clk		*bus_clk;
+	struct clk		*mod_clk;
+	struct clk		*ram_clk;
+	struct regmap		*regs;
+	struct reset_control	*reset;
+};
+
+extern const struct of_device_id sun4i_frontend_of_table[];
+
+int sun4i_frontend_init(struct sun4i_frontend *frontend);
+void sun4i_frontend_exit(struct sun4i_frontend *frontend);
+int sun4i_frontend_enable(struct sun4i_frontend *frontend);
+
+void sun4i_frontend_update_buffer(struct sun4i_frontend *frontend,
+				  struct drm_plane *plane);
+void sun4i_frontend_update_coord(struct sun4i_frontend *frontend,
+				 struct drm_plane *plane);
+int sun4i_frontend_update_formats(struct sun4i_frontend *frontend,
+				  struct drm_plane *plane, uint32_t out_fmt);
+
+#endif /* _SUN4I_FRONTEND_H_ */
diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.c b/drivers/gpu/drm/sun4i/sun4i_layer.c
index 7bddf12548d3..19be798e4fac 100644
--- a/drivers/gpu/drm/sun4i/sun4i_layer.c
+++ b/drivers/gpu/drm/sun4i/sun4i_layer.c
@@ -15,34 +15,107 @@
 #include <drm/drmP.h>
 
 #include "sun4i_backend.h"
+#include "sun4i_frontend.h"
 #include "sun4i_layer.h"
 #include "sunxi_engine.h"
 
 struct sun4i_plane_desc {
-	       enum drm_plane_type     type;
-	       u8                      pipe;
-	       const uint32_t          *formats;
-	       uint32_t                nformats;
+	enum drm_plane_type     type;
+	u8                      pipe;
+	const uint32_t          *formats;
+	uint32_t                nformats;
 };
 
+static void sun4i_backend_layer_reset(struct drm_plane *plane)
+{
+	struct sun4i_layer *layer = plane_to_sun4i_layer(plane);
+	struct sun4i_layer_state *state;
+
+	if (plane->state) {
+		state = state_to_sun4i_layer_state(plane->state);
+
+		__drm_atomic_helper_plane_destroy_state(&state->state);
+
+		kfree(state);
+		plane->state = NULL;
+	}
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (state) {
+		plane->state = &state->state;
+		plane->state->plane = plane;
+		plane->state->zpos = layer->id;
+	}
+}
+
+static struct drm_plane_state *
+sun4i_backend_layer_duplicate_state(struct drm_plane *plane)
+{
+	struct sun4i_layer_state *orig = state_to_sun4i_layer_state(plane->state);
+	struct sun4i_layer_state *copy;
+
+	copy = kzalloc(sizeof(*copy), GFP_KERNEL);
+	if (!copy)
+		return NULL;
+
+	__drm_atomic_helper_plane_duplicate_state(plane, &copy->state);
+	copy->uses_frontend = orig->uses_frontend;
+
+	return &copy->state;
+}
+
+static void sun4i_backend_layer_destroy_state(struct drm_plane *plane,
+					      struct drm_plane_state *state)
+{
+	struct sun4i_layer_state *s_state = state_to_sun4i_layer_state(state);
+
+	__drm_atomic_helper_plane_destroy_state(state);
+
+	kfree(s_state);
+}
+
 static void sun4i_backend_layer_atomic_disable(struct drm_plane *plane,
 					       struct drm_plane_state *old_state)
 {
+	struct sun4i_layer_state *layer_state = state_to_sun4i_layer_state(old_state);
 	struct sun4i_layer *layer = plane_to_sun4i_layer(plane);
 	struct sun4i_backend *backend = layer->backend;
 
 	sun4i_backend_layer_enable(backend, layer->id, false);
+
+	if (layer_state->uses_frontend) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&backend->frontend_lock, flags);
+		backend->frontend_teardown = true;
+		spin_unlock_irqrestore(&backend->frontend_lock, flags);
+	}
 }
 
 static void sun4i_backend_layer_atomic_update(struct drm_plane *plane,
 					      struct drm_plane_state *old_state)
 {
+	struct sun4i_layer_state *layer_state = state_to_sun4i_layer_state(plane->state);
 	struct sun4i_layer *layer = plane_to_sun4i_layer(plane);
 	struct sun4i_backend *backend = layer->backend;
+	struct sun4i_frontend *frontend = backend->frontend;
+
+	if (layer_state->uses_frontend) {
+		sun4i_frontend_init(frontend);
+		sun4i_frontend_update_coord(frontend, plane);
+		sun4i_frontend_update_buffer(frontend, plane);
+		sun4i_frontend_update_formats(frontend, plane,
+					      DRM_FORMAT_ARGB8888);
+		sun4i_backend_update_layer_frontend(backend, layer->id,
+						    DRM_FORMAT_ARGB8888);
+		sun4i_frontend_enable(frontend);
+	} else {
+		sun4i_backend_update_layer_formats(backend, layer->id, plane);
+		sun4i_backend_update_layer_buffer(backend, layer->id, plane);
+	}
 
 	sun4i_backend_update_layer_coord(backend, layer->id, plane);
-	sun4i_backend_update_layer_formats(backend, layer->id, plane);
-	sun4i_backend_update_layer_buffer(backend, layer->id, plane);
+	sun4i_backend_update_layer_zpos(backend, layer->id, plane);
 	sun4i_backend_layer_enable(backend, layer->id, true);
 }
 
@@ -52,11 +125,11 @@ static const struct drm_plane_helper_funcs sun4i_backend_layer_helper_funcs = {
 };
 
 static const struct drm_plane_funcs sun4i_backend_layer_funcs = {
-	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
-	.atomic_duplicate_state	= drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= sun4i_backend_layer_destroy_state,
+	.atomic_duplicate_state	= sun4i_backend_layer_duplicate_state,
 	.destroy		= drm_plane_cleanup,
 	.disable_plane		= drm_atomic_helper_disable_plane,
-	.reset			= drm_atomic_helper_plane_reset,
+	.reset			= sun4i_backend_layer_reset,
 	.update_plane		= drm_atomic_helper_update_plane,
 };
 
@@ -128,32 +201,12 @@ struct drm_plane **sun4i_layers_init(struct drm_device *drm,
 	struct sun4i_backend *backend = engine_to_sun4i_backend(engine);
 	int i;
 
-	planes = devm_kcalloc(drm->dev, ARRAY_SIZE(sun4i_backend_planes) + 1,
+	/* We need to have a sentinel at the need, hence the overallocation */
+	planes = devm_kcalloc(drm->dev, SUN4I_BACKEND_NUM_LAYERS + 1,
 			      sizeof(*planes), GFP_KERNEL);
 	if (!planes)
 		return ERR_PTR(-ENOMEM);
 
-	/*
-	 * The hardware is a bit unusual here.
-	 *
-	 * Even though it supports 4 layers, it does the composition
-	 * in two separate steps.
-	 *
-	 * The first one is assigning a layer to one of its two
-	 * pipes. If more that 1 layer is assigned to the same pipe,
-	 * and if pixels overlaps, the pipe will take the pixel from
-	 * the layer with the highest priority.
-	 *
-	 * The second step is the actual alpha blending, that takes
-	 * the two pipes as input, and uses the eventual alpha
-	 * component to do the transparency between the two.
-	 *
-	 * This two steps scenario makes us unable to guarantee a
-	 * robust alpha blending between the 4 layers in all
-	 * situations. So we just expose two layers, one per pipe. On
-	 * SoCs that support it, sprites could fill the need for more
-	 * layers.
-	 */
 	for (i = 0; i < ARRAY_SIZE(sun4i_backend_planes); i++) {
 		const struct sun4i_plane_desc *plane = &sun4i_backend_planes[i];
 		struct sun4i_layer *layer;
@@ -165,6 +218,8 @@ struct drm_plane **sun4i_layers_init(struct drm_device *drm,
 			return ERR_CAST(layer);
 		};
 
+		drm_plane_create_zpos_immutable_property(&layer->plane, i);
+
 		DRM_DEBUG_DRIVER("Assigning %s plane to pipe %d\n",
 				 i ? "overlay" : "primary", plane->pipe);
 		regmap_update_bits(engine->regs, SUN4I_BACKEND_ATTCTL_REG0(i),
diff --git a/drivers/gpu/drm/sun4i/sun4i_layer.h b/drivers/gpu/drm/sun4i/sun4i_layer.h
index 4e84f438b346..75b4868ba87c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_layer.h
+++ b/drivers/gpu/drm/sun4i/sun4i_layer.h
@@ -22,12 +22,23 @@ struct sun4i_layer {
 	int			id;
 };
 
+struct sun4i_layer_state {
+	struct drm_plane_state	state;
+	bool			uses_frontend;
+};
+
 static inline struct sun4i_layer *
 plane_to_sun4i_layer(struct drm_plane *plane)
 {
 	return container_of(plane, struct sun4i_layer, plane);
 }
 
+static inline struct sun4i_layer_state *
+state_to_sun4i_layer_state(struct drm_plane_state *state)
+{
+	return container_of(state, struct sun4i_layer_state, state);
+}
+
 struct drm_plane **sun4i_layers_init(struct drm_device *drm,
 				     struct sunxi_engine *engine);
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 3c15cf24b503..4b7340ee6290 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -540,6 +540,7 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private)
 	struct sun4i_tcon *tcon = private;
 	struct drm_device *drm = tcon->drm;
 	struct sun4i_crtc *scrtc = tcon->crtc;
+	struct sunxi_engine *engine = scrtc->engine;
 	unsigned int status;
 
 	regmap_read(tcon->regs, SUN4I_TCON_GINT0_REG, &status);
@@ -557,6 +558,9 @@ static irqreturn_t sun4i_tcon_handler(int irq, void *private)
 			   SUN4I_TCON_GINT0_VBLANK_INT(1),
 			   0);
 
+	if (engine->ops->vblank_quirk)
+		engine->ops->vblank_quirk(engine);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
index 28d7c48d50fe..2f0ccd50b54d 100644
--- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
@@ -211,7 +211,7 @@ static int sun8i_ui_layer_atomic_check(struct drm_plane *plane,
 	struct drm_crtc *crtc = state->crtc;
 	struct drm_crtc_state *crtc_state;
 	int min_scale, max_scale;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 
 	if (!crtc)
 		return 0;
@@ -220,10 +220,9 @@ static int sun8i_ui_layer_atomic_check(struct drm_plane *plane,
 	if (WARN_ON(!crtc_state))
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	max_scale = DRM_PLANE_HELPER_NO_SCALING;
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 40c3b303068a..eb3bf2d7291a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -239,7 +239,7 @@ static int sun8i_vi_layer_atomic_check(struct drm_plane *plane,
 	struct drm_crtc *crtc = state->crtc;
 	struct drm_crtc_state *crtc_state;
 	int min_scale, max_scale;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 
 	if (!crtc)
 		return 0;
@@ -248,10 +248,9 @@ static int sun8i_vi_layer_atomic_check(struct drm_plane *plane,
 	if (WARN_ON(!crtc_state))
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	min_scale = DRM_PLANE_HELPER_NO_SCALING;
 	max_scale = DRM_PLANE_HELPER_NO_SCALING;
diff --git a/drivers/gpu/drm/sun4i/sunxi_engine.h b/drivers/gpu/drm/sun4i/sunxi_engine.h
index 4cb70ae65c79..d317ea04b8aa 100644
--- a/drivers/gpu/drm/sun4i/sunxi_engine.h
+++ b/drivers/gpu/drm/sun4i/sunxi_engine.h
@@ -12,16 +12,106 @@
 
 struct drm_plane;
 struct drm_device;
+struct drm_crtc_state;
 
 struct sunxi_engine;
 
