Merge tag 'drm-next-du-20170803' of git://linuxtv.org/pinchartl/media into drm-next

rcar-du updates, contains vsp1 updates as well.

* tag 'drm-next-du-20170803' of git://linuxtv.org/pinchartl/media: (24 commits)
  drm: rcar-du: Use new iterator macros
  drm: rcar-du: Repair vblank for DRM page flips using the VSP
  drm: rcar-du: Fix race condition when disabling planes at CRTC stop
  drm: rcar-du: Wait for flip completion instead of vblank in commit tail
  drm: rcar-du: Use the VBK interrupt for vblank events
  drm: rcar-du: Add HDMI outputs to R8A7796 device description
  drm: rcar-du: Remove an unneeded NULL check
  drm: rcar-du: Setup planes before enabling CRTC to avoid flicker
  drm: rcar-du: Configure DPAD0 routing through last group on Gen3
  drm: rcar-du: Restrict DPLL duty cycle workaround to H3 ES1.x
  drm: rcar-du: Support multiple sources from the same VSP
  drm: rcar-du: Fix comments to comply with the kernel coding style
  drm: rcar-du: Use of_graph_get_remote_endpoint()
  v4l: vsp1: Add support for header display lists in continuous mode
  v4l: vsp1: Add support for multiple DRM pipelines
  v4l: vsp1: Add support for multiple LIF instances
  v4l: vsp1: Add support for new VSP2-BS, VSP2-DL and VSP2-D instances
  v4l: vsp1: Add support for the BRS entity
  v4l: vsp1: Add pipe index argument to the VSP-DU API
  v4l: vsp1: Don't create links for DRM pipeline
  ...

28 files changed, 942 insertions, 536 deletions

diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
index f131fc68cc46..301ea1a8018e 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c
@@ -13,6 +13,7 @@
 
 #include <linux/clk.h>
 #include <linux/mutex.h>
+#include <linux/sys_soc.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
@@ -129,10 +130,8 @@ static void rcar_du_dpll_divider(struct rcar_du_crtc *rcrtc,
 			for (fdpll = 1; fdpll < 32; fdpll++) {
 				unsigned long output;
 
-				/* 1/2 (FRQSEL=1) for duty rate 50% */
 				output = input * (n + 1) / (m + 1)
-				       / (fdpll + 1) / 2;
-
+				       / (fdpll + 1);
 				if (output >= 400000000)
 					continue;
 
@@ -158,6 +157,11 @@ done:
 		 best_diff);
 }
 
+static const struct soc_device_attribute rcar_du_r8a7795_es1[] = {
+	{ .soc_id = "r8a7795", .revision = "ES1.*" },
+	{ /* sentinel */ }
+};
+
 static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 {
 	const struct drm_display_mode *mode = &rcrtc->crtc.state->adjusted_mode;
@@ -168,7 +172,8 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 	u32 escr;
 	u32 div;
 
-	/* Compute the clock divisor and select the internal or external dot
+	/*
+	 * Compute the clock divisor and select the internal or external dot
 	 * clock based on the requested frequency.
 	 */
 	clk = clk_get_rate(rcrtc->clock);
@@ -185,7 +190,20 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 
 		extclk = clk_get_rate(rcrtc->extclock);
 		if (rcdu->info->dpll_ch & (1 << rcrtc->index)) {
-			rcar_du_dpll_divider(rcrtc, &dpll, extclk, mode_clock);
+			unsigned long target = mode_clock;
+
+			/*
+			 * The H3 ES1.x exhibits dot clock duty cycle stability
+			 * issues. We can work around them by configuring the
+			 * DPLL to twice the desired frequency, coupled with a
+			 * /2 post-divider. This isn't needed on other SoCs and
+			 * breaks HDMI output on M3-W for a currently unknown
+			 * reason, so restrict the workaround to H3 ES1.x.
+			 */
+			if (soc_device_match(rcar_du_r8a7795_es1))
+				target *= 2;
+
+			rcar_du_dpll_divider(rcrtc, &dpll, extclk, target);
 			extclk = dpll.output;
 		}
 