+/**
+ * struct sunxi_engine_ops - helper operations for sunXi engines
+ *
+ * These hooks are used by the common part of the DRM driver to
+ * implement the proper behaviour.
+ */
 struct sunxi_engine_ops {
+	/**
+	 * @atomic_begin:
+	 *
+	 * This callback allows to prepare our engine for an atomic
+	 * update. This is mirroring the
+	 * &drm_crtc_helper_funcs.atomic_begin callback, so any
+	 * documentation there applies.
+	 *
+	 * This function is optional.
+	 */
+	void (*atomic_begin)(struct sunxi_engine *engine,
+			     struct drm_crtc_state *old_state);
+
+	/**
+	 * @atomic_check:
+	 *
+	 * This callback allows to validate plane-update related CRTC
+	 * constraints specific to engines. This is mirroring the
+	 * &drm_crtc_helper_funcs.atomic_check callback, so any
+	 * documentation there applies.
+	 *
+	 * This function is optional.
+	 *
+	 * RETURNS:
+	 *
+	 * 0 on success or a negative error code.
+	 */
+	int (*atomic_check)(struct sunxi_engine *engine,
+			    struct drm_crtc_state *state);
+
+	/**
+	 * @commit:
+	 *
+	 * This callback will trigger the hardware switch to commit
+	 * the new configuration that has been setup during the next
+	 * vblank period.
+	 *
+	 * This function is optional.
+	 */
 	void (*commit)(struct sunxi_engine *engine);
+
+	/**
+	 * @layers_init:
+	 *
+	 * This callback is used to allocate, initialize and register
+	 * the layers supported by that engine.
+	 *
+	 * This function is mandatory.
+	 *
+	 * RETURNS:
+	 *
+	 * The array of struct drm_plane backing the layers, or an
+	 * error pointer on failure.
+	 */
 	struct drm_plane **(*layers_init)(struct drm_device *drm,
 					  struct sunxi_engine *engine);
 
+	/**
+	 * @apply_color_correction:
+	 *
+	 * This callback will enable the color correction in the
+	 * engine. This is useful only for the composite output.
+	 *
+	 * This function is optional.
+	 */
 	void (*apply_color_correction)(struct sunxi_engine *engine);
+
+	/**
+	 * @disable_color_correction:
+	 *
+	 * This callback will stop the color correction in the
+	 * engine. This is useful only for the composite output.
+	 *
+	 * This function is optional.
+	 */
 	void (*disable_color_correction)(struct sunxi_engine *engine);
+
+	/**
+	 * @vblank_quirk:
+	 *
+	 * This callback is used to implement engine-specific
+	 * behaviour part of the VBLANK event. It is run with all the
+	 * constraints of an interrupt (can't sleep, all local
+	 * interrupts disabled) and therefore should be as fast as
+	 * possible.
+	 *
+	 * This function is optional.
+	 */
+	void (*vblank_quirk)(struct sunxi_engine *engine);
 };
 
 /**
diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c
index 36a06a993698..7267a01e6f08 100644
--- a/drivers/gpu/drm/tegra/plane.c
+++ b/drivers/gpu/drm/tegra/plane.c
@@ -82,7 +82,7 @@ int tegra_plane_state_add(struct tegra_plane *plane,
 {
 	struct drm_crtc_state *crtc_state;
 	struct tegra_dc_state *tegra;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int err;
 
 	/* Propagate errors from allocation or locking failures. */
@@ -90,10 +90,9 @@ int tegra_plane_state_add(struct tegra_plane *plane,
 	if (IS_ERR(crtc_state))
 		return PTR_ERR(crtc_state);
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->mode.hdisplay;
-	clip.y2 = crtc_state->mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	/* Check plane state for visibility and calculate clipping bounds */
 	err = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c b/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c
index f41fc506ff87..11ae950b0fc9 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-pipe.c
@@ -15,7 +15,7 @@
 
 struct tinydrm_connector {
 	struct drm_connector base;
-	const struct drm_display_mode *mode;
+	struct drm_display_mode mode;
 };
 
 static inline struct tinydrm_connector *
@@ -29,7 +29,7 @@ static int tinydrm_connector_get_modes(struct drm_connector *connector)
 	struct tinydrm_connector *tconn = to_tinydrm_connector(connector);
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(connector->dev, tconn->mode);
+	mode = drm_mode_duplicate(connector->dev, &tconn->mode);
 	if (!mode) {
 		DRM_ERROR("Failed to duplicate mode\n");
 		return 0;
@@ -92,7 +92,7 @@ tinydrm_connector_create(struct drm_device *drm,
 	if (!tconn)
 		return ERR_PTR(-ENOMEM);
 
-	tconn->mode = mode;
+	drm_mode_copy(&tconn->mode, mode);
 	connector = &tconn->base;
 
 	drm_connector_helper_add(connector, &tinydrm_connector_hfuncs);
@@ -199,35 +199,27 @@ tinydrm_display_pipe_init(struct tinydrm_device *tdev,
 			  unsigned int rotation)
 {
 	struct drm_device *drm = tdev->drm;
-	struct drm_display_mode *mode_copy;
+	struct drm_display_mode mode_copy;
 	struct drm_connector *connector;
 	int ret;
 
-	mode_copy = devm_kmalloc(drm->dev, sizeof(*mode_copy), GFP_KERNEL);
-	if (!mode_copy)
-		return -ENOMEM;
-
-	*mode_copy = *mode;
-	ret = tinydrm_rotate_mode(mode_copy, rotation);
+	drm_mode_copy(&mode_copy, mode);
+	ret = tinydrm_rotate_mode(&mode_copy, rotation);
 	if (ret) {
 		DRM_ERROR("Illegal rotation value %u\n", rotation);
 		return -EINVAL;
 	}
 
-	drm->mode_config.min_width = mode_copy->hdisplay;
-	drm->mode_config.max_width = mode_copy->hdisplay;
-	drm->mode_config.min_height = mode_copy->vdisplay;
-	drm->mode_config.max_height = mode_copy->vdisplay;
+	drm->mode_config.min_width = mode_copy.hdisplay;
+	drm->mode_config.max_width = mode_copy.hdisplay;
+	drm->mode_config.min_height = mode_copy.vdisplay;
+	drm->mode_config.max_height = mode_copy.vdisplay;
 
-	connector = tinydrm_connector_create(drm, mode_copy, connector_type);
+	connector = tinydrm_connector_create(drm, &mode_copy, connector_type);
 	if (IS_ERR(connector))
 		return PTR_ERR(connector);
 
-	ret = drm_simple_display_pipe_init(drm, &tdev->pipe, funcs, formats,
-					   format_count, NULL, connector);
-	if (ret)
-		return ret;
-
-	return 0;
+	return drm_simple_display_pipe_init(drm, &tdev->pipe, funcs, formats,
+					    format_count, NULL, connector);
 }
 EXPORT_SYMBOL(tinydrm_display_pipe_init);
diff --git a/drivers/gpu/drm/tinydrm/ili9225.c b/drivers/gpu/drm/tinydrm/ili9225.c
index c0cf49849302..a0759502b81a 100644
--- a/drivers/gpu/drm/tinydrm/ili9225.c
+++ b/drivers/gpu/drm/tinydrm/ili9225.c
@@ -180,7 +180,6 @@ static void ili9225_pipe_enable(struct drm_simple_display_pipe *pipe,
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
-	struct drm_framebuffer *fb = pipe->plane.fb;
 	struct device *dev = tdev->drm->dev;
 	int ret;
 	u8 am_id;
@@ -269,10 +268,7 @@ static void ili9225_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	ili9225_command(mipi, ILI9225_DISPLAY_CONTROL_1, 0x1017);
 
-	mipi->enabled = true;
-
-	if (fb)
-		fb->funcs->dirty(fb, NULL, 0, 0, NULL, 0);
+	mipi_dbi_enable_flush(mipi);
 }
 
 static void ili9225_pipe_disable(struct drm_simple_display_pipe *pipe)
diff --git a/drivers/gpu/drm/tinydrm/mi0283qt.c b/drivers/gpu/drm/tinydrm/mi0283qt.c
index 674d407640be..79cb5af5abac 100644
--- a/drivers/gpu/drm/tinydrm/mi0283qt.c
+++ b/drivers/gpu/drm/tinydrm/mi0283qt.c
@@ -9,47 +9,59 @@
  * (at your option) any later version.
  */
 
-#include <drm/drm_fb_helper.h>
-#include <drm/drm_modeset_helper.h>
-#include <drm/tinydrm/ili9341.h>
-#include <drm/tinydrm/mipi-dbi.h>
-#include <drm/tinydrm/tinydrm-helpers.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/property.h>
 #include <linux/regulator/consumer.h>
 #include <linux/spi/spi.h>
+
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_modeset_helper.h>
+#include <drm/tinydrm/mipi-dbi.h>
+#include <drm/tinydrm/tinydrm-helpers.h>
 #include <video/mipi_display.h>
 
-static int mi0283qt_init(struct mipi_dbi *mipi)
+#define ILI9341_FRMCTR1		0xb1
+#define ILI9341_DISCTRL		0xb6
+#define ILI9341_ETMOD		0xb7
+
+#define ILI9341_PWCTRL1		0xc0
+#define ILI9341_PWCTRL2		0xc1
+#define ILI9341_VMCTRL1		0xc5
+#define ILI9341_VMCTRL2		0xc7
+#define ILI9341_PWCTRLA		0xcb
+#define ILI9341_PWCTRLB		0xcf
+
+#define ILI9341_PGAMCTRL	0xe0
+#define ILI9341_NGAMCTRL	0xe1
+#define ILI9341_DTCTRLA		0xe8
+#define ILI9341_DTCTRLB		0xea
+#define ILI9341_PWRSEQ		0xed
+
+#define ILI9341_EN3GAM		0xf2
+#define ILI9341_PUMPCTRL	0xf7
+
+#define ILI9341_MADCTL_BGR	BIT(3)
+#define ILI9341_MADCTL_MV	BIT(5)
+#define ILI9341_MADCTL_MX	BIT(6)
+#define ILI9341_MADCTL_MY	BIT(7)
+
+static void mi0283qt_enable(struct drm_simple_display_pipe *pipe,
+			    struct drm_crtc_state *crtc_state)
 {
-	struct tinydrm_device *tdev = &mipi->tinydrm;
-	struct device *dev = tdev->drm->dev;
+	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
+	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
 	u8 addr_mode;
 	int ret;
 
 	DRM_DEBUG_KMS("\n");
 
-	ret = regulator_enable(mipi->regulator);
-	if (ret) {
-		DRM_DEV_ERROR(dev, "Failed to enable regulator %d\n", ret);
-		return ret;
-	}
-
-	/* Avoid flicker by skipping setup if the bootloader has done it */
-	if (mipi_dbi_display_is_on(mipi))
-		return 0;
-
-	mipi_dbi_hw_reset(mipi);
-	ret = mipi_dbi_command(mipi, MIPI_DCS_SOFT_RESET);
-	if (ret) {
-		DRM_DEV_ERROR(dev, "Error sending command %d\n", ret);
-		regulator_disable(mipi->regulator);
-		return ret;
-	}
-
-	msleep(20);
+	ret = mipi_dbi_poweron_conditional_reset(mipi);
+	if (ret < 0)
+		return;
+	if (ret == 1)
+		goto out_enable;
 
 	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_OFF);
 
@@ -68,7 +80,7 @@ static int mi0283qt_init(struct mipi_dbi *mipi)
 	mipi_dbi_command(mipi, ILI9341_VMCTRL2, 0xbe);
 
 	/* Memory Access Control */
-	mipi_dbi_command(mipi, MIPI_DCS_SET_PIXEL_FORMAT, 0x55);
+	mipi_dbi_command(mipi, MIPI_DCS_SET_PIXEL_FORMAT, MIPI_DCS_PIXEL_FMT_16BIT);
 
 	switch (mipi->rotation) {
 	default:
@@ -112,19 +124,12 @@ static int mi0283qt_init(struct mipi_dbi *mipi)
 	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_ON);
 	msleep(100);
 
-	return 0;
-}
-
-static void mi0283qt_fini(void *data)
-{
-	struct mipi_dbi *mipi = data;
-
-	DRM_DEBUG_KMS("\n");
-	regulator_disable(mipi->regulator);
+out_enable:
+	mipi_dbi_enable_flush(mipi);
 }
 
 static const struct drm_simple_display_pipe_funcs mi0283qt_pipe_funcs = {
-	.enable = mipi_dbi_pipe_enable,
+	.enable = mi0283qt_enable,
 	.disable = mipi_dbi_pipe_disable,
 	.update = tinydrm_display_pipe_update,
 	.prepare_fb = tinydrm_display_pipe_prepare_fb,
@@ -205,17 +210,6 @@ static int mi0283qt_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	ret = mi0283qt_init(mipi);
-	if (ret)
-		return ret;
-
-	/* use devres to fini after drm unregister (drv->remove is before) */
-	ret = devm_add_action(dev, mi0283qt_fini, mipi);
-	if (ret) {
-		mi0283qt_fini(mipi);
-		return ret;
-	}
-
 	spi_set_drvdata(spi, mipi);
 
 	return devm_tinydrm_register(&mipi->tinydrm);
@@ -231,25 +225,13 @@ static void mi0283qt_shutdown(struct spi_device *spi)
 static int __maybe_unused mi0283qt_pm_suspend(struct device *dev)
 {
 	struct mipi_dbi *mipi = dev_get_drvdata(dev);
-	int ret;
 
-	ret = drm_mode_config_helper_suspend(mipi->tinydrm.drm);
-	if (ret)
-		return ret;
-
-	mi0283qt_fini(mipi);
-
-	return 0;
+	return drm_mode_config_helper_suspend(mipi->tinydrm.drm);
 }
 
 static int __maybe_unused mi0283qt_pm_resume(struct device *dev)
 {
 	struct mipi_dbi *mipi = dev_get_drvdata(dev);
-	int ret;
-
-	ret = mi0283qt_init(mipi);
-	if (ret)
-		return ret;
 
 	drm_mode_config_helper_resume(mipi->tinydrm.drm);
 
diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c
index aa6b6ce56891..75dd65c57e74 100644
--- a/drivers/gpu/drm/tinydrm/mipi-dbi.c
+++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c
@@ -271,21 +271,16 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = {
 };
 
 /**
- * mipi_dbi_pipe_enable - MIPI DBI pipe enable helper
- * @pipe: Display pipe
- * @crtc_state: CRTC state
+ * mipi_dbi_enable_flush - MIPI DBI enable helper
+ * @mipi: MIPI DBI structure
  *
- * This function enables backlight. Drivers can use this as their
+ * This function sets &mipi_dbi->enabled, flushes the whole framebuffer and
+ * enables the backlight. Drivers can use this in their
  * &drm_simple_display_pipe_funcs->enable callback.
  */
-void mipi_dbi_pipe_enable(struct drm_simple_display_pipe *pipe,
-			  struct drm_crtc_state *crtc_state)
+void mipi_dbi_enable_flush(struct mipi_dbi *mipi)
 {
-	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
-	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
-	struct drm_framebuffer *fb = pipe->plane.fb;
-
-	DRM_DEBUG_KMS("\n");
+	struct drm_framebuffer *fb = mipi->tinydrm.pipe.plane.fb;
 
 	mipi->enabled = true;
 	if (fb)
@@ -293,7 +288,7 @@ void mipi_dbi_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	tinydrm_enable_backlight(mipi->backlight);
 }
-EXPORT_SYMBOL(mipi_dbi_pipe_enable);
+EXPORT_SYMBOL(mipi_dbi_enable_flush);
 
 static void mipi_dbi_blank(struct mipi_dbi *mipi)
 {
@@ -316,8 +311,8 @@ static void mipi_dbi_blank(struct mipi_dbi *mipi)
  * mipi_dbi_pipe_disable - MIPI DBI pipe disable helper
  * @pipe: Display pipe
  *
- * This function disables backlight if present or if not the
- * display memory is blanked. Drivers can use this as their
+ * This function disables backlight if present, if not the display memory is
+ * blanked. The regulator is disabled if in use. Drivers can use this as their
  * &drm_simple_display_pipe_funcs->disable callback.
  */
 void mipi_dbi_pipe_disable(struct drm_simple_display_pipe *pipe)
@@ -333,6 +328,9 @@ void mipi_dbi_pipe_disable(struct drm_simple_display_pipe *pipe)
 		tinydrm_disable_backlight(mipi->backlight);
 	else
 		mipi_dbi_blank(mipi);
+
+	if (mipi->regulator)
+		regulator_disable(mipi->regulator);
 }
 EXPORT_SYMBOL(mipi_dbi_pipe_disable);
 
@@ -416,7 +414,7 @@ void mipi_dbi_hw_reset(struct mipi_dbi *mipi)
 		return;
 
 	gpiod_set_value_cansleep(mipi->reset, 0);
-	msleep(20);
+	usleep_range(20, 1000);
 	gpiod_set_value_cansleep(mipi->reset, 1);
 	msleep(120);
 }
@@ -443,6 +441,7 @@ bool mipi_dbi_display_is_on(struct mipi_dbi *mipi)
 
 	val &= ~DCS_POWER_MODE_RESERVED_MASK;
 
+	/* The poweron/reset value is 08h DCS_POWER_MODE_DISPLAY_NORMAL_MODE */
 	if (val != (DCS_POWER_MODE_DISPLAY |
 	    DCS_POWER_MODE_DISPLAY_NORMAL_MODE | DCS_POWER_MODE_SLEEP_MODE))
 		return false;
@@ -453,6 +452,78 @@ bool mipi_dbi_display_is_on(struct mipi_dbi *mipi)
 }
 EXPORT_SYMBOL(mipi_dbi_display_is_on);
 
+static int mipi_dbi_poweron_reset_conditional(struct mipi_dbi *mipi, bool cond)
+{
+	struct device *dev = mipi->tinydrm.drm->dev;
+	int ret;
+
+	if (mipi->regulator) {
+		ret = regulator_enable(mipi->regulator);
+		if (ret) {
+			DRM_DEV_ERROR(dev, "Failed to enable regulator (%d)\n", ret);
+			return ret;
+		}
+	}
+
+	if (cond && mipi_dbi_display_is_on(mipi))
+		return 1;
+
+	mipi_dbi_hw_reset(mipi);
+	ret = mipi_dbi_command(mipi, MIPI_DCS_SOFT_RESET);
+	if (ret) {
+		DRM_DEV_ERROR(dev, "Failed to send reset command (%d)\n", ret);
+		if (mipi->regulator)
+			regulator_disable(mipi->regulator);
+		return ret;
+	}
+
+	/*
+	 * If we did a hw reset, we know the controller is in Sleep mode and
+	 * per MIPI DSC spec should wait 5ms after soft reset. If we didn't,
+	 * we assume worst case and wait 120ms.
+	 */
+	if (mipi->reset)
+		usleep_range(5000, 20000);
+	else
+		msleep(120);
+
+	return 0;
+}
+
+/**
+ * mipi_dbi_poweron_reset - MIPI DBI poweron and reset
+ * @mipi: MIPI DBI structure
+ *
+ * This function enables the regulator if used and does a hardware and software
+ * reset.
+ *
+ * Returns:
+ * Zero on success, or a negative error code.
+ */
+int mipi_dbi_poweron_reset(struct mipi_dbi *mipi)
+{
+	return mipi_dbi_poweron_reset_conditional(mipi, false);
+}
+EXPORT_SYMBOL(mipi_dbi_poweron_reset);
+
+/**
+ * mipi_dbi_poweron_conditional_reset - MIPI DBI poweron and conditional reset
+ * @mipi: MIPI DBI structure
+ *
+ * This function enables the regulator if used and if the display is off, it
+ * does a hardware and software reset. If mipi_dbi_display_is_on() determines
+ * that the display is on, no reset is performed.
+ *
+ * Returns:
+ * Zero if the controller was reset, 1 if the display was already on, or a
+ * negative error code.
+ */
+int mipi_dbi_poweron_conditional_reset(struct mipi_dbi *mipi)
+{
+	return mipi_dbi_poweron_reset_conditional(mipi, true);
+}
+EXPORT_SYMBOL(mipi_dbi_poweron_conditional_reset);
+
 #if IS_ENABLED(CONFIG_SPI)
 
 /**
diff --git a/drivers/gpu/drm/tinydrm/st7586.c b/drivers/gpu/drm/tinydrm/st7586.c
index 5aebfceb740e..a6396ef9cc4a 100644
--- a/drivers/gpu/drm/tinydrm/st7586.c
+++ b/drivers/gpu/drm/tinydrm/st7586.c
@@ -179,20 +179,16 @@ static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe,
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
-	struct drm_framebuffer *fb = pipe->plane.fb;
-	struct device *dev = tdev->drm->dev;
 	int ret;
 	u8 addr_mode;
 
 	DRM_DEBUG_KMS("\n");
 
-	mipi_dbi_hw_reset(mipi);
-	ret = mipi_dbi_command(mipi, ST7586_AUTO_READ_CTRL, 0x9f);
-	if (ret) {
-		DRM_DEV_ERROR(dev, "Error sending command %d\n", ret);
+	ret = mipi_dbi_poweron_reset(mipi);
+	if (ret)
 		return;
-	}
 
+	mipi_dbi_command(mipi, ST7586_AUTO_READ_CTRL, 0x9f);
 	mipi_dbi_command(mipi, ST7586_OTP_RW_CTRL, 0x00);
 
 	msleep(10);
@@ -241,10 +237,7 @@ static void st7586_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_ON);
 
-	mipi->enabled = true;
-
-	if (fb)
-		fb->funcs->dirty(fb, NULL, 0, 0, NULL, 0);
+	mipi_dbi_enable_flush(mipi);
 }
 
 static void st7586_pipe_disable(struct drm_simple_display_pipe *pipe)
diff --git a/drivers/gpu/drm/tinydrm/st7735r.c b/drivers/gpu/drm/tinydrm/st7735r.c
index 98ff447f40b4..08b4fb18edb6 100644
--- a/drivers/gpu/drm/tinydrm/st7735r.c
+++ b/drivers/gpu/drm/tinydrm/st7735r.c
@@ -40,19 +40,14 @@ static void jd_t18003_t01_pipe_enable(struct drm_simple_display_pipe *pipe,
 {
 	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
 	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
-	struct device *dev = tdev->drm->dev;
 	int ret;
 	u8 addr_mode;
 
 	DRM_DEBUG_KMS("\n");
 
-	mipi_dbi_hw_reset(mipi);
-
-	ret = mipi_dbi_command(mipi, MIPI_DCS_SOFT_RESET);
-	if (ret) {
-		DRM_DEV_ERROR(dev, "Error sending command %d\n", ret);
+	ret = mipi_dbi_poweron_reset(mipi);
+	if (ret)
 		return;
-	}
 
 	msleep(150);
 
@@ -102,7 +97,7 @@ static void jd_t18003_t01_pipe_enable(struct drm_simple_display_pipe *pipe,
 
 	msleep(20);
 