@@ -197,8 +215,6 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 
 		if (abs((long)extrate - (long)mode_clock) <
 		    abs((long)rate - (long)mode_clock)) {
-			dev_dbg(rcrtc->group->dev->dev,
-				"crtc%u: using external clock\n", rcrtc->index);
 
 			if (rcdu->info->dpll_ch & (1 << rcrtc->index)) {
 				u32 dpllcr = DPLLCR_CODE | DPLLCR_CLKE
@@ -215,12 +231,14 @@ static void rcar_du_crtc_set_display_timing(struct rcar_du_crtc *rcrtc)
 
 				rcar_du_group_write(rcrtc->group, DPLLCR,
 						    dpllcr);
-
-				escr = ESCR_DCLKSEL_DCLKIN | 1;
-			} else {
-				escr = ESCR_DCLKSEL_DCLKIN | extdiv;
 			}
+
+			escr = ESCR_DCLKSEL_DCLKIN | extdiv;
 		}
+
+		dev_dbg(rcrtc->group->dev->dev,
+			"mode clock %lu extrate %lu rate %lu ESCR 0x%08x\n",
+			mode_clock, extrate, rate, escr);
 	}
 
 	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? ESCR2 : ESCR,
@@ -261,12 +279,14 @@ void rcar_du_crtc_route_output(struct drm_crtc *crtc,
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 	struct rcar_du_device *rcdu = rcrtc->group->dev;
 
-	/* Store the route from the CRTC output to the DU output. The DU will be
+	/*
+	 * Store the route from the CRTC output to the DU output. The DU will be
 	 * configured when starting the CRTC.
 	 */
 	rcrtc->outputs |= BIT(output);
 
-	/* Store RGB routing to DPAD0, the hardware will be configured when
+	/*
+	 * Store RGB routing to DPAD0, the hardware will be configured when
 	 * starting the CRTC.
 	 */
 	if (output == RCAR_DU_OUTPUT_DPAD0)
@@ -342,7 +362,8 @@ static void rcar_du_crtc_update_planes(struct rcar_du_crtc *rcrtc)
 		}
 	}
 
-	/* Update the planes to display timing and dot clock generator
+	/*
+	 * Update the planes to display timing and dot clock generator
 	 * associations.
 	 *
 	 * Updating the DPTSR register requires restarting the CRTC group,
@@ -431,14 +452,8 @@ static void rcar_du_crtc_wait_page_flip(struct rcar_du_crtc *rcrtc)
  * Start/Stop and Suspend/Resume
  */
 
-static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
+static void rcar_du_crtc_setup(struct rcar_du_crtc *rcrtc)
 {
-	struct drm_crtc *crtc = &rcrtc->crtc;
-	bool interlaced;
-
-	if (rcrtc->started)
-		return;
-
 	/* Set display off and background to black */
 	rcar_du_crtc_write(rcrtc, DOOR, DOOR_RGB(0, 0, 0));
 	rcar_du_crtc_write(rcrtc, BPOR, BPOR_RGB(0, 0, 0));
@@ -450,7 +465,20 @@ static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
 	/* Start with all planes disabled. */
 	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0);
 
-	/* Select master sync mode. This enables display operation in master
+	/* Enable the VSP compositor. */
+	if (rcar_du_has(rcrtc->group->dev, RCAR_DU_FEATURE_VSP1_SOURCE))
+		rcar_du_vsp_enable(rcrtc);
+
+	/* Turn vertical blanking interrupt reporting on. */
+	drm_crtc_vblank_on(&rcrtc->crtc);
+}
+
+static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
+{
+	bool interlaced;
+
+	/*
+	 * Select master sync mode. This enables display operation in master
 	 * sync mode (with the HSYNC and VSYNC signals configured as outputs and
 	 * actively driven).
 	 */
@@ -460,38 +488,56 @@ static void rcar_du_crtc_start(struct rcar_du_crtc *rcrtc)
 			     DSYSR_TVM_MASTER);
 
 	rcar_du_group_start_stop(rcrtc->group, true);
+}
 
-	/* Enable the VSP compositor. */
-	if (rcar_du_has(rcrtc->group->dev, RCAR_DU_FEATURE_VSP1_SOURCE))
-		rcar_du_vsp_enable(rcrtc);
+static void rcar_du_crtc_disable_planes(struct rcar_du_crtc *rcrtc)
+{
+	struct rcar_du_device *rcdu = rcrtc->group->dev;
+	struct drm_crtc *crtc = &rcrtc->crtc;
+	u32 status;
 