-	mipi_dbi_pipe_enable(pipe, crtc_state);
+	mipi_dbi_enable_flush(mipi);
 }
 
 static const struct drm_simple_display_pipe_funcs jd_t18003_t01_pipe_funcs = {
diff --git a/drivers/gpu/drm/vc4/Makefile b/drivers/gpu/drm/vc4/Makefile
index f5500df51686..4a3a868235f8 100644
--- a/drivers/gpu/drm/vc4/Makefile
+++ b/drivers/gpu/drm/vc4/Makefile
@@ -15,6 +15,7 @@ vc4-y := \
 	vc4_vec.o \
 	vc4_hvs.o \
 	vc4_irq.o \
+	vc4_perfmon.o \
 	vc4_plane.o \
 	vc4_render_cl.o \
 	vc4_trace_points.o \
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index ceb385fd69c5..94b99c90425a 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -101,6 +101,7 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
 	case DRM_VC4_PARAM_SUPPORTS_THREADED_FS:
 	case DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER:
 	case DRM_VC4_PARAM_SUPPORTS_MADVISE:
+	case DRM_VC4_PARAM_SUPPORTS_PERFMON:
 		args->value = true;
 		break;
 	default:
@@ -111,6 +112,26 @@ static int vc4_get_param_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
+static int vc4_open(struct drm_device *dev, struct drm_file *file)
+{
+	struct vc4_file *vc4file;
+
+	vc4file = kzalloc(sizeof(*vc4file), GFP_KERNEL);
+	if (!vc4file)
+		return -ENOMEM;
+
+	vc4_perfmon_open_file(vc4file);
+	file->driver_priv = vc4file;
+	return 0;
+}
+
+static void vc4_close(struct drm_device *dev, struct drm_file *file)
+{
+	struct vc4_file *vc4file = file->driver_priv;
+
+	vc4_perfmon_close_file(vc4file);
+}
+
 static const struct vm_operations_struct vc4_vm_ops = {
 	.fault = vc4_fault,
 	.open = drm_gem_vm_open,
@@ -143,6 +164,9 @@ static const struct drm_ioctl_desc vc4_drm_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(VC4_GET_TILING, vc4_get_tiling_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VC4_LABEL_BO, vc4_label_bo_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(VC4_GEM_MADVISE, vc4_gem_madvise_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_PERFMON_CREATE, vc4_perfmon_create_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_PERFMON_DESTROY, vc4_perfmon_destroy_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(VC4_PERFMON_GET_VALUES, vc4_perfmon_get_values_ioctl, DRM_RENDER_ALLOW),
 };
 
 static struct drm_driver vc4_drm_driver = {
@@ -153,6 +177,8 @@ static struct drm_driver vc4_drm_driver = {
 			    DRIVER_RENDER |
 			    DRIVER_PRIME),
 	.lastclose = drm_fb_helper_lastclose,
+	.open = vc4_open,
+	.postclose = vc4_close,
 	.irq_handler = vc4_irq,
 	.irq_preinstall = vc4_irq_preinstall,
 	.irq_postinstall = vc4_irq_postinstall,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 3af22936d9b3..fefa1664a9f5 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -11,6 +11,8 @@
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem_cma_helper.h>
 
+#include "uapi/drm/vc4_drm.h"
+
 /* Don't forget to update vc4_bo.c: bo_type_names[] when adding to
  * this.
  */
@@ -29,6 +31,36 @@ enum vc4_kernel_bo_type {
 	VC4_BO_TYPE_COUNT
 };
 
+/* Performance monitor object. The perform lifetime is controlled by userspace
+ * using perfmon related ioctls. A perfmon can be attached to a submit_cl
+ * request, and when this is the case, HW perf counters will be activated just
+ * before the submit_cl is submitted to the GPU and disabled when the job is
+ * done. This way, only events related to a specific job will be counted.
+ */
+struct vc4_perfmon {
+	/* Tracks the number of users of the perfmon, when this counter reaches
+	 * zero the perfmon is destroyed.
+	 */
+	refcount_t refcnt;
+
+	/* Number of counters activated in this perfmon instance
+	 * (should be less than DRM_VC4_MAX_PERF_COUNTERS).
+	 */
+	u8 ncounters;
+
+	/* Events counted by the HW perf counters. */
+	u8 events[DRM_VC4_MAX_PERF_COUNTERS];
+
+	/* Storage for counter values. Counters are incremented by the HW
+	 * perf counter values every time the perfmon is attached to a GPU job.
+	 * This way, perfmon users don't have to retrieve the results after
+	 * each job if they want to track events covering several submissions.
+	 * Note that counter values can't be reset, but you can fake a reset by
+	 * destroying the perfmon and creating a new one.
+	 */
+	u64 counters[0];
+};
+
 struct vc4_dev {
 	struct drm_device *dev;
 
@@ -121,6 +153,11 @@ struct vc4_dev {
 	wait_queue_head_t job_wait_queue;
 	struct work_struct job_done_work;
 
+	/* Used to track the active perfmon if any. Access to this field is
+	 * protected by job_lock.
+	 */
+	struct vc4_perfmon *active_perfmon;
+
 	/* List of struct vc4_seqno_cb for callbacks to be made from a
 	 * workqueue when the given seqno is passed.
 	 */
@@ -406,6 +443,21 @@ struct vc4_exec_info {
 	void *uniforms_v;
 	uint32_t uniforms_p;
 	uint32_t uniforms_size;
+
+	/* Pointer to a performance monitor object if the user requested it,
+	 * NULL otherwise.
+	 */
+	struct vc4_perfmon *perfmon;
+};
+
+/* Per-open file private data. Any driver-specific resource that has to be
+ * released when the DRM file is closed should be placed here.
+ */
+struct vc4_file {
+	struct {
+		struct idr idr;
+		struct mutex lock;
+	} perfmon;
 };
 
 static inline struct vc4_exec_info *
@@ -646,3 +698,19 @@ bool vc4_check_tex_size(struct vc4_exec_info *exec,
 /* vc4_validate_shader.c */
 struct vc4_validated_shader_info *
 vc4_validate_shader(struct drm_gem_cma_object *shader_obj);
+
+/* vc4_perfmon.c */
+void vc4_perfmon_get(struct vc4_perfmon *perfmon);
+void vc4_perfmon_put(struct vc4_perfmon *perfmon);
+void vc4_perfmon_start(struct vc4_dev *vc4, struct vc4_perfmon *perfmon);
+void vc4_perfmon_stop(struct vc4_dev *vc4, struct vc4_perfmon *perfmon,
+		      bool capture);
+struct vc4_perfmon *vc4_perfmon_find(struct vc4_file *vc4file, int id);
+void vc4_perfmon_open_file(struct vc4_file *vc4file);
+void vc4_perfmon_close_file(struct vc4_file *vc4file);
+int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv);
+int vc4_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+int vc4_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index c94cce96544c..2107b0daf8ef 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -467,14 +467,30 @@ again:
 
 	vc4_flush_caches(dev);
 
+	/* Only start the perfmon if it was not already started by a previous
+	 * job.
+	 */
+	if (exec->perfmon && vc4->active_perfmon != exec->perfmon)
+		vc4_perfmon_start(vc4, exec->perfmon);
+
 	/* Either put the job in the binner if it uses the binner, or
 	 * immediately move it to the to-be-rendered queue.
 	 */
 	if (exec->ct0ca != exec->ct0ea) {
 		submit_cl(dev, 0, exec->ct0ca, exec->ct0ea);
 	} else {
+		struct vc4_exec_info *next;
+
 		vc4_move_job_to_render(dev, exec);
-		goto again;
+		next = vc4_first_bin_job(vc4);
+
+		/* We can't start the next bin job if the previous job had a
+		 * different perfmon instance attached to it. The same goes
+		 * if one of them had a perfmon attached to it and the other
+		 * one doesn't.
+		 */
+		if (next && next->perfmon == exec->perfmon)
+			goto again;
 	}
 }
 
@@ -642,6 +658,7 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 		 struct ww_acquire_ctx *acquire_ctx)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_exec_info *renderjob;
 	uint64_t seqno;
 	unsigned long irqflags;
 	struct vc4_fence *fence;
@@ -667,11 +684,14 @@ vc4_queue_submit(struct drm_device *dev, struct vc4_exec_info *exec,
 
 	list_add_tail(&exec->head, &vc4->bin_job_list);
 
-	/* If no job was executing, kick ours off.  Otherwise, it'll
-	 * get started when the previous job's flush done interrupt
-	 * occurs.
+	/* If no bin job was executing and if the render job (if any) has the
+	 * same perfmon as our job attached to it (or if both jobs don't have
+	 * perfmon activated), then kick ours off.  Otherwise, it'll get
+	 * started when the previous job's flush/render done interrupt occurs.
 	 */
-	if (vc4_first_bin_job(vc4) == exec) {
+	renderjob = vc4_first_render_job(vc4);
+	if (vc4_first_bin_job(vc4) == exec &&
+	    (!renderjob || renderjob->perfmon == exec->perfmon)) {
 		vc4_submit_next_bin_job(dev);
 		vc4_queue_hangcheck(dev);
 	}
@@ -936,6 +956,9 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec)
 	vc4->bin_alloc_used &= ~exec->bin_slots;
 	spin_unlock_irqrestore(&vc4->job_lock, irqflags);
 
+	/* Release the reference we had on the perf monitor. */
+	vc4_perfmon_put(exec->perfmon);
+
 	mutex_lock(&vc4->power_lock);
 	if (--vc4->power_refcount == 0) {
 		pm_runtime_mark_last_busy(&vc4->v3d->pdev->dev);
@@ -1088,6 +1111,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_file *vc4file = file_priv->driver_priv;
 	struct drm_vc4_submit_cl *args = data;
 	struct vc4_exec_info *exec;
 	struct ww_acquire_ctx acquire_ctx;
@@ -1101,6 +1125,11 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
+	if (args->pad2 != 0) {
+		DRM_DEBUG("->pad2 must be set to zero\n");
+		return -EINVAL;
+	}
+
 	exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
 	if (!exec) {
 		DRM_ERROR("malloc failure on exec struct\n");
@@ -1126,6 +1155,15 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	if (args->perfmonid) {
+		exec->perfmon = vc4_perfmon_find(vc4file,
+						 args->perfmonid);
+		if (!exec->perfmon) {
+			ret = -ENOENT;
+			goto fail;
+		}
+	}
+
 	if (exec->args->bin_cl_size != 0) {
 		ret = vc4_get_bcl(dev, exec);
 		if (ret)
diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c
index 3dd62d75f531..4cd2ccfe15f4 100644
--- a/drivers/gpu/drm/vc4/vc4_irq.c
+++ b/drivers/gpu/drm/vc4/vc4_irq.c
@@ -104,13 +104,20 @@ static void
 vc4_irq_finish_bin_job(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
-	struct vc4_exec_info *exec = vc4_first_bin_job(vc4);
+	struct vc4_exec_info *next, *exec = vc4_first_bin_job(vc4);
 
 	if (!exec)
 		return;
 
 	vc4_move_job_to_render(dev, exec);
-	vc4_submit_next_bin_job(dev);
+	next = vc4_first_bin_job(vc4);
+
+	/* Only submit the next job in the bin list if it matches the perfmon
+	 * attached to the one that just finished (or if both jobs don't have
+	 * perfmon attached to them).
+	 */
+	if (next && next->perfmon == exec->perfmon)
+		vc4_submit_next_bin_job(dev);
 }
 
 static void
@@ -122,6 +129,10 @@ vc4_cancel_bin_job(struct drm_device *dev)
 	if (!exec)
 		return;
 