-	/* Turn vertical blanking interrupt reporting back on. */
-	drm_crtc_vblank_on(crtc);
+	/* Make sure vblank interrupts are enabled. */
+	drm_crtc_vblank_get(crtc);
 
-	rcrtc->started = true;
+	/*
+	 * Disable planes and calculate how many vertical blanking interrupts we
+	 * have to wait for. If a vertical blanking interrupt has been triggered
+	 * but not processed yet, we don't know whether it occurred before or
+	 * after the planes got disabled. We thus have to wait for two vblank
+	 * interrupts in that case.
+	 */
+	spin_lock_irq(&rcrtc->vblank_lock);
+	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0);
+	status = rcar_du_crtc_read(rcrtc, DSSR);
+	rcrtc->vblank_count = status & DSSR_VBK ? 2 : 1;
+	spin_unlock_irq(&rcrtc->vblank_lock);
+
+	if (!wait_event_timeout(rcrtc->vblank_wait, rcrtc->vblank_count == 0,
+				msecs_to_jiffies(100)))
+		dev_warn(rcdu->dev, "vertical blanking timeout\n");
+
+	drm_crtc_vblank_put(crtc);
 }
 
 static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc)
 {
 	struct drm_crtc *crtc = &rcrtc->crtc;
 
-	if (!rcrtc->started)
-		return;
-
-	/* Disable all planes and wait for the change to take effect. This is
-	 * required as the DSnPR registers are updated on vblank, and no vblank
-	 * will occur once the CRTC is stopped. Disabling planes when starting
-	 * the CRTC thus wouldn't be enough as it would start scanning out
-	 * immediately from old frame buffers until the next vblank.
+	/*
+	 * Disable all planes and wait for the change to take effect. This is
+	 * required as the plane enable registers are updated on vblank, and no
+	 * vblank will occur once the CRTC is stopped. Disabling planes when
+	 * starting the CRTC thus wouldn't be enough as it would start scanning
+	 * out immediately from old frame buffers until the next vblank.
 	 *
 	 * This increases the CRTC stop delay, especially when multiple CRTCs
 	 * are stopped in one operation as we now wait for one vblank per CRTC.
 	 * Whether this can be improved needs to be researched.
 	 */
-	rcar_du_group_write(rcrtc->group, rcrtc->index % 2 ? DS2PR : DS1PR, 0);
-	drm_crtc_wait_one_vblank(crtc);
+	rcar_du_crtc_disable_planes(rcrtc);
 
-	/* Disable vertical blanking interrupt reporting. We first need to wait
+	/*
+	 * Disable vertical blanking interrupt reporting. We first need to wait
 	 * for page flip completion before stopping the CRTC as userspace
 	 * expects page flips to eventually complete.
 	 */
@@ -502,14 +548,13 @@ static void rcar_du_crtc_stop(struct rcar_du_crtc *rcrtc)
 	if (rcar_du_has(rcrtc->group->dev, RCAR_DU_FEATURE_VSP1_SOURCE))
 		rcar_du_vsp_disable(rcrtc);
 
-	/* Select switch sync mode. This stops display operation and configures
+	/*
+	 * Select switch sync mode. This stops display operation and configures
 	 * the HSYNC and VSYNC signals as inputs.
 	 */
 	rcar_du_crtc_clr_set(rcrtc, DSYSR, DSYSR_TVM_MASK, DSYSR_TVM_SWITCH);
 
 	rcar_du_group_start_stop(rcrtc->group, false);
-
-	rcrtc->started = false;
 }
 
 void rcar_du_crtc_suspend(struct rcar_du_crtc *rcrtc)
@@ -529,12 +574,10 @@ void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc)
 		return;
 
 	rcar_du_crtc_get(rcrtc);
-	rcar_du_crtc_start(rcrtc);
+	rcar_du_crtc_setup(rcrtc);
 
 	/* Commit the planes state. */
-	if (rcar_du_has(rcrtc->group->dev, RCAR_DU_FEATURE_VSP1_SOURCE)) {
-		rcar_du_vsp_enable(rcrtc);
-	} else {
+	if (!rcar_du_has(rcrtc->group->dev, RCAR_DU_FEATURE_VSP1_SOURCE)) {
 		for (i = 0; i < rcrtc->group->num_planes; ++i) {
 			struct rcar_du_plane *plane = &rcrtc->group->planes[i];
 
@@ -546,6 +589,7 @@ void rcar_du_crtc_resume(struct rcar_du_crtc *rcrtc)
 	}
 
 	rcar_du_crtc_update_planes(rcrtc);
+	rcar_du_crtc_start(rcrtc);
 }
 
 /* -----------------------------------------------------------------------------
@@ -557,7 +601,16 @@ static void rcar_du_crtc_atomic_enable(struct drm_crtc *crtc,
 {
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 
-	rcar_du_crtc_get(rcrtc);
+	/*
+	 * If the CRTC has already been setup by the .atomic_begin() handler we
+	 * can skip the setup stage.
+	 */
+	if (!rcrtc->initialized) {
+		rcar_du_crtc_get(rcrtc);
+		rcar_du_crtc_setup(rcrtc);
+		rcrtc->initialized = true;
+	}
+
 	rcar_du_crtc_start(rcrtc);
 }
 
@@ -576,6 +629,7 @@ static void rcar_du_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 	spin_unlock_irq(&crtc->dev->event_lock);
 
+	rcrtc->initialized = false;
 	rcrtc->outputs = 0;
 }
 
@@ -584,6 +638,19 @@ static void rcar_du_crtc_atomic_begin(struct drm_crtc *crtc,
 {
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 
+	WARN_ON(!crtc->state->enable);
+
+	/*
+	 * If a mode set is in progress we can be called with the CRTC disabled.
+	 * We then need to first setup the CRTC in order to configure planes.
+	 * The .atomic_enable() handler will notice and skip the CRTC setup.
+	 */
+	if (!rcrtc->initialized) {
+		rcar_du_crtc_get(rcrtc);
+		rcar_du_crtc_setup(rcrtc);
+		rcrtc->initialized = true;
+	}
+
 	if (rcar_du_has(rcrtc->group->dev, RCAR_DU_FEATURE_VSP1_SOURCE))
 		rcar_du_vsp_atomic_begin(rcrtc);
 }
@@ -623,6 +690,7 @@ static int rcar_du_crtc_enable_vblank(struct drm_crtc *crtc)
 
 	rcar_du_crtc_write(rcrtc, DSRCR, DSRCR_VBCL);
 	rcar_du_crtc_set(rcrtc, DIER, DIER_VBE);
+	rcrtc->vblank_enable = true;
 
 	return 0;
 }
@@ -632,6 +700,7 @@ static void rcar_du_crtc_disable_vblank(struct drm_crtc *crtc)
 	struct rcar_du_crtc *rcrtc = to_rcar_crtc(crtc);
 
 	rcar_du_crtc_clr(rcrtc, DIER, DIER_VBE);
+	rcrtc->vblank_enable = false;
 }
 
 static const struct drm_crtc_funcs crtc_funcs = {
@@ -656,14 +725,30 @@ static irqreturn_t rcar_du_crtc_irq(int irq, void *arg)
 	irqreturn_t ret = IRQ_NONE;
 	u32 status;
 
+	spin_lock(&rcrtc->vblank_lock);
+
 	status = rcar_du_crtc_read(rcrtc, DSSR);
 	rcar_du_crtc_write(rcrtc, DSRCR, status & DSRCR_MASK);
 
-	if (status & DSSR_FRM) {
-		drm_crtc_handle_vblank(&rcrtc->crtc);
+	if (status & DSSR_VBK) {
+		/*
+		 * Wake up the vblank wait if the counter reaches 0. This must
+		 * be protected by the vblank_lock to avoid races in
+		 * rcar_du_crtc_disable_planes().
+		 */
+		if (rcrtc->vblank_count) {
+			if (--rcrtc->vblank_count == 0)
+				wake_up(&rcrtc->vblank_wait);
+		}
+	}
 