+	/* Stop the perfmon so that the next bin job can be started. */
+	if (exec->perfmon)
+		vc4_perfmon_stop(vc4, exec->perfmon, false);
+
 	list_move_tail(&exec->head, &vc4->bin_job_list);
 	vc4_submit_next_bin_job(dev);
 }
@@ -131,18 +142,41 @@ vc4_irq_finish_render_job(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_exec_info *exec = vc4_first_render_job(vc4);
+	struct vc4_exec_info *nextbin, *nextrender;
 
 	if (!exec)
 		return;
 
 	vc4->finished_seqno++;
 	list_move_tail(&exec->head, &vc4->job_done_list);
+
+	nextbin = vc4_first_bin_job(vc4);
+	nextrender = vc4_first_render_job(vc4);
+
+	/* Only stop the perfmon if following jobs in the queue don't expect it
+	 * to be enabled.
+	 */
+	if (exec->perfmon && !nextrender &&
+	    (!nextbin || nextbin->perfmon != exec->perfmon))
+		vc4_perfmon_stop(vc4, exec->perfmon, true);
+
+	/* If there's a render job waiting, start it. If this is not the case
+	 * we may have to unblock the binner if it's been stalled because of
+	 * perfmon (this can be checked by comparing the perfmon attached to
+	 * the finished renderjob to the one attached to the next bin job: if
+	 * they don't match, this means the binner is stalled and should be
+	 * restarted).
+	 */
+	if (nextrender)
+		vc4_submit_next_render_job(dev);
+	else if (nextbin && nextbin->perfmon != exec->perfmon)
+		vc4_submit_next_bin_job(dev);
+
 	if (exec->fence) {
 		dma_fence_signal_locked(exec->fence);
 		dma_fence_put(exec->fence);
 		exec->fence = NULL;
 	}
-	vc4_submit_next_render_job(dev);
 
 	wake_up_all(&vc4->job_wait_queue);
 	schedule_work(&vc4->job_done_work);
diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c
new file mode 100644
index 000000000000..437e7a27f21d
--- /dev/null
+++ b/drivers/gpu/drm/vc4/vc4_perfmon.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Broadcom
+ */
+
+/**
+ * DOC: VC4 V3D performance monitor module
+ *
+ * The V3D block provides 16 hardware counters which can count various events.
+ */
+
+#include "vc4_drv.h"
+#include "vc4_regs.h"
+
+#define VC4_PERFMONID_MIN	1
+#define VC4_PERFMONID_MAX	U32_MAX
+
+void vc4_perfmon_get(struct vc4_perfmon *perfmon)
+{
+	if (perfmon)
+		refcount_inc(&perfmon->refcnt);
+}
+
+void vc4_perfmon_put(struct vc4_perfmon *perfmon)
+{
+	if (perfmon && refcount_dec_and_test(&perfmon->refcnt))
+		kfree(perfmon);
+}
+
+void vc4_perfmon_start(struct vc4_dev *vc4, struct vc4_perfmon *perfmon)
+{
+	unsigned int i;
+	u32 mask;
+
+	if (WARN_ON_ONCE(!perfmon || vc4->active_perfmon))
+		return;
+
+	for (i = 0; i < perfmon->ncounters; i++)
+		V3D_WRITE(V3D_PCTRS(i), perfmon->events[i]);
+
+	mask = GENMASK(perfmon->ncounters - 1, 0);
+	V3D_WRITE(V3D_PCTRC, mask);
+	V3D_WRITE(V3D_PCTRE, V3D_PCTRE_EN | mask);
+	vc4->active_perfmon = perfmon;
+}
+
+void vc4_perfmon_stop(struct vc4_dev *vc4, struct vc4_perfmon *perfmon,
+		      bool capture)
+{
+	unsigned int i;
+
+	if (WARN_ON_ONCE(!vc4->active_perfmon ||
+			 perfmon != vc4->active_perfmon))
+		return;
+
+	if (capture) {
+		for (i = 0; i < perfmon->ncounters; i++)
+			perfmon->counters[i] += V3D_READ(V3D_PCTR(i));
+	}
+
+	V3D_WRITE(V3D_PCTRE, 0);
+	vc4->active_perfmon = NULL;
+}
+
+struct vc4_perfmon *vc4_perfmon_find(struct vc4_file *vc4file, int id)
+{
+	struct vc4_perfmon *perfmon;
+
+	mutex_lock(&vc4file->perfmon.lock);
+	perfmon = idr_find(&vc4file->perfmon.idr, id);
+	vc4_perfmon_get(perfmon);
+	mutex_unlock(&vc4file->perfmon.lock);
+
+	return perfmon;
+}
+
+void vc4_perfmon_open_file(struct vc4_file *vc4file)
+{
+	mutex_init(&vc4file->perfmon.lock);
+	idr_init(&vc4file->perfmon.idr);
+}
+
+static int vc4_perfmon_idr_del(int id, void *elem, void *data)
+{
+	struct vc4_perfmon *perfmon = elem;
+
+	vc4_perfmon_put(perfmon);
+
+	return 0;
+}
+
+void vc4_perfmon_close_file(struct vc4_file *vc4file)
+{
+	mutex_lock(&vc4file->perfmon.lock);
+	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, NULL);
+	idr_destroy(&vc4file->perfmon.idr);
+	mutex_unlock(&vc4file->perfmon.lock);
+}
+
+int vc4_perfmon_create_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv)
+{
+	struct vc4_file *vc4file = file_priv->driver_priv;
+	struct drm_vc4_perfmon_create *req = data;
+	struct vc4_perfmon *perfmon;
+	unsigned int i;
+	int ret;
+
+	/* Number of monitored counters cannot exceed HW limits. */
+	if (req->ncounters > DRM_VC4_MAX_PERF_COUNTERS ||
+	    !req->ncounters)
+		return -EINVAL;
+
+	/* Make sure all events are valid. */
+	for (i = 0; i < req->ncounters; i++) {
+		if (req->events[i] >= VC4_PERFCNT_NUM_EVENTS)
+			return -EINVAL;
+	}
+
+	perfmon = kzalloc(sizeof(*perfmon) + (req->ncounters * sizeof(u64)),
+			  GFP_KERNEL);
+	if (!perfmon)
+		return -ENOMEM;
+
+	for (i = 0; i < req->ncounters; i++)
+		perfmon->events[i] = req->events[i];
+
+	perfmon->ncounters = req->ncounters;
+
+	refcount_set(&perfmon->refcnt, 1);
+
+	mutex_lock(&vc4file->perfmon.lock);
+	ret = idr_alloc(&vc4file->perfmon.idr, perfmon, VC4_PERFMONID_MIN,
+			VC4_PERFMONID_MAX, GFP_KERNEL);
+	mutex_unlock(&vc4file->perfmon.lock);
+
+	if (ret < 0) {
+		kfree(perfmon);
+		return ret;
+	}
+
+	req->id = ret;
+	return 0;
+}
+
+int vc4_perfmon_destroy_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct vc4_file *vc4file = file_priv->driver_priv;
+	struct drm_vc4_perfmon_destroy *req = data;
+	struct vc4_perfmon *perfmon;
+
+	mutex_lock(&vc4file->perfmon.lock);
+	perfmon = idr_remove(&vc4file->perfmon.idr, req->id);
+	mutex_unlock(&vc4file->perfmon.lock);
+
+	if (!perfmon)
+		return -EINVAL;
+
+	vc4_perfmon_put(perfmon);
+	return 0;
+}
+
+int vc4_perfmon_get_values_ioctl(struct drm_device *dev, void *data,
+				 struct drm_file *file_priv)
+{
+	struct vc4_file *vc4file = file_priv->driver_priv;
+	struct drm_vc4_perfmon_get_values *req = data;
+	struct vc4_perfmon *perfmon;
+	int ret;
+
+	mutex_lock(&vc4file->perfmon.lock);
+	perfmon = idr_find(&vc4file->perfmon.idr, req->id);
+	vc4_perfmon_get(perfmon);
+	mutex_unlock(&vc4file->perfmon.lock);
+
+	if (!perfmon)
+		return -EINVAL;
+
+	if (copy_to_user(u64_to_user_ptr(req->values_ptr), perfmon->counters,
+			 perfmon->ncounters * sizeof(u64)))
+		ret = -EFAULT;
+	else
+		ret = 0;
+
+	vc4_perfmon_put(perfmon);
+	return ret;
+}
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 515f97997624..61ad955645a5 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -85,47 +85,46 @@ static const struct hvs_format {
 	u32 drm; /* DRM_FORMAT_* */
 	u32 hvs; /* HVS_FORMAT_* */
 	u32 pixel_order;
-	bool has_alpha;
 } hvs_formats[] = {
 	{
 		.drm = DRM_FORMAT_XRGB8888, .hvs = HVS_PIXEL_FORMAT_RGBA8888,
-		.pixel_order = HVS_PIXEL_ORDER_ABGR, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_ABGR,
 	},
 	{
 		.drm = DRM_FORMAT_ARGB8888, .hvs = HVS_PIXEL_FORMAT_RGBA8888,
-		.pixel_order = HVS_PIXEL_ORDER_ABGR, .has_alpha = true,
+		.pixel_order = HVS_PIXEL_ORDER_ABGR,
 	},
 	{
 		.drm = DRM_FORMAT_ABGR8888, .hvs = HVS_PIXEL_FORMAT_RGBA8888,
-		.pixel_order = HVS_PIXEL_ORDER_ARGB, .has_alpha = true,
+		.pixel_order = HVS_PIXEL_ORDER_ARGB,
 	},
 	{
 		.drm = DRM_FORMAT_XBGR8888, .hvs = HVS_PIXEL_FORMAT_RGBA8888,
-		.pixel_order = HVS_PIXEL_ORDER_ARGB, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_ARGB,
 	},
 	{
 		.drm = DRM_FORMAT_RGB565, .hvs = HVS_PIXEL_FORMAT_RGB565,
-		.pixel_order = HVS_PIXEL_ORDER_XRGB, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_XRGB,
 	},
 	{
 		.drm = DRM_FORMAT_BGR565, .hvs = HVS_PIXEL_FORMAT_RGB565,
-		.pixel_order = HVS_PIXEL_ORDER_XBGR, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_XBGR,
 	},
 	{
 		.drm = DRM_FORMAT_ARGB1555, .hvs = HVS_PIXEL_FORMAT_RGBA5551,
-		.pixel_order = HVS_PIXEL_ORDER_ABGR, .has_alpha = true,
+		.pixel_order = HVS_PIXEL_ORDER_ABGR,
 	},
 	{
 		.drm = DRM_FORMAT_XRGB1555, .hvs = HVS_PIXEL_FORMAT_RGBA5551,
-		.pixel_order = HVS_PIXEL_ORDER_ABGR, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_ABGR,
 	},
 	{
 		.drm = DRM_FORMAT_RGB888, .hvs = HVS_PIXEL_FORMAT_RGB888,
-		.pixel_order = HVS_PIXEL_ORDER_XRGB, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_XRGB,
 	},
 	{
 		.drm = DRM_FORMAT_BGR888, .hvs = HVS_PIXEL_FORMAT_RGB888,
-		.pixel_order = HVS_PIXEL_ORDER_XBGR, .has_alpha = false,
+		.pixel_order = HVS_PIXEL_ORDER_XBGR,
 	},
 	{
 		.drm = DRM_FORMAT_YUV422,
@@ -622,7 +621,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	/* Position Word 2: Source Image Size, Alpha Mode */
 	vc4_state->pos2_offset = vc4_state->dlist_count;
 	vc4_dlist_write(vc4_state,
-			VC4_SET_FIELD(format->has_alpha ?
+			VC4_SET_FIELD(fb->format->has_alpha ?
 				      SCALER_POS2_ALPHA_MODE_PIPELINE :
 				      SCALER_POS2_ALPHA_MODE_FIXED,
 				      SCALER_POS2_ALPHA_MODE) |
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index 55677bd50f66..b9749cb24063 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -122,38 +122,9 @@
 #define V3D_VPMBASE  0x00504
 #define V3D_PCTRC    0x00670
 #define V3D_PCTRE    0x00674
-#define V3D_PCTR0    0x00680
-#define V3D_PCTRS0   0x00684
-#define V3D_PCTR1    0x00688
-#define V3D_PCTRS1   0x0068c
-#define V3D_PCTR2    0x00690
-#define V3D_PCTRS2   0x00694
-#define V3D_PCTR3    0x00698
-#define V3D_PCTRS3   0x0069c
-#define V3D_PCTR4    0x006a0
-#define V3D_PCTRS4   0x006a4
-#define V3D_PCTR5    0x006a8
-#define V3D_PCTRS5   0x006ac
-#define V3D_PCTR6    0x006b0
-#define V3D_PCTRS6   0x006b4
-#define V3D_PCTR7    0x006b8
-#define V3D_PCTRS7   0x006bc
-#define V3D_PCTR8    0x006c0
-#define V3D_PCTRS8   0x006c4
-#define V3D_PCTR9    0x006c8
-#define V3D_PCTRS9   0x006cc
-#define V3D_PCTR10   0x006d0
-#define V3D_PCTRS10  0x006d4
-#define V3D_PCTR11   0x006d8
-#define V3D_PCTRS11  0x006dc
-#define V3D_PCTR12   0x006e0
-#define V3D_PCTRS12  0x006e4
-#define V3D_PCTR13   0x006e8
-#define V3D_PCTRS13  0x006ec
-#define V3D_PCTR14   0x006f0
-#define V3D_PCTRS14  0x006f4
-#define V3D_PCTR15   0x006f8
-#define V3D_PCTRS15  0x006fc
+# define V3D_PCTRE_EN	BIT(31)
+#define V3D_PCTR(x)  (0x00680 + ((x) * 8))
+#define V3D_PCTRS(x) (0x00684 + ((x) * 8))
 #define V3D_DBGE     0x00f00
 #define V3D_FDBGO    0x00f04
 #define V3D_FDBGB    0x00f08
diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c
index 493f392b3a0a..bfc2fa73d2ae 100644
--- a/drivers/gpu/drm/vc4/vc4_v3d.c
+++ b/drivers/gpu/drm/vc4/vc4_v3d.c
@@ -68,38 +68,38 @@ static const struct {
 	REGDEF(V3D_VPMBASE),
 	REGDEF(V3D_PCTRC),
 	REGDEF(V3D_PCTRE),
-	REGDEF(V3D_PCTR0),
-	REGDEF(V3D_PCTRS0),
-	REGDEF(V3D_PCTR1),
-	REGDEF(V3D_PCTRS1),
-	REGDEF(V3D_PCTR2),
-	REGDEF(V3D_PCTRS2),
-	REGDEF(V3D_PCTR3),
-	REGDEF(V3D_PCTRS3),
-	REGDEF(V3D_PCTR4),
-	REGDEF(V3D_PCTRS4),
-	REGDEF(V3D_PCTR5),
-	REGDEF(V3D_PCTRS5),
-	REGDEF(V3D_PCTR6),
-	REGDEF(V3D_PCTRS6),
-	REGDEF(V3D_PCTR7),
-	REGDEF(V3D_PCTRS7),
-	REGDEF(V3D_PCTR8),
-	REGDEF(V3D_PCTRS8),
-	REGDEF(V3D_PCTR9),
-	REGDEF(V3D_PCTRS9),
-	REGDEF(V3D_PCTR10),
-	REGDEF(V3D_PCTRS10),
-	REGDEF(V3D_PCTR11),
-	REGDEF(V3D_PCTRS11),
-	REGDEF(V3D_PCTR12),
-	REGDEF(V3D_PCTRS12),
-	REGDEF(V3D_PCTR13),
-	REGDEF(V3D_PCTRS13),
-	REGDEF(V3D_PCTR14),
-	REGDEF(V3D_PCTRS14),
-	REGDEF(V3D_PCTR15),
-	REGDEF(V3D_PCTRS15),
+	REGDEF(V3D_PCTR(0)),
+	REGDEF(V3D_PCTRS(0)),
+	REGDEF(V3D_PCTR(1)),
+	REGDEF(V3D_PCTRS(1)),
+	REGDEF(V3D_PCTR(2)),
+	REGDEF(V3D_PCTRS(2)),
+	REGDEF(V3D_PCTR(3)),
+	REGDEF(V3D_PCTRS(3)),
+	REGDEF(V3D_PCTR(4)),
+	REGDEF(V3D_PCTRS(4)),
+	REGDEF(V3D_PCTR(5)),
+	REGDEF(V3D_PCTRS(5)),
+	REGDEF(V3D_PCTR(6)),
+	REGDEF(V3D_PCTRS(6)),
+	REGDEF(V3D_PCTR(7)),
+	REGDEF(V3D_PCTRS(7)),
+	REGDEF(V3D_PCTR(8)),
+	REGDEF(V3D_PCTRS(8)),
+	REGDEF(V3D_PCTR(9)),
+	REGDEF(V3D_PCTRS(9)),
+	REGDEF(V3D_PCTR(10)),
+	REGDEF(V3D_PCTRS(10)),
+	REGDEF(V3D_PCTR(11)),
+	REGDEF(V3D_PCTRS(11)),
+	REGDEF(V3D_PCTR(12)),
+	REGDEF(V3D_PCTRS(12)),
+	REGDEF(V3D_PCTR(13)),
+	REGDEF(V3D_PCTRS(13)),
+	REGDEF(V3D_PCTR(14)),
+	REGDEF(V3D_PCTRS(14)),
+	REGDEF(V3D_PCTR(15)),
+	REGDEF(V3D_PCTRS(15)),
 	REGDEF(V3D_DBGE),
 	REGDEF(V3D_FDBGO),
 	REGDEF(V3D_FDBGB),
diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
index 5720a0d4ac0a..355569a9b5cb 100644
--- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c
+++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c
@@ -518,6 +518,8 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev,
 