-		if (rcdu->info->gen < 3)
+	spin_unlock(&rcrtc->vblank_lock);
+
+	if (status & DSSR_VBK) {
+		if (rcdu->info->gen < 3) {
+			drm_crtc_handle_vblank(&rcrtc->crtc);
 			rcar_du_crtc_finish_page_flip(rcrtc);
+		}
 
 		ret = IRQ_HANDLED;
 	}
@@ -717,13 +802,15 @@ int rcar_du_crtc_create(struct rcar_du_group *rgrp, unsigned int index)
 	}
 
 	init_waitqueue_head(&rcrtc->flip_wait);
+	init_waitqueue_head(&rcrtc->vblank_wait);
+	spin_lock_init(&rcrtc->vblank_lock);
 
 	rcrtc->group = rgrp;
 	rcrtc->mmio_offset = mmio_offsets[index];
 	rcrtc->index = index;
 
 	if (rcar_du_has(rcdu, RCAR_DU_FEATURE_VSP1_SOURCE))
-		primary = &rcrtc->vsp->planes[0].plane;
+		primary = &rcrtc->vsp->planes[rcrtc->vsp_pipe].plane;
 	else
 		primary = &rgrp->planes[index % 2].plane;
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
index b199ed5adf36..fdc2bf99bda1 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
+++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.h
@@ -15,6 +15,7 @@
 #define __RCAR_DU_CRTC_H__
 
 #include <linux/mutex.h>
+#include <linux/spinlock.h>
 #include <linux/wait.h>
 
 #include <drm/drmP.h>
@@ -30,11 +31,17 @@ struct rcar_du_vsp;
  * @extclock: external pixel dot clock (optional)
  * @mmio_offset: offset of the CRTC registers in the DU MMIO block
  * @index: CRTC software and hardware index
- * @started: whether the CRTC has been started and is running
+ * @initialized: whether the CRTC has been initialized and clocks enabled
+ * @vblank_enable: whether vblank events are enabled on this CRTC
  * @event: event to post when the pending page flip completes
  * @flip_wait: wait queue used to signal page flip completion
+ * @vblank_lock: protects vblank_wait and vblank_count
+ * @vblank_wait: wait queue used to signal vertical blanking
+ * @vblank_count: number of vertical blanking interrupts to wait for
  * @outputs: bitmask of the outputs (enum rcar_du_output) driven by this CRTC
  * @group: CRTC group this CRTC belongs to
+ * @vsp: VSP feeding video to this CRTC
+ * @vsp_pipe: index of the VSP pipeline feeding video to this CRTC
  */
 struct rcar_du_crtc {
 	struct drm_crtc crtc;
@@ -43,15 +50,21 @@ struct rcar_du_crtc {
 	struct clk *extclock;
 	unsigned int mmio_offset;
 	unsigned int index;
-	bool started;
+	bool initialized;
 
+	bool vblank_enable;
 	struct drm_pending_vblank_event *event;
 	wait_queue_head_t flip_wait;
 
+	spinlock_t vblank_lock;
+	wait_queue_head_t vblank_wait;
+	unsigned int vblank_count;
+
 	unsigned int outputs;
 
 	struct rcar_du_group *group;
 	struct rcar_du_vsp *vsp;
+	unsigned int vsp_pipe;
 };
 