 	ret = wait_event_timeout(vgdev->resp_wq,
 				 atomic_read(&cache_ent->is_valid), 5 * HZ);
+	if (!ret)
+		return -EBUSY;
 
 	ptr = cache_ent->caps_cache;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index ead61015cd79..1107d6d03506 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -449,10 +449,9 @@ int vmw_du_primary_plane_atomic_check(struct drm_plane *plane,
 	if (state->crtc)
 		crtc_state = drm_atomic_get_new_crtc_state(state->state, state->crtc);
 
-	if (crtc_state && crtc_state->enable) {
-		clip.x2 = crtc_state->adjusted_mode.hdisplay;
-		clip.y2 = crtc_state->adjusted_mode.vdisplay;
-	}
+	if (crtc_state && crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	ret = drm_atomic_helper_check_plane_state(state, crtc_state, &clip,
 						  DRM_PLANE_HELPER_NO_SCALING,
diff --git a/drivers/gpu/drm/zte/zx_plane.c b/drivers/gpu/drm/zte/zx_plane.c
index 68fd2e2dc78a..8e1f34274e24 100644
--- a/drivers/gpu/drm/zte/zx_plane.c
+++ b/drivers/gpu/drm/zte/zx_plane.c
@@ -55,7 +55,7 @@ static int zx_vl_plane_atomic_check(struct drm_plane *plane,
 	struct drm_framebuffer *fb = plane_state->fb;
 	struct drm_crtc *crtc = plane_state->crtc;
 	struct drm_crtc_state *crtc_state;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 	int min_scale = FRAC_16_16(1, 8);
 	int max_scale = FRAC_16_16(8, 1);
 
@@ -75,10 +75,9 @@ static int zx_vl_plane_atomic_check(struct drm_plane *plane,
 	if (!plane_state->crtc)
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	return drm_atomic_helper_check_plane_state(plane_state, crtc_state,
 						   &clip, min_scale, max_scale,
@@ -292,7 +291,7 @@ static int zx_gl_plane_atomic_check(struct drm_plane *plane,
 	struct drm_framebuffer *fb = plane_state->fb;
 	struct drm_crtc *crtc = plane_state->crtc;
 	struct drm_crtc_state *crtc_state;
-	struct drm_rect clip;
+	struct drm_rect clip = {};
 
 	if (!crtc || !fb)
 		return 0;
@@ -310,10 +309,9 @@ static int zx_gl_plane_atomic_check(struct drm_plane *plane,
 	if (!plane_state->crtc)
 		return -EINVAL;
 
-	clip.x1 = 0;
-	clip.y1 = 0;
-	clip.x2 = crtc_state->adjusted_mode.hdisplay;
-	clip.y2 = crtc_state->adjusted_mode.vdisplay;
+	if (crtc_state->enable)
+		drm_mode_get_hv_timing(&crtc_state->mode,
+				       &clip.x2, &clip.y2);
 
 	return drm_atomic_helper_check_plane_state(plane_state, crtc_state,
 						   &clip,
diff --git a/include/drm/bridge/dw_mipi_dsi.h b/include/drm/bridge/dw_mipi_dsi.h
index 9b30fec302c8..d9c6d549f971 100644
--- a/include/drm/bridge/dw_mipi_dsi.h
+++ b/include/drm/bridge/dw_mipi_dsi.h
@@ -10,6 +10,8 @@
 #ifndef __DW_MIPI_DSI__
 #define __DW_MIPI_DSI__
 
+struct dw_mipi_dsi;
+
 struct dw_mipi_dsi_phy_ops {
 	int (*init)(void *priv_data);
 	int (*get_lane_mbps)(void *priv_data, struct drm_display_mode *mode,
@@ -29,11 +31,14 @@ struct dw_mipi_dsi_plat_data {
 	void *priv_data;
 };
 
-int dw_mipi_dsi_probe(struct platform_device *pdev,
-		      const struct dw_mipi_dsi_plat_data *plat_data);
-void dw_mipi_dsi_remove(struct platform_device *pdev);
-int dw_mipi_dsi_bind(struct platform_device *pdev, struct drm_encoder *encoder,
-		     const struct dw_mipi_dsi_plat_data *plat_data);
-void dw_mipi_dsi_unbind(struct device *dev);
+struct dw_mipi_dsi *dw_mipi_dsi_probe(struct platform_device *pdev,
+				      const struct dw_mipi_dsi_plat_data
+				      *plat_data);
+void dw_mipi_dsi_remove(struct dw_mipi_dsi *dsi);
+struct dw_mipi_dsi *dw_mipi_dsi_bind(struct platform_device *pdev,
+				     struct drm_encoder *encoder,
+				     const struct dw_mipi_dsi_plat_data
+				     *plat_data);
+void dw_mipi_dsi_unbind(struct dw_mipi_dsi *dsi);
 
 #endif /* __DW_MIPI_DSI__ */
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index 1c27526c499e..cf13842a6dbd 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -134,6 +134,15 @@ struct drm_crtc_commit {
 	 * &drm_pending_vblank_event pointer to clean up private events.
 	 */
 	struct drm_pending_vblank_event *event;
+
+	/**
+	 * @abort_completion:
+	 *
+	 * A flag that's set after drm_atomic_helper_setup_commit takes a second
+	 * reference for the completion of $drm_crtc_state.event. It's used by
+	 * the free code to remove the second reference if commit fails.
+	 */
+	bool abort_completion;
 };
 
 struct __drm_planes_state {
diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h
index 682d01ba920c..3270fec46979 100644
--- a/include/drm/drm_bridge.h
+++ b/include/drm/drm_bridge.h
@@ -29,6 +29,7 @@
 #include <drm/drm_modes.h>
 
 struct drm_bridge;
+struct drm_bridge_timings;
 struct drm_panel;
 
 /**
@@ -90,7 +91,7 @@ struct drm_bridge_funcs {
 	 *
 	 * drm_mode_status Enum
 	 */
-	enum drm_mode_status (*mode_valid)(struct drm_bridge *crtc,
+	enum drm_mode_status (*mode_valid)(struct drm_bridge *bridge,
 					   const struct drm_display_mode *mode);
 
 	/**
@@ -222,6 +223,35 @@ struct drm_bridge_funcs {
 	void (*enable)(struct drm_bridge *bridge);
 };
 