 #define to_rcar_crtc(c)	container_of(c, struct rcar_du_crtc, crtc)
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index d6a0255181cc..da3020b622ab 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -39,7 +39,8 @@ static const struct rcar_du_device_info rcar_du_r8a7779_info = {
 	.features = 0,
 	.num_crtcs = 2,
 	.routes = {
-		/* R8A7779 has two RGB outputs and one (currently unsupported)
+		/*
+		 * R8A7779 has two RGB outputs and one (currently unsupported)
 		 * TCON output.
 		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -61,7 +62,8 @@ static const struct rcar_du_device_info rcar_du_r8a7790_info = {
 	.quirks = RCAR_DU_QUIRK_ALIGN_128B | RCAR_DU_QUIRK_LVDS_LANES,
 	.num_crtcs = 3,
 	.routes = {
-		/* R8A7790 has one RGB output, two LVDS outputs and one
+		/*
+		 * R8A7790 has one RGB output, two LVDS outputs and one
 		 * (currently unsupported) TCON output.
 		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -87,7 +89,8 @@ static const struct rcar_du_device_info rcar_du_r8a7791_info = {
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
 	.num_crtcs = 2,
 	.routes = {
-		/* R8A779[13] has one RGB output, one LVDS output and one
+		/*
+		 * R8A779[13] has one RGB output, one LVDS output and one
 		 * (currently unsupported) TCON output.
 		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -127,7 +130,8 @@ static const struct rcar_du_device_info rcar_du_r8a7794_info = {
 		  | RCAR_DU_FEATURE_EXT_CTRL_REGS,
 	.num_crtcs = 2,
 	.routes = {
-		/* R8A7794 has two RGB outputs and one (currently unsupported)
+		/*
+		 * R8A7794 has two RGB outputs and one (currently unsupported)
 		 * TCON output.
 		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -149,7 +153,8 @@ static const struct rcar_du_device_info rcar_du_r8a7795_info = {
 		  | RCAR_DU_FEATURE_VSP1_SOURCE,
 	.num_crtcs = 4,
 	.routes = {
-		/* R8A7795 has one RGB output, two HDMI outputs and one
+		/*
+		 * R8A7795 has one RGB output, two HDMI outputs and one
 		 * LVDS output.
 		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
@@ -180,19 +185,25 @@ static const struct rcar_du_device_info rcar_du_r8a7796_info = {
 		  | RCAR_DU_FEATURE_VSP1_SOURCE,
 	.num_crtcs = 3,
 	.routes = {
-		/* R8A7796 has one RGB output, one LVDS output and one
-		 * (currently unsupported) HDMI output.
+		/*
+		 * R8A7796 has one RGB output, one LVDS output and one HDMI
+		 * output.
 		 */
 		[RCAR_DU_OUTPUT_DPAD0] = {
 			.possible_crtcs = BIT(2),
 			.port = 0,
 		},
+		[RCAR_DU_OUTPUT_HDMI0] = {
+			.possible_crtcs = BIT(1),
+			.port = 1,
+		},
 		[RCAR_DU_OUTPUT_LVDS0] = {
 			.possible_crtcs = BIT(0),
 			.port = 2,
 		},
 	},
 	.num_lvds = 1,
+	.dpll_ch =  BIT(1),
 };
 
 static const struct of_device_id rcar_du_of_table[] = {
@@ -341,7 +352,8 @@ static int rcar_du_probe(struct platform_device *pdev)
 
 	ddev->irq_enabled = 1;
 
-	/* Register the DRM device with the core and the connectors with
+	/*
+	 * Register the DRM device with the core and the connectors with
 	 * sysfs.
 	 */
 	ret = drm_dev_register(ddev, 0);
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.c b/drivers/gpu/drm/rcar-du/rcar_du_group.c
index 64738fca96d0..2f37ea901873 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_group.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_group.c
@@ -64,7 +64,8 @@ static void rcar_du_group_setup_defr8(struct rcar_du_group *rgrp)
 	if (rcdu->info->gen < 3) {
 		defr8 |= DEFR8_DEFE8;
 
-		/* On Gen2 the DEFR8 register for the first group also controls
+		/*
+		 * On Gen2 the DEFR8 register for the first group also controls
 		 * RGB output routing to DPAD0 and VSPD1 routing to DU0/1/2 for
 		 * DU instances that support it.
 		 */
@@ -75,7 +76,8 @@ static void rcar_du_group_setup_defr8(struct rcar_du_group *rgrp)
 				defr8 |= DEFR8_VSCS;
 		}
 	} else {
-		/* On Gen3 VSPD routing can't be configured, but DPAD routing
+		/*
+		 * On Gen3 VSPD routing can't be configured, but DPAD routing
 		 * needs to be set despite having a single option available.
 		 */
 		u32 crtc = ffs(possible_crtcs) - 1;
@@ -124,7 +126,8 @@ static void rcar_du_group_setup(struct rcar_du_group *rgrp)
 	if (rcdu->info->gen >= 3)
 		rcar_du_group_write(rgrp, DEFR10, DEFR10_CODE | DEFR10_DEFE10);
 
-	/* Use DS1PR and DS2PR to configure planes priorities and connects the
+	/*
+	 * Use DS1PR and DS2PR to configure planes priorities and connects the
 	 * superposition 0 to DU0 pins. DU1 pins will be configured dynamically.
 	 */
 	rcar_du_group_write(rgrp, DORCR, DORCR_PG1D_DS1 | DORCR_DPRS);
@@ -177,7 +180,8 @@ static void __rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start)
 
 void rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start)
 {
-	/* Many of the configuration bits are only updated when the display
+	/*
+	 * Many of the configuration bits are only updated when the display
 	 * reset (DRES) bit in DSYSR is set to 1, disabling *both* CRTCs. Some
 	 * of those bits could be pre-configured, but others (especially the
 	 * bits related to plane assignment to display timing controllers) need
@@ -208,23 +212,32 @@ void rcar_du_group_restart(struct rcar_du_group *rgrp)
 
 int rcar_du_set_dpad0_vsp1_routing(struct rcar_du_device *rcdu)
 {
+	struct rcar_du_group *rgrp;
+	struct rcar_du_crtc *crtc;
+	unsigned int index;
 	int ret;
 
 	if (!rcar_du_has(rcdu, RCAR_DU_FEATURE_EXT_CTRL_REGS))
 		return 0;
 
-	/* RGB output routing to DPAD0 and VSP1D routing to DU0/1/2 are
-	 * configured in the DEFR8 register of the first group. As this function
-	 * can be called with the DU0 and DU1 CRTCs disabled, we need to enable
-	 * the first group clock before accessing the register.
+	/*
+	 * RGB output routing to DPAD0 and VSP1D routing to DU0/1/2 are
+	 * configured in the DEFR8 register of the first group on Gen2 and the
+	 * last group on Gen3. As this function can be called with the DU
+	 * channels of the corresponding CRTCs disabled, we need to enable the
+	 * group clock before accessing the register.
 	 */
-	ret = clk_prepare_enable(rcdu->crtcs[0].clock);
+	index = rcdu->info->gen < 3 ? 0 : DIV_ROUND_UP(rcdu->num_crtcs, 2) - 1;
+	rgrp = &rcdu->groups[index];
+	crtc = &rcdu->crtcs[index * 2];
+
+	ret = clk_prepare_enable(crtc->clock);
 	if (ret < 0)
 		return ret;
 
-	rcar_du_group_setup_defr8(&rcdu->groups[0]);
+	rcar_du_group_setup_defr8(rgrp);
 
-	clk_disable_unprepare(rcdu->crtcs[0].clock);
+	clk_disable_unprepare(crtc->clock);
 
 	return 0;
 }
@@ -236,7 +249,8 @@ int rcar_du_group_set_routing(struct rcar_du_group *rgrp)
 
 	dorcr &= ~(DORCR_PG2T | DORCR_DK2S | DORCR_PG2D_MASK);
 
-	/* Set the DPAD1 pins sources. Select CRTC 0 if explicitly requested and
+	/*
+	 * Set the DPAD1 pins sources. Select CRTC 0 if explicitly requested and
 	 * CRTC 1 in all other cases to avoid cloning CRTC 0 to DPAD0 and DPAD1
 	 * by default.
 	 */
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
index 5d681ea53be6..7278b9703c15 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c
@@ -96,7 +96,8 @@ static const struct rcar_du_format_info rcar_du_format_infos[] = {
 		.pnmr = PnMR_SPIM_TP_OFF | PnMR_DDDF_YC,
 		.edf = PnDDCR4_EDF_NONE,
 	},
-	/* The following formats are not supported on Gen2 and thus have no
+	/*
+	 * The following formats are not supported on Gen2 and thus have no
 	 * associated .pnmr or .edf settings.
 	 */
 	{
@@ -153,7 +154,8 @@ int rcar_du_dumb_create(struct drm_file *file, struct drm_device *dev,
 	unsigned int min_pitch = DIV_ROUND_UP(args->width * args->bpp, 8);
 	unsigned int align;
 
-	/* The R8A7779 DU requires a 16 pixels pitch alignment as documented,
+	/*
+	 * The R8A7779 DU requires a 16 pixels pitch alignment as documented,
 	 * but the R8A7790 DU seems to require a 128 bytes pitch alignment.
 	 */
 	if (rcar_du_needs(rcdu, RCAR_DU_QUIRK_ALIGN_128B))
@@ -255,12 +257,12 @@ static void rcar_du_atomic_commit_tail(struct drm_atomic_state *old_state)
 