+/**
+ * struct drm_bridge_timings - timing information for the bridge
+ */
+struct drm_bridge_timings {
+	/**
+	 * @sampling_edge:
+	 *
+	 * Tells whether the bridge samples the digital input signal
+	 * from the display engine on the positive or negative edge of the
+	 * clock, this should reuse the DRM_BUS_FLAG_PIXDATA_[POS|NEG]EDGE
+	 * bitwise flags from the DRM connector (bit 2 and 3 valid).
+	 */
+	u32 sampling_edge;
+	/**
+	 * @setup_time_ps:
+	 *
+	 * Defines the time in picoseconds the input data lines must be
+	 * stable before the clock edge.
+	 */
+	u32 setup_time_ps;
+	/**
+	 * @hold_time_ps:
+	 *
+	 * Defines the time in picoseconds taken for the bridge to sample the
+	 * input signal after the clock edge.
+	 */
+	u32 hold_time_ps;
+};
+
 /**
  * struct drm_bridge - central DRM bridge control structure
  * @dev: DRM device this bridge belongs to
@@ -229,6 +259,8 @@ struct drm_bridge_funcs {
  * @next: the next bridge in the encoder chain
  * @of_node: device node pointer to the bridge
  * @list: to keep track of all added bridges
+ * @timings: the timing specification for the bridge, if any (may
+ * be NULL)
  * @funcs: control functions
  * @driver_private: pointer to the bridge driver's internal context
  */
@@ -240,6 +272,7 @@ struct drm_bridge {
 	struct device_node *of_node;
 #endif
 	struct list_head list;
+	const struct drm_bridge_timings *timings;
 
 	const struct drm_bridge_funcs *funcs;
 	void *driver_private;
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index beab0f0d0cfb..bfe1639df02d 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -38,6 +38,8 @@
 void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
 void drm_clflush_sg(struct sg_table *st);
 void drm_clflush_virt_range(void *addr, unsigned long length);
+u64 drm_get_max_iomem(void);
+
 
 static inline bool drm_arch_can_wc_memory(void)
 {
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index da58a428c8d7..768d9eda06cb 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -75,6 +75,7 @@
 #define DP_MAX_DOWNSPREAD                   0x003
 # define DP_MAX_DOWNSPREAD_0_5		    (1 << 0)
 # define DP_NO_AUX_HANDSHAKE_LINK_TRAINING  (1 << 6)
+# define DP_TPS4_SUPPORTED                  (1 << 7)
 
 #define DP_NORP                             0x004
 
@@ -334,6 +335,7 @@
 # define DP_LINK_BW_1_62		    0x06
 # define DP_LINK_BW_2_7			    0x0a
 # define DP_LINK_BW_5_4			    0x14    /* 1.2 */
+# define DP_LINK_BW_8_1			    0x1e    /* 1.4 */
 
 #define DP_LANE_COUNT_SET	            0x101
 # define DP_LANE_COUNT_MASK		    0x0f
@@ -344,7 +346,9 @@
 # define DP_TRAINING_PATTERN_1		    1
 # define DP_TRAINING_PATTERN_2		    2
 # define DP_TRAINING_PATTERN_3		    3	    /* 1.2 */
+# define DP_TRAINING_PATTERN_4              7       /* 1.4 */
 # define DP_TRAINING_PATTERN_MASK	    0x3
+# define DP_TRAINING_PATTERN_MASK_1_4	    0xf
 
 /* DPCD 1.1 only. For DPCD >= 1.2 see per-lane DP_LINK_QUAL_LANEn_SET */
 # define DP_LINK_QUAL_PATTERN_11_DISABLE    (0 << 2)
@@ -970,6 +974,20 @@ drm_dp_tps3_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 		dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED;
 }
 
+static inline bool
+drm_dp_tps4_supported(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	return dpcd[DP_DPCD_REV] >= 0x14 &&
+		dpcd[DP_MAX_DOWNSPREAD] & DP_TPS4_SUPPORTED;
+}
+
+static inline u8
+drm_dp_training_pattern_mask(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+{
+	return (dpcd[DP_DPCD_REV] >= 0x14) ? DP_TRAINING_PATTERN_MASK_1_4 :
+		DP_TRAINING_PATTERN_MASK;
+}
+
 static inline bool
 drm_dp_is_branch(const u8 dpcd[DP_RECEIVER_CAP_SIZE])
 {
diff --git a/include/drm/drm_fourcc.h b/include/drm/drm_fourcc.h
index 6942e84b6edd..3e86408dac9f 100644
--- a/include/drm/drm_fourcc.h
+++ b/include/drm/drm_fourcc.h
@@ -38,6 +38,7 @@ struct drm_mode_fb_cmd2;
  * @cpp: Number of bytes per pixel (per plane)
  * @hsub: Horizontal chroma subsampling factor
  * @vsub: Vertical chroma subsampling factor
+ * @has_alpha: Does the format embeds an alpha component?
  */
 struct drm_format_info {
 	u32 format;
@@ -46,6 +47,7 @@ struct drm_format_info {
 	u8 cpp[3];
 	u8 hsub;
 	u8 vsub;
+	bool has_alpha;
 };
 
 /**
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index 2cb6f02df64a..7569f22ffef6 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -36,6 +36,7 @@ struct drm_device;
 struct drm_atomic_state;
 struct drm_mode_fb_cmd2;
 struct drm_format_info;
+struct drm_display_mode;
 
 /**
  * struct drm_mode_config_funcs - basic driver provided mode setting functions
@@ -101,6 +102,17 @@ struct drm_mode_config_funcs {
 	 */
 	void (*output_poll_changed)(struct drm_device *dev);
 
+	/**
+	 * @mode_valid:
+	 *
+	 * Device specific validation of display modes. Can be used to reject
+	 * modes that can never be supported. Only device wide constraints can
+	 * be checked here. crtc/encoder/bridge/connector specific constraints
+	 * should be checked in the .mode_valid() hook for each specific object.
+	 */
+	enum drm_mode_status (*mode_valid)(struct drm_device *dev,
+					   const struct drm_display_mode *mode);
+
 	/**
 	 * @atomic_check:
 	 *
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index 9f3421c8efcd..0d310beae6af 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -131,9 +131,6 @@ enum drm_mode_status {
 	MODE_ERROR = -1
 };
 
-#define DRM_MODE_TYPE_CLOCK_CRTC_C (DRM_MODE_TYPE_CLOCK_C | \
-				    DRM_MODE_TYPE_CRTC_C)
-
 #define DRM_MODE(nm, t, c, hd, hss, hse, ht, hsk, vd, vss, vse, vt, vs, f) \
 	.name = nm, .status = 0, .type = (t), .clock = (c), \
 	.hdisplay = (hd), .hsync_start = (hss), .hsync_end = (hse), \
@@ -245,26 +242,25 @@ struct drm_display_mode {
 	 * A bitmask of flags, mostly about the source of a mode. Possible flags
 	 * are:
 	 *
-	 *  - DRM_MODE_TYPE_BUILTIN: Meant for hard-coded modes, effectively
-	 *    unused.
 	 *  - DRM_MODE_TYPE_PREFERRED: Preferred mode, usually the native
 	 *    resolution of an LCD panel. There should only be one preferred
 	 *    mode per connector at any given time.
 	 *  - DRM_MODE_TYPE_DRIVER: Mode created by the driver, which is all of
 	 *    them really. Drivers must set this bit for all modes they create
 	 *    and expose to userspace.
+	 *  - DRM_MODE_TYPE_USERDEF: Mode defined via kernel command line
 	 *
 	 * Plus a big list of flags which shouldn't be used at all, but are
-	 * still around since these flags are also used in the userspace ABI:
+	 * still around since these flags are also used in the userspace ABI.
+	 * We no longer accept modes with these types though:
 	 *
+	 *  - DRM_MODE_TYPE_BUILTIN: Meant for hard-coded modes, unused.
+	 *    Use DRM_MODE_TYPE_DRIVER instead.
 	 *  - DRM_MODE_TYPE_DEFAULT: Again a leftover, use
 	 *    DRM_MODE_TYPE_PREFERRED instead.
 	 *  - DRM_MODE_TYPE_CLOCK_C and DRM_MODE_TYPE_CRTC_C: Define leftovers
 	 *    which are stuck around for hysterical raisins only. No one has an
 	 *    idea what they were meant for. Don't use.
-	 *  - DRM_MODE_TYPE_USERDEF: Mode defined by userspace, again a vestige
-	 *    from older kms designs where userspace had to first add a custom
-	 *    mode to the kernel's mode list before it could use it. Don't use.
 	 */
 	unsigned int type;
 
@@ -299,8 +295,8 @@ struct drm_display_mode {
 	 *  - DRM_MODE_FLAG_PCSYNC: composite sync is active high.
 	 *  - DRM_MODE_FLAG_NCSYNC: composite sync is active low.
 	 *  - DRM_MODE_FLAG_HSKEW: hskew provided (not used?).
-	 *  - DRM_MODE_FLAG_BCAST: not used?
-	 *  - DRM_MODE_FLAG_PIXMUX: not used?
+	 *  - DRM_MODE_FLAG_BCAST: <deprecated>
+	 *  - DRM_MODE_FLAG_PIXMUX: <deprecated>
 	 *  - DRM_MODE_FLAG_DBLCLK: double-clocked mode.
 	 *  - DRM_MODE_FLAG_CLKDIV2: half-clocked mode.
 	 *
@@ -448,7 +444,8 @@ struct drm_display_mode *drm_mode_create(struct drm_device *dev);
 void drm_mode_destroy(struct drm_device *dev, struct drm_display_mode *mode);
 void drm_mode_convert_to_umode(struct drm_mode_modeinfo *out,
 			       const struct drm_display_mode *in);
-int drm_mode_convert_umode(struct drm_display_mode *out,
+int drm_mode_convert_umode(struct drm_device *dev,
+			   struct drm_display_mode *out,
 			   const struct drm_mode_modeinfo *in);
 void drm_mode_probed_add(struct drm_connector *connector, struct drm_display_mode *mode);
 void drm_mode_debug_printmodeline(const struct drm_display_mode *mode);
@@ -501,7 +498,8 @@ bool drm_mode_equal_no_clocks_no_stereo(const struct drm_display_mode *mode1,
 					const struct drm_display_mode *mode2);
 
 /* for use by the crtc helper probe functions */
-enum drm_mode_status drm_mode_validate_basic(const struct drm_display_mode *mode);
+enum drm_mode_status drm_mode_validate_driver(struct drm_device *dev,
+					      const struct drm_display_mode *mode);
 enum drm_mode_status drm_mode_validate_size(const struct drm_display_mode *mode,
 					    int maxX, int maxY);
 enum drm_mode_status
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index 9cd9e36f77b5..4d5f5d6cf6a6 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -54,6 +54,9 @@ struct device;
 
 struct dma_buf_export_info;
 struct dma_buf;
+struct dma_buf_attachment;
+
+enum dma_data_direction;
 
 struct drm_device;
 struct drm_gem_object;
@@ -79,6 +82,25 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
+int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev,
+		       struct dma_buf_attachment *attach);
+void drm_gem_map_detach(struct dma_buf *dma_buf,
+			struct dma_buf_attachment *attach);
+struct sg_table *drm_gem_map_dma_buf(struct dma_buf_attachment *attach,
+				     enum dma_data_direction dir);
+void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
+			   struct sg_table *sgt,
+			   enum dma_data_direction dir);
+void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf);
+void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr);
+void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
+				 unsigned long page_num);
+void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
+				  unsigned long page_num, void *addr);
+void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num);
+void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num,
+			   void *addr);
+int drm_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *vma);
 