 	/* Apply the atomic update. */
 	drm_atomic_helper_commit_modeset_disables(dev, old_state);
-	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 	drm_atomic_helper_commit_planes(dev, old_state,
 					DRM_PLANE_COMMIT_ACTIVE_ONLY);
+	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
 	drm_atomic_helper_commit_hw_done(old_state);
-	drm_atomic_helper_wait_for_vblanks(dev, old_state);
+	drm_atomic_helper_wait_for_flip_done(dev, old_state);
 
 	drm_atomic_helper_cleanup_planes(dev, old_state);
 }
@@ -309,7 +311,7 @@ static int rcar_du_encoders_init_one(struct rcar_du_device *rcdu,
 		return -ENODEV;
 	}
 
-	entity_ep_node = of_parse_phandle(ep->local_node, "remote-endpoint", 0);
+	entity_ep_node = of_graph_get_remote_endpoint(ep->local_node);
 
 	for_each_endpoint_of_node(entity, ep_node) {
 		if (ep_node == entity_ep_node)
@@ -419,7 +421,8 @@ static int rcar_du_properties_init(struct rcar_du_device *rcdu)
 	if (rcdu->props.alpha == NULL)
 		return -ENOMEM;
 
-	/* The color key is expressed as an RGB888 triplet stored in a 32-bit
+	/*
+	 * The color key is expressed as an RGB888 triplet stored in a 32-bit
 	 * integer in XRGB8888 format. Bit 24 is used as a flag to disable (0)
 	 * or enable source color keying (1).
 	 */
@@ -432,6 +435,81 @@ static int rcar_du_properties_init(struct rcar_du_device *rcdu)
 	return 0;
 }
 
+static int rcar_du_vsps_init(struct rcar_du_device *rcdu)
+{
+	const struct device_node *np = rcdu->dev->of_node;
+	struct of_phandle_args args;
+	struct {
+		struct device_node *np;
+		unsigned int crtcs_mask;
+	} vsps[RCAR_DU_MAX_VSPS] = { { 0, }, };
+	unsigned int vsps_count = 0;
+	unsigned int cells;
+	unsigned int i;
+	int ret;
+
+	/*
+	 * First parse the DT vsps property to populate the list of VSPs. Each
+	 * entry contains a pointer to the VSP DT node and a bitmask of the
+	 * connected DU CRTCs.
+	 */
+	cells = of_property_count_u32_elems(np, "vsps") / rcdu->num_crtcs - 1;
+	if (cells > 1)
+		return -EINVAL;
+
+	for (i = 0; i < rcdu->num_crtcs; ++i) {
+		unsigned int j;
+
+		ret = of_parse_phandle_with_fixed_args(np, "vsps", cells, i,
+						       &args);
+		if (ret < 0)
+			goto error;
+
+		/*
+		 * Add the VSP to the list or update the corresponding existing
+		 * entry if the VSP has already been added.
+		 */
+		for (j = 0; j < vsps_count; ++j) {
+			if (vsps[j].np == args.np)
+				break;
+		}
+
+		if (j < vsps_count)
+			of_node_put(args.np);
+		else
+			vsps[vsps_count++].np = args.np;
+
+		vsps[j].crtcs_mask |= BIT(i);
+
+		/* Store the VSP pointer and pipe index in the CRTC. */
+		rcdu->crtcs[i].vsp = &rcdu->vsps[j];
+		rcdu->crtcs[i].vsp_pipe = cells >= 1 ? args.args[0] : 0;
+	}
+
+	/*
+	 * Then initialize all the VSPs from the node pointers and CRTCs bitmask
+	 * computed previously.
+	 */
+	for (i = 0; i < vsps_count; ++i) {
+		struct rcar_du_vsp *vsp = &rcdu->vsps[i];
+
+		vsp->index = i;
+		vsp->dev = rcdu;
+
+		ret = rcar_du_vsp_init(vsp, vsps[i].np, vsps[i].crtcs_mask);
+		if (ret < 0)
+			goto error;
+	}
+
+	return 0;
+
+error:
+	for (i = 0; i < ARRAY_SIZE(vsps); ++i)
+