 int drm_prime_sg_to_page_addr_arrays(struct sg_table *sgt, struct page **pages,
 				     dma_addr_t *addrs, int max_pages);
diff --git a/include/drm/tinydrm/ili9341.h b/include/drm/tinydrm/ili9341.h
deleted file mode 100644
index 807a09f43cad..000000000000
--- a/include/drm/tinydrm/ili9341.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * ILI9341 LCD controller
- *
- * Copyright 2016 Noralf Trønnes
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef __LINUX_ILI9341_H
-#define __LINUX_ILI9341_H
-
-#define ILI9341_FRMCTR1    0xb1
-#define ILI9341_FRMCTR2    0xb2
-#define ILI9341_FRMCTR3    0xb3
-#define ILI9341_INVTR      0xb4
-#define ILI9341_PRCTR      0xb5
-#define ILI9341_DISCTRL    0xb6
-#define ILI9341_ETMOD      0xb7
-
-#define ILI9341_PWCTRL1    0xc0
-#define ILI9341_PWCTRL2    0xc1
-#define ILI9341_VMCTRL1    0xc5
-#define ILI9341_VMCTRL2    0xc7
-#define ILI9341_PWCTRLA    0xcb
-#define ILI9341_PWCTRLB    0xcf
-
-#define ILI9341_RDID1      0xda
-#define ILI9341_RDID2      0xdb
-#define ILI9341_RDID3      0xdc
-#define ILI9341_RDID4      0xd3
-
-#define ILI9341_PGAMCTRL   0xe0
-#define ILI9341_NGAMCTRL   0xe1
-#define ILI9341_DGAMCTRL1  0xe2
-#define ILI9341_DGAMCTRL2  0xe3
-#define ILI9341_DTCTRLA    0xe8
-#define ILI9341_DTCTRLB    0xea
-#define ILI9341_PWRSEQ     0xed
-
-#define ILI9341_EN3GAM     0xf2
-#define ILI9341_IFCTRL     0xf6
-#define ILI9341_PUMPCTRL   0xf7
-
-#define ILI9341_MADCTL_MH  BIT(2)
-#define ILI9341_MADCTL_BGR BIT(3)
-#define ILI9341_MADCTL_ML  BIT(4)
-#define ILI9341_MADCTL_MV  BIT(5)
-#define ILI9341_MADCTL_MX  BIT(6)
-#define ILI9341_MADCTL_MY  BIT(7)
-
-#endif /* __LINUX_ILI9341_H */
diff --git a/include/drm/tinydrm/mipi-dbi.h b/include/drm/tinydrm/mipi-dbi.h
index 5d0e82b36eaf..44e824af2ef6 100644
--- a/include/drm/tinydrm/mipi-dbi.h
+++ b/include/drm/tinydrm/mipi-dbi.h
@@ -67,11 +67,12 @@ int mipi_dbi_init(struct device *dev, struct mipi_dbi *mipi,
 		  const struct drm_simple_display_pipe_funcs *pipe_funcs,
 		  struct drm_driver *driver,
 		  const struct drm_display_mode *mode, unsigned int rotation);
-void mipi_dbi_pipe_enable(struct drm_simple_display_pipe *pipe,
-			  struct drm_crtc_state *crtc_state);
+void mipi_dbi_enable_flush(struct mipi_dbi *mipi);
 void mipi_dbi_pipe_disable(struct drm_simple_display_pipe *pipe);
 void mipi_dbi_hw_reset(struct mipi_dbi *mipi);
 bool mipi_dbi_display_is_on(struct mipi_dbi *mipi);
+int mipi_dbi_poweron_reset(struct mipi_dbi *mipi);
+int mipi_dbi_poweron_conditional_reset(struct mipi_dbi *mipi);
 u32 mipi_dbi_spi_cmd_max_speed(struct spi_device *spi, size_t len);
 
 int mipi_dbi_command_read(struct mipi_dbi *mipi, u8 cmd, u8 *val);
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 5597a87154e5..eb9b68c7c218 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -38,14 +38,18 @@ extern "C" {
 #define DRM_DISPLAY_MODE_LEN	32
 #define DRM_PROP_NAME_LEN	32
 
-#define DRM_MODE_TYPE_BUILTIN	(1<<0)
-#define DRM_MODE_TYPE_CLOCK_C	((1<<1) | DRM_MODE_TYPE_BUILTIN)
-#define DRM_MODE_TYPE_CRTC_C	((1<<2) | DRM_MODE_TYPE_BUILTIN)
+#define DRM_MODE_TYPE_BUILTIN	(1<<0) /* deprecated */
+#define DRM_MODE_TYPE_CLOCK_C	((1<<1) | DRM_MODE_TYPE_BUILTIN) /* deprecated */
+#define DRM_MODE_TYPE_CRTC_C	((1<<2) | DRM_MODE_TYPE_BUILTIN) /* deprecated */
 #define DRM_MODE_TYPE_PREFERRED	(1<<3)
-#define DRM_MODE_TYPE_DEFAULT	(1<<4)
+#define DRM_MODE_TYPE_DEFAULT	(1<<4) /* deprecated */
 #define DRM_MODE_TYPE_USERDEF	(1<<5)
 #define DRM_MODE_TYPE_DRIVER	(1<<6)
 
+#define DRM_MODE_TYPE_ALL	(DRM_MODE_TYPE_PREFERRED |	\
+				 DRM_MODE_TYPE_USERDEF |	\
+				 DRM_MODE_TYPE_DRIVER)
+
 /* Video mode flags */
 /* bit compatible with the xrandr RR_ definitions (bits 0-13)
  *
@@ -66,8 +70,8 @@ extern "C" {
 #define DRM_MODE_FLAG_PCSYNC			(1<<7)
 #define DRM_MODE_FLAG_NCSYNC			(1<<8)
 #define DRM_MODE_FLAG_HSKEW			(1<<9) /* hskew provided */
-#define DRM_MODE_FLAG_BCAST			(1<<10)
-#define DRM_MODE_FLAG_PIXMUX			(1<<11)
+#define DRM_MODE_FLAG_BCAST			(1<<10) /* deprecated */
+#define DRM_MODE_FLAG_PIXMUX			(1<<11) /* deprecated */
 #define DRM_MODE_FLAG_DBLCLK			(1<<12)
 #define DRM_MODE_FLAG_CLKDIV2			(1<<13)
  /*
@@ -99,6 +103,20 @@ extern "C" {
 #define  DRM_MODE_FLAG_PIC_AR_16_9 \
 			(DRM_MODE_PICTURE_ASPECT_16_9<<19)
 
+#define  DRM_MODE_FLAG_ALL	(DRM_MODE_FLAG_PHSYNC |		\
+				 DRM_MODE_FLAG_NHSYNC |		\
+				 DRM_MODE_FLAG_PVSYNC |		\
+				 DRM_MODE_FLAG_NVSYNC |		\
+				 DRM_MODE_FLAG_INTERLACE |	\
+				 DRM_MODE_FLAG_DBLSCAN |	\
+				 DRM_MODE_FLAG_CSYNC |		\
+				 DRM_MODE_FLAG_PCSYNC |		\
+				 DRM_MODE_FLAG_NCSYNC |		\
+				 DRM_MODE_FLAG_HSKEW |		\
+				 DRM_MODE_FLAG_DBLCLK |		\
+				 DRM_MODE_FLAG_CLKDIV2 |	\
+				 DRM_MODE_FLAG_3D_MASK)
+
 /* DPMS flags */
 /* bit compatible with the xorg definitions. */
 #define DRM_MODE_DPMS_ON	0
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
index 52263b575bdc..b95a0e11cb07 100644
--- a/include/uapi/drm/vc4_drm.h
+++ b/include/uapi/drm/vc4_drm.h
@@ -42,6 +42,9 @@ extern "C" {
 #define DRM_VC4_GET_TILING                        0x09
 #define DRM_VC4_LABEL_BO                          0x0a
 #define DRM_VC4_GEM_MADVISE                       0x0b
+#define DRM_VC4_PERFMON_CREATE                    0x0c
+#define DRM_VC4_PERFMON_DESTROY                   0x0d
+#define DRM_VC4_PERFMON_GET_VALUES                0x0e
 
 #define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
 #define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
@@ -55,6 +58,9 @@ extern "C" {
 #define DRM_IOCTL_VC4_GET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_TILING, struct drm_vc4_get_tiling)
 #define DRM_IOCTL_VC4_LABEL_BO            DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_LABEL_BO, struct drm_vc4_label_bo)
 #define DRM_IOCTL_VC4_GEM_MADVISE         DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GEM_MADVISE, struct drm_vc4_gem_madvise)
+#define DRM_IOCTL_VC4_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_CREATE, struct drm_vc4_perfmon_create)
+#define DRM_IOCTL_VC4_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_DESTROY, struct drm_vc4_perfmon_destroy)
+#define DRM_IOCTL_VC4_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_GET_VALUES, struct drm_vc4_perfmon_get_values)
 
 struct drm_vc4_submit_rcl_surface {
 	__u32 hindex; /* Handle index, or ~0 if not present. */
@@ -173,6 +179,15 @@ struct drm_vc4_submit_cl {
 	 * wait ioctl).
 	 */
 	__u64 seqno;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmonid;
+
+	/* Unused field to align this struct on 64 bits. Must be set to 0.
+	 * If one ever needs to add an u32 field to this struct, this field
+	 * can be used.
+	 */
+	__u32 pad2;
 };
 
 /**
@@ -308,6 +323,7 @@ struct drm_vc4_get_hang_state {
 #define DRM_VC4_PARAM_SUPPORTS_THREADED_FS	5
 #define DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER	6
 #define DRM_VC4_PARAM_SUPPORTS_MADVISE		7
+#define DRM_VC4_PARAM_SUPPORTS_PERFMON		8
 
 struct drm_vc4_get_param {
 	__u32 param;
@@ -352,6 +368,66 @@ struct drm_vc4_gem_madvise {
 	__u32 pad;
 };
 
+enum {
+	VC4_PERFCNT_FEP_VALID_PRIMS_NO_RENDER,
+	VC4_PERFCNT_FEP_VALID_PRIMS_RENDER,
+	VC4_PERFCNT_FEP_CLIPPED_QUADS,
+	VC4_PERFCNT_FEP_VALID_QUADS,
+	VC4_PERFCNT_TLB_QUADS_NOT_PASSING_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_NOT_PASSING_Z_AND_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_PASSING_Z_AND_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_ZERO_COVERAGE,
+	VC4_PERFCNT_TLB_QUADS_NON_ZERO_COVERAGE,
+	VC4_PERFCNT_TLB_QUADS_WRITTEN_TO_COLOR_BUF,
+	VC4_PERFCNT_PLB_PRIMS_OUTSIDE_VIEWPORT,
+	VC4_PERFCNT_PLB_PRIMS_NEED_CLIPPING,
+	VC4_PERFCNT_PSE_PRIMS_REVERSED,
+	VC4_PERFCNT_QPU_TOTAL_IDLE_CYCLES,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_VERTEX_COORD_SHADING,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_FRAGMENT_SHADING,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_EXEC_VALID_INST,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_TMUS,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_SCOREBOARD,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_VARYINGS,
+	VC4_PERFCNT_QPU_TOTAL_INST_CACHE_HIT,
+	VC4_PERFCNT_QPU_TOTAL_INST_CACHE_MISS,
+	VC4_PERFCNT_QPU_TOTAL_UNIFORM_CACHE_HIT,
+	VC4_PERFCNT_QPU_TOTAL_UNIFORM_CACHE_MISS,
+	VC4_PERFCNT_TMU_TOTAL_TEXT_QUADS_PROCESSED,
+	VC4_PERFCNT_TMU_TOTAL_TEXT_CACHE_MISS,
+	VC4_PERFCNT_VPM_TOTAL_CLK_CYCLES_VDW_STALLED,
+	VC4_PERFCNT_VPM_TOTAL_CLK_CYCLES_VCD_STALLED,
+	VC4_PERFCNT_L2C_TOTAL_L2_CACHE_HIT,
+	VC4_PERFCNT_L2C_TOTAL_L2_CACHE_MISS,
+	VC4_PERFCNT_NUM_EVENTS,
+};
+
+#define DRM_VC4_MAX_PERF_COUNTERS	16
+
+struct drm_vc4_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 events[DRM_VC4_MAX_PERF_COUNTERS];
+};
+
+struct drm_vc4_perfmon_destroy {
+	__u32 id;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of ncounters u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed  (probably by blocking on the seqno returned by the
+ * last exec that used the perfmon).
+ */
+struct drm_vc4_perfmon_get_values {
+	__u32 id;
+	__u64 values_ptr;
+};
+
 #if defined(__cplusplus)
 }
 #endif